“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

More particularly, calculations are developed and examined to reduce the entire quantity of Wireless access points as well as their locations in almost any given atmosphere while with the throughput needs and the necessity to ensure every place in the area can achieve a minimum of k APs. This paper concentrates on using Wireless for interacting with and localizing the robot. We've carried out thorough studies of Wireless signal propagation qualities both in indoor and outside conditions, which forms the foundation for Wireless AP deployment and communication to be able to augment how human operators communicate with this atmosphere, a mobile automatic platform is developed. Gas and oil refineries could be a harmful atmosphere for various reasons, including heat, toxic gasses, and unpredicted catastrophic failures. When multiple Wireless APs are close together, there's a possible for interference. A graph-coloring heuristic can be used to find out AP funnel allocation. Additionally, Wireless fingerprinting based localization is developed. All of the calculations implemented are examined in real life situations using the robot developed and answers are promising. For example, within the gas and oil industry, during inspection, maintenance, or repair of facilities inside a refinery, people might be uncovered to seriously high temps to have a long time, to toxic gasses including methane and H2S, and also to unpredicted catastrophic failures.

/pdf/internet-of-vehicles-from-intelligent-grid-to-autonomous-pma0tn3ofd.pdf

Internet of Vehicles: From Intelligent Grid to Autonomous Cars and Vehicular Clouds

In millimeter-wave communications, multiple-input-multiple-output (MIMO) systems use large antenna arrays to achieve high gain and spectral efficiency. These massive MIMO systems employ hybrid beamformers to reduce power consumption associated with fully digital beamforming in large arrays. Further savings in cost and power are possible through the use of subarrays. Unlike prior works that resort to large latency methods such as optimization and greedy search for subarray selection, we propose a deep-learning-based approach in order to overcome the complexity issue without causing significant performance loss. We formulate antenna selection and hybrid beamformer design as a classification/prediction problem for convolutional neural networks (CNNs). For antenna selection, the CNN accepts the channel matrix as input and outputs a subarray with optimal spectral efficiency. The resultant subarray channel matrix is then again fed to a CNN to obtain analog and baseband beamformers. We train the CNNs with several noisy channel matrices that have different channel statistics in order to achieve a robust performance at the network output. Numerical experiments show that our CNN framework provides an order better spectral efficiency and is 10 times faster than the conventional techniques. Further investigations with quantized-CNNs show that the proposed network, saved in no more than 5 bits, is also suited for digital mobile devices.

Joint Antenna Selection and Hybrid Beamformer Design Using Unquantized and Quantized Deep Learning Networks

Recognition of human movements with radar for ambient activity monitoring is a developed area of research that yet presents outstanding challenges to address In real environments, activities and movements are performed with seamless motion, with continuous transitions between activities of different duration and a large range of dynamic motions, compared with discrete activities of fixed-time lengths which are typically analysed in the literature This paper proposes a novel approach based on recurrent LSTM and Bi-LSTM network architectures for continuous activity monitoring and classification This approach uses radar data in the form of a continuous temporal sequence of micro-Doppler or range-time information, differently from from other conventional approaches based on convolutional networks that interpret the radar data as images Experimental radar data involving 15 participants and different sequences of 6 actions are used to validate the proposed approach It is demonstrated that using the Doppler-domain data together with the Bi-LSTM network and an optimal learning rate can achieve over 90% mean accuracy, whereas range-domain data only achieved approximately 76% The details of the network architectures, insights in their behaviour as a function of key hyper-parameters such as the learning rate, and a discussion on their performance across are provided in the paper

/pdf/continuous-human-activity-classification-from-fmcw-radar-4a15x2ocmk.pdf

Continuous Human Activity Classification From FMCW Radar With Bi-LSTM Networks

This paper focuses on the detection and classification of micro-unmanned aerial vehicles (UAVs)using radio frequency (RF)fingerprints of the signals transmitted from the controller to the micro-UAV. In the detection phase, raw signals are split into frames and transformed into the wavelet domain to remove the bias in the signals and reduce the size of data to be processed. A naive Bayes approach, which is based on Markov models generated separately for UAV and non-UAV classes, is used to check for the presence of a UAV in each frame. In the classification phase, unlike the traditional approaches that rely solely on time-domain signals and corresponding features, the proposed technique uses the energy transient signal. This approach is more robust to noise and can cope with different modulation techniques. First, the normalized energy trajectory is generated from the energy-time-frequency distribution of the raw control signal. Next, the start and end points of the energy transient are detected by searching for the most abrupt changes in the mean of the energy trajectory. Then, a set of statistical features is extracted from the energy transient. Significant features are selected by performing neighborhood component analysis (NCA)to keep the computational cost of the algorithm low. Finally, selected features are fed to several machine learning algorithms for classification. The algorithms are evaluated experimentally using a database containing 100 RF signals from each of 14 different UAV controllers. The signals are recorded wirelessly using a high-frequency oscilloscope. The data set is randomly partitioned into training and test sets for validation with the ratio 4:1. Ten Monte Carlo simulations are run and results are averaged to assess the performance of the methods. All the micro-UAVs are detected correctly and an average accuracy of 96.3% is achieved using the k-nearest neighbor (kNN)classification. Proposed methods are also tested for different signal-to-noise ratio (SNR)levels and results are reported.

Micro-UAV Detection and Classification from RF Fingerprints Using Machine Learning Techniques

We present an ultrashort range IEEE 802.11ad-based automotive joint radar-communications (JRC) framework, wherein we improve the radar's Doppler resilience by incorporating Prouhet–Thue–Morse sequences in the preamble. The proposed processing reveals detailed microfeatures of common automotive objects verified through extended scattering center models of animated pedestrian, bicycle, and car targets. Numerical experiments demonstrate 2.5% reduction in the probability of false alarm at low signal-to-noise-ratios and improvement in the peak-to-sidelobe level dynamic range up to Doppler velocities of $\pm 144$  km/h over conventional 802.11ad JRC.

Doppler-Resilient 802.11ad-Based Ultrashort Range Automotive Joint Radar-Communications System

Studies have demonstrated the usefulness of micro-Doppler signatures for classifying dynamic radar targets such as humans, helicopters, and wind turbines. However, these classification works are based on the assumption that the propagation channel consists of only a single moving target. When multiple targets move simultaneously in the channel, the micro-Dopplers, in their radar backscatter, superimpose thereby distorting the signatures. In this paper, we propose a method to detect multiple targets that move simultaneously in the propagation channel. We first model the micro-Doppler radar signatures of different movers using dictionary learning techniques. Then, we use a sparse coding algorithm to separate the aggregate radar backscatter signal from multiple targets into their individual components. We demonstrate that the disaggregated signals are useful for accurately detecting multiple targets.

Detection of Multiple Movers Based on Single Channel Source Separation of Their Micro-Dopplers

Occupancy detection and people counting technologies have important uses in many scenarios ranging from management of human resources, optimising energy use in intelligent buildings and improving public services in future smart cities. Wi-Fi based sensing approaches for these applications have attracted significant attention in recent years because of their ubiquitous nature, and ability to preserve the privacy of individuals being counted. In this paper, we present a Passive Wi-Fi Radar (PWR) technique for occupancy detection and people counting. Unlike systems which exploit the Wi-Fi Received Signal Strength (RSS) and Channel State Information (CSI), PWR systems can directly be applied in any environment covered by an existing WiFi local area network without special modifications to the Wi-Fi access point. Specifically, we apply Cross Ambiguity Function (CAF) processing to generate Range-Doppler maps, then we use Time-Frequency transforms to generate Doppler spectrograms, and finally employ a CLEAN algorithm to remove the direct signal interference. A Convolutional Neural Network (CNN) and sliding-window based feature selection scheme is then used for classification. Experimental results collected from a typical office environment are used to validate the proposed PWR system for accurately determining room occupancy, and correctly predict the number of people when using four test subjects in experimental measurements.

/pdf/occupancy-detection-and-people-counting-using-wifi-passive-328wqzrrvs.pdf

Occupancy Detection and People Counting Using WiFi Passive Radar

Radar images of humans and other concealed objects are considerably distorted by attenuation, refraction, and multipath clutter in indoor through-wall environments. Although several methods have been proposed for removing target-independent static and dynamic clutter, there still remain considerable challenges in mitigating target-dependent clutter especially when the knowledge of the exact propagation characteristics or analytical framework is unavailable. In this article, we focus on mitigating wall effects using a machine learning-based solution—denoising autoencoders—that does not require prior information of the wall parameters or room geometry. Instead, the method relies on the availability of a large volume of training radar images gathered in through-wall conditions and the corresponding clean images captured in line-of-sight conditions. During the training phase, the autoencoder learns how to denoise the corrupted through-wall images in order to resemble the free space images. We have validated the performance of the proposed solution for both static and dynamic human subjects. The frontal radar images of static targets are obtained by processing wideband planar array measurement data with 2-D array and range processing. The frontal radar images of dynamic targets are simulated using narrowband planar array data processed with 2-D array and Doppler processing. In both simulation and measurement processes, we incorporate considerable diversity in the target and propagation conditions. Our experimental results, from both simulation and measurement data, show that the denoised images are considerably more similar to the free-space images when compared to the original through-wall images.

Mitigation of Through-Wall Distortions of Frontal Radar Images Using Denoising Autoencoders

Recently, several machine learning algorithms have been applied for classifying micro-Doppler signatures from different human motions. However, these algorithms must demonstrate versatility in handling diversity in test and training data to be used for real-life scenarios. For example, situations may arise where the propagation channel or the presence of interference sources in the test site will permit only specific frequency bands of radar operation. These bands may differ from those used previously while training. In this paper, we examine the performances of three sparsity driven dictionary learning algorithms—synthesis, deep, and analysis—for learning unique features extracted from training data gathered across multiple carrier frequencies. These features are subsequently used for classifying test data from another distinct carrier frequency. Our experimental results, from measurement data, show that the dictionary learning algorithms are capable of extracting meaningful representations of the micro-Dopplers despite the rich frequency diversity in the data. In particular, the deep dictionary learning algorithm yields a high classification accuracy of 91% with a very low computational time for testing.

Shelly Vishwakarma

Papers

Doppler-Resilient 802.11ad-Based Ultrashort Range Automotive Joint Radar-Communications System

Detection of Multiple Movers Based on Single Channel Source Separation of Their Micro-Dopplers

Occupancy Detection and People Counting Using WiFi Passive Radar

Mitigation of Through-Wall Distortions of Frontal Radar Images Using Denoising Autoencoders

Dictionary Learning With Low Computational Complexity for Classification of Human Micro-Dopplers Across Multiple Carrier Frequencies