Computer Sciences Commons^™

Beyond Machine Learning: An Fmri Domain Adaptation Model For Multi-Study Integration, Lauryn Michelle Burleigh

LSU Doctoral Dissertations

Traditional machine learning analyses are challenging with functional magnetic
resonance imaging (fMRI) data, not only because of the amount of data that needs to be
collected, adding a particular challenge for human fMRI research, but also due to the change in
hypothesis being addressed with various analytical techniques. Domain adaptation is a type of
transfer learning, a step beyond machine learning which allows for multiple related, but not
identical, data to contribute to a model, can be beneficial to overcome the limitation of data
needed but may address different hypothesis questions than anticipated given the analysis
computation. This dissertation assesses …

Ten Years After Imagenet: A 360° Perspective On Artificial Intelligence, Sanjay Chawla, Preslav Nakov, Ahmed Ali, Wendy Hall, Issa Khalil, Xiaosong Ma, Husrev Taha Sencar, Ingmar Weber, Michael Wooldridge, Ting Yu

Natural Language Processing Faculty Publications

It is 10 years since neural networks made their spectacular comeback. Prompted by this anniversary, we take a holistic perspective on artificial intelligence (AI). Supervised learning for cognitive tasks is effectively solved - provided we have enough high-quality labelled data. However, deep neural network models are not easily interpretable, and thus the debate between blackbox and whitebox modelling has come to the fore. The rise of attention networks, self-supervised learning, generative modelling and graph neural networks has widened the application space of AI. Deep learning has also propelled the return of reinforcement learning as a core building block of autonomous …

Data Analysis Of Lossy Generative Data Compression For Robust Remote Deep Inference, Silvija Kokalj-Filipovic

College of Science & Mathematics Departmental Research

How does compression affect topological data features and can that be related to classification accuracy?

Conversion Of Fat To Cellular Fuel—Fatty Acids 𝛽-Oxidation Model, Sylwester M. Kloska, Krzysztof Pałczyński, Tomasz Marciniak, Tomasz Talaśka, Marissa Miller, Beata J. Wysocki, Paul Davis, Tadeusz A. Wysocki

School of Computing: Faculty Publications

𝛽-oxidation of fatty acids plays a significant role in the energy metabolism of the cell. This paper presents a 𝛽-oxidation model of fatty acids based on queueing theory. It uses Michaelis–Menten enzyme kinetics, and literature data on metabolites’ concentration and enzymatic constants. A genetic algorithm was used to optimize the parameters for the pathway reactions. The model enables real-time tracking of changes in the concentrations of metabolites with different carbon chain lengths. Another application of the presented model is to predict the changes caused by system disturbance, such as altered enzyme activity or abnormal fatty acid concentration. The model has …

Predicting Thermoelectric Power Factor Of Bismuth Telluride During Laser Powder Bed Fusion Additive Manufacturing, Ankita Agarwal, Tanvi Banerjee, Joy Gockel, Saniya Leblanc, Joe Walker, John Middendorf

Computer Science and Engineering Faculty Publications

An additive manufacturing (AM) process, like laser powder bed fusion, allows for the fabrication of objects by spreading and melting powder in layers until a freeform part shape is created. In order to improve the properties of the material involved in the AM process, it is important to predict the material characterization property as a function of the processing conditions. In thermoelectric materials, the power factor is a measure of how efficiently the material can convert heat to electricity. While earlier works have predicted the material characterization properties of different thermoelectric materials using various techniques, implementation of machine learning models …

From Laboratory To Field: Unsupervised Domain Adaptation For Plant Disease Recognition In The Wild, Xinlu Wu, Xijian Fan, Peng Luo, Sruti Das Choudhury, Tardi Tjahjadi, Chunhua Hu

School of Computing: Faculty Publications

Plant disease recognition is of vital importance to monitor plant development and predicting crop production. However, due to data degradation caused by different conditions of image acquisition, e.g., laboratory vs. field environment, machine learning-based recognition models generated within a specific dataset (source domain) tend to lose their validity when generalized to a novel dataset (target domain). To this end, domain adaptation methods can be leveraged for the recognition by learning invariant representations across domains. In this paper, we aim at addressing the issues of domain shift existing in plant disease recognition and propose a novel unsupervised domain adaptation method via …

Neutrosophic Mcdm Methodology For Assessment Risks Of Cyber Security In Power Management, Ahmed M. Abdelmouty, Ahmed Abdel-Monem

Neutrosophic Systems with Applications

Every day, new reports of cyberattacks on interconnected control systems emerge. The vulnerability of their communication mechanism makes similar control systems a target for malicious outsiders. Protecting sensitive data and maintaining network reliability and availability are two of the main reasons why network security is so important. Strong and dependable network security strategies use a number of safeguards to protect users and businesses from malware and cyber assaults like distributed denial of service. A safety analysis is an essential step that must precede the introduction of any security measures. There hasn't been much experience with cyberattacks on power control systems …

Core-Periphery Principle Guided Redesign Of Self-Attention In Transformers, Xiaowei Yu, Lu Zhang, Haixing Dai, Yanjun Lyu, Lin Zhao, Zihao Wu, David Liu, Tianming Liu, Daijiang Zhu

Computer Science Faculty Research & Creative Works

Designing more efficient, reliable, and explainable neural network architectures is critical to studies that are based on artificial intelligence (AI) techniques. Numerous efforts have been devoted to exploring the best structures, or structural signatures, of well-performing artificial neural networks (ANN). Previous studies, by post-hoc analysis, have found that the best-performing ANNs surprisingly resemble biological neural networks (BNN), which indicates that ANNs and BNNs may share some common principles to achieve optimal performance in either machine learning or cognitive/behavior tasks. Inspired by this phenomenon, rather than relying on post-hoc schemes, we proactively instill organizational principles of BNNs to guide the redesign …

Neutrosophic Mcdm Methodology For Assessment Risks Of Cyber Security In Power Management, Ahmed M. Abdelmouty, Ahmed Abdel-Monem

Neutrosophic Systems with Applications

Every day, new reports of cyberattacks on interconnected control systems emerge. The vulnerability of their communication mechanism makes similar control systems a target for malicious outsiders. Protecting sensitive data and maintaining network reliability and availability are two of the main reasons why network security is so important. Strong and dependable network security strategies use a number of safeguards to protect users and businesses from malware and cyber assaults like distributed denial of service. A safety analysis is an essential step that must precede the introduction of any security measures. There hasn't been much experience with cyberattacks on power control systems …

Cardiac Arrhythmia Disease Classifier Model Based On A Fuzzy Fusion Approach, Fatma Taher, Hamoud Alshammari, Lobna Osman, Mohamed Elhoseny, Abdulaziz Shehab, Eman Elayat

All Works

Cardiac diseases are one of the greatest global health challenges. Due to the high annual mortality rates, cardiac diseases have attracted the attention of numerous researchers in recent years. This article proposes a hybrid fuzzy fusion classification model for cardiac arrhythmia diseases. The fusion model is utilized to optimally select the highest-ranked features generated by a variety of well-known feature-selection algorithms. An ensemble of classifiers is then applied to the fusion’s results. The proposed model classifies the arrhythmia dataset from the University of California, Irvine into normal/abnormal classes as well as 16 classes of arrhythmia. Initially, at the preprocessing steps, …

Object-Oriented Creative Coding For Digital Art Students, Dale E. Parson

Computer Science and Information Technology Faculty

An introductory course in creative graphical coding for both computer science and digital art majors need not be watered down. The availability of an excellent Java-based framework including an IDE, debugger, and high-level class and function library avoids potentially problematic mathematics and device-control demands by encapsulating them within the library. Students can add or modify a few lines of code and then run them from the IDE without explicit compilation steps or tool changes, immediately seeing the results of initial coding or bug fixes in the form of animated graphical objects. Incremental introduction of object-oriented mechanisms within the course such …

Attenuated Skeletal Muscle Metabolism Explains Blunted Reactive Hyperemia After Prolonged Sitting, Cody Anderson, Elizabeth Pekas, Michael Allen, Song-Young Park

UNO Student Research and Creative Activity Fair

Introduction: Although reduced post-occlusive reactive hyperemia (PORH) after prolonged sitting (PS) has been reported as impaired microvascular function, no specific mechanism(s) have been elucidated. One potential mechanism, independent of microvascular function, is that an altered muscle metabolic rate (MMR) may change the magnitude of PORH by modifying the oxygen deficit achieved during cuff-induced arterial occlusions. We speculated that if MMR changes during PS, this may invalidate current inferences about microvascular function during PS. Objective: Therefore, the objective of this study was to examine if peripheral leg MMR changes during PS and to ascertain whether the change in the oxygen deficit …

Healthcare Facilities: Maintaining Accessibility While Implementing Security, Ryan Vilter

UNO Student Research and Creative Activity Fair

In the wake of the Tulsa, Oklahoma hospital shooting in the summer of 2022, it was made clear that more security needed to be implemented in healthcare facilities. As a result, I inquired: What is the happy balance for healthcare facilities to maintain their accessibility to the public while also implementing security measures to prevent terrorist attacks? With that base, I give recommendations in the areas of cybersecurity, physical infrastructure, and physical and mental health, based off the existing literature and data gathered from terrorist attacks against hospitals over several decades.

The Effects Of Demographics And Risk Factors On The Morphological Characteristics Of Human Femoropopliteal Arteries, Sayed Ahmadreza Razian, Majid Jadidi, Alexey Kamenskiy

UNO Student Research and Creative Activity Fair

Background: Disease of the lower extremity arteries (Peripheral Arterial Disease, PAD) is associated with high morbidity and mortality. During disease development, the arteries adapt by changing their diameter, wall thickness, and residual deformations, but the effects of demographics and risk factors on this process are not clear.

Methods: Superficial femoral arteries from 736 subjects (505 male, 231 female, 12 to 99 years old, average age 51±17.8 years) and the associated demographic and risk factor variables were used to construct machine learning (ML) regression models that predicted morphological characteristics (diameter, wall thickness, and longitudinal opening angle resulting from the …

Time Evolution Is A Source Of Bias In The Wolf Algorithm For Largest Lyapunov Exponents, Kolby Brink, Tyler Wiles, Nicholas Stergiou, Aaron Likens

UNO Student Research and Creative Activity Fair

Human movement is inherently variable by nature. One of the most common analytical tools for assessing movement variability is the largest Lyapunov exponent (LyE) which quantifies the rate of trajectory divergence or convergence in an n-dimensional state space. One popular method for assessing LyE is the Wolf algorithm. Many studies have investigated how Wolf’s calculation of the LyE changes due to sampling frequency, filtering, data normalization, and stride normalization. However, a surprisingly understudied parameter needed for LyE computation is evolution time. The purpose of this study is to investigate how the LyE changes as a function of evolution time …

Toward A Simulation Model Complexity Measure, J. Scott Thompson, Douglas D. Hodson, Michael R. Grimaila, Nicholas Hanlon, Richard Dill

Faculty Publications

Is it possible to develop a meaningful measure for the complexity of a simulation model? Algorithmic information theory provides concepts that have been applied in other areas of research for the practical measurement of object complexity. This article offers an overview of the complexity from a variety of perspectives and provides a body of knowledge with respect to the complexity of simulation models. The key terms model detail, resolution, and scope are defined. An important concept from algorithmic information theory, Kolmogorov complexity, and an application of this concept, normalized compression distance, are used to indicate the possibility of measuring changes …

Fraud Pattern Detection For Nft Markets, Andrew Leppla, Jorge Olmos, Jaideep Lamba

SMU Data Science Review

Non-Fungible Tokens (NFTs) enable ownership and transfer of digital assets using blockchain technology. As a relatively new financial asset class, NFTs lack robust oversight and regulations. These conditions create an environment that is susceptible to fraudulent activity and market manipulation schemes. This study examines the buyer-seller network transactional data from some of the most popular NFT marketplaces (e.g., AtomicHub, OpenSea) to identify and predict fraudulent activity. To accomplish this goal multiple features such as price, volume, and network metrics were extracted from NFT transactional data. These were fed into a Multiple-Scale Convolutional Neural Network that predicts suspected fraudulent activity based …

Self-Learning Algorithms For Intrusion Detection And Prevention Systems (Idps), Juan E. Nunez, Roger W. Tchegui Donfack, Rohit Rohit, Hayley Horn

SMU Data Science Review

Today, there is an increased risk to data privacy and information security due to cyberattacks that compromise data reliability and accessibility. New machine learning models are needed to detect and prevent these cyberattacks. One application of these models is cybersecurity threat detection and prevention systems that can create a baseline of a network's traffic patterns to detect anomalies without needing pre-labeled data; thus, enabling the identification of abnormal network events as threats. This research explored algorithms that can help automate anomaly detection on an enterprise network using Canadian Institute for Cybersecurity data. This study demonstrates that Neural Networks with Bayesian …

Neutrosophic Model To Examine The Challenges Faced By Manufacturing Businesses In Adopting Green Supply Chain Practices And To Provide Potential Solutions, Zenat Mohamed, Mahmoud M. Ismail, Amal F. Abd El-Gawad

Neutrosophic Systems with Applications

Several obstacles stand in the way of companies trying to adopt green supply-chain practices. The purpose of this research is to examine the challenges faced by the industrial industry in adopting green supply chain practices and to provide potential solutions. The information for this research was gathered via in-depth, personal conversations with manufacturing sector managers who are well-versed in green supply chain practices. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) technique was used in the evaluation phase to evaluate obstacles and assess efficient options for introducing green supply chain practices. The TOPSIS method is integrated …

Review Of The Myth Of Artificial Intelligence: Why Computers Can’T Think The Way We Do, By Erik J. Larson, Noreen L. Herzfeld

Reuter Professorship of Science and Religion Publications

No abstract provided.

Obstacle Avoidance And Simulation Of Carrier-Based Aircraft On The Deck Of Aircraft Carrier, Junxiao Xue, Xiangyan Kong, Bowei Dong, Hao Tao, Haiyang Guan, Lei Shi, Mingliang Xu

Journal of System Simulation

Abstract: A predictive depth deterministic policy gradient (PDDPG) algorithm is proposed by combining the least squares method with deep deterministic policy gradient(DDPG) for the problems of strong randomness, poor real-time performance, and slow planning speed by obstacle avoidance on aircraft carrier deck. The short-term trajectory of dynamic obstacles on the deck is predicted by the least square method. DDPG is used to provide agents with the ability to learn and make decisions in continuous space by the short-term trajectory of dynamic obstacles. The reward function is set based on the artificial potential field to improve the convergence speed and accuracy …

Floor Evacuation Simulation Based On Bim And Mr, Zhijie Li, Shuangyu Ma, Changhua Li, Xiao Liang, Jie Zhang

Journal of System Simulation

Abstract: Facing with the problem that the floor evacuation simulation only annotates the floor plan route, which is relatively single and not intuitive, a 3D building evacuation simulation method integrating mixed reality and building information model is proposed. The BIM components are reasonably planned and segmented, and reasonable annotation is performed. The BIM information is routed through the surface area heuristic optimization algorithm based on the bounding volume hierarchy. The evacuation simulation process is imported into the Microsoft Hololens2 hardware platform using the Unity3D development engine. The experimental results show that, compared with the previous evacuation simulation expressed only …

Multiagent Following Multileader Algorithm Based On K-Means Clustering, Guodong Yuan, Ming He, Ziyu Ma, Weishi Zhang, Xueda Liu, Wei Li

Journal of System Simulation

Abstract: Three K-means clustering algorithms are proposed to prevent chaos in the formation of a multi-agent system (MAS) with multiple leaders. The algorithm divides the cluster into communities with the same number of leaders, and the agents within the community will follow the same leader. Among the three proposed algorithms, algorithm #1 is suitable for scenarios with widely distributed agents wherein rapid consensus can be achieved in the shortest time; algorithm #2 is suitable for scenarios with a sparse agent distribution and effectively prevented agent collisions; and algorithm #3 exhibits rapid convergence and considerably reduces the MAS control cost, …

Costume Pattern Sketch Colorization And Style Transfer Based On Neural Network, Xingquan Cai, Zhijun Li, Mengyao Xi, Haiyan Sun

Journal of System Simulation

Abstract: Aiming at the problems of color overflow in pattern sketch colorization and lack of fabric texture features in style transfer, this paper proposes a method of costume pattern sketch colorization and style transfer based on neural network. This paper initializes the data set, collects the costume pattern image, extracts the costume pattern sketch, synthesizes the costume pattern sketch with color features and constructs the style data set. The research builds the conditional generative adversarial nets and achieves the costume pattern sketch with color features colorization based on the generator. The study constructs a convolutional neural network model, uses the …

A Comprehensive Review On Deep Learning-Based Generative Linguistic Steganography, Dr Khaled Nagaty, Israa Lotfy Lotfy, Abeer Hamdy Dr.

Computer Science

. The recent development of deep learning has made a significant breakthrough in linguistic generative steganography. The text has become one of the most intensely used communication carriers on the Internet, making steganography an efficient carrier for concealing secret messages. Text steganography has long been used to protect the privacy and confidentiality of data via public transmission. Steganography utilizes a carrier to embed the data to generate a secret unnoticed and less attractive message. Different techniques have been used to improve the security of the generated text and quality of the steganographic text, such as the Markov model, Recurrent Neural …

Hyper-Heuristic Three Dimensional Eda For Solving Green Two-Sided Assembly Line Balancing Problem, Rong Hu, Shuai Ding, Bin Qian, Changsheng Zhang

Journal of System Simulation

Abstract: This paper establishes a model for green robotic two-sided assembly line balancing problem of type-I, and a hyper-heuristic three dimensional estimation of distribution algorithm (HH3DEDA) is proposed for solving this problem. In HH3DEDA, a combinatorial encoding rule based on process selectors is designed via considering the characteristics of the problem. Then, HH3DEDA with a high and low layered structure is proposed. In the upper layer, the three-dimensional probability matrix is utilized to learn high-quality high individual block structure and its distribution information, and then the matrix is sampled to generate new high level individuals. Each high individual is …

Research On Modeling And Solution Method Of Operational Tasks Optimization, Yue Ma, Lin Wu, Yun Liu, Guangzhao Ding

Journal of System Simulation

Abstract: Aiming at the problem of tasks optimization in operation task planning, this paper defines an operational tasks graph based on property graph and influence network to describe tasks, effects and their relationship. The model of operational tasks optimization is constructed based on the operational tasks graph, and the effect network transmission algorithm and resource constraint judgment algorithm are proposed. The problem is solved by the improved differential evolution algorithm. The experimental result shows that the operational tasks graph can vividly describe the relationship between operational tasks and effects, and the model and solution method are feasible and effective.

Multi-Objective Optimization Algorithm Based On Multi-Index Elite Individual Game Mechanism, Xu Wang, Weidong Ji, Guohui Zhou, Jiahui Yang

Journal of System Simulation

Abstract: In order to improve the convergence of multi-objective optimization algorithm and the diversity of optimization solution set, and alleviate the flown down of population in target space, a multi-objective optimization algorithm based on multi-attribute elite individual game mechanism is proposed. This paper uses Pareto dominance relationship and multi-index to comprehensively screen elite individuals. The elite individual game mechanism with K-means clustering is integrated with cross and mutation strategy, which effectively improves the convergence and diversity of the algorithm. A detailed convergence analysis of the algorithm is performed to prove the convergence of the algorithm. Eight representative comparison algorithms are …

Research On Decision Behavior Modeling Method Of Key Figures, Xiao Zheng, Xiaodong Peng, Minyu Lu, Tiejun Liu

Journal of System Simulation

Abstract: The decision-making of key figures is an important factor affecting the evolution of concerned events. The research on their decision-making behavior is of great significance for the prediction of important events. For the problem of decision behavior modeling and decision propensity prediction of key figures, the character attribute and measurement methods required for character modeling are analyzed, the character decision-making process and decision-making related influencing factors are analyzed, the exploration research of decision propensity prediction method is carried out, and the prediction model of decision propensity based on comprehensive interest characteristics and psychological characteristics is constructed. Through the research …

Flexible Job-Shop Scheduling Problem Based On Improved Wolf Pack Algorithm, Chaoyang Zhang, Liping Xu, Jian Li, Yihao Zhao, Kui He

Journal of System Simulation

Abstract: An improved wolf pack algorithm is proposed for solving multi-objective scheduling optimization for flexible job shop problems. A multi-objective flexible job shop scheduling model is developed with the maximum completion time of the workpiece and the energy consumption of the machine as the optimization goals. An improved wolf pack algorithm is proposed for solving the shortcomings that traditional wolf pack algorithm is easy to fall into the local optimization. Through improving the intelligent behavior of the wolf pack algorithm, individual codes are designed from the two levels of job's process and machine, and POX(precedence operation crossover) cross operation is …