Studies show that the early (stage I) diagnosis of cancer increases the survival rate of patients, and significantly reduces treatment costs. Millimeter-wave radars can detect skin tumors based on the difference between the electrical properties of melanomas and healthy skin tissues. This paper proposes a low-power multitone continuous-wave radar design at 77 GHz for biomedical imaging applications, to be used for skin cancer detection. The sensor implementation is based on a low-cost Miniature Hybrid Microwave Integrated Circuit (MHMIC) design. The entire sensor was integrated on a 0.127mm thin ceramic substrate. Two 16-element patch antenna arrays are implemented in the transmitter and receiver modules. The receiver is a six-port homodyne quadrature down-converter. The integrated power detectors are fabricated using HSCH-9161 Schottky diodes. The sensor was encapsulated in a metallic fixture with dimensions 35 by 45 mm. Two cascaded amplifier circuits are designed and implemented for amplifying baseband voltages at the output of each power detector. The proposed radar design has the ability to detect the dielectic properties of tissues, making it suitable for the detection of melanomas with an accuracy on the order of tens of microns.
Human movement detection based on millimeter-wave radar sensors is a technology of interest in various areas such as for smart surveillance, security, behavioral biometrics, biomedical systems, robotics, etc. This paper shows the feasibility and effectiveness of using a compact 24 GHz Doppler radar with a built-in low-noise microwave amplifier (LNA) for detecting and extracting signals coming from human motion. Reliability and accuracy is assessed based on a comprehensive theoretical analysis, and on simulation results followed by experimental investigations. A continuous wavelet transform (CWT) is used to decompose in-phase and quadrature ( ${I/Q}$ ) baseband signals to extract information about the dynamics of the system. The dataset consists of 1000 recordings in 8 motion classes (standing, walking, sitting, etc.). We propose to apply a two-channel convolutional neural network (CNN), which is composed of two CNN channels, for learning high-level features from time-domain signals and CWT spectrograms. One channel has four one-dimensional (1D) convolutional and pooling layers, and the other channel is made of three two-dimensional (2D) convolutional and pooling layers. In addition, the ${I/Q}$ signals are denoised by using Savitzky-Golay filtering, and both noisy and denoised signals are used as input signals for deep learning data augmentation purpose. We achieved an overall classification accuracy rate of 98.85% in motion classification for a two-branch CNN architecture, and an accuracy rate of 95.3% for a one-branch 2D-CNN. Our results show that a dual-channel CNN model can greatly increase the classification capabilities of human motion recognition and classification, and the proposed method can be effectively used with various radar signal classifications.
Noise reduction is one of the most important process used for signal processing in communication systems. The signal-to-noise ratio (SNR) is a key parameter to consider for minimizing the bit error rate (BER). The inherent noise found in millimeter-wave systems is mainly a combination of white noise and phase noise. Increasing the SNR in wireless data transfer systems can lead to reliability and performance improvements. To address this issue, we propose to use a recurrent neural network (RNN) with a long short-term memory (LSTM) autoencoder architecture to achieve signal noise reduction. This design is based on a composite LSTM autoencoder with a single encoder layer and two decoder layers. A V-band receiver test bench is designed and fabricated to provide a high-speed wireless communication system. Constellation diagrams display the output signals measured for various random sequences of PSK and QAM modulated signals. The LSTM autoencoder is trained in real time using various noisy signals. The trained system is then used to reduce noise levels in the tested signals. The SNR of the designed receiver is of the order of 11.8dB, and it increases to 13.66dB using the three-level LSTM autoencoder. Consequently, the proposed algorithm reduces the bit error rate from 10 −8 to 10 −11 . The performance of the proposed algorithm is comparable to other noise reduction strategies. Augmented denoised signals are fed into a ResNet-152 deep convolutional network to perform the final classification. The demodulation types are classified with an accuracy of 99.93%. This is confirmed by experimental measurements.
A target’s movements and radar cross sections are the key parameters to consider when designing a radar sensor for a given application. This paper shows the feasibility and effectiveness of using 24 GHz radar built-in low-noise microwave amplifiers for detecting an object. For this purpose a supervised machine learning model (SVM) is trained using the recorded data to classify the targets based on their cross sections into four categories. The trained classifiers were used to classify the objects with varying distances from the receiver. The SVM classification is also compared with three methods based on binary classification: a one-against-all classification, a one-against-one classification, and a directed acyclic graph SVM. The level of accuracy is approximately 96.6%, and an F1-score of 96.5% is achieved using the one-against-one SVM method with an RFB kernel. The proposed contactless radar in combination with an SVM algorithm can be used to detect and categorize a target in real time without a signal processing toolbox.
A continuous-wave (CW) radar sensor design based on a millimetre-wave six-port interferometer is proposed. A complete sensor prototype is conceived of, fabricated and measured at 77 GHz for short-range professional and industrial applications. This sensor is designed to measure distances and Doppler frequencies with high accuracy, at a reasonable cost. Accurate phase measurements are also performed using the six-port technology, which makes it a promising candidate for CW radar sensing applications. Advances in the performance and functionality of six-port sensors are surveyed to highlight recent progress in this area. These include improvements in design, low power consumption, high signal to noise ratio, compactness, robustness and simplicity in realization. Given the fact that they are easy to fabricate, due to the lack of active circuits and being highly accurate, it is expected that six-port sensors will significantly contribute to the development of human tracking devices and industrial sensors in the near future. The entire circuit prototype, including the transmitter, the receiver antenna, the six-port interferometer and the four power detectors have been integrated on a die. The circuit is fabricated using a hybrid integrated technology on a 127-m ceramic substrate with a relative permittivity of . Calibrated tuning forks are used to assess the performance of the six-port sensor experimentally for various frequencies.