Computer Engineering Commons^™

A Memory-Centric Customizable Domain-Specific Fpga Overlay For Accelerating Machine Learning Applications, Atiyehsadat Panahi

Graduate Theses and Dissertations

Low latency inferencing is of paramount importance to a wide range of real time and userfacing Machine Learning (ML) applications. Field Programmable Gate Arrays (FPGAs) offer unique advantages in delivering low latency as well as energy efficient accelertors for low latency inferencing. Unfortunately, creating machine learning accelerators in FPGAs is not easy, requiring the use of vendor specific CAD tools and low level digital and hardware microarchitecture design knowledge that the majority of ML researchers do not possess. The continued refinement of High Level Synthesis (HLS) tools can reduce but not eliminate the need for hardware-specific design knowledge. The designs …

Femtosecond Laser Surface Processing To Create Self-Organized Micro- And Nano-Scale Features On Composite And Ceramic Materials, Nate Koeppe

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Femtosecond laser surface processing (FLSP) is applied to a range of materials in this thesis. The materials studied were a carbon fiber reinforced polymer (CFRP), a thermosetting polymer, silicon nitride (Si₃N₄), and ceramic alumina. The CFRP is a composite material consisting of a thermosetting polymer and carbon fibers. The CFRP are referred to as a composite and the thermosetting polymer is referred to as a resin in this thesis. Alumina can exist in many different forms. The alumina used is 0.5 mm thick nonporous alumina sheets purchased from McMaster-Carr, and will be referred to as alumina …

Act5 Eit System : A Multiple-Source Electrical Impedance Tomography System, Omid Rajabi Shishvan

Legacy Theses & Dissertations (2009 - 2024)

This dissertation describes the design and implementation of Adaptive Current Tomograph 5 (ACT5) with a focus on the digital processing and data ow in the instrument. ACT5 is an electrical impedance tomography (EIT) instrument that produces images of the complex impedivity distribution within the body by injecting currents through and measuring voltages on electrodes applied to the skin. ACT5 is a parallel-drive EIT system with a dedicated current source for each electrode, capable of driving all electrodes simultaneously and measuring the induced voltages on them. It can support up to 48 electrodes with a frequency range of 5 kHz to …

Snap : A Software-Defined & Named-Data Oriented Publish-Subscribe Framework For Emerging Wireless Application Systems, Manveen Kaur

All Dissertations

The evolution of Cyber-Physical Systems (CPSs) has given rise to an emergent class of CPSs defined by ad-hoc wireless connectivity, mobility, and resource constraints in computation, memory, communications, and battery power. These systems are expected to fulfill essential roles in critical infrastructure sectors. Vehicular Ad-Hoc Network (VANET) and a swarm of Unmanned Aerial Vehicles (UAV swarm) are examples of such systems. The significant utility of these systems, coupled with their economic viability, is a crucial indicator of their anticipated growth in the future. Typically, the tasks assigned to these systems have strict Quality-of-Service (QoS) requirements and require sensing, perception, and …

A Novel Testbed For Evaluation Of Operational Technology Communications Protocols And Their On-Device Implementations, Matthew Boeding

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Operational Technology (OT) and Infrastructure Technology (IT) systems are converging with the rapid addition of centralized remote management in OT systems. Previously air-gapped systems are now interconnected through the internet with application-specific protocols. This has led to systems that had limited access points being remotely accessible. In different OT sectors, legacy protocols previously transmitted over serial communication were updated to allow internet communication with legacy devices. New protocols such as IEC-61850 were also introduced for monitoring of different OT resources. The IEC-61850 standard’s Generic Object Oriented Substation Event (GOOSE) protocol outlines the representation and communication of a variety of different …

Feature Analysis Of Indus Valley And Dravidian Language Scripts With Similarity Matrices, Sarat Sasank Barla, Sai Surya Sanjay Alamuru, Peter Revesz

School of Computing: Conference and Workshop Papers

This paper investigates the similarity between the Indus Valley script and the Kannada, Malayalam, Tamil, and Telugu scripts that are used to write Dravidian languages. The closeness of these scripts is determined by applying a feature analysis of each sign of these scripts and creating similarity matrices that describe the similarity of any pair of signs from two different scripts. The feature list that we use for the analysis of these Dravidian language-related scripts includes six new features beyond the thirteen features that were used for the study of Minoan Linear A and related scripts by Revesz. These new features …

Integrating Plcs With Robot Motion Control In Engineering Capstone Courses, Sanjeevi Chitikeshi, Shirshak K. Dhali, Vukica Jovanovic

Engineering Technology Faculty Publications

Robotic motion control methods and Programmable Logic Controllers (PLCs) are critical in engineering automation and process control applications. In most manufacturing and automation processes, robots are used for moving parts and are controlled by industrial PLCs. Proper integration of external I/O devices, sensors and actuating motors with PLC input and output cards is very important to run the process smoothly without any faults and/or safety concerns. Most traditional electrical and computer engineering (ECE) programs offer high level of motion theory and controls but little hands-on exposure to PLCs which are the main industrial controllers. This paper provides a framework for …

Computer Aided Diagnosis System For Breast Cancer Using Deep Learning., Asma Baccouche

Electronic Theses and Dissertations

The recent rise of big data technology surrounding the electronic systems and developed toolkits gave birth to new promises for Artificial Intelligence (AI). With the continuous use of data-centric systems and machines in our lives, such as social media, surveys, emails, reports, etc., there is no doubt that data has gained the center of attention by scientists and motivated them to provide more decision-making and operational support systems across multiple domains. With the recent breakthroughs in artificial intelligence, the use of machine learning and deep learning models have achieved remarkable advances in computer vision, ecommerce, cybersecurity, and healthcare. Particularly, numerous …

Algorithm Optimization And Hardware Acceleration For Machine Learning Applications On Low-Energy Systems, Jianchi Sun

All Dissertations

Machine learning (ML) has been extensively employed for strategy optimization, decision making, data classification, etc. While ML shows great triumph in its application field, the increasing complexity of the learning models introduces neoteric challenges to the ML system designs. On the one hand, the applications of ML on resource-restricted terminals, like mobile computing and IoT devices, are prevented by the high computational complexity and memory requirement. On the other hand, the massive parameter quantity for the modern ML models appends extra demands on the system's I/O speed and memory size. This dissertation investigates feasible solutions for those challenges with software-hardware …

Reduced Fuel Emissions Through Connected Vehicles And Truck Platooning, Paul D. Brummitt

Electronic Theses and Dissertations

Vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communication enable the sharing, in real time, of vehicular locations and speeds with other vehicles, traffic signals, and traffic control centers. This shared information can help traffic to better traverse intersections, road segments, and congested neighborhoods, thereby reducing travel times, increasing driver safety, generating data for traffic planning, and reducing vehicular pollution. This study, which focuses on vehicular pollution, used an analysis of data from NREL, BTS, and the EPA to determine that the widespread use of V2V-based truck platooning—the convoying of trucks in close proximity to one another so as to reduce air drag …

Comparative Study And Design Optimization Of A Dual-Mechanical-Port Electric Machine For Hybrid Electric Vehicle Applications, Hao Chen, Ayman M. El-Refaie, Yuefei Zuo, Shun Cai, Libing Cao, Christopher H. T. Lee

Electrical and Computer Engineering Faculty Research and Publications

A new dual-mechanical-port (DMP) electric machine for hybrid electric vehicle applications, particularly in the power-split continuously variable transmission systems, is proposed in this paper. In order to comprehensively and quantitatively evaluate the pros and cons of the proposed machine, a comparative study of four DMP electric machines with different topologies is conducted. These four investigated DMP electric machines include a conventional DMP machine, a DMP machine with spoke-type permanent magnets, a DMP machine with reluctance rotor, and a DMP machine with open slots which is the proposed machine in this paper. Even though these four machines have similar topologies, they …

Optimized Three Deep Learning Models Based-Pso Hyperparameters For Beijing Pm2.5 Prediction, Andri Pranolo, Yingchi Mao, Aji Prasetya Wibawa, Agung Bella Putra Utama, Felix Andika Dwiyanto

Knowledge Engineering and Data Science

Deep learning is a machine learning approach that produces excellent performance in various applications, including natural language processing, image identification, and forecasting. Deep learning network performance depends on the hyperparameter settings. This research attempts to optimize the deep learning architecture of Long short term memory (LSTM), Convolutional neural network (CNN), and Multilayer perceptron (MLP) for forecasting tasks using Particle swarm optimization (PSO), a swarm intelligence-based metaheuristic optimization methodology: Proposed M-1 (PSO-LSTM), M-2 (PSO-CNN), and M-3 (PSO-MLP). Beijing PM2.5 datasets was analyzed to measure the performance of the proposed models. PM2.5 as a target variable was affected by dew point, pressure, …

Comparison Of Machine Learning Techniques For Activities Of Daily Living Classification With Electromyographic Data, Sergio A. Salinas, Mohamed Elgalhud, Luke Tambakis, Sanket Salunke, Kshitija Patel, Kenneth Mcisaac, Katarina Grolinger, Ana Luisa Trejos, Abdelkader Ouda, Hamada Ghenniwa

Electrical and Computer Engineering Publications

Advances in data science and wearable robotic devices present an opportunity to improve rehabilitation outcomes. Some of these devices incorporate electromyography (EMG) electrodes that sense physiological patient activity, making it possible to develop rehabilitation systems able to assess the patient’s progress when performing activities of daily living (ADLs). However, additional research is needed to improve the ability to interpret EMG signals. To address this issue, an off-line classification approach for the 26 upper-limb ADLs included in the KIN-MUS UJI dataset is presented in this paper. The ADLs were performed by 22 subjects, while seven EMG signals were recorded from their …

Combining Solution Reuse And Bound Tightening For Efficient Analysis Of Evolving Systems, Clay Stevens, Hamid Bagheri

School of Computing: Conference and Workshop Papers

Software engineers have long employed formal verification to ensure the safety and validity of their system designs. As the system changes—often via predictable, domain-specific operations—their models must also change, requiring system designers to repeatedly execute the same formal verification on similar system models. State-of-the-art formal verification techniques can be expensive at scale, the cost of which is multiplied by repeated analysis. This paper presents a novel analysis technique—implemented in a tool called SoRBoT—which can automatically determine domain-specific optimizations that can dramatically reduce the cost of repeatedly analyzing evolving systems. Different from all prior approaches, which focus on either tightening the …

Classifying Toe Walking Gait Patterns Among Children Diagnosed With Idiopathic Toe Walking Using Wearable Sensors And Machine Learning Algorithms, Rahul Soangra, Yuxin Wen, Hualin Yang, Marybeth Grant-Beuttler

Physical Therapy Faculty Articles and Research

Idiopathic toe walking (ITW) is a gait abnormality in which children’s toes touch at initial contact and demonstrate limited or no heel contact throughout the gait cycle. Toe walking results in poor balance, increased risk of falling, and developmental delays among children. Identifying toe walking steps during walking can facilitate targeted intervention among children diagnosed with ITW. With recent advances in wearable sensing, communication technologies, and machine learning, new avenues of managing toe walking behavior among children are feasible. In this study, we investigate the capabilities of Machine Learning (ML) algorithms in identifying initial foot contact (heel strike versus toe …

A Privacy-Preserving Strategy For The Trust Layer Of The Energy Grid Of Things Distributed Energy Resource Management System, Mohammed Abdullah Alsaid

Dissertations and Theses

Emergent from the shadows of the traditional grid flaws, the Smart Grid (SG) idea was born and led by government mandates toward cleaner energy production. The SG represents the next generation of electricity distribution systems that subsume recent technological innovations. It uses digital communication between its components and entities to attain more automation, self-sufficiency, and reliability. Unfortunately, this relatively new concept is not flawless; the intrinsic reliance on increased digital communication spreads open attack paths for adversaries. Therefore, finding solutions that address information exchange vulnerabilities has become imperative.

The Energy Grid of Things (EGoT) is Portland State University's implementation of …

Influence Of Aluminum Addition On The Laser Powder Bed Fusion Of Copper-Aluminum Mixtures, Nada Kraiem, Loic Constantin, A. Mao, Fei Wang, Bai Cui, Jean-François Silvain, Yongfeng Lu

Department of Electrical and Computer Engineering: Faculty Publications

The high optical reflectivity of copper (Cu) in the near infrared (NIR) domain and its elevated heat dissipation make Cu a challenging metal for laser powder bed fusion (LPBF), even with high energy densities (EDs). In this study, we demonstrated that adding aluminum (Al) powder by as little as 0.75, 1.5, and 3 wt.% substantially enhances Cu processability, leading to denser (up to 98%) and smoother (Ra = 3.3 𝜇m) Cu-Al parts as compared to 95% and 18 𝜇m, respectively, for the parts printed using pure Cu. In addition, this method reduces the ED required by a factor of two …

Credit Card Fraud Detection Using Machine Learning Techniques, Nermin Samy Elhusseny, Shimaa Mohamed Ouf, Amira M. Idrees Ami

Future Computing and Informatics Journal

This is a systematic literature review to reflect the previous studies that dealt with credit card fraud detection and highlight the different machine learning techniques to deal with this problem. Credit cards are now widely utilized daily. The globe has just begun to shift toward financial inclusion, with marginalized people being introduced to the financial sector. As a result of the high volume of e-commerce, there has been a significant increase in credit card fraud. One of the most important parts of today's banking sector is fraud detection. Fraud is one of the most serious concerns in terms of monetary …

Asymmetric Control Of Light At The Nanoscale, Christos Argyropoulos

Department of Electrical and Computer Engineering: Faculty Publications

Breaking reciprocity at the nanoscale can produce directional formation of images due to the asymmetric nonlinear optical response of subwavelength anisotropic resonators. The self-induced passive non-reciprocity has advantages compared to magnet or time modulation approaches and may impact both classical and quantum photonics.

Learning Term Weights By Overfitting Pairwise Ranking Loss, Ömer Şahi̇n, İlyas Çi̇çekli̇, Gönenç Ercan

Turkish Journal of Electrical Engineering and Computer Sciences

A search engine strikes a balance between effectiveness and efficiency to retrieve the best documents in a scalable way. Recent deep learning-based ranker methods are proving to be effective and improving the state-of-the-art in relevancy metrics. However, as opposed to index-based retrieval methods, neural rankers like bidirectional encoder representations from transformers (BERT) do not scale to large datasets. In this article, we propose a query term weighting method that can be used with a standard inverted index without modifying it. Query term weights are learned using relevant and irrelevant document pairs for each query, using a pairwise ranking loss. The …

Automated Question Generation And Question Answering From Turkish Texts, Fati̇h Çağatay Akyön, Ali̇ Devri̇m Eki̇n Çavuşoğlu, Cemi̇l Cengi̇z, Si̇nan Onur Altinuç, Alpteki̇n Temi̇zel

Turkish Journal of Electrical Engineering and Computer Sciences

While exam-style questions are a fundamental educational tool serving a variety of purposes, manual construction of questions is a complex process that requires training, experience and resources. Automatic question generation (QG) techniques can be utilized to satisfy the need for a continuous supply of new questions by streamlining their generation. However, compared to automatic question answering (QA), QG is a more challenging task. In this work, we fine-tune a multilingual T5 (mT5) transformer in a multitask setting for QA, QG and answer extraction tasks using Turkish QA datasets. To the best of our knowledge, this is the first academic work …

Design And Implementation Of A Bioinspired Leaf Shaped Hybrid Rectenna As A Green Energy Manufacturing Concept, Kayhan Çeli̇k, Erol Kurt

Turkish Journal of Electrical Engineering and Computer Sciences

In this communication, the novel low cost hybrid energy harvester combining rectifying antenna with the solar cell for feeding the low power energy systems are reported. The bioinspired leaf shaped monopole antenna is designed to work in the most used communication frequency bands such as GSM-1800, UMTS-2100, WIFI-2.45 and LTE-2.65 GHz for the energy harvesting purposes and microstrip low pass filter is also added on the feeding line for the second harmonic rejection for increasing the efficiency of the harvester. The solar cell is placed on the ground plane of the designed leaf shaped antenna for using volumetric space efficiently …

Breast Cancer-Caps: A Breast Cancer Screening System Based On Capsule Network Utilizing The Multiview Breast Thermal Infrared Images, Devanshu Tiwari, Manish Dixit, Kamlesh Gupta

Turkish Journal of Electrical Engineering and Computer Sciences

This paper proposed an accurate and fully automated breast cancer early screening system called the "Breast Cancer-Caps". The capsule network is used in this approach for the cancer detection in breast utilizing the thermal infrared images for the first time. This capsule network is trained with the help of Dynamic as well as Static breast thermal images dataset consisting of left, right, frontal views along with a new multiview thermal images. These multiview breast thermal images are fabricated by concatenating the conventional left, frontal and right view breast thermal images. The other current and popular deep transfer learning models such …

Measuring The Rol Of Digital Engineering: It's A Journey, Not A Number, Tom Mcdermott, Kaitlin Henderson, Eileen Van Aken, Alejandro Salado, Joseph Bradley

Engineering Management & Systems Engineering Faculty Publications

Systems engineering as a discipline has long had difficulty providing quantifiable evidence of its value (Honour 2004); DE transformation provides an opportunity to better measure its value. Transitioning from a document-based to a model-based approach is expensive, and organizations want to know if the effort and cost to adopt MBSE is worth it.

Non-Gaussian Analysis Of Herbarium Specimen Damageto Optimize Specimen Collection Management, Aris Yaman, Yulia Aris Kartika, Ariani Indrawati, Zaenal Akbar, Lindung P. Manik, Wita Wardani, Tutie Djarwaningsih, Taufik Mahendra, Dadan R. Saleh

Knowledge Engineering and Data Science

Damage to specimen collections occurs in practically every herbarium across the world. Hence, some precautions must be taken, such as investigating the factors that cause specimen damage in their collections and evaluating their herbarium collection handling and usage policy. However, manual investigation of the causes of herbarium collection damage requires a lot of effort and time. Only a few studies have attempted to investigate the causes of herbarium collection damage. So far, the non-gaussian approach to detecting the causes of damage to herbarium specimens has not been studied before. This study attempted to explore the effect of species type, time, …

Social Distancing Monitoring System Using Deep Learning, Amelia Ritahani Ismail, Nur Shairah Muhd Affendy, Asmarani Ahmad Puzi

Knowledge Engineering and Data Science

COVID-19 has been declared a pandemic in the world by 2020. One way to prevent COVID-19 disease, as the World Health Organization (WHO) suggests, is to keep a distance from other people. It is advised to stay at least 1 meter away from others, even if they do not appear to be sick. The reason is that people can also be the virus carrier without having any symptoms. Thus, many countries have enforced the rules of social distancing in their Standard Operating Procedure (SOP) to prevent the virus spread. Monitoring the social distance is challenging as this requires authorities to …

Automatic 3d Cranial Landmark Positioning Based Onsurface Curvature Feature Using Machine Learning, Putu Hendra Suputra, Anggraini Dwi Sensusiati, Myrtati Dyah Artaria, Gijsbertus Jacob Verkerke, Eko Mulyanto Yuniarno, I Ketut Eddy Purnama

Knowledge Engineering and Data Science

Cranial anthropometric reference points (landmarks) play an important role in craniofacial reconstruction and identification. Knowledge to detect the position of landmarks is critical. This work aims to locate landmarks automatically. Landmarks positioning using Surface Curvature Feature (SCF) is inspired by conventional methods of finding landmarks based on morphometrical features. Each cranial landmark has a unique shape. With the appropriate 3D descriptors, the computer can draw associations between shapes and landmarks using machine learning. The challenge in classification and detection in three-dimensional space is to determine the model and data representation. Using three-dimensional raw data in machine learning is a serious …

The Effect Of Resampling On Classifier Performance: Anempirical Study, Utomo Pujianto, Muhammad Iqbal Akbar, Niendhitta Tamia Lassela, Deni Sutaji

Knowledge Engineering and Data Science

An imbalanced class on a dataset is a common classification problem. The effect of using imbalanced class datasets can cause a decrease in the performance of the classifier. Resampling is one of the solutions to this problem. This study used 100 datasets from 3 websites: UCI Machine Learning, Kaggle, and OpenML. Each dataset will go through 3 processing stages: the resampling process, the classification process, and the significance testing process between performance evaluation values of the combination of classifier and the resampling using paired t-test. The resampling used in the process is Random Undersampling, Random Oversampling, and SMOTE. The classifier …

A Comparison Of Machine Learning Models To Prioritise Emailsusing Emotion Analysis For Customer Service Excellence, Mohammad Yasser Chuttur, Yashinee Parianen

Knowledge Engineering and Data Science

There has been little research on machine learning for email prioritization for customer service excellence. To fill this gap, we propose and assess the efficacy of various machine learning techniques for classifying emails into three degrees of priority: high, low, and neutral, based on the emotions inherent in the email content. It is predicted that after emails are classified into those three categories, recipients will be able to respond to emails more efficiently and provide better customer service. We use the NRC Emotion Lexicon to construct a labeled email dataset of 517,401 messages for our proposal. Following that, we train …

Fish Image Classification Using Transfer Learning Method Withadaptive Learning Rate, Rizka Suhana, Wayan Firdaus Mahmudy, Agung Setia Budi

Knowledge Engineering and Data Science

The diversity of fish species in coral reef ecosystems is one of the indications in determining health in coral reef ecosystems. Many Indonesian Fisheries and Marine Research and Development Agency experts carefully classify fish images. A reliable technique for performing image classification is Convolutional Neural Network (CNN). Transfer learning appears and adopts part of CNN, namely the modified convolution layer. The paper aims to solve the fish classification problem using the pre-trained model of Mobilenet V2. The model has a low computational process and does not use too many memory resources when training image data. The research image data used …