In the era of smart devices and connected neighborhoods, the ubiquitous monitoring and care of patients are possible with the Internet of Medical Things (IoMT). Smart healthcare devices may serve their purpose well when they are able to share patient’s data with each other. However, data formats vary widely across vendors, rendering these devices not interoperable. Recent solutions mostly rely on cloud services where a source device uploads the data, and the sink devices download it conforming to their own native formats. However, the quality of service is expected to deteriorate in a cloud processing regime with inherent network delays and traffic congestion, and the real-time data acquisition and manipulation is, therefore, not possible. This article presents MeDIC, a framework of Medical Data Interoperability through Collaboration of healthcare devices. MeDIC improves over a cloud-based IoMT by utilizing translation resources at the network edge, with its probing and translating agents. The probing agents maintain a capability list of MeDIC devices within a local network and enable one MeDIC device to request data conversion from another device when the former is not capable of this conversion by itself. The translating agent of the later then converts the data into the required format and returns it to the former. These novel agents allow IoMT devices to share their redundant computing resources for data translations in order to minimize cloud accesses. Legacy devices are supported through MeDIC-enabled, fog resource managers. We evaluate MeDIC in four use cases with rigorous simulations, which prove that this collaborative framework not only reduces the uplink traffic but also improves the response time, which is critical in real-time medical applications.
This paper considers the problem of anomaly detection in an outdoor environment where surveillance cameras are usually installed to monitor activities of general public. A novel solution is proposed which combines audio and visual data to automatically detect abnormal activities. The proposed anomaly detection algorithm makes use of both visual and audio features to automatically detect anomalous activities in scenes. Visual features such as optical flow technique combined with particle swam optimization and social force model are used, whereas, acoustic features such as, energy, zero crossing rate, volume, spectral-centroid, spectral spread, spectral roll-off, spectral flux, cross correlation and the mel-frequency cepstral coefficients (MFCCs) are used. An anomaly inference is developed which is based on both visual and audio features. The performance of the proposed algorithm is evaluated by testing it on the publicly available UMN datasets combined with the audio recordings. The proposed algorithm is compared with state-of-the-art techniques and is shown to achieve improved performance in terms of accuracy.
The advancements in Edge computing have paved the way for deep learning in real-time systems. One of the beneficiaries is an adaptive traffic control system that responds to real-time traffic observations by governing the signal phase and timings. Reinforcement Learning (RL) is extensively utilized in the literature in order to decrease traffic congestion in a road network. However, most of the previous works leverage centralized and cloud-based RL due to the computational complexity of underlying deep neural networks (DNN). Therefore, a persistent challenge towards adopting Edge learning is in devising a Multi-Agent RL in which agents are simplified, and their state spaces are localized but they perform comparable to the centralized RL. This article presents a Collaborative and Adaptive Signaling on the Edge (CASE), a novel Multi-Agent RL approach to control the traffic signals’ phase and timing. Each signalized intersection in the road network is provided with an Edge Learning Platform which hosts an RL-Agent that observes local traffic states and learns an optimum signal policy. Moreover, CASE allows collaboration among RL-Agents by sharing their signal phase and timings to achieve convergence and performance. This collaboration is limited to one’s direct neighbours only to minimize the computational complexity. We performed rigorous evaluations in terms of the choice of RL methods and their state space/reward and found that our collaborative state-space has resulted in a performance comparable to a centralized RL yet with a cost similar to the decentralized RL. Finally, a performance comparison of the CASE controller ported to the state-of-the-art Edge learning platforms is presented in this article. The results show that the proposed CASE controller can achieve real-time performance when ported to a general-purpose GPU-based platform. This arrangement achieves more than 8 times improvement in computational time over conventional embedded platforms.
Global navigation satellite systems have been used for reliable location-based services in outdoor environments. However, satellite-based systems are not suitable for indoor positioning due to low signal power inside buildings and low accuracy of 5 m. Future smart homes demand low-cost, high-accuracy and low-power indoor positioning systems that can provide accuracy of less than 5 m and enable battery operation for mobility and long-term use. We propose and implement an intelligent, highly accurate and low-power indoor positioning system for smart homes leveraging Gaussian Process Regression (GPR) model using information-theoretic gain based on reduction in differential entropy. The system is based on Time Difference of Arrival (TDOA) and uses ultra-low-power radio transceivers working at 434 MHz. The system has been deployed and tested using indoor measurements for two-dimensional (2D) positioning. In addition, the proposed system provides dual functionality with the same wireless links used for receiving telemetry data, with configurable data rates of up to 600 Kbauds. The implemented system integrates the time difference pulses obtained from the differential circuitry to determine the radio frequency (RF) transmitter node positions. The implemented system provides a high positioning accuracy of 0.68 m and 1.08 m for outdoor and indoor localization, respectively, when using GPR machine learning models, and provides telemetry data reception of 250 Kbauds. The system enables low-power battery operation with consumption of <200 mW power with ultra-low-power CC1101 radio transceivers and additional circuits with a differential amplifier. The proposed system provides low-cost, low-power and high-accuracy indoor localization and is an essential element of public well-being in future smart homes.
In the era of non-volatile memories, the racetrack memory is a promising technology to pack hundreds of bits in a magnetic nanowire. A solid-state read head is grown alongside the nanowire to sense individual bits which are pushed across the head by a shifting force. However, the probabilistic nature of this shifting movement inflicts positional errors. Therefore, robust and low-cost error correcting codes are essential for a reliable alternative in on-chip memories and storage applications. Recent works focus on Varshamov-Tenengolts (VT) codes which can correct all single bit insertions and deletions. However, VT codes are incapable of detecting multiple deletions/insertions. Because a positional error corrupts multiple data words, multi-bit positional error detection is critical for racetrack memories. In this article, we propose a novel positional single error correction and double error detection (P-SECDED) code in the context of racetrack memories with a single read head. In particular, we adopt a postamble-based approach where a VT-encoded codeword appends a carefully selected bit-pattern, stored on the racetrack. We rigorously analyze the limitations of the postamble method, and deduce a criterion for postamble selection. We further provide a methodology to optimize this postamble selection in order to correct all single-bit errors and as much of two-bit errors as possible. Finally, we prove that all incurable two-bit errors are successfully detected. To the best of our knowledge, this work is the first attempt to provide P-SECDED fault-tolerance to three-dimensional racetrack memories which cannot afford multiple read heads.