Monitoring system and method based on spectrum sensing

Abstract

The present invention discloses a monitoring system and method based on spectrum sensing, which relates to the technical field of radio signal monitoring. The method collects radio signal sequences in the environment in real time through spectrum sensing equipment, processes and analyzes the collected radio signal sequences, and extracts spectrum usage characteristics; uses an abnormal detection algorithm to analyze the spectrum usage characteristics and identify normal signals and abnormal signals; when an abnormal signal is identified, an alarm is generated and the spectrum usage characteristics of the abnormal signal are recorded. By using an abnormal detection algorithm to analyze the spectrum usage characteristics, normal signals and abnormal signals can be accurately identified, which significantly improves the accuracy of spectrum sensing, and uses signal strength, signal frequency and timestamp to extract spectrum mutation characteristics and frequency drift characteristics, so that the detection results are more accurate and reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of radio signal monitoring, and in particular to a monitoring system and method based on spectrum sensing. Background Art

[0002] With the rapid development of wireless communication technology, spectrum resources are becoming increasingly scarce. Therefore, spectrum sensing technology, as an important means to effectively utilize spectrum resources, has received widespread attention. At present, spectrum sensing technology is mainly used in fields such as dynamic spectrum access (DSA) and cognitive radio (CR). Its main goal is to improve spectrum utilization by detecting idle frequency bands. However, there are some shortcomings in existing spectrum sensing technology, which are mainly manifested in the following aspects: Low detection accuracy: The existing spectrum sensing technology has low detection accuracy in complex environments and is easily affected by noise and interference, resulting in frequent false detection and missed detection. Poor real-time performance: Many spectrum sensing methods require a long processing time and cannot meet the needs of real-time monitoring, especially in rapidly changing radio environments. High resource consumption: Existing spectrum sensing methods usually require a lot of computing resources and energy, especially on portable devices. This high consumption limits the application scope of spectrum sensing technology. Summary of the invention

[0003] Based on the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a monitoring system and method based on spectrum sensing to solve the above-mentioned technical problems.

[0004] To achieve the above object, the present invention provides the following technical solution: a monitoring method based on spectrum sensing, comprising:

[0005] The spectrum sensing device collects radio signal sequences in the environment in real time, processes and analyzes the collected radio signal sequences, and extracts spectrum usage characteristics;

[0006] Anomaly detection algorithms are used to analyze spectrum usage characteristics and identify normal and abnormal signals;

[0007] When an abnormal signal is identified, an alarm is generated and the spectrum usage characteristics of the abnormal signal are recorded.

[0008] The present invention is further configured to collect data in a radio signal sequence in an environment, including: signal strength, signal frequency and time stamp.

[0009] The present invention is further configured to process and analyze the collected radio signal sequence to extract spectrum usage characteristics, including:

[0010] De-noising, normalizing and interpolating the collected radio signal sequence;

[0011] Extract spectrum mutation features based on signal strength and corresponding timestamps;

[0012] The frequency drift feature is extracted based on the signal frequency and the corresponding timestamp.

[0013] The present invention is further configured to extract spectrum mutation features according to signal strength, including: obtaining signal strength and corresponding timestamps, generating a signal strength sequence, calculating a forward spectrum mutation value and a reverse spectrum mutation value according to the signal strength sequence, and setting the maximum of the forward spectrum mutation value and the reverse spectrum mutation value as the spectrum mutation feature, wherein the calculation logic of the forward spectrum mutation value is: The calculation logic of the reverse spectrum mutation value is: is the positive spectrum mutation value at time t in the signal intensity sequence, is the positive spectrum mutation value at time t-1 in the signal intensity sequence, x t is the signal strength at time t in the signal strength sequence, μ is the expected value of the signal strength sequence, and K is the sensitivity factor, which is a preset constant. is the reverse spectrum mutation value at time t in the signal intensity sequence, is the reverse spectrum mutation value at time t-1 in the signal intensity sequence.

[0014] The present invention is further configured to extract frequency drift according to signal frequency, including: obtaining signal frequency and corresponding timestamp, generating signal frequency sequence, performing Fourier transform on the signal frequency sequence to obtain frequency drift characteristics, wherein the logic of performing Fourier transform on the signal frequency sequence is: F(ω) is the frequency drift characteristic, ω is the signal frequency angular frequency, and the calculation logic of ω is: ω=2πf, f is the signal frequency, N is the number of signal frequencies in the signal frequency sequence, f i is the value of the i-th signal frequency in the signal frequency sequence, j is an imaginary unit, t i is the timestamp of the i-th signal frequency in the signal frequency sequence.

[0015] The present invention is further configured to construct a logic of anomaly detection algorithm, including:

[0016] Use the radio signal sequence data corresponding to the normal signal to build a training set, and extract the spectrum mutation characteristics and frequency drift characteristics of the training set;

[0017] Randomly select any one of the spectrum mutation feature and the frequency drift feature, set it as the first feature, and randomly select a feature value from the first feature, set it as the first random segmentation value, recursively segment until the data points in the training set are segmented into leaf nodes, and obtain a first isolated tree;

[0018] Select another feature, set it as the second feature, and randomly select a feature value from the second feature, set it as the second random segmentation value, recursively segment until the data points in the training set are segmented into leaf nodes, obtain the second isolated tree, and set the first isolated tree and the second isolated tree as the isolated tree set;

[0019] The extracted spectrum mutation features and frequency drift features are input into the isolated tree set, and the average path length is calculated. When the average path length is greater than the preset anomaly score, it is identified as an abnormal signal; when the average path length is less than or equal to the preset anomaly score, it is identified as a normal signal.

[0020] The present invention is further configured such that the calculation logic of the average path length is: h(x) is the average path length, |T| is the size of the isolated tree set, that is, the number of isolated trees, x is the data point to be detected, including spectrum mutation characteristics and frequency drift characteristics, ∑ T PathLrngth(x,T) represents the path length of data point x in the isolated tree T. The path length represents the number of nodes required to reach data point x from the root node. The calculation logic of the preset anomaly score is: s(x,n) is the anomaly score, n is the number of samples, that is, the total number of samples in the training set, and c(n) is the adjustment factor of the average path length. The calculation logic is: H(i) is the i-th harmonic number, and the calculation logic is:

[0021] The present invention also provides a monitoring system based on spectrum sensing, the system comprising:

[0022] Acquisition module: collects radio signal sequences in the environment in real time through spectrum sensing equipment, processes and analyzes the collected radio signal sequences, and extracts spectrum usage characteristics;

[0023] Analysis module: uses anomaly detection algorithms to analyze spectrum usage characteristics and identify normal and abnormal signals;

[0024] Alarm module: When an abnormal signal is identified, an alarm is generated and the spectrum usage characteristics of the abnormal signal are recorded.

[0025] The present invention provides a monitoring system and method based on spectrum sensing. The method collects radio signal sequences in an environment in real time through a spectrum sensing device, processes and analyzes the collected radio signal sequences, and extracts spectrum usage characteristics; uses an anomaly detection algorithm to analyze the spectrum usage characteristics and identify normal signals and abnormal signals; when an abnormal signal is identified, an alarm is generated and the spectrum usage characteristics of the abnormal signal are recorded. The beneficial effects produced include:

[0026] 1. Improve the accuracy of spectrum perception: By using anomaly detection algorithms to analyze spectrum usage characteristics, normal signals and abnormal signals can be accurately identified, significantly improving the accuracy of spectrum perception. Signal strength, signal frequency and timestamp are used to extract spectrum mutation characteristics and frequency drift characteristics, making the detection results more accurate and reliable.

[0027] 2. Enhanced real-time monitoring capabilities: Through real-time processing and analysis of radio signal data, it can quickly identify abnormal signals and generate alarm prompts, significantly enhancing the real-time nature of spectrum monitoring. When an abnormal signal occurs, it can immediately generate an alarm and record the spectrum usage characteristics of the abnormal signal, thereby achieving real-time monitoring and management of the radio environment.

[0028] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0030] Figure 1 A flowchart of a monitoring method based on spectrum sensing is shown as an exemplary embodiment of the present invention;

[0031] Figure 2 The diagram is a structural diagram of a monitoring system based on spectrum sensing according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0033] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0034] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0035] Embodiment 1

[0036] Monitoring methods based on spectrum sensing, such as Figure 1 As shown, including:

[0037] The spectrum sensing device collects radio signal sequences in the environment in real time, processes and analyzes the collected radio signal sequences, and extracts spectrum usage characteristics;

[0038] Anomaly detection algorithms are used to analyze spectrum usage characteristics and identify normal and abnormal signals;

[0039] When an abnormal signal is identified, an alarm is generated and the spectrum usage characteristics of the abnormal signal are recorded.

[0040] Specifically, the spectrum sensing device is a device that can monitor and collect radio signals in real time, including a spectrum analyzer (Spectrum Analyzer), a software-defined radio (Software-Defined Radio, SDR), a radio receiver (Radio Receiver) and a wireless sensor network node (Wireless Sensor Network Node). The spectrum analyzer is used to detect and analyze the spectrum of the radio signal, has high sensitivity and a wide bandwidth, and can display the frequency and strength of the signal in real time. Therefore, in a feasible embodiment of the present invention, the spectrum analyzer is preferably used to collect the radio signal sequence in the environment in real time. The present invention is further configured to collect data in the radio signal sequence in the environment, including: signal strength, signal frequency and timestamp; signal strength (Signal Strength) indicates the power level of the radio signal, in dBm or dB, and the signal strength reflects the strength of the signal, which is used to judge the distance and interference of the signal source; signal frequency (Signal Frequency represents the center frequency of the radio signal in Hz. The signal frequency is used to identify different radio signal sources and spectrum usage. Timestamp represents the time point of data collection in seconds or milliseconds. The timestamp is used to analyze the timing characteristics and changes of the signal.

[0041] The present invention is further configured to process and analyze the collected radio signal sequence to extract spectrum usage characteristics, including:

[0042] The collected radio signal sequence is subjected to denoising, normalization and interpolation processing; denoising is intended to eliminate noise in the radio signal sequence and improve the quality and reliability of the signal; normalization converts the signal sequence to the same scale range for easy comparison and processing; interpolation is used to fill in missing values ​​in the data or generate new data points between known data points;

[0043] A spectrum mutation feature is extracted according to the signal strength and the corresponding timestamp. The spectrum mutation feature is used to identify abnormal changes in the spectrum of the radio signal, and the abnormal signal is identified by calculating the mutation point of the signal strength. The present invention is further configured to extract the spectrum mutation feature according to the signal strength, including: obtaining the signal strength and the corresponding timestamp, generating a signal strength sequence, calculating a forward spectrum mutation value and a reverse spectrum mutation value according to the signal strength sequence, and setting the maximum of the forward spectrum mutation value and the reverse spectrum mutation value as the spectrum mutation feature, wherein the calculation logic of the forward spectrum mutation value is: The calculation logic of the reverse spectrum mutation value is: is the positive spectrum mutation value at time t in the signal intensity sequence, is the positive spectrum mutation value at time t-1 in the signal intensity sequence, x t is the signal strength at time t in the signal strength sequence, μ is the expected value of the signal strength sequence, and K is the sensitivity factor, which is a preset constant. is the reverse spectrum mutation value at time t in the signal intensity sequence, is the reverse spectrum mutation value at time t-1 in the signal strength sequence. By calculating the forward and reverse spectrum mutation values, the mutation of signal strength can be detected in real time, thereby identifying abnormal signals. Abnormal signals usually manifest as sudden changes in signal strength, which will cause a significant increase in the forward or reverse spectrum mutation value.

[0044] A frequency drift feature is extracted according to the signal frequency and the corresponding timestamp. The frequency drift feature is used to analyze the characteristics of the signal frequency changing over time, and the change of the signal frequency is extracted by Fourier Transform. The present invention is further configured to extract the frequency drift according to the signal frequency, including: obtaining the signal frequency and the corresponding timestamp, generating a signal frequency sequence, and performing Fourier transform on the signal frequency sequence to obtain the frequency drift feature, wherein the logic of performing Fourier transform on the signal frequency sequence is: F(ω) is the frequency drift characteristic, ω is the signal frequency angular frequency, and the calculation logic of ω is: ω=2πf, f is the signal frequency, N is the number of signal frequencies in the signal frequency sequence, f i is the value of the i-th signal frequency in the signal frequency sequence, j is an imaginary unit, t i is the timestamp of the ith signal frequency in the signal frequency sequence. Through Fourier transform, the drift and change of the signal frequency can be accurately identified, thereby detecting abnormal signals on the frequency. The frequency drift feature can help identify small changes in the signal frequency over time.

[0045] The present invention is further configured to construct a logic of anomaly detection algorithm, including:

[0046] A training set is constructed using radio signal sequence data corresponding to a normal signal, and spectrum mutation characteristics and frequency drift characteristics of the training set are extracted; specifically, radio signal sequence data including signal strength, signal frequency and timestamp are collected from the normal signal, and spectrum mutation characteristics and frequency drift characteristics of the training set are extracted according to the signal strength, signal frequency and timestamp to represent normal signal characteristics;

[0047] Randomly select any one of the spectrum mutation feature and the frequency drift feature, set it as the first feature, and randomly select a feature value from the first feature, set it as the first random segmentation value, recursively segment until the data points in the training set are segmented into leaf nodes, and obtain a first isolated tree;

[0048] Select another feature, set it as the second feature, and randomly select a feature value from the second feature, set it as the second random segmentation value, recursively segment until the data points in the training set are segmented into leaf nodes, obtain the second isolated tree, and set the first isolated tree and the second isolated tree as the isolated tree set;

[0049] The extracted spectrum mutation features and frequency drift features are input into the isolated tree set, and the average path length is calculated. When the average path length is greater than the preset abnormal score, it is identified as an abnormal signal; when the average path length is less than or equal to the preset abnormal score, it is identified as a normal signal. The present invention is further configured such that the calculation logic of the average path length is: h(x) is the average path length, |T| is the size of the isolated tree set, that is, the number of isolated trees, x is the data point to be detected, including spectrum mutation characteristics and frequency drift characteristics, ∑ T PathLrngth(x,T) represents the path length of data point x in the isolated tree T. The path length represents the number of nodes required to reach data point x from the root node. The calculation logic of the preset anomaly score is: s(x,n) is the anomaly score, n is the number of samples, that is, the total number of samples in the training set, and c(n) is the adjustment factor of the average path length. The calculation logic is: H(i) is the i-th harmonic number, and the calculation logic is: By combining the spectrum mutation characteristics and frequency drift characteristics and using isolation forest for anomaly detection, abnormal signals can be effectively identified and processed, thereby improving the efficiency and accuracy of spectrum monitoring.

[0050] Embodiment 2

[0051] See also Figure 2 , the exemplary spectrum sensing-based monitoring system includes:

[0052] Acquisition module: collects radio signal sequences in the environment in real time through spectrum sensing equipment, processes and analyzes the collected radio signal sequences, and extracts spectrum usage characteristics;

[0053] Analysis module: uses anomaly detection algorithms to analyze spectrum usage characteristics and identify normal and abnormal signals;

[0054] Alarm module: When an abnormal signal is identified, an alarm is generated and the spectrum usage characteristics of the abnormal signal are recorded.

[0055] It should be noted that the monitoring system based on spectrum sensing provided in the above embodiment and the monitoring method based on spectrum sensing provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In practical applications, the monitoring system based on spectrum sensing provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0056] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0057] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0058] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0059] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0060] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0061] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0062] In the several embodiments provided in the present application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0063] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0064] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0065] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0066] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A monitoring method based on spectrum sensing, characterized in that: include: The radio signal sequence in the environment is collected in real time by spectrum sensing equipment, and the collected radio signal sequence is processed and analyzed to extract the spectrum usage characteristics. The data in the radio signal sequence in the collection environment includes: signal strength, signal frequency and timestamp; the collected radio signal sequence is processed and analyzed to extract the spectrum usage characteristics, including: denoising, normalizing and interpolating the collected radio signal sequence; extracting spectrum mutation characteristics according to signal strength and corresponding timestamp; extracting frequency drift characteristics according to signal frequency and corresponding timestamp; extracting spectrum mutation characteristics according to signal strength, including: obtaining signal strength and corresponding timestamp, generating signal strength sequence, calculating forward spectrum mutation value and reverse spectrum mutation value according to signal strength sequence, and setting the maximum of forward spectrum mutation value and reverse spectrum mutation value as spectrum mutation characteristic, wherein the calculation logic of forward spectrum mutation value is: The calculation logic of the reverse spectrum mutation value is: is the positive spectrum mutation value at time t in the signal intensity sequence, is the positive spectrum mutation value at time t-1 in the signal intensity sequence, x t is the signal strength at time t in the signal strength sequence, μ is the expected value of the signal strength sequence, and K is the sensitivity factor, which is a preset constant. is the reverse spectrum mutation value at time t in the signal intensity sequence, is the reverse spectrum mutation value at time t-1 in the signal strength sequence; extracting the frequency drift according to the signal frequency includes: obtaining the signal frequency and the corresponding timestamp, generating a signal frequency sequence, performing Fourier transform on the signal frequency sequence to obtain the frequency drift feature, wherein the logic of performing Fourier transform on the signal frequency sequence is: F(ω) is the frequency drift characteristic, ω is the signal frequency angular frequency, and the calculation logic of ω is: ω=2πf, f is the signal frequency, N is the number of signal frequencies in the signal frequency sequence, f i is the value of the i-th signal frequency in the signal frequency sequence, j is an imaginary unit, t i is the timestamp of the i-th signal frequency in the signal frequency sequence; An anomaly detection algorithm is used to analyze the spectrum usage characteristics and identify normal signals and abnormal signals; the construction logic of the anomaly detection algorithm includes: using the radio signal sequence data corresponding to the normal signal to construct a training set, extracting the spectrum mutation characteristics and frequency drift characteristics of the training set; randomly selecting any one of the spectrum mutation characteristics and the frequency drift characteristics, setting it as the first characteristic, and randomly selecting a characteristic value from the first characteristic, setting it as the first random segmentation value, recursively segmenting until the data points in the training set are segmented into leaf nodes, and obtaining a first isolated tree; selecting another characteristic, setting it as the second characteristic, and randomly selecting a characteristic value from the second characteristic, setting it as the second random segmentation value, recursively segmenting until the data points in the training set are segmented into leaf nodes, and obtaining a second isolated tree, and setting the first isolated tree and the second isolated tree as an isolated tree set; inputting the extracted spectrum mutation characteristics and frequency drift characteristics into the isolated tree set, calculating the average path length, and when the average path length is greater than the preset abnormal score, identifying it as an abnormal signal; when the average path length is less than or equal to the preset abnormal score, identifying it as a normal signal; the calculation logic of the average path length is: h(x) is the average path length, |T| is the size of the isolated tree set, that is, the number of isolated trees, x is the data point to be detected, including spectrum mutation characteristics and frequency drift characteristics, ∑ T PathLrngth(x,T) represents the path length of data point x in the isolated tree T. The path length represents the number of nodes required to reach data point x from the root node. The calculation logic of the preset anomaly score is: s(x,n) is the anomaly score, n is the number of samples, that is, the total number of samples in the training set, and c(n) is the adjustment factor of the average path length. The calculation logic is: H(i) is the i-th harmonic number, and the calculation logic is: When an abnormal signal is identified, an alarm is generated and the spectrum usage characteristics of the abnormal signal are recorded.

2. The monitoring system based on spectrum sensing is characterized by: The monitoring method based on spectrum sensing according to claim 1 comprises: Acquisition module: collects radio signal sequences in the environment in real time through spectrum sensing equipment, processes and analyzes the collected radio signal sequences, and extracts spectrum usage characteristics; Analysis module: uses anomaly detection algorithms to analyze spectrum usage characteristics and identify normal and abnormal signals; Alarm module: When an abnormal signal is identified, an alarm is generated and the spectrum usage characteristics of the abnormal signal are recorded.

Images