Optimizing detection performance of radio frequency based sensing

Abstract

The invention relates to a radio frequency (RF) system having a plurality of nodes (34, 36, 38, 44, 46, 48) and a method for optimizing a detection performance for performing RF-based sensing in a sensing area (32) based on RF system configuration parameters. The RF system configuration parameters having the greatest impact on the detection performance of the RF-based sensing are determined. Then, the RF system configuration parameters having the greatest impact on the detection performance of the RF-based sensing are adjusted in order to optimize the detection performance of the RF-based sensing. The root cause of the detection performance reduction and the respective RF system configuration parameter for mitigating the detection performance reduction can be determined based on a current context. In order to optimize the detection performance, for example, settings of sensing parameters of the nodes (34, …, 48) can be adjusted or nodes (34, …, 38) can be moved, removed, added or replaced.

Description

Technical Field

[0001] This invention relates to a radio frequency (RF) system, a method for optimizing the detection performance of RF-based sensing, and a computer program product. Background Technology

[0002] RF-based sensing is used to detect different types of sensing events in a sensing area, such as human movement or room occupancy, for example, for controlling light settings; and more detailed human biometrics, such as respiratory rate of movement or human gait, for example, for context awareness and detailed daily activity monitoring.

[0003] US 2017 / 366938A1 discloses a system that uses signal absorption and forward and backward scattering of RF waves caused by the presence of biological material in a communication network to detect the presence of a body in the network. This system can automate various aspects of setup, particularly regarding grouping nodes into detection zones and nominally constructing a functional level based on machine learning methods. The system, which infers the nearest node and estimates the detection zone, does not require user setup. Based on the optimal estimate, the user can simply place nodes throughout the building, and unsupervised machine learning automatically groups the nodes into detection zones, ultimately causing the building system to learn how to detect occupants.

[0004] US 2020 / 0096345 A1 discloses a computer-implemented method for cognitive fingerprint recognition of indoor location. The method includes determining calibration information for using a sensing device within an indoor environment; generating instructions corresponding to one or more suggested location sensor placements throughout the indoor environment, based at least in part on the calibration information; and issuing the instructions corresponding to the one or more suggested location sensor placements via the sensing device when a user operating the sensing device navigates the indoor environment. The suggested location sensor placements may be based on one or more Received Signal Strength Indicators (RSSIs), each RSSI received by the sensing device and from location sensors in the indoor environment. The instructions may include instructions to place a new location sensor at a location where the signal strength received from one or more neighboring location sensors is less than a predetermined minimum signal strength threshold.

[0005] Won-Yeol Lee et al. disclosed an optimal spectrum sensing framework for addressing interference avoidance and spectral efficiency issues. More specifically, they first developed a theoretical framework to optimize sensing parameters in such a way that sensing efficiency is maximized under interference avoidance constraints. Second, to utilize multiple spectral bands, a spectrum selection and scheduling method was proposed, where the optimal spectral band for sensing is selected to maximize sensing capacity. Finally, an adaptive and cooperative spectrum sensing method was disclosed, in which sensing parameters are adaptively optimized to adapt to the number of cooperative users. Summary of the Invention

[0006] One object of the present invention is to provide an RF system, a method for optimizing the detection performance of RF-based sensing, a computer program product for optimizing the detection performance of RF-based sensing, and a computer-readable medium that allow for optimization of improved detection performance of RF-based sensing.

[0007] In a first aspect of the invention, an RF system is proposed for optimizing detection performance for performing RF-based sensing based on RF system configuration parameters. The RF system includes multiple nodes, wherein a group of at least two nodes is configured to perform RF-based sensing in a sensing area. The RF system is configured to determine the RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing. Furthermore, the RF system is configured to adjust the RF system configuration parameters that have the greatest impact on the detection performance of the RF-based sensing in order to optimize the detection performance of the RF-based sensing.

[0008] Because the RF system is configured to determine the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing, and to adjust these parameters to optimize the detection performance, the root causes negatively affecting detection performance can be mitigated. This allows for improved optimization of detection performance. Which RF system configuration parameter has the greatest impact on detection performance depends on the root cause negatively affecting detection performance. This allows for determining which adjustments to the RF system best mitigate the root cause, and thus best improve detection performance.

[0009] The greatest impact on detection performance means that adjusting the RF system configuration parameter that has the greatest impact on the detection performance of RF-based sensing has a greater impact on detection performance than adjusting a corresponding parameter of another RF system configuration parameter. For example, one RF system configuration parameter could be the location of the first node, and another could be the location of the second node. Moving the first node vertically by a certain length might have only a small impact on detection performance, while moving the second node vertically by the same length might have a much larger impact. For example, if an RF system is arranged in a room-shaped sensing area to perform respiratory rate identification for two different people lying on a double bed, and the first node is a ceiling light located in the center of the room's ceiling, while the second node is a bedside lamp located on a bedside table on one side of the double bed, moving the bedside lamp vertically has a much greater impact on identifying the respiratory rate of the person lying on the side of the double bed where the bedside lamp is located, compared to moving the ceiling light. Generally, moving the ceiling light has a much smaller impact on respiratory rate identification than moving the bedside lamp because the ceiling light is much farther away from the person on the double bed.

[0010] Compared to other sensing modalities such as passive infrared (PIR) sensors, cameras, and radar, RF-based sensing exhibits unique characteristics because it is a distributed sensing modality. Unlike PIR sensors, cameras, and radar, there is no single, physically identifiable device performing sensing. Instead, a group of nodes generates and processes data (e.g., involving sensing algorithms or sensing analysis algorithms of varying complexity) and, as a group, infers whether a sensing event has occurred. Therefore, for example, different numbers of nodes in different groups or different relative positions of nodes to each other can affect the detection performance of RF-based sensing in different groups.

[0011] When sensing is performed using sensing modes other than RF-based sensing, the field of view (FoV) of the sensing device (e.g., a camera) can be adjusted by oriented the camera lens toward the desired new sensing area to improve detection performance. In the case of RF-based sensing, improving detection performance by adjusting the sensing area (e.g., modifying the detection area of ​​the group performing RF-based sensing) is not trivial. RF-based sensing may be affected by node locations, but it may also be affected by, for example, complex multipath effects. RF signals are not limited to a predefined FOV with clear boundaries. Furthermore, the presence of tangible entities (e.g., objects) in the sensing area can alter multipath behavior.

[0012] The RF system allows identification of which RF system configuration parameter has the greatest impact on detection performance, and allows adjustment of this parameter to improve detection performance. The RF system can also be used to provide feedback to the user to further improve detection performance.

[0013] RF-based sensing allows the detection of various sensing events occurring within a sensing area, which is a specific space or volume, such as a room in a building, a building, or any other space. Sensing algorithms or sensing analysis algorithms can detect and analyze how tangible entities (such as objects or users) within the sensing area affect RF signals. RF signals are used to transmit RF messages. RF-based sensing can be used as a means of detecting and classifying sensing events, such as user activity in homes, offices, etc. For example, based on WiFi RF-based sensing messages transmitted and received by nodes in the form of smart lights, RF-based sensing can determine movement in a room and automatically turn lights on or off; nodes in the form of WiFi routers can estimate a person's breathing rate, etc.

[0014] The fundamental principle of RF-based sensing is that the distortion of RF signals in space is a function of both the tangible entities in space (e.g., moving objects) and the frequency of the RF signal. Radio waves propagate through electromagnetic radiation and interact with the environment through reflection, refraction, diffraction, absorption, polarization, and scattering. Within the typical frequency range used in RF-based sensing applications, the radio attenuation varies among different materials. Therefore, the characteristics of the sensing area (e.g., the building form of the room, the spatial arrangement, and the integral surface area of ​​each material type present in the sensing area) can affect the RF multipath signal characteristics of the sensing area.

[0015] To perform RF-based sensing, one node can act as a transmitting node, transmitting an RF signal including an RF message to another node, which acts as a receiving node. The received RF signal can then be analyzed. If the RF signal interacts with one or more tangible entities (e.g., objects or people) along its transmission path between the nodes, the RF signal is interfered with, for example, by scattering, absorption, reflection, or any combination thereof. This interference can be analyzed and used to perform RF-based sensing. The interfered and / or reflected RF signal can include an RF-based sensing fingerprint based on signal parameters, such as the real and imaginary parts of permittivity and magnetization. Performing RF-based sensing by at least two nodes is also known as passive RF sensing.

[0016] A first node of the at least two nodes may be configured to transmit radio frequency (RF) signals, and a second node of the at least two nodes may be configured to receive the transmitted RF signals. RF-based sensing can be performed by analyzing interference to the RF signals caused by their interaction with one or more objects or people along their transmission path between the at least two nodes. This analysis may be based on comparing the received RF signals to a baseline defined for the sensing area. The baseline may include the propagation of the RF signals within the sensing area. Those skilled in the art of (passive) RF sensing are familiar with obtaining / determining a baseline, and therefore will not be discussed further here.

[0017] The radio frequency (RF) system can be configured to perform presence detection within a sensing area. The RF system can be configured to perform one or more of the following within the sensing area: motion detection, location tracking, and vital sign detection (e.g., respiration detection, heart rate monitoring, sleep monitoring, fall detection, posture detection, activity detection, gait detection, gesture detection, etc.). Other known or future applications of RF sensing are not excluded. Presence detection can be an explicit detection of user presence, or it can be implicitly derived from other sensing functions related to user presence, such as motion detection, location tracking, and health-related detection (e.g., respiration detection, heart rate monitoring, fall detection, etc.).

[0018] RF system configuration parameters can be related to the RF system configuration parameters of at least two or more nodes forming a group that performs RF-based sensing in the sensing area (i.e., all nodes of the RF system including at least two nodes in the group that perform RF-based sensing in the sensing area). The operation of nodes not included in the group that performs RF-based sensing in the sensing area may affect detection performance, for example, due to wireless interference or congestion of the RF system's wireless network.

[0019] RF system configuration parameters may include one or more of the following:

[0020] - The spatial arrangement of at least two nodes in this group

[0021] - Multiple nodes are grouped into this group.

[0022] - The number of nodes in this group

[0023] - The capabilities of the nodes in this group, and

[0024] - One or more sensing parameters used to perform RF-based sensing.

[0025] Radio frequency (RF) system configuration parameters affect detection performance. Depending on the settings of these parameters, detection performance can be higher or lower. This allows for optimization of detection performance by adjusting one or more of the RF system configuration parameters. Improvement can be achieved by adjusting the RF system configuration parameters that have the greatest impact on detection performance.

[0026] The spatial arrangement of at least two nodes in the group can include the spatial arrangement of the nodes relative to each other, relative to nodes in other groups, and relative to other tangible entities (such as walls, corners, or other objects such as a double bed or bookshelf). The spatial arrangement can also include the relative position of at least one of the two nodes relative to other tangible entities. For example, the spatial arrangement of the nodes in the group can be adjusted by moving one or more of the at least two nodes. Movement can be made in any three-dimensional direction, i.e., horizontally, vertically, or a combination thereof. Adjusting the spatial arrangement can allow for improved detection performance, for example, by adjusting the sensing area and / or by moving the nodes closer to the region of interest, where a sensing event is expected to occur. For example, a bedside lamp can be moved closer to one side of the double bed, which corresponds to the region of interest for respiratory rate recognition, because the user is expected to sleep on that side of the bed. This can allow for improved detection performance of the side lamp used for respiratory rate recognition.

[0027] An RF system can be configured to determine which node to remove, replace, or move to maximize detection performance, for example, by comparing the detection performance of different spatial arrangements. For instance, moving a ceiling illuminator might have only a minor impact on improving detection performance. Therefore, the RF system can be configured to determine, based on computer simulations, by actually moving the ceiling illuminator, the root cause of the negative impact on detection performance, or information about RF system configuration parameters received by the user, corresponding to the RF system configuration parameters that have the greatest impact on detection performance, allowing the node to be moved to have the maximum impact on detection performance.

[0028] Multiple nodes can be grouped into a sensing group by removing one of at least two nodes, adding a node from a group of nodes (e.g., from another group of the RF system) to the group performing RF-based sensing in the sensing area, or a combination thereof (e.g., replacing a node with another node). The RF system can be configured to add only nodes from another group to the group performing RF-based sensing in the sensing area if that other group can operate without the node. The RF system can be configured to determine the potential impact of removing a node from another group and adding it to that group to perform RF-based sensing in the sensing area on that other group and on the group itself, in order to decide whether the node should be moved.

[0029] The number of nodes in a group used to perform RF-based sensing in the sensing area can be adjusted by removing a node from the group or adding a node to the group, for example by regrouping the nodes of the RF system and / or by removing or adding a node to the RF system.

[0030] Sensing parameters may include, for example, transmit power, sensitivity, signal strength, signal link, beamform, beam directivity, threshold level, radio type used to perform RF-based sensing, communication protocol used to perform RF-based sensing, or any other sensing parameters. The threshold level may be, for example, a sensitivity threshold level, a signal strength threshold level, or any other threshold level. The radio type used to perform RF-based sensing may differ for different nodes; for example, the first node may use 2.4 GHz WiFi, while the second and third nodes may use 2.4 GHz WiFi and an additional 5 GHz WiFi. The communication protocol used to perform RF-based sensing may include, for example, Bluetooth, Bluetooth Low Energy (BLE), WiFi, cellular radio, Zigbee, or any other communication protocol that can be used to perform RF-based sensing.

[0031] The RF system can be configured to determine the RF system configuration parameters that most significantly impact the detection performance of RF-based sensing based on the current context. This allows for dynamic adjustment of the RF system configuration parameters that have the greatest impact on detection performance to optimize the detection performance of RF-based sensing. The RF system can be configured to determine the current context in which RF-based sensing is performed by a group or the entire RF system within the sensing area. Information about the current context can be provided to the RF system as input by the user, and this information is then processed by the RF system to determine the current context. Alternatively, the RF system can be configured to determine the current context in any other way, for example, based on data stored in the RF system or sensor data acquired by the RF system.

[0032] The current context can include one or more of the following:

[0033] -Settings for one or more of the RF system configuration parameters.

[0034] -Sensing applications,

[0035] -Delay requirements,

[0036] - Expected sensing events in the sensing area,

[0037] -Privacy requirements,

[0038] -Radio power consumption requirements

[0039] -Radio transmission power requirements,

[0040] -Radio beam shape requirements

[0041] - Radio receiver beamforming requirements

[0042] - Current location of the RF system

[0043] The current position of at least one of at least two nodes.

[0044] -The current location of tangible entities within the sensing area.

[0045] -Current date,

[0046] - The current operating mode of at least one of the two nodes.

[0047] -Environmental impact,

[0048] -The bandwidth currently available in the RF system

[0049] - The current capabilities of at least one of the two nodes,

[0050] Current properties of the sensing area

[0051] Error event detection rate requirements, and

[0052] Omitted event detection requirements.

[0053] The RF system can be configured to determine the settings of one or more of the RF system configuration parameters by checking the current stored settings of the RF system configuration parameters.

[0054] Sensing applications may include detecting what type of sensing event is being performed, for example, by performing RF-based sensing, such as fast, low-latency motion detection, occupancy detection, vacancy detection, fall detection, heartbeat detection, respiratory rate recognition, heart rate recognition, or any other sensing event. Sensing applications may also provide current context by including requirements for the sensing application, such as the sensing application's standby power requirements, or the currently required standby power level.

[0055] The current context can also include different sensing applications, for example, ordered by priority to provide certain sensing functions. For instance, sensing applications could include occupancy detection and respiratory rate recognition. Occupancy can have a lower priority than respiratory rate recognition, allowing the RF system to adjust the node's position. This improves the detection performance of respiratory rate recognition but degrades the detection performance of occupancy detection, rather than the reverse, where respiratory rate recognition performance is degraded and occupancy detection performance is improved. This allows for performance improvements based on sensing application priority.

[0056] Delay requirements can include, for example, a duration within which data processing needs to be completed and sensing events need to be detected or not detected, such as in life-critical sensing applications requiring rapid response. Another type of delay requirement can be, for example, a lighting control delay requirement, under which lighting needs to be activated within a specific duration (e.g., 200 ms) in response to a user entering the sensing area.

[0057] The expected sensing event in the sensing area can be any sensing event detected by performing RF-based sensing on a specific sensing application, such as occupancy detection, fall detection, respiratory rate recognition, heart rate recognition, gesture recognition, etc.

[0058] Privacy requirements may include, for example, that certain RF-based sensing applications are not permitted for a particular privacy requirement. For instance, if there is a romantic context, such as the RF system using romantic lighting scenarios, for example in the form of a connected lighting (CL) system where nodes are illuminators, then a specific RF sensing configuration that prohibits certain sensing applications can be used, which is inherently privacy-respecting. For example, an RF system may be allowed to perform RF-based sensing to detect occupancy (i.e., occupancy detection), but may not perform RF-based sensing to identify respiratory rate and / or heart rate (i.e., respiratory rate identification and / or heart rate identification).

[0059] Radio power consumption requirements may include, for example, standby power management requirements. Standby mode may include, for example, not performing the node's primary functions. The node can be configured to perform RF-based sensing, for example, in standby mode, i.e., when it is not performing its primary functions. For example, the node could be a illuminator that does not provide light in standby mode but performs RF-based sensing. In this case, the standby power consumed by the node corresponds to the power consumed by the node while processing RF sensing messages (e.g., including receiving RF sensing messages and processing them, for example, using sensing analysis algorithms). The power consumption used to perform RF-based sensing depends on the settings of the RF system configuration parameters, allowing the power consumption to be adjusted based on the RF system configuration parameters to meet radio power consumption requirements.

[0060] Radio transmission power requirements may include, for example, limitations on transmission power, such as radio interference caused by high transmission power. For instance, in a hospital room, medical equipment may be subject to radio interference, which may limit the permissible RF transmission power used to perform RF-based sensing based on radio transmission power requirements.

[0061] Radio beamforming requirements and radio receiver beamforming requirements relate to how the beam used to perform RF-based sensing is shaped. The beam can be, for example, a narrow beam or a diverging beam. The beam shape can affect the sensing area that can be covered by performing RF-based sensing. A narrow beam can, for example, allow coverage of a longer sensing area, while a diverging beam can, for example, allow coverage of a wider sensing area. Using a narrow beam allows RF-based sensing to be performed between two nodes that are far apart from each other, compared to using a diverging beam. Furthermore, using a narrow beam allows the RF signal to be focused in a specific direction, such that beamforming in this way can allow for higher signal quality to be provided to the receiving node.

[0062] The current location of at least one of the two nodes may include, for example, the relative location of at least one of the two nodes with respect to the other of the two nodes. This may affect the transmission length between the nodes. The current location of at least one of the two nodes may, for example, be near a tangible entity.

[0063] The current location of a tangible entity (such as a user) can include the entity's position within or relative to the sensing area and / or node. This can degrade detection performance if a portion of the sensing area is not well covered by the set. For example, a tangible entity can also be a door or room partition in a room. In the case of a door, its position (e.g., open, closed, or its corresponding opening angle) can affect RF-based sensing and thus detection performance. In the case of a room partition, such as in a restaurant, its position may divide the room into two smaller rooms and affect RF-based sensing and detection performance.

[0064] The current date can include a time of day (e.g., night or daytime) or a day of the week (e.g., weekday or weekend). RF systems can be configured to determine the current date based on a clock and / or calendar.

[0065] Requirements such as standby power management requirements or radio transmit power requirements may depend on, for example, the current location of the RF system and / or at least one of the two nodes, and / or depend on, for example, the current date.

[0066] The current operating mode of each node may include, for example, performing primary functions such as providing lighting, performing RF-based sensing, and / or operating in standby mode.

[0067] Environmental influences can include, for example, wireless interference, background noise levels, or combinations thereof. Environmental influences may be based on, for example, humidity in the air, smoke, cigarette smoke, activity in areas adjacent to the sensing area, or combinations thereof. Background noise may be caused by, for example, noise sources such as microwave ovens or streaming televisions. Background noise can degrade the signal-to-noise ratio (SNR) of RF-based sensing and increase the number of lost RF messages between nodes, i.e., reducing the sampling rate or effective message delivery rate, respectively.

[0068] Considering the available bandwidth in the RF system, a certain degree of compensation can be made for insufficient sampling rate, for example, due to lost RF messages. For instance, RF system configuration parameters can be adapted to avoid wireless congestion on the network used by the RF system for exchanging data.

[0069] The properties of the sensing area can include, for example, shape, regularity, material, the prototype of the room in which the nodes are arranged, or any other properties of the sensing area. This allows room properties to be taken into account to optimize detection performance.

[0070] The error event detection rate requirement corresponds to the error detection tolerance. The error event detection rate requirement can include, for example, false positive rate and false negative rate.

[0071] The requirement for missing events corresponds to a tolerance for missing events; that is, it corresponds to false negative detection. The requirement for missing events could be, for example, allowing only a certain percentage of events to be missed, such as 5% of events.

[0072] The RF system can be configured to determine the impact of adjusting RF system configuration parameters on other sensing applications, specifically those parameters that have the greatest impact on the detection performance of a particular sensing application. The RF system can be configured to adjust RF system configuration parameters that maximize their impact on detection performance based on their effect on other sensing applications. This allows for consideration of trade-offs in adjusting RF system configuration parameters that have the greatest impact on the detection performance of different sensing applications, such as respiratory rate recognition versus rapid motion sensing versus fall detection.

[0073] Detection performance may include one or more sensing metrics. Sensing metrics may include one or more of the following:

[0074] -delay,

[0075] -Accuracy,

[0076] -Spatial resolution,

[0077] - False alarm detection rate

[0078] -Missed detection rate,

[0079] - Confidence level used to detect sensed events,

[0080] - Noise in sensing event detection

[0081] -Generated data traffic,

[0082] - Energy consumption, and

[0083] - Spatial constraints for performing RF-based sensing of RF signals.

[0084] An RF system can be configured to determine how adjusting RF system configuration parameters affects one or more sensing metrics included in detection performance. If one of the sensing metrics is mitigated by adjusting the RF system configuration parameters, the RF system can be configured not to adjust the RF system configuration parameters. Alternatively, the RF system can be configured to determine whether improving one or more of the sensing metrics while mitigating one or more of the other sensing metrics improves detection performance. Detection performance can be a function of the sensing metrics included therein, such as an average, weighted sum, etc. Considering different sensing metrics of detection performance allows for fine-grained optimization of the RF system configuration parameters, and in particular, adjusting the RF system configuration parameters that have the greatest impact on RF-based sensing to optimize detection performance.

[0085] For example, if detection occurs because the detection signal oscillates around a threshold, and a sensing event is considered detected if the signal is above the threshold, this could lead to noise in the detection of sensing events. In this case, the magnitude of the signal oscillation around the threshold does have an impact.

[0086] The limitations of RF signals depend at least on the frequency used to perform RF-based sensing. For example, 5GHz WiFi is more limited than 2.4GHz WiFi. For some sensing applications, such as respiratory rate recognition in a double bed, providing a limited RF signal on one side of the double bed may be beneficial, especially when two people are sleeping on opposite sides of the double bed.

[0087] An RF system can be configured to determine the RF system configuration parameters that most significantly impact the detection performance of RF-based sensing, based on one or more sensing metrics included in the detection performance, such as which of the one or more sensing metrics is included in the detection performance and / or the level of one or more sensing metrics. Determining the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing based on one or more sensing metrics included in the detection performance allows for optimization and improvement of detection performance.

[0088] Users can provide one or more sensing metrics for detection performance, such as one or more sensing metrics that the user is dissatisfied with. For example, if the user is dissatisfied with latency, the user can provide latency as the only sensing metric included in the detection performance. The RF system can be configured to determine the RF system configuration parameters that have the greatest impact on latency for RF-based sensing. The RF system can be configured to adjust the corresponding RF system configuration parameters to optimize latency. The RF system can be configured to automatically adjust the RF system configuration parameters that have the greatest impact on detection performance, or the user can adjust the RF system configuration parameters that have the greatest impact on detection performance.

[0089] An RF system can be configured to determine whether the current level of a corresponding current sensing metric of one or more sensing metrics included in the detection performance is higher or lower than a corresponding threshold sensing metric level. Additionally, the RF system can be configured to determine RF system configuration parameters that most significantly impact the detection performance of RF-based sensing based on which of the one or more sensing metrics included in the detection performance has a current level higher or lower than a corresponding threshold sensing metric level. Considering the threshold sensing metric level allows for easy and rapid identification of which sensing metrics perform below expectations, e.g., below the minimum feasible level or below the average. This may allow for deriving the root cause of the negative impact on detection performance. Based on the root cause, the RF system configuration parameters that have the greatest impact on detection performance can be easily identified, e.g., based on RF system rules and / or experience. The RF system can be configured to determine the current sensing metric level of each or a subset of each of the one or more sensing metrics included in the detection performance, such as a predetermined subset of sensing metrics of interest for performing RF-based sensing based on RF system rules and / or experience, such as the subset of sensing metrics that have the greatest impact on detection performance, e.g., because the sensing metrics have the highest weight.

[0090] The RF system can be configured to determine the current detection performance level of RF-based sensing and to optimize detection performance based on whether the current detection performance level is above or below a threshold detection performance level. This allows for triggering of detection performance optimization, for example, when the detection performance level is below a threshold detection performance level.

[0091] Detection performance can include one or more sensing metrics. The RF system can be configured to determine whether one or more sensing metrics have a corresponding current sensing metric level below a corresponding sensing metric threshold level. The RF system can also be configured to determine RF system configuration parameters based on which sensing metric has a corresponding sensing metric level below its threshold level. This allows consideration of which sensing metric has poor performance in order to determine which RF system configuration parameters allow for improved detection performance.

[0092] The RF system can be configured to determine the root cause of the negative impact on detection performance, the RF system configuration parameters that have the greatest impact on detection performance, or both, for example, based on analysis of RF system configuration parameters, detection performance, current context, or a combination thereof.

[0093] Alternatively, the root cause, the RF system configuration parameters that have the greatest impact on detection performance, or both, can be provided by the user, for example, via a communication interface from the server or, if the communication interface includes a user interface, via direct input. This allows the user to trigger adjustments to the RF system configuration parameters, and especially to the RF system configuration parameters that have the greatest impact on detection performance, in order to optimize the detection performance of RF-based sensing.

[0094] In other words, based on user feedback or by automatically determining whether there are current sensing metrics to optimize, the RF system can be triggered to improve detection performance. The RF system can then adjust its configuration parameters, particularly those that have the greatest impact on the current sensing metrics, to optimize detection performance. Current sensing metrics may need to be optimized, for example, because insufficient performance can cause respiratory rate recognition to frequently lose synchronization with respiratory movements. For instance, in cases of insufficient respiratory rate recognition performance, the RF system might be configured to only determine the presence of a person but not their respiratory rate.

[0095] The RF system can be configured to determine a ranking of one or more RF system configuration parameters based on their respective impact on the detection performance of RF-based sensing, and to adjust the RF system configuration parameters based on this ranking to optimize the detection performance of RF-based sensing. This allows for further optimization of detection performance because various RF system configuration parameters can be adjusted according to their impact on detection performance. The RF system can be configured to assign weights to each RF system configuration parameter based on their respective ranking. The RF system can be configured to adjust the RF system configuration parameters sequentially based on their respective ranking. This allows for faster optimization of detection performance because RF system configuration parameters with a greater impact on detection performance are adjusted before those with a smaller impact are adjusted, thus optimizing detection performance.

[0096] The RF system can be configured to provide RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing, how to adjust these parameters to optimize detection performance, or combinations thereof. This can allow for improved detection performance in situations where external interaction with external systems or users is required, for example, to replace, add, or remove one or more nodes. The RF system can also be configured to provide a ranking of RF system configuration parameters based on their respective impact on the detection performance of RF-based sensing. Additionally or alternatively, the RF system can be configured to provide how to adjust the RF system configuration parameters according to this ranking to optimize detection performance.

[0097] The RF system may include a communication interface. The communication interface may be configured to provide the user with RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing, to provide the user with instructions on how to adjust the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing to optimize the detection performance, or a combination thereof.

[0098] The communication interface may include, or may be, a user interface such as a display for showing RF system configuration parameters to a user, or a touch display that allows the user to provide input, such as information about the current context for performing RF-based sensing. Alternatively, the communication interface may include a transceiver and an antenna for transmitting the RF system configuration parameters to a user equipment or server, allowing the user to obtain the RF system configuration parameters from the user equipment or server. The user can use the information about the RF system configuration parameters to optimize detection performance.

[0099] In another aspect of the invention, a method is provided for optimizing detection performance for performing RF-based sensing based on RF system configuration parameters. This method may be a computer-implemented method, such as a computer-implemented method executed on a computer system (e.g., an RF system) including a processor and a communication interface. The method includes the following steps:

[0100] -RF-based sensing is performed in the sensing area by a group of at least two nodes of an RF system comprising multiple nodes.

[0101] - Identify the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing, and

[0102] - Adjust RF system configuration parameters to optimize the detection performance of RF-based sensing.

[0103] The method may include one or more of the following steps:

[0104] - Determine the current context in which RF-based sensing is performed by the group in the sensing area.

[0105] - Determine the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing based on the current context.

[0106] - Based on one or more sensing metrics included in the detection performance, determine the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing.

[0107] - Determine whether the current sensing metric level of one or more sensing metrics included in the detection performance is higher or lower than the corresponding threshold sensing metric level.

[0108] -Based on which of the one or more sensing metrics included in the detection performance is higher or lower than the corresponding threshold sensing metric level, determine the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing.

[0109] - Determine the current detection performance level of RF-based sensing.

[0110] - Optimize detection performance based on whether the current detection performance level is higher or lower than the threshold detection performance level.

[0111] - Determine the order of one or more RF system configuration parameters based on their respective impact on the detection performance of RF-based sensing.

[0112] - Adjust the RF system configuration parameters based on this sorting to optimize the detection performance of RF-based sensing.

[0113] - Provides RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing.

[0114] - Provides instructions on how to adjust RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing in order to optimize detection performance.

[0115] - Provide users with the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing, and

[0116] - Provide users with instructions on how to adjust RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing in order to optimize detection performance.

[0117] In another aspect of the invention, a computer program product for optimizing the detection performance of RF-based sensing is provided. The computer program product includes program code means that, when executed on a processor, cause the processor to perform the method according to claim 12, claim 13, or any embodiment of that method.

[0118] In another aspect, a computer-readable medium is proposed that has stored the computer program product of claim 14. Alternatively or additionally, the computer-readable medium may enable the storage of a computer program product according to any embodiment of the computer program product.

[0119] It should be understood that the RF system of claim 1, the method of claim 12, the computer program product of claim 14, and the computer-readable medium of claim 15 have similar and / or identical preferred embodiments, particularly as defined in the dependent claims.

[0120] It should be understood that the preferred embodiments of the present invention may also be any combination of the dependent claims or the above embodiments with the corresponding independent claims.

[0121] These and other aspects of the invention will become clear and explained with reference to the embodiments described below. Attached Figure Description

[0122] In the following figures:

[0123] Figure 1 A node for an RF system is illustrated schematically and exemplary.

[0124] Figure 2 An embodiment of an RF system with two sets of nodes in a first configuration is illustrated schematically and exemplary.

[0125] Figure 3 An embodiment of the RF system in a second configuration is illustrated schematically and exemplary.

[0126] Figure 4 An embodiment of the RF system in a third configuration is illustrated schematically and exemplary.

[0127] Figure 5 An embodiment of the RF system in the fourth configuration is illustrated schematically and exemplary.

[0128] Figure 6 An embodiment of the RF system in the fifth configuration is illustrated schematically and exemplaryly.

[0129] Figure 7 An embodiment of a method for optimizing the detection performance of RF-based sensing is shown. Detailed Implementation

[0130] Figure 1 An RF system (e.g., in...) is illustrated schematically and exemplary. Figures 2 to 6The nodes of the CL system 100 are presented in various configurations. In the following, before providing details about the functionality of the CL system 100, we describe the details of an exemplary node 10 that can be used in the CL system 100.

[0131] Node 10 includes a control unit 12 and a communication interface 14 including an antenna array 16. Instead of an antenna array, a single antenna may also be included in the node.

[0132] The control unit 12 includes a computer-readable medium in the form of a processor 18 and a memory 20.

[0133] In this embodiment, the communication interface 14 additionally includes: a WiFi transceiver 22 for transmitting and receiving RF signals, including WiFi-based RF messages (i.e., WiFi RF messages); and a user interface 24 in the form of a touch display. In other embodiments, the communication interface may also exchange data based on one or more other communication protocols (e.g., Threading, cellular radio, Bluetooth, BLE, or any other communication protocol). The communication interface may also include two or more transceivers configured to exchange data based on different communication protocols.

[0134] Communication interface 14 uses antenna array 16 to transmit RF signals to and receive RF signals from nodes of CL system 100, respectively, to wirelessly exchange data including RF messages between nodes and perform RF-based sensing. RF signals transmitted from one node to another may be interfered with by tangible entities (e.g., users) within the transmission path between nodes. RF signals interfered with by users can be analyzed in control unit 12 for performing RF-based sensing.

[0135] The memory 20 of the control unit 12 stores a computer program product for operating the CL system 100. This computer program product includes program code means that, when executed on the processor 18, cause the processor 18 to execute methods for optimizing the detection performance of RF-based sensing, such as... Figure 7 The method presented herein is for optimizing detection performance for performing RF-based sensing based on RF system configuration parameters. Memory 20 also includes a computer program product for operating node 10 and optionally the entire CL system 100, for example, for controlling the functions of the node and controlling the functions of the nodes of the CL system 100, for example, to provide illumination and for performing RF-based sensing.

[0136] Figure 2An embodiment of an RF system in the form of a CL system 100 is shown, comprising a first group 30 of nodes 34, 36, and 38, and a second group 40 of nodes 44, 46, and 48. The CL system 100 is shown in a top perspective view of a first configuration arranged in a building having two rooms. The first group 30 performs RF-based sensing in a first sensing area 32 in the first room, and the second group 40 performs RF-based sensing in a second sensing area 42 in the second room. In other embodiments, the RF system may have a different number of nodes, such as two, three, four, or more, and / or different numbers of groups. In other embodiments, the sensing areas may have different sizes, shapes, and locations. Furthermore, in different embodiments, the RF system may be arranged in different buildings or in an open space.

[0137] Node 34 is a WiFi router, and the other nodes 36, 38, 44, 46, and 48 are illuminators for providing light and for performing RF-based sensing. In other embodiments, the nodes may also be of another type and perform another function, such as a switch, a light, a bridge, etc. Node 34 is wirelessly connected to an external server 200. The external server 200 may be used to control nodes 36 to 48 of the CL system 100, for example, by transmitting control signals to one or more of them. The external server may be, for example, a building management system (BMS) server. In this embodiment, the external server 200 only exchanges data directly with node 34. Node 34 can then exchange data with the other nodes 36 to 48 to control their functions. Node 34 may also transmit control signals to another node (e.g., node 36), which node 36 may forward them to other nodes, such as nodes 44, 46, and 48.

[0138] In this embodiment, the positions of nodes 34, 36, and 38 of the first group 30 define a first sensing area 32, and the positions of nodes 44, 46, and 48 of the second group 40 define a second sensing area 42. In other embodiments or configurations of the CL system 100, the sensing areas may be different. The sensing areas may also be predefined, for example, suitable for rooms in a building.

[0139] The CL system 100 is used to optimize detection performance to perform RF-based sensing based on RF system configuration parameters, and to perform RF-based sensing with optimized detection performance. Figure 2 In the configuration of the CL system 100 shown, the CL system 100 optimizes the detection performance of the first group 30. The CL system 100 can also optimize the detection performance of the second group 40. In other embodiments, the CL system 100 can optimize the detection performance of the entire CL system 100, for example, including the detection performance of the first group 30 and the second group 40.

[0140] In this embodiment, the detection performance includes various sensing metrics, including one or more of the following: latency, confidence level for detecting sensing events, accuracy, spatial resolution, false alarm detection rate, false negative detection rate, noise in sensing event detection, generated data traffic, energy consumption, and spatial limitation of the RF signal used to perform RF-based sensing.

[0141] The RF system configuration parameters include the spatial arrangement of nodes 34 to 48 in each group 30 and 40, the grouping of nodes 34 to 48 in groups 30 and 40, the number of nodes in groups 30 and 40, and various sensing parameters for performing RF-based sensing. Sensing parameters include, for example, transmit power, sensitivity, signal strength, signal link, beam shape, beam directivity, threshold level, radio type for performing RF-based sensing, and communication protocol for performing RF-based sensing.

[0142] Before optimizing the detection performance of the CL system 100, it determines the current detection performance level of the RF-based sensing in order to decide whether it is necessary to optimize it or whether the current detection performance is sufficient. This step is optional.

[0143] In this embodiment, the processing is performed by node 34. In other embodiments, the processing may also be performed by other nodes of the RF system or on an external server. To determine the current detection performance level of the first group 30, the CL system 100 performs RF-based sensing in the sensing area 32 using the current RF system configuration parameters. In this embodiment, if the current detection performance level is below a threshold detection performance level, the CL system 100 only optimizes the detection performance. In other embodiments, the RF system may be configured to optimize the detection performance based on whether the current detection performance level is higher or lower than the threshold detection performance level. If the CL system 100 determines that it does not need to optimize the detection performance, the CL system 100 performs RF-based sensing using the current RF system configuration parameters. Otherwise, the CL system 100 optimizes the detection performance.

[0144] To optimize detection performance, the CL system 100 determines which RF system configuration parameter has the greatest impact on detection performance based on the current context and the level of sensing metrics included in the detection performance. In other embodiments, the RF system may be configured to determine the RF system configuration parameter with the greatest impact on detection performance, for example, based on which of one or more sensing metrics is included in the detection performance, as an alternative to or supplement to its sensing metric level.

[0145] In this embodiment, the current context includes the sensing applications performed by the first group and environmental effects in the form of wireless interference 50 caused by the operation of the second group 40 in the first sensing area 32. The sensing applications are determined by input provided by user 26, i.e., user 26 decides which sensing applications will be performed by the CL system 100. In this embodiment, the CL system 100 is used for occupancy detection. Wireless interference 50 is determined based on a sensing analysis algorithm that detects wireless interference based on RF signals including RF messages exchanged between nodes, i.e., depending on signal strength and the rate of lost RF messages.

[0146] In other embodiments, the current context may also include, for example, settings of one or more of the RF system configuration parameters, latency requirements, expected sensing events in the sensing area, privacy requirements, radio power consumption requirements, radio transmit power requirements, radio beamform requirements, radio receive beamforming requirements, the current location of the RF system, the current location of at least one of at least two nodes, the current location of tangible entities in the sensing area, the current date, the current operating mode of at least one of at least two nodes, the current available bandwidth in the RF system, the current capability of at least one of at least two nodes, the current attributes of the sensing area, error event detection rate requirements, and missed event detection requirements.

[0147] The CL system 100 determines whether the current sensing metric level, which is included in the detection performance, is higher or lower than a corresponding threshold sensing metric level. For example, whether the current latency level is higher or lower than a threshold latency level of, for example, 0.2 seconds. In this embodiment, the user provides the CL system 100 with a current latency level of, for example, 0.5 seconds. Therefore, the current latency level is higher than the threshold latency level. In other embodiments, the current sensing metric level can also be determined automatically, for example, when the current energy consumption level is higher than a threshold energy consumption level.

[0148] Then, based on which of the corresponding current sensing metric levels among one or more sensing metrics included in the detection performance is higher or lower than a corresponding threshold sensing metric level, the RF system configuration parameter that has the greatest impact on the detection performance of RF-based sensing is determined. For example, if the current latency level is higher than a threshold latency level, the latency performance is considered suboptimal. This needs to be considered when determining the root cause that negatively impacts the detection performance. The CL system 100 may include a database, such as a lookup table (LUT), in which the RF system configuration parameter that most affects the detection performance is associated with a combination of suboptimal performance of the sensing metrics. In other embodiments, the root cause may be stored instead of the RF system configuration parameter, and the RF system configuration parameter may be associated with the root cause. The LUT may be provided based on experience, for example, through trial and error or learning based on trial and error.

[0149] After the CL system 100 determines which RF system configuration parameter has the greatest impact on detection performance, the CL system 100 adjusts that RF system configuration parameter to optimize detection performance. In this embodiment, the CL system 100 simulates how to adjust the RF system configuration parameter by simulating its adjustment and determining its impact on detection performance. Alternatively or additionally, the CL system 100 may also determine how to adjust the RF system configuration parameter based on rules (e.g., rules stored in the memory of one of the nodes), such as adjusting a specific RF system configuration parameter in a specific manner based on the current context. In other embodiments, adjusting the RF system configuration parameter that has the greatest impact on detection performance may also be performed by iteratively adjusting the various RF system configuration parameters of the CL system 100 and comparing the previous detection performance with subsequent detection performance obtained by performing RF-based sensing using the various adjusted RF system configuration parameters. This adjustment may be performed automatically by the CL system 100 and / or may be instructed by the user 26 to adjust the RF system configuration parameter, for example, depending on which RF system configuration parameter is to be adjusted.

[0150] Therefore, CL system 100 can use the communication interface of node 34 to provide user 26 with the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing, and how to adjust these parameters to optimize detection performance. User 26 can receive this information, for example, via touch display 24 or via user equipment such as a mobile phone (not shown). User 26 can then adjust the RF system configuration parameters that have the greatest impact on detection performance accordingly to optimize detection performance.

[0151] In other embodiments, after optimizing the detection performance for the RF system configuration parameters that have the greatest impact on detection performance, other RF system configuration parameters can be adjusted to further optimize detection performance. In other embodiments, for example, if adjusting the RF system configuration parameters that have the greatest impact on detection performance does not sufficiently improve detection performance, the CL system 100 can determine a ranking of the RF system configuration parameters based on their respective impact on detection performance. The CL system 100 can then adjust the RF system configuration parameters according to their ranking to optimize detection performance; that is, the RF system configuration parameters can be adjusted sequentially, one after another, until detection performance is sufficiently improved, for example, when the current detection performance level is higher than a threshold detection performance level. The adjustment of the RF system configuration parameters can also consider whether several RF system configuration parameters are interdependent and iteratively adjust these RF system configuration parameters according to one of the techniques known to those skilled in the art.

[0152] Figures 3 to 6Various configurations of the CL system 100 based on different adjustments to optimize the detection performance of RF-based sensing for different contexts are shown.

[0153] exist Figure 3 The image shows a second configuration of the CL system 100, in which nodes 36 and 38 of the first group 30 are moved horizontally relative to the first room to bring them closer together. This allows for compensation for low RF signal strength. In this embodiment, the sensing area 32 is also adjusted. The other nodes 34, 44, 46, and 48 remain stationary.

[0154] The following section presents how the CL system 100 determines whether mobile nodes 36 and 38 are permitted to... Figure 3 The details of optimizing detection performance within the context.

[0155] CL system 100 first determines the impact of adjusting the sensitivity of nodes 34, 36, and 38 on detection performance and finds that it does not significantly affect detection performance. CL system 100 then examines the impact of radio interference 50 in the signal link between nodes 34, 36, and 38 on detection performance. In this case, the impact of radio interference 50 is negligible. CL system 100 then determines the impact of other RF system configuration parameters on detection performance in order to find the root cause of the negative impact on detection performance. CL system 100 finds that the signal link between two nodes (e.g., 36 and 38) has only low RF signal strength. Low RF signal strength may lead to lower detection performance because RF messages are more likely to be affected by even minor environmental influences and therefore may not be received.

[0156] Based on the knowledge that the low RF signal strength between nodes 36 and 38 is the root cause of poor detection performance in RF-based sensing, the CL system 100 determines how to optimize detection performance. Therefore, the CL system 100 uses an optimization method based on prior experience, namely, that adding another new node does not necessarily improve detection performance because it does not improve RF signal strength and thus does not improve the signal link between nodes 36 and 38. Therefore, the CL system 100 determines that moving nodes 36 and 38 closer together improves detection performance because the RF path between them is stronger. Alternatively, the CL system 100 can simulate several slightly modified positions of nodes 36 and 38 to identify the spatial arrangement of nodes 36 and 38 where multipath effects become more significant and allow for an increase in the RF signal strength of the signal link between nodes 36 and 38.

[0157] Alternatively, the position of a node can be adjusted by moving the node in a vertical plane (i.e., in the vertical direction) rather than in a horizontal plane (i.e., in the horizontal direction). For example, a node in the form of a vertical illuminator can have an adjustable bracket for adjusting the vertical position of the antenna array of the node transmitting and receiving RF signals, and a node in the form of a chandelier can have an adjustable chain or wire for adjusting the vertical position of its antenna array. The CL system 100 can determine that adjusting the vertical position has the greatest impact on detection performance, for example, based on metadata such as that of the illuminator prototype, or based on direct measurement information, such as direct measurement information obtained from augmented reality (AR) measurement tools, light detection and ranging (LiDAR), laser distance measurement, etc.

[0158] If horizontal movement of the node is restricted, the CL system 100 can also determine that the vertical position of the node can be adjusted instead of moving it horizontally. Some positions of the node may be unavailable; for example, some horizontal and / or vertical positions may be inaccessible to the node. Adjusting the vertical and / or horizontal position of the node increases the number of available positions. For example, ceiling lights have limited options in where they can be placed horizontally, but can be adjusted more freely in the vertical direction. This can allow for improved automatic or manual adjustment of the node position.

[0159] Alternatively, user 26 can provide CL system 100 with information about the root cause or current context of performing RF-based sensing. This information can be used to determine which RF system configuration parameter has the greatest impact on detection performance and how to adjust that RF system configuration parameter to optimize detection performance.

[0160] For example, user 26 may indicate that the RF-based sensing performs poorly near certain objects (not shown), or does not work at certain times of day (e.g., at night), or frequently does not work during certain activities (e.g., another user in an adjacent room streaming video via the Internet), or the RF-based sensing does not work in different parts of the first room (e.g., occupancy detection fails when the user is working at a desk, or respiratory rate recognition fails when the user is lying on the left side of the double bed instead of the right side).

[0161] For these contexts, the CL system 100 can combine user-provided information with other current contexts, such as the current settings of RF system configuration parameters, as determined by the CL system 100. Furthermore, for example, considering the current context, the CL system 100 can determine the degree of impact of each RF system configuration parameter on detection performance.

[0162] User 26 may also provide information, for example, regarding whether a certain RF system configuration parameter is adjustable. For instance, if the CL system 100 includes nodes in the form of spotlights with rotating heads, the directionality of the RF mode can be changed by aiming the spotlight at different angles. In contrast, such RF system configuration parameters may not be adjustable for nodes, for example, those in the form of suspended illuminators.

[0163] If user 26 inputs the option to add a new node to the first group 30 into the CL system 100, or by adding a node to the first group 30 (e.g., node 46 from the second group 40 (see...) Figure 4 Alternatively, add a new node 39 to CL system 100 (see...). Figure 5 If so, the CL system 100 can determine how the adjustment affects detection performance and which spatial location of the newly added node optimizes detection performance.

[0164] For example, the CL system 100 can optimize detection performance by adding a new node as close as possible to the table where the user is working. Alternatively, the CL system 100 can also optimize detection performance based on other current contexts, such as analyzing the signal links between all nodes in the sensing area and focusing on those signal links that allow for the provision of specific metadata that can infer the node's proximity to the user's table, i.e., the location where RF-based sensing needs improvement. For example, a node close to the table could be a reading light type or have a name like "Desktop Left." This may lead to the discovery that non-trivial RF system configuration parameters, such as a new node in the form of a ceiling light in the center of the room, have the greatest impact on detection performance. Such a ceiling light can provide a signal link across the volume of the area where the table is located, and thus can allow for improved RF-based sensing coverage on the table, thereby optimizing detection performance.

[0165] When adding nodes is impossible or unacceptable, the CL system 100 can provide the user with alternative RF system configuration parameters and information on how to adjust them. These alternative RF system configuration parameters can be, for example, parameters that do not impair other existing signal links. For instance, the CL system 100 might identify one or more RF system configuration parameters that can be adjusted to optimize detection performance as the location of the node with the strongest signal link relative to other nodes. For these nodes, minor movement does not significantly disrupt the quality of these signal links and does not result in lost RF messages, which would disrupt RF-based sensing. Therefore, the location of these nodes can be adjusted to bring them closer to the table, for example, by moving the sensing area and its coverage.

[0166] On the other hand, the location of a moving node can negatively impact other parts of the sensing area or other sensing applications. The CL system 100 can be configured to take this into account when optimizing detection performance. For example, a node with acceptable performance in its original configuration but close to a quality threshold considered noisy might be further degraded by emphasizing improved RF-based sensing near a table. This could result in optimized detection performance at the table but reduced detection performance in another part of the sensing area (e.g., near a door). The CL system 100 can also consider which parts of the sensing area are regions of interest and optimize detection performance such that detection in or near regions of interest is optimized.

[0167] exist Figure 4 The image shows a third configuration of the CL system 100, in which node 46 is removed from the second group 40 and added to the first group 30. This allows for improved detection performance of the first group 30, while potentially reducing the detection performance of the second group 40. In this case, node 46 is not only regrouped from the second group 40 to the first group 30, but also spatially moved.

[0168] Alternatively, the CL system 100 can also regroup the first group 30 and the second group 40 by removing node 46 from the second group 40 and adding it to the first group 30, without adjusting the spatial position, i.e., without moving node 46. This can also allow for optimization of detection performance.

[0169] The CL system 100 can determine whether node 46 is critical to the sensing application of the second group 40 before removing it and adding it to the first group 30. The CL system 100 can decide whether to remove node 46 from the second group 40 and add it to the first group 30 based on whether node 46 is critical to the sensing application of the second group 40. This allows for avoiding a significant reduction in detection performance in the second sensing area 42.

[0170] For example, the CL system 100 can determine, for example, based on a general ZigBee neighbor table, that node 46 is positioned in a sensing area 42 adjacent to a first group 30, which has strong signal links to nodes 36 and 38. The CL system 100 can then determine the RF system configuration parameters that adding node 46 to the first group 30 might be the ones with the greatest impact on detection performance. Before adjusting the RF system configuration parameters by adding node 46 to the first group 30, the CL system 100 can examine whether the adjustment reduces the detection performance of the second group 40 and / or whether and how the detection performance is optimized in the first sensing area 32. The CL system 100 can alternatively or additionally determine how adding node 46 to the first group 30 affects the operation of the second group 40, for example, whether detection performance is reduced in the second sensing area 42, or, for example, whether the false alarm rate of RF-based sensing performed in the first sensing area 32 increases due to activity in the second sensing area 42, where node 46 remains in its unmoved location.

[0171] Alternatively, node 46 can also be included in both groups 30 and 40, and RF-based sensing can be performed in both sensing regions 32 and 42. In this case, the CL system 100 can, for example, adjust or advise the user to adjust one or more sensing parameters for RF-based sensing of both groups 30 and 40. The CL system 100 can also adjust or advise the user to adjust other RF system configuration parameters besides the sensing parameters. For example, the user can be instructed to move another node in the second group 40 to a new location to compensate for a lack of resolution or reliability in performing RF-based sensing in the first sensing region 32 or the second sensing region 42.

[0172] exist Figure 5 The image presents a fourth configuration of the CL system 100, in which node 39 is added to the first group 30 to mitigate radio interference 50. In this configuration, radio interference 50 is caused by the operation of the second group 40. Environmental effects may also include, for example, RF noise provided by any other noise source, such as a microwave oven or a streaming television.

[0173] The first group 30 is deployed in the corridor, and the user 26 has spent some time configuring nodes 34, 36 and 38 of the first group 30 to perform RF-based sensing in the corridor to ensure a satisfactory balance between fast motion detection and avoiding false alarms in the adjacent living room, which includes the second group 40.

[0174] If the detection performance is unsatisfactory, user 26 can report his dissatisfaction to CL system 100, for example, via the communication interface of node 34, such as by using an app on the user device and transmitting the information to node 34, or by using any other available user interface (such as a touch display).

[0175] In response, CL system 100 first examines the impact of all RF system configuration parameters on detection performance. Then, CL system 100 determines that the root cause of the negative impact on detection performance is excessive noise in the signal link between nodes 34, 36, and 38; specifically, in this case, the Received Signal Strength Indication (RSSI) or Channel State Information (CSI) fluctuates too much (e.g., above a threshold). Subsequently, CL system 100 determines that the best solution to mitigate the root cause of the negative impact on detection performance (i.e., the noisy signal link between nodes 34, 36, and 38) is to add another node to group 30. CL system 100 understands that adding data from the additional signal link will allow the sensing analysis algorithm to further correlate what has already been observed from the original signal link, but with higher confidence. This allows for the detection of sensed events with higher confidence.

[0176] For example, an RF system can determine that any signal link with amplitude fluctuations exceeding, for example, 20% of historical values ​​(e.g., historical averages determined for a certain time window) is considered noisy. Alternatively, an RF system can measure the frequency of amplitude peaks and determine that the signal link is currently extremely noisy based on the frequency of the amplitude peaks.

[0177] exist Figure 6 The diagram illustrates a fifth configuration of the CL system 100, where nodes 34, 36, 44, and 46 are regrouped into a first group 30, and groups 38 and 48 are regrouped into a second group 40. This also adjusts sensing areas 32 and 42. Regrouping nodes 34 through 48 allows for optimization of detection performance based on the current context, for example, when adjusting the sensing area improves detection performance, such as when a sensing event occurs in a portion of a sensing area that is not well covered and adjusting the sensing area optimizes coverage. In other cases, nodes may be additionally moved.

[0178] In the following text, without the accompanying drawings, an alternative scenario is presented, namely, the CL system 100 operating in a different current context.

[0179] The CL system 100 can not only identify the node that has the greatest impact on detection performance when moved, but also determine how moving that node affects other sensing applications. For example, if a particular sensing metric is to be optimized for a particular sensing application (e.g., latency for detecting occupancy of a user entering a sensing area), this may affect other sensing applications (e.g., respiratory rate identification of the first of two users lying in a double bed).

[0180] For example, if a bedroom has two nodes, one in the form of a floor-standing nightlight and the other a ceiling light, this configuration may not be sufficient to achieve a sufficiently low latency in turning on the lights when a user enters the room. The CL system 100 can determine that moving one of the floor-standing nightlights 30cm closer to the room entrance, due to factors such as the size of the bedroom and the room type (e.g., a bedroom), allows for optimized detection performance. In this case, this adjustment, simulating the position of the floor-standing nightlight, reduces latency without significantly reducing the signal link between nodes, and the simulation can subsequently be verified by performing RF-based sensing.

[0181] However, moving one of the freestanding nightlights by 30cm can significantly impact the detection performance for respiratory rate identification of the first user lying on the first side of the double bed, when the second user is lying on the second side. For example, since 2.4GHz or 5GHz WiFi signals exhibit low limitations—that is, they do not have clear boundaries—after moving the freestanding nightlight by 30cm, the RF signal can now interact not only with the first user but also with the second user lying on the second side of the double bed. Therefore, moving the freestanding nightlight by 30cm can greatly interfere with the RF sensing analysis algorithm used for respiratory rate identification.

[0182] In this scenario, the CL system 100 can postpone moving the freestanding nightlight by 30cm and instead determine and adjust alternative RF system configuration parameters, such as those that have the greatest impact on occupancy detection performance without significantly reducing or even improving the detection performance of respiratory rate recognition. For example, a new node can be added to a group closer to the room entrance to perform RF-based sensing in the sensing area. Alternatively, for example, the message passing rate can be increased.

[0183] Alternatively, the CL system 100 may determine that moving the freestanding nightlight or adjusting its height within the horizontal plane is preferable to adding a new node. Adding a new node increases the resources required for each node in the group performing RF-based sensing, because, for example, more nodes need to be tracked, and the amount of data traffic between nodes increases. Therefore, adding a new node may have a negative impact on detection performance due to, for example, increased data traffic, wireless interference, and energy consumption.

[0184] Therefore, the CL system 100 can determine whether improving detection performance can be achieved by increasing one sensing metric while decreasing another (e.g., increasing data traffic). The CL system 100 can, for example, determine that the data traffic in the sensing area is already close to, for example, a network congestion threshold for successfully receiving messages. Therefore, adding another new node to the group performing RF-based sensing in the sensing area will further reduce this already weak sensing metric, and may even cause the data traffic to exceed the network congestion threshold, resulting in lost RF messages. Based on this current context, the CL system 100 can determine that adjusting another RF system configuration parameter is preferable to adding a new node or increasing the message delivery rate, for example, moving a freestanding nightlight on a horizontal or vertical plane.

[0185] In summary, RF systems can automatically improve or provide feedback to users to enhance detection performance in specific sensing areas. RF systems can identify the root cause of negative impacts on detection performance, leading users to perceive RF-based sensing as suboptimal. Based on this root cause, the RF system can provide recommendations for improving detection performance by adjusting one or more RF system configuration parameters, particularly those with the greatest impact on detection performance. Recommendations for improving detection performance can also consider the current context, including, for example, the prioritized sensing applications or desired sensing functions, the primary activity types in the sensing area, tolerance for false detections, latency requirements, latency expectations, or any other contextual factors. For example, different contexts allow the RF system to adjust or recommend which RF system configuration parameters should be adjusted, such as by adding nodes or changing the spatial location of existing nodes. The current context can also allow for determining how the RF system can consciously balance the performance of different sensing metrics simultaneously served by the same RF system—for example, breathing detection in a sensing area versus faster motion sensing versus fall detection in an adjacent sensing area—to improve detection performance encompassing different sensing metrics.

[0186] The overall goal of RF systems is to improve detection performance, for example, by providing users with more relevant suggestions or options for adjusting RF system configuration parameters, rather than simply adjusting sensitivity levels as is the case with existing technologies. Adjusting RF system configuration parameters allows for fine-tuning of RF-based sensing in a highly context-aware, and especially application-aware, manner.

[0187] RF systems can guide users to optimize detection performance, especially when the user is unaware of the root cause of the performance degradation and / or how to optimize it. The RF system can guide the user in response to information provided by the user about the current context, as well as information about the current context acquired by the RF system itself. For example, whenever a user enters the sensing area through the front door, the user can indicate that the latency is too long (i.e., RF-based sensing is taking too long), but not when the user enters through another door. In this case, the user provides the RF system with the current context of why the detection performance is inadequate, even though they themselves are unaware of the root cause of the performance degradation, such as too many or too few nodes performing RF-based sensing, insufficient sampling rate, insufficient transmission power, etc. However, combining the user-provided information about the current context with information about the current context of the RF system allows the root cause to be identified, and subsequently, how to optimize the detection performance can be determined.

[0188] Figure 7 An embodiment of a method 700 for optimizing detection performance for performing RF-based sensing based on RF system configuration parameters is shown. This method can be, for example, derived from an RF system (e.g., regarding...). Figures 2 to 6 The CL system 100 is executed.

[0189] In step 702, the user provides information about the current context for RF-based sensing performed by a set of nodes in the sensing area, as well as sensing metrics that the user is dissatisfied with. For example, the user provides the RF system for occupancy detection and provides a latency requirement of 0.2 s to complete the detection, so as to allow the RF system to react quickly, for example, turning on the lighting when the user enters the sensing area. The user can also provide that he is dissatisfied with the latency, for example because the latency exceeds 0.2 s (e.g., 0.4 s).

[0190] In step 704, the current context for the group to perform RF-based sensing in the sensing area is determined based on information provided by the user and information obtained by the nodes, such as the current settings of RF system configuration parameters for the current spatial arrangement of the nodes, and the number of nodes in the group used to perform RF-based sensing in the sensing area. The information provided by the user and obtained by the nodes is analyzed.

[0191] In step 706, a set of nodes of the RF system perform RF-based sensing in the sensing area.

[0192] In step 708, the current detection performance level of the RF-based sensing is determined based on the performed RF-based sensing. In this case, the current detection performance level depends on the current latency occupied by the detection. If the detection performance level is higher than a threshold detection performance level, the current RF system configuration parameters are used to perform RF-based sensing in the sensing area; that is, step 706 is executed as long as the current detection performance level of the RF-based sensing is higher than the threshold detection performance level. If the current detection performance level is lower than the threshold detection performance level, step 710 is executed to optimize the detection performance of the RF-based sensing. In this case, the latency is higher than the latency requirement of 0.2s, and the obtained current detection performance level is lower than the threshold detection performance level, causing step 710 to be executed.

[0193] In step 710, based on the current context and current sensing metric level included in the detection performance, the RF system configuration parameter that has the greatest impact on the detection performance of RF-based sensing is determined. Therefore, it is determined whether the corresponding current sensing metric level of the sensing metric included in the detection performance is lower than the corresponding threshold sensing metric level. In this case, it is determined that the latency is higher than the latency requirement, which corresponds to the sensing metric level being lower than the threshold sensing metric level. In response, based on a LUT including information associated with which RF system configuration parameter most affects which sensing metric, the RF system configuration parameter affecting the corresponding sensing metric level being lower than the corresponding threshold sensing metric level is determined. In this case, latency is generated due to the limited processing capacity of the nodes in the group.

[0194] In step 712, the user is provided with information on which RF system configuration parameter has the greatest impact on the detection performance of RF-based sensing. In this case, the user is provided with information on the capabilities of the nodes in the group that have the greatest impact on detection performance, because a node's processing power is too low to perform RF-based sensing with low latency.

[0195] Additionally, the user is provided with information on how to adjust the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing to optimize detection performance. In this case, the user is provided with information that nodes with lower processing power can be replaced by nodes with higher processing power, or that nodes with higher processing power can be added to the group. In other embodiments, this information can be provided to the RF system nodes that optimize the RF system configuration parameters that have the greatest impact on detection performance. For example, if transmit power is the RF system configuration parameter that has the greatest impact on detection performance, one or more corresponding nodes can adjust their transmit power to optimize detection performance.

[0196] In step 714, the user adjusts the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing in order to optimize the detection performance of RF-based sensing. In this case, additional nodes with higher processing power are added to the group to reduce latency.

[0197] In other embodiments, nodes of the RF system can automatically adjust the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing based on information on how to adjust the RF system configuration parameters that have the greatest impact on detection performance to optimize detection performance (e.g., increasing transmit power).

[0198] In other embodiments, a ranking of one or more RF system configuration parameters may be determined, which are ranked according to the degree of influence of one or more RF system configuration parameters on the detection performance of RF-based sensing, and the RF system configuration parameters may be adjusted based on the ranking to optimize the detection performance of RF-based sensing.

[0199] While the invention has been detailed and described in the accompanying drawings and the foregoing description, such description should be considered illustrative or exemplary and not limiting; the invention is not limited to the disclosed embodiments. For example, it is possible for the invention to operate in embodiments in which the RF system is a heating, ventilation, and air conditioning (HVAC) system or any other smart home system. The RF system may also operate in the context of a BMS environment, a smart home environment, an office environment, or a residential environment.

[0200] By studying the accompanying drawings, the disclosure, and the appended claims, those skilled in the art can understand and implement other variations of the disclosed embodiments in practicing the claimed invention.

[0201] In the claims, the words “comprising” and “including” do not exclude other elements or steps, and the indefinite articles “a” or “an” do not exclude a plurality.

[0202] A single unit, processor, or device can perform the functions of several items listed in the claims. The mere fact that certain measures are referenced in mutually different dependent claims does not indicate that a combination of these measures cannot be used advantageously.

[0203] Operations performed by one or more units or devices (e.g., performing RF-based sensing in a sensing area by a group of at least two nodes of an RF system comprising multiple nodes, determining one or more RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing, adjusting the RF system configuration parameter that has the greatest impact on the detection performance to optimize the detection performance of RF-based sensing; etc.) can be performed by any other number of units or devices. These operations and / or methods can be implemented as program code means of a computer program and / or as dedicated hardware.

[0204] Computer program products may be stored / distributed on suitable media, such as optical storage media or solid-state media, provided together with or as part of other hardware; but may also be distributed in other forms, such as via the Internet, Ethernet, or other wired or wireless telecommunications systems.

[0205] Any reference numerals in the claims should not be construed as limiting the scope.

[0206] This invention relates to an RF system with multiple nodes and a method for optimizing detection performance for performing RF-based sensing in a sensing area based on RF system configuration parameters. The method involves identifying the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing. Then, the RF system configuration parameters that have the greatest impact on the detection performance of RF-based sensing are adjusted to optimize the detection performance. The root cause of the detection performance degradation and the corresponding RF system configuration parameters used to mitigate the degradation can be determined based on the current context. To optimize detection performance, for example, the settings of the sensing parameters of the nodes can be adjusted, or nodes can be moved, removed, added, or replaced.

Claims

1. An RF system (100) for optimizing detection performance for performing RF-based sensing based on RF system configuration parameters, the RF system (100) comprising a plurality of nodes, wherein a group (30) of at least two nodes is configured to perform RF-based sensing in a sensing area (32), wherein a first node of the at least two nodes is configured to transmit an RF signal, and a second node of the at least two nodes is configured to receive the transmitted RF signal, and wherein the RF-based sensing is performed by analyzing interference to the RF signal caused by the interaction of the RF signal with one or more objects or persons on the transmission path between the at least two nodes. The radio frequency system (100) is configured to determine radio frequency system configuration parameters that have a greater impact on the detection performance of radio frequency-based sensing than a corresponding adjustment to another radio frequency system configuration parameter, and to adjust the radio frequency system configuration parameters that have a greater impact on the detection performance of radio frequency-based sensing than a corresponding adjustment to another radio frequency system configuration parameter in order to optimize the detection performance of radio frequency-based sensing.

2. The radio frequency system (100) according to claim 1, wherein the radio frequency system configuration parameters include one or more of the following: -The spatial arrangement of at least two nodes in the group (30), -The plurality of nodes are grouped into the group (30). - The number of nodes in the group (30), - The capabilities of the nodes in the group, and - One or more sensing parameters used to perform radio frequency-based sensing.

3. The radio frequency system (100) of claim 1, wherein the radio frequency system (100) is configured to determine, based on the current context, radio frequency system configuration parameters that most affect the detection performance of the radio frequency-based sensing.

4. The radio frequency system (100) according to claim 3, wherein, The current context includes one or more of the following: -Settings of one or more of the radio frequency system configuration parameters. -Sensing applications, -Delay requirements, -The expected sensing event in the sensing area (32), -Privacy requirements, -Radio power consumption requirements -Radio transmission power requirements, -Radio beam shape requirements - Radio receiver beamforming requirements - The current position of the radio frequency system (100), - The current position of at least one of the at least two nodes, -The current position of the tangible entity in the sensing area (32), -Current date, - The current operating mode of at least one of the at least two nodes, -Environmental impact, -The currently available bandwidth in the radio frequency system (100), - The current capabilities of at least one of the at least two nodes, - The current properties of the sensing area (32), - Error event detection rate requirements, and - Requirements for missing event detection.

5. The radio frequency system (100) of claim 1, wherein the detection performance includes one or more sensing metrics, the one or more sensing metrics including one or more of the following: -delay, -Accuracy, -Spatial resolution - False alarm detection rate -Missed detection rate, - Confidence level used to detect sensed events, - Noise in sensing event detection -Generated data traffic, - Energy consumption, and - Spatial constraints for performing radio frequency-based sensing of radio frequency signals.

6. The radio frequency system (100) of claim 5, wherein the radio frequency system (100) is configured to determine the radio frequency system configuration parameters that have the greatest impact on the detection performance of the radio frequency-based sensing based on one or more sensing metrics included in the detection performance.

7. The radio frequency system (100) according to claim 5, wherein the radio frequency system (100) is configured for - Determine whether the current sensing metric level of one or more sensing metrics included in the detection performance is higher or lower than a corresponding threshold sensing metric level, and - Based on which of the one or more sensing metrics included in the detection performance is higher or lower than the corresponding threshold sensing metric level, determine the radio frequency system configuration parameter that has the greatest impact on the detection performance of the radio frequency-based sensing.

8. The radio frequency system (100) according to claim 1, wherein the radio frequency system (100) is configured for - Determine the current detection performance level of radio frequency-based sensing, and - Optimize detection performance based on whether the current detection performance level is higher or lower than the threshold detection performance level.

9. The radio frequency system (100) according to any one of claims 1 to 8, wherein, The radio frequency system (100) is configured for - Determine the order of one or more radio frequency (RF) system configuration parameters, said RF system configuration parameters being ordered according to their respective impact on the detection performance of RF-based sensing, and - Adjust the RF system configuration parameters based on the sorting to optimize the detection performance of RF-based sensing.

10. The radio frequency system (100) of claim 1, wherein the radio frequency system (100) is configured for one or both of the following: - Provides radio frequency (RF) system configuration parameters that have a greater impact on the detection performance of RF-based sensing than corresponding adjustments to other RF system configuration parameters. - Provides information on how to adjust RF system configuration parameters that have a greater impact on the detection performance of RF-based sensing than corresponding adjustments to other RF system configuration parameters, in order to optimize detection performance.

11. The radio frequency system (100) according to claim 10, wherein, The radio frequency system (100) includes a communication interface (14) for one or both of the following: - Provide the user (26) with radio frequency system configuration parameters, which have a greater impact on the detection performance of radio frequency-based sensing than a corresponding adjustment to another radio frequency system configuration parameter, and - Provide the user (26) with information on how to adjust the RF system configuration parameters that have a greater impact on the detection performance of RF-based sensing than corresponding adjustments to other RF system configuration parameters, in order to optimize detection performance.

12. A method for optimizing detection performance for performing radio frequency-based sensing based on radio frequency system configuration parameters, the method comprising the steps of: - Radio frequency (RF) based sensing is performed in a sensing area by a group of at least two nodes in an RF system comprising multiple nodes, wherein a first node of the at least two nodes is configured to transmit RF signals, and a second node of the at least two nodes is configured to receive the transmitted RF signals, and wherein the RF based sensing is performed by analyzing interference to the RF signals caused by the interaction of the RF signals with one or more objects or people on the transmission path between the at least two nodes. - Identify the RF system configuration parameters that have a greater impact on the detection performance of RF-based sensing than a corresponding adjustment to another RF system configuration parameter, and - Adjust the RF system configuration parameters that have a greater impact on the detection performance of RF-based sensing than corresponding adjustments to other RF system configuration parameters, in order to optimize the detection performance of RF-based sensing.

13. The method of claim 12, comprising one or more of the following steps: - Determine the current context for performing radio frequency-based sensing by the group in the sensing area. - Based on the current context, determine the radio frequency system configuration parameters, which have a greater impact on the detection performance of the radio frequency-based sensing than a corresponding adjustment to another radio frequency system configuration parameter. - Based on one or more sensing metrics included in the detection performance, determine the radio frequency system configuration parameter that has a greater impact on the detection performance of the radio frequency-based sensing than a corresponding adjustment to another radio frequency system configuration parameter. - Determine whether the current sensing metric level of one or more sensing metrics included in the detection performance is higher or lower than a corresponding threshold sensing metric level. -Based on which of the corresponding current sensing metric levels of one or more sensing metrics included in the detection performance are higher or lower than the corresponding threshold sensing metric level, determine the RF system configuration parameter that has a greater impact on the detection performance of RF-based sensing than a corresponding adjustment to another RF system configuration parameter. - Determine the current detection performance level of radio frequency-based sensing. - Optimize detection performance based on whether the current detection performance level is higher or lower than the threshold detection performance level. - Determine the order of one or more radio frequency (RF) system configuration parameters, said RF system configuration parameters being ordered according to their respective impact on the detection performance of RF-based sensing. - Adjust the RF system configuration parameters based on the sorting to optimize the detection performance of RF-based sensing. - Provides radio frequency (RF) system configuration parameters that have a greater impact on the detection performance of RF-based sensing than corresponding adjustments to other RF system configuration parameters. - Provides instructions on how to adjust RF system configuration parameters that have a greater impact on the detection performance of RF-based sensing than corresponding adjustments to other RF system configuration parameters, in order to optimize detection performance. - Provide users with radio frequency (RF) system configuration parameters that have a greater impact on the detection performance of RF-based sensing than corresponding adjustments to other RF system configuration parameters. - Provide the user with information on how to adjust RF system configuration parameters that have a greater impact on the detection performance of RF-based sensing than corresponding adjustments to other RF system configuration parameters, in order to optimize detection performance.

14. A computer program product for optimizing the detection performance of radio frequency-based sensing, wherein the computer program product includes program code that, when executed by a processor (18), implements the method as claimed in claim 12 or 13.

15. A computer-readable medium (20) storing program code that, when executed by a processor (18), implements the method as claimed in claim 12 or 13.

Images