Recently, hand gesture recognition systems have become increasingly interesting to researchers in the field of human-computer interfaces. Real-world systems for human dynamic hand gesture recognition is challenging as: 1) the system must be robust to various conditions; 2) there is a rich diversity in how people perform hand gestures, making hand gesture recognition difficult; and 3) the system must detect and recognize hand gestures continuously using unsegmented input streams in order to avoid noticeable lag between performing a gesture and its classification. In this paper, to address these challenges, we present Latern, a novel system for dynamic continuous hand gesture recognition based on a frequency-modulated continuous wave radar sensor. The radar system does not depend on lighting, noise, or atmospheric conditions. We employ a recurrent 3-D convolutional neural network to perform the classification of dynamic hand gestures. To enhance the processing performance, a connectionist temporal classification algorithm is used to train the network to predict class labels from inprogress gestures in unsegmented input streams. The experimental results show that Latern is able to achieve high recognition rates of 96%, which is higher than state-of-the-art hand gesture recognition systems. In addition, the conclusion in this paper can be used for a real-time hand gesture recognition system design.

In recent years, non-contact radar detection technology has been able to achieve long-term and long-range detection for the breathing and heartbeat signals. Compared with contact-based detection methods, it brings a more comfortable and a faster experience to the human body, and it has gradually received attention in the field of radar sensing. Therefore, this paper extends the application of millimeter-wave radar to the field of health care. The millimeter-wave radar first transmits the frequency-modulated continuous wave (FMCW) and collects the echo signals of the human body. Then, the phase information of the intermediate frequency (IF) signals including the breathing and heartbeat signals are extracted, and the Direct Current (DC) offset of the phase information is corrected using the circle center dynamic tracking algorithm. The extended differential and cross-multiply (DACM) is further applied for phase unwrapping. We propose two algorithms, namely the compressive sensing based on orthogonal matching pursuit (CS-OMP) algorithm and rigrsure adaptive soft threshold noise reduction based on discrete wavelet transform (RA-DWT) algorithm, to separate and reconstruct the breathing and heartbeat signals. Then, a frequency-domain fast Fourier transform and a time-domain autocorrelation estimation algorithm are proposed to calculate the respiratory and heartbeat rates. The proposed algorithms are compared with the contact-based detection ones. The results demonstrate that the proposed algorithms effectively suppress the noise and harmonic interference, and the accuracies of the proposed algorithms for both respiratory rate and heartbeat rate reach about 93%.

The security threats caused by the popularity of Unmanned Aerial Vehicles (UAVs) have received much attention. In this paper, a UAV detection and identification system based on WiFi signal and radio frequency (RF) fingerprint is proposed. The system firstly conducts UAV detection and after the UAV is detected, fractal dimension (FD), axially integrated bispectra (AIB), and square integrated bispectra (SIB) are extracted as UAV RF fingerprints due to their applicability and reliability. Furthermore, we propose weighted AIB and SIB fingerprints to identify UAVs. Since the high dimensionality of AIB and SIB features, the principal component analysis (PCA) algorithm is applied to reduce the dimensionality of these two features. Then the neighborhood component analysis (NCA) algorithm is utilized to weight the dimensions of the two features, AIB and SIB. The extracted UAV fingerprints are stored as training data and test data, respectively. Finally, machine learning algorithms are utilized to identify UAVs. The identification results are as follows: In the indoor scenario, the average identification accuracy of three features (FD, AIB, SIB) are 100%, 97.23%, and 96.11%, respectively. In outdoor scenario, the identification accuracy of three features are 100%, 95.00%, and 93.50%, respectively.

With the rapid increase of industrial systems, industrial spectrum is stepping into the era of big data, and at the same time spectrum resources are facing serious shortage. Cognitive industrial system (CIS) based on cognitive radio can improve spectrum utilization by accessing the idle spectrum licensed to primary user (PU). However, the CIS must find enough idle channels by performing spectrum sensing. In this paper, a reinforcement learning-based multislot double-threshold spectrum sensing with Bayesian fusion is proposed to sense industrial big spectrum data, which can find required idle channels faster while guaranteeing spectrum sensing performance. Double thresholds are set to guarantee both high detection probability and spectrum access probability, and weighed energy detection is proposed to maximize detection probability when the energy statistic falls into the confusion area between the double thresholds. Bayesian fusion is proposed get a final decision on the channel availability by combining the local sensing decisions of all the time slots. An idle channel prediction and selection algorithm is proposed to predict the idle probability of each channel and find required idle channels from the sorted channel set. From simulation results, the proposed spectrum sensing scheme outperforms cooperative spectrum sensing and energy detection, which can predict idle channels accurately and get needed idle channels with fewer sensing operations.

With the broad deployment of Wi-Fi networks, the Received Signal Strength (RSS) based Wi-Fi indoor localization has attained much interest of both academia and industry. At present, most of the currently available Wi-Fi indoor localization techniques focus on increasing the localization accuracy. However, few of them take into account the diversity of Wi-Fi signal distributions and the measurement error associated with RSS values owing to the complicated indoor environment, which consequently results in the low robustness of indoor localization systems. Thus, with the motivation to tackle this gripping problem, we design a new hybrid hypothesis test based on the idea of Asymptotic Relative Efficiency (ARE), which exploits signal distributions by considering different Access Point (AP) contributions to the Wi-Fi indoor localization accuracy. In concrete terms, first of all, the Jarque-Bera (JB) test is used to perform the normality test on the Wi-Fi signal distribution at each Reference Point (RP), and then the Chi-squared Automatic Interaction Detection (CHAID) approach is applied to obtain each AP contribution degree. Secondly, based on the evaluation of the JB test on the Wi-Fi signal distribution, the hybrid Mann-Whitney U and T test is applied to find the set of matching RPs corresponding to each newly-collected RSS data. Finally, the target location estimate is acquired by using the K-Nearest Neighbor (KNN), where the contribution degree of each AP is assigned as the weight during the calculation to find matching RPs. From the extensive experimental results, it is evident that the proposed approach can successfully improve the system performance by achieving a higher localization accuracy and enhanced robustness when compared with the state-of-the-art Wi-Fi indoor localization techniques.

This paper uses an information-theoretic lens to view the error bound of Wireless Local Area Network (WLAN) localization, which is recognized as one of the superior candidate localization techniques in the GPS-denied environment. Interestingly, we analogize the process of WLAN localization into the one of information propagation in a parallel Gaussian noisy channel, and then derive the corresponding localization error bound from the channel capacity of the analogical information propagation system. Experimental results show that compared with the widely-known Cramer-Rao Lower Bound (CRLB), the proposed approach performs better in localization error bound estimation under most of the cases of different Access Point (AP) deployment and Reference Point (RP) calibration.