Digital Commons Network^™

Optical Lens Attack On Deep Learning Based Monocular Depth Estimation, Ce Zhou, Qiben Yan, Daniel Kent, Guangjing Wang, Ziqi Zhang, Haydar Radha

Computer Science Faculty Research & Creative Works

Monocular Depth Estimation (MDE) plays a crucial role in vision-based Autonomous Driving (AD) systems. It utilizes a singlecamera image to determine the depth of objects, facilitating driving decisions such as braking a few meters in front of a detected obstacle or changing lanes to avoid collision. In this paper, we investigate the security risks associated with monocular vision-based depth estimation algorithms utilized by AD systems. By exploiting the vulnerabilities of MDE and the principles of optical lenses, we introduce 𝐿𝑒𝑛𝑠𝐴𝑡𝑡𝑎𝑐𝑘, a physical attack that involves strategically placing optical lenses on the camera of an autonomous vehicle to manipulate the perceived …

Enhancing Resilience And Reducing Waste In Food Supply Chains: A Systematic Review And Future Directions Leveraging Emerging Technologies, Asmaa Seyam, May Ei Barachi, Cheng Zhang, Bo Du, Jun Shen, Sujith Samuel Mathew

All Works

The sustainability of food supply chains is gaining increasing attention, particularly after the COVID-19 pandemic. A food supply system that simultaneously prioritises resilience and minimises wastage is crucial. It is found that many studies have explored reducing food waste and increasing supply chain resilience as separate objectives, but research is scarce investigating both objectives in conjunction. This paper presents a comprehensive systematic review focusing on existing solutions to reducing food waste and enhancing resilience. It discusses future directions, particularly leveraging emerging technologies such as the Internet of Things, blockchain, artificial intelligence, and machine learning. The studies are categorised into three …

Exploring How Uncertain Labels From Non-Consensus Panels Affect Machine Learning, Amal Almansour

College of Computing and Digital Media Dissertations

A dataset becomes meaningful for analysis when it contains more representative features. Machine and deep learning models rely on annotated instances for training. The annotation process is usually done either by humans (experts or crowdsourcing) or by models. In many cases, the variability between humans (the inter-observer variability) in evaluation leads to uncertainty in the learning process. Due to the lack of reliable labels in large datasets, the inter-observer variability can be quantified with different methods to estimate the ground truth label (i.e., referenced standard label) for model learning.

In health care, with the rise of artificial intelligence in clinical …

Revolutionizing Public Safety And Criminal Justice Through Ai, Alan Saquella

Publications

Artificial Intelligence (AI) is rapidly transforming public safety, criminal justice and security by fundamentally changing how crimes are committed, investigated and prevented. As AI tools become increasingly sophisticated, law enforcement and corporate security professionals are utilizing these advancements to enhance their capabilities. However, integrating AI into these sectors also brings significant challenges, including ethical concerns, recruitment difficulties, and the surge in crime rates. This article examines the transformative impact of AI, the ongoing efforts to unify AI applications across public safety and security sectors, and expert advice on overcoming the associated challenges.

Power Quality Enhancement In Hybrid Pv-Bes System Based On Ann-Mppt, Heli̇n Bozkurt, Özgür Çeli̇k, Ahmet Teke

Turkish Journal of Electrical Engineering and Computer Sciences

Battery energy systems (BESs) assisted photovoltaic (PV) plants are among the popular hybrid power systems in terms of energy efficiency, energy management, uninterrupted power supply, grid-connected and off-grid availability. The primary objective of this study is to enhance the power quality of a grid-tied PV-BES hybrid system by developing an operation strategy based on Artificial Neural Network (ANN) based maximum power point tracking (MPPT) method. A test system comprising a 10-kWh BES and a 12.4 kW PV plant is structured and simulated on the MATLAB/Simulink platform. The hybrid system is validated with three different cases: constant radiation, rapid changing radiation, …

Mention Detection In Turkish Coreference Resolution, Şeni̇z Demi̇r, Hani̇fi̇ İbrahi̇m Akdağ

Turkish Journal of Electrical Engineering and Computer Sciences

A crucial step in understanding natural language is detecting mentions that refer to real-world entities in a text and correctly identifying their boundaries. Mention detection is commonly considered a preprocessing step in coreference resolution which is shown to be helpful in several language processing applications such as machine translation and text summarization. Despite recent efforts on Turkish coreference resolution, no standalone neural solution to mention detection has been proposed yet. In this article, we present two models designed for detecting Turkish mentions by using feed-forward neural networks. Both models extract all spans up to a fixed length from input text …

A Single Operational Amplifier-Based Grounded Meminductor Mutators And Their Applications, Shalini Gupta, Kunwar Singh, Shireesh Kumar Rai

Turkish Journal of Electrical Engineering and Computer Sciences

In this work, three simple configurations of meminductor mutator are presented. The first two configurations of meminductor mutator have been implemented utilizing one CMOS-based operational amplifier, one memristor, one capacitor, and five resistors, while the third configuration of meminductor mutator is implemented utilizing one CMOS based operational amplifier, two memristors, one capacitor, and four resistors. The implementation and simulation of the proposed configurations are done by using LTspice tool. The viability of the proposed circuits is demonstrated by utilizing TSMC 180 nm CMOS technology parameters. The proposed circuits of the meminductor have a simple structure in contrast to many of …

Finger Movement Recognition Using Machine Learning Algorithms With Tree-Seed Algorithm, Muhammed Sami̇ Karakul, Ahmet Gökçen

Turkish Journal of Electrical Engineering and Computer Sciences

Electromyography (EMG) signals have been used to recognize various actions of hand movements, finger movements, and hand gestures. This paper aims to improve the classification accuracy of EMG signals while decreasing the number of features using the Tree-Seed Algorithm. The dataset containing EMG signals utilized in this investigation is derived from a publicly accessible source. The rationale for selecting the Tree-Seed Algorithm centers on its ability to enhance classification accuracy while minimizing the dimensionality of feature sets. The object function and Tree-Seed Algorithm's nature avoids the results to have low accuracy with fewer features. The aim is not just to …

Enhancing Dtc Control Of Im Using Fuzzy Logic And Three-Level Inverter: A Comparative Study, Siham Mencou, Majid Benyakhlef, Elbachir Tazi

Turkish Journal of Electrical Engineering and Computer Sciences

Direct torque control is the most appropriate strategy for induction motor drive systems, due to its considerable ability to reduce the impact of of machine parameter variations, while offering fast dynamic response and simplified control implementation. However, persistent problems associated with high torque ripple and variable switching frequencies prevent its widespread adoption. To overcome these limitations, several techniques have been developed, in particular the use of multi-level inverters and fuzzy logic algorithms. This article proposes an in-depth evaluation of these techniques in a MATALB/Simulink environment, under various operational conditions. The main objective is to provide a detailed performance analysis of …

How State Universities Are Addressing The Shortage Of Cybersecurity Professionals In The United States, Gary Harris

Journal of Cybersecurity Education, Research and Practice

Cybersecurity threats have been a serious and growing problem for decades. In addition, a severe shortage of cybersecurity professionals has been proliferating for nearly as long. These problems exist in the United States and globally and are well documented in literature. This study examined what state universities are doing to help address the shortage of cybersecurity professionals since higher education institutions are a primary source to the workforce pipeline. It is suggested that the number of cybersecurity professionals entering the workforce is related to the number of available programs. Thus increasing the number of programs will increase the number of …

Ai In The Health Professions, Heidi Monroe, Carrie Fry, Phillip Baker, Erika Busz

AI and the Future of Work

The aim of this track is to provide health professionals, and those interested in mental health and healthcare careers with an understanding of key aspects of AI use in healthcare. Participants will explore advantages of some recent AI developments and evaluate how they may be effectively leveraged to improve patient care, while addressing potential challenges, limitations, and ethical considerations.

Educating With Ai, Grace Seo, David Wicks

AI and the Future of Work

This conference track explores the integration of AI within teaching and learning, with a focus on practical approaches that leverage AI technologies to optimize teaching practices and enhance students’ learning experience. The topics include the essential AI literacies in educational contexts, collaborative learning with AI, and the use of AI for enhanced learning assessments.

A Generalized Machine Learning Model For Long-Term Coral Reef Monitoring In The Red Sea, Justin J. Gapper, Surendra Maharjan, Wenzhao Li, Erik Linstead, Surya Prakash Tiwari, Mohamed A. Qurban, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Coral reefs, despite covering less than 0.2 % of the ocean floor, harbor approximately 35 % of all known marine species, making their conservation critical. However, coral bleaching, exacerbated by climate change and phenomena such as El Niño, poses a significant threat to these ecosystems. This study focuses on the Red Sea, proposing a generalized machine learning approach to detect and monitor changes in coral reef cover over an 18-year period (2000–2018). Using Landsat 7 and 8 data, a Support Vector Machine (SVM) classifier was trained on depth-invariant indices (DII) derived from the Gulf of Aqaba and validated against ground …

Attention-Based Load Forecasting With Bidirectional Finetuning, Firuz Kamalov, Inga Zicmane, Murodbek Safaraliev, Linda Smail, Mihail Senyuk, Pavel Matrenin

All Works

Accurate load forecasting is essential for the efficient and reliable operation of power systems. Traditional models primarily utilize unidirectional data reading, capturing dependencies from past to future. This paper proposes a novel approach that enhances load forecasting accuracy by fine tuning an attention-based model with a bidirectional reading of time-series data. By incorporating both forward and backward temporal dependencies, the model gains a more comprehensive understanding of consumption patterns, leading to improved performance. We present a mathematical framework supporting this approach, demonstrating its potential to reduce forecasting errors and improve robustness. Experimental results on real-world load datasets indicate that our …

Time-Series Feature Selection For Solar Flare Forecasting, Yagnashree Velanki, Pouya Hosseinzadeh, Soukaina Filali Boubrahimi, Shah Muhammad Hamdi

Computer Science Student Research

Solar flares are significant occurrences in solar physics, impacting space weather and terrestrial technologies. Accurate classification of solar flares is essential for predicting space weather and minimizing potential disruptions to communication, navigation, and power systems. This study addresses the challenge of selecting the most relevant features from multivariate time-series data, specifically focusing on solar flares. We employ methods such as Mutual Information (MI), Minimum Redundancy Maximum Relevance (mRMR), and Euclidean Distance to identify key features for classification. Recognizing the performance variability of different feature selection techniques, we introduce an ensemble approach to compute feature weights. By combining outputs from multiple …

A Limited-Preemption Scheduling Model Inspired By Security Considerations, Benjamin Standaert, Fatima Raadia, Marion Sudvarg, Sanjoy Baruah, Thidapat Chantem, Nathan Fisher, Christopher Gill

Computer Science and Engineering Faculty Research

Safety-critical embedded systems such as autonomous vehicles typically have only very limited computational capabilities on board that must be carefully managed to provide required enhanced functionalities. As these systems become more complex and inter-connected, some parts may need to be secured to prevent unauthorized access, or isolated to ensure correctness.

We propose the multi-phase secure (MPS) task model as a natural extension of the widely used sporadic task model for modeling both the timing and the security (and isolation) requirements for such systems. Under MPS, task phases reflect execution using different security mechanisms which each have associated execution time costs …

Designing A Haptic Boot For Space With Prompt Engineering: Process, Insights, And Implications, Mohammad Amin Kuhail, Jose Berengueres, Fatma Taher, Sana Khan, Ansah Siddiqui

All Works

The existing literature has highlighted the potential of Artificial Intelligence (AI) tools in enhancing ideation and optimizing functionality across various engineering disciplines. However, a comprehensive understanding of the impact of AI on the engineering design process, particularly in creating innovative and efficient designs, is currently lacking. This research specifically investigates the integration of AI in developing space-haptic boots by utilizing haptic technology for immersive virtual interactions. The study analyzes the role of an AI tool, ChatGPT-3.5, in the design process, starting from requirement gathering to prototyping and testing, to assess the effectiveness and challenges of AI in engineering design. We …

Advancing Emotional Health Assessments: A Hybrid Deep Learning Approach Using Physiological Signals For Robust Emotion Recognition, Amna Waheed Awan, Imran Taj, Shehzad Khalid, Syed Muhammad Usman, Ali Shariq Imran, Muhammad Usman Akram

All Works

Emotional health significantly impacts physical and psychological well-being, with emotional imbalances and cognitive disorders leading to various health issues. Timely diagnosis of mental illnesses is crucial for preventing severe disorders and enhancing medical care quality. Physiological signals, such as Electrocardiograms (ECG) and Electroencephalograms (EEG), which reflect cardiac and neuronal activities, are reliable for emotion recognition as they are less susceptible to manipulation than physical signals. Galvanic Skin Response (GSR) is also closely linked to emotional states. Researchers have developed various methods for classifying signals to detect emotions. However, these signals are susceptible to noise and are inherently non-stationary, meaning they …

Synthesis Of Zno: Zro2 Nanocomposites Using Green Method For Medical Applications, Mohammed J. Tuama, Maysoon F. Alias

Karbala International Journal of Modern Science

These days, nanocomposites are very popular, especially in medical applications. The spread of diseases in general, and those caused by microbes and cancerous diseases in particular, and the increased resistance of these diseases to antibiotics, have led to the need for the rapid, low-cost, and environmentally friendly production of nanocomposites. To create the chemical G-ZnO: ZrO2 and S-ZnO: ZrO2 (green technique), two different plant extracts were utilized: Z. officinal and S. aromaticum. The effective synthesis and acceptable properties features of the nanoparticles were confirmed using characterization techniques such as X-ray diffraction (XRD), Fourier transform infrared (FTIR) , diffuse reflectance spectroscopy …

Detecting Lgbtq+ Instances Of Cyberbullying, Arslan Bisharat, Manuel Madrigal, Mohammed Abuhamad, Deborah Hall, Yasin Silva

Computer Science: Faculty Publications and Other Works

Social media continues to have an impact on the trajectory of humanity. However, its introduction has also weaponized keyboards, allowing the abusive language normally reserved for in-person bullying to jump onto the screen, i.e., cyberbullying. Cyberbullying poses a significant threat to adolescents globally, affecting the mental health and well-being of many. A group that is particularly at risk is the LGBTQ+ community, as researchers have uncovered a strong correlation between identifying as LGBTQ+ and suffering from greater online harassment. Therefore, it is critical to develop machine learning models that can accurately discern cyberbullying incidents as they happen to LGBTQ+ members. …

An Automated Machine Learning Approach To The Retrieval Of Daily Soil Moisture In South Korea Using Satellite Images, Meteorological Data, And Digital Elevation Model, Nari Kim, Soo-Jin Lee, Eunha Sohn, Mija Kim, Seonkyeong Seong, Seung Hee Kim, Yangwon Lee

Institute for ECHO Articles and Research

Soil moisture is a critical parameter that significantly impacts the global energy balance, including the hydrologic cycle, land–atmosphere interactions, soil evaporation, and plant growth. Currently, soil moisture is typically measured by installing sensors in the ground or through satellite remote sensing, with data retrieval facilitated by reanalysis models such as the European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis 5 (ERA5) and the Global Land Data Assimilation System (GLDAS). However, the suitability of these methods for capturing local-scale variabilities is insufficiently validated, particularly in regions like South Korea, where land surfaces are highly complex and heterogeneous. In contrast, artificial intelligence …

The Evaluation Of Machine Learning Techniques For Isotope Identification Contextualized By Training And Testing Spectral Similarity, Aaron P. Fjelsted, Tyler J. Morrow, Clayton D. Scott, Yilun Zhu, Darren E. Holland, Azaree T. Lintereur, Douglas E. Wolfe

Faculty Publications

Precise gamma-ray spectral analysis is crucial in high-stakes applications, such as nuclear security. Research efforts toward implementing machine learning (ML) approaches for accurate analysis are limited by the resemblance of the training data to the testing scenarios. The underlying spectral shape of synthetic data may not perfectly reflect measured configurations, and measurement campaigns may be limited by resource constraints. Consequently, ML algorithms for isotope identification must maintain accurate classification performance under domain shifts between the training and testing data. To this end, four different classifiers (Ridge, Random Forest, Extreme Gradient Boosting, and Multilayer Perceptron) were trained on the same dataset …

Impact Of An Online Decision Support Tool For Ductal Carcinoma In Situ (Dcis) Using A Pre-Post Design (Aft-25), Elissa Ozanne, Kellyn Maves, Angela Tramontano, Thomas Lynch, Alastair Thompson, Ann Partridge, Elizabeth Frank, Deborah Collyar, Desiree Basila, Donna Pinto, Terry Hyslop, Marc Ryser, Shoshana Rosenberg, E. Shelley Hwang, Rinaa Punglia

Department of Pharmacology and Experimental Therapeutics Faculty Papers

BACKGROUND: The heterogeneous biology of ductal carcinoma in situ (DCIS), as well as the variable outcomes, in the setting of numerous treatment options have led to prognostic uncertainty. Consequently, making treatment decisions is challenging and necessitates involved communication between patient and provider about the risks and benefits. We developed and investigated an interactive decision support tool (DST) designed to improve communication of treatment options and related long-term risks for individuals diagnosed with DCIS.

FINDINGS: The DST was developed for use by individuals aged > 40 years with DCIS and is based on a disease simulation model that integrates empirical data and …

Systematic Review On Isolation, Purification, Characterization, And Industrial Applications Of Thermophilic Microbial Α- Amylases, Rugaiyah A. Arfah, Sarlan Sarlan, Abdul Karim, Anita Anita, Ahyar Ahmad, Paulina Taba, Harningsih Karim, Siti Halimah Larekeng, Dorothea Agnes Rampisela, Rusdina Bte Ladju

Karbala International Journal of Modern Science

The α-amylase enzyme, sourced from diverse organisms, including plants, animals, and bacteria, plays a crucial role in multiple industries, notably food processing sectors like cakes, fruit juices, and starch syrup. Research identifies thermophilic organisms as prime sources of this enzyme thriving at temperatures ranging from 41°C to 122°C. The enzyme purification was carried out using liquid-liquid extraction, which involved the exchange of substances between two liquid phases that were immiscible or partially soluble. The optimal temperature for α-amylase was 45 to 90°C. The best pH for bacterial and fungal α-amylases ranged from 5.0 to 10.5 and 5.0 to 9.0. Based …

The Aimag Project: Using Machine Learning To Predict Crustal Magnetic Anomaly Values, Xavier Gobble, Marlie Mollett, Dr. Dawn King, Dr. Cory Reed, Erin Knese

Undergraduate Research Symposium

A detailed model of the Earth’s total magnetic field is important for acquiring the means for GPS-alternative, magnetic anomaly-based navigation. The Earth’s total magnetic field is an amalgam of 5 mechanisms: the geodynamo generated by the rotation of the Earth’s molten iron core, the fields induced by the flows of electric current in the atmosphere and oceans, the disturbance of the ionosphere by solar wind, and local anomalies attributable to ferromagnetic minerals present in the crust; the lattermost compose the crustal magnetic field. The EMAG2v3 dataset comprises a compilation of satellite, shipborne, and airborne magnetic measurements differenced from the Comprehensive …

Cyber Victimization In The Healthcare Industry: Analyzing Offender Motivations And Target Characteristics Through Routine Activities Theory (Rat) And Cyber-Routine Activities Theory (Cyber-Rat), Yashna Praveen, Mijin Kim, Kyung-Shick Choi

International Journal of Cybersecurity Intelligence & Cybercrime

The integration of computer technology in healthcare has revolutionized patient care but has also introduced significant cyber risks. Despite the healthcare sector being a primary target for cyber-attacks, research on the dynamics of these threats and practical solutions remains limited. Understanding the complexities of cyberattacks in this sector is critical, as the impact extends beyond financial losses to directly affect patient care and the protection of sensitive information. This paper applies Routine Activities Theory (RAT) and Cyber Routine Activities Theory (C-RAT) to analyze high-tech cyber victimization case studies in healthcare. The analysis explores the motivations behind these attacks and identifies …

Understanding The Use Of Artificial Intelligence In Cybercrime, Sinyong Choi, Thomas Dearden, Katalin Parti

International Journal of Cybersecurity Intelligence & Cybercrime

Artificial intelligence is one of the newest innovations that offenders also exploit to satisfy their criminal desires. Although understanding cybercrimes associated with this relatively new technology is essential in developing proper preventive measures, little has been done to examine this area. Therefore, this paper provides an overview of the articles featured in the special issue of the International Journal of Cybersecurity Intelligence and Cybercrime, ranging from deepfake in the metaverse to social engineering attacks. This issue includes articles that were presented by the winners of the student paper competition at the 2024 International White Hat Conference.

Investigating The Intersection Of Ai And Cybercrime: Risks, Trends, And Countermeasures, Sanaika Shetty, Kyung-Shick Choi, Insun Park

International Journal of Cybersecurity Intelligence & Cybercrime

No abstract provided.

Integrated Model Of Cybercrime Dynamics: A Comprehensive Framework For Understanding Offending And Victimization In The Digital Realm, Troy Smith Phd

International Journal of Cybersecurity Intelligence & Cybercrime

This article introduces the Integrated Model of Cybercrime Dynamics (IMCD), a novel theoretical framework for examining the complex interplay between individual characteristics, online behavior, environmental factors, and outcomes related to cybercrime offending and victimization. The model incorporates key concepts from existing theories, empirical evidence, and interdisciplinary perspectives to provide a comprehensive framework. In contrast to traditional criminological theories, the proposed model integrates concepts from multiple disciplines to offer a holistic framework that captures the complexity of cybercrime and specifically caters for the uniqueness of cyberspace. The article will provide a detailed overview of the conceptual model, its theoretical underpinnings drawing …

Fostering Trust Through User Interface Design In Multi-Drone Search And Rescue, Johanna Ahlskog, Maria Theresa Bahodi, Artur Lugmayr, Timothy Merritt

Research outputs 2022 to 2026

Unmanned Aerial Vehicles (UAVs), or drones, are increasingly used in search and rescue (SAR) missions, with pilots transitioning from manual control of single drones to more collaborative tasks orchestrating semi-autonomous fleets. Designing user interfaces to support UAV pilots effectively is crucial to improving the success of search missions. We developed two versions of a multi-drone SAR system prototype to simulate SAR missions and evaluated them with professional UAV SAR pilots in Sweden. Both versions showed the flight paths of the UAVs, yet in one version, a heatmap was overlayed to provide information from a lost person model. We evaluated situational …