Identification device, identification system, and identification method
The identification system improves the accuracy of substance identification by using ordered detection values from multiple elements to determine source characteristics, mitigating the effects of environmental factors and equipment noise, thus providing stable and reliable detection.
Patent Information
- Application Number
- PCT/JP2024/018531
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-06-01
- Filing Date
- 2024-05-20
- Publication Date
- 2024-12-05
AI Technical Summary
Chemical sensor devices face challenges in stabilizing the accuracy of substance identification due to equipment noise and environmental factors like temperature and humidity, which cause deviations in map data even for the same source.
The identification system uses multiple detection elements that react differently to substances, ordering them by detection value magnitude to determine characteristic information, and generates information about the relationship between detection element order and source characteristics, allowing for accurate identification by referencing this information.
This approach stabilizes the accuracy of substance identification by reducing the impact of environmental factors and equipment noise, ensuring reliable detection of substances based on the ordered detection values.
Smart Images

Figure JP2024018531_05122024_PF_FP_ABST
Abstract
Description
Identification device, identification system, and identification method
[0001] The present invention relates to an identification device, an identification system, and an identification method.
[0002] Patent Literature 1 discloses a chemical sensor device that identifies a source of a substance based on the amount of change in the resonant frequency of the oscillator that occurs when a substance is adsorbed or desorbed. This chemical sensor device includes multiple oscillators that exhibit adsorption / desorption characteristics for different substances. Each oscillator is excited when an AC voltage is applied. The substance is identified by comparing map data obtained by mapping the resonant frequencies of multiple oscillators to which a specific substance has been adsorbed or desorbed with map data obtained by mapping the detected resonant frequencies.
[0003] JP 2009-204584 A
[0004] The above-mentioned chemical sensor devices are susceptible to noise from the equipment and changes in temperature and humidity at the time of detection. Differences in the ambient temperature and humidity at the time of detection can cause discrepancies in map data even for the same source, making it difficult for chemical sensor devices to consistently identify the source.
[0005] The present invention has been made in light of the above-mentioned circumstances, and an object of the present invention is to provide an identification device, an identification system, and an identification method that can stabilize the accuracy of identifying the source.
[0006] In order to achieve the above object, an identification device according to a first aspect of the present invention comprises a plurality of detection elements that react to different types of substances among a plurality of types of substances emitted from a source and output detection values whose magnitudes correspond to the amounts of the reacted substances; and an identification unit that identifies the characteristic information of a source of a substance based on information indicating the order of the plurality of detection elements when the plurality of detection elements detect a substance, the order being determined by the magnitude of each detection value when the plurality of detection elements detect a substance emitted from a source whose characteristic information indicating a type or state is known, and by referring to information indicating the relationship between the order of the plurality of detection elements and the characteristic information of the known source.
[0007] The substance may include a substance that allows for the perception of an odor.
[0008] An identification system according to a second aspect of the present invention comprises a plurality of detection elements that react to different types of substances emitted from a source and output detection values of magnitudes corresponding to the amounts of the reacted substances; a generation unit that generates information indicating the order of the plurality of detection elements, for a plurality of known sources having different characteristic information indicating their types or states, ordered by the magnitude of the detection values when detected by the plurality of detection elements, in association with the characteristic information of the known sources; and an identification unit that identifies the characteristic information of the source of a substance based on the information indicating the order of the plurality of detection elements when a substance is detected by the plurality of detection elements, by referring to the information generated by the generation unit that indicates the relationship between the order of the plurality of detection elements and the characteristic information of the known sources.
[0009] The generation unit may be configured such that, when detection is performed multiple times with the multiple detection elements for a known source with the same characteristic information, if there is a detection element for which the order of the magnitude of the detection values changes, and if the order of the remaining detection elements does not overlap between sources even if that detection element is excluded, the generation unit narrows down the list to the remaining detection elements and generates information indicating the order of the detection elements, and the identification unit identifies the characteristic information of the source of the substance based on the information indicating the order of the detection elements when the substance is detected with the detection elements narrowed down by the generation unit.
[0010] The generation unit may be configured such that, when detection is performed multiple times with the multiple detection elements for a known source with the same characteristic information, there are detection elements for which the order of the magnitude of the detection values changes, and if the order does not overlap between sources even when the detection elements are grouped, the generation unit groups the detection elements with consecutive orders among the detection elements for which the order changes, and generates information indicating the order of the groups of detection elements; and the identification unit identifies the characteristic information of the source of the substance based on the information indicating the order of the detection elements when the substance is detected by the detection elements of each group generated by the generation unit.
[0011] The generation unit may group sources having the same order of the detection elements when detection is performed with the plurality of detection elements on a plurality of known sources having different characteristic information, and generate information indicating the order of the detection elements in association with the group; and the identification unit may refer to the information generated by the generation unit indicating the relationship between the order of the plurality of detection elements and the characteristic information of the group of known sources, and identify the characteristic information of the group of sources of the substance based on the information indicating the order of the plurality of detection elements when the substance is detected with the plurality of detection elements.
[0012] The generation unit may generate information indicating detection values when detected by the plurality of detection elements for a plurality of known sources having different characteristic information, in association with the characteristic information of the known sources; and the identification unit may refer to the information generated by the generation unit indicating the relationship between the order of the detection elements and the characteristic information of the known sources, as well as the information indicating the relationship between the detection values of the detection elements and the characteristic information of the known sources, and identify the characteristic information of the source of the substance based on the detection values of the detection elements when the substance is detected by the plurality of detection elements, together with the information indicating the order of the detection elements when the substance is detected by the plurality of detection elements.
[0013] An identification method according to a third aspect of the present invention is an identification method performed by an identification device that identifies a source using a plurality of detection elements that each react to different types of substance out of a plurality of types of substance emitted from the source and output detection values whose magnitude corresponds to the amount of the reacted substance, and identifies the characteristic information of the source of the substance based on information indicating the order of the plurality of detection elements when the plurality of detection elements detect a substance, with reference to information indicating the relationship between the order of the plurality of detection elements, which are ordered by the magnitude of each detection value when the plurality of detection elements detect substances emitted from known sources whose characteristic information indicating type or state is different from each other, and the characteristic information of the known source.
[0014] According to the present invention, it is possible to stabilize the accuracy of identifying the source.
[0015] 1 is a block diagram showing the configuration of an identification system according to a first embodiment of the present invention. FIG. 1 is a graph showing an example of map data of detection values from a plurality of detection elements. FIG. 2 is a table showing the order of largest detection values from a plurality of detection elements. FIG. 3 is a block diagram showing the configuration for performing identification in the identification system of FIG. 1. FIG. 4 is a block diagram showing the configuration for registering an order in the identification system of FIG. 1. FIG. 5 is a block diagram showing the hardware configuration of the identification unit of FIG. 1. FIG. 6 is a flowchart of registration mode processing. FIG. 7 is a flowchart of identification mode processing. FIG. 8 is a flowchart of registration mode processing for an identification system according to a second embodiment of the present invention. FIG. 9 is a diagram showing a first example of a case where the order of detection elements changes. FIG. 10 is a diagram showing a second example of a case where the order of detection elements changes. FIG. 11 is a flowchart of registration mode processing for an identification system according to a third embodiment of the present invention. FIG. 12 is a diagram showing a first example of grouping of detection elements. FIG. 13 is a diagram showing a second example of grouping of detection elements. FIG. 14 is a flowchart of registration mode processing for an identification system according to a fourth embodiment of the present invention. FIG. 15 is a diagram showing a first example of grouping of generation sources. FIG. 16 is a diagram showing a second example of grouping of generation sources. FIG. 17 is a block diagram showing the configuration of an identification system according to a fifth embodiment of the present invention. FIG. 18 is a flowchart of registration mode processing in the identification system of FIG. 14. FIG. 19 is a block diagram showing the configuration of an identification system according to a sixth embodiment of the present invention. 1 is a table showing the order of the detection values of a plurality of detection elements in two different types of generation sources; FIG. 2 is a graph showing map data of the detection values of a plurality of detection elements in two different types of generation sources; FIG. 3 is a schematic diagram showing an example of a detection unit; FIG. 4 is a perspective view showing the detection elements by partially breaking down the detection unit;
[0016] An embodiment of the present invention will now be described in detail with reference to the drawings. In the drawings, the same or equivalent parts are designated by the same reference numerals. An identification device, an identification system, and an identification method according to the present embodiment identify the source of a substance.
[0017] Embodiment 1 A first embodiment of the present invention will be described. As shown in Fig. 1, an identification system 1 according to this embodiment identifies the type of a substance source T as characteristic information of the substance source T. The identification system 1 includes an identification device 2 and a storage device 3. The identification device 2 includes a detection unit 10 and an identification unit 11.
[0018] [Detection Unit] The detection unit 10 includes a plurality of detection elements 5. The plurality of detection elements 5 each react to a different type of substance among the plurality of types of substances emitted from the source T. Each detection element 5 outputs a detection value whose magnitude corresponds to the amount of the reacted substance. For example, the detection element 5 may include a vibrator on which a substance adsorption film that adsorbs the substance is formed. When a substance is adsorbed onto the substance adsorption film, the weight of the entire vibrator increases and the vibration level changes. The magnitude of the change in vibration level corresponds to the amount of substance adsorbed onto the substance adsorption film. The detection element 5 outputs the magnitude of the change in vibration level as a reaction level (detection value) that indicates the amount of substance adsorption, i.e., the amount of reacted component.
[0019] Each detection element 5 is assigned a unique identification number. Hereinafter, the identification numbers assigned to each detection element 5 will be referred to as D[1] to D[M] (M is a natural number of 2 or greater). In this embodiment, M is a natural number of 6 or greater. The detection elements 5 output data in which each detection value is associated with an identification number. This data makes it possible to determine which detection element 5 detected the detection value included in the data.
[0020] The identification unit 11 receives data including the detection values and identification numbers output from the plurality of detection elements 5 in the detection unit 10, and performs information processing on the received data. The identification unit 11 includes a conversion unit 20, an identification unit 21, and a generation unit 22.
[0021] [Conversion Unit] The conversion unit 20 generates information indicating the order of the multiple detection elements 5 (D[1] to D[M]) when a substance is detected by the multiple detection elements 5 (D[1] to D[M]) based on data including the detection values and identification numbers output from the multiple detection elements 5. In other words, the conversion unit 20 converts the map data of the detection values output from the multiple detection elements 5 into information indicating the order of their magnitudes. For example, if the magnitudes of the detection values of the detection elements 5 (D[1] to D[M]) are displayed as map data like the white bar graph in FIG. 2A, the conversion unit 20 generates information indicating the order of the multiple detection elements 5 (D[1] to D[M]) as shown in FIG. 2B. Note that detection elements 5 with detection values lower than a threshold may be excluded from the order. Note that this order may be based on detection values normalized by a reference value such as the maximum detection value of each detection element 5, or may be based on the detection values of each detection element 5 themselves.
[0022] 2A, the detection values of the detection elements 5 detected by the same source T are shown in two ways, with white and diagonal bars. As shown in FIG. 2A, even for the same source T, the magnitude of the detection value of each detection element 5 varies depending on the measurement conditions, etc., but the order of the multiple detection elements 5 (D[1] to D[M]) according to the magnitude of the detection value remains unchanged.
[0023] [Identification Unit] The identification unit 21 identifies characteristic information (type) of the source T based on information generated by the conversion unit 20 indicating the order of the multiple detection elements 5, which are ordered by the magnitude of the detection values when a substance is detected. The storage device 3 stores information indicating the relationship between the order of the magnitude of the detection values of the multiple detection elements 5 and the type of known source T. The identification unit 21 identifies the type of source T of the substance by referring to the information stored in the storage device 3 indicating the relationship between the order of the multiple detection elements 5 and the type of known source T.
[0024] In FIG. 1 , the storage device 3 stores the order of the detection elements 5 (D[1] to D[M]) for each known type of source T (G[1] to G[N]; N is a natural number equal to or greater than 2) in association with the type (G[1] to G[N]) of the known source T. In the present embodiment, N is a natural number equal to or greater than 4. The sources G[1] to G[N] are not particularly limited, and can include, for example, fruits such as apples, bananas, and mandarin oranges, vegetables, and various objects that emit substances into the air. For example, the storage device 3 stores the order of the detection elements 5 for each of the known types of source T, G[1], G[2], G[3], ..., G[N], in association with each other. For example, the order of the detection elements 5 associated with G[1] is (D[1], D[2], D[3], D[4], D[5]) = (1, 3, 2, 4, 5).
[0025] Now, suppose that a new source T of unknown type is detected by the multiple detection elements 5, and the conversion unit 20 generates information indicating the order of the magnitudes of the detection values of the multiple detection elements 5. The identification unit 21 compares the order of the multiple detection elements 5 stored in the storage device 3 with the order of the multiple detection elements 5 of the unknown source T, and identifies the unknown source T as a source T with the same order. For example, as shown in FIG. 3 , if the order of the detection elements 5 of the unknown source T is (D[1], D[2], D[3], D[4], D[5]) = (1, 3, 2, 4, 5), the unknown source T is identified as G[1].
[0026] [Generation Unit] In order for the identification unit 21 to perform identification, it is necessary to store in the storage device 3 information indicating the relationship between the order of the multiple detection elements 5 and the type of known generation source T. The generation unit 22 generates the information to be stored in the storage device 3.
[0027] The generation unit 22 inputs information indicating the type of the generation source T detected by the plurality of detection elements 5. This input is performed by a user's operation input. For example, before the plurality of detection elements 5 detect a substance emitted from the generation source T (G[1]), it is input that the type of the generation source T is G[1].
[0028] The generation unit 22 associates information indicating the order of magnitude of the detection values of the multiple detection elements 5 detected by the multiple detection elements 5 for the source T whose type has been input and generated by the conversion unit 20 with the type of the input source T and stores the information in the storage device 3.
[0029] 4 , when the type G[1] of the source T is input and multiple detection elements 5 detect a substance emitted from the source T (type G[1]), the conversion unit 20 generates information indicating the order of the multiple detection elements 5, which are ordered by the magnitude of their respective detection values when detecting the substance emitted from the source T (G[1]). The generation unit 22 generates information indicating the order of the multiple detection elements in association with the known source G[1] and stores the information in the storage device 3.
[0030] Similarly, for G[2], G[3], G[4], ..., G[N], which are sources T of known type, substance detection is performed by the multiple detection elements 5, an order is generated by the conversion unit 20, and registration is performed by the generation unit 22. As a result, information indicating the order of the multiple detection elements 5 associated with each of G[1], G[2], G[3], G[4], ..., G[N], which are sources T of known type, is stored in the storage device 3.
[0031] [Hardware Configuration of Recognition Unit] The recognition unit 11 shown in Fig. 1 is realized, for example, by a computer having the hardware configuration shown in Fig. 5 executing a software program. Specifically, the recognition unit 11 includes a CPU (Central Processing Unit) 31 that controls the entire device, a main memory 32 that operates as a work area or the like for the CPU 31, an external memory 33 that stores the operating program or the like for the CPU 31, an operation unit 34, a display unit 35, an input / output unit 36, a communication unit 37, and an internal bus 38 that connects these units together.
[0032] The main memory 32 is composed of RAM (Random Access Memory) etc. A program 39 to be executed by the CPU 31 is loaded into the main memory 32 from the external memory 33. The main memory 32 is also used as a working area (temporary data storage area) for the CPU 31.
[0033] The external memory 33 is configured by a nonvolatile memory such as a flash memory, a hard disk, etc. The external memory 33 stores in advance a program 39 to be executed by the CPU 31.
[0034] The operation unit 34 is made up of devices such as a keyboard and a mouse, and an interface device that connects these devices to the internal bus 38 .
[0035] The display unit 35 is composed of a display device such as a CRT (Cathode Ray Tube) or a liquid crystal monitor.
[0036] The input / output unit 36 is an interface for transmitting and receiving data to and from external devices. In accordance with instructions from the CPU 31, the input / output unit 36 outputs a detection command signal to the detection element 5 and inputs a detection signal from the detection element 5. The input detection signal is stored in the main memory 32 or the external memory 33, or displayed on the display unit 35.
[0037] The communication unit 37 is an interface for data communication. Data communication with an external device is possible via the communication unit 37. For example, if the storage device 3 is configured as an external device, data is written to and read from the storage device 3 through data communication via the communication unit 37.
[0038] The functions of the identification unit 11 can be implemented in a computer system consisting of one or more computers including one or more processors and one or more storage devices including non-transitory storage media. The multiple computers realize the functions of the identification unit 11 while communicating with each other via a communication network. For example, some of the functions of the identification unit 11 may be implemented in one computer, and other parts may be implemented in other computers.
[0039] Next, the operation of the identification system 1 according to this embodiment will be described. This operation executes the identification method. The identification system 1 operates in one of two operation modes. The first operation mode is a registration mode in which data for identifying the type of the emission source T is generated and stored in the storage device 3. The second operation mode is an identification mode in which the data stored in the storage device 3 is referenced and the type of the emission source T is identified based on the detection results detected by the multiple detection elements 5.
[0040] [Registration Mode Processing] First, the registration mode processing (registration mode processing) will be described. In the registration mode, a variable m is used. The variable m takes on any value from 1 to M (M is a natural number equal to or greater than 2). This value indicates a source T whose type is currently known as the identification target.
[0041] In the registration mode process, as shown in FIG. 6, the recognition unit 11 first initializes a variable m to 0 (step S1), and then increments the variable m by 1 (step S2).
[0042] Next, the generation unit 22 constituting the identification unit 11 inputs information on the type of the generation source T (step S3). Here, for example, it is input that the type of the generation source T is G[1]. Here, for example, "apple" is registered as G[1].
[0043] Next, the identification unit 11 waits until the source T of a known type becomes detectable, i.e., until detection preparation is complete (Step S4; No). Specifically, after the multiple detection elements 5 in the detection unit 10 are set to a state in which they have not reacted with the respective substances to be identified, i.e., an initialized state, the source T of the type input in Step S3 (G[1] when m = 1) is placed near the detection unit 10, and the substance emitted from the source T becomes detectable by the multiple detection elements 5, detection preparation is considered to be complete. Here, the generation unit 22 is awaiting a user operation input, and when an operation input indicating completion is performed, it is determined that detection preparation is complete.
[0044] When the detection preparation is completed (Step S4; Yes), the identification unit 11 causes the plurality of detection elements 5 to detect a substance emitted from the source T whose type is known (Step S5). As a result, data including the detection value and identification information of the substance emitted from the source T whose type is known is sent from the detection elements 5 to the conversion unit 20 of the identification unit 11.
[0045] When data is input from the detection elements 5, the conversion unit 20 of the identification unit 11 generates information indicating the order of the multiple detection elements 5 based on the magnitude of the detection values output from the multiple detection elements 5 (step S6). As a result, for example, as shown in Fig. 4, for the source T (type G[1]), information indicating the order of the multiple detection elements 5, such as D[1], D[3], D[2], D[4], and D[5], is generated in descending order of the detection values.
[0046] Next, the generating unit 22 of the identifying unit 11 associates the order generated by the converting unit 20 with the information indicating the type of the input generation source T, and registers them in the storage device 3 (step S7).
[0047] Next, the identification unit 11 determines whether the variable m is M (step S8). If the variable m is not M (step S8; No), the identification unit 11 returns to step S2. Subsequently, the following steps are performed: incrementing the variable m (step S2; m = 2), inputting information about the source G[2] (step S3), waiting for completion of detection preparation, including initialization of the detection elements 5 (step S4), detecting substances emitted from the source G[2] using the multiple detection elements 5 (step S5), generating order information (step S6), registering (step S7), and determining the variable m (step S8). Furthermore, steps S2 to S8 are performed for m = 3 to M, generating an order for the multiple detection elements 5, and storing information indicating the order in the storage device 3 in association with the types of the source T G[3] to G[M]. If the identification unit 11 determines that the variable m is M (step S8; Yes), the identification unit 11 terminates the registration mode process.
[0048] [Identification Mode] Next, the processing in the identification mode (identification mode processing) will be described. In the identification mode processing, as shown in Fig. 7 , first, the identification unit 11 initializes the multiple detection elements 5 and then prepares for detection (step S21). Here, the detection unit 10 is brought close to a source T to be identified, the type of which is unknown. Next, the identification unit 11 causes the multiple detection elements 5 to detect substances emitted from the source T to be identified (step S22). The multiple detection elements 5 send data including their respective detection values and identification numbers to the identification unit 11.
[0049] Next, the conversion unit 20 of the identification unit 11 generates information indicating the order of the multiple detection elements 5 based on the magnitudes of the detection values output from the multiple detection elements 5 (step S23). As a result, for example, as shown in Fig. 3, information indicating the order of the multiple detection elements 5, such as D[1], D[3], D[2], D[4], and D[5], is generated in descending order of the detection values.
[0050] Next, the identification unit 21 compares the order generated by the conversion unit 20 with the order stored in the storage device 3, reads out from the storage device 3 the type of source T whose order matches, and identifies the source T (step S24). For example, as shown in Fig. 3, G[1] is identified as the source T whose detection values are D[1], D[3], D[2], D[4], and D[5] in descending order. Thereafter, the identification unit 11 ends the identification mode process.
[0051] As described above in detail, the identification system 1 according to this embodiment identifies the type of substance source T in order of the magnitude of the detection values, rather than the magnitude of the detection values (reaction levels) of the multiple detection elements 5, which are prone to contain errors. In this way, the type of source T can be identified using information that is less prone to contain errors, and therefore the accuracy of identifying the type of source T can be stabilized.
[0052] It is also possible to identify the source T by comparing map data of the magnitudes of the detection values of multiple detection elements 5. However, the map data of the magnitudes of the detection values of the detection elements 5 differs with each detection, and also includes influences and errors due to temperature and humidity, as shown in Fig. 2A, for example. The identification system 1 according to this embodiment reduces the amount of information used for identification and identifies the source T using order as a criterion, thereby improving the accuracy of the identification.
[0053] The ranking of the plurality of detecting elements 5 may include elements having the same magnitude of detected value and the same ranking.
[0054] Second Embodiment Next, a second embodiment of the present invention will be described. The configuration of an identification system 1 according to this embodiment is the same as that of the identification system 1 according to the first embodiment, as shown in Fig. 1. As shown in Fig. 8, the identification system 1 according to this embodiment differs from the identification system 1 according to the first embodiment (see Fig. 6) in the operation of the identification unit 11, particularly the registration mode processing. In the registration mode processing according to this embodiment, the detection elements 5 are narrowed down.
[0055] [Registration Mode Processing] The registration mode processing executed by the identification unit 11 constituting the identification device 2 according to this embodiment will be described. In this registration mode processing, a variable k is used in addition to a variable m. The variable m takes a value between 1 and M, and is a value that indicates the type of known source T, as in the first embodiment. The variable k takes a value between 1 and K (K is a natural number of 2 or greater). This value indicates the number of times the same type of source T has been detected. The maximum value K of k can be set to a value according to the number of samples that provide a statistically sufficient number of samples.
[0056] In the registration mode process, as shown in FIG. 8, the recognition unit 11 first initializes a variable m to 0 (step S1), increments the variable m by 1, and initializes a variable k to 1 (step S9).
[0057] Next, the generation unit 22 constituting the identification unit 11 inputs information on the type of the source T (step S3). Here, for example, the input information indicates that the source T is G[1]. Next, the identification unit 11 waits until the source T, whose type is known, is in a state where it can be detected, that is, until detection preparation is complete (step S4; No). After initializing the multiple detection elements 5, the user brings the detection unit 10 close to the source T to be identified, thereby completing detection preparation.
[0058] When the detection preparation is completed (Step S4; Yes), the identification unit 11 causes the plurality of detection elements 5 to detect a substance emitted from the source T whose type is known (Step S5). As a result, data including the detection value and identification information of the substance emitted from the source T whose type is known is sent from the detection elements 5 to the conversion unit 20 of the identification unit 11.
[0059] When data is input from the detection elements 5, the conversion unit 20 of the identification unit 11 generates information indicating the order of the multiple detection elements 5 based on the magnitude of the detection values output from the multiple detection elements 5 (step S6).
[0060] Next, the generating unit 22 of the identifying unit 11 associates the order generated by the converting unit 20 with the information indicating the type of the input generation source T, and registers them in the storage device 3 (step S7).
[0061] Next, the identification unit 11 determines whether the variable k is K (step S10). Here, since k=1, the determination is negative, and the identification unit 11 increments the variable k by 1 (step S11). The identification unit 11 again performs detection (step S5), order information generation (step S6), and registration (step S7), determines whether the variable k is equal to K (step S10), and if the determination is negative (step S10; No), increments the variable k (step S11). As a result, the reaction levels of the multiple detection elements 5 are detected K times for the same source T (G[1]).
[0062] At each detection, in step S4, the plurality of detection elements 5 are initialized by desorbing the substance. If the detection element 5 has an oscillator, the oscillator is vibrated to desorb the substance.
[0063] When the variable k becomes equal to K (step S10; Yes), the identification unit 11 determines whether the variable m is equal to M (step S8). If the variable m is not equal to M (step S8; No), the identification unit 11 returns to step S9. Thereafter, the following steps are repeated: incrementing the variables m and k and initializing the variables to 1 (step S9), inputting information about the source T (type: G[2]) (step S3), waiting for completion of detection preparation (step S4), detection (step S5), generating sequence information (step S6), registering (step S7), determining the variable k (step S10), and incrementing the variable k (step S11), and thus K substance detections are performed for the source G[2]. When k = K (step S10; Yes), the variable m is judged (step S8), and then substance detection is performed K times for m = 3 to M. Each time, the order of the multiple detection elements 5 is generated, and information indicating the order is associated with the type G[3] to G[M] of the source T and stored (registered) in the memory device 3.
[0064] Thereafter, when it is determined that the variable m is M (step S8; Yes), the generation unit 22 of the identification unit 11 determines whether there are detection elements 5 of the same type of source T but with different orders (step S12). For example, as shown in FIG. 9A , if there are multiple detection elements 5 with different orders for the same source T (G[1]), the determination in step S12 is positive. This also includes cases where multiple detection elements 5 change from different orders to the same order.
[0065] If there are no multiple detection elements 5 with different orders for the same generation source T(G[1]) (step S12; No), the identification unit 11 ends the registration mode process.
[0066] On the other hand, if there are multiple detection elements 5 with different orders for the same generation source T(G[1]) (step S12; Yes), the generation unit 22 narrows down the detection elements 5 (step S13). Here, the generation unit 22 excludes the detection elements 5 with different orders.
[0067] The generation unit 22 of the identification unit 11 determines whether the order of the multiple detection elements 5 corresponding to the source T (G[1] to G[M]) is different and distinguishable from other sources T even when elements with different orders are excluded from the order of the multiple detection elements 5, i.e., whether there are multiple detection elements 5 with the same order among the sources T (step S14). If there are no detection elements T with the same order among the sources T (G[1] to G[M]) (step S14; Yes), the generation unit 22 updates the information indicating the order of the narrowed-down detection elements 5 (step S15), associates the order generated by the conversion unit 20 with the input information indicating the type of the source T, and registers the updated information in the storage device 3 (step S16). For example, if the order of the detection element 5 (D[2]) and the detection element 5 (D[3]) is different as shown in FIG. 9A , the generation unit 22 excludes the detection element 5 (D[2]) and the detection element (D[3]) from the order as shown in FIG. 9B. Thereafter, the recognition unit 11 ends the registration mode process.
[0068] On the other hand, if there are any occurrences of the same order for the sources T (G[1] to G[M]) (step S14; No), the generation unit 22 narrows down the detection elements 5 (step S13). For example, if the order of the narrowed-down detection elements 5 for G[1], G[2], and G[3] is the same, the generation unit 22 individually extracts, from the narrowed-down detection elements 5, combinations of detection elements 5 for which the accuracy rate for G[1] and G[2] is equal to or greater than a threshold. Furthermore, the generation unit 22 individually extracts combinations of detection elements 5 for which the accuracy rate for G[2] and G[3] is equal to or greater than a threshold. As a result, for example, D[1], D[4], and D[5] are extracted as combinations of detection elements 5 for distinguishing G[1] from G[2], and these are finally ranked. Furthermore, for example, D[1], D[7], and D[8] are extracted as combinations of detection elements 5 for distinguishing G[2] from G[3], and these are finally ranked.
[0069] After step S13 is completed, the generation unit 22 performs steps S14, S15, and S16, and the identification unit 11 ends the registration mode process.
[0070] In this way, if there are different sources T with the same order (step S12; No), the generation unit 22 narrows down the detection elements 5 (step S13), but may change the threshold value of the accuracy rate used to narrow down the detection elements 5, and repeat the narrowing down process until there are no more detection elements with the same order (step S13; Yes).
[0071] In this way, in this embodiment, when detection is performed multiple times using multiple detection elements 5 for known sources of the same type, if there is a detection element 5 whose order of the magnitude of the detection values changes, and even if that detection element 5 is excluded, the order of the remaining detection elements 5 does not overlap between sources T, the generation unit 22 narrows down to the remaining detection elements 5 and generates information indicating the order of the detection elements 5.
[0072] The identification unit 21 of the identification unit 11 identifies the type of source T of the substance based on information indicating the order of the detection elements 5 when the substance was detected by the detection elements 5 narrowed down by the generation unit 22. The identification mode process executed by the identification unit 11 is the same as the identification mode process (see FIG. 7 ) of the identification system 1 according to the first embodiment. That is, preparation for detection is performed for a source T of unknown type (step S21), the substance is detected by the plurality of detection elements 5 (step S22), order information is generated (step S23), and the order information is collated to identify the source T (step S24).
[0073] As described above, according to the identification system 1 of this embodiment, if detection is performed multiple times for the same type of source T, and some of the detection elements are in a different order, and even if the detection elements 5 with the different order are excluded, the order of the elements is different for all sources T and identification is possible, then those elements are excluded from the elements used for identification. This makes it possible to reduce the number of detection elements 5 actually used for identification. As a result, the identification unit 11 identifies the type of source T of the substance based on information indicating the order of the detection elements 5 when the substance was detected by the detection elements 5 narrowed down by the generation unit 22, so the number of detection elements 5 can be reduced.
[0074] Next, a third embodiment of the present invention will be described. The configuration of an identification system 1 according to this embodiment is the same as that of the identification systems 1 according to the first and second embodiments shown in FIG. 1. The identification system 1 according to this embodiment differs from the identification system 1 according to the second embodiment (see FIG. 8) in the operation of the identification unit 11, particularly the registration mode process. In the registration mode process executed by the identification unit 11 according to this embodiment, a plurality of detection elements 5 are grouped.
[0075] [Registration mode processing] As shown in Figure 10, in the registration mode processing, the processing flow from steps S1, S9, S3 to S7, S10, S11, and S8 is the same as the registration mode processing of the identification system according to the second embodiment, and therefore the description thereof will be omitted.
[0076] Thereafter, when it is determined that the variable m is M (step S8; Yes), the generation unit 22 of the identification unit 11 determines whether there are detection elements 5 of the same type of source T, in which the order of magnitude of the detection values changes (step S12). For example, as shown in FIG. 11A , if there are multiple detection elements 5 of the same type of source T (G[1]), in which the order of the successive values changes, the determination in step S12 is positive.
[0077] For the same source T (G[1]), if the order of the magnitudes of the detection values of multiple detection elements 5 is reversed or there are no identical detection values for sources T of the same type (step S12; No), the identification unit 11 terminates the registration mode processing.
[0078] On the other hand, for the same source T (G[1]), if there are multiple detection elements 5 of the same type of source T where the order of the magnitude of the detection values changes (step S12; Yes), the generation unit 22 groups the detection elements 5 with consecutive orders among the detection elements whose order changes (step S17).
[0079] For example, as shown in FIG. 11A , if the order of the magnitudes of the detection values of the detection elements 5 is different for the same source T (type G[1]), the generation unit 22 of the identification unit 11 groups the detection elements 5 whose order changes into a group [A, I, U] as shown in FIG. 11B . The information [A, I, U] that identifies the group can be set by user input. For example, [A, B, C] can be defined as [1, 2, 3].
[0080] After step S17, the generation unit 22 determines whether the order of the sources T is different even after grouping the detection elements 5, and whether the sources T can be distinguished from other sources T (step S18). If the order of the sources T is different even after grouping (step S18; Yes), the generation unit 22 updates the order information of the grouped detection elements 5 (step S15) and registers them (step S7). Thereafter, the identification unit 11 ends the registration mode process.
[0081] If grouping results in overlapping orders and the source cannot be distinguished from other sources T (step S18; No), the generation unit 22 performs grouping again (step S17), but changes the threshold value for grouping the detection elements 5 (the same as the threshold value for the accuracy rate) and repeats this process until there are no more detection elements with the same order (step S18; Yes).
[0082] In this way, in this embodiment, when detection is performed multiple times using multiple detection elements 5 for a known source T of the same type, if there are detection elements 5 whose order of detection value magnitude changes, and even if these detection elements 5 are grouped, the order is different among the sources T and they can be distinguished from other known sources T, the generation unit 22 groups the detection elements 5 whose order changes and whose order is continuous, and generates information indicating the order of the group of detection elements 5.
[0083] The identification unit 21 of the identification unit 11 identifies the type of source T of the substance based on information indicating the order of the groups of detection elements 5 when the substance was detected by the detection elements 5 of each group, generated by the generation unit 22. The identification mode process executed by the identification unit 11 is the same as the identification mode process (see FIG. 7 ) of the identification system 1 according to the first embodiment. That is, preparation for detection is performed for a source T of unknown type (step S21), the substance is detected by the multiple detection elements 5 (step S22), order information is generated (step S23), and the order information is compared to identify the type of source T (step S24).
[0084] As described above, according to the identification system 1 of this embodiment, when detection is performed on the same type of source T multiple times, and some of the detection elements T change order, and even if the detection elements 5 whose order changes are grouped together, if there are no detection elements 5 whose groups are in the same order for different types of sources T, the detection elements 5 are grouped. This makes it possible to reduce the number of detection elements 5 actually used for identification, as only one detection element 5 is required in the same group. The identification unit 11 identifies the type of source T of a substance based on information indicating the group of detection elements 5 when a substance is detected by the detection elements 5 grouped by the generation unit 22.
[0085] Fourth Embodiment Next, a fourth embodiment of the present invention will be described. The configuration of an identification system 1 according to this embodiment is the same as that of the identification systems 1 according to the first, second, and third embodiments shown in FIG. 1. The identification system 1 according to this embodiment differs from the identification system 1 according to the second embodiment (see FIG. 8) in the operation of the identification unit 11, particularly in the registration mode processing. In the registration mode processing of this embodiment, the sources T are grouped.
[0086] [Registration mode processing] As shown in Figure 12, in the registration mode processing, the processing flow from steps S1, S9, S3 to S7, S10, S11, and S8 is the same as the registration mode processing of the identification system according to the second embodiment, and therefore the description thereof will be omitted.
[0087] Thereafter, when it is determined that the variable m is M (step S8; Yes), the generation unit 22 of the identification unit 11 determines whether there are sources T of different types that have the same order of magnitude of the detection values of the multiple detection elements 5 (step S30). For example, as shown in FIG. 13A , if there are sources T (type G[1]) and T (type G[2]) that have the same order of magnitude of the detection values of the multiple detection elements 5, the determination in step S30 is positive.
[0088] If the order of the detection elements 5 is the same and there are no different sources T (step S30; No), the identification unit 11 ends the registration mode process.
[0089] On the other hand, if there are sources T of different types that have the same order of magnitude of the detection values of the detection elements 5 (step S30; Yes), the generation unit 22 determines whether or not to group the sources T (step S31). Whether or not to group the sources T can be set in advance.
[0090] If grouping is not to be performed (step S31; No), the identification unit 11 ends the registration mode process. On the other hand, if grouping is to be performed (step S31; Yes), the generation unit 22 of the identification unit 11 performs grouping (step S32). For example, as shown in FIG. 13A , if the order of magnitude of the detection values of the detection elements 5 is the same for source T (type G[1]) and source T (G[2]), the generation unit 22 combines both into one record as group IG[1], as shown in FIG. 13B .
[0091] The group IG[1] can be set by user input. For example, if G[1] is "mandarin orange" and G[2] is "grapefruit," the group IG[1] can be set as "citrus fruits." The registrations of G[1] and G[2] are deleted.
[0092] After step S32 is completed, the identification unit 11 ends the registration mode process. In this way, when detection is performed on multiple known sources of different types using multiple detection elements 5, the generation unit 22 groups the sources T having the same order of the detection elements 5, and generates information indicating the order of the detection elements 5 in association with the group.
[0093] The identification unit 21 of the identification unit 11 refers to the information generated by the generation unit 22 indicating the relationship between the order of the multiple detection elements 5 and the type of the group of known source T, and identifies the type of source T of the substance based on the information indicating the order of the multiple detection elements 5 when the multiple detection elements 5 detected the substance. The identification mode process executed by the identification unit 11 is the same as the identification mode process (see FIG. 7 ) of the identification system 1 according to the first embodiment. That is, preparation for detection is performed for a source T of unknown type (step S21), the multiple detection elements 5 detect the substance (step S22), order information is generated (step S23), and the order information is compared to identify the type of source T (step S24).
[0094] As described above, according to the identification system 1 of the present embodiment, when different types of sources T have the same order of the detection elements 5, the different types of sources T can be grouped together. As a result, for example, when identifying a new variety of mandarin orange as an unknown source T, even if it cannot be identified as a mandarin orange, it may be possible to identify it as a citrus fruit.
[0095] Fifth Embodiment Next, a fifth embodiment of the present invention will be described. The configuration of an identification system 1 according to this embodiment is the same as that of the identification system 1 according to the first embodiment shown in Fig. 1, except for the information stored in the storage device 3. The identification system 1 according to this embodiment differs from the identification system 1 according to the first embodiment (see Fig. 6) in the operation of the identification unit 11, particularly the registration mode processing.
[0096] The identification system 1 according to the present embodiment identifies the state of the source T as the specific information instead of the type of the source T. For example, if the source T is a fruit, the fruit will progress from a prematurely ripe state, through a fully ripe state, and then to a decayed state. The identification system 1 according to the present embodiment identifies such a state of the source T, for example, a change over time.
[0097] Here, the states of the source T are represented by C[1], C[2], C[3], ..., C[J]. As shown in Fig. 14, the storage device 3 stores information indicating the order of the magnitude of the detection values of the multiple detection elements 5 for each of the states C[1], C[2], C[3], ..., C[J] of the source T. The information is stored in the storage device 3 by a registration mode process executed by the generation unit 22 of the identification unit 11.
[0098] [Registration Mode Processing] The registration mode processing executed by the identification unit 11 will now be described. In the registration mode, j is used as a variable. The variable j takes on any value from 1 to J. This value indicates the current state of the target source. In the registration mode processing, as shown in FIG. 15, first, in the identification unit 11, the conversion unit 20 initializes the variable j to 0 (step S41) and increments the variable j by 1 (step S42).
[0099] The generating unit 22 constituting the identifying unit 11 receives information indicating the state of the source T, i.e., source state information (step S43). Here, for example, the input information indicates that the state of the source T is C[1]. Next, the identifying unit 11 waits until the known state of the source T becomes detectable, i.e., until detection preparation is complete (step S44; No). Here, the identifying unit 11 waits until detection preparation is complete for the state of the source T, C[1].
[0100] When the detection preparation is completed (Step S44; Yes), the identification unit 11 causes the plurality of detection elements 5 to detect the substance emitted from the source T (state C[1]) (Step S45). As a result, data including the detection value and identification information of each detection element 5 is sent from the detection elements 5 to the conversion unit 20 of the identification unit 11.
[0101] When data is input from the detection elements 5, the conversion unit 20 generates information indicating the order of the multiple detection elements 5 based on the magnitude of the detection values output from the multiple detection elements 5 (step S46). As a result, for example, for the source T (state C[1]), information indicating the order of the multiple detection elements 5, such as D[1], D[3], D[2], D[4], and D[5], is generated in descending order of the detection values.
[0102] Next, the generating unit 22 associates the order generated by the converting unit 20 with the input information indicating the state of the generation source T, and registers them in the storage device 3 (step S47).
[0103] Here, the generation unit 22 determines whether the variable j is J (step S48). If the variable j is not J (step S48; No), the identification unit 11 returns to step S42. Subsequently, the following steps are performed: setting j = 2 (step S42), inputting information about the source T (state C[2]) (step S43), waiting for completion of detection preparation (step S44), detection (step S45), generating order information (step S46), registering (step S47), and determining the variable j (step S48). Furthermore, the order of the multiple detection elements 5 is generated for the states C[j] (j = 3 to J) of the source T, and information indicating the order is stored in the storage device 3 in association with the states C[3] to C[J] of the source T. If the identification unit 11 determines that the variable j is J (step S48; Yes), the identification unit 11 terminates the registration mode process.
[0104] 16 , the identification mode process according to this embodiment is the same as the identification mode process of the identification system 1 according to the first embodiment in that detection preparation is performed for a source T whose state is unknown (step S21), material detection is performed by the multiple detection elements 5 (step S22), and sequence information is generated (step S23). After executing step S23, the generation unit 22 of the identification unit 11 compares the sequence information with the sequence information stored in the storage device 3 to identify the state of the source T (step S25).
[0105] As described above, according to the identification system 1 of this embodiment, the state of the substance source T is identified not by the detection values of the multiple detection elements 5, which are prone to contain errors, i.e., not by the magnitude of the detection values, but by the order of the magnitude of the detection values. In this way, the source T can be identified using information that is less prone to contain errors, and the accuracy of identifying the state of the source T can be stabilized.
[0106] In the identification system 1 according to this embodiment, similarly to the second to fourth embodiments, it is possible to narrow down or group the detection elements 5 and group the generation sources T.
[0107] Sixth Embodiment Next, a sixth embodiment of the present invention will be described. The identification system 1 according to this embodiment identifies the type or state of the emission source by taking into consideration not only the order of the plurality of detection elements 5 but also map data of normalized detection values.
[0108] 17 , the configuration of the identification system 1 according to this embodiment is the same as the configuration of the identification system 1 according to the first embodiment (see FIG. 1 ). In this identification system 1, the generation unit 12 of the identification unit 11 generates normalized map data indicating normalized detection values when detected by the multiple detection elements 5 for multiple known sources T (G[1] to G[N]) of different types, in association with the types of the known sources, and stores the normalized map data in the storage device 3. Note that this normalization is performed using a reference value of 1 for the maximum value of the detection values, the difference between the minimum value and the maximum value, etc.
[0109] The identification unit 21 of the identification unit 11 refers to the information generated by the generation unit 22 indicating the relationship between the order of the detection elements 5 and the source T of known type, as well as the information indicating the relationship between the normalized detection values of the detection elements 5 and the known source T, and identifies the type of the source T of the substance based on the information indicating the order of the detection elements 5 when the substance is detected by the multiple detection elements 5, as well as the normalized detection values of the detection elements 5 when the substance is detected by the multiple detection elements 5. For example, even if the order of the magnitudes of the detection values of the multiple detection elements 5 is the same for source T (type G[1]) and source T (type G[2]) as shown in FIG. 18A , the identification unit 21 can compare the differences in the normalized map data with map data of a source T of unknown type, as shown in FIG. 18B , and identify the source T whose map data has the closest shape (high similarity by pattern matching).
[0110] The process that takes into consideration not only the order of magnitude of the detection values of the plurality of detection elements 5 but also the normalized map data can be applied to identifying the state of the source T. It is also possible to use map data based on non-normalized detection values.
[0111] Seventh Embodiment Next, a seventh embodiment of the present invention will be described. In this embodiment, a detailed configuration of a detector 50 corresponding to the detection unit 10 constituting the identification system 1 will be described.
[0112] 19A , the detector 50 includes a detector main body 6, a sensor module 7, and a sensor cover 8. The sensor module 7 is attached to the detector main body 6, which is configured to be able to input and output data from and to the identification unit 11, and the sensor cover 8 protects the sensor module 7 attached to the detector main body 6.
[0113] As shown in Figure 19B, a total of 20 detection elements 5 are formed on the sensor module 7. Each detection element 5 has an oscillator formed to block a portion of a through-hole, and a substance adsorption film is formed on the oscillator. The multiple detection elements 5 formed on the sensor module 7 are capable of detecting different substances. Each detection element 5 detects a substance, and the detection value is output to the detector main body 6 together with the identification number of the detection element 5. The detector main body 6 outputs data including the detection value and the identification number to the identification unit 11.
[0114] In this way, in the detection unit 10, the sensor module 7 can be replaced with respect to the detector main body 6. By replacing the sensor module 7, it is possible to significantly increase the types of detection elements 5 that can be used for detection. Furthermore, a sensor module 7 equipped with detection elements 5 that can detect multiple substances contained in the source T to be identified can be selected, attached to the detector main body 6, and used. This makes it possible to configure an identification device 2 that has only the detection elements 5 necessary to identify the identification target, excluding the detection elements 5 necessary to identify the identification target, as in the second embodiment above. Furthermore, it is possible to configure an identification device 2 that has only the detection elements 5 of each group, as in the third embodiment above.
[0115] The identification unit 11 can be constructed on a computer that can communicate with the detection unit 10 via a communication network. The same applies to the storage device 3. The storage device 3 can also be constructed on another server computer that can communicate with this computer. Conversely, the identification unit 11 may be incorporated into the device shown in Fig. 19A, and the storage device 3 may also be incorporated therein.
[0116] Furthermore, the identification unit 11 may include either the identification unit 21 or the generation unit 22. The developer of the identification system 1 may use the identification device 2 including the generation unit 22 to generate information to be stored in the storage device 3, and the user may use the identification device 2 including the identification unit 21 to identify the type or state of a source T whose type or state is unknown. In other words, the generation unit 22 does not need to be included in the identification unit 11.
[0117] It is also possible to identify both the type and state of the generation source T. The storage device 3 may store information indicating the order of the magnitude of the detection value of the detection element 5 for each type and state of the generation source T.
[0118] Furthermore, even if there are sources T with the same characteristic information but different rankings of the detection elements 5, they may simply be stored as they are in the storage device 3. Furthermore, sources T with different characteristic information but the same ranking of the detection elements 5 may also be stored as they are in the storage device 3. In this case, the corresponding source T may be used as the identification result.
[0119] The detecting elements 5 that did not react to the source T to be identified can be removed from the detecting unit 10 when identifying the unknown source T.
[0120] The hardware and software configurations of the recognition unit 11 are merely examples and can be changed and modified as desired.
[0121] The core processing portion of the identification unit 11, which is composed of the CPU 31, main memory 32, external memory 33, operation unit 34, display unit 35, input / output unit 36, communication unit 37, and internal bus 38, can be realized using an ordinary computer system, rather than a dedicated system. For example, the identification unit 11 that executes the above processing may be configured by storing and distributing a computer program for executing the above operations on a computer-readable recording medium (such as a flexible disk, CD-ROM, or DVD-ROM), and installing the computer program on a computer. Alternatively, the identification unit 11 may be configured by storing the computer program in a storage device of a server device on a communication network such as the Internet, and then downloading the program to an ordinary computer system.
[0122] When the functions of the identification unit 11 are realized by sharing the functions between an OS (operating system) and an application program, or by cooperation between the OS and the application program, only the application program portion may be stored in a recording medium or storage device.
[0123] It is also possible to superimpose a computer program on a carrier wave and distribute it over a communication network. For example, the computer program may be posted on a bulletin board system (BBS) on the communication network and distributed over the network. The computer program may then be started and executed under the control of an OS in the same way as any other application program, thereby enabling the above-mentioned processing to be performed.
[0124] This invention allows various embodiments and modifications without departing from the broad spirit and scope of this invention. Furthermore, the above-described embodiments are intended to explain this invention and do not limit the scope of this invention. That is, the scope of this invention is defined by the claims, not the embodiments. Various modifications made within the scope of the claims and the meaning of the invention equivalent thereto are considered to be within the scope of this invention.
[0125] In addition, this application claims priority based on Japanese Patent Application No. 2023-91233 filed on June 1, 2023, and the entire specification, claims, and drawings of Japanese Patent Application No. 2023-91233 are incorporated herein by reference.
[0126] The present invention can be applied to identifying sources by the substances emitted by the source.
[0127] REFERENCE SIGNS LIST 1 Identification system, 2 Identification device, 3 Storage device, 5 Detection element, 6 Detector body, 7 Sensor module, 8 Sensor cover, 10 Detection unit, 11 Identification unit, 20 Conversion unit, 21 Identification unit, 22 Generation unit, 31 CPU, 32 Main memory, 33 External memory, 34 Operation unit, 35 Display unit, 36 Input / output unit, 37 Communication unit, 38 Internal bus, 39 Program, 50 Detector, T Generation source
Claims
1. An identification device comprising: a plurality of detection elements that react to different types of substances out of a plurality of types of substances emitted from a source, and output detection values whose magnitude corresponds to the amount of the reacted substance; and an identification unit that identifies the characteristic information of the source of a substance based on information indicating the order of the plurality of detection elements when a substance is detected by the plurality of detection elements, with reference to information indicating the relationship between the order of the plurality of detection elements, which are ordered by the magnitude of each detection value when the plurality of detection elements detect a substance emitted from a source whose characteristic information indicating a type or state is known, and the characteristic information of the known source.
2. The identification device according to claim 1, wherein the substance includes a substance that causes the sensor to sense an odor.
3. An identification system comprising: a plurality of detection elements that react to different types of substances emitted from a source and output detection values having magnitudes corresponding to the amount of the reacted substance; a generation unit that generates information indicating the order of the plurality of detection elements, which are ordered by the magnitude of the detection values when detected by the plurality of detection elements, for a plurality of known sources having different characteristic information indicating type or state, in association with the characteristic information of the known sources; and an identification unit that identifies the characteristic information of the source of a substance based on the information indicating the order of the plurality of detection elements when a substance is detected by the plurality of detection elements, by referring to the information generated by the generation unit that indicates the relationship between the order of the plurality of detection elements and the characteristic information of the known sources.
4. The identification system described in claim 3, wherein when detection is performed multiple times with the multiple detection elements for a known source with the same characteristic information, if there is a detection element for which the order of the magnitude of the detection values changes and the order of the remaining detection elements does not overlap between sources even if that detection element is excluded, the generation unit narrows down to the remaining detection elements and generates information indicating the order of the detection elements, and the identification unit identifies the characteristic information of the source of the substance based on the information indicating the order of the detection elements when the substance is detected with the detection elements narrowed down by the generation unit.
5. The identification system described in claim 3, wherein when detection is performed multiple times with the multiple detection elements for a known source with the same characteristic information, if there are detection elements whose order of detection value magnitude changes and the order does not overlap between sources even when the detection elements are grouped, the generation unit groups the detection elements whose order changes and whose order is consecutive, and generates information indicating the order of the groups of the detection elements; and the identification unit identifies the characteristic information of the source of the substance based on the information indicating the order of the detection elements when the substance is detected by the detection elements of each group generated by the generation unit.
6. The identification system of claim 3, wherein the generation unit, when detection with the multiple detection elements is performed on multiple known sources having different characteristic information, groups sources having the same order of the detection elements and generates information indicating the order of the detection elements in association with the group; and the identification unit refers to the information generated by the generation unit indicating the relationship between the order of the multiple detection elements and the characteristic information of the group of known sources, and identifies the characteristic information of the group of sources of the substance based on the information indicating the order of the multiple detection elements when the substance is detected by the multiple detection elements.
7. The identification system described in claim 3, wherein the generation unit generates information indicating detection values when detected by the multiple detection elements for multiple known sources having mutually different characteristic information, in association with the characteristic information of the known sources, and the identification unit refers to the information generated by the generation unit indicating the relationship between the order of the detection elements and the characteristic information of the known sources, as well as information indicating the relationship between the detection values of the detection elements and the characteristic information of the known sources, and identifies the characteristic information of the source of the substance based on the detection values of the detection elements when the substance is detected by the multiple detection elements, together with information indicating the order of the detection elements when the substance is detected by the multiple detection elements.
8. An identification method executed by an identification device that identifies a source using multiple detection elements that react to different types of substances out of multiple types of substances emitted from a source and output detection values of magnitudes corresponding to the amount of the reacted substance, wherein the method identifies the characteristic information of the source of a substance based on information indicating the order of the multiple detection elements when the multiple detection elements detect a substance emitted from known sources having different characteristic information indicating type or state, by referring to information indicating the relationship between the order of the multiple detection elements, which are ordered by the magnitude of each detection value when the multiple detection elements detect the substance emitted from the known sources, and the characteristic information of the known sources.
Citation Information
Patent Citations
Chemical sensor device, and material measuring device equipped with it
JP2009204584A
Game machine
JP2023091233A
Chemical sensor for detecting odor
JP1989244335A
Method of identifying chemical / Physical value and device therefor
JP1995198641A
Smell discrimination device
JP2005077099A
