Computer Engineering Commons^™

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 …

A Game Cheating Detection System Based On Petri Nets, Zheng Hong, Ye Cheng, Wenxuan Deng, Pan Li

Journal of System Simulation

Abstract: Game cheating endangers the normal cyber game seriously. The bottlenecks of the anti-cheating technology are the low efficiency and its too much dependence on the signature matching. Not relying on the signature matching, a highly efficient game cheating detection system is proposed, which models by process trees. This can save the storage space without affecting the detection results. The system is tested with the cheating softwares on the popular cyber game and the fusion efficiency of the update model is evaluated. The results show that the storage space reduction rate can reach about 60%, which means effectiveness and feasibility …

Optimization Simulation Of Feeder Airport Runway Structure For Pollutant Discharge Control, Jiang Bo, Yunfan Zhou, Chenglong Li, Zhang Hao

Journal of System Simulation

Abstract: Air pollutant discharge in the LTO (Landing and Take-off) cycle of the civil aviation transport is harmful to the ground personnel and the near-ground environment, which can be restrained primarily by reducing the ground taxi time. Considering the structure of the single-taxiway-single-runway in the common feeder airport, a method for calculating the aircraft ground taxi time is presented. Based on this method, an evaluation index of the pollutants is proposed and an assessment model of aircraft pollutants emission in feeder airport is established. Taking a feeder airport as an example, the taxiway crossing position with the smallest pollutant evaluation …

How Data Became Part Of New Orleans’ Dna During The Katrina Recovery, Lamar Gardere, Allison Plyer, Denice Ross

New England Journal of Public Policy

Data intermediaries have a symbiotic relationship with government as the source of most of their information. The open-data movement in government and development of software-as-a-service technologies shaped the data landscape after Katrina. Through relationships and talent transfers with The Data Center, the City of New Orleans went from having its chief technology officer in federal prison and its data systems in shambles to being a nationally recognized leader in open and accountable government. To be effective during disasters, an intermediary should be (1) in place and widely respected before the event, (2) ready to respond immediately after the event and …

An Implementation Of Firmware For Non-Invasive Charge-Coupled Brain Stimulation, Elizabeth Staley, Harsha Ganegoda

Research Horizons Day Posters

No abstract provided.

Novel Approaches For Evaluating The Performance Of Antenna Arrays For Massive Mimo Systems, Abbas Al-Wahhamy

Theses and Dissertations

Massive Multiple-Input Multiple-Output (MIMO) is a key promising technology for 5G networks that allows a significant increase in spectral and energy efficiency without increasing the spectrum and/or the number of cell sites. However, the computational time and resources required to rigorously analyze the capacity offered by a base station equipped with a large number of antenna elements increases with the increase of the number of antenna elements. A novel approach is presented for modeling large microstrip antenna arrays in base stations of massive MIMO systems. The approach subdivides an M×N array into columns, rows, rectangular, or square subarrays, each consisting …

Composition Of Atomic-Obligation Security Policies, Yan Cao Albright

USF Tampa Graduate Theses and Dissertations

Existing security-policy specification languages allow users to specify obligations, but open challenges remain in the composition of complex obligations, including effective approaches for resolving conflicts between policies and obligations and allowing policies to react to the obligations of other policies.

An atomic obligation requires that either all or none of the included actions are executed. Atomicity can be extended to include the decision to permit or deny an event after the obligation executes. For many practical policies, obligation atomicity is necessary for correctness. Executing only the parts of such an obligation violates its atomicity which can lead to an undesirable …

The Design And Development Of A Wrist-Hand Orthosis, Amber Gatto

USF Tampa Graduate Theses and Dissertations

Individuals with an incomplete C5-C7 spinal cord injury (SCI) lose grasping abilities but wrist function is almost universally retained. Most rehabilitation techniques apply the tenodesis effect, however, current tenodesis wrist-hand orthoses (WHOs) engage only the thumb and index finger, meaning that only 20% of activities of daily living (ADLs) can be completed.

This study tested the feasibility of a student-designed powered WHO by testing the device on healthy subjects to see if they could complete a variety of ADLs. A simulation software was then used to analyze wrist, thumb, and index finger joint angles. Additionally, an Assistive Technology Survey was …

Low Latency Bearing Fault Detection Of Direct-Drive Wind Turbines Using Stator Current, Samrat Nath, Jingxian Wu, Yue Zhao, Wei Qiao

Department of Electrical and Computer Engineering: Faculty Publications

Low latency change detection aims to minimize the detection delay of an abrupt change in probability distributions of a random process, subject to certain performance constraints such as the probability of false alarm (PFA). In this paper, we study the low latency detection of bearing faults of direct-drive wind turbines (WT), by analyzing the statistical behaviors of stator currents generated by the WT in real-time. It is discovered that the presence of fault will affect the statistical distribution of WT stator current amplitude at certain frequencies. Since the signature of a fault can appear in one of the multiple possible …

Bim For Bridges And Structures Pooled Fund Initiative, Julie Rivera, Connor Christian

Purdue Road School

The BIM for Bridges and Structures initiative, also known as TPF-5(372), is a transportation pooled fund project that is a collaborative effort of 20 states, FHWA, and the AASHTO Committee on Bridges and Structures. The pooled fund objective is to develop an open, national standard for exchanging information necessary for the design, fabrication, and construction of bridges and structures in the United States. The presentation will provide an overview of the project and explain ways in which stakeholders can get involved.

Understanding And Optimizing Flash-Based Key-Value Systems In Data Centers, Yichen Jia

LSU Doctoral Dissertations

Flash-based key-value systems are widely deployed in today’s data centers for providing high-speed data processing services. These systems deploy flash-friendly data structures, such as slab and Log Structured Merge(LSM) tree, on flash-based Solid State Drives(SSDs) and provide efficient solutions in caching and storage scenarios. With the rapid evolution of data centers, there appear plenty of challenges and opportunities for future optimizations.

In this dissertation, we focus on understanding and optimizing flash-based key-value systems from the perspective of workloads, software, and hardware as data centers evolve. We first propose an on-line compression scheme, called SlimCache, considering the unique characteristics of key-value …

Using Supercomputers To Control Multiple Robots, Andrew Roberts, Jeremy Evert

Student Research

Supercomputers have been a key enabler to many technological advancements. The pipeline to develop capable supercomputer users is years long. Getting started with a supercomputer can be difficult. As a part of the XSEDE EMPOWER Learner program, this research focuses super-computer user development. SWOSU students do not have working code for many of the training modules available for learning supercomputing. This research details the development of these codes based on materials provided by the Nation-al Science Foundation, Shodor Foundation, and National Center for Supercomputing Applications. The result of this research is a better understand-ing of supercomputing training and more tools …

Super Education For Supercomputers, Ezgi Gursel, Jeremy Evert

Student Research

Supercomputing (1 OOX more powerful than a desktop) allows organizations to solve complex problems that are not easily studied in any other way (ex. Blue Waters to simulate the known universe since the beginning of time for the design of the James Webb telescope). Producing qualified individuals to take advantage of the growing number of supercomputing jobs is a constant struggle. This poster provides an overview of education in supercomputing, explains how training occurs, and describes some of the key players working to educate a taskforce to deal with these highly complex machines.

Handheld Data Analyzer, Nicholas Shade, Jake Herman, Doug Kern, Graham Hazlett, Anita Richardson

ENGS 89/90 Reports

The goal of this project is to design and build a handheld data analyzer prototype paired with an iPad app that our sponsor can further develop into a marketable product. The system should allow technicians to easily collect vibration data from IEPE accelerometers, inspect the data, and upload the reading to our sponsor’s database system for further analysis.

Dashboard-Mounted Driver Monitoring System, Daniel Lein, Prahlad Sarma, William Roussell, Nathan Nuñez, Elvis Manzanares

ENGS 89/90 Reports

The objective of this project is to deliver safe DMS hardware and interfacing/preprocessing software on which Toyota can run its drowsiness detection neural net. The system shall: securely house all necessary imaging, electronic, and computer hardware to output facial recognition data to the car’s computer, without data input from any other car system; obscure less than 10% of the driver’s field of view out of a standard windshield; be able to capture and process images such that the image classification neural net recognize the images, meeting the top-1 benchmark accuracy statistic across static and dynamic car-cabin lighting conditions; and meet …

Simultaneous Localization And Mapping Analysis, Jacob Miller, Kurtis Clark, Jeremy Evert

Student Research

Objectives

• Simulate virtual robot for test and analysis
• Analyze SLAM solutions using ROS
• Assemble a functional Turtlebot
• Emphasize projects related to current research trajectories for NASA, and general robotics applications

Robot Simulation Analysis, Kurtis Clark, Jacob Miller, Jeremy Evert

Student Research

Objectives

• Build a tutorial targeted to Middle School and High School Students to get ROS running on a Virtual Machine
• Make ROS and it's simulations approachable to middle school and high school students.

Innovation In Pedagogy And Technology Symposium, 2019: Selected Conference Proceedings, University Of Nebraska Online, University Of Nebraska Information Technology Services

Zea E-Books Collection

Advancing Technology in Education at the University of Nebraska, May 7, 2019

Welcome Address • Susan Fritz, Ph.D., Executive Vice President and Provost, University of Nebraska 6

Opening Remarks • Mary Niemiec, Associate Vice President for Digital Education, Director of University of Nebraska Online 6

Keynote Presentation: Shaping the Next Generation of Higher Education • Bryan Alexander, Ph.D. 6

Featured Extended Presentation: Redesigning Courses & Determining Effectiveness Through Research • Tanya Joosten, University of Wisconsin-Milwaukee (UWM), Erin Blankenship, Ph.D. (UNL), Ella Burnham (UNL), Nate Eidem, Ph.D. (UNK), Marnie Imhoff (UNMC), Linsey Donner (UNMC), Ellie Miller (UNMC) 7

5 Ways to …

Integrating The 1st Person View And The 3rd Person View Using A Connected Vr-Mr System For Pilot Training, Chang-Geun Oh Ph.D., Myunghoon Oh Ph.D.

National Training Aircraft Symposium (NTAS)

Many virtual reality (VR)-based flight simulation programs provide pilots the enhanced reality from the 1^st person-view to make themselves immersed in the cockpit. Using the VR simulations, pilots can take flight training in many challenging situations that are hard to create in real environments due to its natural entropy and safety concerns such as severe crosswind or engine fire. Mixed reality (MR) technology provides three-dimensional graphics so that users can effectively see all 360 degree-vertical and horizontal aspects of an object while they freely move around to see the graphics maintaining the consciousness of real space. Flight instructors may …

Validation Framework For Autonomous Aerial Vehicles, Mustafa Akbas Ph.D.

National Training Aircraft Symposium (NTAS)

Autonomous aerial vehicles (AAV) have the potential to have market disruptions for various industries such as ground delivery and aerial transportation. Hence, the USAF has called for increased level of autonomy and rapid progress is being made in artificial intelligence (AI) engines, complex and non-deterministic system components, which are at the core of the autonomous aerial platforms. Traditional testing and validation methods fall short of satisfying the requirement of testing such complex systems. Therefore, to achieve highly or fully autonomous capabilities, a major leap forward in the validation is required. Otherwise, the full capabilities of autonomy will not be realized. …

W-Gun: Whale Optimization For Energy And Delay-Centric Green Underwater Networks, Rajkumar Singh Rathore, Houbing Song, Suman Sangwan, Sukriti Mazumdar, Omprakash Kaiwartya, Kabita Adhikari, Rupak Kharel

Publications

Underwater sensor networks (UWSNs) have witnessed significant R&D attention in both academia and industry due to their growing application domains, such as border security, freight via sea or river, natural petroleum production and the fishing industry. Considering the deep underwater-oriented access constraints, energy-centric communication for the lifetime maximization of tiny sensor nodes in UWSNs is one of the key research themes in this domain. Existing literature on green UWSNs are majorly adapted from the existing techniques in traditional wireless sensor network relying on geolocation and the quality of service-centric underwater relay node selection, without paying much attention to the dynamic …