Digital Commons Network^™

Communicating Uncertain Information From Deep Learning Models In Human Machine Teams, Harishankar V. Subramanian, Casey I. Canfield, Daniel Burton Shank, Luke Andrews, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

The role of human-machine teams in society is increasing, as big data and computing power explode. One popular approach to AI is deep learning, which is useful for classification, feature identification, and predictive modeling. However, deep learning models often suffer from inadequate transparency and poor explainability. One aspect of human systems integration is the design of interfaces that support human decision-making. AI models have multiple types of uncertainty embedded, which may be difficult for users to understand. Humans that use these tools need to understand how much they should trust the AI. This study evaluates one simple approach for communicating …

Automated Discussion Analysis - Framework For Knowledge Analysis From Class Discussions, Swapna Gottipati, Venky Shankararaman, Mallikan Gokarn Nitin

Research Collection School Of Computing and Information Systems

This research full paper, describes knowledge management of class discussions using an analytics based framework. Discussions, either live classroom or through online forums, when used as a teaching method can help stimulate critical thinking. It allows the teacher to explore in-depth the key concepts covered in the course, motivates students to articulate their ideas clearly and challenge the students to think more deeply. Analysing the discussions helps instructors gain better insights on the personal and collaborative learning behaviour of students. However, knowledge from in-class discussions and online forums is not effectively captured and mined due to lack of appropriate automated …

Establishing Topological Data Analysis: A Comparison Of Visualization Techniques, Tanmay J. Kotha

USF Tampa Graduate Theses and Dissertations

When visualizing data, we would like to convey both the data and the uncertainty associated with it. There are many incentives to do this, ranging from hurricane path projection to geographical surveys. Important decision making tasks rely upon humans perceiving a clear picture of the data and having confidence in their decisions. Topological Data Analysis has the potential to visualize the data as features or hierarchies in ways that are familiar to human intuition, and thus could help us convey the variation associated with uncertainty.

In this thesis, we evaluate four visualization techniques: color maps, isocontours, Reeb graphs, and persistence …

Virtual Viewpoint Synthesis Based On Grid Mapping, Yao Li, Qiongying Wu, Xu Hui

Journal of System Simulation

Abstract: Due to imperfect depth maps, occlusion and the illumination difference between reference images, annoying artifacts, such as holes and ghost edges, appearing in the rendering image by DIBR, holes filling being time-consuming, triangle mesh based on the depth contour and maps mesh triangles with energy constrains were created. Image fusion algorithm merged different viewpoint images and got final virtual viewpoint image. While DIBR warped the image with pixels, triangles were mapped with. Compared with the traditional DIBR, the proposed algorithm has a faster processing speed than the traditional pixel based processing method in the same image quality.

Gpu-Accelerated Cloth Animation Based On Module Division, Kun Zhou, Liu Zhen, Gaoqi He, Chen Tian, Tingting Liu, Cuijuan Liu

Journal of System Simulation

Abstract: In order to improve the simulation speed of cloth animation, a module division parallel computing method was proposed by studying two kinds of cloth simulation models with dynamics and position based dynamics (PBD). A computing task was divided into a plurality of independent blocks by the way of data block. GPU parallel computing was used within the data block to improve the real-time performance and robustness of the cloth simulation. The applicability and effectiveness of the algorithm were verified under different scenarios and stochastic wind field. Experimental results show that under the same conditions, the proposed method can effectively …

Title Medical Image Fusion Based On Multi-Scale Coefficient Decomposition Framework, Kaifeng Wen, Bingjian Li

Journal of System Simulation

Abstract: The main purpose of medical image fusion is to obtain a high resolution image with as much details as possible for diagnosis. Magnetic resonance (MR) and computed tomography (CT) medical images has special sophisticated and complementary characteristics which are required for accurate diagnosis of disease. Based on this, a new medical fusion approach for MR and CT images based on multi-scale coefficient decomposition framework was proposed. The proposed approach used a combination of discrete wavelet and non-subsampled shearlet transforms for the initial multi-scale decompositions firstly. The decomposition multi-scale coefficients were fused twice using various local activity measures. The …

Controlling Framing Effects For Web-Based Group Decision Support Systems, Badria Sulaiman Alfurhood

Theses and Dissertations

The way the proposal and the available alternatives are presented or framed for a group decision may alter the ultimate group decision. Strategic framing is an attack method used to manipulate people into irrationally preferring a particular alternative. The adverse effects of framing threaten the trustworthiness and results of the group decision support systems (GDSSs). Nonetheless, the avoidance or reduction of framing effects is possible. Negative framing effects arise when users are not consistent with their choices if framing is applied for a collaborative decision using GDSSs. In this interdisciplinary research, human-computer interaction (HCI) informed methods, cognitive science, and political …

Simulation Of Dongba Art Style Painting, Wenhua Qian, Xu Dan, Xu Jin, He Lei, Zhang Bo

Journal of System Simulation

Abstract: An interactive technique that can generate the Dongba art paintings from 2D images is proposed. A Dongba painting line drawing system is designed and developed which adopts the interactive selection method to obtain the smooth and continuous line drawings. To produce the foreground image of the Dongba styles, a multi-frequency noise integral convolution algorithm is utilized to simulate the block texture color of the Dongba paintings. Texture synthesis algorithm is used to generate the image of large sizes from samples to simulate the background image. Based on the layer-mapping technique and local color transmission methods, the final artistic style …

Real-Time Simulation On Virtual Dressing Based On Virtual Human Body Model, Chuanyu Xue, Hongwei Dong, Mingmin Zhang, Zhigeng Pan

Journal of System Simulation

Abstract: In this paper we put forward a real-time method of virtual dressing using a single Kinect device. Virtual dressing using a low-cost device has very important application, but classic 3D human body dressing algorithms cannot work in real time. We need to generate 3D human body model before virtual dressing using Kinect. In this paper, we use a method which is based on body's basic information to build human body model, and the method is optimized to enhance the local simulation results.This paper presents a tracking ellipsoid modeland applies GPU parallel computing to decrease the amount of calculation …

Progressive Image Denoising Algorithm, Haiyang Li, Weiguo Cao, Shirui Li, Kelu Tao, Li Hua

Journal of System Simulation

Abstract: Currently almost all denoising algorithms are implemented by processing original noisy image itself simply, which could not enhance the performance further by combining original noisy image with the denoised image. To solve the problem, a framework of progressive image denoising method was proposed. The framework is based on the block matching and 3D collaborative filtering (BM3D) algorithm, which has the most remarkable denoising effect. It includes three layers and two fusions. Each layer is implemented by BM3D and denoises the fused image generated from the previous layers. Adequate statistical results show that under the same noise condition, our proposed …

Tools For Analyzing R Code The Tidy Way, Lucy D'Agostino Mcgowan, Sean Kross, Jeffrey Leek

The R Journal

With the current emphasis on reproducibility and replicability, there is an increasing need to examine how data analyses are conducted. In order to analyze the between researcher variability in data analysis choices as well as the aspects within the data analysis pipeline that contribute to the variability in results, we have created two R packages: matahari and tidycode. These packages build on methods created for natural language processing; rather than allowing for the processing of natural language, we focus on R code as the substrate of interest. The matahari package facilitates the logging of everything that is typed in the …

Image Subset Communication For Resource-Constrained Applications In Wirelesssensor Networks, Sajid Nazir, Omar Alzubi, Mohammad Kaleem, Hassan Hamdoun

Turkish Journal of Electrical Engineering and Computer Sciences

JPEG is the most widely used image compression standard for sensing, medical, and security applications. JPEG provides a high degree of compression but field devices relying on battery power must further economize on data transmissions to prolong deployment duration with particular use cases in wireless sensor networks. Transmitting a subset of image data could potentially enhance the battery life of power-constrained devices and also meet the application requirements to identify the objects within an image. Depending on an application's needs, after the first selected subset is received at the base station, further transmissions of the image data for successive refinements …

A New Biometric Identity Recognition System Based On A Combination Of Superior Features In Finger Knuckle Print Images, Hadis Heidari, Abdolah Chalechale

Turkish Journal of Electrical Engineering and Computer Sciences

Biometric methods are among the safest and most secure solutions for identity recognition and verification. One of the biometric features with sufficient uniqueness for identity recognition is the finger knuckle print (FKP). This paper presents a new method of identity recognition and verification based on FKP features, where feature extraction is combined with an entropy-based pattern histogram and a set of statistical texture features. The genetic algorithm (GA) is then used to find the superior features among those extracted. After extracting superior features, a support vector machine-based feedback scheme is used to improve the performance of the biometric system. Two …

Development Of A Supervised Classification Method To Construct 2d Mineral Mapson Backscattered Electron Images, Mahmut Camalan, Mahmut Çavur

Turkish Journal of Electrical Engineering and Computer Sciences

The Mineral Liberation Analyzer (MLA) can be used to obtain mineral maps from backscattered electron (BSE) images of particles. This paper proposes an alternative methodology that includes random forest classification, a prospective machine learning algorithm, to develop mineral maps from BSE images. The results show that the overall accuracy and kappa statistic of the proposed method are 97% and 0.94, respectively, proving that random forest classification is accurate. The accuracy indicators also suggest that the proposed method may be applied to classify minerals with similar appearances under BSE imaging. Meanwhile, random forest predicts fewer middling particles with binary and ternary …

Performance Analysis Of A Fuzzy Disparity Selector For Stereo Matching Of Imagesegments Under Radiometric Variations, Akhil Appu Shetty, Vadakekara Itty George, Chempi Gurudas Nayak, Raviraj Shetty

Turkish Journal of Electrical Engineering and Computer Sciences

Stereo matching algorithms generate disparity maps, which contain the depth information of the environment, from two or more images of a scene taken from different viewpoints. The process of obtaining dense disparity maps is a problem which is still being actively researched. The presence of radiometric differences in the images only further complicates the stereo matching problem. In the present research work, the images are initially split into small patches of pixels, such that pixels in each patch have similar intensities. The authors attempt to study the effect of the parameters, namely, tuning parameter `?? and the number of segments, …

Human Face Sketch To Rgb Image With Edge Optimization And Generative Adversarial Networks, Feng Zhang, Huihuang Zhao, Wang Ying, Qingyun Liu, Alex Noel Joseph Raj, Bin Fu

Computer Science Faculty Publications

Generating an RGB image from a sketch is a challenging and interesting topic. This paper proposes a method to transform a face sketch into a color image based on generation confrontation network and edge optimization. A neural network model based on Generative Adversarial Networks for transferring sketch to RGB image is designed. The face sketch and its RGB image is taken as the training data set. The human face sketch is transformed into an RGB image by the training method of generative adversarial networks confrontation. Aiming to generate a better result especially in edge, an improved loss function based on …

Development Of A Modeling Algorithm To Predict Lean Implementation Success, Richard Charles Barclay

Doctoral Dissertations

”Lean has become a common term and goal in organizations throughout the world. The approach of eliminating waste and continuous improvement may seem simple on the surface but can be more complex when it comes to implementation. Some firms implement lean with great success, getting complete organizational buy-in and realizing the efficiencies foundational to lean. Other organizations struggle to implement lean. Never able to get the buy-in or traction needed to really institute the sort of cultural change that is often needed to implement change. It would be beneficial to have a tool that organizations could use to assess their …

Facial Expression Synthesis Using Mals-Based Bilinear Factorization Model, Jiaci Guo, Shuling Dai

Journal of System Simulation

Abstract: Study on the facial expression synthesis is a constructive and creative subject in the field of virtual reality technology. The bilinear model is used for facial expression synthesis by separating the identity factor and the expression factor. The translation procedure in the bilinear model always requires a repetitive computation of matrix inverse operations to reach the identity factor and the expression factor. This computation may be instable when the observation data has the correlation or noisy information. In order to increase the stability of the bilinear model for expression synthesis, the modified iterative least square (MALS) regression is introduced …

Visualizing The Invisible: Occluded Vehicle Segmentation And Recovery, Xiaosheng Yan, Feigege Wang, Wenxi Liu, Yuanlong Yu, Shengfeng He, Jia Pan

Research Collection School Of Computing and Information Systems

In this paper, we propose a novel iterative multi-task framework to complete the segmentation mask of an occluded vehicle and recover the appearance of its invisible parts. In particular, firstly, to improve the quality of the segmentation completion, we present two coupled discriminators that introduce an auxiliary 3D model pool for sampling authentic silhouettes as adversarial samples. In addition, we propose a two-path structure with a shared network to enhance the appearance recovery capability. By iteratively performing the segmentation completion and the appearance recovery, the results will be progressively refined. To evaluate our method, we present a dataset, Occluded Vehicle …

Experiences Of Using Intelligent Virtual Assistants By Visually Impaired Students In Online Higher Education, Michele R. Forbes

USF Tampa Graduate Theses and Dissertations

In today’s world, the attainment of higher education impacts the acquisition of competitive employment and, thus, quality of life. As a group, persons with disabilities continually fall behind others in such academic progress, requiring new efforts to support their earning of advanced credentials. Though highly beneficial for these individuals, obtaining a degree comes with elevated levels of stress. As enrollment of students with disabilities grows in all formats of higher education, those involved must understand the stress endured by these students and how to diminish it. Theories speculate that technology, such as intelligent virtual assistants, may be a viable tool …

Big-Data Talent Analytics In The Public Sector: A Promotion And Firing Model Of Employees At Federal Agencies, Rabih Neouchi

Operations Research and Engineering Management Theses and Dissertations

Talent analytics is a relatively new area of focus to researchers working in analytics and data science. Talent Analytics has the potential to help companies make many informed critical decisions around talent acquisition, promotion and retention. This work investigates data science to predict “shiny star” employees in the U.S. public sector, defined as top-notch performers over the years of a given time span. Its scope falls within talent analytics, also called people analytics, a relatively new research area.

We clean a data set made available by the U.S. Office of Personnel Management (OPM) and present two models to predict the …

An Accelerated Hierarchical Approach For Object Shape Extraction And Recognition, Mahmoud K. Quweider, Bassam Arshad, Hansheng Lei, Liyu Zhang, Fitratullah Khan

Computer Science Faculty Publications

We present a novel automatic supervised object recognition algorithm based on a scale and rotation invariant Fourier descriptors algorithm. The algorithm is hierarchical in nature to capture the inherent intra-contour spatial relationships between the parent and child contours of an object. A set of distance metrics are introduced to go along with the hierarchical model. To test the algorithm, a diverse database of shapes is created and used to train standard classification algorithms, for shape-labeling. The implemented algorithm takes advantage of the multi-threaded architecture and GPU efficient image-processing functions present in OpenCV wherever possible, speeding up the running time and …

Exploring Eye Tracking Data On Source Code Via Dual Space Analysis, Li Zhang

School of Computing: Dissertations, Theses, and Student Research

Eye tracking is a frequently used technique to collect data capturing users' strategies and behaviors in processing information. Understanding how programmers navigate through a large number of classes and methods to find bugs is important to educators and practitioners in software engineering. However, the eye tracking data collected on realistic codebases is massive compared to traditional eye tracking data on one static page. The same content may appear in different areas on the screen with users scrolling in an Integrated Development Environment (IDE). Hierarchically structured content and fluid method position compose the two major challenges for visualization. We present a …

Chatterbox, Clayton Crispim, Jacqueline Siquiera De Medeiros, Joao Pedro Haddad Oliveira, Kleyton Soares, Maria Fabiana Nunes Dos Santos

ICT

In the market, there are not many options or tools for people that once could speak. However, due to an accident or stroke, not only lost their voices and even some of their movements, but also sign language is not an option either. The issue is that whichever communication alternative that is available is either too expensive to use or too complicated for their actual situation such as google voice, notepads, general writing tools, etc. as each of them requires a little bit of work to manage.

Therefore we intended to ease speech-impaired people’s lives by designing and developing an …

Transparency And Communication Patterns In Human-Robot Teaming, Shan Lakhmani

Electronic Theses and Dissertations

In anticipation of the complex, dynamic battlefields of the future, military operations are increasingly demanding robots with increased autonomous capabilities to support soldiers. Effective communication is necessary to establish a common ground on which human-robot teamwork can be established across the continuum of military operations. However, the types and format of communication for mixed-initiative collaboration is still not fully understood. This study explores two approaches to communication in human-robot interaction, transparency and communication pattern, and examines how manipulating these elements with a robot teammate affects its human counterpart in a collaborative exercise. Participants were coupled with a computer-simulated robot to …

Robust Adaptive Rate Control Algorithm And Its Simulation For P2p-Tv Streaming Media Systems, Fengjie Yin, Yang Hui, Zhang Ying

Journal of System Simulation

Abstract: A control algorithm proposed to control the upstream rate based on sliding mode control in P2P-TV streaming media node. Through the rational design of sliding mode controller, the algorithm can adaptively control the numbers of signaling threads between neighbor pairs connected simultaneously and then control the upload rate. Further, it can achieve the fair use of resources. Due to the sliding mode control has strong robust with modeling uncertainties, time varying parameter fluctuations and external disturbances, it can avoid the system congestion under network condition change. Simulation results demonstrate that it can lead to the convergence of the …

Flashlight In A Dark Room: A Grounded Theory Study On Information Security Management At Small Healthcare Provider Organizations, Gerald Auger

Masters Theses & Doctoral Dissertations

Healthcare providers have a responsibility to protect patient’s privacy and a business motivation to properly secure their assets. These providers encounter barriers to achieving these objectives and limited academic research has been conducted to examine the causes and strategies to overcome them. A subset of this demographic, businesses with less than 10 providers, compose a majority 57% of provider organizations in the United States. This grounded theory study provides exploratory findings, discovering these small healthcare provider organizations (SHPO) have limited knowledge on information technology (IT) and information security that results in assumptions and misappropriations of information security implementation, who is …

A 3d Tree Visualization Of Network Data Based On Webvr, Lin Ding, Guoxin Huang, Xu Ying

Journal of System Simulation

Abstract: A new method of three dimensional tree-style visualization of network data is proposed in this paper based on cluster computing, which maps the network structure of clustered data to hierarchical tree structure. The number of nodes of a community is treated as the weight to improve the PhylloTrees' phyllotactic layout algorithm and the 3D visualization of network data is implemented based on WebVR. Friendly interactive manipulations are achieved in the immersive VR scene such as rotation, zooming, pan, picking, and transparent fade / highlight enhancement of different displaying. The experimental results show that our method can show not only …

Variable Scale Point Cloud Registration Algorithm, Shuifa Sun, Zhun Li, Kun Xia, Yunfei Shi, Jiquan Yang, Fangmin Dong

Journal of System Simulation

Abstract: To address the low registration accuracy issue caused by scale mismatch of two point clouds, a multi-scale point cloud registration algorithm is proposed based on the distance ratio invariance of the geometric center of gravity and centroid. The point cloud is firstly filtered. Then, the scale ratio calculation model of the point cloud data is established by computing the point cloud’s gravity center and centroid. Finally, according to the relationship between the registration error and the scale true value, the scale factor is refined step by step with ICP algorithm. For the noise and the inconsistent point in the …

Cloud Fraction Of Satellite Imagery Based On Convolutional Neural Networks, Xia Min, Maoyang Shen, Jianfeng Wang, Yangguang Wang

Journal of System Simulation

Abstract: Cloud fraction is the basis for the application of meteorological satellite. Existing methods cannot use all the characteristics and optical parameters of the satellite cloud, which results in the inaccuracy of cloud detection and cloud fraction. In order to solve this problem, convolutional neural network is used for cloud detection. Based on the improved convolutional neural network, the satellite cloud image is divided into thin cloud, thick cloud and clear sky. Based on the cloud detection, an improved spatial correlation method is used for cloud fraction. The results for Chinese HJ-1A/B satellite imagery show that convolutional neural network can …