Computer Sciences Commons^™

Energy And Performance-Optimized Scheduling Of Tasks In Distributed Cloud And Edge Computing Systems, Haitao Yuan

Dissertations

Infrastructure resources in distributed cloud data centers (CDCs) are shared by heterogeneous applications in a high-performance and cost-effective way. Edge computing has emerged as a new paradigm to provide access to computing capacities in end devices. Yet it suffers from such problems as load imbalance, long scheduling time, and limited power of its edge nodes. Therefore, intelligent task scheduling in CDCs and edge nodes is critically important to construct energy-efficient cloud and edge computing systems. Current approaches cannot smartly minimize the total cost of CDCs, maximize their profit and improve quality of service (QoS) of tasks because of aperiodic arrival …

Global Optimization Algorithms For Image Registration And Clustering, Cuicui Zheng

Dissertations

Global optimization is a classical problem of finding the minimum or maximum value of an objective function. It has applications in many areas, such as biological image analysis, chemistry, mechanical engineering, financial analysis, deep learning and image processing. For practical applications, it is important to understand the efficiency of global optimization algorithms. This dissertation develops and analyzes some new global optimization algorithms and applies them to practical problems, mainly for image registration and data clustering.

First, the dissertation presents a new global optimization algorithm which approximates the optimum using only function values. The basic idea is to use the points …

Changing The Focus: Worker-Centric Optimization In Human-In-The-Loop Computations, Mohammadreza Esfandiari

Dissertations

A myriad of emerging applications from simple to complex ones involve human cognizance in the computation loop. Using the wisdom of human workers, researchers have solved a variety of problems, termed as “micro-tasks” such as, captcha recognition, sentiment analysis, image categorization, query processing, as well as “complex tasks” that are often collaborative, such as, classifying craters on planetary surfaces, discovering new galaxies (Galaxyzoo), performing text translation. The current view of “humans-in-the-loop” tends to see humans as machines, robots, or low-level agents used or exploited in the service of broader computation goals. This dissertation is developed to shift the focus back …

An Automated Feedback System To Support Student Learning Of Conceptual Knowledge In Writing-To-Learn Activities, Ye Xiong

Dissertations

As a pedagogical strategy, Writing-to-Learn (WTL) intends to use writing to improve students’ understanding of course content. However, most of the existing feedback systems for writing are mainly focused on improving students’ writing skills rather than their conceptual development. In this dissertation, an automatic approach is proposed to generate timely, actionable, and individualized feedback based on comparing knowledge representations extracted from lecture slides and individual students’ writing assignments. The novelty of the proposed approach lies in the feedback generation: to help students assimilate new knowledge into their existing knowledge better, their current knowledge is modeled as a set of matching …

Mind Maps And Machine Learning: An Automation Framework For Qualitative Research In Entrepreneurship Education, Yasser Farha

Dissertations

Entrepreneurship Education researchers often measure entrepreneurial motivation of college students. It is important for stakeholders, such as policymakers and educators, to assert if entrepreneurship education can encourage students to become entrepreneurs, as well as to understand factors that influence entrepreneurial motivation. For that purpose, researchers have used different methods and instruments to measure students' entrepreneurial motivation. Most of these methods are quantitative, e.g., closed-ended surveys, whereas qualitative methods, e.g., open-ended surveys, are rarely used.

Mind maps are an attractive qualitative survey tool because they capture the individual's reflections, thoughts, and experiences. For Entrepreneurship Education, mind maps can be utilized to …

Towards Practical Homomorphic Encryption And Efficient Implementation, Gyana R. Sahu

Dissertations

Cloud computing has gained significant traction over the past few years and its application continues to soar as evident from its rapid adoption in various industries. One of the major challenges involved in cloud computing services is the security of sensitive information as cloud servers have been often found to be vulnerable to snooping by malicious adversaries. Such data privacy concerns can be addressed to a greater extent by enforcing cryptographic measures. Fully homomorphic encryption (FHE), a special form of public key encryption has emerged as a primary tool in deploying such cryptographic security assurances without sacrificing many of the …

Analyzing And Assisting Patient Decision-Making In Online Health Communities, Mingda Li

Dissertations

In recent years, many users have joined online health communities (OHC) to seek information, suggestions and social support. However, little has been studied about the roles of OHCs in patients' decision-making processes. The aim of this research is to analyze OHC data to better understand patient decision-making processes, and to provide assistance to OHC users in their decision-making.

In order to analyze or assist patients in their decision-making, a novel classification model is designed to identify discussion threads in OHC that are related to decision making. This is achieved by building a two-step combined deep learning model. Empirical evaluation shows …

Understanding The Complex Ethical Landscape Of Artificial Intelligence Adoptions, Chrissann R. Ruehle

USF Tampa Graduate Theses and Dissertations

Although Artificial Intelligence (AI) has existed since the 1950’s, it has experienced a series of expansions and declines over the years. Currently, AI is on an upward trajectory and has prompted the fourth industrial revolution as many scientists have noted. Some firms have rapidly embraced this technology and experienced growth while others have been slow to adopt. Naturally, this expansion often has societal impacts. The aim of this study is to explore ethical considerations that arise during the adoption of this technology. This research addressed three questions: 1. How do market and regulatory forces reportedly shape Artificial Intelligence adoptions? 2. …

Accurate Patient Health Condition Identification And Risk Prediction From Health Data, Jinhe Shi

Dissertations

Online Health communities (OHCs), Electronic Health Records (EHRs) and Claims data contain rich patient information. Accurate identification of patient's health conditions is critical for providing effective and safe health care service and for trustable knowledge discovery. This dissertation proposes several deep-learning based techniques on identifying patient health conditions and predicting adverse drug event (ADE) risks using various health data.

First, this dissertation presents a novel patient experience mining model to differentiate the data expressing user experiences from the one describing hearsays. Indeed, OHCs contain information with varying degrees of quality. Identifying information that describes patient health experience from OHCs is …

Systems For Free Parking Assignment, Abeer M. Hakeem

Dissertations

Finding a free, curbside parking spaces in metropolitan areas, especially during rush hours, is difficult for drivers. The difficulty arises from not knowing where the available spaces may be at that time; and, even if the spaces are known, many vehicles may pursue the same spaces, causing serious parking contention and traffic congestion. This dissertation presents three cost-effective and easily deployable free parking assignment systems that optimize the travel time of the drivers.

The first contribution is the Free Parking System (FPS), a centralized solution that solves the curbside parking problem. Unlike existing solutions, FPS is cost-effective, as it does …

Ranking Volatility In Building Energy Consumption Using Ensemble Learning And Information Entropy, Kunal Sharma, Jung-Ho Lewe

Georgia Journal of Science

Given the rise in building energy consumption and demand worldwide, energy inefficiency detection has become extremely important. A significant portion of the energy used in commercial buildings is wasted as a result of poor maintenance, degradation or improperly controlled equipment. Most facilities employ sensors to track energy consumption across multiple buildings. Smart fault detection and diagnostic systems use various anomaly detection techniques to discover point anomalies in consumption. While these systems work reasonably well in detecting equipment anomalies over short-term intervals, further exploration is needed in finding methods that consider long-term consumption to detect anomalous buildings. This paper presents a …

An Effective Method For Attribute Subset Selection, Considering The Resource In Pattern Recognition, Bakhtiyorjon Bakirovich Akbaraliev

Chemical Technology, Control and Management

An analytical method for determining informative sets of features (INP) is developed, taking into account the resource for criteria based on the use of a measure of dispersion of classified objects. The areas of existence of the solution are defined. The statements and properties for the Fischer-type information criterion are proved, using which the proposed analytical method for determining the INP guarantees optimal results in the sense of maximizing the selected functional. The appropriateness of choosing this type of informative criterion is justified. A method for transforming attributes is proposed. The universality of the method in relation to the type …

Prerequisite Course Recommendation Based On Course Description And Students’ Grades, Haozhe Zhou

The Journal of Purdue Undergraduate Research

No abstract provided.

Estimating Vehicular Traffic Intensity With Deep Learning And Semantic Segmentation, Logan Bradley-Trietsch

The Journal of Purdue Undergraduate Research

No abstract provided.

Comparison Of Machine Learning Models: Gesture Recognition Using A Multimodal Wrist Orthosis For Tetraplegics, Charlie Martin

The Journal of Purdue Undergraduate Research

Many tetraplegics must wear wrist braces to support paralyzed wrists and hands. However, current wrist orthoses have limited functionality to assist a person’s ability to perform typical activities of daily living other than a small pocket to hold utensils. To enhance the functionality of wrist orthoses, gesture recognition technology can be applied to control mechatronic tools attached to a novel fabricated wrist brace. Gesture recognition is a growing technology for providing touchless human-computer interaction that can be particularly useful for tetraplegics with limited upper-extremity mobility. In this study, three gesture recognition models were compared—two dynamic time-warping models and a hidden …

Find Me If You Can: Aligning Users In Different Social Networks, Priyanka Kasbekar, Katerina Potika, Chris Pollett

Faculty Publications, Computer Science

Online Social Networks allow users to share experiences with friends and relatives, make announcements, find news and jobs, and more. Several have user bases that number in the hundred of millions and even billions. Very often many users belong to multiple social networks at the same time under possibly different user names. Identifying a user from one social network on another social network gives information about a user's behavior on each platform, which in turn can help companies perform graph mining tasks, such as community detection and link prediction. The process of identifying or aligning users in multiple networks is …

A Fortran-Keras Deep Learning Bridge For Scientific Computing, Jordan Ott, Mike Pritchard, Natalie Best, Erik Linstead, Milan Curcic, Pierre Baldi

Engineering Faculty Articles and Research

Implementing artificial neural networks is commonly achieved via high-level programming languages such as Python and easy-to-use deep learning libraries such as Keras. These software libraries come preloaded with a variety of network architectures, provide autodifferentiation, and support GPUs for fast and efficient computation. As a result, a deep learning practitioner will favor training a neural network model in Python, where these tools are readily available. However, many large-scale scientific computation projects are written in Fortran, making it difficult to integrate with modern deep learning methods. To alleviate this problem, we introduce a software library, the Fortran-Keras Bridge (FKB). This two-way …

Big Data Energy Management, Analytics And Visualization For Residential Areas, Ragini Gupta, A. R. Al-Ali, Imran A. Zualkernan, Sajal K. Das

Computer Science Faculty Research & Creative Works

With the rapid development of IoT based home appliances, it has become a possibility that home owners share with Utilities in the management of home appliances energy consumption. Thus, the proposed work empowers home owners to manage their home appliances energy consumption and allow them to compare their consumption with respect to their local community total consumption. This serves as a nudge in consumer's behavior to schedule their home appliances operation according to their local community consumption profile and trend. Utilizing the same common communication infrastructure, it also allows the utilities on different consumption levels (community, state, country) to monitor …

Analysis Of Distributed And Autonomous Scheduling Functions For 6tisch Networks, Francesca Righetti, Carlo Vallati, Sajal K. Das, Giuseppe Anastasi

Computer Science Faculty Research & Creative Works

The 6TiSCH architecture is expected to play a significant role to enable the Internet of Things paradigm also in industrial environments, where reliability and timeliness are of paramount importance to support critical applications. Many research activities have focused on the Scheduling Function (SF) used for managing the allocation of communication resources in order to guarantee the application requirements. Two different approaches have mainly attracted the interest of researchers, namely distributed and autonomous scheduling. Although many different (both distributed and autonomous) SFs have been proposed and analyzed, a direct comparison of these two approaches is still missing. In this work, we …

An Empirical Study Of Refactorings And Technical Debt In Machine Learning Systems, Yiming Tang, Raffi Khatchadourian, Mehdi Bagherzadeh, Rhia Singh, Ajani Stewart, Anita Raja

Publications and Research

Machine Learning (ML), including Deep Learning (DL), systems, i.e., those with ML capabilities, are pervasive in today's data-driven society. Such systems are complex; they are comprised of ML models and many subsystems that support learning processes. As with other complex systems, ML systems are prone to classic technical debt issues, especially when such systems are long-lived, but they also exhibit debt specific to these systems. Unfortunately, there is a gap of knowledge in how ML systems actually evolve and are maintained. In this paper, we fill this gap by studying refactorings, i.e., source-to-source semantics-preserving program transformations, performed in real-world, open-source …

Machine Learning Corrected Quantum Dynamics Calculations, A. Jasinski, J. Montaner, R. C. Forrey, B. H. Yang, P. C. Stancil, Naduvalath Balakrishnan, J. Dai, A. Vargas-Hernandez, R. V. Krems

Chemistry and Biochemistry Faculty Research

Quantum scattering calculations for all but low-dimensional systems at low energies must rely on approximations. All approximations introduce errors. The impact of these errors is often difficult to assess because they depend on the Hamiltonian parameters and the particular observable under study. Here, we illustrate a general, system- and approximation-independent, approach to improve the accuracy of quantum dynamics approximations. The method is based on a Bayesian machine learning (BML) algorithm that is trained by a small number of exact results and a large number of approximate calculations, resulting in ML models that can generalize exact quantum results to different dynamical …

Cryptography, Passwords, Privacy, And The Fifth Amendment, Gary C. Kessler, Ann M. Phillips

Journal of Digital Forensics, Security and Law

Military-grade cryptography has been widely available at no cost for personal and commercial use since the early 1990s. Since the introduction of Pretty Good Privacy (PGP), more and more people encrypt files and devices, and we are now at the point where our smartphones are encrypted by default. While this ostensibly provides users with a high degree of privacy, compelling a user to provide a password has been interpreted by some courts as a violation of our Fifth Amendment protections, becoming an often insurmountable hurdle to law enforcement lawfully executing a search warrant. This paper will explore some of the …

Evaluation Of Standard And Semantically-Augmented Distance Metrics For Neurology Patients, Daniel B. Hier, Jonathan Kopel, Steven U. Brint, Donald C. Wunsch, Gayla R. Olbricht, Sima Azizi, Blaine Allen

Electrical and Computer Engineering Faculty Research & Creative Works

Background: Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks.

Methods: We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by …

New Bounds On Augmenting Steps Of Block-Structured Integer Programs, Lin Chen, Martin Koutecký, Lei Xu, Weidong Shi

Computer Science Faculty Publications

Iterative augmentation has recently emerged as an overarching method for solving Integer Programs (IP) in variable dimension, in stark contrast with the volume and flatness techniques of IP in fixed dimension. Here we consider 4-block n-fold integer programs, which are the most general class considered so far. A 4-block n-fold IP has a constraint matrix which consists of n copies of small matrices A, B, and D, and one copy of C, in a specific block structure. Iterative augmentation methods rely on the so-called Graver basis of the constraint matrix, which constitutes a set of fundamental augmenting steps. All existing …

Network Architecture For Generating A Labeled Overhead Image, Nathan Jacobs, Scott Workman

Computer Science Faculty Patents

A computer-implemented process is disclosed for generating a labeled overhead image of a geographical area. A plurality of ground level images of the geographical area is retrieved. A ground level feature map is generated, via a ground level convolutional neural network, based on features extracted from the plurality of ground level images. An overhead image of the geographical area is also retrieved. A joint feature map is generated, via an overhead convolutional neural network based on the ground level feature map and features extracted from the plurality of ground level images. Geospatial function values at a plurality of pixels of …

Benchmarking Deep Learning Robustness On Images With Two-Factor Corruption, Wei Dai

Theses and Dissertations

Deep learning is an increasingly popular technology used for such tasks as image classification, speech recognition, and language translation. Deep learning technology is under active development, so that many innovative chipsets, useful frameworks, creative algorithms, and big data sets are emerging. Previous research using image data for measuring deep learning classifiers has usually focused on high quality image datasets. Thus, scientists usually have not tried to benchmark deep learning robustness with imperfect images. However, high quality images are not always available, and people also expect image classifier robustness in applications where image quality is not high. Therefore, in this research …

An Effective Method For Synthesizing The Abbreviated Disjunctive Normal Form Of A Boolean Function, Erkin Urunbaev

Scientific Journal of Samarkand University

In discrete mathematics, minimizing Boolean functions in the class of disjunctive normal forms is one of the necessary tasks. This paper presents an effective method for synthesizing the reduced disjunctive normal form of a Boolean function.

Misogyny Detection In Social Media On The Twitter Platform, Elena Shushkevich

Doctoral

The thesis is devoted to the problem of misogyny detection in social media. In the work we analyse the difference between all offensive language and misogyny language in social media, and review the best existing approaches to detect offensive and misogynistic language, which are based on classical machine learning and neural networks. We also review recent shared tasks aimed to detect misogyny in social media, several of which we have participated in. We propose an approach to the detection and classification of misogyny in texts, based on the construction of an ensemble of models of classical machine learning: Logistic Regression, …

Self-Stabilizing Token Distribution On Trees With Constant Space, Yuichi Sudo, Ajoy K. Datta, Lawrence L. Larmore, Toshimitsu Masuzawa

Computer Science Faculty Research

Self-stabilizing and silent distributed algorithms for token distribution in rooted tree networks are given. Initially, each process of a graph holds at most l tokens. Our goal is to distribute the tokens uniformly in the whole network so that every process holds exactly k tokens. In the initial configuration, the total number of tokens in the network may not be nk where n is the number of processes in the network. The root process is given the ability to create a new token or remove a token from the network. We aim to minimize the convergence time, the number of …

Blockchain Technology And Freight Forwarder Exploration Of Implications Focused On Practitioners In Shanghai, Johannes Van Bohemen

World Maritime University Dissertations

No abstract provided.