CN111091831B - Silent lip language recognition method and system - Google Patents
Silent lip language recognition method and system Download PDFInfo
- Publication number
- CN111091831B CN111091831B CN202010016710.9A CN202010016710A CN111091831B CN 111091831 B CN111091831 B CN 111091831B CN 202010016710 A CN202010016710 A CN 202010016710A CN 111091831 B CN111091831 B CN 111091831B
- Authority
- CN
- China
- Prior art keywords
- signals
- wave
- silent
- signal
- carrier
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000006073 displacement reaction Methods 0.000 claims abstract description 11
- 230000009466 transformation Effects 0.000 claims abstract description 6
- 210000000214 mouth Anatomy 0.000 claims abstract description 4
- 230000003321 amplification Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 230000010363 phase shift Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 230000000630 rising effect Effects 0.000 claims description 2
- 238000009966 trimming Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 239000000969 carrier Substances 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000001097 facial muscle Anatomy 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/24—Speech recognition using non-acoustical features
- G10L15/25—Speech recognition using non-acoustical features using position of the lips, movement of the lips or face analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
A silent lip language identification method and system are disclosed, wherein millimeter wave signals as carrier waves are continuously emitted and focused in the oral cavity area of a user, the millimeter wave signals are modulated and partially reflected on phases through the speaking behavior of the user, and the speech behavior information of the user is obtained by converting the reflected signals to a baseband, correcting the reflected signals and then adopting speech phase fuzzy linear reconstruction based on triangular transformation. The invention has the advantages of no contact, strong penetrability, high precision and the like; the method can accurately track the fine displacement movement of the lips and well detect the accurate voice command.
Description
Technical Field
The invention relates to a technology in the field of information security, in particular to a silent lip language identification method and a silent lip language identification system based on a small 120GHz interference radar system.
Background
As interaction with computer devices becomes more prevalent, the trend in interaction is to become more natural and intelligent. People have therefore developed a variety of natural user interaction interfaces such as touch screens, gaze tracking, gesture recognition and speech recognition systems, where speech recognition is of particular interest because it is similar to the way people issue commands in daily life. However, it is inconvenient for people to use speech recognition in some situations, such as where silence should be maintained, or where privacy is desired in public. In addition, some people may lose the ability to speak because of illness, and their need for language communication should be taken into account. Thus, the concept of silent lip language perception emerged. Several methods for silent lip language perception are currently being investigated.
Disclosure of Invention
The invention provides a silent lip language identification method and system based on millimeter wave radar interference phase, and provides a silent lip language identification method and system aiming at the problem of phase ambiguity in millimeter wave nonlinear phase modulation in the prior art, and the silent lip language identification method and system have the advantages of no need of contact, strong penetrability, high precision and the like; the method can accurately track the fine displacement movement of the lips and well detect the accurate voice command.
The invention is realized by the following technical scheme:
the invention relates to a silent lip language identification method, which is characterized in that millimeter wave signals serving as carrier waves are continuously sent out and focused on an oral cavity area of a user, the millimeter wave signals are modulated and partially reflected on phases through the speaking behavior of the user, and the reflected signals are converted to a baseband and corrected, and then voice phase fuzzy linear reconstruction based on triangular transformation is adopted to obtain the speaking behavior information of the user.
The invention relates to a silent lip language recognition system, comprising: power supply unit, radar transceiver, carrier wave generating unit and intermediate frequency amplifying unit, wherein: the power supply unit is connected with other units and provides working voltage, the input end of the radar transceiver can be independently selected to be connected with the carrier generation unit or connected with fixed reference voltage through a switch, the output end of the radar transceiver is connected with the intermediate frequency amplification unit and transmits I/Q signals, and the intermediate frequency amplification unit is connected with the signal output end and transmits the amplified I/Q signals.
The carrier wave is a frequency modulation continuous wave, preferably a sawtooth wave.
Technical effects
The invention integrally solves the problem of lip Doppler phase ambiguity obtained by a millimeter wave radar interference phase measurement method.
Compared with the prior art, the method can measure the Doppler phase shift caused by lip movement by using a millimeter wave radar interference phase method, senses lip language by using 120GHz millimeter waves, customizes a fully integrated 120GHz millimeter wave radar miniaturized system comprising a radio frequency front end, an intermediate frequency, power management, signal transmission and the like, and realizes signal reconstruction of micro lip movement by using a phase linear reconstruction algorithm based on a coherent radar.
Drawings
FIG. 1 is a schematic diagram of a silent lip language identification method based on short-range millimeter wave radar sensing according to the present invention;
FIG. 2 is a schematic view of a radar sensor system of the present invention;
FIG. 3 is a schematic diagram of a sawtooth signal with two different pulse repetition times and amplitudes according to an embodiment;
FIG. 4 is a normalized spectrum graph of I/Q signals and I/Q signals of command phrases "Cancel" and "Up" output by the intermediate frequency amplifier in the embodiment
FIG. 5 is a schematic diagram of the I/Q signals and displacement waveforms for eight command phrases in an embodiment;
in the figure: (a) "Delete"; (b) "Left"; (c) "Off"; (d) "Yes"; (e) "Go"; (f) "Next"; (g) "Stop"; (h) "Play".
FIG. 6 is a schematic diagram of the I/Q signals and displacement waveforms of three command sentences in an embodiment;
in the figure: (a) "Buy a/7:30/ticket/for/frozen/tonight "; (b) "How's the/weather/today"; (c) "Text Lucy and tell her/that the house for diner/is book".
Detailed Description
As shown in fig. 2, the 120GHz millimeter wave radar sensing system for implementing the above method according to the present embodiment uses a 3.24 cm × 4.27 cm double-sided printed circuit board processed by a component surface patch, and has two modes of Frequency Modulated Continuous Wave (FMCW) and Continuous Wave (CW), both of which allow radar interference, wherein the FMCW mode has range finding capability and greatly expands sensing dimensions. The sensing system adopts a TRX-120 _001radar radio frequency transceiver of the company SiliconRadar, the frequency range of which is 119.1GHz to 125.9GHz, and the Tx power of which is-7 dBm to 1dBm. The system comprises: the device comprises a power module and a power management circuit for providing 5v voltage, a radar transceiver in the form of a chip, a carrier generation unit and an intermediate frequency amplification unit, wherein the radar transceiver is respectively connected with the power module.
The power module comprises a USBtype-C connector and a low dropout regulator (LDO) and outputs stable 3.3V voltage.
The radar transceiver includes: a Power Amplifier (Power Amplifier), a Low Noise Amplifier (LNA), a quadrature mixer, a polyphase filter, a Voltage Controlled Oscillator (VCO), a package Transmit-receive antenna (TX/RX), and a local oscillator, wherein: the power amplifier is connected with the local oscillator and the transmitting antenna respectively and transmits a transmitting signal, the input end of the low-noise amplifier is connected with the receiving antenna and transmits a receiving signal, the quadrature mixer is connected with the low-noise amplifier and transmits the receiving signal converted to a baseband, the polyphase filter is connected with the voltage-controlled oscillator, and the voltage-controlled oscillator is connected with the input voltage and the local oscillator respectively.
The carrier generation unit is a self-excited oscillation circuit designed based on a triangular wave generation circuit, and different integration paths can be realized by using the unidirectional conductivity of a diode, and the circuit comprises: the input hysteresis comparator of homophase and integral arithmetic circuitry, wherein: when the time constant of the forward integration is far larger than that of the backward integration, the slope of the rising edge is greatly different from that of the falling edge, so that the triangular wave is converted into the sawtooth wave.
The self-oscillation circuit is further provided with a trimming potentiometer for controlling the amplitude and the period of the sawtooth wave so as to realize adjustable scanning near a reference voltage.
The sensing system is further provided with an intermediate frequency amplifier (IF amplifier) which is connected with the radar transceiver and is used for improving the signal-to-noise ratio (SNR) level of the output of the radio frequency mixer.
As shown in FIG. 3, two different waveforms represent sawtooth waveforms with different amplitudes and pulse repetition times for two sawtooth signal examples. Four analog tuning input ends of a 120GHz Local Oscillator (LO) are connected in a short circuit mode and are selectively connected with a fixed voltage output end in a CW mode or a sawtooth wave output end in an FMCW mode through a switch, so that the local oscillator correspondingly works at a fixed frequency point or within a certain bandwidth range.
As shown in fig. 1, the present embodiment relates to the silent lip-language identification method of the above system, by continuously emitting millimeter-wave signals as carriers and focusing the millimeter-wave signals on the oral area of the user, the millimeter-wave signals are modulated and partially reflected in phase by the speaking behavior of the user, and the reflected signals are converted to baseband and corrected, and then speech phase fuzzy linear reconstruction based on triangular transformation is adopted, so as to obtain the information of the speaking behavior of the user.
The millimeter wave signals, namely carriers, are as follows: x c (t)=A cos[2πf c t+φ(t)]Wherein: a is amplitude, f c Is the carrier frequency and is,is the phase noise of the transmitter.
The reflected signal is converted to a baseband to obtain: wherein: a. The I And A Q The amplitudes of the I and Q signals are, theta is a constant phase shift and->Is residual phase noise, λ is carrier wavelength, DC I And DC Q Is the dc offset in the I and Q signals.
for 120GHz millimeter waves, the wavelength is only 2.5mm, which easily results in phase ambiguity since facial muscle movements are likely to exceed half a wavelength. In this case, it is necessary to perform complicated phase unwrapping.
The speech phase fuzzy linear reconstruction based on the triangular transformation refers to: and sequentially differentiating the correction signal and the signal and then integrating the signals to obtain displacement information, wherein the specific time domain expression and the discrete form thereof are as follows: after obtaining the displacement information of silent lip movements, various signal processing methods are further utilized, such as: and obtaining a multi-dimensional feature vector by using a feature extraction method in the traditional machine learning, or realizing optimized fitting by using a Convolutional Neural Network (CNN) in deep learning so as to identify the features of different lip languages.
The present embodiment performs the effect evaluation by performing the effect evaluation in the office environment: the radar sensor system is connected to a data acquisition Device (DAQ) to acquire real-time I and Q signals. To achieve a better signal-to-noise ratio, the radar sensor is placed approximately 5 centimeters away from the subject's mouth. In a first set of experiments, silent lip commands for 20 different words were tested, including "Yes", "cancel", "No", "play", "cause", "search", "Up", "Down", "Left", "Right", "On", "Off", "Stop", "Go", "Save", "delete", "Send", "Next", "Enter", and "Return".
As shown in fig. 4 (a) and (b), I/Q signals of command phrases "Cancel" and "Up" output from the if amplifier, and face displacement that moves when a silent lip command is issued, which is recovered by the new algorithm, are shown.
As shown in fig. 4 (c) and (d), for normalizing the spectrograms of the I/Q signals for the two command phrases, the shaded area represents the portion of the frequency range that the human ear cannot perceive, since the human can only perceive frequencies between 20 and 20000 Hz. As shown, on the one hand, the radar sensor system can detect every small lip movement with high accuracy in displacement sensing, and on the other hand, different commands correspond to different relative displacements and spectral information. It is therefore possible to derive that the lip language from which each command phrase is issued has its own unique characterization. The same signal processing procedure can be applied to other command phrases, where experimental results for 8 command words are shown in fig. 5. It can be seen that the time-domain patterns of different command words are different. Further processing may extract richer features. Based on these features, machine learning or pattern recognition may be used to identify different silent lips.
The second set of experiments tested sentences of 12 silent lip commands, with the results of 3 command sentences as shown in fig. 6, with corresponding words approximately marked next to the waveform. The 3 command sentences are "Buy a 7:30ticket for freezenith "," at's the weather today "and" Text Lucy and Text her th the house for diner signed ". The results also indicate that unique patterns also exist in different command sentences, and that they are not simple combinations of each word pattern, but are caused by speaking habits such as continuous reading and weak reading.
The foregoing embodiments may be modified in many different ways by those skilled in the art without departing from the spirit and scope of the invention, which is defined by the appended claims and all changes that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (6)
1. A silent lip language identification method is characterized in that millimeter wave signals serving as carrier waves are continuously sent out and focused in the oral cavity area of a user, the millimeter wave signals are modulated and partially reflected on the phase through the speaking behavior of the user, the reflected signals are converted to a baseband and corrected, and then voice phase fuzzy linear reconstruction based on triangular transformation is adopted to obtain the speaking behavior information of the user;
the carrier wave is frequency modulation continuous wave;
the carrier wave is sawtooth wave X c (t)=A cos[2πf c t+φ(t)]Wherein: a is amplitude, f c Is the carrier frequency and is,phase noise for the transmitter;
the reflected signal is converted to a baseband to obtain: wherein: a. The I And A Q The amplitudes of the I and Q signals are, theta is a constant phase shift and->Is residual phase noise, λ is carrier wavelength, DC I And DC Q Is the DC offset in the I and Q signals;
the speech phase fuzzy linear reconstruction based on the triangular transformation refers to: the correction signal and the signal are differentiated and then integrated in sequence, so that displacement information is obtained, and a specific time domain expression and a discrete form thereof are as follows: after displacement information of silent lip language movement is obtained, a multi-dimensional feature vector is further obtained by using a feature extraction method in machine learning, or features of different lip languages are identified by using a convolutional neural network in deep learning.
2. A silent lip language identification system according to the method of claim 1, comprising: power supply unit, radar transceiver, carrier wave generation unit and intermediate frequency amplification unit, wherein: the power supply unit is connected with other units and provides working voltage, the input end of the radar transceiver can be independently selected to be connected with the carrier generation unit or connected with fixed reference voltage through a switch, the output end of the radar transceiver is connected with the intermediate frequency amplification unit and transmits I/Q signals, and the intermediate frequency amplification unit is connected with the signal output end and transmits the amplified I/Q signals.
3. The system of claim 2, wherein said radar transceiver comprises: power amplifier, low noise amplifier, quadrature mixer, polyphase filter, voltage controlled oscillator, packaged transmit receive antenna and local oscillator, wherein: the power amplifier is connected with the local oscillator and the transmitting antenna respectively and transmits a transmitting signal, the input end of the low-noise amplifier is connected with the receiving antenna and transmits a receiving signal, the quadrature mixer is connected with the low-noise amplifier and transmits the receiving signal converted to a baseband, the polyphase filter is connected with the voltage-controlled oscillator, and the voltage-controlled oscillator is connected with the input voltage and the local oscillator respectively.
4. The system of claim 2, wherein the carrier generation unit is a self-oscillating circuit designed based on a triangular wave generation circuit, and different integration paths are realized by using unidirectional conductivity of a diode, the circuit comprising: the input hysteresis comparator of homophase and integral arithmetic circuitry, wherein: when the time constant of the forward integration is far larger than that of the backward integration, the difference between the slope of the rising edge and the slope of the falling edge is large, so that the triangular wave is converted into the sawtooth wave.
5. The system as claimed in claim 4, wherein the self-oscillation circuit further comprises a trimming potentiometer for controlling the amplitude and period of the sawtooth wave to achieve an adjustable sweep around the reference voltage.
6. The system of claim 2, further comprising an intermediate frequency amplifier coupled to the radar transceiver for increasing the signal-to-noise level of the output of the rf mixer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010016710.9A CN111091831B (en) | 2020-01-08 | 2020-01-08 | Silent lip language recognition method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010016710.9A CN111091831B (en) | 2020-01-08 | 2020-01-08 | Silent lip language recognition method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111091831A CN111091831A (en) | 2020-05-01 |
CN111091831B true CN111091831B (en) | 2023-04-07 |
Family
ID=70398876
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010016710.9A Active CN111091831B (en) | 2020-01-08 | 2020-01-08 | Silent lip language recognition method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111091831B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113628617A (en) * | 2020-05-09 | 2021-11-09 | 西安电子科技大学青岛计算技术研究院 | Intelligent voice equipment control method based on millimeter wave radar |
CN111505601A (en) * | 2020-05-21 | 2020-08-07 | 上海交通大学 | Linear motion demodulation implementation method based on improved differential cross multiplication |
CN111856422A (en) * | 2020-07-03 | 2020-10-30 | 西安电子科技大学 | Lip language identification method based on broadband multichannel millimeter wave radar |
CN111986674B (en) * | 2020-08-13 | 2021-04-09 | 广州仿真机器人有限公司 | Intelligent voice recognition method based on three-level feature acquisition |
CN113314121B (en) * | 2021-05-25 | 2024-06-04 | 北京小米移动软件有限公司 | Soundless voice recognition method, soundless voice recognition device, soundless voice recognition medium, soundless voice recognition earphone and electronic equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015210419A (en) * | 2014-04-28 | 2015-11-24 | カシオ計算機株式会社 | Converter, method, and program |
CN106778179A (en) * | 2017-01-05 | 2017-05-31 | 南京大学 | A kind of identity identifying method based on the identification of ultrasonic wave lip reading |
CN107171994A (en) * | 2017-06-06 | 2017-09-15 | 南京理工大学 | Radio Fuze Signal is recognized and reconfiguration system and method |
CN110584631A (en) * | 2019-10-10 | 2019-12-20 | 重庆邮电大学 | Static human heartbeat and respiration signal extraction method based on FMCW radar |
-
2020
- 2020-01-08 CN CN202010016710.9A patent/CN111091831B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015210419A (en) * | 2014-04-28 | 2015-11-24 | カシオ計算機株式会社 | Converter, method, and program |
CN106778179A (en) * | 2017-01-05 | 2017-05-31 | 南京大学 | A kind of identity identifying method based on the identification of ultrasonic wave lip reading |
CN107171994A (en) * | 2017-06-06 | 2017-09-15 | 南京理工大学 | Radio Fuze Signal is recognized and reconfiguration system and method |
CN110584631A (en) * | 2019-10-10 | 2019-12-20 | 重庆邮电大学 | Static human heartbeat and respiration signal extraction method based on FMCW radar |
Non-Patent Citations (2)
Title |
---|
JIAYAO TAN et al..《 SilentKey: A New Authentication Framework through Ultrasonic-based Lip Reading》.《Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies》.2018,第2卷(第1期),第1-18页. * |
W.Xu et al..《Robust Doppler radar demodulation via compressed sensing》.《ELECTRONICS LETTERS》.2012,第48卷(第22期),第1-2页. * |
Also Published As
Publication number | Publication date |
---|---|
CN111091831A (en) | 2020-05-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111091831B (en) | Silent lip language recognition method and system | |
US9846226B2 (en) | Motion detection device | |
US9645234B2 (en) | RFID device, methods and applications | |
Costanzo et al. | Energy autonomous UWB localization | |
Li et al. | Recent advances in Doppler radar sensors for pervasive healthcare monitoring | |
Zhou et al. | Ultra low-power UWB-RFID system for precise location-aware applications | |
US8924214B2 (en) | Radar microphone speech recognition | |
Wu et al. | Dynamic hand gesture recognition using FMCW radar sensor for driving assistance | |
Bao et al. | A wirelessly powered UWB RFID sensor tag with time-domain analog-to-information interface | |
Wen et al. | Silent speech recognition based on short-range millimeter-wave sensing | |
CN102247146A (en) | Wireless sensing device and method | |
Heidrich et al. | Local positioning with passive UHF RFID transponders | |
Yavari et al. | System-on-Chip based Doppler radar occupancy sensor | |
US20230358856A1 (en) | Harmonic radar based on field programmable gate array (fpga) and deep learning | |
Hui et al. | Near-field coherent sensing of vibration with harmonic analysis and balance signal injection | |
CN110763923A (en) | Specific absorption rate value control method and mobile terminal | |
CN109738885A (en) | A kind of life detection radar system and method based on random code modulated sinusoid signal | |
Eggimann et al. | Low power embedded gesture recognition using novel short-range radar sensors | |
Liu et al. | Ultrasound-based 3-D gesture recognition: Signal optimization, trajectory, and feature classification | |
Zhao et al. | Gesture Recognition System Resilient to Interdevice Interference Based on Direct Sequence Spread Spectrum | |
Chinnam et al. | Implementation of a low cost synthetic aperture radar using software defined radio | |
Lai et al. | Finger gesture sensing and recognition using a Wi-Fi-based passive radar | |
Fabbri et al. | Micropower design of an energy autonomous rf tag for uwb localization applications | |
Fang et al. | A silicon-based radio platform for integrated edge sensing and communication toward sustainable healthcare | |
Yuan et al. | A high-sensitivity low-power vital sign radar sensor based on super-regenerative oscillator architecture |
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 |