Engineering Commons^™

Computation Offloading Strategy Based On Stackelberg Game And Drl, Xianwei Zhou, Qixu Gong, Songsen Yu

Journal of System Simulation

Abstract: To achieve the optimal computation offloading strategy for two kinds of MEC users in 5G hybrid private network, Stackelberg game is used to build the model of the competition for MEC server resources of two kinds of users, andthe strategies of complete information game and partially incomplete information game are researched respectively. It is proved that there is only one Nash equilibrium solution in the complete information scenario. In the incomplete information scenario, the environment is modeled as POMDP, and a two-stage deep reinforcement learning(TSDRL) is proposed to obtain the optimal computation offloading strategy. Simulation results show the proposed …

A Highly Efficient Broadband Multi-Functional Metaplate, Azhar Javed Satti, Muhammad Ashar Naveed, Isma Javed, Nasir Mahmood, Muhammad Zubair, Muhammad Qasim Mehmood, Yehia Massoud

Department of Electrical and Computer Engineering: Faculty Publications

Due to the considerable potential of ultra-compact and highly integrated meta-optics, multi-functional metasurfaces have attracted great attention. The mergence of nanoimprinting and holography is one of the fascinating study areas for image display and information masking in meta-devices. However, existing methods rely on layering and enclosing, where many resonators combine various functions effectively at the expense of efficiency, design complication, and complex fabrication. To overcome these limitations, a novel technique for a tri-operational metasurface has been suggested by merging PB phase-based helicity-multiplexing and Malus's law of intensity modulation. To the best of our knowledge, this technique resolves the extreme-mapping issue …

Hangprinter For Large Scale Additive Manufacturing Using Fused Particle Fabrication With Recycled Plastic And Continuous Feeding, Ravneet S. Rattan, Nathan Nauta, Alessia Romani, Joshua Pearce

Electrical and Computer Engineering Publications

The life cycle of plastic is a key source of carbon emissions. Yet, global plastics production has quadrupled in 40 years and only 9 % has been recycled. If these trends continue, carbon emissions from plastic wastes would reach 15 % of global carbon budgets by 2050. An approach to reducing plastic waste is to use distributed recycling for additive manufacturing (DRAM) where virgin plastic products are replaced by locally manufactured recycled plastic products that have no transportation-related carbon emissions. Unfortunately, the design of most 3-D printers forces an increase in the machine cost to expand for recycling plastic at …

Machine Learning Applications In Malware Classification: A Metaanalysis Literature Review, Tjada Nelson, Austin O'Brien, Cherie Noteboom

Research & Publications

With a text mining and bibliometrics approach, this study reviews the literature on the evolution of malware classification using machine learning. This work takes literature from 2008 to 2022 on the subject of using machine learning for malware classification to understand the impact of this technology on malware classification. Throughout this study, we seek to answer three main research questions: RQ1: Is the application of machine learning for malware classification growing? RQ2: What is the most common machine-learning application for malware classification? RQ3: What are the outcomes of the most common machine learning applications? The analysis of 2186 articles resulting …

Stand-Up Comedy Visualized, Berna Yenidogan

Dissertations, Theses, and Capstone Projects

Stand-up comedy has become an increasingly popular form of comedy in the recent years and comedians reach audiences beyond the halls they are performing through streaming services, podcasts and social media. While comedic performances are typically judged by how 'funny' they are, which could be proxied by the frequency and intensity of laughs through the performance, comedians also explore untapped social issues and provoke conversation, especially in this age where interaction with artists goes beyond their act. It is easy to see commonalities in the topics addressed in comedians’ work such as relationships, race and politics.This project provides an interactive …

Resource Management In Mobile Edge Computing For Compute-Intensive Application, Xiaojie Zhang

Dissertations, Theses, and Capstone Projects

With current and future mobile applications (e.g., healthcare, connected vehicles, and smart grids) becoming increasingly compute-intensive for many mission-critical use cases, the energy and computing capacities of embedded mobile devices are proving to be insufficient to handle all in-device computation. To address the energy and computing shortages of mobile devices, mobile edge computing (MEC) has emerged as a major distributed computing paradigm. Compared to traditional cloud-based computing, MEC integrates network control, distributed computing, and storage to customizable, fast, reliable, and secure edge services that are closer to the user and data sites. However, the diversity of applications and a variety …

Drone Detection Using Yolov5, Burchan Aydin, Subroto Singha

Faculty Publications

The rapidly increasing number of drones in the national airspace, including those for recreational and commercial applications, has raised concerns regarding misuse. Autonomous drone detection systems offer a probable solution to overcoming the issue of potential drone misuse, such as drug smuggling, violating people’s privacy, etc. Detecting drones can be difficult, due to similar objects in the sky, such as airplanes and birds. In addition, automated drone detection systems need to be trained with ample amounts of data to provide high accuracy. Real-time detection is also necessary, but this requires highly configured devices such as a graphical processing unit (GPU). …

Ads-B Classification Using Multivariate Long Short-Term Memory–Fully Convolutional Networks And Data Reduction Techniques, Sarah Bolton, Richard Dill, Michael R. Grimaila, Douglas Hodson

Faculty Publications

Researchers typically increase training data to improve neural net predictive capabilities, but this method is infeasible when data or compute resources are limited. This paper extends previous research that used long short-term memory–fully convolutional networks to identify aircraft engine types from publicly available automatic dependent surveillance-broadcast (ADS-B) data. This research designs two experiments that vary the amount of training data samples and input features to determine the impact on the predictive power of the ADS-B classification model. The first experiment varies the number of training data observations from a limited feature set and results in 83.9% accuracy (within 10% of …

Learning Relation Prototype From Unlabeled Texts For Long-Tail Relation Extraction, Yixin Cao, Jun Kuang, Ming Gao, Aoying Zhou, Yonggang Wen, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Relation Extraction (RE) is a vital step to complete Knowledge Graph (KG) by extracting entity relations from texts. However, it usually suffers from the long-tail issue. The training data mainly concentrates on a few types of relations, leading to the lack of sufficient annotations for the remaining types of relations. In this paper, we propose a general approach to learn relation prototypes from unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient training data. We learn relation prototypes as an implicit factor between entities, which reflects the meanings of relations as well …

Towards Machine Learning-Based Fpga Backend Flow: Challenges And Opportunities, Imran Taj, Umer Farooq

All Works

Field-Programmable Gate Array (FPGA) is at the core of System on Chip (SoC) design across various Industry 5.0 digital systems—healthcare devices, farming equipment, autonomous vehicles and aerospace gear to name a few. Given that pre-silicon verification using Computer Aided Design (CAD) accounts for about 70% of the time and money spent on the design of modern digital systems, this paper summarizes the machine learning (ML)-oriented efforts in different FPGA CAD design steps. With the recent breakthrough of machine learning, FPGA CAD tasks—high-level synthesis (HLS), logic synthesis, placement and routing—are seeing a renewed interest in their respective decision-making steps. We focus …

Skeleton-Based Hand Gesture Recognition Using Data-Level Fusion, Oluwaleke Yusuf

Theses and Dissertations

Hand Gesture Recognition (HGR) is a form of perceptual computing that allows artificial systems to capture and interpret human gestures. HGR has applications in human-machine interaction, virtual reality, augmented reality, and human behavior analysis. The human hand can assume a near-infinite number of poses and orientations to form myriad gestures, thus increasing the difficulty of the HGR task.

The hand skeleton of connected joints effectively describes the hand’s geometric shape and thus contains richer semantic gesture information while eliminating noise from individual differences in physical hand characteristics. The efficacy and computational efficiency of skeleton-based HGR frameworks can be significantly enhanced …

A Novel Insect And Pest Identification Model Based On A Weighted Multipath Convolutional Neural Network And Generative Adversarial Network, Vinita Abhishek Gupta, M.V. Padmavati, Ravi R. Saxena, Raunak Kumar Tamrakar

Karbala International Journal of Modern Science

Timely identification of insects and their management play a significant role in sustainable agriculture development. The proposed hybrid model integrates a weighted multipath convolutional neural network and generative adversarial network to identify insects efficiently. To address the shortcomings of single-path networks, this novel model takes input from numerous iterations of the same image to learn more specific features. To avoid redundancy produced due to multipath, weights have been assigned to each path. For Xie2 dataset, the model shows 3.75%, 2.74%, 1.54%, 1.76%, 1.76%, 2.74 %, and 2.14% performance improvement from AlexNet, ResNet50, ResNet101, GoogleNet, VGG-16, VGG-19, and simple CNN respectively. …

Completeness Of Nominal Props, Samuel Balco, Alexander Kurz

Engineering Faculty Articles and Research

We introduce nominal string diagrams as string diagrams internal in the category of nominal sets. This leads us to define nominal PROPs and nominal monoidal theories. We show that the categories of ordinary PROPs and nominal PROPs are equivalent. This equivalence is then extended to symmetric monoidal theories and nominal monoidal theories, which allows us to transfer completeness results between ordinary and nominal calculi for string diagrams.

Integrated Organizational Machine Learning For Aviation Flight Data, Michael J. Pritchard, Paul Thomas, Eric Webb, Jon Martin, Austin Walden

National Training Aircraft Symposium (NTAS)

An increased availability of data and computing power has allowed organizations to apply machine learning techniques to various fleet monitoring activities. Additionally, our ability to acquire aircraft data has increased due to the miniaturization of small form factor computing machines. Aircraft data collection processes contain many data features in the form of multivariate time-series (continuous, discrete, categorical, etc.) which can be used to train machine learning models. Yet, three major challenges still face many flight organizations 1) integration and automation of data collection frameworks, 2) data cleanup and preparation, and 3) embedded machine learning framework. Data cleanup and preparation has …

Artificial Intelligence For Automated Detection Of Large Mammals Creates Path To Upscale Drone Surveys, Javier Lenzi, Andrew Barnas, Abdelrahman A. Elsaid, Travis Desell, Robert F. Rockwell, Susan N. Ellis-Felege

Biology Faculty Publications

Imagery from drones is becoming common in wildlife research and management, but processing data efficiently remains a challenge. We developed a methodology for training a convolutional neural network model on large-scale mosaic imagery to detect and count caribou (Rangifer tarandus), compare model performance with an experienced observer and a group of naïve observers, and discuss the use of aerial imagery and automated methods for large mammal surveys. Combining images taken at 75 m and 120 m above ground level, a faster region-based convolutional neural network (Faster-RCNN) model was trained in using annotated imagery with the labels: “adult …

Research On Mixed Flow Line Balancing And Scheduling Optimization With Multiple Constraints, Zhenping Li, Ying Shi, Lingyun Wu

Journal of System Simulation

Abstract: Aiming at the phenomena of unbalanced load between stations and product accumulation caused by unreasonable design of mixed flow line in G enterprise, based on the matching relationship between processes and stations, cycle time, process priority and other constraint, with the objectives of reducing the number of stations, balancing the workload between stations, and reducing the products waiting time, a multi-objective mixed integer programming model for mixed flow line balance and product scheduling problem is established. A hierarchical algorithm and a hybrid heuristic algorithm are designed respectively; the accuracy of the hierarchical algorithm is verified by small-scale …

Research On Modeling And Simulation Of Application Efficiency Of Tactical Medical Equipment, Guowei Lu, Xueqiang Tao, Deguang Duan, Hao Li, Zerui Zhang, En Chen

Journal of System Simulation

Abstract: In view of the lack of effective modeling and simulation means for the current research on the application efficiency of tactical medical treatment equipment in our army, a modeling and simulation research framework for the application effectiveness of equipment through the wounded model, equipment model and evaluation model is constructed. Based on the multi-agent method in Anylogic8.7.0 modeling and simulation platform, the casualty generation and its circulation process among medical treatment equipment are simulated. In the context of a tactical medical exercis, the overall support capability of medical treatment equipment is evaluated scientifically and quantitatively, and the key equipment …

Development Opportunities And Application Prospects Of Aero-Engine Simulation Technology Under Digital Transformation, Jianguo Cao

Journal of System Simulation

Abstract: The development of China's social economy and the improvement of its national defense capability in the new era put forward higher requirements for the development of aero-engines. It is urgent to promote the digital transformation of aero-engines in order to achieve coordinated, agile and efficient aero-engine development. Based on the current research and development of aero-engine in China, this paper clarifies the new connotation of "speediness and efficiency, accurate mapping, comprehensive coverage, and dynamic prediction" given by the development of emerging cutting-edge technologies to aero-engine simulation technology, as well as the new technical features of "spatio-temporal ubiquity, data driven, …

Research On Vr Experience Comfort Based On Motion Perception, Wei Quan, Chao Wang, Xuena Geng, Cheng Han

Journal of System Simulation

Abstract: A VR video comfort evaluation model based on motion perception is proposed for viewers who will feel discomfort such as vertigo and nausea after a virtual reality (VR) experience. By performing dense optical flow estimation on stereoscopic VR video and calculating the video frame velocity matrix by analyzing the horizontal and vertical motions in the scene, the frame acceleration feature extraction methods based on frame difference method and based on time domain are proposed. Taking the extracted velocity, acceleration and other motions features as input, a model is established using the support vector regression algorithm, and VR video experience …

Research On Intelligent Prediction Method Of Wargaming Air Mission, Dayong Zhang, Jingyu Yang, Xi Wu

Journal of System Simulation

Abstract: The efficient, accurate and automatic judgment of the combat mission or intention of the enemy's air targets in the battlefield is the basis of situation awareness and the key to the allocation of auxiliary combat resources. Combined with the calculation characteristics of feed forward deep neural network and long-term and short-term memory network model, two targeted basic index learners are designed, and then the weighted combination is carried out according to the cross entropy of the basic index, which can be used to further train the evaluation index of the learner. It can not only effectively prevent the model …

Research On Intelligent Optimization Method Of Combat Sos Based On Gabc Algorithm, Hucheng Zhang, Jingyu Yang

Journal of System Simulation

Abstract: In order to solve the problem that exploratory simulation can not traverse the solution space quickly, and provide the auxiliary decision-making scheme in real time, a genetic algorithm based on classifier is proposed. The framework of simulation optimization method based on the algorithm is established. It can find the optimal solution according to the dynamic changes of key factors and decision targets of the system, which is suitable for such as seeking the best efficiency-cost ratio scheme and the optimization of the optimal power deployment and other systems. Based on the simulation bed system of the National Defense …

Chameleon Swarm Algorithm For Segmental Variation Learning Of Population And S-Type Weight, Damin Zhang, Yi Wang, Linna Zhang

Journal of System Simulation

Abstract: It is the best choice for intelligent algorithms to be applied to specific fields to explore strong searching ability, good reliability and stability.In this paper, aiming at the defects of chameleon swarm algorithm, such as unstable solution, low convergence accuracy and unbalanced search and development, a chameleon swarm algorithm (RMSCSA) based on population diversity segmental mutation learning and S-type weight is proposed. The refraction mirror learning strategy (RML) is introduced to make the chameleon more consistent with the observation in nature and enhance its diversity. The introduction of segmental variation of population diversity can keep the individuals with poor …

Large-Scale Multi-Objective Natural Computation Based On Dimensionality Reduction And Clustering, Weidong Ji, Yuqi Yue, Xu Wang, Ping Lin

Journal of System Simulation

Abstract: In multi-objective optimization problems, as the number of decision variables increases, the optimization ability decreases significantly. To solve "dimension disaster", a large-scale multi-objective natural computation method based on dimensionality reduction and clustering is proposed. The decision variables are optimized by locally linear embedding(LLE) to obtain the representation of high-dimensional variables in the low-dimensional space, then the individuals are grouped through K-means to select the appropriate guide individuals for the population to strengthen the convergence and diversity. To verify the effectiveness, the method is applied to the multi-objective particle swarm optimization algorithm and the non-dominated sorting genetic algorithm. The convergence …

Dynamic Risk Assessment Of Vocs Cross Regional Flow Based On Petri Nets, Guangqiu Huang, He Wang

Journal of System Simulation

Abstract: In order to evaluate the interaction between regions due to the cross regional flow of VOCs(volatile organic compounds) under polluted weather, a dynamic risk assessment method of cross regional flow of VOCs is proposed by using Petri net modeling method. The migration paths of VOCs between multiple potential pollution sources and contaminated areas are determined by HYSPLIT model, and the relationship between each migration path is described by Petri net; the dynamic risk assessment method is defined, and the calculation of dynamic risk is integrated into the operation of functional Petri net; through case analysis, the dynamic risk assessment …

Simulation-Based Adaptive Dynamic Scheduling For Bi-Objective Parallel Multi-Processor Open Shop, Yarong Chen, Shuchen Guan, Chengjun Huang, Lixia Zhu, Fuhder Chou

Journal of System Simulation

Abstract: Aiming at the parallel multi-processor open shop scheduling problem with uncertain job's release time,processing time and urgent jobs, an adaptive dynamic method integrating FlexSim simulation model and NSGA-Ⅱ algorithm is designed to optimize the bi-objectives of TWC(total weighted completion time) and TWT(total weighted tardiness). By using the FlexSim simulation model, this method determines the adaptive scheduling cycle according to the dynamic workload of the open shop, and conducts right-shift rescheduling to the urgent jobs. NSGA-Ⅱ algorithm is used to generate the bi-objective optimization scheduling scheme. Experimental results of a grain sorting shop show that compared with the rule-based real-time …

Research On System Of Virtual-Reality Fusion And Inquiry-Based Learning, Yongning Zhu, Zeru Lou, Tianxiang Wu, Jianmin Wang

Journal of System Simulation

Abstract: With the increasing interest in personalized and self-motivated education, emphasizing active learning and practical experiences, inquiry-based learning (IBL) is attracting interest in education. Considering the requirement for inquiry-based education, a framework of full process inquiry-based learning environment in the real-virtual worlds is designed. As an example, a mixed-reality chemical experiment system is developed. The metadata including user behavior data, interactive suite status and interactive interface status is collected through physical sensing. By mapping real-world status to the virtual world avatar, virtual experiments are simulated with computational dynamic solvers and real-time rendering. The generated images are sent back to the …

Knn Fault Detection Based On Reconstruction Error And Multi-Block Modeling Strategy, Jing Zheng, Weili Xiong, Xiaodong Wu

Journal of System Simulation

Abstract: For the fault monitoring algorithm based on k-nearest neighbor (kNN), the abnormal information that caused the fault is easy to be overwhelmed by the normal operating condition information, which leads to the problem of untimely fault detection and low alarm rate. A kNN fault monitoring method based on reconstruction error is proposed using auto-encoder and multi-block modeling strategy. The method uses the normal working condition data set to train the auto-encoder model, and extracts the reconstruction error based on the model to solve the problem that abnormal information is easy to be overwhelmed. Further considering the fault characteristics such …

Uniform Experimental Design With Constrained Region Based On Fruit Fly Algorithm, Jiawei Zhou, Xin Du, Youcong Ni, Hu Zhang, Hao Zhang, Haoran Ni, Feng Wang

Journal of System Simulation

Abstract: To solve the problems that existing two-phase differential evolutionary algorithms still have poor diversity of population distribution and weak local search ability in solving uniform designs in constrained experimental region, a new two-phase fruit fly optimization algorithm (ToPFOA) based on uniform experimental design is proposed. In the first stage, fruit fly search strategy combined with differential operator, K-means clustering and external document updating the centers of clusters is used todynamically improve distribution diversity of population in constrained region. In the second stage, a new fruit fly operator is designed to improve local search ability in constrained region. …

Drosophila Retina Simulation System And The Emergence Of Orientation Selectivity, Ziyu Liu, Yiran Zhuo, Zhuoyi Song

Journal of System Simulation

Abstract: To investigate the biophysical mechanisms underlying the Drosophila retinal computations, a piece of simulation software is constructed. By constructing the connectivity of the optical structure of the Drosophila compound eye with the neural network and retinal neuronal information encoding processes,, the retinal transformation from the light to the electrical signals is simulated. The photo-transduction model is optimized by a stochastic process. The generating mechanism of orientation selectivity (OS) is explored in the Drosophila retina's output neurons through a simulation system. Experiments show that with comparable simulation accuracy, the simulation speed increases by 40 times. The software can now be …

Research On Multiple Filter Signal Compensation For Washout Algorithm Optimization Of Flight Simulator, Weichao Liu, Hui Wang

Journal of System Simulation

Abstract: Aiming at the defects of signal loss and poor adaptability of the classical washout algorithm when applied to flight simulator, an optimization scheme of washing algorithm based on multiple filtering signal compensation is proposed. Analyzing the lost signal in classical washout algorithm, intercepting the lost signals to the depth filter with depth filtering strategy, basing on human perception errors and platform movement margin, after multiple filtering signal to certain proportion respectively compensation to the three channel of washout algorithm to achieve the maximum reduction of signal loss, thus reducing human perception error. The classical washing algorithm and the improved …