Computer Engineering Commons^™

Design Of Delro Autonomous Delivery Robot And Ai Based Localization, Tolga Karakurt

USF Tampa Graduate Theses and Dissertations

Autonomous robots are employed in numerous areas. In this thesis, it is proposed to design and build a self-controlled wheeled vehicle to deliver food.

As there are many applications of an autonomous agent for indoor and outdoor environments, this study is conducted on indoor settings whereas all the requirements and design processes are achieved for both operational boundaries.

The fundamental approach is to design and implement a Wheeled Mobile Robot (WMR), and to test skid-steering performance on proposed trajectories using a System Engineering approach. From this point of view, system requirements in mechanical, electrical, and software are evaluated, and overall …

Novel Bit-Sliced In-Memory Computing Based Vlsi Architecture For Fast Sobel Edge Detection In Iot Edge Devices, Rajeev Joshi

USF Tampa Graduate Theses and Dissertations

For today’s Internet-of-Things (IoT) edge devices, there is an acute need for fast and power-efficient hardware for an image processing task. Traditional hardware solutions with sequential and/or pipelined architectures incur high latency and power. This motivates us to propose a novel in-memory computing architecture for rapid image processing. We propose a bit-sliced in-memory computing architecture for CMOS VLSI implementation for fast Sobel edge detection. To the best of our knowledge, this is the first work to propose in-memory computing based VLSI architecture foredge detection. The novelty of the proposed work is that one image can be processed in constant time …

Sliver: Simulation-Based Logic Bomb Identification/Verification For Unmanned Aerial Vehicles, Jake M. Magness

Theses and Dissertations

This research introduces SLIVer, a Simulation-based Logic Bomb Identification/Verification methodology, for finding logic bombs hidden within Unmanned Aerial Vehicle (UAV) autopilot code without having access to the device source code. Effectiveness is demonstrated by executing a series of test missions within a high-fidelity software-in-the-loop (SITL) simulator. In the event that a logic bomb is not detected, this methodology defines safe operating areas for UAVs to ensure to a high degree of confidence the UAV operates normally on the defined flight plan. SLIVer uses preplanned flight paths as the baseline input space, greatly reducing the input space that must be searched …

Implications And Limitations Of Securing An Infiniband Network, Lucas E. Mireles

Theses and Dissertations

The InfiniBand Architecture is one of the leading network interconnects used in high performance computing, delivering very high bandwidth and low latency. As the popularity of InfiniBand increases, the possibility for new InfiniBand applications arise outside the domain of high performance computing, thereby creating the opportunity for new security risks. In this work, new security questions are considered and addressed. The study demonstrates that many common traffic analyzing tools cannot monitor or capture InfiniBand traffic transmitted between two hosts. Due to the kernel bypass nature of InfiniBand, many host-based network security systems cannot be executed on InfiniBand applications. Those that …

A Study Of Execution Performance For Rust-Based Object Vs Data Oriented Architectures, Joseph A. Vagedes

Theses and Dissertations

To investigate the Data-Oriented Design (DOD) paradigm, in particular, an architecture built off its principles: the Entity-Component-System (ECS). ECS is commonly used by video game engines due to its ability to store data in a way that is optimal for the cache to access. Additionally, the structure of this paradigm produces a code-base that is simple to parallelize as the workload can be distributed across a thread-pool based on the data used with little to no need for data safety measures such as mutexes and locks. A final benefit, although not easily measured, is that the DOD paradigm produces a …

Multi-Channel Security Through Data Fragmentation, Micah J. Hayden

Theses and Dissertations

This thesis presents a novel security system developed for a multi-channel communication architecture, which achieves security by distributing the message and its associated message authentication code across the available channels at the bit level, to support systems that require protection from confidentiality and integrity attacks without relying solely on traditional encryption. One contribution of the work is to establish some helpful terminology, present a basic theory for multi-channel communications, describe the services provided by an optimal system, and then implement a proof of concept system to demonstrate the concept's validity. This proof of concept, focused on the splitting and recombination …

A Comparative Evaluation Of The Detection And Tracking Capability Between Novel Event-Based And Conventional Frame-Based Sensors, James P. Boettiger

Theses and Dissertations

Traditional frame-based technology continues to suffer from motion blur, low dynamic range, speed limitations and high data storage requirements. Event-based sensors offer a potential solution to these challenges. This research centers around a comparative assessment of frame and event-based object detection and tracking. A basic frame-based algorithm is used to compare against two different event-based algorithms. First event-based pseudo-frames were parsed through standard frame-based algorithms and secondly, target tracks were constructed directly from filtered events. The findings show there is significant value in pursuing the technology further.

Developing A Serious Game To Explore Joint All Domain Command And Control, Nathaniel W. Flack

Theses and Dissertations

Changes in the geopolitical landscape and increasing technological complexity have prompted the U.S. Military to coin Multi-Domain Operations (MDO) and Joint All-Domain Command and Control as terms to describe an over-arching strategy that frames the complexity of warfare across both traditional and emerging warfighting domains. Teaching new and advanced concepts associated with these terms requires both innovation as well as distinct education and training tools in order to realize the cultural change advocated by senior military leaders. BSN, a Collectible Card Game, was developed to teach concepts integral to MDO and initiate discussion on military strategy.

System Methodology Of Digital Transformation In Military Manufacturing Industry, Daolin Yu, Wenhai Zhu, Qing Xiao, Guoqiang Shi

Journal of System Simulation

Abstract: Focusing on the lack of the understanding and the solutions to the digital transformation of the military manufacturing enterprises and service providers, the background of the digital transformation in the military manufacturing industry is analyzed. By studying the advanced manufacturing models, the core competitiveness, the value chains and the production (productivity) factors, the (generalization) goals of the digital transformation in the military manufacturing industry are identified, and some urgent problems and the suggestions to solve the complex system problems are provided. The digital transformation in the military manufacturing industry is a long-term strategic action and should be continuously optimized …

Wind Power Generation Hardware-In-Loop Simulation System Based On Rapid Control Prototype Technology, Aihua Wu, Buhui Zhao, Jingfeng Mao, Haiqun Shen, Xudong Zhang

Journal of System Simulation

Abstract: In order to improve the efficiency and effectiveness in the design and testing process of the wind power generation MPPT controller, a rapid control prototype (RCP) system based on the LabVIEW FPGA platform is proposed. The real-time simulation model of wind speed, wind turbine and PMSG, as well as MPPT rapid control prototyping are designed by using PXI-FPGA architecture on the LabVIEW RT real-time operation platform. The power converter, the real-time simulation model and the MPPT rapid control prototyping are connected together to construct a hardware-in-loop (HIL) test system. The simulation results on the gradient wind speed condition and …

Emergency Evacuation Simulation For Dense Passenger Flow In A Rail Transit Transfer Station, Xu Hui, Tian Cheng, Wang Yong

Journal of System Simulation

Abstract: The rail transit is one of the important modes of the public transportation, and its safety operation is crucial. Based on the passenger volume and structure features that have been obtained through the field investigation in Chongqing Lianglukou railway station in China, a multi-level rail transit transfer station simulation model is built to analyze the evacuation process of pedestrians in the consideration of explosion and other emergencies by the software AnyLogic. The evacuation routes and evacuation time of passengers during emergency evacuation in a rail transit transfer station are studied. The research aims at verifying the emergency evacuation capacity …

Research On Evolution Model Of Online Public Opinion Based On Temporal Network, Li Feng, Wei Ying

Journal of System Simulation

Abstract: With the in-depth study on the social medias, the social networks of online platforms are recognized gradually as the time-varying temporal networks. In order to compare and analyze the information diffusion process and the result, the analysis method of computer simulations is adopted, a temporal network is generated, and the SIR model is used as the online public opinion diffusion model. The simulation results based on multi-agent approach show that the uncertainty of information diffusion on the social platforms comes from the complicated structure of the temporal networks and the SIR model. In addition, the misunderstanding of the social …

Performance Balanced Opportunistic Routing And Simulation Analysis Based On Cooperative Game, Huahong Ma, Honghai Wu, Guoqiang Zheng, Baofeng Ji

Journal of System Simulation

Abstract: Opportunistic transmission mode of “store-carry-forward” is usually used to make routing in mobile opportunistic network. Currently, there have been many researches in this area. However, the existing opportunistic routing mechanisms pay much attention to the single index of delivery success ratio, but neglect the constraints on other performance indicators, which may lead to the extreme imbalance of network performance. Aiming at this issue, the diffusion of data packets between multiple nodes are modeled as a cooperative game with the goal of maximal performance balancing, and an opportunistic routing protocol based on the cooperative game for performance balancing is proposed. …

Parallel Computing Of Multi-Agent System In Spatially-Explicit Modeling And Simulation, Hongchun Qu, Xianhui Yao, Yin Li

Journal of System Simulation

Abstract: Aiming at the synchronization in the spatially-explicit parallel simulations, a limited optimistic synchronization algorithm based on Agent sensing region is proposed. The algorithm inherits the advantages of the optimistic synchronization algorithm and the security-guaranteed conservative synchronization algorithm. The algorithm categories all simulated agents into the security agent region and non-security agent region. The simulation is performed through the collaboration between the dispatch server and the execution servers where simulation tasks are scheduled and executed. The dispatch server determines whether an agent is in a security zone according to the security radius. The execution servers are responsible for performing the …

Visualization Of Tropical Cyclones Based On Digital Earth, Shuoben Bi, Yucheng Gong, Mingyue Lu, Zhou Hao, Tang Zhi

Journal of System Simulation

Abstract: Tropical cyclones are often accompanied by heavy rains, storm surges and so on, which have serious impact on the southeast coast of China. Visualization of tropical cyclones can directly demonstrate its motion state, occurrence process and internal structure, and support the research and prediction on it. This paper builds digital earth platform based on Cesium(an open source library),introduces the system architecture, verificates the applicability of point cloud method to the visualization of cloud field data, proposes an improved wind field visualization method based on particle tracking, with includes the calculation of wind field particle properties, the drawing of wind …

Maritime Radar Terrain Echo Simulation Based On Dem And Sar, Yongfeng Suo, Shenhua Yang, Guoquan Chen, Zhuqiang Xiang

Journal of System Simulation

Abstract: Due to the huge amount of work required for terrain database building, the application of navigation radar simulation on the reflectivity of land object has been greatly limited. A novel radar simulation method is proposed based on the DEM(Digital Elevation Model) data and the same-band SAR(Synthetic Aperture Radar) reflection data. The target reflectance information is obtained, which is used as the basis for the surface radar reflectivity simulation. In combination with the radar equations, the surface reflectivity model of the navigation radar is established. Taking into account the elevation shielding relationship of the radar echo topography, an algorithm of …

Spatial Structure Optimization Of Natural Forest Based On Bee Colony-Particle Swarm Algorithm, Dongsheng Qing, Xiaofang Zhang, Jianjun Li, Guo Rui, Qiaoling Deng

Journal of System Simulation

Abstract: The natural forest spatial structure contains the spatial location information of the forest, which affects the growth, competition and stability of the forest development. Its optimization is a multi-objective programming problem. A bee colony particle swarm optimization (ABC-PSO) hybrid algorithm is proposed, which improves the initial particle generation mechanism, the number of follow bees and the circulation mechanism. The algorithm is applied to the multi-objective optimization of the spatial structure of natural forest. An optimization model which takes account of the tree distribution grid, tree size segmentation and tree competition is established. The simulation results show that the bee …

An Estimation Of Distribution Algorithm Based On Multiple Elites Sampling And Individuals Differential Search, Yu Fei, Ruifeng Wu, Wei Bo, Yinglong Zhang, Xuewen Xia

Journal of System Simulation

Abstract: An estimation distribution algorithm based on the multiple elites sampling and the individuals differential search (EDA-M/D) is proposed. In EDA-M/D, the elites carry out the sampling to generate the offspring independently and enhance the exploration. Meanwhile, the variance of the population distributionis selected to control the sampling radius. Thus, the target of the population can be gradually transited from exploration to exploitation. If the elite population stagnates, the nonentities will choose the mean value of the elites distribution μ and the population historical best solution as the two exemplars to execute a differential search operator, and then help the …

Multi-Uav 3d Formation Path Planning Based On Improved Artificial Potential Field, Haiyun Chen, Huazhou Chen, Liu Qiang

Journal of System Simulation

Abstract: Focusing on the GNRON (goal nonreachable with obstacles nearby), the local minima and chattering of the traditional artificial potential field method, the potential field functions are improved and analyzed to guarantee the goal is the global minimum. In the dynamic potential field, a mechanism of judging whether to fall into local minima is introduced, a method of “moving along the orientation of 90° of goal direction” is used to jump out of the local minima, and the path planning of multi-UAV formation, the synergistic obstacle avoidance and collision prevention are achieved. The path is optimized by applying the regression …

Simulation Analysis On Flexible Track Drilling Machine Based On Adams, Yanchao Zhang, Ting Wang, Danlong Song

Journal of System Simulation

Abstract: The three-dimensional model of the flexible track drilling machine is designed by the virtual prototyping technology. The model is imported into ADAMS (Automatic Dynamic Analysis of Mechanical Systems) software to carry out the kinematics and dynamic simulation analysis of its virtual prototype, and the rationality and feasibility of the system design are evaluated. Through the comparative analysis, the reasonable driving velocity and acceleration parameters of the hole making system are given. According to the analysis of the dynamic characteristics of the systems, the asymmetric driving problems in the system are found and the corresponding improvement scheme is put forward. …

Speech Control Scheme Design And Simulation For Uav Based On Hmm And Rnn, Zhou Nan, Jianliang Ai

Journal of System Simulation

Abstract: In order to simplify the operation and avoid the misoperation of UAVs, Based on Hidden Markov Model and Recurrent Neural Networks, a speech control scheme for UAVs is designed. In this scheme, HMM is used to train and recognize the speech command samples of UAVs. HMM is used to pick out the error commands, RNN is used to train the sets of UAVs commands, and the next command based on the training result is predicted. It is determined whether to execute or not by calculating the correlation between commands recognized by HMM and predicted by RNN. The simulation results …

Model Of Initial Spare Parts Configuration And Ordering Policy Optimization Based On Inventory State, Songshi Shao, Minzhi Ruan, Zhihua Zhang

Journal of System Simulation

Abstract: Rational planning of spare parts configuration project is an effective approach to improve the equipment availability and reduce the life cycle cost (LCC). First of all, the spare parts demand rate forecast model is constructed. According to the systemic analysis method, the spare parts support effectiveness evaluation targets system is built, and then, the initial spare parts configuration optimization method is researched. Aim to the consumption for partial repairable spare parts, the expected backorders function of the approximate Laplace demand distribution is given. Combining the (s-1, s) and (R, Q) inventory policy, the ordering model is established under the …

Analysis Of Aeroengine Vibration Signal, Pi Jun, Jiaze Chang, Guangcai Liu

Journal of System Simulation

Abstract: Aiming at the analysis of the vibration characteristics of aeroengine rotor, an improved blind source separation algorithm based on cumulant independent component analysis (ICA) is proposed. The new algorithm is used to separate the rotor vibration signal and identify the rotor fault types. The effectiveness of this algorithm is verified by the aeroengine rotor vibration signal simulation. Comparing with the existing algorithms based on second-order cumulants and high-order cumulants, the new method improves the performance index and the signal similarity coefficient. This algorithm is used to separate the vibration signal collected by the engine rotor platform and the rotor …

Research On Building Mechanism Model Simulation In Energy-Saving Control, Bai Yang, Decheng Yuan, Li Ling

Journal of System Simulation

Abstract: In the existing building system, the energy consumption is huge, the control system is complex, and the electricity cost is high. In order to reduce the cost of electricity, the mechanism model of the building is established for simulation. The accuracy of the model is verified by simulation to confirm the model applicability to the building system. Comparing the constant electricity price with the time-varying electricity price, the system under the model predictive control can response to the price change of electricity with time and can achieve the cost control and energy-saving.

Learning In The Machine: To Share Or Not To Share?, Jordan Ott, Erik Linstead, Nicholas Lahaye, Pierre Baldi

Engineering Faculty Articles and Research

Weight-sharing is one of the pillars behind Convolutional Neural Networks and their successes. However, in physical neural systems such as the brain, weight-sharing is implausible. This discrepancy raises the fundamental question of whether weight-sharing is necessary. If so, to which degree of precision? If not, what are the alternatives? The goal of this study is to investigate these questions, primarily through simulations where the weight-sharing assumption is relaxed. Taking inspiration from neural circuitry, we explore the use of Free Convolutional Networks and neurons with variable connection patterns. Using Free Convolutional Networks, we show that while weight-sharing is a pragmatic optimization …

Knowledge Infused Learning (K-Il): Towards Deep Incorporation Of Knowledge In Deep Learning, Ugur Kursuncu, Manas Gaur, Amit Sheth

Publications

Learning the underlying patterns in data goes beyondinstance-based generalization to external knowledge repre-sented in structured graphs or networks. Deep learning thatprimarily constitutes neural computing stream in AI hasshown significant advances in probabilistically learning la-tent patterns using a multi-layered network of computationalnodes (i.e., neurons/hidden units). Structured knowledge thatunderlies symbolic computing approaches and often supportsreasoning, has also seen significant growth in recent years,in the form of broad-based (e.g., DBPedia, Yago) and do-main, industry or application specific knowledge graphs. Acommon substrate with careful integration of the two willraise opportunities to develop neuro-symbolic learning ap-proaches for AI, where conceptual and probabilistic repre-sentations are combined. …

Research On Emergency Risk Decision Simulation Based On Multi-Agent And Prospect Theory, Wang Jian, Chenqi Situ, Shengqiang Yuan

Journal of System Simulation

Abstract: Focusing on the modeling and the simulation of emergency response risk decision that multi-sections involve in, a simulation model and simulation framework based on multi-agent and prospect theory are proposed. By introducing agent theory, the multi-agent architecture model of emergency risk decision is described and the decision agent are modelled. By introducing prospect theory, following the dynamic evolution of emergencies, the impact of the psychological changes of the decision-makers have on the decision results is studied. The multi-agent emergency risk decision simulation framework is designed and implemented. Taking the risk decision of a fire emergency in the petrochemical plants …

Rapid Simulation And Volume Rendering Of Electromagnetic Environment Based On Geographic Coordinate System, Yuguo Wu, Beibei Han

Journal of System Simulation

Abstract: Considering the earth's curvature, the spherical regular grid model is used to organize the electromagnetic field data. In order to reduce computational complexity of ITM model, the terrain reuse is proposed to improve the efficiency of the simulation. The Multithread and the terrain reuse are combined to improve the efficiency of the multi-radiation source. Considering that the traditional ray casting algorithm which takes the cube model as the bounding box cannot draw spherical regular grid data directly, a ray casting algorithm which uses the dome model as the bounding box is proposed. Experiments show that even considering the influence …

Research Of Link Acquisition Technology For Virtual-Reality Network, Liu Yuan, Xingbing Feng, Xiaofeng Wang, Zhaohong Deng

Journal of System Simulation

Abstract: Network simulation is an important foundation for the cyberspace shooting range, where the data acquisition and evaluation for the emulation network is its key link. Based on the emulation network formed by OpenStack, a distributed link data acquisition system for the diversified emulation links is constructed. The paper studies the collaborative acquisition technology and the efficient link data acquisition technology of 3 kinds of links, such as the virtual link in the host, the virtual link between the host and the virtual-reality link, and the evaluation technology based on the link data. Experiments show that the proposed method improves …

Anti-Dead-Zone Control For Two Flexible Links Space Robot With Integration Of Motion And Vibration, Xiaoqin Huang, Chen Li

Journal of System Simulation

Abstract: The angle tracking and flexible vibration suppression integrated control for the two flexible links free-floating space robot with joint torque output dead-zone and external disturbance are discussed. The hybrid trajectory concept with rigid motion and flexible mode is introduced, and an adaptive control scheme of the integral sliding mode neural network based on the integration of motion and vibration is proposed. In case the slope and boundary of dead-zone is uncertain and the upper kind of the optimal approximation error is unknown, the compensation term of the scheme can eliminate the effect, and ensures the robustness of the rigid …