Digital Commons Network^™

Solving Electromagnetic Inverse Scattering Problems In Inhomogeneous Media By Deep Convolutional Encoder-Decoder Structure, Huan Huan Zhang, He Ming Yao, Lijun Jiang, Michael Ng

Electrical and Computer Engineering Faculty Research & Creative Works

This communication proposes a novel deep learning (DL) approach to solve electromagnetic inverse scattering (EMIS) problems in inhomogeneous media. The conventional approaches for solving inhomogeneous EMIS problems generally have to consider inhomogeneous Green’s functions or conduct approximation operations to media, which inevitably introduces various challenges, including complex mathematical derivation, high computation cost, unavoidable nonlinearity, and even strong ill-posedness. To avoid these challenges, we propose a DL approach based on the complex-valued deep convolutional neural networks (DConvNets), which comprise the deep convolutional encoder–decoder (DCED) structure. Its training data are collected based on the simple synthetic dataset. While the scattered fields received …

Lifelong Deep Learning-Based Control Of Robot Manipulators, Irfan Ganie, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

This study proposes a lifelong deep learning control scheme for robotic manipulators with bounded disturbances. This scheme involves the use of an online tunable deep neural network (DNN) to approximate the unknown nonlinear dynamics of the robot. The control scheme is developed by using a singular value decomposition-based direct tracking error-driven approach, which is utilized to derive the weight update laws for the DNN. To avoid catastrophic forgetting in multi-task scenarios and to ensure lifelong learning (LL), a novel online LL scheme based on elastic weight consolidation is included in the DNN weight-tuning laws. Our results demonstrate that the resulting …

Rafid: A Lightweight Approach To Radio Frequency Interference Detection In Time Domain Using Lstm And Statistical Analysis, Luke A. Smith, Vishesh Kumar Tanwar, Maciej Jan Zawodniok, Sanjay Kumar Madria

Electrical and Computer Engineering Faculty Research & Creative Works

Recently, the utilization of Radio Frequency (RF) devices has increased exponentially over numerous vertical platforms. This rise has led to an abundance of Radio Frequency Interference (RFI) continues to plague RF systems today. The continued crowding of the RF spectrum makes RFI efficient and lightweight mitigation critical. Detecting and localizing the interfering signals is the foremost step for mitigating RFI concerns. Addressing these challenges, we propose a novel and lightweight approach, namely RaFID, to detect and locate the RFI by incorporating deep neural networks (DNNs) and statistical analysis via batch-wise mean aggregation and standard deviation (SD) calculations. RaFID investigates the …

Continual Learning-Based Optimal Output Tracking Of Nonlinear Discrete-Time Systems With Constraints: Application To Safe Cargo Transfer, Behzad Farzanegan, S. (Sarangapani) Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This Paper Addresses a Novel Lifelong Learning (LL)-Based Optimal Output Tracking Control of Uncertain Non-Linear Affine Discrete-Time Systems (DT) with State Constraints. First, to Deal with Optimal Tracking and Reduce the Steady State Error, a Novel Augmented System, Including Tracking Error and its Integral Value and Desired Trajectory, is Proposed. to Guarantee Safety, an Asymmetric Barrier Function (BF) is Incorporated into the Utility Function to Keep the Tracking Error in a Safe Region. Then, an Adaptive Neural Network (NN) Observer is Employed to Estimate the State Vector and the Control Input Matrix of the Uncertain Nonlinear System. Next, an NN-Based …

Analysis On Extraction Of Potential Radiated Emission Limit Line For Data Center Equipment From 10 Ghz To 40 Ghz, Zhekun Peng, Wei Zhang, Jong Hwa Kwon, Donghyun Kim

Electrical and Computer Engineering Faculty Research & Creative Works

The Radiated Emission (RE) Potential Limit Line for Router System is Analyzed from 10 GHz to 40 GHz based on CISPR TR 16-4-4 Standard. Statistical Data is Collected for the Limit Line Extraction from Measurement, Numerical Analysis, 3D Full-Wave Simulation and Literature Studies. All the Factors Considered in Limit Line Calculation Are Analyzed for Data Center Equipment Operation. the Result of Extracted Potential Limit Line Shows the Rising Limit Line between 10 GHz and 40 GHz Frequency Band for Potential Future Radiated Emission Limit Line above 40 GHz Targeted for High-Speed Equipment Radiated Emission. This Paper is Not a Standard …

Challenges And Solutions For Automotive Ota Testing, Jiyu Wu, Yihong Qi, Penghui Shen, Wei Yu, Lie Liu, James L. Drewniak

Electrical and Computer Engineering Faculty Research & Creative Works

OTA (Over-The-Air) Testing is Essential for Developing Assisted and Autonomous Driving Systems in Vehicles, as It Plays a Crucial Role in the Localization, Perception, and Intelligent Driving Capabilities of ICVs (Intelligent Connected Vehicles). Automotive Antennas, Typically Much Smaller in Size Than the Vehicle itself and Can Be Located in Various Positions, Require Spherical Near-Field Measurement for OTA Testing. While There Are Established Standards for OTA Testing Methods and Uncertainties for Mobile Devices, Base Stations, and Satellite Components, There Are Still Many Challenges in the OTA Testing of Automotive Systems. These Challenges, specifically in SISO (Single Input Single Output) and MIMO …

Design And Construction Of An Arbitrary Pulse Compressive Amplifier, Cody Goins, Aaron Harmon, Victor Khilkevich, Daryl G. Beetner

Electrical and Computer Engineering Faculty Research & Creative Works

Compressive Pulse Amplifiers Are a Class of Amplifiers that Convert Long Low Amplitude Signals into Very Broadband Pulses of High Amplitude, Yielding a Very High Instantaneous Peak Power Output Pulse. However, in the Realm of Electronic Immunity and Susceptibility Testing, Very Broadband Short Pulses Are Not Always Desired. This Work Presents a Design for a Compressive Amplifier that is Aimed at Creating Arbitrary Pulsed Signals of Varying Bandwidths. Limitations of the Achievable Gain and Methods Used Are Discussed.

A Real-Time Microwave Camera Prototype With Zero-Bias Diode Detectors For Emi Source Imaging, Xin Yan, Liang Liu, Victor Khilkevich

Electrical and Computer Engineering Faculty Research & Creative Works

Emission Source Microscopy (ESM) Could Be Utilized to Localize the Electromagnetic Interference (EMI) Sources that Contribute to the Far-Field Radiation. in Those Cases, the Electrical Field over a Two-Dimensional Plane is Collected by Mechanical Scanning, Resulting in a Long Measurement Time and the Presence of Mechanical Errors. in This Work, a Microwave Camera based on a Two-Dimensional Array of Elliptical Slot Antennas and Diode Detectors is Presented. Multiplexers Are Utilized to Access the Output of Each Detector and the Scanning of the Whole Array Could Be Done Multiple Times Per Second.

Challenges And Prospects Of Vehicle Ota Spherical Near-Field Measurement Probes, Dao Lin, Zhanghua Cai, Lidong Chi, Fuhai Li, James L. Drewniak, Gang Feng, Yihong Qi

Electrical and Computer Engineering Faculty Research & Creative Works

This Paper Discusses the Issue of Measuring Probe Indicators for Large-Scale Equipment, Such as Automobiles, under Conditions of Offset Configuration. a Simulation of Spherical Near-Field Measurement based on an Offset Configuration is Presented in This Paper. the Measurement Error is Defined According to the Reference Data Calculated by Spherical Wave Expansion Theory. through Comparative Analysis of the Simulation Results, the Main Reason for the Measurement Error is the Insufficient Coverage of the Probe's Beamwidth. by Adjusting the Probe's Radiation Pattern using Simulation Software, an Optimized Probe that Satisfies Near-Field Measurement Requirements under Meter-Level Offset Conditions is Obtained. Finally, based on …

Lifelong Learning-Based Multilayer Neural Network Control Of Nonlinear Continuous-Time Strict-Feedback Systems, Irfan Ahmad Ganie, S. (Sarangapani) Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In This Paper, We Investigate Lifelong Learning (LL)-Based Tracking Control for Partially Uncertain Strict Feedback Nonlinear Systems with State Constraints, employing a Singular Value Decomposition (SVD) of the Multilayer Neural Networks (MNNs) Activation Function based Weight Tuning Scheme. the Novel SVD-Based Approach Extends the MNN Weight Tuning to (Formula Presented.) Layers. a Unique Online LL Method, based on Tracking Error, is Integrated into the MNN Weight Update Laws to Counteract Catastrophic Forgetting. to Adeptly Address Constraints for Safety Assurances, Taking into Account the Effects Caused by Disturbances, We Utilize a Time-Varying Barrier Lyapunov Function (TBLF) that Ensures a Uniformly Ultimately …

Towards Robust Consensus For Intelligent Decision-Making In Iot Blockchain Networks, Charles Rawlins, S. (Sarangapani) Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

Distributed consensus is the core aspect of blockchain protocol security design. Recent protocols like IOTA have improved concurrency and scalability over Proof-of-work (PoW) with Bitcoin but have core design decisions that are inefficient for limited devices and do not take advantage of previous network experience to reduce calculations. This work proposes the first blockchain consensus protocol based on active machine-learning decisions, called Proof-of-history (PoH). PoH is setup as a distributed reinforcement-learning task for monitoring classification and training of blockchain transactions with an inner deep classifier. Early theoretical analysis and simulations show that PoH is robust to uncoordinated byzantine attacks through …

Improved Intelligent Ledger Construction For Realistic Iot Blockchain Networks, Charles Rawlins, S. (Sarangapani) Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

Scalability is essential for next generation blockchain technology to integrate with large mobile networks like Internet of Things (IoT). The IOTA distributed ledger protocol has combined transaction generation and verification to address this, but at the expense of increased reliance on connectivity to resolve conflicts with a novel ledger data structure. Intelligent Ledger Construction (ILC) was proposed as an auditable lightweight reinforcement-learning scheme to address this constraint with proposal of local conflict resolution with machine-learning classification. This effort presents an improved reliability reward model to enhance training for ILC and further reduce adversarial gaming and resource usage. Testing this revision …

Accelerated Statistical Eye Diagram Estimation Method For Efficient Signal Integrity Analysis, Junyong Park, Youngwoo Kim, Donghyun Kim

Electrical and Computer Engineering Faculty Research & Creative Works

This article proposes an accelerated statistical eye diagram estimation method for efficient signal integrity (SI) analysis. An eye diagram is a critical metric in the SI analysis, however obtaining an eye diagram is time-consuming in simulation. The required time might be a few weeks depending on the complexity. Because the eye diagram is obtained by superposition of the received waveforms. Statistical eye diagram estimation methods were proposed to make the eye diagram acquisition efficient, however, it still has a limited improvement due to a large number of convolution operations. To address this limitation, the proposed method includes two approaches: (i) …

Cooperative Deep $Q$ -Learning Framework For Environments Providing Image Feedback, Krishnan Raghavan, Vignesh Narayanan, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In This Article, We Address Two Key Challenges in Deep Reinforcement Learning (DRL) Setting, Sample Inefficiency and Slow Learning, with a Dual-Neural Network (NN)-Driven Learning Approach. in the Proposed Approach, We Use Two Deep NNs with Independent Initialization to Robustly Approximate the Action-Value Function in the Presence of Image Inputs. in Particular, We Develop a Temporal Difference (TD) Error-Driven Learning (EDL) Approach, Where We Introduce a Set of Linear Transformations of the TD Error to Directly Update the Parameters of Each Layer in the Deep NN. We Demonstrate Theoretically that the Cost Minimized by the EDL Regime is an Approximation …

A Resilience-Oriented Multi-Stage Adaptive Distribution System Planning Considering Multiple Extreme Weather Events, Siyuan Wang, Rui Bo

Electrical and Computer Engineering Faculty Research & Creative Works

Climate Change May Increase the Risk of an Area Being Hit by Multiple Extreme Weather Events, Which Brings Significant Challenges for Distribution System Planners in an Increasing Renewable Penetration Era. There is an Urgent Need for Planning Approaches to Be More Flexible and Allow for Adaptive Adjustments in the Future to Hedge Against High Uncertainties in Extreme Weather Event Scenarios. in This Work, We Propose a Resilience-Oriented Distribution System Planning Approach that Considers Multiple Extreme Weather Events. a Multi-Stage Hybrid-Stochastic-And-Robust Formulation is Developed to Model Decisions Not Only for Initial Investments, But Also for Adaptive Investments and Emergent Operations in …

Extended Kalman Filter Based Resilient Formation Tracking Control Of Multiple Unmanned Vehicles Via Game-Theoretical Reinforcement Learning, Lei Xue, Bei Ma, Jian Liu, Chaoxu Mu, Donald C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

In This Paper, We Discuss the Resilient Formation Tracking Control Problem of Multiple Unmanned Vehicles (MUV). a Dynamic Leader-Follower Distributed Control Structure is Utilized to Optimize the Performance of the Formation Tracking. for the Follower of the MUV, the Leader is a Cooperative Unmanned Vehicle, and the Target of Formation Tracking is a Non-Cooperative Unmanned Vehicle with a Nonlinear Trajectory. Therefore, an Extended Kalman Filter (EKF) Observer is Designed to Estimate the State of the Target. Then the Leader of the MUV is Adjusted Dynamically According to the State of the Target. in Order to Describe the Interactions between the …

Communety: Deep Learning-Based Face Recognition System For The Prediction Of Cohesive Communities, Syed Afaq Ali Shah, Weifeng Deng, Muhammad Aamir Cheema, Abdul Bais

Research outputs 2022 to 2026

Effective mining of social media, which consists of a large number of users is a challenging task. Traditional approaches rely on the analysis of text data related to users to accomplish this task. However, text data lacks significant information about the social users and their associated groups. In this paper, we propose CommuNety, a deep learning system for the prediction of cohesive networks using face images from photo albums. The proposed deep learning model consists of hierarchical CNN architecture to learn descriptive features related to each cohesive network. The paper also proposes a novel Face Co-occurrence Frequency algorithm to quantify …

Covid-19 Two Years On: A Review Of Covid-19-Related Empirical Research In Major Tourism And Hospitality Journals, Songshan (Sam) Huang, Xuequn Wang

Research outputs 2022 to 2026

Purpose: This study aims to provide a timely review of the COVID-19-related empirical research published in 19 quartile one (Q1) and quartile two (Q2) tourism and hospitality journals in social science citation index (SSCI).

Design/methodology/approach: A total of 407 COVID-19-related empirical papers were collected from the 19 SSCI Q1 and Q2 tourism and hospitality journals via Scopus database. Thematic content analysis was supplemented with Leximancer software to identify the research themes/subthemes, research methods and countries/regions of research.

Findings: The study found studies of COVID-19’s impact on consumer behaviour predominate in number, followed by studies on response actions and recovery strategies, …

Long Future Frame Prediction Using Optical Flow Informed Deep Neural Networks For Enhancement Of Robotic Teleoperation In High Latency Environments, Md Moniruzzaman, Alexander Rassau, Douglas Chai, Syed M. S. Islam

Research outputs 2022 to 2026

High latency in teleoperation has a significant negative impact on operator performance. While deep learning has revolutionized many domains recently, it has not previously been applied to teleoperation enhancement. We propose a novel approach to predict video frames deep into the future using neural networks informed by synthetically generated optical flow information. This can be employed in teleoperated robotic systems that rely on video feeds for operator situational awareness. We have used the image-to-image translation technique as a basis for the prediction of future frames. The Pix2Pix conditional generative adversarial network (cGAN) has been selected as a base network. Optical …

Multivariate Cross-Validation And Measures Of Accuracy And Precision, Ute Mueller, Sangga Rima Roman Selia, Raimon Tolosana-Delgado

Research outputs 2022 to 2026

Cross-validation and performance measures are standard components in the evaluation of a geostatistical model. These are well established in the univariate case, but measures for multivariate geostatistical modeling have not received as much attention. In the case of a single target variable, the univariate approaches remain valid, but in the fully multivariate case where a vector of variables needs to be estimated, the evaluation needs to be based on all estimates simultaneously. An extension of cross-validation and associated performance measures to the fully multivariate case is presented and discussed for the case of regionalized compositions. The method is demonstrated by …

A New Augmented Reality System For Calculating Social Distancing Between Children At School, Omar Alshaweesh, Mohammad Wedyan, Moutaz Alazab, Bilal Abu-Salih, Adel Al-Jumaily

Research outputs 2022 to 2026

Social distancing is one of the most important ways to prevent many diseases, especially the respiratory system, where the latest internationally spread is coronavirus disease, and it will not be the last. The spreading of this pandemic has become a major threat to human life, especially to the elderly and people suffering from chronic diseases. During the Corona pandemic, medical authorities were keen to control the spread through social distancing and monitoring it in markets, universities, and schools. This monitoring was mostly used to estimate the distance with the naked eye and interfere with estimating the distance on the observer …

Camdec: Advancing Axis P1435-Le Video Camera Security Using Honeypot-Based Deception, Leslie F. Sikos, Craig Valli, Alexander E. Grojek, David J. Holmes, Samuel G. Wakeling, Warren Z. Cabral, Nickson M. Karie

Research outputs 2022 to 2026

The explosion of online video streaming in recent years resulted in advanced services both in terms of efficiency and convenience. However, Internet-connected video cameras are prone to exploitation, leading to information security issues and data privacy concerns. The proliferation of video-capable Internet of Things devices and cloud-managed surveillance systems further extend these security issues and concerns. In this paper, a novel approach is proposed for video camera deception via honeypots, offering increased security measures compared to what is available on conventional Internet-enabled video cameras.

Educational Leaders’ Perceptions Of Stem Education Revealed By Their Drawings And Texts, Vesife Hatisaru, Garry Falloon, Andrew Seen, Sharon Fraser, Markus Powling, Kim Beswick

Research outputs 2022 to 2026

This study explored school principals' and teacher educators' perceptions of STEM education based on how they described STEM as a discipline, their understanding of the nature of teaching and learning of STEM, and the capabilities of a STEM-educated person. Data were generated through the Draw a STEM Learning Environment (D-STEM) instrument comprising drawn and written descriptions where participants drew a picture of a STEM learning environment and completed five prompt statements about what STEM is and how an individual develops personal STEM capability. The Legitimation Code Theory (LCT) specialization codes were used for data analysis (198 individual response items in …

Improving Accuracy And Efficiency In Seagrass Detection Using State-Of-The-Art Ai Techniques, Md Kislu Noman, Syed M. S. Islam, Jumana Abu-Khalaf, Seyed M. J. Jalali, Paul Lavery

Research outputs 2022 to 2026

Seagrasses provide a wide range of ecosystem services in coastal marine environments. Despite their ecological and economic importance, these species are declining because of human impact. This decline has driven the need for monitoring and mapping to estimate the overall health and dynamics of seagrasses in coastal environments, often based on underwater images. However, seagrass detection from underwater digital images is not a trivial task; it requires taxonomic expertise and is time-consuming and expensive. Recently automatic approaches based on deep learning have revolutionised object detection performance in many computer vision applications, and there has been interest in applying this to …

Fabrication And Optimization Of Nafion As A Protective Membrane For Tin-Based Ph Sensors, Shimrith P. Shylendra, Magdalena Wajrak, Kamal Alameh

Research outputs 2022 to 2026

In this study, a solid-state modified pH sensor with RF magnetron sputtering technology was developed. The sensor consists of an active electrode consisting of a titanium nitride (TiN) film with a protective membrane of Nafion and a reference glass electrode of Ag/AgCl. The sensitivity of the pH sensor was investigated. Results show a sensor with excellent characteristics: sensitivity of 58.6 mV/pH for pH values from 2 to 12, very short response time of approximately 12 s in neutral pH solutions, and stability of less than 0.9 mV in 10 min duration. Further improvement in the performance of the TiN sensor …

Ranking The Risk Of Co2 Emissions From Seagrass Soil Carbon Stocks Under Global Change Threats, Martin Dahl, Kathryn Mcmahon, Paul S. Lavery, Serena H. Hamilton, Catherine E. Lovelock, Oscar Serrano

Research outputs 2022 to 2026

Seagrass meadows are natural carbon storage hotspots at risk from global change threats, and their loss can result in the remineralization of soil carbon stocks and CO2 emissions fueling climate change. Here we used expert elicitation and empirical evidence to assess the risk of CO2 emissions from seagrass soils caused by multiple human-induced, biological and climate change threats. Judgments from 41 experts were synthesized into a seagrass CO2 emission risk score based on vulnerability factors (i.e., spatial scale, frequency, magnitude, resistance and recovery) to seagrass soil organic carbon stocks. Experts perceived that climate change threats (e.g., gradual ocean warming and …

A Cross-Domain Trust Model Of Smart City Iot Based On Self-Certification, Yao Wang, Yubo Wang, Zhenhu Ning, Sadaqat Ur Rehman, Muhammad Waqas

Research outputs 2022 to 2026

Smart city refers to the information system with Internet of things and cloud computing as the core technology and government management and industrial development as the core content, forming a large-scale, heterogeneous and dynamic distributed Internet of things environment between different Internet of things. There is a wide demand for cooperation between equipment and management institutions in the smart city. Therefore, it is necessary to establish a trust mechanism to promote cooperation, and based on this, prevent data disorder caused by the interaction between honest terminals and malicious terminals. However, most of the existing research on trust mechanism is divorced …

Identity-Based Edge Computing Anonymous Authentication Protocol, Naixin Kang, Zhenhu Ning, Shiqiang Zhang, Sadaqat Ur Rehman, Muhammad Waqas

Research outputs 2022 to 2026

With the development of sensor technology and wireless communication technology, edge computing has a wider range of applications. The privacy protection of edge computing is of great significance. In the edge computing system, in order to ensure the credibility of the source of terminal data, mobile edge computing (MEC) needs to verify the signature of the terminal node on the data. During the signature process, the computing power of edge devices such as wireless terminals can easily become the bottleneck of system performance. Therefore, it is very necessary to improve efficiency through computational offloading. Therefore, this paper proposes an identity-based …

Intrusion Detection Based On Bidirectional Long Short-Term Memory With Attention Mechanism, Yongjie Yang, Shanshan Tu, Raja Hashim Ali, Hisham Alasmary, Muhammad Waqas, Muhammad Nouman Amjad

Research outputs 2022 to 2026

With the recent developments in the Internet of Things (IoT), the amount of data collected has expanded tremendously, resulting in a higher demand for data storage, computational capacity, and real-time processing capabilities. Cloud computing has traditionally played an important role in establishing IoT. However, fog computing has recently emerged as a new field complementing cloud computing due to its enhanced mobility, location awareness, heterogeneity, scalability, low latency, and geographic distribution. However, IoT networks are vulnerable to unwanted assaults because of their open and shared nature. As a result, various fog computing-based security models that protect IoT networks have been developed. …

2023 Fall Commencement, Georgia Southern University

Commencement Programs

No abstract provided.