Computer Sciences Commons^™

Reinforcement Learning: Low Discrepancy Action Selection For Continuous States And Actions, Jedidiah Lindborg

College of Graduate Studies: Theses & Dissertations

In reinforcement learning the process of selecting an action during the exploration or exploitation stage is difficult to optimize. The purpose of this thesis is to create an action selection process for an agent by employing a low discrepancy action selection (LDAS) method. This should allow the agent to quickly determine the utility of its actions by prioritizing actions that are dissimilar to ones that it has already picked. In this way the learning process should be faster for the agent and result in more optimal policies.

Exo-Sir: An Epidemiological Model To Analyze The Impact Of Exogenous Spread Of Infection, Nirmal Kumar Sivaraman, Manas Gaur, Shivansh Baijal, Sakthi Balan Muthiah, Amit Sheth

Publications

Epidemics like Covid-19 and Ebola have impacted people's lives significantly. The impact of mobility of people across the countries or states in the spread of epidemics has been significant. The spread of disease due to factors local to the population under consideration is termed the endogenous spread. The spread due to external factors like migration, mobility, etc. is called the exogenous spread. In this paper, we introduce the Exo-SIR model, an extension of the popular SIR model and a few variants of the model. The novelty in our model is that it captures both the exogenous and endogenous spread of …

Extensive Thiol Profiling For Assessment Of Intracellular Redox Status In Cultured Cells By Hplc-Ms/Ms, Jiandong Wu, Anna Chernatynskaya, Annalise Pfaff, Huari Kou, Nan Cen, Nuran Ercal, Honglan Shi

Computer Science Faculty Research & Creative Works

Oxidative stress may contribute to the pathology of many diseases, and endogenous thiols, especially glutathione (GSH) and its metabolites, play essential roles in the maintenance of normal redox status. Understanding how these metabolites change in response to oxidative insult can provide key insights into potential methods of prevention and treatment. Most existing methodologies focus only on the GSH/GSH disulfide (GSSG) redox couple, but GSH regulation is highly complex and depends on several pathways with multiple redox-active sulfur-containing species. In order to more fully characterize thiol redox status in response to oxidative insult, a high-performance liquid chromatography with tandem mass spectrometry …

Brain Image Fusion Approach Based On Side Window Filtering, Ahmad Al Smadi, Ahed Abugabah, Atif Mehmood, Shuyuan Yang

All Works

Brain medical image fusion plays an important role in framing a contemporary image to enhance the reciprocal and repetitive information for diagnosis purposes. A novel approach using kernel-based image filtering on brain images is presented. Firstly, the Bilateral filter is used to generate a high-frequency component of a source image. Secondly, an intensity component is estimated for the first image. Thirdly, side window filtering is employed on several filters, including the guided filter, gradient guided filter, and weighted guided filter. Thereby minimizing the difference between the intensity component of the first image and the low pass filter of the second …

Multi-Party Contract Management For Microservices, Zakaria Maamar, Noura Faci, Joyce El Haddad, Fadwa Yahya, Mohammad Askar

All Works

This paper discusses the necessary steps and means for ensuring the successful deployment and execution of software components referred to as microservices on top of platforms referred to as Internet of Things (IoT) devices, clouds, and edges. These steps and means are packaged into formal documents known in the literature as contracts. Because of the multi-dimensional nature of deploying and executing microservices, contracts are specialized into discovery, deployment, and collaboration types, capturing each specific aspect of the completion of these contracts. This completion is associated with a set of Quality-of-Service (QoS) parameters that are monitored allowing to identify potential deviations …

Autonomous Driving And Connected Mobility Modeling: Smart Dynamic Traffic Monitoring And Enforcement System For Connected And Autonomous Mobility, Dimitrios Zavantis, Fatma Outay, Youssef El-Hansali, Ansar Yasar, Elhadi Shakshuki, Haroon Malik

All Works

In recent years, autonomous vehicles (AVs), connected vehicles (CVs) and all relative technology have been in the spotlight, being intensively researched and developed. There is high anticipation on the benefits of automation and the overall reform it will bring to the transport sector, with some optimistic estimates considering it as a reality within the next few years. Evidently, AVs and CVs are attracting considerable attention and are developed very rapidly, cultivating great expectations for traffic safety improvements. While their potential is enormous and undeniable, benefits are not automatically guaranteed as there are parameters that currently appear unforeseen. This paper investigates …

A Two-Tier Framework Based On Googlenet And Yolov3 Models For Tumor Detection In Mri, Farman Ali, Sadia Khan, Arbab Waseem Abbas, Babar Shah, Tariq Hussain, Dongho Song, Shaker Ei-Sappagh, Jaiteg Singh

All Works

Medical Image Analysis (MIA) is one of the active research areas in computer vision, where brain tumor detection is the most investigated domain among researchers due to its deadly nature. Brain tumor detection in magnetic resonance imaging (MRI) assists radiologists for better analysis about the exact size and location of the tumor. However, the existing systems may not efficiently classify the human brain tumors with significantly higher accuracies. In addition, smart and easily implementable approaches are unavailable in 2D and 3D medical images, which is the main problem in detecting the tumor. In this paper, we investigate various deep learning …

Leveraging Natural Language Processing To Analyse The Temporal Behavior Of Extremists On Social Media, May El Barachi, Sujith Samuel Mathew, Farhad Oroumchian, Imene Ajala, Saad Lutfi, Rand Yasin

All Works

Aiming at achieving sustainability and quality of life for citizens, future smart cities adopt a data-centric approach to decision making in which assets, people, and events are constantly monitored to inform decisions. Public opinion monitoring is of particular importance to governments and intelligence agencies, who seek to monitor extreme views and attempts of radicalizing individuals in society. While social media platforms provide increased visibility and a platform to express public views freely, such platforms can also be used to manipulate public opinion, spread hate speech, and radicalize others. Natural language processing and data mining techniques have gained popularity for the …

Part I - Ai And Data As Medical Devices, W. Nicholson Price Ii

Other Publications

It may seem counterintuitive to open a book on medical devices with chapters on software and data, but these are the frontiers of new medical device regulation and law. Physical devices are still crucial to medicine, but they – and medical practice as a whole – are embedded in and permeated by networks of software and caches of data. Those software systems are often mindbogglingly complex and largely inscrutable, involving artificial intelligence and machine learning. Ensuring that such software works effectively and safely remains a substantial challenge for regulators and policymakers. Each of the three chapters in this part examines …

Online Deep Learning From Doubly-Streaming Data, Heng Lian, John S. Atwood, Bo-Jian Hou, Jian Wu, Yi He

Computer Science Faculty Publications

This paper investigates a new online learning problem with doubly-streaming data, where the data streams are described by feature spaces that constantly evolve, with new features emerging and old features fading away. A plausible idea to deal with such data streams is to establish a relationship between the old and new feature spaces, so that an online learner can leverage the knowledge learned from the old features to better the learning performance on the new features. Unfortunately, this idea does not scale up to high-dimensional multimedia data with complex feature interplay, which suffers a tradeoff between onlineness, which biases shallow …

Secure Multi-Robot Adaptive Information Sampling With Continuous, Periodic And Opportunistic Connectivity, Tamim Khatib

UNF Graduate Theses and Dissertations

Multi-robot teams are an increasingly popular approach for information gathering in large geographic areas, with applications in precision agriculture, natural disaster aftermath surveying, and pollution tracking. In a coordinated multi-robot information sampling scenario, robots share their collected information amongst one another to form better predictions. These robot teams are often assembled from untrusted devices, making the verification of the integrity of the collected samples an important challenge. Furthermore, such robots often operate under conditions of continuous, periodic, or opportunistic connectivity and are limited in their energy budget and computational power. In this thesis, we study how to secure the information …

Microsoft Defender Will Be Defended: Memoryranger Prevents Blinding Windows Av, Denis Pogonin, Igor Korkin, Phd

Annual ADFSL Conference on Digital Forensics, Security and Law

Windows OS is facing a huge rise in kernel attacks. An overview of popular techniques that result in loading kernel drivers will be presented. One of the key targets of modern threats is disabling and blinding Microsoft Defender, a default Windows AV. The analysis of recent driver-based attacks will be given, the challenge is to block them. The survey of user- and kernel-level attacks on Microsoft Defender will be given. One of the recently published attackers’ techniques abuses Mandatory Integrity Control (MIC) and Security Reference Monitor (SRM) by modifying Integrity Level and Debug Privileges for the Microsoft Defender via syscalls. …

Privacy Concerns With Using Public Data For Suicide Risk Prediction Algorithms: A Public Opinion Survey Of Contextual Appropriateness, Michael Zimmer, Sarah Logan

Computer Science Faculty Research and Publications

Purpose

Existing algorithms for predicting suicide risk rely solely on data from electronic health records, but such models could be improved through the incorporation of publicly available socioeconomic data – such as financial, legal, life event and sociodemographic data. The purpose of this study is to understand the complex ethical and privacy implications of incorporating sociodemographic data within the health context. This paper presents results from a survey exploring what the general public’s knowledge and concerns are about such publicly available data and the appropriateness of using it in suicide risk prediction algorithms.

Design/methodology/approach

A survey was developed to measure …

Jparsec - A Parser Combinator For Javascript, Sida Zhong

Master's Projects

Parser combinators have been a popular parsing approach in recent years. Compared with traditional parsers, a parser combinator has both readability and maintenance advantages.

This project aims to construct a lightweight parser construct library for Javascript called Jparsec. Based on the modular nature of a parser combinator, the implementation uses higher-order functions. JavaScript provides a friendly and simple way to use higher-order functions, so the main construction method of this project will use JavaScript's lambda functions. In practical applications, a parser combinator is mainly used as a tool, such as parsing JSON files.

In order to verify the utility of …

Harnessing The Power Of Interdisciplinary Research With Psychology-Informed Cyberbullying Detection Models, Deborah Hall, Yasin N. Silva, Brittany Wheeler, Lu Cheng, Katie Baumel

Computer Science: Faculty Publications and Other Works

Cyberbullying has become increasingly prevalent, particularly on social media. There has also been a steady rise in cyberbullying research across a range of disciplines. Much of the empirical work from computer science has focused on developing machine learning models for cyberbullying detection. Whereas machine learning cyberbullying detection models can be improved by drawing on psychological theories and perspectives, there is also tremendous potential for machine learning models to contribute to a better understanding of psychological aspects of cyberbullying. In this paper, we discuss how machine learning models can yield novel insights about the nature and defining characteristics of cyberbullying and …

Bias Mitigation For Toxicity Detection Via Sequential Decisions, Lu Cheng, Ahmadreza Mosallanezhad, Yasin N. Silva, Deborah Hall, Huan Liu

Computer Science: Faculty Publications and Other Works

Increased social media use has contributed to the greater prevalence of abusive, rude, and offensive textual comments. Machine learning models have been developed to detect toxic comments online, yet these models tend to show biases against users with marginalized or minority identities (e.g., females and African Americans). Established research in debiasing toxicity classifiers often (1) takes a static or batch approach, assuming that all information is available and then making a one-time decision; and (2) uses a generic strategy to mitigate different biases (e.g., gender and racial biases) that assumes the biases are independent of one another. However, in real …

Dbsnap 2: New Features To Construct Database Queries By Snapping Blocks, Yasin N. Silva, Alexis Loza, Humberto Razente

Computer Science: Faculty Publications and Other Works

Block-based environments for creating computer programs have become very useful learning tools in computer science as they enable focusing on the logic of a program rather than on its syntactical details. While most block-based environments support conventional (imperative) instructions, a few tools have been proposed to create database queries. One of these tools is DBSnap, a highly dynamic and open-source tool to create database query trees by dragging and connecting visual blocks representing datasets and database operators. In this paper, we introduce DBSnap 2, an extension of DBSnap that provides a set of improvements to facilitate the creation of simple …

Smart Application For Every Car (Saec). (Ar Mobile Application), Murad Al-Rajab, Samia Loucif, Ossama Kousi, Mohamad Bassem Irani

All Works

Technology is continuously evolving at an exponential rate. Fast technological advances are being made, especially in the field of smart phones, that facilitate the conduct of our daily activities in many areas such as driving. The ever-increasing number of vehicles on roads increases the likelihood of traffic accidents, resulting in higher number of deaths and serious injuries to drivers, passengers, and pedestrians. Among the main causes of road accidents are over speeding, unsafe lane jumping, and failure to keep a safe distance between vehicles, to name a few. In an attempt to contribute to the improvement of road traffic safety, …

Secure Storage Model For Digital Forensic Readiness, Avinash Singh, Richard Adeyemi Ikuesan, Hein Venter

All Works

Securing digital evidence is a key factor that contributes to evidence admissibility during digital forensic investigations, particularly in establishing the chain of custody of digital evidence. However, not enough is done to ensure that the environment and access to the evidence are secure. Attackers can go to extreme lengths to cover up their tracks, which is a serious concern to digital forensics – particularly digital forensic readiness. If an attacker gains access to the location where evidence is stored, they could easily alter the evidence (if not remove it altogether). Even though integrity checks can be performed to ensure that …

Crowdsensing Application On Coalition Game Using Gps And Iot Parking In Smart Cities, Hasan Abu Hilal, Narmeen Abu Hilal, Ala’ Abu Hilal, Tariq Abu Hilal

All Works

This paper provides an overview of crowdsensing and some of its applications. Crowdsensing is a part of the collecting data situations also; it’s built on a data system on multiple customer interactions. Moreover, writing the general information of the smart cities can be used to boost to received number frequency to send messages. This work mentioned the Crowdsensing layers that describe Mobile crowdsensing. The article focuses on crowdsensing layers, developed an application in Coalition Game using crowdsensing in terms of GPS. In addition, this paper discussed the Mobile crowdsensing system and how important the cloud is in serving the wireless …

On The Use Of Allen’S Interval Algebra In The Coordination Of Resource Consumption By Transactional Business Processes, Zakaria Maamar, Fadwa Yahya, Lassaad Ben Ammar

All Works

This paper presents an approach to coordinate the consumption of resources by transactional business processes. Resources are associated with consumption properties known as unlimited, limited, limited-but-extensible, shareable, and non-shareable restricting their availabilities at consumption-time. And, processes are associated with transactional properties known as pivot, retriable, and compensatable restricting their execution outcomes in term of either success or failure. To consider the intrinsic characteristics of both consumption properties and transactional properties when coordinating resource consumption by processes, the approach adopts Allen’s interval algebra through different time-interval relations like before, overlaps, and during to set up the coordination, which should lead to …

On Modelling And Analyzing Composite Resources’ Consumption Cycles Using Time Petri-Nets, Amel Benna, Fatma Masmoudi, Mohamed Sellami, Zakaria Maamar, Rachid Hadjidj

All Works

ICT community cornerstones (IoT in particular) gain competitive advantage from using physical resources. This paper adopts Time Petri-Nets (TPNs) to model and analyze the consumption cycles of composite resources. These resources consist of primitive, and even other composite, resources that are associated with consumption properties and could be subject to disruptions. These properties are specialized into unlimited, shareable, limited, limited-but-renewable, and non-shareable, and could impact the availability of resources. This impact becomes a concern when disruptions suspend ongoing consumption cycles to make room for the unplanned consumptions. Resuming the suspended consumption cycles depends on the resources’ consumption properties. To ensure …

Improved Reptile Search Optimization Algorithm Using Chaotic Map And Simulated Annealing For Feature Selection In Medical Filed, Zenab Elgamal, Aznul Qalid Md Sabri, Mohammad Tubishat, Dina Tbaishat, Sharif Naser Makhadmeh, Osama Ahmad Alomari

All Works

The increased volume of medical datasets has produced high dimensional features, negatively affecting machine learning (ML) classifiers. In ML, the feature selection process is fundamental for selecting the most relevant features and reducing redundant and irrelevant ones. The optimization algorithms demonstrate its capability to solve feature selection problems. Reptile Search Algorithm (RSA) is a new nature-inspired optimization algorithm that stimulates Crocodiles’ encircling and hunting behavior. The unique search of the RSA algorithm obtains promising results compared to other optimization algorithms. However, when applied to high-dimensional feature selection problems, RSA suffers from population diversity and local optima limitations. An improved metaheuristic …

A Brief Comparison Of K-Means And Agglomerative Hierarchical Clustering Algorithms On Small Datasets, Hassan I. Abdalla

All Works

In this work, the agglomerative hierarchical clustering and K-means clustering algorithms are implemented on small datasets. Considering that the selection of the similarity measure is a vital factor in data clustering, two measures are used in this study - cosine similarity measure and Euclidean distance - along with two evaluation metrics - entropy and purity - to assess the clustering quality. The datasets used in this work are taken from UCI machine learning depository. The experimental results indicate that k-means clustering outperformed hierarchical clustering in terms of entropy and purity using cosine similarity measure. However, hierarchical clustering outperformed k-means clustering …

Interacting With Educational Chatbots: A Systematic Review, Mohammad Amin Kuhail, Nazik Alturki, Salwa Alramlawi, Kholood Alhejori

All Works

Chatbots hold the promise of revolutionizing education by engaging learners, personalizing learning activities, supporting educators, and developing deep insight into learners’ behavior. However, there is a lack of studies that analyze the recent evidence-based chatbot-learner interaction design techniques applied in education. This study presents a systematic review of 36 papers to understand, compare, and reflect on recent attempts to utilize chatbots in education using seven dimensions: educational field, platform, design principles, the role of chatbots, interaction styles, evidence, and limitations. The results show that the chatbots were mainly designed on a web platform to teach computer science, language, general education, …

Analysis Of Blockchain Solutions For E-Voting: A Systematic Literature Review, Ali Benabdallah, Antoine Audras, Louis Coudert, Nour El Madhoun, Mohamad Badra

All Works

To this day, abstention rates continue to rise, largely due to the need to travel to vote. This is why remote e-voting will increase the turnout by allowing everyone to vote without the need to travel. It will also minimize the risks and obtain results in a faster way compared to a traditional vote with paper ballots. In fact, given the high stakes of an election, a remote e-voting solution must meet the highest standards of security, reliability, and transparency to gain the trust of citizens. In literature, several remote e-voting solutions based on blockchain technology have been proposed. Indeed, …

Loguad: Log Unsupervised Anomaly Detection Based On Word2vec, Jin Wang, Changqing Zhao, Shiming He, Yu Gu, Osama Alfarraj, Ahed Abugabah

All Works

System logs record detailed information about system operation and are important for analyzing the system's operational status and performance. Rapid and accurate detection of system anomalies is of great significance to ensure system stability. However, large-scale distributed systems are becoming more and more complex, and the number of system logs gradually increases, which brings challenges to analyze system logs. Some recent studies show that logs can be unstable due to the evolution of log statements and noise introduced by log collection and parsing. Moreover, deep learning-based detection methods take a long time to train models. Therefore, to reduce the computational …

Classification Of Parkinson Disease Based On Patient’S Voice Signal Using Machine Learning, Imran Ahmed, Sultan Aljahdali, Muhammad Shakeel Khan, Sanaa Kaddoura

All Works

Parkinson’s disease (PD) is a nervous system disorder first described as a neurological condition in 1817. It is one of the more prevalent diseases in the elderly, and Alzheimer’s is the second most common neurodegenerative illness. It impacts the patient’s movement. Symptoms start gradually with tremors, stiffness in movement, and speech and voice disorders. Researches proved that 89% of patients with Parkinson’s has speech disorder including uncertain articulation, hoarse and breathy voice and monotone pitch. The cause behind this voice change is the reduction of dopamine due to damage of neurons in the substantia nigra responsible for dopamine production. In …

Trajectory Design For Uav-Based Data Collection Using Clustering Model In Smart Farming, Tariq Qayyum, Zouheir Trabelsi, Asad Malik, Kadhim Hayawi

All Works

Unmanned aerial vehicles (UAVs) play an important role in facilitating data collection in remote areas due to their remote mobility. The collected data require processing close to the end-user to support delay-sensitive applications. In this paper, we proposed a data collection scheme and scheduling framework for smart farms. We categorized the proposed model into two phases: data collection and data scheduling. In the data collection phase, the IoT sensors are deployed randomly to form a cluster based on their RSSI. The UAV calculates an optimum trajectory in order to gather data from all clusters. The UAV offloads the data to …

"What's In A Name?”: The Use Of Instructional Design In Overcoming Terminology Barriers Associated With Dark Patterns, Andrea Curley, Damian Gordon, Dympna O'Sullivan

Conference Papers

Many users experience a phenomena when they are shopping on-line where they feel they are being pressured to either spend more money than they had intended, or to share more personal data than they wanted. In academic circles we use the term “Dark Patterns” to describe these deceptive practices, and categorize them as being within the discipline of User Experience (Narayanan, 2020). As academics it is important to name phenomena, and to categorize them, so that we can discuss and analyze these issues. However, this particular topic is one that all users should be made aware of when interacting online, …