Digital Commons Network^™

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 …

Mitigating Learning Bias In Healthcare Datasets, Samyak Jagdish Kumbhalwar

Master's Projects

CVDs have been a major cause of deaths worldwide with WHO reporting 17.9 million deaths annually. Although there are advancements in the treatment of these diseases, most of the fatalities are a result of untimely diagnosis. Active research is going on to collect data points and risk factors related to these diseases, which can enable early diagnosis. Of the datasets available, many researchers have employed different ML models to predict/detect the prevalence of heart diseases. Many employed Tree based, regression models [3, 6]. Few also tried ensemble approaches [1, 2, 4]. These healthcare datasets are generally found to be imbalanced. …

Frame Rate Enhancement Using Gans: A Deep Learning Approach, Shanmukah Sri Harsha Anivilla

Master's Projects

Videos are sequences of frames that are displayed continuously within a time frame, which creates the illusion. FPS is defined as the number of frames per second, and is crucial to determine the smoothness of motion or scene changes in the video. To improve the appearance of the videos, we can a technique called Frame Rate Enhancement. This is an approach to augment generated frames between pairs of frames using Generative Adversarial Networks. There are a few traditional techniques using Convolution Neural Networks and Optical Flow based methods, but they create unwanted artifacts such as blurring or ghosting and might …

Gesture Recognition Dynamics: Unveiling Video Patterns With Deep Learning, Nithish Reddy Agumamidi

Master's Projects

This paper, Gesture Recognition Dynamics: Revealing Video Patterns with Deep Learning, explores the combination of Long Short-Term Memory(LSTM) with Convolutional Neural Network(CNN) in the identification of convoluted human activities. The study assesses LSTM’s capability to capture temporal dependencies and CNN’s potential to apprehend and extract spatial characteristics to detect the gestures from UCF50. It further evaluates the architecture linkage of LSTM and CNN, which will improve the analytical capacity to interpret and validate dynamic gesture trends. The paper utilizes Mediapipe, an open-source framework created by Google specifically designed for extracting poses. The Mediapipe tool is well-designed to track important body …

Unveiling Gender Bias: An Eye-Tracking Analysis Of Scene Perception, Naga Srija Gopisetty

Master's Projects

Gender bias deeply affects how we perceive and interact with the world around us. This study examined how gender bias affects scene perception by using eye-tracking technology. The relation between gender bias and pupil dilation is examined utilizing art as a stimuli and also studied the underlying cognitive processes. This experiment combines image presentations along with input from participants, drawing on previous research in gender bias, cognitive psychology, and eye-tracking methodologies. The experiment design showcases a series of images to participants, subtly replacing one image during the trial, and then asks participants whether the

replacement took place. This study uses …

Exploring Gender Bias In Large Language Models: Cross-Linguistic Comparisons And Evaluation Letters Analysis, Athira Kumar

Master's Projects

Large language models (LLMs) play a significant role in modern human-computer interaction. They have exploded in popularity recently, becoming widely used for various tasks. However, concerns persist regarding potential biases within these models. This project investigates gender bias in the popular LLMs - GPT-3.5, GPT-4, Gemini, and LLAMA. The first part of our study focuses on analyzing biases using ambiguous sentences across three languages - English, Malayalam, and Tamil. We evaluate the LLMs to see if they associate occupations with commonly held gender stereotypes, by using specific professions within our test sentences. Through the use of two low-resource languages, this …

Understanding Distracted Driving And Gaze Patterns In A Driving Simulator: Simple Vs. Complex Challenges, Rishi Prabhat Narayana Sannala

Master's Projects

Distracted driving has grown in criticality over the recent years, given the numerous distractions that drivers face today, and which have further been magnified by the proliferation of in-vehicle technologies and mobile devices. Such distractions can seriously compromise a driver's ability to be fully focused on the road and to carry out timely responses and informed decisions that are key in minimizing the risks of a crash and maximizing road safety. The general aim of the research is to observe how simple versus complex distractors affect driving performance and gaze patterns. The eyetracker used is the Tobii Pro Fusion, synchronized …

Intelligent Caching Using Continuous Machine Learning In Named Data Networking, Sai Sameer Yanamandra

Master's Projects

Our project focuses on improving Named Data Networking (NDN), an alternative network architecture to traditional IP networks, particularly in unstable conditions where connections frequently drop, and data movement is unpredictable. In NDN, data is cached at various routers across the network, enhancing accessibility even amidst unstable connections. A key challenge we address is determining the optimal level of data redundancy in unstable scenarios. We aim to balance the need for data availability with the risk of excessive data duplication. Our solution involves developing a novel data caching approach for the NDN’s content store based on continuous machine learning. This method …

Gender Classification Through Postural Analysis: A Comparative Study Of 2d Images And 3d Reconstructions., Prathamesh Dixit

Master's Projects

In computer vision, gender classification has become a vital task having applications in human-computer interaction, healthcare, and surveillance. In this study, we look at a two-step approach based on human joint information for gender classification. In this research, we use convolutional neural networks (CNNs).

With Leeds Sports Pose (LSP) dataset, we use a C5 pre-trained model to map and extract joint information from 2D RGB images and after pre-processing and background removal, we use PiFUHD to transform these 2D images into 3D representations. Next, we train our models on RGB images and joint images for both 2D and 3D representations. …

Deciphering Speech Through Vision: A Deep Learning Lip Reading System, Srujith Rao Ambati

Master's Projects

Lip-reading, a ubiquitous field between computer vision and speech processing, focuses on identifying what spoken words a person generates depending on their uttering lip movements. This paper presents a streamlined lip-reading solution that employs machine learning and deep learning. First, Our work utilizes the Multi-Task Cascaded Convo- lutional Networks to detect facial “landmarks,” including the face and lips region, and the aligns the face. The aligned faces are segmented to get the lip images. Lip images are preprocessed using the Real-Enhanced Super Resolution Generative Adversarial Network to enhance image resolution to identify subtle lip movement in video images: a critical …

Characterizing Nanopore Sequencing Artifacts With Deep Learning, David Zhou

Master's Projects

Oxford Nanopore sequencing is a revolutionary new technology for sequencing DNA molecules in long stretches. However, it has a significantly higher error rate than conventional short-read sequencing, resulting in numerous sequencing artifacts. These artifacts can be indistinguishable from low frequency somatic variants, which is a roadblock for cancer diagnosis using liquid biopsies. In this study, benchmarked human genome samples from Genome in a Bottle were used to create a dataset of labeled variants, including artifacts and true variants. Variant features, including sequence context, were used to train various deep learning models. The multi-input neural network combining sequence context features and …

Image Segmentation By Convolutional Neural Networks In Coral Resilience Research, Jennifer Benbow

Master's Projects

As ocean temperatures rise, coral bleaching is becoming more frequent and severe. Selective breeding experiments show promise for enhancing coral resilience, but scaling these projects is hindered by the labor-intensive nature of taking numerous time series measurements as corals grow. Automating this process with computer vision is one solution to this bottleneck, and to our knowledge, no such tool exists at present. To fill this gap, we have trained a set of machine learning models, based on the Mask R-CNN framework, for segmenting juvenile corals in lab-based coral resilience research. This work shows that retraining the Mask R-CNN architecture through …

Investigating Uncertainty In Gaussian Process Models, Wilson Strasilla

Master's Projects

N. A.

Deception Detection Models From Speech, Tien Nguyen

Master's Projects

Recently, researchers have shown an increased interest in automatically detecting deceptive actions. The attention given to this area can be attributed to the many potential applications of deception detection, especially in the field of criminology. To contribute to the deception detection research, this project investigates textual and audio data extracted from spoken and written words. We evaluated and compared the traditional linguistic models with advanced Large Language Models (LLMs) while using Natural Language Processing (NLP) techniques. Additionally, various feature selection techniques were applied to assess the importance of linguistic features. We conducted extensive experiments to evaluate the effectiveness of both …

Response To Intervention: The Effect Of Sensory Processing Tier 1 And Tier 2 Occupational Therapy Intervention, Workshops & Consultation On Kindergarten Students, Kieran Bolger, Cindy Zhang, Julia Dariychuk, Janine Yu, Zuriel Chester

Master's Projects

Sensory modulation is critical for self-regulation in learning environments where children may experience unexpected or atypical sensory stimuli leading to disruptive behaviors often misunderstood or misinterpreted by teachers (Mac Donald & Baist, 2021; Smith & Douglass, 2022). Teachers often lack understanding of sensory processing and evidence-based strategies to address the behavioral challenges related to sensory processing (Cahill et al., 2014; Gee & Nwora, 2011; Mac Donald & Baist, 2021). Occupational therapists practitioners (OTPs) are beneficial team members that are skilled in addressing sensory processing (Cahill, 2010) and can partner with teachers to increase their understanding and utilization of sensory processing …

J-Cag: Java Comment Analysis & Generation - A Sublime Text Plugin Powered By Gpt, Linh Le

Master's Projects

Developers are notoriously disinterested in writing and maintaining comments for their code. The J-CAG plugin automates code analysis and comment generation to save developer time and improve code quality. The project utilizes the Generative Pretrained Transformer model to analyze and provide users with constructive feedback on JavaDoc comments and functions. Embedded within Sublime Text, J-CAG is designed to provide developers with useful advice. It can also generate JavaDoc comments based on the function itself, reducing the time developers spend on writing documentation. The plugin integrates seamlessly with Sublime Text, offering an intuitive interface. With positive results in comment analysis and …

Employing Large Language Models And Retrieval Augmented Generation For Enhanced Predictive Flexibility In Cancer Mortality Prediction, Mridang Kejriwal

Master's Projects

Today, cancer is a major health risk to thousands of people, and there are over a two-hundred different types of cancer. Luckily, over the past several years, the outcomes and survival rates have increased, all thanks to machine learning, specifically Recurrent Neural Networks (RNN) and Long Short-Term memory (LSTM) networks. However, the current prognostic models don’t allow healthcare professionals to adapt the variables to mimic all the different features of every type of cancer, resulting in a model that works but is not as accurate as it could be. This study explores improving the accuracy and adaptability of the current …

Multimodal Emotion Detection In Conversations And Dialogues: A Fusion Model Approach, Abhinay Jatoth

Master's Projects

Emotion recognition is gaining traction due to its wide range of potential applications across different fields. With the rise of social media, chat platforms, and voice assistants, there is a vast increase in data through which humans implicitly and explicitly carry emotional cues. With new algorithms being developed for understanding the nuances of human language and emotion, businesses can tailor more personalized and empathetic service. Sentiment analysis, expresses a positive, negative, or neutral viewpoint laid the foundation of Emotion classification. Emotion classification in conversations represents the most advanced stage of classification. It is also challenging due to the existence and …

Temporal Dynamics In Diabetes Prediction: A Sensor-Driven Time-Series Exploration, Monica Meduri

Master's Projects

Diabetes is a lifelong illness that, if not detected or managed appropriately, turns into serious complications. Correct glucose forecasting is critical to ensuring timely interventions, thereby minimizing risks of hyperglycemia and hypoglycemia, and optimizing the management strategies of the disease. Classical machine learning models have been applied in the blood glucose forecasting problem for a long time, however, usage of transformer-based architectures is still scarce within the literature. Due to the self-attention mechanism, transformers can capture temporal relationships very effectively, which makes them suitable for time-series data. TFT is a novel framework proposed here to utilize time-series data from CGM …

Intelligent Caching In Named Data Networking, Deep Pradipbhai Shah

Master's Projects

Named Data Networking (NDN) has a built-in caching capability that is enabled with the help of its Content Store. Caching in NDN has several benefits, such as reducing overhead on the producer side, avoiding a single point of failure, and reducing network load. The primary caching policy of the NDN architecture is to leave copies everywhere. However, this scheme induces significant cache redundancy. Existing advanced cache techniques either periodically share the entire list of cached content at a node or make a caching decision without knowing the cached content at other nodes in the network. We propose an intelligent cache …

Comparitive Analysis Of Time Series Forecasting Using Frequency Informed Dense Neural Networks And Lstm, Avinash Mangalore Suresh

Master's Projects

Time series forecasting influences our lives on a daily basis, being a versatile tool in various application areas like environmental studies, finance, medicine and much more. While there are many established statistical and deep learning approaches to model time series data, each implementation comes with their own set of drawbacks or areas of improvements. Most of the existing deep learning architectures and research have focused on modeling time series data in the time-domain exclusively. However training deep learning models in the time-domain has some drawbacks, mainly due to the inherent temporal dependence of each time-step on the time-steps before it, …

Multimodal Retrieval-Augmented Generation: Design And Application, Charul Rathore

Master's Projects

The rapid advancement in generative AI and large language models have forever revolutionized how we synthesize data. This project explores and experiments with the potential of a multimodal Retrieval-Augmented Generation (RAG) framework for processing text, tabular and image data. Starting with prompt engineering techniques, we address their limitations in dynamic and domain-specific real world applications by building a multimodal RAG pipeline and evaluating it against human-generated ground truth. The project culminates in BrightMind.ai, a full-stack educational platform featuring novel personalized AI companions for context-aware and adaptive response generation. Its innovative capabilities extend to music, video, and code generation, setting it …

Lexigen: Lexical-Driven Image Generation, Sangram Prashant Chincholkar

Master's Projects

This research project proposes a novel approach to user-driven image editing via natural language descriptions. The aim is an accurate change of certain features of an image with respect to the descriptive text while maintaining, with equal concern, the integrity of the remaining parts of the image not affected by the description. The task is particularly relevant for fields like content creation, personalized design, and automated image editing that require both coherence of a visual scene and textual description. We propose a generative model, LexiGen, which perfectly integrates natural language descriptions with their corresponding visual changes within an image. The …

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 …

Implicit Personality Detection From User Behaviour In Recommendation Systems, Uzma Zubair Shaikh

Master's Projects

Recommendation systems are an integral part of any business, and a crucial factor in determining their success as these systems help businesses in marketing their products to the right kind of audience. Conventional methods of building recommendation systems such as collaborative filtering and content-based recommendation, although effective, suffer from limitations such as cold start and the data sparsity problems. Moreover, these methods aim at finding similar products as user’s past interactions rather than personalizing the recommendations. The upsurge in use of social media, over-the-top content (OTT), and e-commerce platforms has made the task of personalizing recommendations imperative, leading to the …

Load Balancing For Cloud-Based Applications, Nitish Ranjan

Master's Projects

Effective load balancing is critical in ensuring optimal resource utilization, reducing latency, and improving the overall performance of distributed systems. This report commences with a comprehensive literature review on existing load-balancing algorithms, examining their methodologies, strengths, and limitations within various computing environments, including cloud computing, data centers, and network traffic management. Despite significant advancements in this field, the dynamic nature of distributed systems, coupled with the ever-increasing demand for efficient data processing, poses ongoing challenges. In response, this study proposes a novel load-balancing algorithm to address these contemporary challenges. The approach leverages dynamic and hybrid load balancing, distinguishing it from …

Artifacts In Low-Pass Whole Genome Sequencing, Nguyen Mai Anh Do

Master's Projects

Low-pass whole genome sequencing (LP-WGS) provides a cost-effective way to achieve broad genomic coverage, but it comes with the challenge of sequencing artifacts that can complicate accurate variant detection. To address this, we developed a bioinformatics pipeline using Nextflow. Starting with raw sequencing data, the pipeline performed variant calling using VarDict, with Genome in a Bottle (GIAB) high-confidence variants serving as the benchmark for variant validation. We explored machine learning approaches, testing classifiers such as AdaBoost, ExtraTrees, and RandomForest, to evaluate variant classification. Twenty-two features generated by VarDict were fed into Machine Learning pipeline, with AdaBoost standing out for its …

Personalizing Image Generation From Prompts Using Generative Ai, Mit Ramesh Jain

Master's Projects

The rapid advancements in Generative AI, particularly Text-to-Image (T2I) models, have opened up new possibilities for personalized image generation. Finetuning large T2I models for specific downstream tasks is a key approach to achieving tailored outputs. In recent years, Parameter-Efficient Fine-Tuning (PEFT) techniques have gained significant attention as a cost-effective and efficient solution for fine-tuning large models. Initially developed for fine-tuning large language models (LLMs), PEFT techniques have been extensively studied and compared in the context of language tasks. However, regarding the T2I domain, there is a lack of similarly exhaustive and detailed literature on PEFT. This research project, in the …

Leveraging Large Language Models For Transforming Student Information Into Actionable Data, Sree Hari Karri

Master's Projects

Admission season places significant demands on university committees, necessitating the review of vast arrays of documents to assess students’ competence. This project advances the development of an automated system designed to streamline this process by evaluating application materials such as Letters of Recommendation (LoRs), Statements of Purpose (SoPs), and resumes. Utilizing a variety of advanced Natural Language Processing (NLP) techniques, the system compares the performance of several Large Language Model (LLM) approaches. It also experiments with different data handling strategies, including the use of vector stores versus traditional context-based processing, to optimize model efficiency and accuracy. Special attention is given …

Code Quality Enhancement: Evaluating Ai Code Generation With Software Metrics, Sirisha Krishna Murthy

Master's Projects

With the advancements in the stream of AI in the recent time and the evolution of Generative AI, it is a given that there is a need to effectively integrate AI into daily tasks, including Coding. When talking about Generative AI, one important thing to consider is prompting, which is that way to talk to the AI. Depending on specific needs and tasks the way we need to prompt AI can vary. With rapid development in the field, there are a lot of new benchmarks that evaluate the AI coders on correctness, but to effectively adapt AI into actual coding …