Computer Sciences Commons^™

Optimizing Large-Scale Hyperparameters Via Automated Learning Algorithm, Bin Gu, Guodong Liu, Yanfu Zhang, Xiang Geng, Heng Huang

Machine Learning Faculty Publications

Modern machine learning algorithms usually involve tuning multiple (from one to thousands) hyperparameters which play a pivotal role in terms of model generalizability. Black-box optimization and gradient-based algorithms are two dominant approaches to hyperparameter optimization while they have totally distinct advantages. How to design a new hyperparameter optimization technique inheriting all benefits from both approaches is still an open problem. To address this challenging problem, in this paper, we propose a new hyperparameter optimization method with zeroth-order hyper-gradients (HOZOG). Specifically, we first exactly formulate hyperparameter optimization as an A-based constrained optimization problem, where A is a black-box optimization algorithm (such …

Identification Of Lsb Image Steganography Using Cover Image Comparisons, Michael Pelosi, Chuck Easttom

Journal of Digital Forensics, Security and Law

Steganography has long been used to counter forensic investigation. This use of steganography as an anti-forensics technique is becoming more widespread. This requires forensic examiners to have additional tools to more effectively detect steganography. In this paper we introduce a new software concept specifically designed to allow the digital forensics professional to clearly identify and attribute instances of LSB image steganography by using the original cover image in side-by-side comparison with a suspected steganographic payload image. This technique is embodied in a software implementation named CounterSteg. The CounterSteg software allows detailed analysis and comparison of both the original cover …

Backup And Recovery Mechanisms Of Cassandra Database: A Review, Karina Bohora, Amol Bothe, Damini Sheth, Rupali Chopade, V. K. Pachghare

Journal of Digital Forensics, Security and Law

Cassandra is a NoSQL database having a peer-to-peer, ring-type architecture. Cassandra offers fault-tolerance, data replication for higher availability as well as ensures no single point of failure. Given that Cassandra is a NoSQL database, it is evident that it lacks the amount of research that has gone into comparatively older and more widely and broadly used SQL databases. Cassandra’s growing popularity in recent times gives rise to the need of addressing any security-related or recovery-related concerns associated with its usage. This review paper discusses the existing deletion mechanism in Cassandra and presents some identified issues related to backup and recovery …

Non-Transgenic Crispr-Mediated Knockout Of Entire Ergot Alkaloid Gene Clusters In Slow-Growing Asexual Polyploid Fungi, Simona Florea, Jolanta Jaromczyk, Christopher L. Schardl

Computer Science Faculty Publications

The Epichloë species of fungi include seed-borne symbionts (endophytes) of cool-season grasses that enhance plant fitness, although some also produce alkaloids that are toxic to livestock. Selected or mutated toxin-free endophytes can be introduced into forage cultivars for improved livestock performance. Long-read genome sequencing revealed clusters of ergot alkaloid biosynthesis (EAS) genes in Epichloë coenophiala strain e19 from tall fescue (Lolium arundinaceum) and Epichloë hybrida Lp1 from perennial ryegrass (Lolium perenne). The two homeologous clusters in E. coenophiala—a triploid hybrid species—were 196 kb (EAS1) and 75 kb (EAS2), and …

Social Media User Relationship Framework (Smurf), Anne David, Sarah Morris, Gareth Appleby-Thomas

Journal of Digital Forensics, Security and Law

The use of social media has spread through many aspects of society, allowing millions of individuals, corporate as well as government entities to leverage the opportunities it affords. These opportunities often end up being exploited by a small percentage of the user community who use it for objectionable or unlawful activities; for example, trolling, cyber bullying, grooming, luring. In some cases, these unlawful activities result in investigations where swift retrieval of critical evidence required in order to save a life.

This paper presents a proof of concept (PoC) framework for social media user attribution. The framework aims to provide digital …

Application Of Guided Local Search (Gls) In Portfolio Optimization, Collether John

Tanzania Journal of Science

Portfolio optimization is a major activity in any operating business. Conventional portfolio optimization research makes simplifying assumptions; for example, they assume no constraint in how many assets one holds (cardinality constraint). They also assume no minimum and maximum holding sizes (holding size constraint). Once these assumptions are relaxed, conventional methods become inapplicable, and hence new methods are needed to tackle this challenge. Threshold Accepting is an established algorithm in the extended portfolio optimization problem. In this paper, an algorithm called Guided Local Search (GLS) is applied using an accurate and efficient designed hill climbing algorithm, named HC-C-R. GLS sitting on …

Capacity Analysis Of A Television White Space Network Deployed Under Distance Distribution Approach, Moses Ismail, Mussa Kissaka, Prosper Mafole

Tanzania Journal of Science

Television White Space (TVWS) is currently a leading technology for broadband connectivity in rural areas due to its penetration capability and robustness to attenuation and fading. Since most rural areas where TVWS is suitable are characterized by sparse population distribution, a deployed network must be adequately planned to provide the required coverage while meeting the targeted quality of service. This paper modelled and analyzed the capacity of a TVWS suitable for sparsely populated settings. The TVWS network was modelled using the distance distribution approach, and capacity simulation was carried out through Matlab. Results showed that, at the signal quality of …

Exploring The Efficiency Of Self-Organizing Software Teams With Game Theory, Clay Stevens, Jared Soundy, Hau Chan

School of Computing: Conference and Workshop Papers

Over the last two decades, software development has moved away from centralized, plan-based management toward agile methodologies such as Scrum. Agile methodologies are founded on a shared set of core principles, including self-organizing software development teams. Such teams are promoted as a way to increase both developer productivity and team morale, which is echoed by academic research. However, recent works on agile neglect to consider strategic behavior among developers, particularly during task assignment–one of the primary functions of a self-organizing team. This paper argues that self-organizing software teams could be readily modeled using game theory, providing insight into how agile …

A Secure And Flexible Fpga–Based Blockchain System For Iiots, Han-Yee Kim, Lei Xu, Weidong Shi, Taeweon Suh

Computer Science Faculty Publications

Blockchain is a promising solution for Industry 4.0 due to its traceability and immutability. However, blockchain itself does not guarantee the input data integrity. The tampered data from an endpoint device can be a significant problem because it may result in a cascaded negative effect on the whole smart factory operations. In this paper, we propose an FPGA-based private blockchain system for IIoTs, where the transaction generation is performed inside the FPGA in an isolated and enclaved manner. For the key confidentiality and transaction integrity, the proposed system utilizes a PUF, soft processor, and tightly coupled sensor connections inside the …

Google Books, Jody Condit Fagan

Libraries

Google Books’ (GB) full-text search of more than 40 million books offers significant value for libraries and their patrons. However, Google’s refusal to disclose information about the coverage of GB, as well as observed gaps and inaccuracies in the collection and its metadata, makes it difficult to recommend with confidence for a given research need. While most search and retrieval functions work well, glitches aren’t hard to find, which suggests GB development is focused on user experiences that relate to monetization. Privacy and equity concerns surrounding GB mirror those of other big technology platforms. Still, every librarian should familiarize themselves …

On Mentzer’S Hardness Of The K-Center Problem On The Euclidean Plane., Raymond Chen

Computer Science Technical Reports

An instance of the k-center problem consists of n points in a metric space along with a positive integer k. The goal is to find the smallest radius r such that there exists a subset of k centers picked among them such that every point is within distance r of at least one center. Stuart Mentzer (Mentzer, 1988) wrote a paper showing that in the Euclidean plane, it is NP-Hard to approximate this problem up to a factor of √2 +√3 ≈ 1.93. However, his report is missing some details. In this note, we present details of his full construction.

2021 February 08 - Computation And Research In Data Science (Cards) Minutes, Computation And Research In Data Science, East Tennessee State University

Computation and Research in Data Science (CaRDS) Board Meeting Minutes

No abstract provided.

Unsupervised Data Mining Technique For Clustering Library In Indonesia, Robbi Rahim, Joseph Teguh Santoso, Sri Jumini, Gita Widi Bhawika, Daniel Susilo, Danny Wibowo

Library Philosophy and Practice (e-journal)

Organizing school libraries not only keeps library materials, but helps students and teachers in completing tasks in the teaching process so that national development goals are in order to improve community welfare by producing quality and competitive human resources. The purpose of this study is to analyze the Unsupervised Learning technique in conducting cluster mapping of the number of libraries at education levels in Indonesia. The data source was obtained from the Ministry of Education and Culture which was processed by the Central Statistics Agency (abbreviated as BPS) with url: bps.go.id/. The data consisted of 34 records where the attribute …

An Optimal Deterministic Algorithm For Geodesic Farthest-Point Voronoi Diagrams In Simple Polygons, Haitao Wang

Computer Science Faculty and Staff Publications

Given a set S of m point sites in a simple polygon P of n vertices, we consider the problem of computing the geodesic farthest-point Voronoi diagram for S in P. It is known that the problem has an Ω(n + m log m) time lower bound. Previously, a randomized algorithm was proposed [Barba, SoCG 2019] that can solve the problem in O(n + m log m) expected time. The previous best deterministic algorithms solve the problem in O(n log log n + m log m) time [Oh, Barba, and Ahn, …

Hybrid Cloud Workload Monitoring As A Service, Shreya Kundu

Master's Projects

Cloud computing and cloud-based hosting has become embedded in our daily lives. It is imperative for cloud providers to make sure all services used by both enterprises and consumers have high availability and elasticity to prevent any downtime, which impacts negatively for any business. To ensure cloud infrastructures are working reliably, cloud monitoring becomes an essential need for both businesses, the provider and the consumer. This thesis project reports on the need of efficient scalable monitoring, enumerating the necessary types of metrics of interest to be collected. Current understanding of various architectures designed to collect, store and process monitoring data …

Addressing Artificial Intelligence Bias In Retinal Diagnostics, Philippe Burlina, Neil Joshi, William Paul, Katia D Pacheco, Neil M Bressler

Faculty, Staff and Students Publications

PURPOSE: This study evaluated generative methods to potentially mitigate artificial intelligence (AI) bias when diagnosing diabetic retinopathy (DR) resulting from training data imbalance or domain generalization, which occurs when deep learning systems (DLSs) face concepts at test/inference time they were not initially trained on.

METHODS: The public domain Kaggle EyePACS dataset (88,692 fundi and 44,346 individuals, originally diverse for ethnicity) was modified by adding clinician-annotated labels and constructing an artificial scenario of data imbalance and domain generalization by disallowing training (but not testing) exemplars for images of retinas with DR warranting referral (DR-referable) from darker-skin individuals, who presumably have greater …

Japanese Quail (Coturnix Japonica) As A Novel Model To Study The Relationship Between The Avian Microbiome And Microbial Endocrinology-Based Host-Microbe Interactions, Joshua M. Lyte, James Keane, Julia Eckenberger, Nicholas Anthony, Sandip Shrestha, Daya Marasini, Karrie M. Daniels, Valentina Caputi, Annie M. Donoghue, Mark Lyte

Department of Computer Science Publications

Microbial endocrinology, which is the study of neuroendocrine-based interkingdom signaling, provides a causal mechanistic framework for understanding the bi-directional crosstalk between the host and microbiome, especially as regards the effect of stress on health and disease. The importance of the cecal microbiome in avian health is well-recognized, yet little is understood regarding the mechanisms underpinning the avian host-microbiome relationship. Neuroendocrine plasticity of avian tissues that are focal points of host-microbiome interaction, such as the gut and lung, has likewise received limited attention. Avian in vivo models that enable the study of the neuroendocrine dynamic between host and microbiome are needed. …

Noise Annoyance In The Uae: A Twitter Case Study Via A Data-Mining Approach, Andrew Peplow, Justin Thomas, Aamna Alshehhi

All Works

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. Noise pollution is a growing global public health concern. Among other issues, it has been linked with sleep disturbance, hearing functionality, increased blood pressure and heart disease. Individuals are increasingly using social media to express complaints and concerns about problematic noise sources. This behavior—using social media to post noise-related concerns—might help us better identify troublesome noise pollution hotspots, thereby enabling us to take corrective action. The present work is a concept case study exploring the use of social media data as a means of identifying and monitoring noise annoyance across the …

Computational Catalyst Discovery: Active Classification Through Myopic Multiscale Sampling, Kevin Tran, Willie Neiswanger, Kirby Broderick, Eric Xing, Jeff Schneider, Zachary W. Ulissi

Machine Learning Faculty Publications

The recent boom in computational chemistry has enabled several projects aimed at discovering useful materials or catalysts. We acknowledge and address two recurring issues in the field of computational catalyst discovery. First, calculating macro-scale catalyst properties is not straightforward when using ensembles of atomic-scale calculations [e.g., density functional theory (DFT)]. We attempt to address this issue by creating a multi-scale model that estimates bulk catalyst activity using adsorption energy predictions from both DFT and machine learning models. The second issue is that many catalyst discovery efforts seek to optimize catalyst properties, but optimization is an inherently exploitative objective that is …

Why Romans Sometimes Wrote 8 As Viii, And Sometimes As Iix: A Possible Explanation, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Most of us are familiar with Roman numerals and with the standard way of describing numbers in the form of these numerals. What many people do not realize is that the actual ancient Romans often deviated from these rules. For example, instead of always writing the number 8 as VIII, i.e., 5 + 3, they sometimes wrote it as IIX, i.e., as 10 − 2. Some of such differences can be explained: e.g., the unusual way of writing 98 as IIC, i.e., as 100 − 2, can be explained by the fact that the Latin word for 98 literally means …

Why Do We Need Two Doses Of Covid-19 Vaccine: A Qualitative Explanation, Laxman Bokati, Julio Urenda, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

It is known that the most effective protection from Covid-19 comes if the vaccination is done in two doses separated by several weeks. In this paper, we provide a qualitative explanation for this empirical fact.

Why T-Duality: A Simple Explanation, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

In many physical theories, there is a -- somewhat surprising -- similarity between events corresponding to large distances R and events corresponding to very small distances 1/R. Such similarity is known as T-duality. At present, the only available explanation for T-duality comes from a complex mathematical analysis of the corresponding formulas. In this paper, we provide an alternative explanation based on the fundamental notion of causality.

Csci 40500/77100: Software Engineering, Raffi Khatchadourian

Open Educational Resources

This course is intended to be an introductory survey on the fundamental concepts and principles that underlie current and emerging methods, tools, and techniques for the efficient engineering of high-quality software systems. This may include understanding and appreciating problems in large-scale software development such as functional analysis of information processing systems, system design concepts, timing estimates, documentation, and system testing.

Csci 40500/77100: Software Engineering, Raffi Khatchadourian

Open Educational Resources

This course is intended to be an introductory survey on the fundamental concepts and principles that underlie current and emerging methods, tools, and techniques for the efficient engineering of high-quality software systems. This may include understanding and appreciating problems in large-scale software development such as functional analysis of information processing systems, system design concepts, timing estimates, documentation, and system testing.

An Exploration Of Stress: Leveraging Online Data From Crowdsourcing Platforms, James Roddy, Samantha Robinson

Mathematical Sciences Faculty Publications and Presentations

Background: Early detection of community health risk factors such as stress is of great interest to health policymakers, but representative data collection is often expensive and time-consuming. It is important to investigate the use of alternative means of data collection such as crowdsourcing platforms.

Methods: An online sample of Amazon Mechanical Turk (MTurk) workers (N = 500) filled out, for themselves and their child, demographic information and the 10-item Perceived Stress Scale (PSS-10), designed to measure the degree to which situations in one’s life are appraised as stressful. Internal consistency reliability of the PSS-10 was examined via Cronbach’s alpha. Analysis …

Parking Recommender System Privacy Preservation Through Anonymization And Differential Privacy, Yasir Saleem Shaikh, Mubashir Husain Rehmani, Noel Crespi, Roberto Minerva

Publications

Recent advancements in the Internet of Things (IoT) have enabled the development of smart parking systems that use services of third-party parking recommender system to provide recommendations of personalized parking spot to users based on their past experience. However, the indiscriminate sharing of users’ data with an untrusted (or semitrusted) parking recommender system may breach the privacy because users’ behavior and mobility patterns could be inferred by analyzing their past history. Therefore, in this article, we present two solutions that preserve privacy of users in parking recommender systems while analyzing the past parking history using k-anonymity (anonymization) and differential privacy …

What Is The Logic Behind Cistercian Numbers?, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

In the 13-15 centuries, many European monasteries used an unusual number system developed originally by the Cistercian monks; later on, this system was used by winemakers. In this paper, we provide a possible explanation of why these particular symbols were used.

Zadeh's Vision, Modern Physics, And The Future Of Computing, Vladik Kreinovich, Olga Kosheleva

Departmental Technical Reports (CS)

At first glance, Zadeh's ideas that everything is a matter of degree seem to be more appropriate for situations when we do not know the exact equations, when we only have expert rules for control and/or decision making. From this viewpoint, it may seem that in physics, where equations are ubiquitous and all the terms seem precise, there is not much place for fuzziness. But, as we show, in reality, fuzzy ideas can help -- and help dramatically -- in physics as well: in spite of the first impression, as physicists know well, many arguments in physics rely heavily on …

The Utep Corpus Of Dissatisfaction In Spoken Dialog, Jonathan E. Avila, Nigel Ward, Aaron Alarcon

Departmental Technical Reports (CS)

We present a corpus of spoken dialogs collected to support research in the automatic detection of times of dissatisfaction. We collected 191 mock customer-merchant dialogs in two conditions: one where the scripts guided the participants to a satisfactory, mutually agreeable outcome, and one where agreement was precluded. Most dialogs were 1 to 5 minutes in length. The corpus and metadata are freely available for research purposes.

Zhvillimi I Mikroserviseve Në Infrastrukturë Të Kontinjerizuar, Agnesa Saliaga

Theses and Dissertations

Kjo temë bazohet në aplikimin e metodologjive më të mira të punës duke përdorur veglat e përshtatshme për krijimin, testimin, versionimin dhe lansimin e ciklit të zhvillimit të një softueri dhe adaptimin e tij në mjedisin e kontinjerizuar, qoftë ai i hostuar në infrastrukturën tonë apo atë cloud.

Në këtë punim këto teknologji do të elaborohen me fokus të madh praktik, duke prezentuar zgjidhje të ndryshme për pjesë të sfidave që shfaqen. Këto sfida elaborohen specifikisht përmes veglave që do të përdoren dhe aplikacionit që do ta lansojmë.

Nga skenaret e lartëpërmendura nxirren dhe vizualizohen rezultatet të cilat mund të …