Computer Engineering Commons^™

Weakly Supervised Attention-Based Recognition Under Spectral, Turbulence, And Resource Variations, Kshitij Naresh Nikhal

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

While supervised optimization paradigms are ubiquitous across diverse recognition systems, the risk of over-fitting and increasing bias have limited their applicability.

This dissertation focuses on unsupervised learning—learning without precisely curated data—and argues that unsupervised learning methods can enable both discriminability and generalizability. Through the use of attention-based machine learning and advanced clustering, unsupervised methods are able to focus on fine-grained information in images without any explicit supervision. The dissertation introduces a domain-bridging framework for tasks like cross-spectrum matching and long-range recognition, utilizing intra-domain clustering and inter-domain matching to generate pseudo-labels. Additionally, a hash-based network is proposed to accelerate the search …

A Machine Learning Approach For Multipath Characterization And Mitigation Using Chipshape Observations, Sean A. L. Quiterio

Theses and Dissertations

Multipath continues to be a significant error source in satellite navigation. Recent solutions with Neural Networks (NN) model the effects of multipath on the autocorrelation function to predict errors in the Delay Lock Loop (DLL). Chipshape correlation provides a detailed look into the spreading code transitions in the time domain. It is useful in applications such as Signal Quality Monitoring (SQM) and is much more sensitive to multipath than autocorrelation. This research proposes NN models that each predict pseudorange or carrier range errors due to multipath by monitoring the chipshape correlation output. For a simulation with 50 MHz precorrelation bandwidth …

Bert-Based Detection Of Ai-Generated Text For Content Verification, Soham Biren Katlariwala

2024 REYES Proceedings

With advancements in AI-driven natural language generation, distinguishing between AI-generated and human-written text has become imperative for ensuring content authenticity across industries. This study explores the effectiveness of Bidirectional Encoder Representations from Transformers (BERT) in addressing this classification challenge. Utilizing a diverse dataset and robust preprocessing techniques, BERT achieved a peak F1-score of 0.94364, outperforming traditional models such as Logistic Regression and Support Vector Machines. The results underscore the potential of transformer-based models in addressing real-world con- tent verification problems. Future enhancements include fine-tuning and expanding datasets for greater generalizability.

Predicting Compressive Strength Of Concrete Incorporating Fly Ash, Blast Furnace Slag, And Superplasticizer Using Machine Learning Techniques, Muhammad Faisal Yaqub

2024 REYES Proceedings

Concrete is the second most essential element in the construction industry, and its strength requirements vary based on the specific conditions of each project. However, determining the compressive strength of concrete involves laboratory tests, which wastes a lot of time and money. Researchers have developed machine learning models that predict the compressive strength of cement-based concrete having various mixes. In this research, the compressive strength of concrete incorporating fly ash, blast furnace slag, and superplasticizer is predicted using different machine learning models, namely, Linear Regression, Random Forest Regression, Decision Tree Regression, Extreme Gradient Boosting, Light Gradient Boosting, AdaBoost, and CatBoost …

Benchmarking And Enhancing Generalization In Multilingual Speech Emotion Recognition, Mohamed Osman Ismael

Theses and Dissertations

Speech Emotion Recognition (SER) is pivotal in advancing human-computer interaction by enabling machines to understand and respond to human emotions. Despite significant progress with self-supervised learning models, SER systems often struggle with generalization across diverse languages and unseen data distributions, limiting their real-world applicability. This thesis addresses these challenges by first introducing a large-scale benchmark to evaluate the robustness and adaptability of state-of-the-art SER models in both in-domain and out-of-domain settings. The benchmark includes a diverse set of multilingual datasets, emphasizing cross-lingual and out-of-domain evaluations to assess model generalization. Surprisingly, we find that the Whisper model, originally designed for automatic …

A Two-Stage Machine Learning Approach For Fake News Detection And News Article Categorization, Snegdha Adusumilli

Master's Projects

This project employs machine learning techniques to develop a sequential model for detecting and categorizing fake news, aiming to mitigate its proliferation in today's digital landscape. The model operates in two phases: in the first phase, the classification algorithms like Naïve Bayes, XGBoost and Random Forest are used to distinguish between true and false news stories and in the second phase the capabilities of Naïve Bayes, XGBoost, Random Forest, and the Transformer-based BERT (Bidirectional Encoder Representations from Transformers) model are leveraged to further categorize the news into specific topics.

The methodology encompasses several key steps: data acquisition, preprocessing, feature extraction, …

Novel Approach To Music Analysis Using Apache Spark, Nidhi Zare

Master's Projects

Music is one of the most common source of entertainment. Every user has their own taste of music and prefer to listen music that adheres to their taste and mood. There are various categories, called as music genres in which music can be classified. This research project addresses the challenge in music genre classification by using various deep learning models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Very Deep Convolutional Networks (VGGNet), ResNet and others. The primary objective of this research is to enhance the accuracy of music genre classification using a distributed computing framework Apache Spark. …

Robustness Of Learning Models To Label Flipping Attacks, Sarvagya Bhargava

Master's Projects

In this paper we compare traditional machine learning and deep learning models

trained on a malware dataset when subjected to adversarial attack based on label- flipping. Specifically, we investigate the robustness of different models when faced

with varying percentages of misleading labels, assessing their ability to maintain their accuracy in the face of such adversarial manipulations of the training data. This research aims to provide insights into which models are more robust, in the sense of being better able to resist intentional disruptions to the training data. We find that traditional machine learning models and boosting techniques are more robust …

Multi-Platform Cyberbullying Detection Using Nlp And Machine Learning, Chinmayi Lokeshwar Hegde

Master's Projects

The issue of cyberbullying is growing due to the online anonymity and due to online platforms having less repercussions. This research proposes for proactive measures to detect and prevent such behavior before it reaches the victim. By using data from various social media platforms and employing machine learning techniques, this research proposes an innovative system aimed at identifying and thwarting cyberbullying incidents preemptively. While existing methods have primarily focused on prediction and detection of cyberbullying incidents, there remains a significant gap in research regarding prevention strategies. This project aims to address this gap by leveraging machine learning, natural language processing …

A Comprehensive Survey On Rare Event Prediction, Chathurangi Shyalika Jayakody Kankanamalage, Ruwan Wickramarachchi, Amit Sheth

Publications

Rare event prediction involves identifying and forecasting events with a low probability using machine learning (ML) and data analysis. Due to the imbalanced data distributions, where the frequency of common events vastly outweighs that of rare events, it requires using specialized methods within each step of the ML pipeline, i.e., from data processing to algorithms to evaluation protocols. Predicting the occurrences of rare events is important for real-world applications, such as Industry 4.0, and is an active research area in statistics and ML. This paper comprehensively reviews the current approaches for rare event prediction along four dimensions: rare event data, …

Assessing The Condition Of Pavements (Road Surfaces) Using Computer Vision & Machine Learning, Syed Ibrahim Hassam

Doctoral

Regular inspections of pavements are conducted by civil infrastructure departments to evaluate the surface condition. Pavement surfaces are subject to deterioration caused by several factors such as traffic, weather, and sunlight. This deterioration becomes evident through various distresses, including potholes, rutting, cracking, bleeding, patching, and ravelling, which gradually affects the surface layer over time. It is essential to assess the condition of pavements as it not only ensures their usability but also maximises public safety. Effective pavement maintenance requires substantial resources and capital investment to carry out the most suitable maintenance treatments at the optimal time. Furthermore, the outcomes of …

Fake News Detection In Online Platforms, Elena Shushkevich

Doctoral

This thesis presents research conducted during a Ph.D. program at Technological University Dublin from 2020 to 2024. The objective of this research is to develop and evaluate effective methods for detecting and classifying fake news in social media and press, addressing the critical issue of misinformation in the digital age. The relevance of this study is underscored by the increasing prevalence of fake news and its potential societal impact, emphasizing the importance of advanced tools for identifying and mitigating misinformation.

Ai-Enabled Hardware Security Approach For Aging Classification And Manufacturer Identification Of Sram Pufs, Harshdeep Singh

Browse all Theses and Dissertations

Semiconductor microelectronics integrated circuits (ICs) are increasingly integrated into modern life-critical applications, from intelligent infrastructure and consumer electronics to the Internet of Things (IoT) and advanced military and medical systems. Unfortunately, these applications are vulnerable to new hardware security attacks, including microelectronics counterfeits and hardware modification attacks. Physical Unclonable Functions (PUFs) are state-of-the-art hardware security solutions that utilize process variations of integrated circuits for device authentication, secret key generation, and microelectronics counterfeit detection. The negative impact of aging on Static Random Access Memory Physical Unclonable Functions (SRAM PUFs) has significant consequences for microelectronics authentication, security, and reliability. This research thoroughly …

Pneumonia Detection With Limited And Imbalanced Data Using Energy-Based Out-Of-Distribution Technique, Jasbin Karki

Browse all Theses and Dissertations

The automated detection of pneumonia through chest X-ray presents a critical challenge in medical diagnostics, particularly due to the restrictions of limited and imbalanced chest X-ray data for training AI models. Traditional methods that depend on softmax confidence scores can be overconfident even when generating erroneous outputs especially when they are processing completely new inputs, leading to unreliable diagnostic results. This research addresses challenges in AI models which aim to develop a robust pneumonia detection system using an Energy-Based Out-of-Distribution (OOD) technique that can work effectively even with limited and imbalanced data. The study focused on creating a more reliable …

Improvements In Biomedical Image Analysis With Computational Intelligence And Data Fusion Techniques, Akanksha Maurya

Doctoral Dissertations

"An estimated 2 million new cases of basal cell carcinoma (BCC) are diagnosed each year in the United States, making it one of the most common skin cancers. Earlier detection of these cancers enables less invasive biopsies. Clinical detection consists of a preliminary visual observation of these skin lesions by an experienced dermatologist making it a specialized task highly dependent on their time, availability, and resources. Hence, there is a need for automating this process that can assist healthcare staff. In recent years, deep learning (DL) has been used extensively and successfully to diagnose different cancers in dermoscopic images. Telangiectasia …

Wall-E: An Autonomous Ai Rover For Precision Agriculture, Simar Ghumman

Master's Projects

Unmanned Ground Vehicles (UGVs) are emerging as a crucial tool in the world of precision agriculture. By working with UGVs equipped with machine learning, we can find solutions to a range of complex agricultural problems. My project, titled “Wall-E: Artificial Intelligence Robot for Precision Agriculture,” focuses on developing a UGV capable of navigating through agriculture fields autonomously while capturing data. Using machine learning, computer vision, and other sensor technologies, Wall-E is capable of estimating the total yield of crops, self-localization, mapping its environment in real time, and avoiding obstacles along its route. The purpose of this project is to automate …

Ensemble Learning With Sleep Mode Management To Enhance Anomaly Detection In Iot Environment, Khawlah Harahsheh, Rami Al-Naimat, Malek Alzaqebah, Salam Shreem, Esraa Aldreabi, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

The rapid proliferation of Internet of Things (IoT) devices has underscored the critical need for energy-efficient cybersecurity measures. This presents the dual challenge of maintaining robust security while minimizing power consumption. Thus, this paper proposes enhancing the machine learning performance through Ensemble Techniques with Sleep Mode Management (ELSM) approach for IoT Intrusion Detection Systems (IDS). The main challenge lies in the high-power consumption attributed to continuous monitoring in traditional IDS setups. ELSM addresses this challenge by introducing a sophisticated sleep-awake mechanism, activating the IDS system only during anomaly detection events, effectively minimizing energy expenditure during periods of normal network operation. …

Explore Security And Machine Learning Applications In Next Generation Wireless Networks, Haolin Tang

Theses and Dissertations

Next-generation (NextG) or Beyond-Fifth-Generation (B5G) wireless networks have become a prominent focus in academic and industry circles. This is driven by the increasing demand for cutting-edge applications such as mobile health, self-driving cars, the metaverse, digital twins, virtual reality, and more. These diverse applications typically require high communication network performance, including spectrum utilization, data speed, and latency. New technologies are emerging to meet the communication requirements of various applications. Intelligent Reflecting Surface (IRS) and Artificial Intelligence (AI) are two representatives that have been demonstrated as promising and powerful technologies in NextG communications. While new technologies significantly enhance communication performance, they …

Development Of A Machine Learning System For Irrigation Decision Support With Disparate Data Streams, Eric Wilkening

Department of Agricultural and Biological Systems Engineering: Dissertations, Theses, and Student Research

In recent years, advancements in irrigation technologies have led to increased efficiency in irrigation applications, encompassing the adoption of practices that utilize data-driven irrigation scheduling and leveraging variable rate irrigation (VRI). These technological improvements have the potential to reduce water withdrawals and diversions from both groundwater and surface water sources. However, it is vital to recognize that improved application efficiency does not necessarily equate to increased water availability for future or downstream use. This is particularly crucial in the context of consumptive water use, which refers to water consumed and not returned to the local or sub-regional watershed, representing a …

Detection Of Myofascial Trigger Points With Ultrasound Imaging And Machine Learning, Benjamin Formby

All Theses

Myofascial Pain Syndrome (MPS) is a common chronic muscle pain disorder that affects a large portion of the global population, seen in 85-93% of patients in specialty pain clinics [10]. MPS is characterized by hard, palpable nodules caused by a stiffened taut band of muscle fibers. These nodules are referred to as Myofascial Trigger Points (MTrPs) and can be classified by two states: active MTrPs (A-MTrPs) and latent MtrPs (L-MTrPs). Treatment for MPS involves massage therapy, acupuncture, and injections or painkillers. Given the subjectivity of patient pain quantification, MPS can often lead to mistreatment or drug misuse. A deterministic way …

Accelerating Machine Learning Inference For Satellite Component Feature Extraction Using Fpgas., Andrew Ekblad

Theses and Dissertations

Running computer vision algorithms requires complex devices with lots of computing power, these types of devices are not well suited for space deployment. The harsh radiation environment and limited power budgets have hindered the ability of running advanced computer vision algorithms in space. This problem makes running an on-orbit servicing detection algorithm very difficult. This work proposes using a low powered FPGA to accelerate the computer vision algorithms that enable satellite component feature extraction. This work uses AMD/Xilinx’s Zynq SoC and DPU IP to run model inference. Experiments in this work centered around improving model post processing by creating implementations …

Learning-Based Ant Colony Optimization Algorithm For Solving A Kind Of Complex 2-Echelon Vehicle Routing Problem, Xue Chen, Rong Hu, Hui Wang, Zuocheng Li, Bin Qian, Yixu Li

Journal of System Simulation

Abstract: Aiming at green 2-echelon vehicle routing problem with simultaneous pick-up and delivery, a learning-based ant colony optimization algorithm combined with clustering decomposition is proposed. The objective function to be minimized is total transportation cost wherein carbon emission cost is specially considered. Associated with the mutual coupling features of the 2-echelon vehicle routing problem, we propose a distance-based clustering method to decompose the original problem into a set of sub-problems. Then, a learning-based ant colony optimization algorithm is presented to find the solutions of the sub-problems based on which the solution of the original problem can be obtained. In the …

Machine Learning Based Bioinformatics Analysis Of Intron Usage Alterations And Metabolic Regulation In Adipose Browning, Hamza Umut Karakurt, Pinar Pi̇r

Turkish Journal of Electrical Engineering and Computer Sciences

Adipose tissue is the major energy depot of the body and is considered an endocrine organ. Adipose tissue involves many different cell types, first and foremost, the adipocytes. White adipose cells that store fat and brown adipocytes that take part in lipid oxidation and heat generation are the most common cell types in adipose tissue. Even though brown adipocytes which have a high number of mitochondria and high fat-burning capacity are rare in adults, they are abundant in newborns and rodents. White adipocytes can gain a temporal brown-like character with a process called browning, which can be induced with cold …

Fuzzycsampling: A Hybrid Fuzzy C-Means Clustering Sampling Strategy For Imbalanced Datasets, Abdullah Maraş, Çi̇ğdem Erol

Turkish Journal of Electrical Engineering and Computer Sciences

Classification model with imbalanced datasets is recently one of the most researched areas in machine learning applications since they induce to the emergence of low-performing machine learning models. The imbalanced datasets occur if target variables have an uneven number of examples in a dataset. The most prevalent solutions to imbalanced datasets can be categorized as data preprocessing, ensemble techniques, and cost-sensitive learning. In this article, we propose a new hybrid approach for binary classification, named FuzzyCSampling, which aims to increase model performance by ensembling fuzzy c-means clustering and data sampling solutions. This article compares the proposed approaches' results not only …

Classification Of Chronic Pain Using Fmri Data: Unveiling Brain Activity Patterns For Diagnosis, Rejula V, Anitha J, Belfin Robinson

Turkish Journal of Electrical Engineering and Computer Sciences

Millions of people throughout the world suffer from the complicated and crippling condition of chronic pain. It can be brought on by several underlying disorders or injuries and is defined by chronic pain that lasts for a period exceeding three months. To better understand the brain processes behind pain and create prediction models for pain-related outcomes, machine learning is a potent technology that may be applied in Functional magnetic resonance imaging (fMRI) chronic pain research. Data (fMRI and T1-weighted images) from 76 participants has been included (30 chronic pain and 46 healthy controls). The raw data were preprocessed using fMRIprep …

Stepwise Dynamic Nearest Neighbor (Sdnn): A New Algorithm For Classification, Deni̇z Karabaş, Derya Bi̇rant, Peli̇n Yildirim Taşer

Turkish Journal of Electrical Engineering and Computer Sciences

Although the standard k-nearest neighbor (KNN) algorithm has been used widely for classification in many different fields, it suffers from various limitations that abate its classification ability, such as being influenced by the distribution of instances, ignoring distances between the test instance and its neighbors during classification, and building a single/weak learner. This paper proposes a novel algorithm, called stepwise dynamic nearest neighbor (SDNN), which can effectively handle these problems. Instead of using a fixed parameter k like KNN, it uses a dynamic neighborhood strategy according to the data distribution and implements a new voting mechanism, called stepwise voting. Experimental …

Cognitive Load Detection Using Ci-Ssa For Eeg Signal Decomposition And Nature-Inspired Feature Selection, Jammisetty Yedukondalu, Lakhan Dev Sharma

Turkish Journal of Electrical Engineering and Computer Sciences

Cognitive load detection is eminent during the mental assignment of neural activity because it indicates how the brain reacts to stimuli. The level of cognitive load experienced during mental arithmetic tasks can be determined using an electroencephalogram (EEG). The EEG data were collected from publicly available datasets, namely, mental arithmetic task (MAT) and simultaneous task workload (STEW). The first phase comprises decomposing the electroencephalogram (EEG) signal into intrinsic mode functions (IMFs) using circulant singular spectrum analysis (Ci-SSA). In the second phase, entropy-based features were evaluated using IMFs. After that, the extracted features were fed to nature-inspired feature selection algorithms: genetic …

A Machine Learning Approach For Dyslexia Detection Using Turkish Audio Records, Tuğberk Taş, Muhammed Abdullah Bülbül, Abas Haşi̇moğlu, Yavuz Meral, Yasi̇n Çalişkan, Gunay Budagova, Mücahi̇d Kutlu

Turkish Journal of Electrical Engineering and Computer Sciences

Dyslexia is a learning disorder, characterized by impairment in the ability to read, spell, and decode letters. It is vital to detect dyslexia in earlier stages to reduce its effects. However, diagnosing dyslexia is a time-consuming and costly process. In this paper, we propose a machine-learning model that predicts whether a Turkish-speaking child has dyslexia using his/her audio records. Therefore, our model can be easily used by smart phones and work as a warning system such that children who are likely to be dyslexic according to our model can seek an examination by experts. In order to train and evaluate, …

Analysing Child Sexual Abuse Activities In The Dark Web Based On An Efficient Csam Detection Algorithm, Vuong Ngo, Christina Thorpe, Susan Mckeever

Articles

Abstract: Child sexual abuse material (CSAM) activities are prevalent on the Dark Web to evade detection, posing a global challenge for law enforcement. Our objective is to analyze CSAM discussions in this concealed space using a Support Vector Machine model, achieving an accuracy of 87.6%. Across eight forums, approximately 28.4% of posts contained CSAM, with victim ages most commonly reported as 12, 14, 13, and 11 years old for YouTube, Skype, Instagram, and Facebook, respectively. Additionally, in forums discussing boys, the most frequently mentioned nationalities in CSAM posts were English, German, and American, accounting for 12%, 7.8%, and 6% of …

Compatibility Of Clique Clustering Algorithm With Dimensionality Reduction, Ug ̆Ur Madran, Duygu Soyog ̆Lu

Applied Mathematics & Information Sciences

In our previous work, we introduced a clustering algorithm based on clique formation. Cliques, the obtained clusters, are constructed by choosing the most dense complete subgraphs by using similarity values between instances. The clique algorithm successfully reduces the number of instances in a data set without substantially changing the accuracy rate. In this current work, we focused on reducing the number of features. For this purpose, the effect of the clique clustering algorithm on dimensionality reduction has been analyzed. We propose a novel algorithm for support vector machine classification by combining these two techniques and applying different strategies by differentiating …