Computer Sciences Commons^™

Global Product And Technology Intern- Cs 7995, Krushita Patel, Project Advisor: Dawn Tatum

C-Day Computing Showcase

My project is about the experience that I have had and I have been currently having working as an intern at ADP working full time. I have also included my work description and what I am looking forward to for my rest of internship.

It Deployment And Fulfillment Co-Op- Cs 4983, Sam Wilson, Project Advisor: Dawn Tatum

C-Day Computing Showcase

No abstract provided.

Facial Recognition And Object Detection-Based Smart Cashier System- Cs 4732, Timmy Duong, Project Advisor: Mohammed Aledhari

C-Day Computing Showcase

The topic of smart based cashier system. Professor Dr. Aledhari is the project advisor for CS4732 Machine Vision.

Second Language Education Website And App Design, Songqiao Yu, Project Advisor: Mohammed Aledhari

C-Day Computing Showcase

During the pandemic, schools are closed and it brought a great chance for JoJo Learning to expand and explore the new method of customer acquisition. With a combination method of educational robot and E-book, JoJo is providing his customers with a compound solution for summer second language learning for kids and toddlers. As part of the team, my main responsibility is to prototype and publish new UIUX design and using data analysis as a method to find the key channels of the business.

Using Artificial Intelligence To Prescribe Medicine- Cs 4732, Xander Bush, Louis Livingston, Project Advisor: Mohammed Aledhari

C-Day Computing Showcase

With the current advancements being made in the Machine Learning field, utilizing Artificial Intelligence and Deep Learning techniques to analyze complex information such as genome information has become possible. By creating and building up a database of such data as well as compatible medicines, we suspect it is possible to prescribe personalized medicines to treat patients with a high percentage of success while also being able to take into account various other health conditions and pre-dispositions. This possibility depends heavily on the ability of the Neural Network or various other Machine Learning structure to correctly interpret the information from a …

Tracking High-Speed Chase Vehicles With Machine Learning​- Cs 4732, Louis Livingston, Dylan Sirna, Project Advisor: Mohammed Aledhari

C-Day Computing Showcase

From law enforcement officers, to fleeing suspects, to the general public, lengthy police pursuits poses a risk to all involved. With modern advances in machine vision, pursuits caught on camera can be analyzed with machine learning techniques. These techniques can then be used to produce datasets for future researchers to use in machine learning algorithms. This paper explores ways to produce those datasets using OpenCV, a machine vision library for Python, as well as GOTURN, a object tracker for OpenCV.

Service Industry Sentience- Cs 4267, Charles Peery, Project Advisor: Mohammed Aledhari

C-Day Computing Showcase

Since Amazon GO opened its' doors to employees in late 2016, businesses have been watching closely to see if a store without checkout can succeed in the current market.

While self-checkout stations have been in use since 1986, businesses are looking for ways to enhance the convenience of shoppers. From online ordering, contactless payments, and same day pickup, to drone delivery, leaving packages inside your home, and now checkout free stores.

In this presentation I explore the possibility of using YOLO and OpenCV to produce a checkout system based on object recognition which makes a system that is cheaper and …

Data, Stats, Go: Navigating The Intersections Of Cataloging, E-Resource, And Web Analytics Reporting, Rachel S. Evans, Wendy Moore, Jessica Pasquale, Andre Davison

Presentations

Do you trudge through gathering statistics at fiscal or calendar year-end? Do you wonder why you track certain things, thinking many seem outdated or irrelevant? Many places seem to keep counting certain statistics because "that's what they've always done." For e-resources, how do you integrate those with physical counts and reconcile the variations (updated e-resources versus re-cataloged physical items)? What about repository downloads and other web traffic? The quantity of stats that libraries track is staggering and keeps growing. This program will encourage attendees to stop and evaluate what and why they're gathering data and help identify possible alternatives to …

Modeling And Simulation On Influence Of Complex Network Nodes Based On Data Field In, Chenxi Shao, Xiaoqi Chen, Xingfu Wang, Fuyou Miao

Journal of System Simulation

Abstract: Research on the influence of complex network nodes is an important part of data mining. Mining the influential nodes in complex networks not only has important academic significance, but also helps to suppress the outbreak of epidemics, control the spread of rumors, and promote e-commercial products and so on. By selecting the Mixed Degree Decomposition (MDD) value of each node as its mass, the complex network is abstracted into a data field, the influential nodes are identified by combining the data field model, and some well-known centralities are compares with. The classical Susceptible-Infected-Recovered (SIR) epidemic model is …

Foot Measurement Based On Deep Alignment Network, Shi Min, Hanqin Yao, Chunpeng Li, Liangchen Chen

Journal of System Simulation

Abstract: Foot measurement plays an important role in many areas. Limited by equipment and algorithms, three-dimensional foot measurement cannot make a convenient and quick foot measurement. A method is proposed by combining the image measurement with the deep neural network. Based on the physiological structure analysis of foot, key points are extracted and the measurement parameters are defined. During the key point detection of foot, the activation function and loss function of DAN (Deep Alignment Network) model is optimized, and a data acquisition method is defined based on the handheld camera. Foot key points are detected, and main parameters are …

Mobile-Phone-Oriented Stereoscopic Display And Interaction Framework For Cloud-Based Virtual Reality 3d Scenes, Jiazhe Liu, Chunyi Chen, Xiaojuan Hu, Weidong Liang, Qiwei Xing, Huamin Yang

Journal of System Simulation

Abstract: A VR application framework based on cloud computing is proposed to overcome the difficulty of interactively generating high quality 3D scene images on mobile phones. We combine the cloud-based rendering and the VR technology. Our framework uses a mobile browser as a client, transmits the image data by the video block stream, processes the interactive data by the anti-jitter algorithm, and has accomplished the web-based lightweight rendering. The framework reduces the cost of data visualization on mobile phone and avoids the need of installing a plug-in package. The experimental results show that our display rate could be improved to …

Maintenance Operation Control Of Virtual Human In Collaborative Virtual Maintenance, Liang Feng, Zhili Zhang, Xiangyang Li

Journal of System Simulation

Abstract: Aiming at the operators being not able to move freely in the limited capture area of optical motion capture devices, the maintenance operation control of virtual human in Collaborative Virtual Maintenance is studied. The lower limb action of operators is captured by the optical motion capture devices, and the wide range motion of the virtual human is controlled according to the real-time recognition results. In order to control the hand motion process of the virtual human in the maintenance operation, the hand interaction of the virtual human is analyzed and an intelligent assistant method for the maintenance operations based …

Simulation Research On Cooperative Control Of Multi Intelligent Ground Platform Based On Agent Theory, Yunrong Zhang, Zhili Zhang, Xiangyang Li, Hongguang Wang, Wenpeng Mi, Xiangtong Kong, Pengpeng Liu

Journal of System Simulation

Abstract: In order to improve the cooperative control ability of the multi Intelligent ground platform and to adapt to the trend of intelligent war in the new situation, a multi intelligent ground platform cooperative Control simulation system based on jade and world wind Java is constructed. Based on multi-agent theory, the simulation model of intelligent ground platform is build. Based on JADE, the cooperative Control simulation platform is constructed. The task allocation mechanism is optimized by the particle swarm optimization algorithm. The simulation results show that the cooperative Control simulation platform has good robustness and flexibility. The optimized task allocation …

A Survey On Visual Slam Based On Deep Learning, Ruijun Liu, Xiangshang Wang, Zhang Chen, Bohua Zhang

Journal of System Simulation

Abstract: Following the development of computer vision and robotics, visual Simultaneous Localization and Mapping becomes a research focus in the field of unmanned systems. The powerful advantages of deep learning in the image processing offer a huge opportunity to the wide combination of the two fields. The outstanding research achievements of deep learning combined with visual odometry, loop closure detection and semantic Simultaneous Localization and Mapping are summarized. A comparison between the traditional algorithm and method based on deep learning is carried out. The development direction of visual Simultaneous Localization and Mapping based on deep learning is …

Visual Tracking And Localization Based On Confidence Evaluation Of Adjacent Targets, Youquan Liu, Pei Xue, Li Wan, Zhengxiong Liu

Journal of System Simulation

Abstract: In visual target tracking and localization, the target could not be located due to the lack of features or the severe occlusion. Aiming at this, an algorithm based on confidence evaluation of neighboring targets is designed. In the tracking process, by detecting and extracting the marker features of neighboring targets, and combining the Hamming distance of each feature marker and the normalized result with respect to other markers as well as the probability of occurrence of each marker, the final confidence of each marker is obtained. The marker with the maximum confidence is to used determine the target …

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 …

Mrmark: A Machine Performance Evaluation Method For Three-Dimensional Video Fusion, Yifei Sun, Liangliang Cai, Zhou Yi, Zhou Zhong

Journal of System Simulation

Abstract: The three-dimensional video fusion system needs the calculation of video and graphics, and requires high machine performance. The existing commercial evaluation tools lack the corresponding considerations, which may cause the inconsistency of a machine's performance from the score. A machine performance evaluation method for three-dimensional video fusion is proposed and an evaluation tool MRMark is implemented. Several sets of standard 3D test scenes are designed according to the characteristics of the video fusion system, the statistics on the frame rate, the number of video channels played and the other parameters during the test are collected to calculate the …

Research On Highway Bim Perception And Engineering Evaluation Based On Virtual Reality, Zhaohui Wu, Zhiqiang Fu, Wang Liang, Dou Fei

Journal of System Simulation

Abstract: Virtual reality technology is a new way for the highway BIM to upgrade from 2D to 3D. Based on the analysis of the characteristics of highway engineering and the travel needs of traffic participants, five methods are proposed to perceive highway BIM and evaluate the engineering design results of different road users, including virtual driving, virtual flight, virtual riding, virtual walking and augmented reality. These methods provide technical and tool support for the people-oriented road BIM perception, engineering evaluation, collaborative work, and design optimization. The experiment tests show that virtual reality connects the BIM models with human perception, …

Icp Optimized B-Spline Non-Rigid Registration For 4d-Ct Images, Wenjie Tang, Ruotong Li, Xuesong Deng, Weixin Si, Wang Qiong

Journal of System Simulation

Abstract: In order to improve the accuracy and speed of registration between two groups of 4D-CT images under different physiological activities, based on FFD model of multi-resolution B-spline, a registration algorithm using ICP to optimize the model is proposed. The ICP algorithm is added before the traditional b-spline to realize the point cloud registration between two groups of 4D-CT images: the appropriate model is generated from the two segmented groups of 4D-CT images, then the two groups of point clouds in the model are registered with ICP. The improvement rates of similarity measurement at level 1, level 2 and …

Advanced Parallel Algorithms In Computational Electromagnetics, Shu Wang

Electrical and Computer Engineering ETDs

The rapid development of high performance computing has pushed the computational electromagnetic(CEM) towards high accuracy, high fidelity and extreme computational scales. There is a great need for existing CEM solvers to have enhanced parallelism and scaling capability. The purpose of this dissertation is to investigate advanced parallel algorithms for both frequency and time domain solvers.

In frequency domain, this work first develop the underpinnings of parallel preconditioning technique and high-order transmission condition in the context of multi-solver scheme. The result is a computing resource-aware and implementation wise compact solver. Then this work targeted at developing efficient algorithms for cases where …

Methods Of Uncertainty Quantification For Physical Parameters, Kellin Rumsey

Mathematics & Statistics ETDs

Uncertainty Quantification (UQ) is an umbrella term referring to a broad class of methods which typically involve the combination of computational modeling, experimental data and expert knowledge to study a physical system. A parameter, in the usual statistical sense, is said to be physical if it has a meaningful interpretation with respect to the physical system. Physical parameters can be viewed as inherent properties of a physical process and have a corresponding true value. Statistical inference for physical parameters is a challenging problem in UQ due to the inadequacy of the computer model. In this thesis, we provide a comprehensive …

Simulation Reach On Multi-Generation Digital Product Diffusion Based On Agent, Qiao Jian, Jingwen Xia, Wang Pan

Journal of System Simulation

Abstract: Digital products have the characteristics of multi-generation coexistence and diffusion, and the multi-generation product diffusion model is an important tool to study it. The existing models ignores some factors of the product, consumer and environment that significantly affect the diffusion process. A multi-generation digital product diffusion model is proposed by using the ABMS, fuzzy inference, complex network and utility theories. The experiment results show that the model can playback the diffusion process of iPhones, which indicates that the model has a good simulation/prediction capability when the historical data is sufficient, and can be a marketing analysis and decision-making …

Review On Finite Element Model For Anti-Riot Kinetic Projectile Thorax Blunt Impact, Wang Song, Renjun Zhan

Journal of System Simulation

Abstract: In order to promote the construction and verification of the finite element models of human thorax and non-lethal projectiles in the field of blunt ballistic impact, the detailed anatomical and analogous structures of the thorax finite element models are combed and five typical of them are compared and verified. The construction and verification methods of the typical non-lethal projectile models are refined and the impact injury assessment methods are summarized. The next research recommendations are given. In order to improve the accuracy and biological fidelity of the thorax model, it is necessary to establish the physical and finite …

Real-Time Leaf Recognition Method Based On Cnn Network And Multi-Task Loss Function, Xingquan Cai, Yuxin Tu, Yakun Ge, Zhe Yang

Journal of System Simulation

Abstract: Aiming at the problems that the traditional leaf recognition is susceptible to the environmental interference and is difficult to realize the multi-leaf real-time recognition in complex background, a real-time leaf recognition method based on CNN network and multi-task loss function is proposed. The CNN network is used to the extract image feature maps and input them into RPN network to generate regional proposals. On the basis of the feature maps and region proposals, the feature map is proposaled, the leaf classification and bounding box regression are performed respectively, and the leaf classification and position of the leaf prediction box …

Hyperspectral Image Anomaly Detection Based On Background Reconstruction, Xiaorui Song, Zou Ling, Lingda Wu, Wanpeng Xu

Journal of System Simulation

Abstract: In the anomaly detection of hyperspectral images (HSIs), aiming at the difficulty of distinguishing the abnormal target from the background and the low accuracy of background prediction, a new HSI anomaly detection algorithm based on background sparse reconstruction is proposed. An online dictionary learning method is used to estimate the background spectral dictionary. The estimated background image is sparse reconstructed by the learning dictionary. The estimated background image is subtracted from the origin image to get the residual image. The anomaly detection is achieved by using the local RX detector to traverse the residual image. The effectiveness of the …

Human Depth Maps Restoration Based On Guided Gan, Jingfang Yin, Dengming Zhu, Shi Min, Zhaoqi Wang

Journal of System Simulation

Abstract: The depth maps captured by a small depth camera on mobile devices suffer from the problem of severe holes. The Guided Generative Adversarial Network (Guided GAN) based on deep learning is proposed to restore human depth maps with above problems. The high-precision human segmentation features and depth class features are extracted from the monocular RGB image by the guider based on the stacked hourglass network. The holes in the human depth maps are filled by the special generator under the guidance of the extracted human features. In order to get the more realistic results, the discriminator is introduced …

Modeling And Visualization On Scalar Fields Of Meteorological Data, Shuoben Bi, Yucheng Gong, Mingyue Lu, Zhou Hao, Yuanxiang Mao

Journal of System Simulation

Abstract: There are still many deficiencies in efficiency, interactivity, and accuracy in the visualization of meteorological scalar fields. Aiming at these problems, a display method based on multi-level volume rendering technology is proposed, which processes the spatial field data to form a three-dimensional space grid. Through the dynamic mapping between the scalar values and the color values and transparency, the three-dimensional dynamic visualization effect of the meteorological scalar data is realized. Aiming at the interpolation method for the traditional MC (Marching Cubes) algorithm being not applicable to the meteorological data, and the connection method having ambiguity problem, the improvement method …

Preloading Mechanism Of Large-Scale Web3d Scene Based On Dr Prediction, Huijuan Zhang, Xinqi Guo, Dongqing Wang, Jinyuan Jia

Journal of System Simulation

Abstract: In order to improve the loading efficiency of large-scale Web3D scene, a mechanism based on DR prediction is proposed. It combines the DR track prediction algorithm and historical path-based interest path clustering algorithm to track the field. The medium path prediction and path clustering in the traffic domain are applied to the virtual scene loading field, and a preloading mechanism of the Web3D scene is proposed. Experiment results show that the preloading mechanism can significantly improve the data transmission efficiency, optimize the loading speed of large-scale Web3D scene, and effectively improve the roaming experience of users in Web3D scene. …

Learning Expression Recognition Based On Image Sequence, Suqin Wang, Zhang Feng, Yudou Gao, Shi Min

Journal of System Simulation

Abstract: By recognizing the facial expressions, the emotional state of learner can be judged and their learning effect can be analyzed. Due to the persistence and timing of facial expressions, the sequence of facial images is adopted as the object of facial expression recognition. The Long Short Term Memory Network (LSTM) and VGGNet are combined into a VGGNET-LSTM model. On this basis, facial expression recognition is carried out, which significantly improves the accuracy of recognition. Based on the transfer learning method, VGGNet is transferred to the learning expression data set after being pre-trained through the basic expression data set CK+ …

An Adaptable Vr Software Framework For Collaborative Multi-Modal Haptic And Immersive Visual Display, Guo Yuan, Qianqian Tong, Yukai Zheng, Ziqi Wang, Yuru Zhang, Dangxiao Wang

Journal of System Simulation

Abstract: The spatiotemporal consistency of multi-modal haptic and immersive visual feedback, as well as the integration of hardware devices in the existing VR software framework, restricts the rapid development of visuo-haptic fusion scenarios in different industries such as medical, business, and entertainment. In order to tackle this problem, an adaptable VR software framework combining multi-modal haptic and immersive visual display is proposed. To meet the different requirements of visual rendering, haptic rendering and hardware control, the double-layer and three-layer architectures are devised according to the different precision requirements of visuo-haptic fusion feedback. Experimental results show that the framework has the …