Computer Engineering Commons^™

Pollutant Forecasting Using Neural Network-Based Temporal Models, Richard Pike

Masters Theses & Specialist Projects

The Jing-Jin-Ji region of China is a highly industrialized and populated area of the country. Its periodic high pollution and smog includes particles smaller than 2.5 μm, known as PM2.5, linked to many respiratory and cardiovascular illnesses. PM2.5 concentration around Jing-Jin-Ji has exceeded China’s urban air quality safety threshold for over 20% of all days in 2017 through 2020.

The quantity of ground weather stations that measure the concentrations of these pollutants, and their valuable data, is unfortunately small. By employing many machine learning strategies, many researchers have focused on interpolating finer spatial grids of PM2.5, or hindcasting PM2.5. However, …

Source Code Plagiarism Detection Using Jplag & Stack Overflow Data, Sudheer Yetthapu

Masters Theses & Specialist Projects

Advancements in computer technology and internet services have led to the availability of vast amounts of information like videos, articles, research papers, and code samples. Free online information will increase the possibility of plagiarism and collusion among students. People can commit plagiarism in both text and code [1], as tools used to detect plagiarism between texts and between codes are distinct. Traditionally plagiarism in code is detected using manual inspection, which is a tedious process and misses to compare code from previous submissions and external sources. To overcome this issue, systems that can automatically detect plagiarism in code were developed …

Bibliography, Huanjing Wang

Faculty/Staff Personal Papers

Bibliography of publications by Huanjing Wang.

A Low-Cost And Low-Tech Solution To Test For Variations Between Multiple Offline Programming Software Packages., Steffen Wendell Bolz

Masters Theses & Specialist Projects

This research paper chronicles the attempt to bring forth a low-cost and low-tech testing methodology whereby multiple offline programming (OLP) software packages’ generated programs may be compared when run on industrial robots. This research was initiated by the discovery that no real research exists to test between iterations of OLP software packages and that most research for positional accuracy and/or repeatability on industrial robots is expensive and technologically intensive. Despite this, many countries’ leaders are pushing for intensive digitalization of manufacturing and Small and Mediumsized Enterprises (SMEs) are noted to be lagging in adoption of such technologies. The research consisted …

K-Means Clustering Using Gravity Distance, Ajinkya Vishwas Indulkar

Masters Theses & Specialist Projects

Clustering is an important topic in data modeling. K-means Clustering is a well-known partitional clustering algorithm, where a dataset is separated into groups sharing similar properties. Clustering an unbalanced dataset is a challenging problem in data modeling, where some group has a much larger number of data points than others. When a K-means clustering algorithm with Euclidean distance is applied to such data, the algorithm fails to form good clusters. The standard K-means tends to split data into smaller clusters during a clustering process evenly.

We propose a new K-means clustering algorithm to overcome the disadvantage by introducing a different …

Supply Chain Analysis To Determine E-Commerce Distribution Center Locations, Fatima Chebchoub

Masters Theses & Specialist Projects

Supply chain management is the key success for each business. Having a robust supply chain will help the business to improve service, quality, reduce the costs, improve the speed, and be more flexible. Organizations need to look at data and deploy plans to move the product from operation to logistics to manage a global chain. In this paper we will use E-Comm shipment data to identify the best locations to build a new distribution center (DC).

Load Balancing Of Financial Data Using Machine Learning And Cloud Analytics, Dimple Jaiswal

Masters Theses & Specialist Projects

The rising use of technology for web applications, android applications, digital marketing, and e-application systems for financial investments benefits a large sector of stakeholders and common people. It allows investors to make an appropriate choice for investment and to increase their capital growth. This requires proper research of investment companies, their trends in price and analysis of historical and current information. In addition, prediction of prices makes the process of investment more comfortable and reliable for investors as shares are the most volatile type of investment. To offer this service to multiple users spread across the globe, there are certain …

Design And Implementation Of Sql Online Practice Platform, Wenhui Zhang

Masters Theses & Specialist Projects

Database management is a very important subject in computer science education. The study of SQL syntax is the most important part of this course. The traditional teaching method only lets the students practice SQL syntax through the textbook exercise. Students cannot get the query result directly. Moreover, students do not know intuitively what is wrong with the query sentence. In this study, we want to find a better way for the teachers and the students to learn this part of database management. Teacher uploads a SQL file through a web page, it will create a database with several tables and …

Exploring The Effect Of Different Numbers Of Convolutional Filters And Training Loops On The Performance Of Alphazero, Jared Prince

Masters Theses & Specialist Projects

In this work, the algorithm used by AlphaZero is adapted for dots and boxes, a two-player game. This algorithm is explored using different numbers of convolutional filters and training loops, in order to better understand the effect these parameters have on the learning of the player. Different board sizes are also tested to compare these parameters in relation to game complexity. AlphaZero originated as a Go player using an algorithm which combines Monte Carlo tree search and convolutional neural networks. This novel approach, integrating a reinforcement learning method previously applied to Go (MCTS) with a supervised learning method (neural networks) …

Application Of Huffman Data Compression Algorithm In Hashing Computation, Lakshmi Narasimha Devulapalli Venkata,

Masters Theses & Specialist Projects

Cryptography is the art of protecting information by encrypting the original message into an unreadable format. A cryptographic hash function is a hash function which takes an arbitrary length of the text message as input and converts that text into a fixed length of encrypted characters which is infeasible to invert. The values returned by the hash function are called as the message digest or simply hash values. Because of its versatility, hash functions are used in many applications such as message authentication, digital signatures, and password hashing [Thomsen and Knudsen, 2005].

The purpose of this study is to apply …

Vertical Implementation Of Cloud For Education (V.I.C.E.), Travis S. Brummett

Masters Theses & Specialist Projects

There are several different implementations of open source cloud software that organizations can utilize when deploying their own private cloud. Some possible solutions are OpenNebula, Nimbus, and Eucalyptus. These are Infrastructure-as-a-Service (IaaS) cloud implementations that ultimately gives users virtual machines to undefined job types. A typical IaaS cloud is composed of a front-end cloud controller node, a cluster controller node for controlling compute nodes, a virtual machine image repository node, and many persistent storage nodes and compute nodes. These architectures are built for ease of scalability and availability.

Interestingly, the potential of such architectures could have in the educational field …

Pedestrian Detection Using Basic Polyline: A Geometric Framework For Pedestrian Detection, Liang Gongbo

Masters Theses & Specialist Projects

Pedestrian detection has been an active research area for computer vision in recently years. It has many applications that could improve our lives, such as video surveillance security, auto-driving assistance systems, etc. The approaches of pedestrian detection could be roughly categorized into two categories, shape-based approaches and appearance-based approaches. In the literature, most of approaches are appearance-based. Shape-based approaches are usually integrated with an appearance-based approach to speed up a detection process.

In this thesis, I propose a shape-based pedestrian detection framework using the geometric features of human to detect pedestrians. This framework includes three main steps. Give a static …

Distributed Approach For Peptide Identification, Naga V K Abhinav Vedanbhatla

Masters Theses & Specialist Projects

A crucial step in protein identification is peptide identification. The Peptide Spectrum Match (PSM) information set is enormous. Hence, it is a time-consuming procedure to work on a single machine. PSMs are situated by a cross connection, a factual score, or a probability that the match between the trial and speculative is right and original. This procedure takes quite a while to execute. So, there is demand for enhancement of the performance to handle extensive peptide information sets. Development of appropriate distributed frameworks are expected to lessen the processing time.

The designed framework uses a peptide handling algorithm named C-Ranker, …

Ogden College Of Science & Engineering Newsletter (Summer 2014), Cheryl Stevens, Dean

Ogden College of Science & Engineering Publications

No abstract provided.

A Problem Solving Approach To Enterprise Filevault 2 Management And Integration, Nicholas Cobb

Masters Theses & Specialist Projects

Consumer technology adoption into large enterprise environments is occurring at an unprecedented rate. Employees require the flexibility and efficiency of using operating systems, computers, and mobility products they are familiar with and that enable their productivity. Due to this industry phenomenon, one large shipping enterprise must work to create solutions to integrate Apple’s OS X operating system into its traditional Windows-based operating environment. This level of integration must take place carefully to enable usability and foster the continued data security of enterprise assets. This paper describes the steps and methodology taken, as well as the rationale used, to accomplish the …

A Novel Dataset-Similarity-Aware Approach For Evaluating Stability Of Software Metric Selection Techniques, Huanjing Wang, Taghi M. Khoshgoftaar, Randall Wald, Amri Napolitano

Dr. Huanjing Wang

No abstract provided.

A Novel Dataset-Similarity-Aware Approach For Evaluating Stability Of Software Metric Selection Techniques, Taghi M. Khoshgoftaar, Huanjing Wang, Randall Wald, Amri Napolitano

Computer Science Faculty Publications

Software metric (feature) selection is an important preprocessing step before building software defect prediction models. Although much research has been done analyzing the classification performance of feature selection methods, fewer works have focused on their stability (robustness). Stability is important because feature selection methods which reliably produce the same results despite changes to the data are more trustworthy. Of the papers studying stability, most either compare the features chosen from different random subsamples of the dataset or compare each random subsample with the original dataset. These either result in an unknown degree of overlap between the subsamples, or comparing datasets …

Stability And Classification Performance Of Feature Selection Techniques., Huanjing Wang, Taghi M. Khoshgoftaar, Qianhui Althea Liang

Dr. Huanjing Wang

No abstract provided.

Stability And Classification Performance Of Feature Selection Techniques, Huanjing Wang, Taghi Khoshgoftaar, Qianhui Liang

Computer Science Faculty Publications

Feature selection techniques can be evaluated based on either model performance or the stability (robustness) of the technique. The ideal situation is to choose a feature selec- tion technique that is robust to change, while also ensuring that models built with the selected features perform well. One domain where feature selection is especially important is software defect prediction, where large numbers of met- rics collected from previous software projects are used to help engineers focus their efforts on the most faulty mod- ules. This study presents a comprehensive empirical ex- amination of seven filter-based feature ranking techniques (rankers) applied to …

Measuring Stability Of Threshold-Based Feature Selection Techniques, Huanjing Wang, Taghi M. Khoshgoftaar

Dr. Huanjing Wang

No abstract provided.

Measuring Stability Of Threshold-Based Feature Selection Techniques, Huanjing Wang, Taghi Khoshgoftaar

Computer Science Faculty Publications

Feature selection has been applied in many domains, such as text mining and software engineering. Ideally a feature selection technique should produce consistent out- puts regardless of minor variations in the input data. Re- searchers have recently begun to examine the stability (robustness) of feature selection techniques. The stability of a feature selection method is defined as the degree of agreement between its outputs to randomly-selected subsets of the same input data. This study evaluated the stability of 11 threshold-based feature ranking techniques (rankers) when applied to 16 real-world software measurement datasets of different sizes. Experimental results demonstrate that AUC …

Measuring Robustness Of Feature Selection Techniques On Software Engineering Datasets, Huanjing Wang, Taghi M. Khoshgoftaar, Randall Wald

Dr. Huanjing Wang

No abstract provided.

Measuring Robustness Of Feature Selection Techniques On Software Engineering Datasets, Huanjing Wang, Taghi Khoshgoftaar, Randall Wald

Computer Science Faculty Publications

Feature Selection is a process which identifies irrelevant and redundant features from a high-dimensional dataset (that is, a dataset with many features), and removes these before further analysis is performed. Recently, the robustness (e.g., stability) of feature selection techniques has been studied, to examine the sensitivity of these techniques to changes in their input data. In this study, we investigate the robustness of six commonly used feature selection techniques as the magnitude of change to the datasets and the size of the selected feature subsets are varied. All experiments were conducted on 16 datasets from three real-world software projects. The …

Ua3/9/2 I.T. Division Annual Report + Tactical Plan, Wku Information Technology

WKU Archives Records

Annual report of WKU Information Technology Division submitted to WKU President Gary Ransdell. Report is housed in UA3/9/2 Subject Files.

Quantifying Network Reliability Through Finding An Upper Bound For Graph Integrity Using Graph Coloring, Ian Burchett

Mahurin Honors College Capstone Experience/Thesis Projects

Integrity of a graph is defined as 𝐺 = 𝑚𝑖𝑛𝑆⊆𝑉(𝐺){ 𝑆 + 𝑚 𝐺 − 𝑆 } , where G is a graph with vertex set V and m(G-S) denotes the order of the largest component of G - S. This provides an upper estimate of the integrity of the given graph. Using graph coloring, the color sequence of the graph can be generated, with the leading term being the largest component of the graph, the maximal independent set. The determination of the set is too time intensive to be feasible for moderate to large graphs, since there is no …

The Videoconferencing Classroom: What Do Students Think?, Dr. Anthony Mark Doggett

Architectural and Manufacturing Sciences Faculty Publications

The advantages of video conferencing in educational institutions are well documented. Scholarly literature has indicated that videoconferencing technology reduces time and costs between remote locations, fill gaps in teaching services, increases training productivity, enables meetings that would not be possible due to prohibitive travel costs, and improves access to learning (Martin, 2005; Rose, Furner, Hall, Montgomery, Katsavras, & Clarke, 2000; Townes-Young & Ewing, 2005; West, 1999). However, there are few studies that analyze the effectiveness of videoconferencing from the student’s perspective. Videoconferencing technology is often touted as a method to connect with previously inaccessible student populations, but does it adequately …

Desitv - The Indian Tv, Saurin Shah

Mahurin Honors College Capstone Experience/Thesis Projects

DesiTV – The Indian TV project would utilize latest technology to provide live channels from the Indian Television World to Online World. The project would hence serve Indian demographic providing regional entertainment. It would contribute to the knowledge on how to utilize new technology and use it to provide better entertainment to the online users. Additionally, the project would help in learning how to build website/blog, how to host/post content and how to set up servers for broadcasting live channels. Also, how to maintain servers downtime and provide technical support. It would also contribute in the learning of how to …

Back-Up Server For Computer Science Department, Victoria Gaylord

Mahurin Honors College Capstone Experience/Thesis Projects

Because Western Kentucky University does not maintain a back-up system for its departments, the Computer Science Department has implemented its own. Using Bacula software on a Unix server, files from faculty desktop computers and servers are backed up to a tape drive on a daily basis. The server is protected from outside threats with a carefully configured firewall script. This paper explains how both the firewall and the back-up software were implemented and how successful that implementation has been.

Ua3/9/2 Information Technology Summary Report, Wku Information Technology

WKU Archives Records

Report of the WKU Information Technology Division to the president regarding operations from 1991 through 1997.

Ua3/8/5 Application For Cause Award For Excellence In Campus Networking, Wku President's Office-Meredith

WKU Archives Records

Application for CAUSE award for excellence in campus networking gives details about the first WKU computer network.