Selena He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Selena He has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Kun Suo
Kennesaw State University
3 shared publications - Tu Ngoc Nguyen
Kennesaw State University, Kennesaw, GA, USA
3 shared publications - Long Vu
Kennesaw State University, Marietta, Georgia, USA
2 shared publications - Nobel Dhar
Kennesaw State University, Marietta, USA
2 shared publications - Romyull Islam
Kennesaw State University, Marietta, USA
2 shared publications - Xin Tian
Kennesaw State University, Marietta, Georgia, USA
2 shared publications
Latest Publications
- 21 July 2026
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 214
UMCA-Net: Uncertainty-aware multi-stage cross-attention for cost-aware multi-omics data classification
- 21 July 2026
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 214
UMCA-Net: Uncertainty-aware multi-stage cross-attention for cost-aware multi-omics data classification
- Open Access
- 5 November 2025
- Published by JMIR Publications Inc. in JMIR Biomedical Engineering
- Vol. 10, e72218
Advancing Brain-Computer Interface Closed-Loop Systems for Neurorehabilitation: Systematic Review of AI and Machine Learning Innovations in Biomedical Engineering
Background: Brain-computer interface (BCI) closed-loop systems have emerged as a promising tool in health care and wellness monitoring, particularly in neurorehabilitation and cognitive assessment. With the increasing burden of neurological disorders, including Alzheimer disease and related dementias (AD/ADRD), there is a critical need for real-time, noninvasive monitoring technologies. BCIs enable direct communication between the brain and external devices, leveraging artificial intelligence (AI) and machine learning (ML) to interpret neural signals. However, challenges such as signal noise, data processing limitations, and privacy concerns hinder widespread implementation. Objective: The primary objective of this study is to investigate the role of ML and AI in enhancing BCI closed-loop systems for health care applications. Specifically, we aim to analyze the methods and parameters used in these systems, assess the effectiveness of different AI and ML techniques, identify key challenges in their development and implementation, and propose a framework for using BCIs in the longitudinal monitoring of AD/ADRD patients. By addressing these aspects, this study seeks to provide a comprehensive overview of the potential and limitations of AI-driven BCIs in neurological health care. Methods: A systematic literature review was conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, focusing on studies published between 2019 and 2024. We sourced research articles from PubMed, IEEE, ACM, and Scopus using predefined keywords related to BCIs, AI, and . A total of 220 papers were initially identified, with 18 meeting the final inclusion criteria. Data extraction followed a structured matrix approach, categorizing studies based on methods, ML algorithms, limitations, and proposed solutions. A comparative analysis was performed to synthesize key findings and trends in AI-enhanced BCI systems for neurorehabilitation and cognitive monitoring. Results: The review identified several ML techniques, including transfer learning (TL), support vector machines (SVMs), and convolutional neural networks (CNNs), that enhance BCI closed-loop performance. These methods improve signal classification, feature extraction, and real-time adaptability, enabling accurate monitoring of cognitive states. However, challenges such as long calibration sessions, computational costs, data security risks, and variability in neural signals were also highlighted. To address these issues, emerging solutions such as improved sensor technology, efficient calibration protocols, and advanced AI-driven decoding models are being explored. In addition, BCIs show potential for real-time alert systems that support caregivers in managing AD/ADRD patients. Conclusions: BCI closed-loop systems, when integrated with AI and ML, offer significant advancements in neurological health care, particularly in AD/ADRD monitoring and neurorehabilitation. Despite their potential, challenges related to data accuracy, security, and scalability must be addressed for widespread clinical adoption. Future research should focus on refining AI models, improving real-time data processing, and enhancing user accessibility. With continued advancements, AI-powered BCIs can revolutionize personalized health care by providing continuous, adaptive monitoring and intervention for patients with neurological disorders.
- 5 November 2025
- Published by JMIR Publications Inc. in JMIR Biomedical Engineering
- Vol. 10, e72218
Open AccessAdvancing Brain-Computer Interface Closed-Loop Systems for Neurorehabilitation: Systematic Review of AI and Machine Learning Innovations in Biomedical Engineering
Background: Brain-computer interface (BCI) closed-loop systems have emerged as a promising tool in health care and wellness monitoring, particularly in neurorehabilitation and cognitive assessment. With the increasing burden of neurological disorders, including Alzheimer disease and related dementias (AD/ADRD), there is a critical need for real-time, noninvasive monitoring technologies. BCIs enable direct communication between the brain and external devices, leveraging artificial intelligence (AI) and machine learning (ML) to interpret neural signals. However, challenges such as signal noise, data processing limitations, and privacy concerns hinder widespread implementation. Objective: The primary objective of this study is to investigate the role of ML and AI in enhancing BCI closed-loop systems for health care applications. Specifically, we aim to analyze the methods and parameters used in these systems, assess the effectiveness of different AI and ML techniques, identify key challenges in their development and implementation, and propose a framework for using BCIs in the longitudinal monitoring of AD/ADRD patients. By addressing these aspects, this study seeks to provide a comprehensive overview of the potential and limitations of AI-driven BCIs in neurological health care. Methods: A systematic literature review was conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, focusing on studies published between 2019 and 2024. We sourced research articles from PubMed, IEEE, ACM, and Scopus using predefined keywords related to BCIs, AI, and . A total of 220 papers were initially identified, with 18 meeting the final inclusion criteria. Data extraction followed a structured matrix approach, categorizing studies based on methods, ML algorithms, limitations, and proposed solutions. A comparative analysis was performed to synthesize key findings and trends in AI-enhanced BCI systems for neurorehabilitation and cognitive monitoring. Results: The review identified several ML techniques, including transfer learning (TL), support vector machines (SVMs), and convolutional neural networks (CNNs), that enhance BCI closed-loop performance. These methods improve signal classification, feature extraction, and real-time adaptability, enabling accurate monitoring of cognitive states. However, challenges such as long calibration sessions, computational costs, data security risks, and variability in neural signals were also highlighted. To address these issues, emerging solutions such as improved sensor technology, efficient calibration protocols, and advanced AI-driven decoding models are being explored. In addition, BCIs show potential for real-time alert systems that support caregivers in managing AD/ADRD patients. Conclusions: BCI closed-loop systems, when integrated with AI and ML, offer significant advancements in neurological health care, particularly in AD/ADRD monitoring and neurorehabilitation. Despite their potential, challenges related to data accuracy, security, and scalability must be addressed for widespread clinical adoption. Future research should focus on refining AI models, improving real-time data processing, and enhancing user accessibility. With continued advancements, AI-powered BCIs can revolutionize personalized health care by providing continuous, adaptive monitoring and intervention for patients with neurological disorders.
- Open Access
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 18-26
Living on the Electric Vehicle and Cloud Era: A Study of Cyber Vulnerabilities, Potential Impacts, and Possible Strategies
In recent years, electric vehicles (EVs) have emerged as a sustainable alternative to conventional automobiles. Distinguished by their environmental friendliness, superior performance, reduced noise, and low maintenance requirements, EVs offer numerous advantages over traditional vehicles. The integration of electric vehicles with cloud computing has heralded a transformative shift in the automotive industry. However, as EVs become increasingly interconnected with the internet, various devices, and infrastructure, they become susceptible to cyberattacks. These attacks pose a significant risk to the safety, privacy, and functionality of both the vehicles and the broader transportation infrastructure. In this paper, we delve into the topic of electric vehicles and their connectivity to the cloud. We scrutinize the potential attack vectors that EVs are vulnerable to and the consequential impact on vehicle operations. Moreover, we outline both general and specific strategies aimed at thwarting these cyberattacks. Additionally, we anticipate future developments aimed at enhancing EV performance and reducing security risks.
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 18-26
Open AccessLiving on the Electric Vehicle and Cloud Era: A Study of Cyber Vulnerabilities, Potential Impacts, and Possible Strategies
In recent years, electric vehicles (EVs) have emerged as a sustainable alternative to conventional automobiles. Distinguished by their environmental friendliness, superior performance, reduced noise, and low maintenance requirements, EVs offer numerous advantages over traditional vehicles. The integration of electric vehicles with cloud computing has heralded a transformative shift in the automotive industry. However, as EVs become increasingly interconnected with the internet, various devices, and infrastructure, they become susceptible to cyberattacks. These attacks pose a significant risk to the safety, privacy, and functionality of both the vehicles and the broader transportation infrastructure. In this paper, we delve into the topic of electric vehicles and their connectivity to the cloud. We scrutinize the potential attack vectors that EVs are vulnerable to and the consequential impact on vehicle operations. Moreover, we outline both general and specific strategies aimed at thwarting these cyberattacks. Additionally, we anticipate future developments aimed at enhancing EV performance and reducing security risks.
- Open Access
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 9-17
A Systematic Investigation of Hardware and Software in Electric Vehicular Platform
In recent years, computing has been moving rapidly from the centralized cloud to various edges. For instance, electric vehicles (EVs), one of the next-generation computing platforms, have grown in popularity as a sustainable alternative to conventional vehicles. Compared with traditional ones, EVs have many unique advantages, such as less environmental pollution, high energy utilization efficiency, simple structure, and convenient maintenance etc. Meanwhile, it is also currently facing lots of challenges, including short cruising range, long charging time, inadequate supporting facilities, cyber security risks, etc. Nevertheless, electric vehicles are still developing as a future industry, and the number of users keeps growing, with governments and companies around the world continuously investing in promoting EV-related supply chains. As an emerging and important computing platform, we comprehensively study electric vehicular systems and state-of-the-art EV-related technologies. Specifically, this paper outlines electric vehicles' history, major architecture and components in hardware and software, current state-of-the-art technologies, and anticipated future developments to reduce drawbacks and difficulties.
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 9-17
Open AccessA Systematic Investigation of Hardware and Software in Electric Vehicular Platform
In recent years, computing has been moving rapidly from the centralized cloud to various edges. For instance, electric vehicles (EVs), one of the next-generation computing platforms, have grown in popularity as a sustainable alternative to conventional vehicles. Compared with traditional ones, EVs have many unique advantages, such as less environmental pollution, high energy utilization efficiency, simple structure, and convenient maintenance etc. Meanwhile, it is also currently facing lots of challenges, including short cruising range, long charging time, inadequate supporting facilities, cyber security risks, etc. Nevertheless, electric vehicles are still developing as a future industry, and the number of users keeps growing, with governments and companies around the world continuously investing in promoting EV-related supply chains. As an emerging and important computing platform, we comprehensively study electric vehicular systems and state-of-the-art EV-related technologies. Specifically, this paper outlines electric vehicles' history, major architecture and components in hardware and software, current state-of-the-art technologies, and anticipated future developments to reduce drawbacks and difficulties.
- Open Access
- 3 January 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (1) , 433
A Stacking Model-Based Classification Algorithm Is Used to Predict Social Phobia
University students, as a special group, face multiple psychological pressures and challenges, making them susceptible to social anxiety disorder. However, there are currently no articles using machine learning algorithms to identify predictors of social anxiety disorder in university students. This study aims to use a stacked ensemble model to predict social anxiety disorder in university students and compare it with other machine learning models to demonstrate the effectiveness of the proposed model. AUC and F1 are used as classification evaluation metrics. The experimental results show that in this dataset, the model combining logistic regression, Naive Bayes, and KNN algorithms as the first layer and Naive Bayes as the second layer performs better than traditional machine learning algorithms. This provides a new approach to studying social anxiety disorder.
- 3 January 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (1) , 433
Open AccessA Stacking Model-Based Classification Algorithm Is Used to Predict Social Phobia
University students, as a special group, face multiple psychological pressures and challenges, making them susceptible to social anxiety disorder. However, there are currently no articles using machine learning algorithms to identify predictors of social anxiety disorder in university students. This study aims to use a stacked ensemble model to predict social anxiety disorder in university students and compare it with other machine learning models to demonstrate the effectiveness of the proposed model. AUC and F1 are used as classification evaluation metrics. The experimental results show that in this dataset, the model combining logistic regression, Naive Bayes, and KNN algorithms as the first layer and Naive Bayes as the second layer performs better than traditional machine learning algorithms. This provides a new approach to studying social anxiety disorder.
- Open Access
- 9 November 2023
- Published by MDPI AG in Brain Sciences
- Vol. 13 (11) , 1571
Investigating Sex-Based Neural Differences in Autism and Their Extended Reality Intervention Implications
Autism Spectrum Disorder (ASD) affects millions of individuals worldwide, and there is growing interest in the use of extended reality (XR) technologies for intervention. Despite the promising potential of XR interventions, there remain gaps in our understanding of the neurobiological mechanisms underlying ASD, particularly in relation to sex-based differences. This scoping review synthesizes the current research on brain activity patterns in ASD, emphasizing the implications for XR interventions and neurofeedback therapy. We examine the brain regions commonly affected by ASD, the potential benefits and drawbacks of XR technologies, and the implications of sex-specific differences for designing effective interventions. Our findings underscore the need for ongoing research into the neurobiological underpinnings of ASD and sex-based differences, as well as the importance of developing tailored interventions that consider the unique needs and experiences of autistic individuals.
- 9 November 2023
- Published by MDPI AG in Brain Sciences
- Vol. 13 (11) , 1571
Open AccessInvestigating Sex-Based Neural Differences in Autism and Their Extended Reality Intervention Implications
Autism Spectrum Disorder (ASD) affects millions of individuals worldwide, and there is growing interest in the use of extended reality (XR) technologies for intervention. Despite the promising potential of XR interventions, there remain gaps in our understanding of the neurobiological mechanisms underlying ASD, particularly in relation to sex-based differences. This scoping review synthesizes the current research on brain activity patterns in ASD, emphasizing the implications for XR interventions and neurofeedback therapy. We examine the brain regions commonly affected by ASD, the potential benefits and drawbacks of XR technologies, and the implications of sex-specific differences for designing effective interventions. Our findings underscore the need for ongoing research into the neurobiological underpinnings of ASD and sex-based differences, as well as the importance of developing tailored interventions that consider the unique needs and experiences of autistic individuals.
- Open Access
- 11 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 142-147
An IoT-based System of Converting Handwritten Text to Editable Format via Gesture Recognition
Despite the prevalence of online learning or e-learning, the evolution of traditional classrooms has never stopped. Electronic classrooms, where classrooms equipped with projectors, computers, and sound systems, have become dominant in the last decade. The next step of evolution for electronic classrooms is smart classrooms. One of the most popular features of an electronic classroom is capturing video/photos of lecture content and extracting handwriting for note-taking. Various techniques have been implemented in order to extract handwriting from the video/photos of the lecture. However, there are still deficiencies in the existing techniques that prevent us from turning an electronic classroom into a smart classroom. This paper presents a real-time Internet of Things (loT)-based system to convert handwritten text into editable format by implementing Hand Gesture Recognition (HGR) with Raspberry Pi. Handwritten images are converted into editable format by using OpenCV and machine learning algorithms. For text conversion, the recognition of uppercase and lowercase alphabets, numbers, special characters, mathematical symbols, equations, graphs, and figures is included with the recognition of words, lines, blocks, and paragraphs. With the help of Raspberry Pi and IoT technologies, students can access the editable format of lecture notes via a desktop application, which helps students to edit and share notes and images according to their necessity. Implementation details and comprehensive evaluations of the system are summarized in the paper.
- 11 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 142-147
Open AccessAn IoT-based System of Converting Handwritten Text to Editable Format via Gesture Recognition
Despite the prevalence of online learning or e-learning, the evolution of traditional classrooms has never stopped. Electronic classrooms, where classrooms equipped with projectors, computers, and sound systems, have become dominant in the last decade. The next step of evolution for electronic classrooms is smart classrooms. One of the most popular features of an electronic classroom is capturing video/photos of lecture content and extracting handwriting for note-taking. Various techniques have been implemented in order to extract handwriting from the video/photos of the lecture. However, there are still deficiencies in the existing techniques that prevent us from turning an electronic classroom into a smart classroom. This paper presents a real-time Internet of Things (loT)-based system to convert handwritten text into editable format by implementing Hand Gesture Recognition (HGR) with Raspberry Pi. Handwritten images are converted into editable format by using OpenCV and machine learning algorithms. For text conversion, the recognition of uppercase and lowercase alphabets, numbers, special characters, mathematical symbols, equations, graphs, and figures is included with the recognition of words, lines, blocks, and paragraphs. With the help of Raspberry Pi and IoT technologies, students can access the editable format of lecture notes via a desktop application, which helps students to edit and share notes and images according to their necessity. Implementation details and comprehensive evaluations of the system are summarized in the paper.
- Open Access
- 12 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 104-111
Robust Efficient License Plate and Character Detection System Based on Simplified CNN
Current license plate recognition systems struggle with image noise reduction and license plate feature detecting processes. This paper presents an efficient and highly accurate license plate detection and character detection program based on the YOLO neural network, which is a simplified CNN-based neural network frame for robust image processing systems. Different than most approaches, the system we proposed simply requires a prioritized analysis of the dataset in order to evaluate potential noises inside images so that program implementations could be more effective and more targeted to design and optimize with YOLO neural network. With our presented system, the accuracy of license plate detection improves from 63% which is performed by traditional image processing methods to 90.3%.
- 12 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 104-111
Open AccessRobust Efficient License Plate and Character Detection System Based on Simplified CNN
Current license plate recognition systems struggle with image noise reduction and license plate feature detecting processes. This paper presents an efficient and highly accurate license plate detection and character detection program based on the YOLO neural network, which is a simplified CNN-based neural network frame for robust image processing systems. Different than most approaches, the system we proposed simply requires a prioritized analysis of the dataset in order to evaluate potential noises inside images so that program implementations could be more effective and more targeted to design and optimize with YOLO neural network. With our presented system, the accuracy of license plate detection improves from 63% which is performed by traditional image processing methods to 90.3%.
- 1 June 2022
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 94 (11) , 1243-1251
Optimization of Big Data Parallel Scheduling Based on Dynamic Clustering Scheduling Algorithm
- 1 June 2022
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 94 (11) , 1243-1251
Optimization of Big Data Parallel Scheduling Based on Dynamic Clustering Scheduling Algorithm
- 9 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 1986-1999
A Fully Authenticated Diffie-Hellman Protocol and Its Application in WSNs
The secure authenticated key establishment between nodes in Wireless Sensor Networks (WSNs) has not been fully solved in the existing schemes. It’s a good idea to apply the Diffie-Hellman protocol to address it perfectly, but the existing authenticated Diffie-Hellman (ADH) protocols are not perfect because their authentication are partial or delayed. In this paper, we first present a concept of full authentication and propose a new fully authenticated Diffie-Hellman (FADH) prototype with light-certificate-based authentication. And then based on the theory of elliptic curve cryptography, we construct the TinyADH (Tiny Authenticated Diffie-Hellman) protocol with applying the FADH in WSNs. Compared with the existing similar solutions, TinyADH has lower communication overload, is easier to implement into existing standards, and more secure under equivalent computational complexity. The experimental results show that using this scheme for a successful key agreement between two nodes averagely takes about 54 seconds on TelosB. Moreover, the simulation results indicate that repeated key agreement can improve the secure connectivity rate. However, considering the cost performance ratio, it is advisable to take 2 runs of the negotiation.
- 9 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 1986-1999
A Fully Authenticated Diffie-Hellman Protocol and Its Application in WSNs
The secure authenticated key establishment between nodes in Wireless Sensor Networks (WSNs) has not been fully solved in the existing schemes. It’s a good idea to apply the Diffie-Hellman protocol to address it perfectly, but the existing authenticated Diffie-Hellman (ADH) protocols are not perfect because their authentication are partial or delayed. In this paper, we first present a concept of full authentication and propose a new fully authenticated Diffie-Hellman (FADH) prototype with light-certificate-based authentication. And then based on the theory of elliptic curve cryptography, we construct the TinyADH (Tiny Authenticated Diffie-Hellman) protocol with applying the FADH in WSNs. Compared with the existing similar solutions, TinyADH has lower communication overload, is easier to implement into existing standards, and more secure under equivalent computational complexity. The experimental results show that using this scheme for a successful key agreement between two nodes averagely takes about 54 seconds on TelosB. Moreover, the simulation results indicate that repeated key agreement can improve the secure connectivity rate. However, considering the cost performance ratio, it is advisable to take 2 runs of the negotiation.