Digital Commons Network^™

Deep Learning Approaches For Gender Classification From Facial Images, Mustafa Abdulfattah Habeeb, Yahya Layth Khaleel, Reem D. Ismail, Z. T. Al-Qaysi, Fatimah N. Ameen

Mesopotamian Journal of Big Data

Gender recognition on the facial level is considered one of the most important technologies that finds use in such fields as a personalized marketing plan, safe systems of authentication, and effective human-computer interfaces. However, it has the following challenges; variation of lighting, facial movement, and ethnic/age face images. AI and DL has been improving on the effectiveness, flexibility, and speed of the gender classification system. AI enables complex and automatic feature learning in Data, while DL is tailored for handle variants in vision-based data. In this paper, we evaluated several architectures including Efficient Net_B2, ResNet50, ResNet18, and Lightning whilst determining …

Automated Water Quality Assessment Using Big Data Analytics, Yasmin Makki Mohialden, Nadia Mahmood Hussien, Saba Abdulbaqi Salman

Mesopotamian Journal of Big Data

Water is one of the world's most precious resources, essential to life. Industrial waste, agricultural runoff, and urban discharge degrade water, rendering it unfit for consumption. Water quality monitoring and evaluation are more important than ever. Big Data analytics is used to examine water quality utilizing enormous datasets of pH, hardness, solids concentration, chloramine, sulfate, conductivity, organic carbon, trihalomethanes, and turbidity. This work classifies water potability, which is vital for human consumption, using strong machine learning on massive datasets. Classifiers were Random Forest, Gradient Boosting, and Support Vector Machine on 3,276 water bodies. The Random Forest classifier obtained the highest …

Anomaly-Based Ids (Intrusion Detection System) For Cyber-Physical Systems, Ahmad Muter Awaad, Khattab M. Alheeti, Abdul Kream A.H. Najem

Mesopotamian Journal of Big Data

Cyber-physical systems (CPS) are critical infrastructures that integrate physical processes with computational components. The security of CPS is paramount, as any breach can lead to severe consequences. Anomaly-based intrusion detection systems (IDS) have emerged as a promising approach to safeguard CPS against cyber threats. This paper presents an anomaly-based IDS designed specifically for CPS, leveraging machine learning techniques to establish a baseline of normal system behaviour and promptly detect deviations indicative of malicious activities. The proposed system incorporates multiple classification techniques, including KNeighbors, RandomForest, XGB, DecisionTree, SGD, SVM, LGBM, AdaBoost, Bagging, and MLP Classifier, to enhance detection accuracy and robustness. …

Age-Related Development Of Bilateral Coordination Of The Upper Limbs In Children And Adolescents, Samuel Nemanich, Sheila M. Schindler-Ivens

Physical Therapy Faculty Research and Publications

Bilateral coordination of the upper limbs (UL) is important for activities of daily living and physical activities. Motor coordination improves from childhood through adolescence. However, age-coordination trajectories for bilateral UL movements are not well-established, and it is unclear if bimanual coordination develops slower than unilateral coordination. In this study we examined age-related changes in UL coordination from childhood to late adolescence. Typically-developing children (N = 29, aged 7–17 years) performed unilateral and bilateral, antiphase cycling tasks with their ULs. Variations in cycling velocity and interlimb phase errors were computed as measures of coordination. Linear regression was used to examine …

The Effects Of Attentional Focus Instructions On Approach Jump Performance, Hanwen Liu, Scott Arnett, Dano Tolusso, Kaylee Woodard

Physical Therapy Faculty Research and Publications

Introduction

Attentional focus has been shown to significantly influence motor learning and performance, with external focus instructions enhancing performance compared to internal focus instructions. Research has also demonstrated that novice performance is improved when instructed to focus on skill execution processes rather than outcomes. However, this effect remains untested in complex jumping skills crucial to numerous sports.

Purpose

This study aimed to investigate the effect of internally and externally directed process and outcome focus instructions on approach jump height and approach speed in novice participants.

Methods

Twelve individuals aged 18 to 22 participated across three sessions: Familiarization, Test Session 1, …

Empirically Assessing 510(K) Device Safety, George Horvath

Akron Law Faculty Publications

Innovations in medical device technology hold the potential to improve health outcomes across the populace. Nearly half of all medical devices that enter the U.S. market each year are regulated by the Food and Drug Administration (FDA) under the 510(k) pathway. If FDA regulation of 510(k) devices stifles innovation, health outcomes will suffer over time because beneficial devices would not reach patients; on the other hand, if regulation facilitates innovation, health outcomes could improve. Most discussions of innovation under the 510(k) pathway have been either excessively reductionist (such as claims that the pathway stifles innovation) or wholly pessimistic (notably, the …

The Patent Law Origins Of Science Fiction, Camilla Hrdy, Daniel H. Brean

Akron Law Faculty Publications

This Article reveals the surprising role of patent law in shaping the literary genre of science fiction. Drawing on previously unpublished sources, the Article shows that Hugo Gernsback—the so-called “father” of science fiction who started the first all-science-fiction magazine in 1926—believed that works of science fiction are analogous to patents. Like patents, science fiction stories can disclose useful information to the public about new inventions. Like patents, science fiction stories can influence future inventors and drive innovation. Gernsback went even further, positing that some of the inventions depicted in science fiction should themselves be patentable. In 1952, he urged Congress …

Dobbs And Democracy, Melissa Murray, Katherine A. Shaw

Articles

In Dobbs v. Jackson Women’s Health Organization, Justice Alito justified the decision to overrule Roe v. Wade and Planned Parenthood of Southeastern Pennsylvania v. Casey with an appeal to democracy. He insisted that it was “time to heed the Constitution and return the issue of abortion to the people’s elected representatives.” This invocation of democracy had undeniable rhetorical power: it allowed the Dobbs majority to lay waste to decades’ worth of precedent, while rebutting charges of judicial imperialism and purporting to restore the people’s voices. This Article interrogates Dobbs’s claim to vindicate principles of democracy, examining both the intellectual pedigree …

Situating The Modern Public Trust Doctrine In Trust Law: The Duty Of Loyalty And The Case For Bifurcated, De Novo Judicial Review, Edward A. Zelinsky

Articles

This article situates the modern public trust doctrine (PTD) in contemporary trust law. Grounding the PTD in trust law leads to two important corollaries. First, the PTD planted in trust law imposes upon government actors and agencies trust law’s fiduciary duty of loyalty. In the context of the PTD, that duty of loyalty runs to the public as the beneficiary of the PTD. Second, faced with plausible claims that this fiduciary duty of loyalty to the public has been violated, courts should apply trust law’s de novo standard of review to those administrative and legislative decisions alleged to impair public …

K-Perm: Personalized Response Generation Using Dynamic Knowledge Retrieval And Persona-Adaptive Queries, Kanak Raj, Kaushik Roy, Vamshi Bonagiri, Priyanshul Govil, Krishnaprasad Thirunarayan, Raxit Goswami, Manas Gaur

Publications

Personalizing conversational agents can enhance the quality of conversations and increase user engagement. However, they often lack external knowledge to tend to a user’s persona appropriately. This is particularly crucial for practical applications like mental health support, nutrition planning, culturally sensitive conversations, or reducing toxic behavior in conversational agents. To enhance the relevance and comprehensiveness of personalized responses, we propose using a two-step approach that involves (1) selectively integrating user personas and (2) contextualizing the response with supplementing information from a background knowledge source. We develop K-PERM (Knowledge-guided PErsonalization with Reward Modulation), a dynamic conversational agent that combines these elements. …

Causal Event Graph-Guided Language-Based Spatiotemporal Question Answering, Kaushik Roy, Alessandro Oltramari, Yuxin Zi, Chathurangi Shyalika, Vignesh Narayanan, Amit Sheth

Publications

Large Language Models have excelled at encoding and leveraging language patterns in large text-based corpora for various tasks, including spatiotemporal event-based question answering (QA). However, due to encoding a text-based projection of the world, they have also been shown to lack a fullbodied understanding of such events, e.g., a sense of intuitive physics, and cause-and-effect relationships among events. In this work, we propose using causal event graphs (CEGs) to enhance language understanding of spatiotemporal events in language models, using a novel approach that also provides proofs for the model’s capture of the CEGs. A CEG consists of events denoted by …

Tutorial: Knowledge-Infused Artificial Intelligence For Mental Healthcare, Kaushik Roy

Publications

Artificial Intelligence (AI) systems for mental healthcare (MHCare) have been ever-growing after realizing the importance of early interventions for patients with chronic mental health (MH) conditions. Social media (SocMedia) emerged as the go-to platform for supporting patients seeking MHCare. The creation of peer-support groups without social stigma has resulted in patients transitioning from clinical settings to SocMedia supported interactions for quick help. Researchers started exploring SocMedia content in search of cues that showcase correlation or causation between different MH conditions to design better interventional strategies. User-level Classification-based AI systems were designed to leverage diverse SocMedia data from various MH conditions, …

Ontolog Summit 2024 Talk Report: Healthcare Assistance Challenges-Driven Neurosymbolic Ai, Kaushik Roy

Publications

Although Artificial Intelligence technology has proven effective in providing healthcare assistance by analyzing health data, it still falls short in supporting decision-making. This deficiency largely stems from the predominance of opaque neural networks, particularly in mental health care AI applications, which raise concerns about their unpredictable and unverifiable nature. This skepticism hinders the transition from information support to decision support. This presentation will explore neurosymbolic approaches that combine neural networks with symbolic control and verification mechanisms. These approaches aim to unlock AI’s full potential by enhancing information analysis and decision-making support for healthcare assistance1.

Proknow: Process Knowledge For Safety Constrained And Explainable Question Generation For Mental Health Diagnostic Assistance In The Age Of Large Language Models, Kaushik Roy, Manas Gaur, Misagh Soltani, Vipula Rawte, Ashwin Allen, Amit P. Sheth

Publications

Current Virtual Mental Health Assistants (VMHAs) primarily offer counseling and suggestive care but do not assist with patient diagnosis due to their lack of training in safety-constrained and specialized clinical process knowledge, referred to as ProKnow. In this work, we define ProKnow as an ordered set of information aligned with evidence-based guidelines or categories of conceptual understanding used by domain experts. We also introduce a new dataset of diagnostic conversations guided by safety constraints and Pro- Know, known as ProKnow-data. We develop a method for natural language question generation (NLG) designed to interactively gather diagnostic information from patients, termed ProKnow-algo. …

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, …

Active Techniques Of Heat Transfer Enhancement: A Review, Duaa Mraiza, Foad Faraji

Babylonian Journal of Mechanical Engineering

In this work, active methods for improving heat transfer are discussed, with a particular emphasis on new ideas and their applicability in various sectors of different types. Heat transfer efficiency is essential for optimising energy utilisation in industries such as chemical processing, heating, ventilation, air conditioning (HVAC), and renewable energy. Mechanical assistance, surface vibrations, electrostatic fields, and fluid injection are some approaches investigated in this research. The study also investigates the ideas behind these techniques and their practical ramifications. The results of this study indicate that active approaches, even though they often call for more power, have the potential to …

Improving Growth Models Of Cultivated Sugar Kelp, Saccharina Latissima, By Accounting For Intraspecific Variation In Thermal Tolerance, Ruby Krasnow, Sara Gonzalez, Scott Lindell

Student Publications [Scholarly]

Dynamic models of sugar kelp (Saccharina latissima) growth are used to estimate the production potential of seaweed aquaculture in many regions around the world. These models do not currently account for the existence of S. latissima ecotypes that are adapted to regional environmental conditions, particularly temperature. We tested the hypothesis that recalibrating the temperature parameters of a dynamic energy budget model using literature data for S. latissima from regions with a similar climate to the region of interest would result in more accurate predictions than using a general species-wide temperature response curve. Calibrating the model using data from warm regions …

Enhancing Pitch Stability In Floating Wind Platforms: The Hydrodynamic Effects Of Thin Plates, Ignacio Pregnan Johannesen

School of Engineering, Computing and Mathematics Theses

The Floating Offshore Wind Turbines (FOWT) technology is still at an early stage looking for ways to make it competitive. In the case of semi-submersible FOWT the large structure has been pointed as an option to tackle the final energy price and therefore, smaller/cheaper platforms are desired. However, this would have implications on the platform hydrodynamic performance. This thesis discusses the use of thin disks as pitch motion suppression surfaces for FOWT platforms, employing three methodologies; potential flow, Computational Fluid Dynamics (CFD) and Experiments. With NEMOH a boundary element method code, the added mass and excitation forces/moments were calculated for …

Data Security And User Authentication In Public Cloud Computing Environments, Nelson Vasconcelos Soares Dos Santos

School of Engineering, Computing and Mathematics Theses

Cloud computing has become a prevalent paradigm for organisations and individuals, offering a range of services and resources that enable the efficient management, processing and storage of large quantities of data. However, despite its numerous advantages, cloud computing also presents significant challenges related to data security and user authentication. The distributed nature of cloud environments, coupled with the relinquishment of control over data to cloud service providers, has raised concerns regarding data vulnerability to various types of attacks, such as data breaches, malware injection, and denial of service. Moreover, traditional password and token-based authentication methods have been shown to be …

“A View Into The Ccu” – Investigating Visual Analysis And Machine Learning Approaches To Aid Clinicians In Critical Care Units, Christopher Haynes

School of Engineering, Computing and Mathematics Theses

Despite the vast quantities of data stored by critical care units, there is a resistance to applying this to technological innovation. This is limiting the potential to enable the best clinical decision making and increasing time pressures on clinical staff. This thesis examines the current state of data use in two critical care units at University Hospitals Plymouth. Through discussions with clinical staff, the main limitations of their current digital work environment are considered to develop a three-element system. A thorough literature review is then carried out into critical care practices, visualisation principles for multi-variate heterogeneous data, and supervised machine …

Gendered Violence And Sexualized Representations In Video Games: (Lack Of) Effect On Gender-Related Attitudes, Liam Cross, Linda K. Kaye, Juris Savostijanovs, Neil Mclatchie, Matthew Johnston, Liam Whiteman, Robyn Mooney, Gray Atherton

School of Psychology

This research explored how gender portrayals in video games affect gender-related attitudes. Two hundred participants from the United Kingdom and Malaysia participated across three experiments, where the appearance and behaviour of video game characters were manipulated with regard to target (enemy) gender (Study 1), sexually explicit attire (Study 2) and level of character agency (Study 3). We found minimal evidence that exposure to gender-stereotyped content resulted in differential gender-related attitudes (implicit associations, hostile and benevolent sexism, or rape myth acceptance). However, Study 1 findings showed that individuals who played a first-person shooter with male enemies showed lower endorsement of some …

Reward Count(S): Negative Recency In Probabilistic Experience-Based Learning, Andy Wills, René Schlegelmilch, Bettina Von Helversen

School of Psychology

Learning how to make decisions from experience is often studied using probabilistic outcome prediction or choice tasks, asin conditioning, reward learning, or risky gambles (e.g., response A provides reward in 75% of the cases, response B in25% over repeated trials with feedback). One debated phenomenon in such tasks is that of negative recency, describingthat learners expect the rare event after observing a streak ofcommon events (e.g., Gamblers fallacy). Here, we show thatthis behavior, despite instructing participants to use a visualstimulus, also occurs in probabilistic single-cue conditioningtraining, where participants predicted whether digging at a specific location on a plane (visual cue) …

Early-Phase Neuroplasticity Induced By Offline Transcranial Ultrasound Stimulation In Primates, Nadège Bault, Siti N. Yaakub, Elsa Fouragnan

School of Psychology

The use of ‘offline’ transcranial ultrasound stimulation (TUS) protocols is of particular interest in the rapidly growing field of low-intensity TUS. Offline TUS can modulate neural activity up to several hours after stimulation, suggesting the induction of early-phase neuroplasticity. Studies in both humans and nonhuman primates have shown spatially specific changes in both the neuromodulation target and in a distributed network of regions associated with it. These changes suggest that excitatory or inhibitory effects are a result of a complex interaction between the protocol used and the underlying brain region and state. Understanding how early-phase neuroplasticity is induced by offline …

Does Daily Activity Overlap Of Seven Mesocarnivores Vary Based On Human Development?, Leah E. Mctigue, Ellery V. Lassiter, Mike Shaw, Emily Johansson, Ken Wilson, Brett Degregorio

Biological Sciences Faculty Publications and Presentations

Many species of wildlife alter their daily activity patterns in response to co-occurring species as well as the surrounding environment. Often smaller or subordinate species alter their activity patterns to avoid being active at the same time as larger, dominant species to avoid agonistic interactions. Human development can complicate interspecies interactions, as not all wildlife respond to human activity in the same manner. While some species may change the timing of their activity to avoid being active when humans are, others may be unaffected or may benefit from being active at the same time as humans to reduce predation risk …

Entertaining And Embracing Professional Identity Development In The 1l Legal Writing Curriculum, Charles Oldfield

Akron Law Faculty Publications

Because of their already heavy workload, legal writing faculty sometimes resist taking on new curricular responsibilities, including calls to incorporate ethics and professionalism training in the first-year legal writing curriculum. But the ABA now requires law schools to provide students with opportunities to develop their professional identities throughout their time in law school. This requirement means that faculty will need to add professional identity development to their courses. Rather than resist this change, first-year legal writing faculty should embrace the opportunity by using the Model Rules of Professional Conduct to incorporate concepts of ethics and professionalism in their first-year courses. …

Legislative Redistricting And The Partisan Distribution Of Transportation Expenditure, Walter Melnik

Economics Faculty Research and Publications

I show that a state representative’s political party determines transportation expenditure in the area she represents. Previous studies of this topic consider party changes through election outcomes, which may be correlated with unobservable determinants of expenditure. To overcome this issue, I identify my estimates using Ohio’s 2012 state legislative redistricting, which moved many geographic areas into districts with opposite party incumbents. The Republican party controlled the state legislature and governorship over the period I study. I find that areas moving from governing party Republican to minority party Democratic districts received $3.4M (0.18 standard deviations) less annual highway construction funding than …

Flattening Breast Cancer By Removing The Breasts: Protecting A Woman's Right To Choose Reconstruction Of An Aesthetic Flat Chest After A Mastectomy, Amelia Landenberger

Akron Law Faculty Publications

Breast cancer takes away women’s choices. Many women decide to regain control of their bodies and prevent future cancer or follow-up surgeries by having a double mastectomy without any reconstruction, leaving a fat chest. When their doctors refuse to perform this surgery or their insurers refuse to cover this form of chest reconstruction, women are traumatized by their loss of choice in a system that clings to the outdated idea that women cannot be feminine without breasts. The Women’s Health and Cancer Rights Act of 1998 was intended to protect women facing cancer from the second trauma of being unable …

Reactive Hypotheticals In Legal Education: Leveraging Ai To Create Interactive Fact Patterns, Sean Steward

Akron Law Faculty Publications

Good legal hypotheticals require carefully constructed scenarios designed to mimic the challenges and dilemmas that students will face in their future legal careers. Hypotheticals help students take abstract concepts such as negligence or res ipsa loquitor and ground them in the reality that these rules were meant to control. Yet, despite our best efforts, creating hypotheticals with a rich tapestry of facts, personalities, and complexities that characterize real-world legal practice remains challenging and time-consuming. Artificial Intelligence (AI) can solve this problem. By leveraging emerging AI technology, legal educators can create richer, more realistic hypotheticals that react to students and keep …

Racial Bias, Accomplice Liability, And The Felony Murder Rule: A National Empirical Study, G. Ben Cohen, Justin D. Levinson, Koichi Hioki

Akron Law Faculty Publications

Two long criticized prosecutorial tools—the felony murder rule and the accomplice liability doctrine—play an outsized role in the operation of American homicide law. Though each of these tools have separately faced intense criticism for their resistance to the supposedly foundational principles of moral culpability and individual responsibility, their legacy is also defined by the way they function symbiotically and specifically to heighten racialized punishment. This Article addresses the weighty combined reach of the accomplice liability doctrine and felony murder rule, and proposes that racial bias has fueled the operation and survival of these tools. Specifically, it suggests that implicit racial …

Ai And The Regulation Of Tax Return Preparers, Linda Galler, Jay A. Soled

Hofstra Law Faculty Scholarship

Tax return preparers play a pivotal role for millions of taxpayers, and

their number ranges in the hundreds of thousands. Despite preparers'

importance in the tax return submission process and their numerical size,

they are largely unregulated. Because of this lack of oversight, a significant

number of tax returnp reparersp ut their ownfinanciali nterests and

those of their clients ahead of the government's financial interests.

In the past, there have been calls for increased regulatory

oversight to keep wayward practitioners' actions in check. Therefore,

a decade and a half ago, Congress, in conjunction with the Treasury

Department, mandated that every …