[go: up one dir, main page]

CN112130118B - Ultra-wideband radar signal processing system and method based on SNN - Google Patents

Ultra-wideband radar signal processing system and method based on SNN Download PDF

Info

Publication number
CN112130118B
CN112130118B CN202010841963.XA CN202010841963A CN112130118B CN 112130118 B CN112130118 B CN 112130118B CN 202010841963 A CN202010841963 A CN 202010841963A CN 112130118 B CN112130118 B CN 112130118B
Authority
CN
China
Prior art keywords
snn
neural network
uwb
module
analysis
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010841963.XA
Other languages
Chinese (zh)
Other versions
CN112130118A (en
Inventor
邹卓
褚皓明
傅宇鸿
李文卓
环宇翔
郑立荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
WUXI INSTITUTE OF FUDAN UNIVERSITY
Original Assignee
WUXI INSTITUTE OF FUDAN UNIVERSITY
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by WUXI INSTITUTE OF FUDAN UNIVERSITY filed Critical WUXI INSTITUTE OF FUDAN UNIVERSITY
Priority to CN202010841963.XA priority Critical patent/CN112130118B/en
Publication of CN112130118A publication Critical patent/CN112130118A/en
Application granted granted Critical
Publication of CN112130118B publication Critical patent/CN112130118B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/28Details of pulse systems
    • G01S7/285Receivers
    • G01S7/295Means for transforming co-ordinates or for evaluating data, e.g. using computers
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/28Details of pulse systems
    • G01S7/285Receivers
    • G01S7/292Extracting wanted echo-signals

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses an SNN-based ultra-wideband radar signal processing system and a processing method, which relate to the technical field of brain-like artificial intelligence and comprise an IR-UWB sensor for detecting and receiving a reflected pulse signal, wherein an IR-UWB module for carrying out time-event coding on the reflected pulse signal is arranged in the IR-UWB sensor, the IR-UWB module inputs coded data into an SNN array module for nerve mimicry calculation, and sends the data obtained after the nerve mimicry calculation to a corresponding processor module for analysis, and the processor module feeds back result information to the SNN array module after the analysis is completed. The method integrates perception (radar pulse signal detection) and cognition (nerve mimicry calculation), so that the traditional radar signal processing and signal reconstruction process is avoided, and the full event-driven signal transmission and model can directly output results.

Description

Ultra-wideband radar signal processing system and method based on SNN
Technical Field
The invention relates to the technical field of brain-like artificial intelligence, in particular to an SNN-based ultra-wideband radar signal processing system and an SNN-based ultra-wideband radar signal processing method.
Background
An impulse Radio-UI tra Wideband (IR-UWB), hereinafter abbreviated as ultra Wideband, is a short-range wireless communication technology. Unlike conventional wireless communication technology, ultra wideband does not employ carrier modulation, but rather directly employs pulses with very narrow time widths (nanoseconds or sub-nanoseconds), which are transferred directly or through buffers to the antenna, and typically the system does not require more complex circuitry such as local oscillators and up-conversion mixers.
The IR-UWB signal has the characteristics of extremely short pulse duration, extremely high time domain resolution, low complexity, low cost, strong multipath interference resistance, wide frequency spectrum range (up to several GHz or more), penetrability, low power consumption and the like, and can be widely applied to the applications of the Internet of things, wireless positioning, short distance measurement, low-cost radars and the like.
The radar sensor based on IR-UWB generally integrates a plurality of components such as a transmitting end, an amplifier end, a receiving end and the like, is consistent with other radar principles, and can be reflected and received by the receiving end under the condition of encountering an obstacle after the UWB radar sensor transmits UWB signals through the transmitting end. Compared with the traditional radar, the radar sensor based on the IR-UWB has the advantages of high time domain precision, small volume, low power consumption and low cost, and is widely used for non-contact sensors such as human body monitoring, gesture recognition, human body activity analysis, target monitoring, human-computer interaction and the like, and meanwhile, the radar sensor based on the IR-UWB can be used for nondestructive internal detection and the like due to the penetrability of an IR-UWB signal. Received signals acquired using IR-UWB radar sensors are typically processed using fast and slow time sampling systems, as shown in fig. 1. In the fast time dimension, storing L samples in a period of time after the sampling time begins in a digital memory to obtain L distance gates; in the slow time dimension, pulsed radar transmits not only one pulse, but in the form of a set of pulses, the dimension in which these axes of repetition lie being the slow time axis.
In view of the received signal form of IR-UWB, conventional IR-UWB radar sensors generally process binary images in the XY direction of three-dimensional echoes. The signal processing method and steps are shown in fig. 2, and after the signal is detected and received, the received radar echo signal is first preprocessed. Preprocessing includes clutter suppression, background noise removal, etc., and in general, preprocessing may employ direct subtractive averaging, singular value decomposition, moving object detection, etc. for clutter filtering. And then, extracting signal characteristics by adopting different methods according to application scenes and working requirements. The extraction method varies according to the application type, and in multi-target detection, principal component analysis (PCA, principal Component Analysis) is generally adopted; in gesture recognition, time-frequency feature extraction or a Range-Doppler (RD) algorithm is generally used. After the characteristics are extracted, the characteristics are analyzed by adopting a mode recognition or machine learning method to finally obtain a result. Traditional machine learning methods include Nearest Neighbor classifiers (K-Nearest Neighbor), decision tree classifiers, support Vector Machines (SVMs), and the like. With the increase of computational power, analysis methods employing convolutional neural networks are also widely used in the feature extraction of IR-UWB radar echoes.
With the rapid development of artificial intelligence, the method is widely applied to machine vision, and extends from image recognition classification to microwave vision represented by radar application, and the method of deep learning and Artificial Neural Network (ANN) is generally used for performing pattern recognition and classification on radar signals. The method is also used for IR-UWB radar sensor (infrared-ultra-wideband radar sensor), including Convolutional Neural Network (CNN), cyclic neural network (RNN), long-term short-term memory network (LSTM), support Vector Machine (SVM), etc.
In summary, artificial intelligence based on ANN has a great demand for hardware resources, which greatly increases the difficulty of deploying artificial intelligence algorithms in low power devices. However, as neuromorphic calculations began to rise, it became possible to implement low-power, high-efficiency artificial intelligence calculations (an order of magnitude improvement in energy efficiency) aimed at mimicking the human brain's way of operation. The present patent therefore proposes a new improvement over the prior art techniques described above, in particular in the processing of radar signals.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an ultra-wideband radar signal processing system and an ultra-wideband radar signal processing method based on SNN, which avoid the processes of traditional radar signal processing and signal reconstruction by integrating perception (radar pulse signal detection) and cognition (nerve mimicry calculation), and directly output results by using signal transmission and models driven by full events.
In order to achieve the above object, the present invention provides the following technical solutions:
the ultra-wideband radar signal processing system based on SNN comprises an IR-UWB sensor for detecting and receiving a reflected pulse signal, wherein an IR-UWB module for carrying out time-event coding on the reflected pulse signal is arranged in the IR-UWB sensor, the IR-UWB module inputs coded data into an SNN array module for nerve mimicry calculation, the data obtained after the nerve mimicry calculation is sent to a corresponding processor module for analysis, and the processor module feeds back result information to the SNN array module after the analysis is completed;
or, the system also comprises a neural network state machine which can interact with the SNN array module, wherein the neural network state machine adopts WTA rules, the number of the state machines in the neural network state machine is determined according to the number of the required classifications, and the neural network state machine is trained through a pulse time domain sequence recognition training algorithm.
The processing method of the SNN-based ultra-wideband radar signal processing system comprises the following steps:
the IR-UWB sensor detects and receives the reflected pulse signal;
the IR-UWB module in the step (2) carries out time-event coding on the reflected pulse signals received in the step (1) to obtain coded data;
the SNN array module receives the encoded data in the step (2), adds time domain expression into the encoded data through neuro-mimicry calculation to form a dynamic pulse sequence, and transmits the dynamic pulse sequence to the processor module for analysis;
and (4) feeding back analysis result information to the SNN array module after the processor module completes analysis so as to realize real-time updating of a network.
Preferably, the neuromorphic calculation in step (3) is specifically implemented by a pulsed neural network model.
Advantageous effects
The SNN-based ultra-wideband radar signal processing system and the SNN-based ultra-wideband radar signal processing method provided by the invention have the following advantages:
1. because of the sparsity of the pulse sequence and the event-driven characteristic, the acquisition, transmission and processing of a large amount of redundant data are omitted in the system, and the IR-UWB radar has low energy consumption, so that the system has extremely low power consumption.
The IR-UWB radar directly adopts pulses with very narrow time width (nanosecond or sub-nanosecond level) to modulate, and the time domain precision is extremely high, so that the IR-UWB radar has high real-time characteristic.
The SNN can process pulse data naturally, and for pulse sequences generated by the IR-UWB radar, the SNN can directly input pulse signals into a network without processing steps such as signal type conversion, feature extraction and the like.
In ir-UWB radar, the pulses are transferred to the antenna directly or through a buffer, and in general, the system does not need more complex circuitry, and the system has lower complexity and is suitable for low-cost deployment and application.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a received signal obtained by a conventional IR-UWB radar sensor;
FIG. 2 is a diagram of a conventional IR-UWB radar sensor signal processing method;
FIG. 3 is a schematic diagram of an ultra wideband radar signal processing system with a supervised learning impulse neural network for an SNN-based ultra wideband radar signal processing system according to the present invention;
FIG. 4 is a schematic diagram of an ultra wideband radar signal processing system of an unsupervised learning impulse neural network of the SNN-based ultra wideband radar signal processing system of the present invention;
FIG. 5 is a schematic diagram of ultra wideband radar signal processing of a supervised learning impulse neural network of an SNN-based ultra wideband radar signal processing system according to the present invention;
fig. 6 is an ultra wideband radar signal processing schematic diagram of an unsupervised learning impulse neural network of the SNN-based ultra wideband radar signal processing system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The ultra-wideband radar signal processing system based on SNN comprises two forms of supervised learning and unsupervised learning, wherein the supervised learning form is shown in figure 3, and comprises an IR-UWB sensor for detecting and receiving a reflected pulse signal, an IR-UWB module for performing time-event coding on the reflected pulse signal is arranged in the IR-UWB sensor, the IR-UWB module inputs coded data into an SNN array module for performing nerve mimicry calculation, and sends the data obtained after the nerve mimicry calculation to a corresponding processor module for analysis, and the processor module feeds back result information to the SNN array module after the analysis is completed;
the non-supervision learning form also comprises a neural network state machine which can realize interaction with the SNN array module on the basis of supervision learning, wherein the neural network state machine adopts WTA rules, the number of the state machines in the neural network state machine is determined according to the number of the required classification, and the neural network state machine is trained through a pulse time domain sequence recognition training algorithm.
The processing method of the SNN-based ultra-wideband radar signal processing system comprises the following steps:
the IR-UWB sensor detects and receives the reflected pulse signal;
the IR-UWB module in the step (2) carries out time-event coding on the reflected pulse signals received in the step (1) to obtain coded data;
the SNN array module receives the encoded data in the step (2), adds time domain expression into the encoded data through neuro-mimicry calculation to form a dynamic pulse sequence, and transmits the dynamic pulse sequence to the processor module for analysis; the nerve mimicry calculation is realized by a pulse neural network model;
and (4) feeding back analysis result information to the SNN array module after the processor module completes analysis so as to realize real-time updating of a network.
Specifically, as shown in fig. 5, the algorithm flow of supervised learning is that the IR-UWB module performs time-event encoding according to the echo of the radar, and the encoded data may be directly input to perform neuro-mimicry calculation.
The process of the neuro-mimicry calculation is performed by using a pulse neural network model, and the calculation is mainly divided into the following two processes:
one is the calculation of the existing output, the pulse passes through each node of each layer of neural network and generates output, and finally the neural network generates a final output which is irrelevant to our target application and is the result of self-calculation;
secondly, according to the type of the output pulse sequence which we want to obtain, new weight is obtained through analysis and result output and calculation through neuro-mimicry, the process is Surrogate Propagation (agent propagation), and the result of the next self-calculation after learning is gradually similar to the target result;
the two processes are repeated, and the supervised identification and classification of the targets can be realized according to application scenes. In addition, the pulse neural network can be customized according to the application scene, and the larger the network is, the more pattern types can be identified, and more differentiated classifications can be accommodated. The model ensures that the identification object can be accurately identified at any position and any direction of the IR-UWB input matrix.
Specifically, taking gesture recognition under supervised learning as an example, firstly, according to the echo of a radar, an IR-UWB module carries out time-event coding, and the coded data can be directly input to carry out nerve mimicry calculation.
The SNN neural network for gesture recognition has a simple structure, and is only one input layer, one hidden layer and one output layer.
The process of the neuro-mimicry calculation is performed by using a pulse neural network model, and the calculation is mainly divided into the following two processes:
one is the calculation of the existing output, the pulse passes through each node of each layer of neural network and generates output, and finally the neural network generates a final output, and the quantity of the neurons of the output layer is determined by the action to be identified.
According to the type of the output pulse sequence which we want to obtain, for example, we can design different time sequence impulse response sequences according to different gestures, calculate the loss function through analysis and result output, calculate new weight through the loss function and response input and output, the process is Surrogate Gradient Learning rules (agent gradient learning rule), and the result of the next self-calculation after learning is gradually similar to the target result.
The two processes are repeated, the supervised identification and classification of the targets can be realized according to the application scene, and in the repeated process, the learning rate is gradually reduced, so that the model is ensured not to stay in the local optimal solution.
As shown in FIG. 6, the algorithm flow of the unsupervised learning is that firstly, according to the echo of the radar, the IR-UWB module carries out time-event coding, and the coded data can be directly input to carry out nerve mimicry calculation; the process of the neuro-mimicry calculation is performed by using a pulse neural network model, and the calculation is mainly divided into the following two processes:
one is the calculation of the existing output, the pulse passes through each node of each layer of neural network and generates output, and finally the neural network generates a final output which is irrelevant to our target application and is the result of self-calculation, and the output can enable the neural network to generate a fixed state;
secondly, after generating a plurality of neural network state machines according to the required classification, signals are input into the whole neural network state machine system at intervals, the process is called initialization of the neural network, after each time a signal is input, a control neuron restores the state of the whole neural network, and meanwhile, the same neural network state machine is ensured not to be continuously excited in two continuous samples (the signals required to be input are respectively in different types) through a special weight attenuation structure; when all state machines are excited at least once, after the weights of all the neural network state machines are updated once, the control neurons are removed, various random pulse samples are input to the neural network state machines, and the weight attenuation structures are removed by phase inversion in some modes, so that the related neural network state machines can be continuously excited (such as when continuous signal input of the same type is met), and the weights are continuously updated. The termination condition of the process is that none of the signals is tuned to be classified into another neural network state machine, the method being such that all of the same class of inputs excite a fixed neural network state;
the two processes are repeated, and the unsupervised identification and classification of the targets can be realized according to the application scene. Different from supervised learning, a self-supervised learning structure of a neural network state machine is added, the neural network state machine adopts a WTA (Winner-Take-All) rule, the number of the state machines in the neural network state machine is determined according to the number of required classification, and the neural network state machine is trained through a pulse time domain sequence recognition training algorithm, for example, if 5 gestures are required to be recognized, 5 neural network state machines are generated.
In summary, the invention integrates sensing (radar pulse signal detection) and cognition (nerve mimicry calculation), avoids the processes of traditional radar signal processing and signal reconstruction, and directly outputs results through signal transmission and model driven by full events, and under the framework of the system:
1. the relative bandwidth of-10 db of the signal generator is more than 20% of the central frequency, or the bandwidth of-10 db of the signal exceeds 500MHz, then the signal is UWB (Ultra Wide Band, UWB) technology, which is a wireless carrier communication technology, which does not adopt sinusoidal carriers, but utilizes nanosecond non-sinusoidal narrow pulse to transmit data, so that the UWB technology occupies a very wide frequency spectrum range. Wherein the definition of the relative bandwidth η is:
f in h For the upper bound of the signal spectrum, f l Is the lower bound of the signal spectrum.
2. After the echo signal is detected, directly generating an Event sequence (Event lndex), directly entering a nerve mimicry calculation unit without transformation, and performing intelligent processing by using a pulse neural network;
3. performing SNN using a neuro-mimicry architecture, including but not limited to general purpose computers and servers, GPUs, FPGAs, application specific integrated circuit chips, or novel brain-like computing devices and architectures including memristors, and the like;
4. SNN model training methods are applied to typical applications such as gesture recognition, heartbeat and breath recognition, human motion recognition and the like.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.

Claims (2)

1. Ultra-wideband radar signal processing system based on SNN, its characterized in that: the device comprises an IR-UWB sensor for detecting and receiving a reflected pulse signal, wherein an IR-UWB module for carrying out time-event coding on the reflected pulse signal is arranged in the IR-UWB sensor, the IR-UWB module inputs coded data into an SNN array module for nerve mimicry calculation, the data obtained after the nerve mimicry calculation is sent to a corresponding processor module for analysis, and the processor module feeds back result information to the SNN array module after the analysis is completed;
or, the system also comprises a neural network state machine which can realize interaction with the SNN array module, wherein the neural network state machine adopts WTA rules, determines the number of the state machines in the neural network state machine according to the number of the required classifications, and trains the neural network state machine through a pulse time domain sequence recognition training algorithm;
the process of the neuro-mimicry calculation is performed by using a pulse neural network model, and the calculation is mainly divided into the following two processes:
firstly, the pulse passes through each node of each layer of neural network and generates output, and finally the neural network generates final output, and the quantity of the neurons of the output layer is determined by the action to be identified;
secondly, different time sequence impulse response sequences are designed according to different gestures, a loss function is calculated through analysis and result output, and new weights are calculated through the loss function and response input and output.
2. The method for processing the SNN-based ultra-wideband radar signal processing system according to claim 1, wherein: the method comprises the following steps:
the IR-UWB sensor detects and receives the reflected pulse signal;
the IR-UWB module in the step (2) carries out time-event coding on the reflected pulse signals received in the step (1) to obtain coded data;
the SNN array module receives the encoded data in the step (2), adds time domain expression into the encoded data through neuro-mimicry calculation to form a dynamic pulse sequence, and transmits the dynamic pulse sequence to the processor module for analysis;
and (4) feeding back analysis result information to the SNN array module after the processor module completes analysis so as to realize real-time updating of a network.
CN202010841963.XA 2020-08-19 2020-08-19 Ultra-wideband radar signal processing system and method based on SNN Active CN112130118B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010841963.XA CN112130118B (en) 2020-08-19 2020-08-19 Ultra-wideband radar signal processing system and method based on SNN

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010841963.XA CN112130118B (en) 2020-08-19 2020-08-19 Ultra-wideband radar signal processing system and method based on SNN

Publications (2)

Publication Number Publication Date
CN112130118A CN112130118A (en) 2020-12-25
CN112130118B true CN112130118B (en) 2023-11-17

Family

ID=73851721

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010841963.XA Active CN112130118B (en) 2020-08-19 2020-08-19 Ultra-wideband radar signal processing system and method based on SNN

Country Status (1)

Country Link
CN (1) CN112130118B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112699956B (en) * 2021-01-08 2023-09-22 西安交通大学 Neuromorphic visual target classification method based on improved impulse neural network
WO2022155964A1 (en) * 2021-01-25 2022-07-28 Chengdu SynSense Technology Co., Ltd. Equipment anomaly detection method, computer readable storage medium, chip, and device
CN113050060B (en) * 2021-03-25 2024-04-26 南京敏智达科技有限公司 Life detection method and detection device based on sparse reconstruction and neural network
CN113255905B (en) * 2021-07-16 2021-11-02 成都时识科技有限公司 Signal processing method of neurons in impulse neural network and network training method
CN114399033B (en) * 2022-03-25 2022-07-19 浙江大学 Brain-like computing system and computing method based on neuron instruction coding
CN116016046B (en) * 2022-12-08 2025-08-01 齐鲁工业大学(山东省科学院) OFDM channel estimation and signal detection method based on self-normalization network
CN115774850B (en) * 2023-01-09 2024-11-22 重庆大学 Indoor and outdoor detection method and system based on pulse neural network
EP4614184A1 (en) * 2024-03-05 2025-09-10 IMRA Europe S.A.S. Discrimination between adult and child based on radar signal

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2358611A1 (en) * 2000-10-10 2002-04-10 Heidelberger Druckmaschinen Ag System and method for interfacing with a production scanner
CN103036590A (en) * 2013-01-01 2013-04-10 复旦大学 High-swing impulse radio ultra-wideband transmitter
WO2016070188A1 (en) * 2014-11-02 2016-05-06 Kim Revyn Smart audio headphone system
CN106344005A (en) * 2016-10-28 2017-01-25 张珈绮 Mobile ECG (electrocardiogram) monitoring system and monitoring method
CN108919218A (en) * 2018-06-07 2018-11-30 北京邮电大学 A kind of contactless number of people in car and the method and device of position judgement
CN109407067A (en) * 2018-10-13 2019-03-01 中国人民解放军海军航空大学 Radar moving targets detection and classification integral method based on time-frequency figure convolutional neural networks
KR20190040822A (en) * 2017-10-11 2019-04-19 엘지전자 주식회사 Mobile terminal
CN109906101A (en) * 2016-08-25 2019-06-18 天堂医疗公司 System and method for handling nerve signal
CN110210563A (en) * 2019-06-04 2019-09-06 北京大学 The study of pattern pulse data space time information and recognition methods based on Spike cube SNN
WO2019182265A1 (en) * 2018-03-21 2019-09-26 엘지전자 주식회사 Artificial intelligence device and method for operating same
CN110288510A (en) * 2019-06-11 2019-09-27 清华大学 A proximity sensor visual perception processing chip and IoT sensing device
CN110426560A (en) * 2019-06-28 2019-11-08 北京大学 A kind of pulse array signals space-time up-sampler generation method
CN111272764A (en) * 2020-01-22 2020-06-12 哈尔滨工业大学 Large-scale intelligent temporary platform non-contact image recognition mobile management and control system and method
CN111334982A (en) * 2018-12-19 2020-06-26 Lg电子株式会社 Laundry treatment apparatus and method of operating the same

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9177246B2 (en) * 2012-06-01 2015-11-03 Qualcomm Technologies Inc. Intelligent modular robotic apparatus and methods
US11669914B2 (en) * 2018-05-06 2023-06-06 Strong Force TX Portfolio 2018, LLC Adaptive intelligence and shared infrastructure lending transaction enablement platform responsive to crowd sourced information
US11269058B2 (en) * 2018-06-13 2022-03-08 Metawave Corporation Autoencoder assisted radar for target identification

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2358611A1 (en) * 2000-10-10 2002-04-10 Heidelberger Druckmaschinen Ag System and method for interfacing with a production scanner
CN103036590A (en) * 2013-01-01 2013-04-10 复旦大学 High-swing impulse radio ultra-wideband transmitter
WO2016070188A1 (en) * 2014-11-02 2016-05-06 Kim Revyn Smart audio headphone system
CN109906101A (en) * 2016-08-25 2019-06-18 天堂医疗公司 System and method for handling nerve signal
CN106344005A (en) * 2016-10-28 2017-01-25 张珈绮 Mobile ECG (electrocardiogram) monitoring system and monitoring method
KR20190040822A (en) * 2017-10-11 2019-04-19 엘지전자 주식회사 Mobile terminal
WO2019182265A1 (en) * 2018-03-21 2019-09-26 엘지전자 주식회사 Artificial intelligence device and method for operating same
CN108919218A (en) * 2018-06-07 2018-11-30 北京邮电大学 A kind of contactless number of people in car and the method and device of position judgement
CN109407067A (en) * 2018-10-13 2019-03-01 中国人民解放军海军航空大学 Radar moving targets detection and classification integral method based on time-frequency figure convolutional neural networks
CN111334982A (en) * 2018-12-19 2020-06-26 Lg电子株式会社 Laundry treatment apparatus and method of operating the same
CN110210563A (en) * 2019-06-04 2019-09-06 北京大学 The study of pattern pulse data space time information and recognition methods based on Spike cube SNN
CN110288510A (en) * 2019-06-11 2019-09-27 清华大学 A proximity sensor visual perception processing chip and IoT sensing device
CN110426560A (en) * 2019-06-28 2019-11-08 北京大学 A kind of pulse array signals space-time up-sampler generation method
CN111272764A (en) * 2020-01-22 2020-06-12 哈尔滨工业大学 Large-scale intelligent temporary platform non-contact image recognition mobile management and control system and method

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
Deep learning in spiking neural networks;A Tavanaei等;《Neural Networks》;47-63 *
M. R. Yuce ; J-M. Redouté ; Kasun M. Thotahewa ; Ho Chee Keong.Development of low-power UWB body sensors.《Information Technologies (ISCIT)》.2013,1-9. *
一种新的OFDM相位编码频率步进雷达信号及其特性;霍凯;姜卫东;黎湘;毛钧杰;;电子与信息学报(第03期);全文 *
基于EMD和BP神经网络的雷达体征信号检测算法;崔丽辉;赵安兴;宁方正;;计算机系统应用(第08期);全文 *

Also Published As

Publication number Publication date
CN112130118A (en) 2020-12-25

Similar Documents

Publication Publication Date Title
CN112130118B (en) Ultra-wideband radar signal processing system and method based on SNN
Sun et al. Real-time radar-based gesture detection and recognition built in an edge-computing platform
CN112184849B (en) Intelligent processing method and system for complex dynamic multi-target micro-motion signals
CN110245581B (en) Human behavior recognition method based on deep learning and distance-Doppler sequence
CN111220958A (en) Radar target Doppler image classification and identification method based on one-dimensional convolutional neural network
Zhengliang et al. Dataset of human motion status using IR-UWB through-wall radar
Tang et al. Human activity recognition based on mixed CNN with radar multi-spectrogram
Jin et al. Robust dynamic hand gesture recognition based on millimeter wave radar using Atten-TsNN
CN114708663B (en) A millimeter wave radar sensing gesture recognition method
Gan et al. Gesture recognition system using 24 GHz FMCW radar sensor realized on real-time edge computing platform
Hou et al. Jamming recognition of carrier-free UWB cognitive radar based on MANet
Arsalan et al. Resource efficient gesture sensing based on fmcw radar using spiking neural networks
Zhang et al. Temporal-range-doppler features interpretation and recognition of hand gestures using MmW FMCW radar sensors
Cheng et al. A real-time human activity recognition method for through-the-wall radar
Zhu et al. Ground target recognition using carrier-free UWB radar sensor with a semi-supervised stacked convolutional denoising autoencoder
CN117471412A (en) Radar-based activity classification
Ruan et al. Automatic recognition of radar signal types based on CNN-LSTM
CN116008984B (en) A method of human motion recognition based on millimeter wave radar based on pattern contour limitation
Liang et al. A posture recognition based fall detection system using a 24GHz CMOS FMCW radar SoC
Jung et al. Digit recognition using FMCW and UWB radar sensors: A transfer learning approach
CN115184890B (en) Method and device for identifying human body behaviors of through-wall radar based on multilink information decision
Zhang et al. CNN based target classification in vehicular networks with millimeter-wave radar
Shaaban et al. Evaluation of spiking neural networks for time domain-based radar hand gesture recognition
Wang et al. Through-wall human motion representation via autoencoder-self organized mapping network
Zhou et al. Radar-based swimming activity recognition with temporal dynamic convolution and spectral data augmentation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant