Dr. Yazan A Alqudah

This paper investigates the tracking of Unmanned Aerial Vehicles (UAV) using video feed. Gaussian Mixture Models (GMM) are used to detect the presence of the UAV from a video feed. If the feed is reliable the position of the UAV is detected and tracked. In case the feed is interrupted or becomes unreliable, a Kalman filter is used to predict the location of the UAV. To study the ability of the filter to track the UAV, an actual video capture of flying drone is used, a section of the video is removed to simulate an interruption of the feed. The results show the ability of the filter to accurately predict the location of UAV.

Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.

This paper investigates the impact of measurements availability on the accuracy of position prediction using a mobile device equipped with GPS, acceleration, and gyro sensors. The paper also discusses the effects of the sampling factor for the available data. The experiment results emphasize the importance of sampling factor in achieving robust and reliable location estimation, particularly in challenging environments where GPS signals may be intermittent or compromised. The insights gained from this study may contribute to the advancement of location estimation-based applications, fostering improved autonomous systems in real-world scenarios.

The advent of cloud computing and the ubiquity of broadband wireless coverage and wide spread usage of smart phones around the world carries the potential for transforming health care services, reducing health care cost and ensuring faster care for urgent cases. To these objectives, we present a cloud-based mobile health monitoring solution that takes advantage of cloud infrastructure and mobile processing capability to address the rising cost of health care monitoring. The solution enables health care providers to remotely analyze, monitor and diagnose patient's data. The solution integrates a powerful data analysis tool, cloud computing and mobile services. This paper presents a proof of concept that has been developed to monitor, record and analyze heart rate. The design enables a physician to develop custom analysis and monitoring to collect key indicator or set alerts without a need for infrastructure implementations to store or transfer the data.

To meet the ever-growing demand for higher data rates, accurate channel models are needed for optimal design and deployment of mobile wireless networks. This work proposes a new method for addressing path loss modeling at 800 MHz of suburban environment based on field measurements. Using generalized linear mixed models, we develop a new statistical model that accounts for the autocorrelation among measurements at the same distance at different times. The proposed method allows linear, quadratic, and cubic relationship forms between the path loss measurements and the natural logarithm of the distance, which is almost unexplored as existing models use a straight line relationship. A comparison study consists of comparing nine propagation models in terms of the mean absolute prediction error. The new model performs over 30% better than the existing models for the considered measurements. We also show that a cubic relationship form between path loss measurements and the logarithm of distance could be more suitable than a straight line form for prediction purposes. The results show that the generalized linear mixed models significantly improve the prediction power regardless of the form of the model (linear, quadratic, or cubic).

This work presents a solution to monitor breathing patterns to detect any signs of abnormalities and ensure properly ventilating pulmonary system. The solution includes the ability to track and detect coughing. The system can be used by individuals to monitor breathing or athletes to monitor performance while exercising. The solution utilizes machine learning algorithms implemented through Edge Impulse to classify and analyze breathing patterns. It also features a user mobile application to record and transmit data and receive the classification results.

Optical Wireless (OW) provides an alternative to RF for wireless connectivity. In applications where Radio Frequency (RF) might interfere with system operations, OW can be used to provide connectivity. This work studies the applicability of OW to connect two agents in a swarm. The work discusses transmitter and receiver designs and shares the results of simulation and lab experiments for different circuits configurations. The work shows the results of a reliable 100Kbps link between agents operating at a distance of approximately equal to 3 meters.

In this paper a model-based embedded systems design laboratory course development is presented. The course is an enhancement over an existing embedded systems laboratory course that uses conventional methods along with low-level and high-level programming languages in designing embedded systems. The proposed laboratory course introduces the concepts of model-based design, rapid prototyping, and auto-code generation to junior students of an undergraduate electrical engineering program. The students are exposed to model-based development and design through using MATLAB ® Simulink ® . The graphical environment of Simulink ® allows students to easily design and implement embedded software and generate code without worrying about the details of conventional coding issues. Moreover, MATLAB ® Simulink ® allows easy auto-code generation to be executed on a variety of microcontrollers and FPGAs. The developed lab course and its experiments were implemented for two semesters at least. One of them was during the COVID-19 shutdown and thus the lab was conducted by students at home. The students' feedback is promising and shows that the lab has helped attain more skills needed by the industry in addition to acquiring a new knowledge area that was not covered by the conventional curriculum.

With the introduction of autonomous and self-driving cars, innovative research is needed to ensure safety and reliability on the road. This work introduces a solution to understand vehicle behaviour based on sensors data. The behaviour is classified according to driving events. Understanding driving events can play a significant role in road safety and estimating the expense and risks of driving a vehicle. Rather than relying on the distance and time driven, driving events can provide a more accurate measure of vehicle driving consumption. This measure will become valuable as more ride-sharing applications are introduced to roads around the world. Estimating driving events can also help better design the road infrastructure to reduce congestion, energy consumption and pollution. By sharing data from official vehicles and volunteers, crowd sensing can be used to better understand congestion and road safety. This work studies driving events and proposes using machine learning to classify these events into different categories. The acquired data is collected using embedded mobile device motion sensors to train machine learning algorithms to classify the events.

In this work, a low-cost device is developed that enables the monitoring and classification of sleep positions. Driven by the growing problem of sleep disorders, the device can be utilized at the patients’ place to record and report their sleep positions. The device can also be used by hospitals and clinics for patients that requires continuous monitoring. Machine learning is used to classify different sleep positions based on sensors data collected from the device.