Search

With advances in the Internet of Things, patients in intensive care units are constantly monitored to expedite emergencies. Due to the COVID-19 pandemic, non-face-to-face monitoring has been required for the safety of patients and medical staff. A control center monitors the vital signs of patients in ICUs. However, some medical devices, such as ventilators and infusion pumps, operate in a standalone fashion without communication capabilities, requiring medical staff to check them manually. One promising solution is to use a robotic system with a camera. We propose a real-time optical digit recognition embedded system called ROMI. ROMI is a mobile robot that monitors patients by recognizing digits displayed on LCD screens of medical devices in real time. ROMI consists of three main functions for recognizing digits: digit localization, digit classification, and digit annotation. We developed ROMI by using Matlab Simulink, and the maximum digit recognition performance was 0.989 mAP on alexnet. The developed system was deployed on NVIDIA GPU embedded platforms: Jetson Nano, Jetson Xavier NX, and Jetson AGX Xavier. We also created a benchmark by evaluating the runtime performance by considering ten pre-trained CNN models and three NVIDIA GPU platforms. We expect that ROMI will support medical staff with non-face-to-face monitoring in ICUs, enabling more effective and prompt patient care. [ABSTRACT FROM AUTHOR]

In the vehicular ad-hoc networks (VANETs), wireless access in vehicular environments (WAVE) as the core networking technology is suitable for supporting safety-critical applications, but it is difficult to guarantee its performance when transmitting non-safety data, especially high volumes of data, in a multi-hop manner. Therefore, to provide non-safety applications effectively and reliably for users, we propose a hybrid V2V communication system (HVCS) using hierarchical networking architecture: a centralized control model for the establishment of a fast connection and a local data propagation model for efficient and reliable transmissions. The centralized control model had the functionality of node discovery, local ad-hoc group (LAG) formation, a LAG owner (LAGO) determination, and LAG management. The local data propagation indicates that data are transmitted only within the LAG under the management of the LAGO. To support the end-to-end multi-hop transmission over V2V communication, vehicles outside the LAG employ the store and forward model. We designed three phases consisting of concise device discovery (CDD), concise provisioning (CP), and data transmission, so that the HVCS is highly efficient and robust on the hierarchical networking architecture. Under the centralized control, the phase of the CDD operates to improve connection establishment time, and the CP is to simplify operations required for security establishment. Our HVCS is implemented as a two-tier system using a traffic controller for centralized control using cellular networks and a smartphone for local data propagation over Wi-Fi Direct. The HVCS' performance was evaluated using Veins, and compared with WAVE in terms of throughput, connectivity, and quality of service (QoS). The effectiveness of the centralized control was demonstrated in comparative experiments with Wi-Fi Direct. The connection establishment time measured was only 0.95 s for the HVCS. In the case of video streaming services through the HVCS, about 98% of the events could be played over 16 frames per second. The throughput for the streaming data was between 74% to 81% when the vehicle density was over 50%. We demonstrated that the proposed system has high throughput and satisfies the QoS of streaming services even though the end-to-end delay is a bit longer when compared to that of WAVE. [ABSTRACT FROM AUTHOR]

Standard upper-limb motor function impairment assessments, such as the Fugl-Meyer Assessment (FMA), are a critical aspect of rehabilitation after neurological disorders. These assessments typically take a long time (about 30 min for the FMA) for a clinician to perform on a patient, which is a severe burden in a clinical environment. In this paper, we propose a framework for automating upper-limb motor assessments that uses low-cost sensors to collect movement data. The sensor data is then processed through a machine learning algorithm to determine a score for a patient's upper-limb functionality. To demonstrate the feasibility of the proposed approach, we implemented a system based on the proposed framework that can automate most of the FMA. Our experiment shows that the system provides similar FMA scores to clinician scores, and reduces the time spent evaluating each patient by 82%. Moreover, the proposed framework can be used to implement customized tests or tests specified in other existing standard assessment methods.

In smart environments, target tracking is an essential service used by numerous applications from activity recognition to personalized infotaintment. The target tracking relies on sensors with known locations to estimate and keep track of the path taken by the target, and hence, it is crucial to have an accurate map of such sensors. However, the need for manually entering their locations after deployment and expecting them to remain fixed, significantly limits the usability of target tracking. To remedy this drawback, we present a self-configuring and device-free localization protocol based on genetic algorithms that autonomously identifies the geographic topology of a network of ultrasonic range sensors as well as automatically detects any change in the established network structure in less than a minute and generates a new map within seconds. The proposed protocol significantly reduces hardware and deployment costs thanks to the use of low-cost off-the-shelf sensors with no manual configuration. Experiments on two real testbeds of different sizes show that the proposed protocol achieves an error of 7.16~17.53 cm in topology mapping, while also tracking a mobile target with an average error of 11.71~18.43 cm and detecting displacements of 1.41~3.16 m in approximately 30 s.

Research on smart environments saturated with ubiquitous computing devices is rapidly advancing while raising serious privacy issues. According to recent studies, privacy concerns significantly hinder widespread adoption of smart home technologies. Previous work has shown that it is possible to infer the activities of daily living within environments equipped with wireless sensors by monitoring radio fingerprints and traffic patterns. Since data encryption cannot prevent privacy invasions exploiting transmission pattern analysis and statistical inference, various methods based on fake data generation for concealing traffic patterns have been studied. In this paper, we describe an energy-efficient, light-weight, low-latency algorithm for creating dummy activities that are semantically similar to the observed phenomena. By using these cloaking activities, the amount of  fake data transmissions can be flexibly controlled to support a trade-off between energy efficiency and privacy protection. According to the experiments using real data collected from a smart home environment, our proposed method can extend the lifetime of the network by more than 2× compared to the previous methods in the literature. Furthermore, the activity cloaking method supports low latency transmission of real data while also significantly reducing the accuracy of the wireless snooping attacks.

In a point-of-care (POC) setting, it is critically important to reliably count the number of specific cells in a blood sample. Software-based cell counting, which is far faster than manual counting, while much cheaper than hardware-based counting, has emerged as an attractive solution potentially applicable to mobile POC testing. However, the existing software-based algorithm based on the normalized cross-correlation (NCC) method is too time- and, thus, energy-consuming to be deployed for battery-powered mobile POC testing platforms. In this paper, we identify inefficiencies in the NCC-based algorithm and propose two synergistic optimization techniques that can considerably reduce the runtime and, thus, energy consumption of the original algorithm with negligible impact on counting accuracy. We demonstrate that an AndroidTM smart phone running the optimized algorithm consumes 11.5× less runtime than the original algorithm.