No abstract

In this article, we present a survey of recent advances in passive human behaviour recognition in indoor areas using the channel state information (CSI) of commercial WiFi systems. Movement of human body causes a change in the wireless signal reflections, which results in variations in the CSI. By analyzing the data streams of CSIs for different activities and comparing them against stored models, human behaviour can be recognized. This is done by extracting features from CSI data streams and using machine learning techniques to build models and classifiers. The techniques from the literature that are presented herein have great performances, however, instead of the machine learning techniques employed in these works, we propose to use deep learning techniques such as long-short term memory (LSTM) recurrent neural network (RNN), and show the improved performance. We also discuss about different challenges such as environment change, frame rate selection, and multi-user scenario, and suggest possible directions for future work.

No abstract

No abstract

In this paper, we consider the problem of minimizing the mean completion delay in wireless broadcast for instantly decodable network coding. We first formulate the problem as a stochastic shortest path (SSP) problem. Although finding the packet selection policy using SSP is intractable, we use this formulation to draw the theoretical properties of efficient selection algorithms. Based on these properties, we propose a simple online selection algorithm that efficiently minimizes the mean completion delay of a frame of broadcast packets, compared to the random and greedy selection algorithms with a similar computational complexity. Simulation results show that our proposed algorithm indeed outperforms these random and greedy selection algorithms.

No abstract

Vehicle-to-vehicle communications via dedicatedshort-range-communication (DSRC) devices will enable safety applications such as cooperative collision warning. These devices use the IEEE 802.11p standard to support low-latency vehicleto-vehicle and vehicle-to-infrastructure communications. However, a major challenge for the cooperative collision warning is to accurately determine the location of vehicles. In this paper, we present a novel cooperative-vehicle-position-estimation algorithm which can achieve a higher accuracy and more reliability than the existing global-positioning-system-based positioning solutions by making use of intervehicle-distance measurements taken by a radio-ranging technique. Our algorithm uses signal-strengthbased intervehicle-distance measurements, vehicle kinematics, and road maps to estimate the relative positions of vehicles in a cluster. We have analyzed our algorithm by examining its performance-bound, computational-complexity, and communicationoverhead requirements. In addition, we have shown that the accuracy of our algorithm is superior to previously proposed localization algorithms.Index Terms-Dedicated short-range communication (DSRC), IEEE802.11p, localization, position estimation, vehicular networks, wireless access in vehicular environment, wireless communication.

Medical datasets are often highly imbalanced with overrepresentation of common medical problems and a paucity of data from rare conditions. We propose simulation of pathology in images to overcome the above limitations. Using chest X-rays as a model medical image, we implement a generative adversarial network (GAN) to create artificial images based upon a modest sized labeled dataset. We employ a combination of real and artificial images to train a deep convolutional neural network (DCNN) to detect pathology across five classes of chest X-rays. Furthermore, we demonstrate that augmenting the original imbalanced dataset with GAN generated images improves performance of chest pathology classification using the proposed DCNN in comparison to the same DCNN trained with the original dataset alone. This improved performance is largely attributed to balancing of the dataset using GAN generated images, where image classes that are lacking in example images are preferentially augmented.Index Terms-Chest X-ray, data augmentation, deep convolutional neural network (DCNN), generative adversarial network (GAN), simulated images.