Digital Commons Network^™

Enhanced Network Anomaly Detection Using Hybrid Deep Learning Network Based On Interactive Threshold, Maythem S. Derweesh, Sundos A. Hameed Alazawi, Anwar H. Al-Saleh

Baghdad Science Journal

In recent years, the growing use of the internet by both governments and private companies has led to a major increase in individual online activity. This expand lead to make the systems more effected to the threats and cyber attacks, and need more strong solutions to cyber security. Recently, deep learning (DL) and machine learning (ML) have become powerful tools in the cybersecurity field, especially for tasks such as detecting malware and filtering spam. This study present new multi layer method to detect the abnormal activities by busing advanced deep learning techniques. The proposed system work in tow main steps. …

Real-Time Production Of High-Resolution, Gap-Free, 3-Hourly Aod Over South Korea: A Machine Learning Approach Using Model Forecasts, Satellite Products, And Air Quality Data, Seoyeon Kim, Youjeong Youn, Menas Kafatos, Jaejin Kim, Wonsik Choi, Seung Hee Kim, Yangwon Lee

Institute for ECHO Articles and Research

Aerosol optical depth (AOD) is essential for air quality monitoring and climate research. However, satellite-based retrievals suffer from cloud-related data gaps, and reanalysis products are limited by coarse spatial resolution and substantial production latency. This study develops a real-time, gap-free, high-resolution (1.5 km) AOD retrieval system for South Korea. The system integrates Copernicus Atmosphere Monitoring Service (CAMS) forecasts, high-resolution meteorological fields, and ground-based air quality observations within a machine learning framework. Three models with varying training periods were systematically evaluated using cross-validation and independent validation with 2024 Aerosol Robotic Network (AERONET) data. The optimal model, trained on 2015–2023 data, achieved …

Advancing Skin Cancer Diagnostics: A Comparative Analysis Of Convolutional Neural Network Models For Skin Lesion Classification, Jesse Osuji, Tania Malik

SURE Journal: Science Undergraduate Research Experience Journal

For many years, skin cancer diagnosis and cancer research have been major focal points in the healthcare sector. Accurate classification of different types of skin lesions, including cancerous ones, is essential for proper diagnostics. Many machine learning (ML) techniques and models are used to solve various problems across various domains. One of such techniques is called neural networks. Convolutional Neural Networks (CNNs) are primarily used in computer vision-based problems, allowing computer systems to process and understand images. CNNs offer a potential tool for diagnosing skin lesions from images, occasionally demonstrating superior accuracy compared to trained dermatologists. This project explores various …

Pixel-Perfect Segmentation Of Solar Filaments, Jamie Harris

Undergraduate Research Symposium

The observation and classification of solar filaments has a drastic impact on the ability to predict solar-magnetic weather phenomena that threatens to put both satellite infrastructure and astronauts at risk. Using the Hɑ filter provided by the Global Oscillations Network Group (GONG), a network of six telescopes around the world dedicated to 24/7 surveillance of the sun, we are able to get images that clearly and prominently display filament activity. With the vast amount of images the GONG takes, it is not possible to manually analyze every image. Using the U-Net model for computer vision, we were able to train …

Rapid Detection Of Aflatoxin B 1 Contamination Levels In Peanuts Based On Dual-Band Hyperspectral Imaging And Machine Learning, Lu Ren, Shuyue Shen, Wanrong Shi, Chuang Rui, Maofeng Dong, Tingting Li

Journal of Food Science and Biotechnology

[Objective ] This study aims to achieve rapid detection of AFB 1 contamination levels in peanuts through dual-band hyperspectral imaging and machine learning.[Method ] A peanut AFB 1 contamination level warning model was constructed via a dual-band hyperspectral imaging system consisting of visible near-infrared spectroscopy at 400~1 000 nm and short-wave near-infrared spectroscopy at 900~1 700 nm,combined with machine learning.Peanut samples with four contamination levels were collected,in which the mass fraction of AFB 1 was determined by ultra-high performance liquid chromatography-tandem mass spectrometry.The effects of four pretreatment methods [first derivative,second derivative,multiplicative scatter correction,and standard normal variate (SNV )],two characteristic wavelength …

Studying Causal Inferences For Student Success In Higher Education, Prabesh Shrestha

Theses and Dissertations

Higher education institutions strive to support students in achieving their academic goals through targeted interventions and data-driven strategies. This study analyzed 19 variables, spanning student demographics, enrollment patterns, and institutional interventions, to identify predictors of students completing all enrolled courses in a semester. Using random forest, logistic regression, and bootstrap forest models, we assessed variable importance and derived causal estimates to determine their impact. Results from causal analysis indicate positive effects from session type, term load, referrals, kudos, flags, and scholarships, while negative impacts were associated with location, course delivery method, enrollment status, advisor contact, and registration interval. These findings …

Protein-Nucleic Acid Language Model-Assisted Design Of Precise And Compact Adenine Base Editor, Jingxuan Ren, Jiawei Yao, Qiuyu Cao, Yinuo Li, Yang Li, Ziyi Zhang, Xiyu Ge, Shengfang Wang, Yang Zhang, Xiaogang Wang, Xiaohui Zhang

Faculty, Staff and Students Publications

Adenine base editors (ABEs) are powerful tools for gene therapy. However, efficient version of ABEs (e.g. ABE8e) always induce excessive bystander and off-target editing events and are large in size, hindering their potential in clinical disease treatment. Here, we develop a pre-trained Protein-Nucleic Acid Constrained Language Model to design ABE8e with high activity, reduced editing window and decreased size. By further engineering, the smallest ABE8e- PNLM-pcABE- with a 27% size reduction, exhibits high activity, precise 3-nt editing window, and reduced off-target events near background level in HEK293T cells. Compared to ABE8e, PNLM-pcABE has up to 133.5-fold precision improvement in pathogenic …

Stakeholder Criteria For Trust In Artificial Intelligence-Based Computer Perception Tools In Health Care: Qualitative Interview Study, Ansh Rai, Meghan E Hurley, John Herrington, Eric A Storch, Casey J Zampella, Julia Parrish-Morris, Anika Sonig, Gabriel Lázaro-Muñoz, Kristin Kostick-Quenet

Faculty, Staff and Students Publications

Background: Computer perception (CP) technologies hold significant promise for advancing precision mental health care systems, given their ability to leverage algorithmic analysis of continuous, passive sensing data from wearables and smartphones (eg, behavioral activity, geolocation, vocal features, and ambient environmental data) to infer clinically meaningful behavioral and physiological states. However, successful implementation critically depends on cultivating well-founded stakeholder trust.

Objective: This study aims to investigate, across adolescents, caregivers, clinicians, and developers, the contingencies under which CP technologies are deemed trustworthy in health care.

Methods: We conducted 80 semistructured interviews with a purposive sample of adolescents (n=20) diagnosed with autism, Tourette …

Hidden Threats In Water: The Global Rise Of Emerging Contaminants, Baljit Singh, Abhijnan Bhat, Gayathree Thenuwara, Kamna Ravi, Azza Silotry Naik, Christine O’Connor, Furong Tian

Research Outputs: 2025-Present

The general spread of water safety awareness and enforcement often masks the escalating risks of emerging contaminants (ECs) that evade standard detection and monitoring techniques. Traditional monitoring infrastructures depend heavily on localized laboratory-based testing, which is expensive, time-consuming, and reliant on specialized infrastructure and skilled personnel. While specific types of ECs and detection technologies have been examined in numerous studies, a significant gap remains in compiling and commenting on this information in a concise framework that incorporates global impact and monitoring strategies. We aimed to compile and highlight the impact ECs have on global water safety and how advanced sensor …

Fully Integrated Slippage Detection System For Lower Limb Amputees, Christopher E. Miglio

Master's Theses

Lower limb amputees face significant challenges in maintaining a proper prosthetic fit, as improper fit can lead to slippage at the limb-socket interface, resulting in discomfort, pressure sores, and long-term musculoskeletal complications. To address this issue, a fully integrated slippage detection system was developed to monitor an amputee’s daily activities and slippage occurrences to understand their prosthetic fit over time. The system consists of a prosthetic sock embedded with Interlink 406 flexible piezoresistive force-sensing resistors (FSRs). The sock, worn directly on the residual limb, continuously measures pressure at the limb-socket interface. Sensor data from six FSRs is sampled at approximately …

Clinical Decision Support For Pharmacologic Management Of Treatment-Resistant Depression With Augmented Large Language Models, Martha Sajatovic

Faculty Scholarship

Background: We evaluated whether a large language model could assist in selecting psychopharmacological treatments for adults with treatment-resistant depression. Methods: We generated 20 clinical vignettes reflecting treatment-resistant depression among adults based on distributions drawn from electronic health records. Each vignette was evaluated by 2 expert psychopharmacologists to determine and rank the 5 best next-step pharmacologic interventions, as well as contraindicated or poor next-step treatments. Vignettes were then presented in random order, permuting gender and race, to a large language model (Qwen 2.5:7B), augmented with a synopsis of published treatment guidelines. Model output was compared to expert rankings, as well as …

Generalized Detection Of Animal Behavior Using Accelerometers, Alexander J. Arrieta

Master's Theses

Animal mounted sensors are becoming increasingly used to passively monitor both domestic and wild animals. Advances in lightweight accelerometer and GPS technology have allowed many animals to be fitted with high accuracy sensors for extended periods of time. This leads to new opportunities to study animal behavior without direct observation. However, interpreting the raw data is difficult due to the high volume and missing context of the information. Machine learning techniques excel at extracting information from raw data streams and are excellent candidates for processing the sensor data. However, due to large variance in how different animals execute the same …

Predicting Newsworthiness Of California Bill Discussions, Venkata Kedarnath Chaturvedula

Master's Theses

Among various California bill hearings, it is crucial to identify which hearings are most likely to receive media coverage, as this highlights the importance of the bill and the hearing, while also underscoring its societal impact. Digital Democracy, established at Cal Poly’s Institute for Advanced Technology and Public Policy, provides users access to a distinctive dataset and information about state legislative committee hearings, hearing transcripts, assets, bill information, etc.

This thesis presents a machine learning framework for predicting whether California legislative bills are likely to receive media coverage. Drawing on a dataset of legislative ”tip sheets” provided by Digital Democracy …

Introducing Statistical And Machine Learning-Based Methods Of Enhancing The Resiliency And Security Of Electrical-Based Critical Infrastructure, Joshua Tyler

Masters Theses and Doctoral Dissertations

Since its introduction into society in the late 1800’s, electricity has become a critical component in how society has functioned. High-voltage electricity provides power for appliances that have become integral to daily living, such as lights, refrigeration, and Heating, Ventilation, And Cooling (HVAC). Low-voltage electricity is used to process and transmit information on and between computers. This information may pertain to medical, financial, and defense-related activities. Over the past hundred years, significant research has been performed to improve electrical-based technology’s capability, scale, resiliency, and security. This study focuses solely on resiliency and security, both of which require efficient data collection, …

Exploring Synthetic Data Generation For Machine Learning And Statistical Analysis, Aditi S. Gajjar

Master's Theses

In the data-driven machine learning and statistical analysis world, real-world data availability is often constrained by privacy concerns, access restrictions, or resource limitations. To address these challenges, synthetic data provides a groundbreaking solution, enabling academics and data scientists to generate artificial datasets that mimic real-world data for model development and testing in a controlled, privacy-preserving environment. The syntheticDatasets package represents an R-based counterpart to Python's widely-used Scikit-learn dataset generators, adapted to meet the needs of statisticians, educators, and data scientists primarily working in the R programming ecosystem.

This thesis explores the design and implementation of the syntheticDatasets package, focusing on …

Marsanywhere: Dataset And Cross-View Diffusion Model For Satellite-To-Ground View Synthesis With Mars Data, Benjamin T. Hinchliff

Master's Theses

Satellite-to-ground view synthesis aims to create a realistic ground view image from a corresponding satellite view image. This is a well-studied problem for street level imagery, with good results being achieved by using modern image synthesis techniques such as diffusion models. However, despite the public availability of satellite and ground level imagery on Mars, these techniques have yet to be applied to the domain due to difficulties in collating and processing the data into a usable form. We address this deficiency by creating a dataset consisting of ground view panorama imagery from the Perseverance rover, along with associated satellite view …

Deepfake Audio Detection, Rashed Alfalasi

Theses

The rise of deepfake audio technology has introduced a serious threat to information credibility, personal security, and media integrity. This thesis investigates the application of machine learning techniques for detecting synthetic audio through the analysis of acoustic features, including Mel-Frequency Cepstral Coefficients (MFCCs), spectral centroid, chroma_stft, and zero-crossing rate. The dataset used in this study was sourced from Kaggle and contains labeled samples of real and fake audio clips. The research aimed to train and evaluate multiple machine learning models—Support Vector Machines (SVM), Random Forest, XGBoost, Logistic Regression, and Neural Networks—to determine the most effective approach for deepfake audio classification. …

Bias Testing And Mitigation In Llm-Based Code Generation, Dong Huang, Jie M. Zhang, Qingwen Bu, Xiaofei Xie, Junjie Chen, Heming Cui

Research Collection School Of Computing and Information Systems

As the adoption of LLMs becomes more widespread in software coding ecosystems, a pressing issue has emerged: does the generated code contain social bias and unfairness, such as those related to age, gender, and race? This issue concerns the integrity, fairness, and ethical foundation of software applications that depend on the code generated by these models but are underexplored in the literature. This paper presents a novel bias testing framework that is specifically designed for code generation tasks. Based on this framework, we conduct an extensive empirical study on the biases in code generated by five widely studied LLMs (i.e., …

Comparative Analysis Of Leading Artificial Intelligence Chatbots In The Context Of Entrepreneurship, Firuz Kamalov, David Santandreu Calonge, Patrik T. Hultberg, Linda Smail, Dima Jamali

All Works

Artificial intelligence (AI) chatbots show remarkable abilities across applications. Despite a growing literature, their capability in the field of entrepreneurship is not fully understood. The aim of this study is to empirically evaluate and compare capabilities of five major AI chatbots—GPT-3.5, GPT-4, Gemini 1.0, Llama 2, and Claude—in the context of entrepreneurship theory, using a benchmark entrepreneurship test. In particular, the performance of the chatbots on a set of multiple-choice questions, short-answer questions, and essay questions related to entrepreneurship is assessed. The results indicate that GPT-4 delivers the strongest overall performance. Meanwhile, Llama 2 offers precise responses with a significantly …

Unmasking Corruption And Bribery Using Predictive Analytics, Maha Salem

Theses

The initiative (Unmasking Corruption and Bribery Using Predictive Analytics) aims to identify employees in government sectors who commit corruption and bribery by addressing issues such as the lack of transparency, fairness, equality, and public trust, as well as weakened loyalty and poor reputation. This project focuses on data analytics and predictive modeling to detect suspicious or high-risk employee behaviors related to corruption and bribery. The main objective is to reduce these unethical activities in government sectors, strengthen integrity, and promote transparency and public trust through predictive capabilities. It also seeks to raise awareness about how serious and harmful these crimes …

Integrating Semi-Supervised Learning And Ensemble Deep Learning For Low-Resource Deep Knowledge Tracing, Uchechukwu Melody Okechukwu

All Theses

As learning platforms scale, two obstacles prevent Deep Knowledge Tracing (DKT) from thriving in practice: the scarcity of labeled interactions and the opacity of predictions. We introduced a semi-supervised, ensemble DKT pipeline that trains diverse architectures, including Knowledge Proficiency Tracing (KPT), Exercise-Correlated KPT (EKPT), and Dynamic Key-Value Memory Networks (DKVMN) on a mixture of limited labeled and abundant unlabeled learner interactions, then aggregates predictions via majority voting to stabilize learning and reduce variance. Evaluated on benchmark datasets such as ASSISTments, the combined approach yields consistent gains in AUC, accuracy, and precision over strong supervised baselines while revealing influential interactions, surfacing …

Integrating Dft And Machine Learning To Predict Structural Properties In High Entropy Alloys, Nathan Linton

All Dissertations

In the past decade, a paradigm shift in the design of metal alloys has been observed. These new alloys are commonly referred to as high entropy alloys (HEAs), multi-principal element alloys (MPEAs), or complex, concentrated alloys (CCAs). In contrast to conventional alloys, which consist of one main element (for example 80%) with other elements in small amounts, HEAs are made of four or more main elements ranging from 5 to 35% each element. Due to the large presence of multiple elements, HEAs have shown substantial material property improvements over conventional alloys such as steel. For example, they have high ductility …

Early Diabetes Prediction Using Machine Learning: A Comparative Study Of Classification Models, Ahmed Abdelqadir Bawazir

Theses

The current dissertation investigates the application of machine learning in diabetes prediction at early stages through a comparison of the performances of three classification models, including Logistic Regression, Decision Tree, and Random Forest. Inspired by the increased and spread cases of diabetes worldwide, the research objective is to facilitate early diagnosis by providing interpretable and accurate predictive models. Based on Pima Indians Diabetes Dataset containing 768 clinical records, the research implemented data preprocessing including KNN imputation and outlier processing, feature scaling, and formation of interaction features. Quantitative and comparative approach was made to train and test the models based on …

Predicting Residential Real Estate Prices In Dubai Using Integrated Data Analytics: A Machine Learning Approach, Mohammad Nasser

Theses

Dubai’s rapidly evolving real estate market attracts substantial global investment yet remains characterized by information asymmetry, pricing volatility, and fragmented data sources. This study examines how integrated data analytics and ensemble machine learning can be used not primarily for precise price prediction, but rather to identify and quantify the key behavioral and transactional drivers of residential property prices in Dubai. A unified dataset was constructed by integrating over 100,000 residential property transactions from the Dubai Land Department with macroeconomic indicators, web-scraped listing attributes, and sentiment measures derived from online reviews and social media discussions. Supervised learning models including Linear Regression, …

Predicting Loan Defaults: A Behavioral Scoring Approach For Portfolio Risk Monitoring In Banking And P2p Lending, Humaid Sultan Almarri

Theses

The critical challenge of lending institutions and peer-to-peer investors is to single out high-risk active borrowers in order to avoid defaults and corresponding losses. This thesis is devoted to the development of a data-driven approach to predict loan defaults, which balances predictive accuracy with interpretability and cost-sensitive evaluation. Using a large dataset of loans from LendingClub, we applied the CRISP-DM methodology, performing extensive data preprocessing and exploratory analysis before training several machine learning models-logistic regression, decision tree, random forest, and XGBoost-to classify loans as default or non-default. Class imbalance was addressed through resampling, and models were tuned via cross-validation with …

Machine Learning-Based Detection Of Covert Data Exfiltration Via Electromagnetic Side-Channel Emissions From Computer Memory In Air-Gapped Systems, Oladapo Akintoye Ajike

All Theses

Air-gapped computer systems are physically isolated from unsecured networks. Though isolated, they remain vulnerable to covert data exfiltration via electromagnetic side channels and other covert-channel attacks. This research presents a comprehensive approach to detecting electromagnetic data exfiltration by establishing a controlled laboratory environment using low-cost, readily available hardware components. The study shows a proof-of-concept covert data transmission system that exploits electromagnetic emissions from computer memory access patterns through software-controlled Random Access Memory (RAM) operations.

The research methodology involved developing a C++ transmitter program that modulates CPU and memory-intensive operations to generate detectable electromagnetic signals at 100 MHz frequency, and implementing …

Integrating Gis And Machine Learning To Uncover Spatial, Temporal, And Contributing Factors To Bicycle Crashes, Precious Kamsiyo Ejikeme

All Theses

The recent drive for a cleaner environment has led to an increase in greener modes of transportation, including the use of bicycles. These emerging trends have led to an increase in bicycle-related crashes. According to the CDC, an estimated 1,150 cyclists were killed in 2023, with 120,000 sustaining non-fatal injuries. Transportation planners and agencies are under pressure to make cycling safer by providing dedicated bike lanes and improving existing infrastructure. To accomplish this, it is very important to understand which factors contribute to bicycle crash severity across different roadways.

Despite recent advancements in modeling bicycle crash severity, most studies rely …

Integrating Gis And Machine Learning To Uncover Spatial, Temporal, And Contributing Factors To Bicycle Crashes, Precious Kamsiyo Ejikeme

All Theses

The recent drive for a cleaner environment has led to an increase in greener modes of transportation, including the use of bicycles. These emerging trends have led to an increase in bicycle-related crashes. According to the CDC, an estimated 1,150 cyclists were killed in 2023, with 120,000 sustaining non-fatal injuries. Transportation planners and agencies are under pressure to make cycling safer by providing dedicated bike lanes and improving existing infrastructure. To accomplish this, it is very important to understand which factors contribute to bicycle crash severity across different roadways.

Despite recent advancements in modeling bicycle crash severity, most studies rely …

Interpretive Prediction Of Hyperuricemia And Gout Patients Via Machine Learning Analysis Of Human Gut Microbiome, Jia Wei Tang, Alfred Chin Yen Tay, Liang Wang

Research outputs 2022 to 2026

Hyperuricemia (HUA) and gout result from imbalances in uric acid metabolism and are closely associated with the gut microbiota. Advanced analytical methods facilitate the exploration of microbiota complexity. In this study, 16S rRNA sequencing data from stool samples of 233 patients were thoroughly collected. Machine learning (ML) and Shapley Additive exPlanations (SHAP) interpretability algorithms were applied to identify core taxa and predict the metabolic functions. The results revealed that the high-contribution core taxa identified by SHAP in each group, such as Oscillospiraceae_UCG-005 and Rhodococcus provided the basis for ML prediction. Among the five classification models, Random Forest (RF) achieved the …

Feature Extraction From Railroad Bearing Onboard Vibration Sensors Using Machine Learning Models, Diego Cantu

Theses and Dissertations

The University Transportation Center for Railway Safety (UTCRS) has developed an algorithm capable of identifying defective railroad bearings, determining damaged component(s) within, and quantifying severity of the defects. The defect-detection algorithm requires the operating speed as an input, which is not readily available in field operation of onboard sensors. Therefore, onboard sensors deployed in rail revenue service must rely on Global Positioning Systems (GPS) to obtain speed, which can be power-intensive and susceptible to signal interference. This study covers the development of a vibration-based model that extracts operating speed from wireless sensor data to enable fully autonomous onboard diagnostics. Signal …