Computer Engineering Commons^™

Clover Care: Website And E-Marketing Development, Parker Bryant, Amber Elliott, Weston Kingery, Ervin Ramos

Capstone Design Expo Posters

Clover Care is a geographically diverse company with both caregivers and clients spread across multiple counties. Efficient resource management and communication is critical for such a broadly distributed company. Clover Care also expects to continue expanding its geographical service area, making a solution even more critical. Clover Care was interested in updating and expanding their existing website to address this need. The centralization provided by using a website allows caregivers, clients and their families, and managers a way to quickly and effectively communicate.

The primary Clover Care forms that were to be centralized included the caregiver timesheet, client case management …

Predator-Prey Game To Maintain Stable Fish Population For Ecotoxicological Studies, Jason Blondin, Catherine Halpern, Tyler Malkus

Capstone Design Expo Posters

With the state of the environment on the forefront of many minds today, it’s important for our society to be able to understand how we interact with our local ecosystems and the potential impacts we can cause. Creating computational simulations of these environments can help to predict the possible effects of different situations. The purpose of our project was to create a predator-prey simulation of different species of fish that could take into account different population management strategies and accurately reflect the waves that could be caused by the introduction of various chemicals into the fish’s environment.

In order to …

Church Hill Activities & Tutoring, Dhundi Acharya, Dhruvil Shah, Michael Mcalexander

Capstone Design Expo Posters

Problem Statement: Church Hill Activities and Tutoring ( CHAT ), a non-profit organization which invests in the lives of Richmond’s most at-risk children by establishing strong connections through one-on one tutoring, mentorship, and enrichment activities , is facing difficulty in managing consistent communication with parents and volunteers. Each of these audiences requires different channels and information, and currently, sending paper to the home through students has become the primary channel for communicating with parents. The reliability of this practice is limited but continues because parents’ contact information, such as phone number or email, changes frequently.

Rationale: Since CHAT is facing …

Tatami: An Open Source Enterprise Social Network, Kenny Hegeland, Jeremy Narron, Kameron Spruill

Capstone Design Expo Posters

Tatami is an open source enterprise social network created by Ippon, a consulting and software design company with offices in France and the USA. Any company can install Tatami, allowing its employees to communicate in a Twitter-like fashion. Self-hosting Tatami also lets a company retain ownership of its data, keeping it out of the hands of third parties.

Tatami’s front end was originally coded using the Backbone.js library, which can make it challenging to add and modify features. Ippon decided to have it rewritten using the AngularJS web application framework, which will fix the previously mentioned problems. This rewrite will …

Dismira: Prioritization Of Disease Candidates In Mirna-Disease Associations Based On Maximum Weighted Matching Inference Model And Motif-Based Analysis, Joseph J. Nalluri, Bhanu K. Kamapantula, Debmalya Barh, Neha Jain, Antaripa Bhattacharya, Sintia Silva De Almeida, Rommel Thiago Juca Ramos, Artur Silva, Vasco Azevedo, Preetam Ghosh

Computer Science Publications

Background

MicroRNAs (miRNAs) have increasingly been found to regulate diseases at a significant level. The interaction of miRNA and diseases is a complex web of multilevel interactions, given the fact that a miRNA regulates upto 50 or more diseases and miRNAs/diseases work in clusters. The clear patterns of miRNA regulations in a disease are still elusive.

Methods

In this work, we approach the miRNA-disease interactions from a network scientific perspective and devise two approaches - maximum weighted matching model (a graph theoretical algorithm which provides the result by solving an optimization equation of selecting the most prominent set of diseases) …

Use Of A Green Familiar Faces Paradigm Improves P300-Speller Brain-Computer Interface Performance, Qi Li, Shuai Lu, Jian Li, Ou Bai

Computer Science Publications

Background

A recent study showed improved performance of the P300-speller when the flashing row or column was overlaid with translucent pictures of familiar faces (FF spelling paradigm). However, the performance of the P300-speller is not yet satisfactory due to its low classification accuracy and information transfer rate.

Objective

To investigate whether P300-speller performance is further improved when the chromatic property and the FF spelling paradigm are combined.

Methods

We proposed a new spelling paradigm in which the flashing row or column is overlaid with translucent green pictures of familiar faces (GFF spelling paradigm). We analyzed the ERP waveforms elicited by …

Transcriptional Network Growing Models Using Motif-Based Preferential Attachment, Ahmed F. Abdelzaher, Ahmad F. Al-Musawi, Preetam Ghosh, Michael L. Mayo, Edward J. Perkins

Computer Science Publications

Understanding relationships between architectural properties of gene-regulatory networks (GRNs) has been one of the major goals in systems biology and bioinformatics, as it can provide insights into, e.g., disease dynamics and drug development. Such GRNs are characterized by their scale-free degree distributions and existence of network motifs – i.e., small-node subgraphs that occur more abundantly in GRNs than expected from chance alone. Because these transcriptional modules represent “building blocks” of complex networks and exhibit a wide range of functional and dynamical properties, they may contribute to the remarkable robustness and dynamical stability associated with the whole of GRNs. Here, we …

Miregulome: A Knowledge-Base Of Mirna Regulomics And Analysis, Debmalya Barh, Bhanu Kamapantula, Neha Jain, Joseph Nalluri, Antaripa Bhattacharya, Lucky Juneja, Neha Barve, Sandeep Tiwari, Anderson Miyoshi, Vasco Azevedo, Kenneth Blum, Anil Kumar, Artur Silva, Preetam Ghosh

Computer Science Publications

miRNAs regulate post transcriptional gene expression by targeting multiple mRNAs and hence can modulate multiple signalling pathways, biological processes, and patho-physiologies. Therefore, understanding of miRNA regulatory networks is essential in order to modulate the functions of a miRNA. The focus of several existing databases is to provide information on specific aspects of miRNA regulation. However, an integrated resource on the miRNA regulome is currently not available to facilitate the exploration and understanding of miRNA regulomics. miRegulome attempts to bridge this gap. The current version of miRegulome v1.0 provides details on the entire regulatory modules of miRNAs altered in response to …

Maprepeat: An Approach For Effective Assembly Of Repetitive Regions In Prokaryotic Genomes, Diego Cb Mariano, Felipe L. Pereira, Preetam Ghosh, Debmalya Barh, Henrique Cp Figueiredo, Artur Silva, Rommel Tj Ramos, Vasco Ac Azevedo

Computer Science Publications

The newest technologies for DNA sequencing have led to the determination of the primary structure of the genomes of organisms, mainly prokaryotes, with high efficiency and at lower costs. However, the presence of regions with repetitive sequences, in addition to the short reads produced by the Next-Generation Sequencing (NGS) platforms, created a lot of difficulty in reconstructing the original genome in silico. Thus, even today, genome assembly continues to be one of the major challenges in bioinformatics specifically when repetitive sequences are considered. In this paper, we present an approach to assemble repetitive regions in prokaryotic genomes. Our methodology …

Self-Organizing Feature Maps Identify Proteins Critical To Learning In A Mouse Model Of Down Syndrome, Clara Higuera, Katheleen J. Gardiner, Krzysztof J. Cios

Computer Science Publications

Down syndrome (DS) is a chromosomal abnormality (trisomy of human chromosome 21) associated with intellectual disability and affecting approximately one in 1000 live births worldwide. The overexpression of genes encoded by the extra copy of a normal chromosome in DS is believed to be sufficient to perturb normal pathways and normal responses to stimulation, causing learning and memory deficits. In this work, we have designed a strategy based on the unsupervised clustering method, Self Organizing Maps (SOM), to identify biologically important differences in protein levels in mice exposed to context fear conditioning (CFC). We analyzed expression levels of 77 proteins …

Self-Organizing Feature Maps Identify Proteins Critical To Learning In A Mouse Model Of Down Syndrome, Clara Higuera, Katheleen J. Gardiner, Kryzysztof Cios

Computer Science Publications

Down syndrome (DS) is a chromosomal abnormality (trisomy of human chromosome 21) associated with intellectual disability and affecting approximately one in 1000 live births worldwide. The overexpression of genes encoded by the extra copy of a normal chromosome in DS is believed to be sufficient to perturb normal pathways and normal responses to stimulation, causing learning and memory deficits. In this work, we have designed a strategy based on the unsupervised clustering method, Self Organizing Maps (SOM), to identify biologically important differences in protein levels in mice exposed to context fear conditioning (CFC). We analyzed expression levels of 77 proteins …

Enabling Smartphone-Based Hd Video Chats By Cooperative Transmissions In Crns, Tao Jing, Xuewei Cui, Wei Cheng, Shixiang Zhu, Yan Huo, Xiuzhen Cheng

Computer Science Publications

Smartphones have been equipped with the cameras that can shoot HD videos, and the video chat apps such as Skype are becoming popular. We can, therefore, intuitively predict the trend that users are expecting to enjoy HD video chats via utilizing their smartphones. Most of the current Internet services, however, cannot support the live HD video transmissions because of their low uplink rate. In order to overcome this limit, we propose to offload the uplink transmissions to cooperative users via cognitive radio networks. Specifically, we first divide the video stream into several substreams according to the H.264/SVC standard and the …

Self-Organizing Feature Maps Identify Proteins Critical To Learning In A Mouse Model Of Down Syndrome, Clara Higuera, Kathleen J. Gardiner, Kryzysztof Cios

Computer Science Publications

Down syndrome (DS) is a chromosomal abnormality (trisomy of human chromosome 21) associated with intellectual disability and affecting approximately one in 1000 live births worldwide. The overexpression of genes encoded by the extra copy of a normal chromosome in DS is believed to be sufficient to perturb normal pathways and normal responses to stimulation, causing learning and memory deficits. In this work, we have designed a strategy based on the unsupervised clustering method, Self Organizing Maps (SOM), to identify biologically important differences in protein levels in mice exposed to context fear conditioning (CFC). We analyzed expression levels of 77 proteins …

Identifying Influential Nodes In A Wound Healing-Related Network Of Biological Processes Using Mean First-Passage Time, Tomasz Jakub Arodz, Danail Bonchev

Computer Science Publications

In this study we offer an approach to network physiology, which proceeds from transcriptomic data and uses gene ontology analysis to identify the biological processes most enriched in several critical time points of wound healing process (days 0, 3 and 7). The top-ranking differentially expressed genes for each process were used to build two networks: one with all proteins regulating the transcription of selected genes, and a second one involving the proteins from the signaling pathways that activate the transcription factors. The information from these networks is used to build a network of the most enriched processes with undirected links …

Vcu Cctr Mobile App: Android & Ios, Vattana Vichith, Stephen Wu, Bowen Zhang

Capstone Design Expo Posters

In today’s day and age, data should be accessible at all times. The biggest break-through for data accessibility is mobile technologies such as phones and tablets. The CCTR provides a continuum of informatics research and services to support translational and clinical research. Clinical Trials represent one of the central themes for the Center for Clinical and Translational Research, but they do not have a mobile app for the VCU community to access CCTR’s informatics resources.

This project aims to promote the expanded informatics research and services available to VCU students, faculty and staff as well as patients interested in discovering …

Mobile Crm Integration Using Amc Technology Apis, Matthew Bates, Allen Calderwood, Matthew Jenkins

Capstone Design Expo Posters

The problem our project solves is the feasibility of use of Salesforce, MSCRM and many other CRM technologies outside of the desk environment. When a user is away from their desk, they are unable to easily use these CRM technologies and our project solves that problem through the use of a Mobile Application that communicates with a desired CRM technology and deliver the desired information to an Android Smart-Watch. Regardless of what a company may do, efficiency is important. Through the use of our Mobile Application, companies that use CRM technologies such as Salesforce are able to further enhance their …

Enhanced Presentation Of Tomographic Data, Carmen Watts Clayton, Bernice E. Mills, George Buffleben, Thien Vu-Nguyen

STAR Program Research Presentations

Solid materials can now be viewed non-destructively with x-rays by tomography; a technique for taking many 2D images of an object at many angles and reconstructing the images into a 3D data cube. The data is next rendered into 2D or 3D still images or movies. By nature, x-ray tomography yields a very large amount of data in three dimensions. Effectively displaying this data to an audience is a challenge.

In this work techniques are explored to improve the presentation methods of movies of both 2D and 3D tomographic data for visual appeal and correct perspective. Finding the optimal ways …

Recdroid: A Resource Access Permission Control Portal And Recommendation Service For Smartphone Users, Gerrit Bond, Steven Jackson, Marcus Pare

Capstone Design Expo Posters

The rapid growth of the smartphone applications market raises security concerns regarding untrusted applications. Studies have shown that most apps in markets request to collect data irrelevant to the main functions of the apps. Traditional Android permission control design based on one-time decisions on installation has been proven to be ineffective in protecting users’ privacy and poorly utilizes scarce mobile resources (e.g. battery). RecDroid is designed to help protect user data in a market where unauthorized data collection is prevalent in most applications. With RecDroid’s recommendation feature, which is based on expert analysis, the user will be able to avoid …

Virtual Bus Simulation: Driver And Fuel Efficiency, James Freund, Ivan Grinkevich, Justin Boswell

Capstone Design Expo Posters

Problem Statement: VCU will be putting together state of the art 3D curved screen driving simulator. This simulator will mimic fleets of vehicles behavior and will be networked with INL and Univ. of Idaho simulators. The project will entail putting the simulator together and improving existing simulator software.

Rationale: Conduct research in the areas of important behaviors to increase driver efficiency, how simulation training can encourage good driving habits, Psychology of driver habits and distractions, and benefits of audio and visual cues to assist drivers. Approach: Identify the most optimal 3d engine and develop simulation environment using the chosen engine. …

Developing An Epics Ioc In Labview, Kenneth Butler, David Shires, Michael Talbott

Capstone Design Expo Posters

Problem Statement In working with labView and experimental physics at Jefferson Lab the current configuration is a linux based control system. Christiana has posed the task of implementing a windows based network configuration where input and output from the data readings is distributed across the network. With the help of LabView demos and CALabs softIOC we were asked to prove the concept of this windows based configuration to be possible. Specifically the task is to prove (or disprove) that we can serve data using the caLabs soft IOC.

Rationale The current configuration of Jefferson Labs data systems is served on …

Federated Account System For Accelerated Development Of Internal Systems, Javan Cohen, Nandu Radhakrishnan, Brian Seal

Capstone Design Expo Posters

Massey Cancer Center is currently bound by an internal Active Directory and role based account system and organizations outside of VCU need to write specific code to be able to access the information provided. Massey wanted to move their system to a federated account system with claims based authentication. This project is important because having information readily available to other trusted cancer research groups will help promote understanding and treatment of cancerous cells. Our approach was to take what we learned in CMSC 355 to create a design document that was approved by Dr. Fenstermacher. We used this to create …

Visualization Of Nlp Extractions, K. Barbour, D. Vieth, D. Warraich

Capstone Design Expo Posters

The goal of this project is to design a visualization system for information extracted from large amounts of unstructured text. The importance of the project is for the system to display information in a more informative way than simple highlighting of the raw text. The data is obtained from a program that scans multiple files for entities and extracts the information in said files pertaining to those entities. The entities that the program scans for includes people, organizations, locations, dates, incidents and any relative key words. The information is extracted and stored in JSON files, specifically in a format that …

Print Estimation: Columbia Printing And Graphics, Alex Jacobi, Chris Wooten, Sahil Zubair

Capstone Design Expo Posters

Problem Statement: Can we create a web application to help facilitate the estimation of printing services as requested by clients and allow for the full interaction between a client, sales representative, and an administrator all through a single web application.

Rationale: The importance of this project is to create an easy to use online service that a user can access from either their smartphone or desktop computer. If successful, this project will allow users to have quick access to quotes regarding their printing needs anywhere they are without the need of contacting an actual printing company. This project will also …

Probabilistic Verification Of Multi-Robot Missions In Uncertain Environments, Damian M. Lyons, Ronald Arkin, Shu Jiang, Dagan Harrington, Feng Tang, Peng Tang

Faculty Publications

The effective use of autonomous robot teams in highly-critical missions depends on being able to establish performance guarantees. However, establishing a guarantee for the behavior of an autonomous robot operating in an uncertain environment with obstacles is a challenging problem. This paper addresses the challenges involved in building a software tool for verifying the behavior of a multi-robot waypoint mission that includes uncertain environment geometry as well as uncertainty in robot motion. One contribution of this paper is an approach to the problem of a-priori specification of uncertain environments for robot program verification. A second contribution is a novel method …

Direct Optimization For Classification With Boosting, Shaodan Zhai

Browse all Theses and Dissertations

Boosting, as one of the state-of-the-art classification approaches, is widely used in the industry for a broad range of problems. The existing boosting methods often formulate classification tasks as a convex optimization problem by using surrogates of performance measures. While the convex surrogates are computationally efficient to globally optimize, they are sensitive to outliers and inconsistent under some conditions. On the other hand, boosting's success can be ascribed to maximizing the margins, but few boosting approaches are designed to directly maximize the margin. In this research, we design novel boosting algorithms that directly optimize non-convex performance measures, including the empirical …

Contrast Pattern Aided Regression And Classification, Vahid Taslimitehrani

Browse all Theses and Dissertations

Regression and classification techniques play an essential role in many data mining tasks and have broad applications. However, most of the state-of-the-art regression and classification techniques are often unable to adequately model the interactions among predictor variables in highly heterogeneous datasets. New techniques that can effectively model such complex and heterogeneous structures are needed to significantly improve prediction accuracy. In this dissertation, we propose a novel type of accurate and interpretable regression and classification models, named as Pattern Aided Regression (PXR) and Pattern Aided Classification (PXC) respectively. Both PXR and PXC rely on identifying regions in the data space where …

Merging Two Worlds: Agent-Based Simulation Methods For Autonomous Systems, Andreas Tolk

Computational Modeling & Simulation Engineering Faculty Publications

This chapter recommends the increased use of agent-based simulation methods to support the design, development, testing, and operational use of autonomous systems. This recommendation is motivated by deriving taxonomies for intelligent software agents and autonomous robotic systems from the public literature, which shows their similarity: intelligent software agents can be interpreted as the virtual counterparts of autonomous robotic systems. This leads to examples of how simulation can be used to significantly improve autonomous system research and development in selected use cases. The chapter closes with observations on the operational effects of possible emergent behaviour and the need to align the …

How Design Quality Improves With Increasing Computational Abilities: General Formulas And Case Study Of Aircraft Fuel Efficiency, Joe Lorkowski, Olga Kosheleva, Vladik Kreinovich, Sergei Soloviev

Departmental Technical Reports (CS)

It is known that the problems of optimal design are NP-hard -- meaning that, in general, a feasible algorithm can only produce close-to-optimal designs. The more computations we perform, the better design we can produce. In this paper, we theoretically derive quantitative formulas describing how the design qualities improves with the increasing computational abilities. We then empirically confirm the resulting theoretical formula by applying it to the problem of aircraft fuel efficiency.

Testing A Power Law Model Of Knowledge Propagation: Case Study Of The Out Of Eden Walk Project, Octavio Lerma, Leobardo Valera, Deana Pennington, Vladik Kreinovich

Departmental Technical Reports (CS)

To improve teaching and learning, it is important to understand how knowledge propagates. In general, when a new piece of knowledge is introduced, people start learning about it. Since the potential audience is limited, after some time, the number of new learners starts to decrease. Traditional models of knowledge propagation are based on differential equations; in these models, the number of new learners decreases exponentially with time. Recently, a new power law model for knowledge propagation was proposed. In this model, the number of learners decreases much slower, as a negative power of time. In this paper, we compare the …

Optimizing Pred(25) Is Np-Hard, Martine Ceberio, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Usually, in data processing, to find the parameters of the models that best fits the data, people use the Least Squares method. One of the advantages of this method is that for linear models, it leads to an easy-to-solve system of linear equations. A limitation of this method is that even a single outlier can ruin the corresponding estimates; thus, more robust methods are needed. In particular, in software engineering, often, a more robust pred(25) method is used, in which we maximize the number of cases in which the model's prediction is within the 25% range of the observations. In …