Computer Engineering Commons^™

Debtor Eligibility Prediction Using Deep Learning With Chatbot-Based Testing, Reski Noviania, Enny Itje Sela, Luther Alexander Latumakulita, Steven R. Sentinuwo

Knowledge Engineering and Data Science

Predicting debtor eligibility is essential for effective risk management and minimizing lousy credit risks. However, financial institutions face challenges such as imbalanced data, inefficient feature selection, and limited user accessibility. This study combines Recursive Feature Elimination (RFE) and Deep Learning (DL) to improve prediction accuracy. It integrates a chatbot interface for user-friendly testing. RFE effectively identifies critical features, while the DL model achieves a validation accuracy of 97.62%, surpassing previous studies with less comprehensive methodologies. The chatbot's novel design not only ensures accessibility but also enhances user engagement through flexible input options, such as approximate values, enabling non experts to …

Optimal Strategy For Handling Unbalanced Medical Datasets: Performance Evaluation Of K-Nn Algorithm Using Sampling Techniques, Yulita Salim, Aulia Putri Utami, Abdul Rachman Manga, Huzain Azis, Fadhila Tangguh Admojo

Knowledge Engineering and Data Science

This study addresses the critical role of medical image classification in enhancing healthcare effectiveness and tackling the challenges of imbalanced medical datasets. It focuses on optimizing classification performance by integrating Canny edge detection for segmentation and Hu-moment feature extraction and applying oversampling and undersampling techniques. Five diverse medical datasets were utilized, covering Alzheimer’s and Parkinson’s diseases, COVID-19, brain tumours, and lung cancer. The K-Nearest Neighbors (K-NN) algorithm was implemented to enhance classification accuracy, aiming to develop a more robust framework for medical image analysis. The evaluation, conducted using cross-validation, demonstrated notable improvements in key metrics. Specifically, oversampling significantly enhanced lung …

A Hierarchical Density-Based Spatial Clustering Of Applications With Noise (Hdbscan) Approach For Identifying Potential Villages In Buleleng Regency, Dina Nur Amalina, Achmad Fauzan

Knowledge Engineering and Data Science

Buleleng Regency, located in Bali Province, possesses diverse village potential, including agricultural production and tourist attractions. However, this potential has not been fully optimized. Therefore, it is important to enhance village potential by clustering villages based on their specific characteristics to identify and prioritize those requiring special attention. This approach aims to promote equitable village development and reduce poverty levels. This study clusters villages in Buleleng Regency based on their potential using the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) method. The data utilized in this study comprises village potential data obtained from the Buleleng Regency Statistics Office …

A Talking Cart, Abdullah Bin Naeem

LSU New Orleans Theses and Dissertations

This research investigates the development of a robust AI-powered detection and tracking engine aimed at revolutionizing the retail checkout experience. The foundation of this work is a comprehensive exploration of state-of-the-art Computer Vision methodologies, particularly focusing on object detection, segmentation, and tracking. The study employs a modular pipeline that integrates advanced visual recognition algorithms with a robust data processing framework.

Key to this work is the construction of a synthetic dataset using Unity3D, enabling the generation of high-quality annotated data that mirrors real-world retail scenarios. This approach addresses the challenge of insufficient labeled datasets by simulating diverse and cluttered shopping …

Manifold Learning And Undersampling Approaches For Imbalanced Class Sentiment Classification, L.M. Risman Dwi Jumansyah, Agus Mohamad Soleh, Utami Dyah Syafitri

Knowledge Engineering and Data Science

Movie reviews are crucial in determining a film's success by influencing audience decisions. Automating sentiment classification is essential for efficient public opinion analysis. However, it faces challenges such as high-dimensional data and imbalanced class distributions. This study addresses these issues by applying manifold learning techniques, Principal Component Analysis (PCA) and Laplacian Eigenmaps (LE) to reduce data complexity and undersampling strategies (Random Undersampling (RUS) and EasyEnsemble) to balance data and improve predictions for both sentiment classes. On reviews of The Raid 2: Berandal, EasyEnsemble achieved the highest average G-Mean of 0.694 using Term Frequency-Inverse Document Frequency (TF IDF) features with a …

Constructing Qur’An Recitation Classification Using Alexnet Algorithm, Harits Ar Rosyid, Dzulkifli Abdullah, Mohammed S. Alqahtani

Knowledge Engineering and Data Science

The growing demands for accurate and efficient methods in the Qur'an recitation classification highlight the limitations of existing models, particularly in assisting the memorization process. This study aims to address these challenges by implementing the AlexNet Convolutional Neural Network architecture, widely recognized for its effectiveness in image classification, to classify the Qur'an recitations using the Mel Frequency Cepstral Coefficient (MFCC) as the feature extraction method. The research involves several stages, including data collection, preprocessing (audio segmentation by verse), data augmentation, feature extraction, and classification using the AlexNet architecture, followed by performance evaluation. Key results demonstrate that the combination of MFCC …

Deep Learning Approach For Dental Anomalies X-Ray Imaging Using Yolov8, Amelia Ritahani Ismail, Md Salim Sadman Taseen

Knowledge Engineering and Data Science

Dental X-ray imaging is a critical diagnostic tool for identifying various dental anomalies. However, manual interpretation is time-consuming, prone to human error, and requires specialized expertise. Deep learning models, particularly object detection frameworks like YOLO, have demonstrated promising results in automating medical image analysis. This study aims to develop and evaluate a YOLOv8-based deep learning model for automated detection and classification of 14 dental anomaly categories, including Caries, Crowns, Fillings, Implants, and Periapical lesions. The proposed approach addresses limitations in previous YOLO versions by leveraging anchor-free detection and enhanced feature extraction for improved accuracy. The model was trained on a …

Classification Of Anxiety Levels Entering The World Of Work In Final Year Students Using The Neighbor Weighted K-Nearest Neighbor Method, Awang Hendrianto Pratomo, Muhammad Fahmi Adam, Dessyanto Boedi Prasetyo

Knowledge Engineering and Data Science

This study evaluates the accuracy of the Neighbor Weighted K-Nearest Neighbor (NWKNN) method in classifying the anxiety levels of final-year students as they prepare to enter the workforce, particularly in cases of unbalanced data distribution. The system was developed using the prototype method, and NWKNN was applied to classify anxiety levels into low, medium, and high categories. Testing using the Confusion Matrix demonstrated strong performance, achieving an accuracy of 94% based on a dataset of 1009 students, with a 90:10 ratio of training to test data. The results indicate that NWKNN effectively provides classification input values, making it a reliable …

Comparative Analysis Of Bpnn And Lvq For Sundanese Character Recognition, Haviluddin Haviluddin, Herman Santoso Pakpahan, Dinda Izmya Nurpadillah, Hario Jati Setyadi, Medi Taruk, Rayner Alfred

Knowledge Engineering and Data Science

The Sundanese script (Aksara Sunda), an essential part of Sundanese cultural heritage, has been used since the 14th century AD. However, recognizing handwritten Sundanese characters remains challenging due to variations in individual writing styles. This study compares the performance of Backpropagation Neural Network (BPNN) and Learning Vector Quantization (LVQ) for recognizing handwritten Sundanese vowel (Swara) characters. A dataset was collected from 15 individuals, each writing seven Sundanese vowel characters, which were then used for training and testing the recognition models. Experimental results show that BPNN outperforms LVQ, achieving a higher classification accuracy (95.23%), lower Mean Squared Error (MSE), and faster …

Pseudo Gps For Romi, Emmanuel Baez, Owen Guinane, Gabriel Coria, Conor Schott

Mechanical Engineering

The Pseudo-GPS system for Romi robots addresses the need for precise real-time location tracking in Cal Poly's Mechatronics lab. This project, developed by Emmanuel Baez, Gabriel Coria, Owen Guinane, and Conor Schott, under the guidance of instructor Charlie Refvem, provides a proof-of-concept system to enhance the Romi robots' geolocation capabilities for advanced robotic algorithms.

The proposed system uses a Raspberry Pi 4 equipped with a Pi camera module and ArUco markers to track the position and orientation of Romi robots within a lab environment. Custom 3D-printed stands secure markers on the robots, and a designated origin marker defines the coordinate …

Causal Discovery In Time Series Data Using Deep Learning Techniques, Saima Zahin Farhana Absar

Graduate Theses and Dissertations

Causal structure learning from observational data has been an active field of research over the past decades. In the literature, different algorithms and models have been proposed, such as constrained-based methods and score-based methods including the emerging deep learning-based methods. However, most of the approaches apply to static and non-dynamic data only. In many applications, the data is temporal. For example, monitoring systems, weather surveillance systems, and stock data, to name but a few. Incorporating temporal information is an important extension of the causal discovery field. With the growth of observational data these days, the discovery of causal relationships from …

Dynamic Key-Based Privacy-Preserving Authentication Scheme For Internet Of Drones, Zain Chaudhary

Honors Theses

The Internet of Drones (IoD) proliferation has catalyzed transformative changes across various industries, from agriculture to urban management. However, expanding drone networks also presents significant security challenges concerning secure communication and authentication. This paper introduces a robust privacy-preserving key-based authentication scheme tailored explicitly for the IoD, utilizing a matrix key generated by Hierarchical Message Authentication Codes (HMAC) and the SHA-256 algorithm to address these vulnerabilities. Our system enhances security by ensuring each drone in the network can authenticate securely and reliably with a central unit, preventing unauthorized access and securing communications against common threats like eavesdropping and impersonation attacks. Our …

Advancing Visual Geometric Perception: Camera-Based Depth, Reconstruction, And Active Vision, Ziyue Feng

All Dissertations

The advancement of autonomous driving technology and intelligent robotic applications has emerged as a focal point in the realm of autonomy. One of the driving forces behind this trend is the profound understanding of the environment, and at the core of this endeavor lies the three-dimensional geometric perception. This dissertation embarks on a comprehensive exploration of this domain, emphasizing the advances of depth prediction, 3D scene reconstruction, and active vision to enhance geometric perception and scene understanding capabilities in autonomous driving, embodied AI, and robotics. In the domain of depth prediction, this research addresses the challenges of accurately inferring three-dimensional …

Using Symbolic Execution To Analyze The Hardware Tcp Protocol, Nianhang Hu

School of Computing: Dissertations, Theses, and Student Research

As the demand for high performance and flexible networking capabilities increases, the shift from software to hardware implementations of stateful networking functions (such as TCP) is becoming increasingly important. This transition not only enhances processing efficiency in modern networking environments where data transmission rates are rising, but it also reduces the inherent CPU overhead found in software implementations, allowing hardware devices to handle network traffic more efficiently. However, validating the correctness of these hardware designs poses significant challenges due to the complex timing requirements and the vast input space associated with packet-level properties.

The verification of packet-level properties requires coverage …

Not All Samples Are Created Equal: Task-Aware Informative Sampling And Adaptive Inference For Efficient Edge Ai, Rebati Gaire

School of Computing: Dissertations, Theses, and Student Research

The rapid proliferation of Internet of Things (IoT) devices has resulted in an unprecedented influx of data generated at the edge by billions of sensors. Traditional approaches relying on cloud-based processing are increasingly inadequate due to constraints in bandwidth, latency, and privacy. Edge computing has emerged as a transformative paradigm, enabling real-time data processing and decision-making by decentralizing computation to the edge. While the integration of deep learning into edge environments—termed edge intelligence—promises autonomous and personalized operations, it is hindered by challenges such as limited computational resources, energy constraints, and data redundancies.

This thesis addresses these challenges by presenting three …

Prevalence Of Autism Spectrum Characteristics In Students Taking Undergraduate Computing Courses, Rachel Michaela Mettenbrink

School of Computing: Dissertations, Theses, and Student Research

The incidence rate of autism spectrum condition (ASC) has increased significantly in recent decades, as awareness of the condition and its impacts increases amongst clinicians, parents, and the general population. Medical literature has proposed that there may be a relationship between ASC and participation in the computing field. This study tests for the prevalence of autism spectrum condition traits measured by delivering the Autism Spectrum Quotient (AQ) to a population of undergraduate computer science students. We examine the relationships between AQ scores and students taking undergraduate computer science classes, sex, socioeconomic status, and parents in the computing industry. Additionally, we …

Model Reference Adaptive Control For Mobile Manipulators And Beyond, Srivatsan Srinivasan

All Dissertations

In recent years, robotics has expanded into various sectors, including manufacturing, transportation, and household services, making the integration of autonomy a critical area of research. This shift aims to ensure safety and enhance the utility of autonomous systems. Traditionally, robotic applications focused separately on mobility, like automated guided vehicles, and manipulation, such as serial-chain arms in manufacturing. Today, however, we see a merging of these capabilities in the growing field of mobile manipulator robots that combine movement with purposeful interactive functionalities.

A typical mobile manipulator is a robotic arm mounted on a wheeled base. This thesis focuses on advancing control …

Channel Estimation In Millimeter Wave Mimo Systems: The Tensor-Based Methods, Fei He

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

This dissertation presents two novel tensor-based methods for solving channel estimation (CE) problems in Millimeter Wave (mmWave) multiple-input multiple-output (MIMO) wireless communication systems. First, we proposed a method of tensor rank regularization with bias compensation for CE in a hybrid mmWave MIMO system. We modified the CANDECOMP/PARAFAC(CP) decomposition-based method and jointly estimated the tensor rank and channel factor matrices. It differs from most existing works by assuming that the number of channel paths is unknown, yet it can accurately estimate channel parameters without prior knowledge of the number of multipath components. The tensor rank is estimated by a novel sparsity-promoting …

Virtual Control: A Comparison Of Methods For Hand-Tracking Implementation, Nathan Roberts

Honors Program: Senior Projects (Public)

This thesis examines the design philosophy of modern virtual reality applications that utilize hand-tracking as a primary form of user input. The analysis presented hopes to provide ideas for future implementations of this technology so that more immersive experiences are developed. This analysis starts with the discussion of a modern example of successful hand-tracking implementation, then comparing that implementation to a recent senior design project. This comparison is primarily based on each experience’s ability to create interactivity and immediacy. Interactivity is the degree to which the user can quickly and reliably make changes to their virtual environment, while immediacy is …

General Purpose Gpu Benchmarks For Neural Networks, Jose Maria Granados

Open Access Theses & Dissertations

Neural networks are a field of computing experiencing a rise in popularity in recent years due to the utilization of graphics processing units as their computational centerpiece. The lack of neural network benchmarks for the open-source Nyuzi architecture, a developing general-purpose processor with graphical processing capabilities, is the focus of this thesis. This work aims to determine whether Nyuziâ??s performance counters and traceable events suffice for performance tuning of neural network implementations. Given the mathematical intensity of neural networks, a strong emphasis is placed on events related to arithmetic instructions. Experimenting with neural network implementations in C and C++, existent …

Populations Digitally Excluded From Education: Issues, Factors, Contributions And Actions For Policy, Practice And Research In A Post-Pandemic Era, Don Passey, Jean Gabin Ntebutse, Manal Yazbak Abu Ahmad, Janet Cochrane, Simon Collin, Asmaa Ganayem, Elizabeth Langran, Sadaqat Mulla, Ma. Mercedes T. Rodrigo, Toshinori Saito, Miri Shonfeld, Saunand Somasi

Department of Information Systems & Computer Science Faculty Publications

This conceptual paper draws on a wide range of research and policy literature, providing a contemporary view of issues, factors and practices that affect education for digitally excluded populations. Concern for how education for digitally excluded populations can be supported is focal to this paper, with different sections offering key related perspectives. From an analysis of issues, factors and practices, actions for policy, practice and research are identified. Given a key finding that power issues can have major effects on plans, implementation processes and outcomes when addressing needs of education for digitally excluded populations, the paper concludes by offering frameworks …

Heterogeneous Collaborative Robotics: Multi-Robot Navigation In Dynamic Environments, Tyler Nicholas Raettig

Theses and Dissertations

Abstract: The challenges of multi-robot navigation in dynamic environments, focusing on uncertainties in obstacle complexities, partial observation, and the transition of policies from simulations to the real world. The proposed approach utilizes a deep reinforcement learning (DRL) framework enabling a Light Detection and Ranging (LiDAR)-equipped robot to communicate with a camera-equipped robot to achieve optimal paths despite their different sensors. The key contributions include the development of a cooperative architecture for information exchange between robots, a DRL-based framework for learning navigation policies, and a training mechanism based on dynamic randomization for enhanced real-world adaptability. Experimental validation using Gazebo simulations demonstrates …

An Analysis Of Security Risks Posed By Text-Based Generative Ai And Corporate Security Weaknesses Leading To Data Leaks, Tashya Rakshana Byreddy

Electronic Theses, Projects, and Dissertations

ABSTRACT

Generative AI (GenAI) has become a fundamental part of modern life, influencing how we work, learn, and interact with technology. This project focuses specifically on text-based GenAI, which is widely used for tasks such as information gathering, code improvement, and content creation. Despite its benefits, it presents significant security risks that are often underestimated by users. This project investigates these risks and the corporate security gaps that lead to unintentional data leaks. The project also provides a brief overview of Large Language Models (LLMs), which are based on the deep learning technique known as Transformer architecture, used for performing …

Autism Spectrum Disorder, Vidhya Lakshmi Jeevarathinam

Electronic Theses, Projects, and Dissertations

Autism Spectrum Disorder (ASD) diagnosis requires an integrative approach that combines behavioral, biomedical, and computational methodologies for enhanced accuracy. This study introduces a comprehensive framework that employs machine learning (ML) and deep learning (DL) techniques alongside linear regression to model relationships between behavioral traits, biomedical markers, and ASD likelihood. Behavioral inputs, such as social interaction patterns, repetitive behaviors, and communication characteristics, are analyzed using linear regression to identify significant predictors of ASD. Simultaneously, a Convolutional Neural Network (CNN) is trained on image datasets to detect visual cues, such as facial expressions, associated with ASD. Advanced techniques, including transfer learning and …

Project Tracking With Mobile Devices, Mike Son

Electronic Theses, Projects, and Dissertations

This innovative project tracking with mobile devices provides comprehensive access to project information, modernized communication, and effective work management from any device. Through a simple interface, it enables real-time collaboration, work delegation, and progress monitoring, making project management simpler everywhere. A standout feature of this application is its provision of a dedicated API (Web Programming Interface) for mobile devices, enabling seamless integration and synchronization between the web application and mobile platform apps. This guarantees a consistent and integrated user experience across all devices, allowing for quick task updates, and information sharing. The web application emphasizes security, with secure encryption and …

Optimizing Compression Efficiency With Adaptive Quantization Bit Depths, Carson Sisk

All Theses

Large-scale scientific instruments and applications generate massive amounts of data, lead- ing to significant challenges in data transfer and storage for analysis. This constitutes a major

bottleneck to workflow efficiency and scientific throughput. Lossy compression offers a solution to

these storage challenges in increasingly complex systems and services. Error-bounded lossy compression allows users to limit the error introduced during the compression process according to a user-defined metric and achieves significantly higher compression ratios than lossless compression for floating-point data. However, certain data types and compression configurations hinder the attainment of large compression ratios. To address the need for improved compression …

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 …

Co-Emulation Of Robotics And Software-Defined Radio Based 5g Wireless Communications., Bhaskara Venkata Raju Garuda

Electronic Theses and Dissertations

The convergence of robotics and 5G wireless communication technologies has opened new avenues for real-time, dynamic robotic applications. This dissertation introduces a novel framework that integrates the Robot Operating System (ROS), Software-Defined Radios (SDRs), and 5G wireless networks to achieve seamless coemulation of robotic systems. The research emphasizes the unique features of 5G, such as ultra-low latency and high throughput, which enable critical applications like remote surgery, industrial automation, and autonomous vehicles. The methodology combines ROS for robotic control, SDRs for programmable communication channels, and 5G testbeds for high-speed, reliable data transmission. The experimental evaluation focuses on both position-based and …

End-To-End Learning For A Low-Cost Robotics Arm, Abhishek Chothani

Theses and Dissertations

Robotic manipulation is a cornerstone of automation, with the ultimate goal of developing versatile systems capable of executing a wide range of real-world tasks autonomously. Traditional robotics approaches, while reliable and widely adopted in industrial settings, often struggle with adaptability, perception, and dynamic task execution. This thesis explores the evolution from classical robotics techniques to modern learning-based approaches, leveraging advancements in artificial intelligence to overcome these limitations.

Initially, the thesis presents a pick-and-place pipeline built using the Drake robotics framework and the KUKA iiwa robotic arm. This system employs a pseudoinverse controller for inverse kinematics to perform structured tasks like …

Integrating Deep Traffic Prediction And Environmental Impact Assessment Using Noisy Real-World Data In Las Vegas, Tarek Bin Zahid

UNLV Theses, Dissertations, Professional Papers, and Capstones

This thesis introduces an integrated framework for advanced traffic prediction and real-time emission estimation, designed to aid urban planning and environmental monitoring. Utilizing a graph-based transformer model, it predicts traffic conditions across the Las Vegas road network, drawing on spatial and temporal data from a large-scale sensor network. The study significantly expands the dataset from 26 to approximately 900 sensors, enhancing predictive accuracy and regional coverage. Inspired by masking techniques and strategies tailored to incomplete datasets, the model effectively handles real-world, noisy data without relying on resource-intensive imputation. Innovative training approaches enable robust traffic flow predictions despite missing or imperfect …