Engineering Commons^™

Development Of A Ppg Sensor Array As A Wearable Device For Monitoring Cardiovascular Metrics, Jose Ignacio Rodriguez-Labra

Masters Theses

Wearable devices with integrated sensors for tracking human vitals are widely used for a variety of applications, including exercise, wellness, and health monitoring. Photoplethysmography (PPG) sensors use pulse oximetry to measure pulse rate, cardiac cycle, oxygen saturation, and blood flow by passing a light beam of variable wavelength through the skin and measuring its reflection. A multi-channel PPG wearable system was developed to include multiple nodes of pulse oximeters, each capable of using different wavelengths of light. The system uses sensor fusion along with a machine learning model to perform feature extraction of relevant cardiovascular metrics across multiple pulse oximeters …

Iot Greenhouse Monitoring System, Raj Basnet

Honors Theses

Our project is a greenhouse monitoring system. The customer states that they need a complete monitoring system for their greenhouse. There are a lot of items within the greenhouse that need to be watered at the right time and kept at a certain temperature. The customer is not always around to check the status of these items due to their busy lifestyle. They would like a system to monitor all these items so they can check it on their smartphone no matter how far away they are from the greenhouse. The customer wants this to be a low-cost and energyefficient …

Data Mining Of Unstructured Textual Information In Transportation Safety Domain: Exploring Methods, Opportunities And Limitations, Keneth Morgan Kwayu

Dissertations

The unprecedented increase in volume and influx of structured and unstructured data has overwhelmed conventional data management system capabilities in organizing, analyzing, and procuring useful information in a timely fashion. Structured data sources have a pre-defined pattern that makes data preprocessing and information retrieval tasks relatively easy for the current technologies that have been designed to handle structured and repeatable data. Unlike structured data, unstructured data usually exists in an unorganized format that offers no or little insight unless indexed and stored in an organized fashion. The inherent format of unstructured data exacerbates difficulties in data preprocessing and information extraction. …

Evaluation Of State-Of-The-Art Nlp Deep Learning Architectures On Commonsense Reasoning Task, Guo Rui (Justin) Lee

Honors Theses

The goal of this project was to explore modern neural network technology in the application of discerning and generating statements that are ‘reasonable’, in what is known as commonsense reasoning. We built off of the work of Saeedi et al. In their work on the 2020 SemEval task, Commonsense Validation and Explanation (ComVE). SemEval is a workshop that creates a variety of semantic evaluation tasks to examine the state of the art in the practical application of natural language processing. This particular task involved three sections: task A, Validation, in which a program tries to select which of two statements …

Software Quality Control Through Formal Method, Jialiang Chang

Dissertations

With the improvement of theories in the software industry, software quality is becoming the most significant part of the procedure of software development. Due to the implicit and explicit vulnerabilities inside the software, software quality control has caught more researchers and engineers’ attention and interest.

Current research on software quality control and verification are involving various manual and automated testing methods, which can be categorized into static analysis and dynamic analysis. However, both of them have their own disadvantages. With static analysis methods, inputs will not be taken into consideration because the software system isn’t executed so we do not …

Sunseeker Solar Car Display And Driver Unit, Conner Mccarthy

Honors Theses

Digital dashboard displays with critical driver information are found in all modern vehicles. Examples of such information available to the driver include a speedometer, odometer, engine RPM, fuel gauge and more. The current 2016 Sunseeker solar car already has numerous displays that can show critical information to the driver, however, there are several problems that exist. Each display itself is less than two inches in size, the text on the screens is difficult to read, and the measurements have no units. Furthermore, these displays were made by a company that no longer exists, thus preventing the solar car team from …

Efficient Hardware/Software Partitioning Techniques For A Cloud-Scale Cpu-Fpga Platform, Samah Ziyad Rahamneh

Dissertations

The diversity of workload characteristics has stimulated the deployment of heterogeneous architectures to accommodate workloads’ requirements disparity in cloud data centers. In heterogeneous computing, co-processors are utilized to support Central Processing Units (CPUs) in fulfilling workload demands. Field Programmable Gate Arrays (FPGAs) have advantages over other accelerators because of their power, performance and re-configurability benefits. In order to achieve the most benefit of a heterogeneous platform, efficient partitioning of workload between the CPU and the FPGA is a crucial demand.

This dissertation first presents a design and implementation of cooperative CPU-FPGA execution techniques, which include code and data partitioning, of …

Extending The Capabilities Of Von Neumann With A Dataflow Sub-Isa, Martin Cowley

Masters Theses

Instruction set architectures (ISAs) such as x86, ARM, and RISC-V follow the control flow model of computation, where a program is defined as a sequence of instructions. Early processors executed instructions one-by-one based on the control flow of a program. Dataflow is an alternative model of computation that uses the availability of data to drive instruction execution. Any instruction can be chosen for execution, independent of the instruction order, as long as the data is available for that instruction. While modern processors incorporate concepts of the dataflow model in the microarchitecture, the implementation of the ISA, the amount of instruction …

Power-Efficient And Highly Scalable Parallel Graph Sampling Using Fpgas, Muhammad Usman Tariq

Masters Theses

Energy efficiency is a crucial problem in data centers where big data is generally represented by directed or undirected graphs. Analysis of this big data graph is challenging due to volume and velocity of the data as well as irregular memory access patterns. Graph sampling is one of the most effective ways to reduce the size of graph while maintaining crucial characteristics. This thesis presents design and implementation of a field programmable gate array (FPGA) based graph sampling method which is both time- and energy-efficient. This is in contrast to existing parallel approaches which include memory-distributed clusters, multicore and GPUs. …

Computer Aided Brain Tumor Edge Extraction Using Morphological Operations, Warqaa Shaher Alazawee

Masters Theses

Detecting the precise boundary of the area containing a recognized brain tumor is a complex problem and must be addressed since it applies to many medical modalities and tumor types. The objective of this thesis is to provide an efficient algorithm for detecting edges of brain tumors to help neurosurgeons identify the border of the critical area and distinguish the precise margin of the tumor from the rest of the brain tissue during the surgery. This thesis work exploits MRI brain tumor images as a tool to aid surgeons. MRI image segmentation is an essential step as a preliminary process …

Design Of Digital Down Converter Chain For Software Defined Radio Systems On Fpga, Nagarjun Marappa

Masters Theses

Modern communication systems have increasingly attempted to trade off the digital signal processing for analog circuitry. In performing this tradeoff, advanced algorithms have been implemented in both custom programmable hardware and in software; such systems are commonly called Software Defined Radios (SDR). Advanced software defined radios consist of highly configurable hardware and computers used as digital signal processing (DSP) platforms that provide the technology for realizing current and future generations of digital wireless communication infrastructure. Many sophisticated signal processing tasks are performed in SDR, including compression algorithms, channel estimation, equalization, forward error correction and protocol management. This research has focused …

Signage Recognition Based Wayfinding System For The Visually Impaired, Abdullah Khalid Ahmed

Masters Theses

Persons of visual impairment make up a growing segment of modern society. To cater to the special needs of these individuals, society ought to consider the design of special constructs to enable them to fulfill their daily necessities. This research proposes a new method for text extraction from indoor signage that will help persons of visual impairment maneuver in unfamiliar indoor environments, thus enhancing their independence and quality of life.

In this thesis, images are acquired through a video camera mounted on glasses of the walking person. Frames are then extracted and used in an integrated framework that applies Maximally …

Control Of Cation Ordering In Zinc Tin Nitride And In-Situ Monitoring Of Growth, Brian Christopher Durant

Masters Theses

Semiconducting materials with a band gap around 1.5 eV are very much sought after due to their close match to the solar spectrum. However, some compounds that have shown promise for highly efficient solar cells contain rare, expensive, and sometimes toxic elements, such as indium and gallium. As such, a search for earth abundant materials has become more prominent recently. One such earth abundant semiconducting material that has garnered interest is ZnSnN₂. It has been shown through previous studies that there is the possibility of continuously tuning the band gap between 1.0 and 2.0 eV by controlling the …

A High Performance Architecture For An Exact Match Short-Read Aligner Using Burrows-Wheeler Aligner On Fpgas, Dana Abdul Qader

Masters Theses

Due to modern DNA sequencing technologies vast amount of short DNA sequences known as short-reads is generated. Biologists need to be able to align the short-reads to a reference genome to be able to make scientific use of the data. Fast and accurate short-read aligner programs are needed to keep up with the pace at which this data is generated. Field Programmable Gate Arrays have been widely used to accelerate many data-intensive bioinformatics applications.

Burrows-Wheeler Transform has been used in the theory of string matching which has led to the development of many short-read alignment programs. This thesis presents a …

Morphology Based Framework For Improved Driver's Visibility In Inclement Weather Conditions, Saleem Farhood Hussein

Masters Theses

The U.S. Department of Transportation reports that on average there are 5,870,000 vehicle accidents each year. Twenty-three percent (23%) of these accidents are attributed to weather conditions with an annual average of more than 6,000 people are killed and 480,000 people are injured. Weather-related accidents occur mainly because of the low visibility on the roads under inclement conditions such as snow, rain and fog. While these conditions can be predictable and individuals try to avoid driving in inclement weather, there are circumstances that require driving in such conditions such as emergency responders or when the severity of the storm has …

Design Of A New Digital Relay For Transmission Line Fault Detection, Classification And Localization Based On A New Composite Relay And Artificial Neural Network Approach, Ahmed Sabri Altaie

Masters Theses

This thesis focuses on new approach to detect, classify, and localize the fault in transmission line. Firstly, fault detection was carried out using the New Composite Relay (CR) which, has different characteristics and the ability to detect any type of fault including series faults. Secondly, fault classification was conducted using the Feed Forward Artificial Neural Network (FFANN). In addition, the fault classification led to the investigation of the best use of the FFANN. The data used come from MATLAB/SIMULINK three phase series compensated network. The results obtained using FFANN, were compared with the type of the fault that have been …

An Integrated Framework For Cardiac Sounds Diagnosis, Zichun Tong

Masters Theses

The Phonocardiogram (PCG) signal contains valuable information about the cardiac condition and is a useful tool in recognizing dysfunction and heart failure. By analyzing the PCG, early detection and diagnosis of heart diseases can be accomplished since many pathological conditions of the cardiovascular system cause murmurs or abnormal heart sounds. This thesis presents an algorithm to classify normal and abnormal heart sound signals using PCG. The proposed analysis is based on a framework composed of several statistical signal analysis techniques such as wavelet based de-noising, energy-based segmentation, Hilbert-Huang transform based feature extraction, and Support Vector Machine based classification. The MATLAB …

Novel Software Defined Radio Architecture With Graphics Processor Acceleration, Lalith Narasimhan

Dissertations

Wireless has become one of the most pervasive core technologies in the modern world. Demand for faster data rates, improved spectrum efficiency, higher system access capacity, seamless protocol integration, improved security and robustness under varying channel environments has led to the resurgence of programmable software defined radio (SDR) as an alternative to traditional ASIC based radios. Future SDR implementations will need support for multiple standards on platforms with multi-Gb/s connectivity, parallel processing and spectrum sensing capabilities. This dissertation implemented key technologies of importance in addressing these issues namely development of cost effective multi-mode reconfigurable SDR and providing a framework to …

Performance Analysis Of Distance Relay On Shunt/Series Facts-Compensated Transmission Line, Ahmed Kareem Lafta Al-Behadili

Masters Theses

Flexible Alternating Current Transmission Systems (FACTS) are increasingly being used to enhance the efficiency and reliability of power system networks. FACTS devices can influence the performance of existing protective system components (specifically distance relays) due to the fact that FACTS change power system quantities such as line impedances, voltages, and currents. Distance relay may mal-operate when FACTS devices are connected since they cause some of the tripping characteristics to change. This thesis investigates the impact on distance relay performance due to compensations using two types of FACTS controllers: Static Synchronous Compensator (STATCOM) and Static Synchronous Series Compensator (SSSC). Analytical study …

Implementation Of Traditional Printing Techniques For The Development Of Flexible Printed Sensors, Sai Guruva Reddy Avuthu

Dissertations

Printed electronics has gained a remarkable interest over the past decade for the fabrication of cost efficient electronic devices, with a major focus on the development of flexible sensors. This dissertation focuses on the fabrication of flexible sensors using traditional printing processes such as screen, inkjet and gravure printing.

A flexible organic thin film transistor (OTFT) was successfully fabricated on a polyethylene terephthalate (PET) substrate and employed as a humidity sensor. Aluminum gate electrode was thermally evaporated on PET and UV clear dielectric layer was spin coated. Source and drain silver interdigitated electrodes were screen printed. 6,13-bis(triisopropylsilylethynyl) pentacene, a humidity …

Exploration Of Stimulus Current Energy Reduction And Bifurcation Dynamics In Conductance-Based Neuron Models Using Optimal Control Theory, Michael E. Ellinger

Dissertations

Hodgkin-Huxley type conductance-based models can simulate the effect of time-varying injected stimulus currents on the neuron membrane voltage. The dynamics simulated by these model types enables investigation of the biophysical basis of neuronal activity which is fundamental to higher level function. Broadened understanding the basis of nervous system function could lead to development of effective treatment for related diseases, disorders, and the effects of trauma. In this dissertation, optimal control is used with conductance-based neuron models to develop a "Reduced Energy Input Stimulus Discovery Method." Within the method, an objective function balances two competing criteria: tracking a reference membrane voltage …

Dynamically Reconfigurable Miniature Golf Course, James Lind

Honors Theses

The purpose of this report is to inform the reader of the Senior Design Project lead by 3 students in the Electrical and Computer Engineering department at Western Michigan University. The project is in needed for use within the ECE department as a tool for showcasing to prospective students the attributes of electrical and computer engineering.

At the heart of the project lies an Arduino microcontroller acting as the commanding brain of the system. Its task is to manipulate various types of obstacles throughout the playing field with a goal of delivering a dynamic experience to the player(s). Additionally, a …

Direct Torque Control Of An Lnduction Machine Using Multi-Layer Perceptron Network, Adithya Chandrashekharan

Masters Theses

In conventional direct torque control (DTC) scheme of induction motor (lM), Proportional Integral Controller (PI) is used as the speed controller. PI controller is more suitable in steady state condition and for linear system but both DTC and IM are mostly nonlinear. Multi-Layer perceptron neural network. (MLPNN) controller is more suitable and performs better than PI controller. The switching table of the conventional DTC is replaced by the MLPNN controller. The MLPNN inputs are, the magnitude of the stator flux, torque and the Voltage sectors. Levenberg-Marquardt back propagation technique has been used to train the MLPNN. The output of the …

Lntegration Of Conventional Lithography And Printing Processes As A Key Enabling Technology For Printed And Flexible Sensing Systems, Binu Baby Narakathu

Dissertations

Sensors, which are used ubiquitously in a wide variety of applications, are revolutionizing the already ever-changing world we live in by providing real-time information about our surroundings. This dissertation focuses on the integration of conventional photolithography and printing processes as a key enabling technology for printed and flexible sensing systems.

Initially, an efficient opto-electrochemical sensing system, for the dual detection of heavy metal compounds was successfully developed. A novel microfluidic flow cell, with a reservoir volume of 25 μl, was designed and fabricated using acrylic. An electrochemical sensor with gold (Au) interdigitated electrodes (IDE) on a glass substrate was photolithographically …

Improved Accuracy In Real-Time Rfid Localization Systems Using Kalman Filtering, Benjamin J. Sanda

Masters Theses

The use of Radio Frequency Identification (RFID) has become widespread in industry as a means to quickly and wirelessly identify and track packages and equipment. Now there is a commercial interest in using RFID to provide real-time localization. Efforts to use RFID technology for this purpose experience localization errors due to noise and multipath effects inherent to these environments. This paper presents the use of both linear Kalman filters and non-linear Unscented Kalman filters to reduce error effects inherent to real-time RFID localization systems and provide more accurate localization results in indoor environments. A commercial RFID localization system designed for …

An Enhanced Self-Healing Protection System In Smart Grid: Using Advanced And Intelligent Devices And Applying Hierarchical Routing In Sensor Network Technique, Mohamed Eid Aljahani

Masters Theses

This paper presents a self-healing protection systems were designed using PSCAD software to test and investigate the efficiency of this method. The system was applied on a typical distribution system with loads, buses, and power sources. The availability of advanced and intelligent devices, such as IEDs and PMUs was the trigger to design proficient and accurate self-healing protection systems which are associated with future smart grids. Deploying optimal sensors distributed within the grid could be a suitable method to monitor and control the distribution network. By using a hierarchical clustering communication technique, optimal sensors can work wirelessly and efficiently without …

Opportunistic Service Differentiation And Cloud Resource Management In Support Of Enhanced Vehicular Applications, Mohammad Ali Salahuddin

Dissertations

An integral part of Intelligent Transportation Systems (ITS) are Vehicular Ad hoc Networks (VANETs), which consist of vehicles with on-board units (OBUs) and fixed road-side units (RSUs). Wireless Access in Vehicular Environment (WAVE) offers QoS via service differentiation by using application defined priorities. However, WAVE has unbounded delay and is oblivious to network load and severity of vehicles with respect to their environment. Our context severity metric innovatively enhances WAVE to be sensitive to vehicle and environment interactions. Our novel Opportunistic Service Differentiation (OSD) technique, dynamically readjusts the WAVE packet priorities to improve utilization of lower latency queues, prioritizing packets …

Position Tracking Using Wifi, Nathan Conrad

Honors Theses

Position tracking using WiFi is needed as a more accurate method of intra-building tracking due to Global Positioning System’s (GPS) lack of accuracy in buildings. The main application of this project is to provide a safety system, which may be either tracking employees within a building and allowing them to send an emergency message through a device, or to track objects throughout a building. The devices can send simple messages to a central location. These messages will include position information and which emergency has been selected. The devices consist of two buttons and two LEDs, and with a button press, …

Position Tracking Using Wifi, Tyler Bayne

Honors Theses

Position tracking using WiFi is needed as a more accurate method of intra-building tracking due to Global Positioning System's (GPS) lack of accuracy in buildings. The main application of this project is to provide a safety system, which may be either tracking employees within a building and allowing them to send an emergency message through a device, or to track objects throughout a building. The devices can send simple messages to a central location. These messages will include position information and which emergency has been selected. The devices consist of two buttons and two LEDs, and with a button press, …

Design Of Hardware Accelerator For Fuzzy Automata Using Dynamic Partial Reconfiguration, Chinh K. Nguyen

Masters Theses

As embedded systems have become more complex and designers are required to develop new products faster while using fewer chips. FPGAs are a good choice because they offer flexibility to design on-chip devices as well as the embedded systems that are reprogrammable and reconfigurable. Today's tougher cost, higher performance, and lower power consumption requirements demand even more efficient design strategies. Dynamic partial reconfiguration (PR) is a good approach to meet these requirements because it extends the inherent flexibility of the FPGA by allowing partial regions of the FPGA to be dynamically reconfigured with new functionality while other applications are still …