Engineering Commons^™

Energy And Performance-Optimized Scheduling Of Tasks In Distributed Cloud And Edge Computing Systems, Haitao Yuan

Dissertations

Infrastructure resources in distributed cloud data centers (CDCs) are shared by heterogeneous applications in a high-performance and cost-effective way. Edge computing has emerged as a new paradigm to provide access to computing capacities in end devices. Yet it suffers from such problems as load imbalance, long scheduling time, and limited power of its edge nodes. Therefore, intelligent task scheduling in CDCs and edge nodes is critically important to construct energy-efficient cloud and edge computing systems. Current approaches cannot smartly minimize the total cost of CDCs, maximize their profit and improve quality of service (QoS) of tasks because of aperiodic arrival …

Changing The Focus: Worker-Centric Optimization In Human-In-The-Loop Computations, Mohammadreza Esfandiari

Dissertations

A myriad of emerging applications from simple to complex ones involve human cognizance in the computation loop. Using the wisdom of human workers, researchers have solved a variety of problems, termed as “micro-tasks” such as, captcha recognition, sentiment analysis, image categorization, query processing, as well as “complex tasks” that are often collaborative, such as, classifying craters on planetary surfaces, discovering new galaxies (Galaxyzoo), performing text translation. The current view of “humans-in-the-loop” tends to see humans as machines, robots, or low-level agents used or exploited in the service of broader computation goals. This dissertation is developed to shift the focus back …

Towards Practical Homomorphic Encryption And Efficient Implementation, Gyana R. Sahu

Dissertations

Cloud computing has gained significant traction over the past few years and its application continues to soar as evident from its rapid adoption in various industries. One of the major challenges involved in cloud computing services is the security of sensitive information as cloud servers have been often found to be vulnerable to snooping by malicious adversaries. Such data privacy concerns can be addressed to a greater extent by enforcing cryptographic measures. Fully homomorphic encryption (FHE), a special form of public key encryption has emerged as a primary tool in deploying such cryptographic security assurances without sacrificing many of the …

Analyzing And Assisting Patient Decision-Making In Online Health Communities, Mingda Li

Dissertations

In recent years, many users have joined online health communities (OHC) to seek information, suggestions and social support. However, little has been studied about the roles of OHCs in patients' decision-making processes. The aim of this research is to analyze OHC data to better understand patient decision-making processes, and to provide assistance to OHC users in their decision-making.

In order to analyze or assist patients in their decision-making, a novel classification model is designed to identify discussion threads in OHC that are related to decision making. This is achieved by building a two-step combined deep learning model. Empirical evaluation shows …

Ranking Volatility In Building Energy Consumption Using Ensemble Learning And Information Entropy, Kunal Sharma, Jung-Ho Lewe

Georgia Journal of Science

Given the rise in building energy consumption and demand worldwide, energy inefficiency detection has become extremely important. A significant portion of the energy used in commercial buildings is wasted as a result of poor maintenance, degradation or improperly controlled equipment. Most facilities employ sensors to track energy consumption across multiple buildings. Smart fault detection and diagnostic systems use various anomaly detection techniques to discover point anomalies in consumption. While these systems work reasonably well in detecting equipment anomalies over short-term intervals, further exploration is needed in finding methods that consider long-term consumption to detect anomalous buildings. This paper presents a …

Comparison Of Machine Learning Models: Gesture Recognition Using A Multimodal Wrist Orthosis For Tetraplegics, Charlie Martin

The Journal of Purdue Undergraduate Research

Many tetraplegics must wear wrist braces to support paralyzed wrists and hands. However, current wrist orthoses have limited functionality to assist a person’s ability to perform typical activities of daily living other than a small pocket to hold utensils. To enhance the functionality of wrist orthoses, gesture recognition technology can be applied to control mechatronic tools attached to a novel fabricated wrist brace. Gesture recognition is a growing technology for providing touchless human-computer interaction that can be particularly useful for tetraplegics with limited upper-extremity mobility. In this study, three gesture recognition models were compared—two dynamic time-warping models and a hidden …

A Fortran-Keras Deep Learning Bridge For Scientific Computing, Jordan Ott, Mike Pritchard, Natalie Best, Erik Linstead, Milan Curcic, Pierre Baldi

Engineering Faculty Articles and Research

Implementing artificial neural networks is commonly achieved via high-level programming languages such as Python and easy-to-use deep learning libraries such as Keras. These software libraries come preloaded with a variety of network architectures, provide autodifferentiation, and support GPUs for fast and efficient computation. As a result, a deep learning practitioner will favor training a neural network model in Python, where these tools are readily available. However, many large-scale scientific computation projects are written in Fortran, making it difficult to integrate with modern deep learning methods. To alleviate this problem, we introduce a software library, the Fortran-Keras Bridge (FKB). This two-way …

Evaluation Of Standard And Semantically-Augmented Distance Metrics For Neurology Patients, Daniel B. Hier, Jonathan Kopel, Steven U. Brint, Donald C. Wunsch, Gayla R. Olbricht, Sima Azizi, Blaine Allen

Electrical and Computer Engineering Faculty Research & Creative Works

Background: Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks.

Methods: We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by …

An Effective Method For Synthesizing The Abbreviated Disjunctive Normal Form Of A Boolean Function, Erkin Urunbaev

Scientific Journal of Samarkand University

In discrete mathematics, minimizing Boolean functions in the class of disjunctive normal forms is one of the necessary tasks. This paper presents an effective method for synthesizing the reduced disjunctive normal form of a Boolean function.

Paralleling Simulation Of Operation Plan Based On Decision Point Controlling, Zhanguang Cao, Pinggang Yu, Kuo Wang

Journal of System Simulation

Abstract: Operation plan simulation traditionally uses serial and static method. It can't be fulfilled for the military need of swift simulation and real-time decision in the modern complicated and dynamically battle field. So, the higher complexity and dynamical decision according to situation of the operation plan bring new challenge to the simulation. Operation Plan Paralleling Simulation Based on Decision Point Controlling (P2SDPC) can realize the operation plan's dynamic adjusting and cutting impossible branch based on decision point controlling technology. From then on, the efficiency of operation plan's simulation could be improved by the way of paralleling simulation. Thus the problem …

Model And Simulation Of Virtual Character Based On Real-Time Sensor Data-Driven, Lufeng Luo, Xiangjun Zou, Zhang Cong, Xie Lei

Journal of System Simulation

Abstract: The real-time control of virtual character behavior is a challenge in simulating virtual exercise. A kind of virtual character running behavior control method based on real-time data-driven was proposed, the real-time data acquisition with the help of sensor was expounded, the time-series law of human body running was analyzed, the human body posture mathematics expression was modeled, and a limb movement parts and rotation degrees of freedom computing model was proposed. By use of rotation angle method, the space and time relationship of each part of human movement chains was established and the movement process frame when moving was …

Method For Auto-Generating Cartoon Based On A Set Of Portrait Dictionary, Jingjing Sun, Jiajun Yu, Li Bei, Zhifeng Xie, Youdong Ding

Journal of System Simulation

Abstract: An efficient method of auto-generating portrait cartoon based on true portrait pictures was proposed. The first step was to establish a set of portrait dictionary. As a result, the portrait was divided into six components including eyebrows, eyes, nose, mouth, face, hair, so that the material library of cartoon corresponding to each component could be established. The next was to collect some real portrait images and synthesize them using the component material, meanwhile to calculate the facial shape features and the texture features of hair corresponding to each portrait. The second step was to input a real portrait image …

Neural Network Model Of Information Fusion For Coal Storage And Kinetic Energy Of Ball Mill, Bai Yan, He Fang

Journal of System Simulation

Abstract: A dynamic mathematical model of coal pulverizing system was analyzed. Simulation experiments on mill operation process were conducted by PFC3D software platform based on discrete element method. The associated data between different coal quality, coal storage and balls' motion were obtained under certain quantitative optimized operating parameters configuration. Neural network model of information fusion for coal storage and kinetic energy of ball mill was established by using an adaptive combination learning algorithm. Coal storage in mill cylinder was predicted from the energy point of view. The results indicate that there is a close relationship between coal storage, pulverizing efficiency …

Modeling Of High-Speed Railway Operation Informational Interaction Process Using Oopn, Liping Feng, Qiyuan Peng, Wen Chao

Journal of System Simulation

Abstract: High-speed railway transportation is an informational interaction process involving multi-levels and multiple subsystems. The majority of the present study focuses on the local system, causing some limitations to the overall control of high-speed rail traffic command. The high-speed railway operation process covering traffic control subsystem, train control subsystem, computer interlocking subsystem were researched with the key point of information interaction. Then the future directions were proposed, modeling and application respectively, which could remind of the deepen research on high-speed railway operation. Based on OOPN, the HTOIIP model with the formalized definition was built.

Application Of Domain Knowledge Representation In Simulation Tutoring For Weapon Utilization, Zhang Chi, Danhua Peng, Kedi Huang

Journal of System Simulation

Abstract: According to the requirements and characteristics of the simulation tutoring system for weapon utilization, a knowledge base depending on the domain ontology was designed. The knowledge for weapon utilization, the knowledge representation, and the method of knowledge representation were introduced. Through a combination of the ontology technology and various existing models, the key points of using specific weapon could be mastered by processing the date, information, and experience from expert. The conceptual model of knowledge was built. A knowledge base for weapon utilization was designed and implemented. The structure and function of the simulation tutoring system and rule-based expert …

Method For Auto-Detection Of Tracking Moving Objects In Complicated Dynamic Environment, Yanling Wang, Guanglun Li, Lin Xiao

Journal of System Simulation

Abstract: An approach was proposed to solve the problem of not accurately identifying the moving targets in the complex dynamic environment. The moving objects were detected by utilizing the method based on the HSV color space and auto-updating the background. The background subtraction method based on the HSV color space was used to solve the problem that the objects could not be accurately identified for the color similarity of objects and background and the influence of the shadow of the moving targets. The background change was divided into the temporary stability and the rapid change, and an automatically updating double …

Robust Image Cloning With Color Harmonization, Li Bei, Wang Hao, Jiajun Yu, Zhifeng Xie, Youdong Ding

Journal of System Simulation

Abstract: Image cloning has always been an important part of image editing. In general, it can be divided into three methods, based on a component, based on gradient domain, and based on coordinate respectively, but the color discordant and boundary distortion problems have not been well solved. In order to solve the color discordant problem in the method based on mean value coordinate, a method of image cloning was proposed based on local affinity propagation. The affinity considered the location information of pixels, color information, background information comprehensively, thus it could ease the color discordant and reach color harmonization. The …

Multi-Objective Cuckoo Search Algorithm, Xingshi He, Li Na, Xinshe Yang, Yu Bing

Journal of System Simulation

Abstract: It is challenging to solve multi-objective optimization problems with getting high-quality Pareto fronts accurately. The multi-objective Cuckoo Search algorithm (MOCS) was designed by firstly applying the recently developed Cuckoo Search Algorithm (CS) in solving Multi-objective optimization problems, and the fitness function based Pareto definiteness was improved, and the Gradual archive reduction method based on niche technology was proposed to improve the Archive solutions quality. The simulation test results and related performance indicators of nine test problems show that, MOCS algorithm is obviously improved in the aspect of the convergence, the diversity and the uniformity compared with the classic NSGA-II …

Simulation Analysis Of Rutting Length Based On Driving Safety Under Condition Of Road Waterlogging, Zhang Min, Xinxin Guo, Zhang Chi

Journal of System Simulation

Abstract: Rutting is one of the important factors for vehicle hydroplaning in raining days. Based on the analysis of vehicle driveability and lateral stability on the pavement covered by water, the rutting safety evaluation method considering driving safety under the condition of road waterlogging was put forward. Using the CarSim software to simulate vehicle lateral offset and lateral acceleration with different speeds, the rutting evaluation indicators on driving safety were set up. It shows that vehicle lateral offset and lateral acceleration increase quickly and exceed the safety threshold easily when more than 80km/h speed. On the rutting pavement covered by …

Security Model For Multi-Level Interaction Based On Portable Devices, Xuesi Zhang, Bin Yu

Journal of System Simulation

Abstract: Aiming at the problem of information interaction between multi-security-level devices, a security model based on portable devices was proposed. In use of portable storage device partitions, this model established a security communication channel that transmitted the multi-level interaction problem to the problem of controlling ordered read-write operation sequences. By setting the condition of security level as well as the recognition of partitions and operation, the read-write function for partition was designed to control the read and write operation towards the interactive partition. Based on the above, by designing operation control rules between interaction devices, an effective and bidirectional controlled …

Research Of Multi-Factor Identity Authentication Scheme For Zigbee Network Nodes, Weiwei Zhou, Yuntian Yue, Bin Yu

Journal of System Simulation

Abstract: To solve the problem of the man-in-the-middle attack and impersonation attack in ZigBee networks, a scheme based on multi-factor identity authentication for ZigBee network nodes was proposed. The scheme bound the fresh factor updated in a particular cycle with hardware information via a one-way hash function to generate hardware information factor. On this basis, the scheme achieved the authentication mechanism for the nodes through the comparison among key factor, hardware information factor and configuration information factor received by control center. Meanwhile, the nodes completed control center authentication through the signature verification of the message received. Thus, the bidirectional authentication …

Spatio-Temporal Correlation Described And Analysis Method Of Video Event Based On Case Frame, Ke Jia, Yongzhao Zhan, Xiaojun Chen, Manrong Wang

Journal of System Simulation

Abstract: In the mass of video resources, how to describe and represent video event content is one of hot issues in the current multimedia information processing. The original theory of case grammar for natural language understanding was extended; Case Frame was designed to describe the relationships between the structures of complex events in the sub-events. In Ref_Asso, which is one of relationships, spatio-temporal correlation was analyzed and reasoned among sub-events. In the experimental part, Case Semantic Frame Net was used to describe and understand the typical complex events in surveillance video. And results of users' retrieval were compared; in which …

Digital Analysis For Van Gogh's Painting, Yuqing Liu, Yuanyuan Pu, Yangfu Ren, Xu Dan

Journal of System Simulation

Abstract: Usually, Sparse Coding can be used to extract image characteristics for analyzing the style of visual art works, while researchers always don't do deep data mining on the trained basis function. The basic functions that could reflect the interior characteristics of a stylish image were trained based on Sparse Coding on art works. The spatial and higher-order characteristic statistics were figured out. Van Gogh's art works of different periods were analyzed through normalized mutual information computing using trained basis function's Gabor transform power, in order to find the diversity of style. The simulation results show that data mining on …

Research On High Usability Based On Cloud Simulation Platform, Limin Zhou, Yanfang Fu, Wuqi Gao, Gao Xiang, Cheng Bing

Journal of System Simulation

Abstract: With the increasing complexity of the simulation system, the reliability requirement is also growing. In order to ensure the reliability of the simulation system, a cloud simulation platform was built. Through the research of virtualization and high availability, a set of cloud simulation platform client management program was designed and developed according to the simulation needs. In the process of running, virtual simulation system node migration and analog off network operations were proposed to verify the reliability of the platform disaster. This ensures that the simulation system runs efficiently and stably.

Fluid Simulation Of Sph Based On Opencl, Miaomiao Xiao, Liu Zhen, Jiabin Shi, Tingting Liu, Cuijuan Liu, Bangquan Liu

Journal of System Simulation

Abstract: Fluid plays an important role in the Virtual Reality Scene. Physics-based fluid animation can enhance the reality of numerical simulation. The efficiency of fluid animation based on physical computing usually is not real-time rendering without parallel computing. Fluid simulation was proposed based on SPH using OpenCL, which could make full use of the data interoperability of OpenCL and the graphics API, and use the coordination work of CPU and GPU to increase the potential of the hardware; when physics computing, the surface particles and normals based on the Coulomb's law were solved out. The preliminary experiment shows that the …

Research On Augmented Reality Of Library's Navigation System, Zhou Wei, Lilong Chen, Jianwen Song

Journal of System Simulation

Abstract: Library science is an interdisciplinary or multidisciplinary field, classifying and retrieving books is very tedious and complex, librarians spend a lot of time on tidying books, readers on searching as well. AR (Augmented Reality) was used in library's book searching and navigation. Encoding a book's Id to a two-dimension code marker, using a AR software development kit, and Wi-Fi localization using RSSI(received signal strength), and combining the virtual mark of navigator with the scene of library, the procedure of book searching and borrowing was simplified. The test results indicate that this system benefits to locate the right place of …

Graphics And Image Local Deformation Based On Moving Least Squares Method, Xiaorong Du, Shuwen Ping, Zhang Yong

Journal of System Simulation

Abstract: Combined with Moving Least Squares method, a deformation function based on control points and area was defined. A localization processing method for image deformation was proposed which extended to vector graph deformation. After adding control points to control deformation and setting the target deformation zone as control area, control points were controlled to deform image and vector graph, which could produce affine transformation, similarity transformation and rigid transformation results. Experiments show that, this method can inhibit boundary aliasing as well as ensuring graphics and image local deformation result smoothness. By applying it to vector graph deformation, multiple complex deformation …

Design And Key Technologies Of Virtual Assembly And Simulation Of Mining, Driving And Transporting Equipment System, Jiacheng Xie, Zhaojian Yang, Xuewen Wang, Yiliang Wang

Journal of System Simulation

Abstract: For there was no connection among coal mine machinery equipment design, manufacture and its actual work environment, virtual assembly and simulation system, consisting of virtual assembly subsystem, scene simulation and roaming subsystem etc., were realized ultimately, which took shearer, scraper conveyor, roadheader and hoister as the study objects and were supported by double channel prop scene system as the hardware and Visual Studio and Open Scene Graph as the software platform, integrating force feedback, data gloves and other human interface devices, virtual assembly and simulation system made equipment operating status visible in the process of the coal production. In …

Digital Bathymetry Model For Multibeam Based On Attitude And Terrain Effect, Jiacheng Yu, Xueqiang Xu

Journal of System Simulation

Abstract: Aiming at the problems of expensive multibeam system and bumpy ship in bathymetric survey for seafloor, a digital bathymetry model based on depth data according to principle of multibeam mathymetric sonar system was designed, and a correction method of water depth survey due to effect of angular beam-width, vehicle attitude and terrain was given. Accordingly, seafloor was scanned with this model and terrain map was constructed to mimic the realtime terrain. The model and correction were verified by using practical water depth data of certain seafloor. Simulation results show that the model is in accordance with theoretical analysis and …

Gesture Segmentation And Recognition Based On Kinect Depth Data, Yanming Mao, Liliang Zhang

Journal of System Simulation

Abstract: Aiming at the problems that gesture recognition required high environmental background, segmented gesture usually contained wrist data and closing fingers easily caused false recognition, a gesture recognition method based on depth data was proposed. It captured gesture depth map, and it used Hands Generator to obtain the information of palm for gesture segmentation, in order to remove redundant wrist data, the constraint of the palm which looks like a square was added. The number of all the other four fingers except thumb could be acquired with the use of the scanline method, therefore, the width ratio of the adjacent …