Computer Engineering Commons^™

Towards The Advancement Of Violence Recognition In Security Footage With Explainable Neural Networks, Paris Her

Dissertations (1934 -)

This dissertation investigates the problem of violence recognition in surveillance footage using computer vision and machine learning techniques. More specifically, our goal is to achieve interpretable and explainable deep learning models because violence recognition is a sensitive task. We first propose to perform violence recognition using a 3D convolutional neural network through intuitive hyperparameter tuning and transfer learning. We utilize a state-of-the-art 3D model used for general activity recognition that is lightweight and adjustable. Along with that, we introduce a data augmentation technique called "resize-within" which uses interpolation, rather than cropping, to resize the original input video to a new …

Automated Data Analysis For Concussion Patient Records: A Flutter-Based Desktop Application, Fhaheem Tadamarry

USF Tampa Graduate Theses and Dissertations

Concussions are a prevalent and complex medical condition requiring careful clinical assessment and data-driven insights for effective management. This thesis presents the development of an automated data analysis system for concussion patient records, integrating Flutter-based desktop application development with SQL-driven data processing. The system provides a streamlined, interactive interface for clincians and researchers to upload, visualize, and analyze patient data efficiently.

The proposed solution automates data cleaning, preprocessing, and statistical analysis, ensuring robust and reliable insights into demographic, clinical, and recovery-related factors. Key analyses include sex-based differences injury mechanisms, prior head injury impact, mood disorder correlations, and time-to-treatment variations. The …

War Strategy Algorithm- Based Hybrid Optimization For Accurate And Rapid Speech Recognition, Shahad Thamear Abd Al-Latief, Salman Yussof, Azhana Ahmad, Saif Mohanad Khadim, Ahmed Alkhayyat

Iraqi Journal for Computer Science and Mathematics

Speech recognition-based applications increased and developed as a result of artificial intelligence's rapid growth, particularly Machine Learning, which play a crucial role in many aspects of daily life, such as applications related to human-computer interaction, and natural language processing. The complexity and diversity of speech signals provides challenges in maximizing the rate of accuracy and efficiency of speech recognition systems. Hyperparameter tuning is a crucial step in machine learning that has a significant role in optimizing the performance and generalization by determining the optimal values for the model's hyperparameters. This paper employed the recently developed WAR Strategy optimization algorithm for …

Methods For Detecting Anomalies In Network Traffic Based On One-Class Svm Technology, Komil Kerimov, Sardor Kurbanov, Zarina Azizova

Chemical Technology, Control and Management

This article is dedicated to the research and application of the One-Class Support Vector Machines method for detecting anomalies in network traffic. It examines the problems of detecting anomalies in network traffic and proposes a methodology for using One-Class SVM, including an overview of the main concepts and formulas of the algorithm. A discussion of the results of One-Class SVM is presented, including interpretation, advantages, limitations and possible directions for development of the proposed technique, as well as the practical significance of using the proposed method for detecting anomalies in network traffic.

Correlations Between Song Popularity And Their Audio Features Using Machine Learning, Rong Chen

Dissertations, Theses, and Capstone Projects

This project is an interactive visual project that explores the relationship between audio features and song popularity on Spotify using machine learning techniques. Through the collection of nearly half a million songs and implementation of seven different machine learning models, including Linear Regression, Random Forest, Decision Trees, and Gradient Boosting, I investigated how audio characteristics correlate with a song's popularity ranking. The project utilized MongoDB for data storage, Spotipy for API integration, and Streamlit with Plotly for visualization. This work provides insights into the practical challenges of large-scale music analysis and the relationship between technical audio characteristics and commercial success, …

Assessment Of Risk Factor Prediction Using Machine Learning Techniques And Hybrid Approach Based On Soft Sets, Menaga A

Theses and Dissertations

Cardiovascular diseases (CVDs) are the leading cause of mortality worldwide, and India reports a significantly high death rate due to its large population base and the increasing prevalence of non-communicable diseases. National statistics indicate that 20–27% of deaths in India are attributed to CVDs, with the proportion steadily rising over the years. Recognizing the urgency of early detection and risk prevention, the World Health Organization (WHO) introduced “The Global Action Plan for the Prevention and Control of Non-Communicable Diseases (2013–2020),” emphasizing early identification, risk reduction, and timely treatment. In this context, decision-making applications have gained importance across domains especially healthcare …

An Integrated Approach To Enhance The Performance Of Rainfall Forecasting By Leveraging Stacking Based Machine Learning And Deep Learning Techniques, Umamaheswari P

Theses and Dissertations

Rainfall forecasting is critical for a variety of reasons, the most important of which is the substantial impact it has on many sectors of the community and the environment. It helps farmers with planting schedules, crop choices and irrigation techniques, all of which directly impact food production and agricultural yields. Rainfall forecasting is also vital in sectors such as hydroelectric power generation, since knowledge about water availability is essential for electricity generation. Accurate rainfall forecasts play very important roles in disaster planning and flood control. They enable authorities to take precautionary measures and, where necessary, plan for the evacuation of …

Sentiment Analysis For Stock Market Prediction Using Machine Learning Techniques, Rajendiran P

Theses and Dissertations

Sentiment analysis has become one of the most important procedures to predict the stock market behaviour according to the customer reviews about a particular topic such as news, movie, event, and remarks related to the product. Due to the huge number of reviews generated from the customer, for analyzing information in an accurate manner. In order to detect general view of product, sentiment analysis technique is performed. Lately, the majority of research works is designed for Sentiment analysis by application of an organization and ranking techniques. But it suffers less exactness of the accurate classification of the customer reviews.

The …

An Evaluation Of Reinforcement Learning Algorithms In Video Game Development, Isaac Lockwood

Masters Theses & Specialist Projects

Reinforcement Learning (RL) has demonstrated substantial promise for creating adaptive, responsive AI in complex environments such as video games. Yet despite growing academic interest, industry adoption remains limited due to computational overhead, reward-design challenges, and unpredictable AI behaviors. This thesis investigates how RL algorithms—specifically Advantage Actor-Critic (A2C), Deep Q-Network (DQN), and Proximal Policy Optimization (PPO)—can be applied to three different genres of video games. Those being first-person shooter (fps), fighting, and strategy.

Through a combination of scenario-based experimentation and comprehensive analysis, this work explores the feasibility and design considerations crucial for integrating RL-driven AI into commercial games. Key factors examined …

Deep Neural Network Models For Heatsink Performance Prediction And Optimization In Single Phase Immersion Cooling: Framework For Future Design Tools And Digital Twin Integration, Braxton J. Smith

Mechanical and Aerospace Engineering Theses - Archive

The rapidly rising computational power of modern computing components combined with the advanced packaging techniques being implemented has resulted in exponentially increasing thermal design powers (TDP) from CPUs and GPUs. Traditional air-cooling methods are approaching their effective cooling limits for many of these components, requiring lower supply air temperatures, higher supply air flowrates, and much larger heatsinks to remain feasible. Transitioning from air-cooling to single-phase immersion cooling offers numerous benefits in thermal performance, data-center size reduction, and energy efficiency. To leverage the merits of immersion cooling, the performance of a given heatsink must be predicted and optimized for best performance …

An Intelligent Robotic System For Multi-Sensory Cognitive Fatigue Detection To Assist Persons With Paralysis In Activities Of Daily Living, Enamul Karim

Computer Science and Engineering Dissertations - Archive

Assistive robotics is a promising area for improving the quality of life of people with paralysis, specifically through assistance in Activities of Daily Living (ADLs). Current state-of-the-art assistive robotic systems do not have the capability to dynamically modulate their functionality according to the cognitive fatigue level of the user, which can negatively impact their effectiveness and usability in real-life settings.

This dissertation explores an adaptive robotic framework that adjusts its behavior depending on the cognitive fatigue level of users. The system operates in three different modes, and switches between Fully Controlled, Semi-Autonomous, and Fully Autonomous modes. The overall goal is …

Advancing Machine Learning Approaches Through Robust Methodologies In Llm Code Generation, Adversarial Text Classification, And Unsupervised Learning, Anahita Samadi

Computer Science and Engineering Dissertations - Archive

This dissertation combines insights across text, code, and image modalities to advance the robustness, efficiency, and adaptability of machine learning models. Specifically, we address challenges like adversarial vulnerability in text, the impact of test strategies on code generation, and dimensionality in image representation in unsupervised learning domain. These efforts highlight pipelines for designing machine learning systems that are not only efficient, but also adaptable to complex environments. In addition, these efforts together help form the basis for a multimodal AI capable of thriving in medical applications that this dissertation prototypes for future efforts.

Optimizing Indoor Localization Using Rssi And Iq Data With Machine Learning, Gokdeniz Tingur

Computer Science Theses

This paper explores implementing and evaluating a Bluetooth Low Energy (BLE)-based indoor localization system using Received Signal Strength Indicator (RSSI) and Angle of Arrival (AoA) data via machine learning. A survey of localization technologies (RFID, GPS, ZigBee, and BLE) provides context on capabilities and limitations in indoor positioning. IQ data and phase-based angle estimation show how BLE 5.1’s direction-finding features enable sub-meter accuracy. A multi-phase experiment in a three-story academic building examines model performance with different tag distributions, movement patterns, and environmental constraints. Machine learning models such as Support Vector Machines and Deep Neural Networks are trained and evaluated across …

Machine Learning Based Network Traffic Classification With Cosine-Similarity Based Out-Of-Distribution Detection, Prabhat Edupuganti

Master's Projects

The changes occurring in the amount of encrypted network traffic is growing at an alarming rate. This development has created intricate problems in traffic classification which is vital for effective cybersecurity. Moreover, most frameworks seem to ignore OOD detection, model calibration and novel pattern detection as cornerstone problem areas. The due analysis is presented as a machine learning approach aimed at resolving encrypted traffic classification issues and focuses on novel OOD detection and calibration issues. Primary contributions comprise detection of out-of-distribution states using softmax scaled cosine similarity, advanced variance-based feature elimination, and lowering ECE using stringent NNs. This work demonstrates …

Augmenting Machine Learning Technique Through Natural Language, Tasmia Tasrin

Theses and Dissertations--Computer Science

While artificial intelligence (AI) and machine learning (ML) have proven effective at addressing many of the challenges that we face in our everyday lives, there are many situations in which these methods struggle. Examples include environments where AI or ML systems must perform complex behaviors or those where rewards are difficult to calculate. To address this limitation, interactive machine learning (IML) techniques have been introduced, which incorporate machine-understandable human feedback into traditional ML approaches. This feedback is often given as a discrete, positive or negative numeric value. This feedback is typically provided as often as possible to convey a dense …

Deep Target Recognition: Semi-Supervised Annotation, Sensor Fusion And Super-Resolution, Shoaib Meraj Sami

Graduate Theses, Dissertations, and Problem Reports (ETD)

Despite the recent expansion of machine learning algorithms to cover a wide range of disciplines, several areas of automatic target recognition (ATR) remain underexplored. This dissertation presents tools developed to improve performance in three significant aspects of ATR: semi-supervised annotation, sensor fusion, and image super-resolution. The aim of the semi-supervised methods is to automatically annotate targets in scenarios where labeled data are scarce in the target domain but available in the source domain. Secondly, to address the limitations of individual image sensors and enhance robustness under different environmental conditions and man-made constraints, a sensor fusion algorithm was developed to improve …

Wearable Sensor Data Analysis For Machine Learning-Based Detection Of Posture And Autonomic Responses, Chaitanya Vardhini Anumula

Browse all Theses and Dissertations

This study investigates how Iyengar yoga postures influence autonomic nervous system (ANS) activity by analyzing multimodal physiological signals collected via wearable sensors. The physiological mechanisms underlying Iyengar yoga’s therapeutic effects remain under-explored at the granular, pose-level. Using data collected from 16 participants, this research evaluates whether machine learning models can distinguish between baseline, parasympathetic-dominant, and sympathetic-dominant states based on wrist-worn sensor data. The goals were to explore whether subtle postural variations elicit measurable autonomic responses and to identify which sensor features most effectively capture these changes. Participants performed a sequence of yoga poses while wearing synchronized sensors measuring electrodermal activity …

Performance Comparison Of Machine Learning Across Metal, Cuda, And Neuromorphic Frameworks, Ryan Saini

Master's Projects

Machine learning’s computational demands necessitate optimal performance and utilization. This research compares Apple Silicon M3 Pro with MPS, NVIDIA RTX 3070 GPU with CUDA, and neuromorphic computing for machine learning methods. We provide a cross-platform and cross-architecture performance analysis of machine learning methods to identify optimal configurations for training and inference scenarios. On traditional neural networks, Apple Silicon with MPS delivers superior energy efficiency at the cost of longer processing times for training and inference. NVIDIA with CUDA offers faster computation in training and inference at higher energy costs. Convolutional spiking neural networks perform competitively on event-based data, particularly on …

Malware Generation And Classification Using Pixelcnn, Mounika Krishna Teja Karumudi

Master's Projects

Malware poses a serious threat to both data privacy and system security. With the wide variety of malware families and the surge in cyber-attacks, the accurate classification of malware is crucial for building effective detection and prevention systems. In recent years, deep learning (DL) methods in computer vision have shown promise in classifying malware by converting malware files into visual representations and applying DL algorithms to classify the resulting images. Among the different approaches to malware family classification, image-based methods have gained significant interest. This research focuses on leveraging DL techniques for image-based classification of malware. The success of identifying …

Framework For Identity Privacy Through Gender Based Skeletonization, Harrison Hwang

Master's Projects

The protection of one’s privacy and sensitive information is becoming increasingly difficult in the modern age full of surveillance and data collection. Through the use of image based object detection machine learning models trained for human and facial recognition, people can be identified and tracked to a terrifyingly accurate degree. On the other hand, the information present in surveillance media can play a key role in security and law enforcement. This presents a problem of how to preserve key information without compromising the privacy of any individuals present in the video. In this research project, Computer Vision techniques and a …

Predicting Crises On The African Frontier Stock Markets With Investor Sentiment Indicators: A Machine Learning Approach, David Korsah, Lord Mensah

Journal of International Technology and Information Management

This study examined the predictive ability of machine learning algorithms in identifying crises within African stock markets. The study employed seven distinct machine-learning models, analyzing historical stock prices from eight stock markets, three major sentiment indicators, and the exchange rates of local currencies against the US dollar, with each data spanning from May 1, 2007, to April 1, 2023. Extreme Gradient Boosting (XGBoost) emerged as the most effective algorithm for predicting crises. Historical stock prices and exchange rates were identified as the most critical features for prediction. On the sentiment side, investors’ perceptions of potential volatility on the S&P 500, …

Predicting Global Healthcare Supply Chain Delays: A Machine Learning Approach Leveraging Country-Level Logistics Metrics, Jeevan Sai Gali, Nima Molavi, Sepideh Alavi

Journal of International Technology and Information Management

In global healthcare logistics, ensuring the timely delivery of medical commodities is critical, particularly in low- and middle-income countries characterized by infrastructural limitations and operational uncertainties. This research introduces an advanced, data-driven predictive framework designed to forecast delivery delays by synthesizing granular, internal shipment-level data from the USAID Global Health Supply Chain Program (GHSC-PSM) with external country-level logistics capabilities indicators derived from the World Bank’s Logistics Performance Index (LPI). Rather than relying on retrospective trend analyses, this study employs machine learning algorithms such as Random Forest, XGBoost, Support Vector Machines (SVM), and Multi-Layer Perceptron (MLP) to detect …

Enhancing Ai-Driven Automation For Object Detection And Computer Vision, Nafeeul Alam Walee

College of Graduate Studies: Theses & Dissertations

In recent years, AI-driven automation has revolutionized the field of object detection and computer vision, enabling sophisticated and efficient solutions across various industries. This research explores the latest advances and techniques in improving AI-driven automation for object detection and computer vision applications. We examine state-of-the-art deep learning models and frameworks that have contributed to significant improvements in accuracy and speed and highlight the generative results. The focus is on exploring the real-time processing capabilities that have expanded the applicability of these technologies in real-world scenarios. Furthermore, we investigate image integration and video data to improve precision detection and contextual understanding. …

Customer Segmentation And Fuel Economy Prediction Using Telemetry Data From Heavy-Duty Trucks, Batishahe Selimi

Graduate Theses, Dissertations, and Problem Reports (ETD)

Heavy-duty trucks constitute only a modest fraction of on-road vehicles, yet their intensive duty cycles and high fuel demands yield a disproportionately large share of transportation fuel use and greenhouse gas emissions. Addressing this imbalance requires data-driven tools that capture the realities of fleet operation and translate complex telemetry into actionable insight.

This dissertation introduces a unified machine-learning framework that operates exclusively on high resolution time-series data collected from fifty-nine diesel trucks deployed across Southern California. It begins by constructing a multi-modal feature space that blends statistical summaries of key engine signals, static vehicle descriptors, and Mel-Frequency Cepstral Coefficients, thereby …

Ai-Based Dynamic Spectrum Allocation Model For Wireless Network Management, Sai Sashank Peddibhotla

Master's Projects

The growth of wireless communication has introduced challenges in the dynamic and resource contrived space which is the efficient utilization of bandwidth and spectrum. This research presents a model for dynamic spectrum allocation with the help of Convolutional Neural Network (CNN) for feature extraction and the Deep Q-Network (DQN) model’s reinforcement learning architecture. The CNN captures both spatial and temporal features of the network states and gives them to the DQN for optimal allocation decision making. This CNN-DQN architecture effectively implements spectrum resource allocation in wireless networks and adapts to resource allocation changes within performance bounds. The system’s performance is …

Landslide Prediction Using Time-Series Decomposition, Reinforcement Learning-Based Feature Selection And Ml Models, Mohith Sai Venkat Ankem

Master's Projects

Landslides pose significant risks to human life, the community, and the environment, yet their prediction remains a complex and unexplored challenge. Existing prediction models often rely on surface measurements and satellite images, neglecting the critical role, in providing deeper insights into landslide analysis. The literature review highlights a lack of research in time series decomposition techniques, despite their potential to improve prediction accuracy. Similarly, feature selection methods that enhance model robustness and precision have not been adequately addressed. This study presents a novel approach to predicting landslide displacement by combining feature selection through reinforcement learning techniques with advanced time-series machine …

Quantitative Analysis Of Machine Learning Model Performance And The Need To Consider Explainability, Vishnu S. Pendyala

Open Educational Resources

This presentation, titled "Quantitative analysis of Machine Learning model performance and the need to consider explainability," delves into various metrics used for evaluating machine learning models. It thoroughly examines fundamental classification metrics like accuracy, precision, recall, and F-score, while also discussing more advanced measures such as the Kappa Statistic and Matthews Correlation Coefficient (MCC), particularly highlighting their relevance in scenarios with imbalanced datasets. The presentation underscores the importance of model accuracy in real-world applications and briefly introduces regression metrics like R-squared and F-statistic. Additionally, it addresses challenges related to data imbalance and fairness in ML models, stressing the critical need …

Application Of Lossy And Lossless Compression To Dicom Files, Yizhe Yang

All Theses

The Digital Imaging and Communications in Medicine (DICOM) standard is widely utilized for the management, storage, and transfer of medical images. However, the substantial file sizes associated with DICOM data present challenges in terms of storage and data transmission. Data reduction techniques help address these challenges by minimizing the size of the data while preserving its integrity. This thesis examines various compression methods aimed at reducing the size of DICOM files. We evaluate five lossless compressors and four lossy compressors on DICOM data to compare and assess their performance. Through an analysis of each compressor’s compression efficiency and resulting image …

Identifying Redundant Audio Content Over Cloud Environment Using Deduplication Techniques, Venkatesh K

Theses and Dissertations

Cloud computing has become an integral part of modern internet-based services, with users relying heavily on cloud environments as primary storage solutions. However, the exponential growth in data volume presents a challenge (i.e) the proliferation of duplicated content within cloud repositories. Deduplication techniques provide a promising approach to mitigate this issue. This research focuses on detecting redundant audio content within a cloud environment, specifically targeting the sharing of extensive audio files, such as those in Waveform Audio File Format (WAV). The study proposes the Refined Super Subset Identification Algorithm (RSSIA) to efficiently identify redundant content and segments within existing audio …

Investigating Spatiotemporal Trends Using Precursory Signatures: Implications To Develop Short-Term Earthquake Forecasting Techniques In Sumatra-Andaman Region, Ramya Jeyaraman J

Theses and Dissertations

Earthquake forecasting is a challenging field due to Earth's heterogeneous nature. This research aims to develop a short-term earthquake forecasting model by analyzing spatiotemporal trends and precursory signatures in the Sumatra-Andaman region, known for its high seismic activity and tsunami risk. The study adopts an interdisciplinary approach, integrating solid earth tides (SET), micro shocks, and outgoing longwave radiation (OLR) to gain deeper insights into seismic nucleation processes. The research begins by using Singular Spectral Analysis (SSA) to identify potential seismically vulnerable areas through the analysis of irregularities in SET.

A spatiotemporal analysis of micro shocks is conducted to assess the …