Computer Engineering Commons^™

Machine Learning For Electronic Design Automation: Specification Mining And High-Level Synthesis, Md Rubel Ahmed

USF Tampa Graduate Theses and Dissertations

The rapid growth of complex system-on-chip (SoC) designs has presented unprecedented opportunities and challenges in electronic design automation (EDA). This dissertation explores two facets of electronic design automation: message flow specification mining using data mining and natural language processing (NLP) and high-level synthesis (HLS) acceleration using different machine learning (ML) methods. It also discusses an ML model co-optimization method for energy-efficient hardware implementation.

Effective SoC design validation relies heavily on message flow specifications. This dissertation presents an efficient technique for synthesizing finite state automaton (FSA) models from SoC execution traces. The synthesized models can provide valuable insights into the on-chip …

Room Temperature Two-Dimensional Electron Gas Scattering Time, Effective Mass, And Mobility Parameters In AlXGa1−XN/Gan Heterostructures (0.07 ≤ X ≤ 0.42), Sean Knight, Steffen Richter, Alexis Papamichail, Philipp Kühne, Nerijus Armakavicius, Shiqi Guo, Axel R. Persson, Vallery Stanishev, Viktor Rindert, Per O. Å. Persson, Plamen P. Paskov, Mathias Schubert, Vanya Darakchieva

Department of Electrical and Computer Engineering: Faculty Publications

Al_xGa_1-xN/GaN high-electron-mobility transistor (HEMT) structures are key components in electronic devices operating at gigahertz or higher frequencies. In order to optimize such HEMT structures, understanding their electronic response at high frequencies and room temperature is required. Here, we present a study of the room temperature free charge carrier properties of the two-dimensional electron gas (2DEG) in HEMT structures with varying Al content in the Al_xGa_1-xN barrier layers between x = 0:07 and x = 0:42. We discuss and compare 2DEG sheet density, mobility, effective mass, sheet resistance, and scattering times, …

Six-Degree-Of-Freedom Optimal Feedback Control Of Pinpoint Landing Using Deep Neural Networks, Omkar S. Mulekar, Hancheol Cho, Riccardo Bevilacqua

Student Works

Machine learning regression techniques have shown success at feedback control to perform near-optimal pinpoint landings for low fidelity formulations (e.g. 3 degree-of-freedom). Trajectories from these low-fidelity landing formulations have been used in imitation learning techniques to train deep neural network policies to replicate these optimal landings in closed loop. This study details the development of a near-optimal, neural network feedback controller for a 6 degree-of-freedom pinpoint landing system. To model disturbances, the problem is cast as either a multi-phase optimal control problem or a triple single-phase optimal control problem to generate examples of optimal control through the presence of disturbances. …

Study On Debinding And Sintering Conditions In Extrusion-Based Additive Manufacturing Of 316l And 316l + Cu, Jean-François Silvain, Daniel Lincoln Gifford, Sébastien Fourcade, Laurent Cuzacq, Jean-Luc Grosseau-Poussard, Catherine Debiemme-Chouvy, Nicolas Tessier Doyen, Yongfeng Lu

Department of Electrical and Computer Engineering: Faculty Publications

This study investigates the use of a methylcellulose binder in extrusion additive manufacturing of 316L as an alternative to common wax-based binders. Various quantities of copper (Cu) powder were also added in the paste composition to attempt to reduce the sintering temperature by promoting persistent liquid phase sintering. Debinding experiments were conducted under different temperatures and dwell times using argon (Ar), Ar/5%H₂, and Ar/1%O₂ atmospheres. Debinding reduced carbon (C) content to 0.032 wt.% by using a two-step debinding process of Ar/5%H₂ and Ar/1%O₂ thermal treatments. Using this debinding process, sintering was conducted at 1200 ^{o …}

An Ontology Design Pattern For Representing Causality, Utkarshani Jaimini, Cory Henson, Amit Sheth

Publications

The causal pattern is a proposed ontology design pattern for representing the structure of causal relations in a knowledge graph. This pattern is grounded in the concepts defined and used by the CausalAI community i.e., Causal Bayesian Networks and do-calculus. Specifically, the pattern models three primary concepts: (1) causal relations, (2) causal event roles, and (3) causal effect weights. Two use cases involving a sprinkler system and asthma patients are provided along with their relevant competency questions.

Machine Learning Applications And Sustainable Development, Vishnu Pendyala

Open Educational Resources

This presentation, "Machine Learning Applications and Sustainable Development," explores the intersection of machine learning and its impact on privacy, equity, and societal well-being. It delves into the potential for re-identification of "anonymized" data through various techniques like k-anonymity, L-diversity, and the vulnerabilities of large language models, illustrating these concepts with real-world examples such as the AOL search data, Netflix Prize dataset, and Strava's fitness tracking. The presentation also discusses solutions to enhance data privacy, including differential privacy and the emerging field of machine unlearning, highlighting their applications and limitations. Finally, it addresses the broader implications for civil rights and ethical …

Bridging Domain Gaps For Cross-Spectrum And Long-Range Face Recognition Using Domain Adaptive Machine Learning, Cedric Armel Nimpa Fondje

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Face recognition technology has witnessed significant advancements in recent decades, enabling its widespread adoption in various applications such as security, surveillance, and biometrics applications. However, one of the primary challenges faced by existing face recognition systems is their limited performance when presented with images from different modalities or domains( such as infrared to visible, long range to close range, nighttime to daytime, profile to f rontal, etc.) Additionally, advancements in camera sensors, analytics beyond the visible spectrum, and the increasing size of cross-modal datasets have led to a particular interest in cross-modal learning for face recognition in the biometrics and …

Custom Led Dashboard Integration For The Cal Poly Racing Team, Josue Hernandez

Computer Engineering

The Custom LED Dashboard Integration was made for the Cal Poly Racing Team, specifically the BAJA division. The dashboard was made as a way to combat the current limitations endured from the past methods used to display critical information of the vehicle to the car. The display was made to combat issues of limited quantity of data being able to be displayed to the driver and its small readability was an issue, the display helped combat that by providing a greater quantity of data being able to be sent and displayed on the display and the information being displayed having …

Continuous Time Recurrent Network For Human Activity Detection, Abdallah Al Zubi

Durham School of Architectural Engineering and Construction: Dissertations, Theses, and Student Research

Human activity detection is crucial to personalize the control of the building environment. For example, understanding certain human activities (e.g., walking, sitting, etc.) for an occupant in a building helps provide the proper thermal comfort control. However, these applications require large-scale neural networks that are challenging to implement and train.

In this thesis, we implemented a continuous-time recurrent neural network implementation (CTRNN) network that can solve real-time human activity detection with a smaller-size network. The CTRNN uses differential equations with a time constant to describe the neuron equations. It was implemented and trained for the first time using TensorFlow. Specifically, …

Examining The Externalities Of Highway Capacity Expansions In California: An Analysis Of Land Use And Land Cover (Lulc) Using Remote Sensing Technology, Serena E. Alexander, Bo Yang, Owen Hussey, Derek Hicks

Mineta Transportation Institute

There are over 590,000 bridges dispersed across the roadway network that stretches across the United States alone. Each bridge with a length of 20 feet or greater must be inspected at least once every 24 months, according to the Federal Highway Act (FHWA) of 1968. This research developed an artificial intelligence (AI)-based framework for bridge and road inspection using drones with multiple sensors collecting capabilities. It is not sufficient to conduct inspections of bridges and roads using cameras alone, so the research team utilized an infrared (IR) camera along with a high-resolution optical camera. In many instances, the IR camera …

Demo Abstract: Vgglass - Demonstrating Visual Grounding And Localization Synergy With A Lidar-Enabled Smart-Glass, Darshana Rathnayake, Dulanga Weerakoon, Meeralakshmi Radhakrishnan, Vigneshwaran Subbaraju, Inseok Hwang, Archan Misra

Research Collection School Of Computing and Information Systems

This work demonstrates the VGGlass system, which simultaneously interprets human instructions for a target acquisition task and determines the precise 3D positions of both user and the target object. This is achieved by utilizing LiDARs mounted in the infrastructure and a smart glass device worn by the user. Key to our system is the union of LiDAR-based localization termed LiLOC and a multi-modal visual grounding approach termed RealG(2)In-Lite. To demonstrate the system, we use Intel RealSense L515 cameras and a Microsoft HoloLens 2, as the user devices. VGGlass is able to: a) track the user in real-time in a global …

Deep Learning-Based Automatic Stereology For High- And Low-Magnification Images, Hunter Morera

USF Tampa Graduate Theses and Dissertations

Quantification of the true number of stained cells in specific brain regions is an important metric in many fields of biomedical research involving cell degeneration, cytotoxicology, cellular inflammation, and drug development for a wide range of neurological disorders and mental illnesses. Unbiased stereology is the current state-of-the-art method for collecting the cell count data from tissue sections. These studies require trained experts to manually focus through a z-stack of microscopy images and count (click) on a hundred or more cells per case, making this approach time consuming (~1 hour per case) and prone to human error (i.e., inter-rater variability). Thus, …

Trends In The Development And Improvement Of Glass Furnaces And Monitoring And Control Systems, N.R Yusupbekov, O'Tkir U. Xolmanov

Chemical Technology, Control and Management

The theory and practice of establishing industrial automation systems for glass furnaces and installations as they are right now are taken into consideration. Comparative analysis is based on publications over the last 20 years in the field being studied. On the basis of an analysis of the review materials, generalizations are made that form the basis for proposals aimed at modernizing and improving the technology and instrumentation of fuel combustion processes in gas-burning furnaces and installations, as well as monitoring and control systems for technological processes occurring in glass furnaces and installations.

Electromagnetic Transient Equivalent Modeling Method For Wind Power Clusters Adapted To Expected Faults, Dongsheng Li, Ye Liu, Yankan Song, Chen Shen

Journal of System Simulation

Abstract: Based on an existing equivalent modeling method for individual wind farm, an iterative simulation-based equivalent modeling method for wind power clusters is proposed and a software development for equivalent modeling of wind power clusters is completed by using CloudPSS-XStudio suite. The system integrates expected fault selection, equivalent parameter calculation and result analysis, which provides support for dynamic security assessment of power systems with large-scale wind power clusters. The equivalent method takes the average wind speed of each wind farm and the expected faults as input, and obtains the cluster index of each wind turbine based on the iterative simulation …

Key Technology And Application Of Digital Twin Modeling For Mri, Shanshan Chen, Hongzhi Wang, Tian Xia

Journal of System Simulation

Abstract: With the accelerating digitalization in education, the construction of digital resources and application platforms has caught increasing attention. The framework of MRI equipment digital twin fivedimensional model is constructed to solve the problems in teaching and training for magnetic resonance imaging (MRI). A modeling and simulation method based on the mechanism model is proposed. The multi-dimensional physical data are obtained to perform digital human modeling, and the virtual acquisition and image reconstruction method is proposed to generate images. The digital twin data are adopted for iterative optimization to implement the whole process of the three-dimensional visual operation including preparation …

A Hybrid Empirical Method For Fast Modeling Of Ship Manoeuvring Motion, Peng Wu, Zongmo Yang, Qianfeng Jing, Yulin Li

Journal of System Simulation

Abstract: Simulation testing is an important means to verify the functions of intelligent ships. Ship maneuvering motion modeling and simulation is the key theoretical basis for the intelligent collision avoidance of multiple vessels in complex sea areas. To address the problem that the calculation of the hydrodynamic coefficients required for ship maneuvering modeling is complex and difficult to obtain, a hybrid empirical method is proposed, a combination method of the existing regression methods is established, the comprehensive performance indicators are constructed, the optimal hydrodynamic coefficients groups are selected by simulated maneuvering experiments, and a rapid modeling program code is developed …

A Structured Conceptual Model Of Joint Operations From Design Perspective, Rui Wen

Journal of System Simulation

Abstract: With the development of technology, through the complementary interaction among operations, operation effectiveness can non-linearly increase and realize fissional and exponential effect. In order to realize dynamic convergence, it is necessary to carry out the action, information and energy unified design. From the antagonism view, taking into account the factors such as the purpose of the operation, the strength of the operation, the conditions of the operation, and so on, the joint operation is divided into the preorder action/ state, the major operational action, the counter-action, the response action, and the branch action, which is synthesized to major operation, …

Time-Varying Rbf Neural Network-Based Controller Design For A Class Of Time-Varying Nonlinear Systems, Jing Li, Taotao Zhang, Kai Jin, Shengzhi Yuan, Zilong Zha

Journal of System Simulation

Abstract: A time-varying RBF neural network with time-varying properties is firstly proposed, and its approximation theorem is obtained. For a class of nonlinear systems with non-parametric time-varying uncertainties, the proposed time-varying RBF neural network is used to approximate the time-varying uncertainties, and the controller is designed by making use of Lyapunov stability theory and adaptive iterative learning control techniques. We obtain the stability theorem of the designed controller. The simulation results verify the effectiveness of the time-varying neural network and the correctness of the controller design scheme.

Terrain Surface Texture Generation Networks For User Semantics Customization, Yan Gao, Jimeng Li, Jianzhong Xu, Hongyan Quan

Journal of System Simulation

Abstract: Customizing terrain based on user semantics has practical value in the virtual terrain modeling of military simulation applications. This study provides a terrain surface texture generation network (TSTG-Net) that can synthesize realistic terrain based on user input semantics. TSTG-Net is designed as a Pix2pix structure and is based on CGAN. It learns the topology of customized terrain by encoding and parsing user semantics and regards the semantics feature as the constraint of CGAN. In the generator-discriminator structure, user-customized semantics are used as the input, and the real terrain with semantics is employed as the ground truth in network optimization. …

Reliability Evaluation Method Of Radar Simulation Model Based On Air Combat Mechanism, Chenguang Wang, Jinpeng Bai, Tingting Li, Lifeng Miao, Kaifeng Wang

Journal of System Simulation

Abstract: In modern air combat simulation, the reliability of radar simulation model is very important. Based on simulation model VV&A theory, a cropped and suitable for engineering applications simulation model reliability evaluation method is proposed. Based on the analysis of radar use mechanism in medium and long range air combat and short range air combat is analyzed,, the requirement of radar model in air combat simulation system, the evaluation index system is established, and the reliability quantification method based on JS dispersion is proposed, which further enriches the base of basic method. The test case is designed, the simulation test …

A Fuzzy Group Decision-Making-Based Method For Green Supplier Selection And Order Allocation, Lu Liu, Wenxin Li, Xiao Song, Bingli Sun, Guanghong Gong

Journal of System Simulation

Abstract: With the intensity of market competitiveness, the worsening of the global environment, and the improvement of public concern about environmental protection, the issue of green purchasing has received considerable attention. The vast majority of existing studies on green purchasing have concentrated on supplier selection with green criteria, so as to realize sustainable operations, whereas it is more feasible and economical for businesses to obtain the proper products from adaptable and suitable suppliers at the right times, rates, and volumes, which is referred to as supplier selection and order allocation. To resolve the aforementioned two crucial challenges, we propose a …

Learning And Analysis Of Dynamic Models For Grid Discrete Events Based On Log Information, Danlong Zhu, Yunqi Yan, Ying Chen, Jiaqi Zhang, Longxing Jin, Wei Fu

Journal of System Simulation

Abstract: With the increasing scale of power grid, the massive amount of log information generated bydevices in the power grid poses a challenge to the manual analysis of abnormal grid conditions. The log information generated during the operation of the power grid has the typical discrete sequential characteristics. By analyzing the log information of grid alarm messages, a station event transition probability model and an event sequence risk calculation method are proposed to effectively model and analyze the abnormal operation level of primary and secondary systems in substations. The proposed method not only successfully identifies the event sequences corresponding to …

Air Distribution Simulation And Comfort Evaluation Of Large Space Building Based On Rans And Les, Shen Zhang, Ming Cheng, Yifan Wang, Fankai Meng, Ting Li, Han Chen, Zhifeng Ji

Journal of System Simulation

Abstract: Air distribution simulation and thermal comfort evaluation for heating, ventilation and air conditioning (HVAC) design of large space buildings is of great significance for the human thermal comfort improvement and the energy consumption reduction. By combining the steady analysis based on RANS and the transient analysis of large eddy simulation (LES), an air distribution simulation and thermal comfort evaluation process in large space buildings is established. Due to the low calculation consumption, the steady analysis based on RANS is conducted to efficiently evaluate the thermal comfort and the air quality under multiple working conditions. Considering the high computational consumption …

Research On Multi-Aircraft Air Combat Behavior Modeling Based On Hierarchical Intelligent Modeling Methods, Yukun Wang, Ze Wang, Liwei Dong, Ni Li

Journal of System Simulation

Abstract: In response to the problem of the difficulty of decision-making in the game of force under the constraints of high-dimensional state-space in multi-machine air combat confrontation scenarios, a force intelligent agent decision-making generation strategy based on deep reinforcement learning is adopted. The developing situational cognition and reward feedback generation algorithms for force intelligentgame are proposed, a behavior modeling hierarchical framework based on hybrid intelligence modeling method is constructed, which solve the technical difficulty of sparse reward in the reinforcement learning process. It provides an feasible reinforcement learning training method that can solve the large-scale, multi-model, and multi-element air combat …

Dynamic 3d Scene Perception Based On Battlefield Metaverse, Haoyu Wang, Guanghong Gong, Jihong Cai, Bipeng Ye, Zhaofang Zhou, Zheng Mei, Ni Li

Journal of System Simulation

Abstract: Informatization combat needs higher requirements for battlefield situational awareness, and the use of unmanned intelligences to conduct battlefield reconnaissance and perceive target information is particularly important. Facing the needs of complex dynamic environment localization and target recognition, a dynamic 3D scene perception system is proposed and constructed based on battlefield meta-universe target data and operational environment, which uses vision and IMU fusion sensor simulation data as inputs, extracts battlefield target information through instance segmentation and dense optical flow estimation network and uses it as a scene prior, and synchronizes the position estimation of unmanned intelligences in the battlefield with …

A Precise Attention Tracking System Based On Computer Vision, Jiyuan Liu, Hanwen Qi, Zhicheng Liu, Minrui Fei, Kun Zhang

Journal of System Simulation

Abstract: A precise attention tracking system based on machine vision is designed to address the difficulty in studying students' attention allocation. The system includes an image capture device and an accurate attention tracking algorithm. The image capture device can capture the clearer ocular images. The pupil center localization algorithm replaces VGG16 with lightweight MobileNetv3 and uses twostage feature fusion and center keypoint prediction techniques to improve the speed and accuracy. The algorithm achieves a speed of up to 36 frames/s and 97.42% accuracy. The gaze tracking algorithm compensates for the head movements to achieve the meticulous gaze tracking. An interactive …

Modeling And Analysis On Scattering Characteristics Automatic Driving Radar Bands In Rainy Environment, Mengfan Zou, Xiaoyu He

Journal of System Simulation

Abstract: The operating frequency band of modern communication and radar systems has extended to millimeter wave and terahertz frequency band, and the analysis on propagation characteristics of electromagnetic signals in rainy environment is important. A calculation model through Mie scattering theory is built to simulate the attenuation and the scattering of electromagnetic signals in rainy environments. Different types of raindrop size distribution function are adopted to analyze the propagation attenuation under different rainfall of frequencies spanning from 1 GHz to 1 THz. Experimental results are compared with international telecommunication union (ITU) half-empirical model to verify the validation of the model. …

Integrated Scheduling Simulation Based On Improved Moth Flame Optimizer, Tianrui Zhang, Huiyuan Niu, Wei Xie

Journal of System Simulation

Abstract: Aiming at the rising cost of manufacturing enterprises, a mathematical programming model of integrated scheduling of production and transportation is established, and a double adaptive weights for moth flame optimizer(DAWMFO) is proposed. A double adaptive weight mechanism is proposed. The spiral function is used to update the population, which improves the convergence speed and accuracy of the algorithm. The benchmark function is tested by the improved algorithm. The results show that the improved algorithm can converge quickly and not easily fall into local optimum. Compared with other algorithms, the optimization ability is also improved. Through the simulation experiment on …

Simulation And Research Of Manipulator Motion Strategy Based On Adaptive Dynamic Programming, Ming Li, Qun Xu, Yan Wang, Zhicheng Ji

Journal of System Simulation

Abstract: Aiming at the difficulty of manipulator to realize high-precision motion tracking in complex and harsh environment, a strategy method based on the combination of adaptive dynamic programming (ADP) and sliding mode admittance control is proposed. The unknown environment is modeled as a linear model and based on quasi, a sliding mode admittance controller is derived to resist disturbance interference. An optimal control method that combines ADP with sliding mode admittance controller is proposed, in which the definition of R-matrix in value function is optimized and improved to further improve the tracking accuracy. The neural network based on ADP is …

Design And Simulation Of A Location Privacy Protection Scheme Based On Zero-Knowledge Proof For Military Iot, Mingjie Shi, Chengyu Xie, Chuanfu Zhang

Journal of System Simulation

Abstract: In the military Internet of Things (IoT) combat environment, the location privacy issue becomes a key challenge. An innovative location privacy protection scheme based on zero-knowledge proof is proposed to ensure that in unreliable communication channels, the location information of combat units can be verified without revealing their specific coordinates, so as to achieve the goal of protecting sensitive location information. Based on the idea of cryptography, by using zero-knowledge proof, through algebraic circuit, rank-1 constraint system(R1CS), quadratic arithmetic programs(QAP), and other steps, the position coordinate information proof problem is transformed into a point verification problem on a polynomial …