Article
Neurosciences
Yuanyuan Gao, Hanqing Chao, Lora Cavuoto, Pingkun Yan, Uwe Kruger, Jack E. Norfleet, Basiel A. Makled, Steven Schwaitzberg, Suvranu De, Xavier Intes
Summary: This study presents a motion artifact removal method for fNIRS data using a deep learning approach. The developed deep learning model, with a specific loss function and generated training data, outperforms conventional methods in removing motion artifacts.
Review
Chemistry, Analytical
Kira Flanagan, Manob Jyoti Saikia
Summary: This paper presents an overview of neurofeedback devices for consumer use, discussing their potential applications in clinical settings. While there is some evidence supporting the efficacy of neurofeedback, the research is still inconclusive. The paper compares different devices in terms of treatment parameters, structural composition, available software, and clinical appeal. Based on this comparison, the future applications of these systems are discussed.
Article
Biotechnology & Applied Microbiology
Xuhong Li, Feng Fang, Rihui Li, Yingchun Zhang
Summary: This study used functional brain controllability analysis to accurately interpret and assess motor control deficits caused by stroke. The results indicated that stroke patients had lower modal controllability in the executive control network and supplementary motor cortex compared to healthy subjects. Furthermore, the baseline controllability of the primary motor cortex was significantly correlated with clinical scores. These findings provide new insights into the understanding of motor control deficits caused by stroke.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2022)
Article
Psychology, Developmental
Velu Prabhakar Kumaravel, Elisabetta Farella, Eugenio Parise, Marco Buiatti
Summary: This study focuses on the removal of artifacts in EEG data of human newborns and proposes the NEAR pipeline for artifact removal. The validation results on simulated and real data show that NEAR outperforms existing methods in removing non-stereotypical artifacts in newborns.
DEVELOPMENTAL COGNITIVE NEUROSCIENCE
(2022)
Article
Engineering, Biomedical
Hongzuo Chu, Yong Cao, Jin Jiang, Jiehong Yang, Mengyin Huang, Qijie Li, Changhua Jiang, Xuejun Jiao
Summary: Through analyzing feature importance and optimizing signal acquisition configuration, a more accurate and convenient EEG-fNIRS-based mental workload detection method was developed. The number of EEG channels has an impact on detection accuracy, with the optimal configuration being 26 EEG channels and two fNIRS channels.
BIOMEDICAL ENGINEERING ONLINE
(2022)
Article
Engineering, Biomedical
Matteo Dora, David Holcman
Summary: This paper proposes a new wavelet-based method for removing artifacts from single-channel EEGs. The method adaptively attenuates artifacts of different nature through data-driven renormalization of wavelet components and demonstrates superior performances on different kinds of artifacts and signal-to-noise levels. The proposed method provides a valuable tool to remove artifacts in real-time EEG applications with few electrodes, such as monitoring in special care units.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Qi Zhu, Yangming Shi, Jing Du
Summary: With the rapid development of building information technologies, wayfinding information has become more accessible, leading to the emergence of cognitive load related to processing such information. This paper tested a functional near-infrared spectroscopy (fNIRS)-based method to monitor and classify cognitive loads during wayfinding information processing, showing satisfactory performance in classifying load changes driven by task difficulty levels. Personalized models were found to be necessary for accurate classification based on the neuroimaging data.
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
(2021)
Article
Biochemical Research Methods
Lin Gao, Yuhui Wei, Yifei Wang, Gang Wang, Quan Zhang, Jianbao Zhang, Xiang Chen, Xiangguo Yan
Summary: This study introduces a hybrid artifact detection and correction approach for fNIRS signals, improving the viability of fNIRS as a functional neuroimaging modality by detecting and correcting artifacts such as baseline shift, slight oscillation, and severe oscillation.
JOURNAL OF BIOMEDICAL OPTICS
(2022)
Article
Clinical Neurology
Vidhya Vijayakrishnan Nair, Brianna R. Kish, Ho-Ching (Shawn) Yang, Zhenyang Yu, Hang Guo, Yunjie Tong, Zhenhu Liang
Summary: This study aims to develop a comprehensive multimodal anesthesia depth monitor by understanding the neural and hemodynamic responses during general anesthesia using fNIRS and EEG. The research found a significant decrease in the complexity and power of fNIRS signals during the maintenance phase of anesthesia and variations in responses to anesthesia between adults and children. Multimodal approach could provide a reliable measure of anesthesia depth, taking into account specific differences between age groups.
CLINICAL NEUROPHYSIOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Yuqing Li, Aiping Liu, Jin Yin, Chang Li, Xun Chen
Summary: In this article, a simple yet effective segmentation-denoising network (SDNet) is proposed for artifact removal in electroencephalography (EEG). It can differentiate noisy EEG segments from clean ones via semantic segmentation, avoiding distortion caused by processing clean segments. Experimental results demonstrate that SDNet outperforms state-of-the-art approaches, providing a novel way to reconstruct artifact-attenuated EEG signals and potentially benefiting EEG-based diagnosis and treatment.
IEEE SENSORS JOURNAL
(2023)
Article
Neurosciences
J. Adam Noah, Xian Zhang, Swethasri Dravida, Courtney DiCocco, Tatsuya Suzuki, Richard N. Aslin, Ilias Tachtsidis, Joy Hirsch
Summary: This study compared short-channel temporal regression and spatial principal component filtering strategies for removing non-neural signals in fNIRS data, finding that both methods effectively eliminate non-neural components. Utilizing either technique is sufficient for removing these interfering signals.
Review
Engineering, Biomedical
Wajid Mumtaz, Suleman Rasheed, Alina Irfan
Summary: This manuscript discusses the challenges of EEG artifact removal methods and provides recommendations to address them. It also introduces Matlab and Python-based toolboxes for EEG preprocessing. Overall, the manuscript provides information on various EEG artifact removal methods, and the recommendations offered can serve as guidelines for selecting appropriate tools and methods for EEG artifact corrections.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Neurosciences
Xue Deng, Chuyao Jian, Qinglu Yang, Naifu Jiang, Zhaoyin Huang, Shaofeng Zhao
Summary: This study investigated the analgesic effect of different virtual reality interactive modes using functional near-infrared spectroscopy (fNIRS). It found that both the active mode and motor imagery (MI) mode had a larger analgesic effect compared to the passive mode. The activated cortical regions involved motor and cognitive functions.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Chemistry, Analytical
Hayder R. Al-Omairi, Sebastian Fudickar, Andreas Hein, Jochem W. Rieger
Summary: Functional near-infrared spectroscopy (fNIRS) is a non-invasive neuroimaging technique that allows participants to move freely. An improved algorithmic approach combining wavelet and correlation-based signal improvement (WCBSI) was proposed for motion artifact (MA) correction. The WCBSI algorithm consistently outperformed other correction approaches, demonstrating its potential as the best algorithm for MA correction.
Article
Computer Science, Interdisciplinary Applications
Yangming Shi, Connor Johnson, Pengxiang Xia, John Kang, Oshin Tyagi, Ranjana K. Mehta, Jing Du
Summary: Disorientation is a leading cause of firefighter injuries and fatalities. This study examined the impact of different types of spatial information on firefighters' spatial memory development and found that route or survey information had a positive effect on task performance, while landmark and map information had a negative effect.
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
(2022)
Article
Neurosciences
Idris Fatakdawala, Hasan Ayaz, Adrian Safati, Mohammad Nazmus Sakib, Peter A. Hall
Summary: This study examined the effects of excitatory brain stimulation on eating behavior, and found that targeting the dorsolateral prefrontal cortex (dlPFC) and dorsomedial prefrontal cortex (dmPFC) had different effects. Stimulation of the dlPFC enhanced interference control, while stimulation of the dmPFC reduced delay discounting. Gender also moderated the effects during the taste test, with females in the dmPFC stimulation group showing paradoxical increases in food consumption.
SOCIAL COGNITIVE AND AFFECTIVE NEUROSCIENCE
(2023)
Article
Psychology, Clinical
Girija Kaimal, Katrina Carroll-Haskins, Yigit Topoglu, Arun Ramakrishnan, Asli Arslanbek, Hasan Ayaz
Summary: The study investigated differences in PFC activation during two VR drawing conditions with and without fragrance stimulus, finding that rote tracing resulted in higher PFC activity than creative self-expression. Age and gender were observed to impact responsiveness to fragrance.
Article
Computer Science, Artificial Intelligence
Dafeng Wang, Hongbo Liu, Naiyao Wang, Yiyang Wang, Hua Wang, Sean McLoone
Summary: In this paper, a novel Sequence Entropy Energy-based Model (SEEM) is proposed to address the limitations of current trajectory prediction models. SEEM achieves diversity in candidate trajectory generation by optimizing sequence entropy, and improves accuracy and stability through probability distribution clipping mechanism and energy network. Experimental results demonstrate that SEEM outperforms the state-of-the-art approaches in terms of diversity, accuracy, and stability of pedestrian trajectory prediction.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Automation & Control Systems
Federico Zocco, Sean McLoone
Summary: Reducing data dimensionality is crucial for improving model performance in data analysis applications, and unsupervised variable selection techniques can help select the best subset of variables without prior information. The Recovery of Linear Components (RLC) method strikes a balance between linear and non-linear techniques, providing higher accuracy, similar robustness, and faster training times compared to similar complex autoencoders.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Health Care Sciences & Services
Lili Zhang, Himanshu Vashisht, Alekhya Nethra, Brian Slattery, Tomas Ward
Summary: Individuals with chronic pain were found to be more reward-driven and less consistent in decision-making in a laboratory-in-the-field experiment. The study also revealed that patients were quicker in updating their behavior and more sensitive to rewards.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2022)
Article
Psychology, Clinical
Laura A. Berner, Samantha R. Winter, Hasan Ayaz, Patricia A. Shewokis, Meltem Izzetoglu, Rachel Marsh, Jennifer A. Nasser, Alyssa J. Matteucci, Michael R. Lowe
Summary: This study used fNIRS to measure activation in the prefrontal cortices of individuals with bulimia nervosa (BN) and healthy controls (HC) during eating inhibition tasks. The results showed that individuals with BN made more errors in inhibiting eating responses. Those with more severe loss of control (LOC) eating and stronger binge eating feelings exhibited abnormal activation in specific brain regions associated with eating inhibition. Lower activation in specific brain region was also related to more frequent and severe LOC eating in the overall BN sample. These findings suggest that diminished prefrontal cortex activation may contribute to more severe eating-specific control deficits in BN.
PSYCHOLOGICAL MEDICINE
(2023)
Article
Computer Science, Information Systems
Xin Jiang, Zhengxin Yu, Chao Hai, Hongbo Liu, Xindong Wu, Tomas Ward
Summary: This article proposes a transfer learning model called DNformer for predicting temporal link sequences in dynamic networks. By sequencing the structural dynamic evolution into consecutive links, capturing serial correlation using self-attention, and utilizing structural encoding to perceive the importance and correlation of links, the DNformer model outperforms other state-of-the-art TLP methods in various dynamic network problems.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2022)
Review
Computer Science, Theory & Methods
Eoin Brophy, Zhengwei Wang, Qi She, Tomas Ward
Summary: This article reviews the variants of generative adversarial networks (GANs) designed for time series related applications. It proposes a classification of discrete-variant GANs and continuous-variant GANs, showcasing the latest literature, architectures, results, and applications in this field. The article also covers evaluation metrics, privacy measures, and future directions for dealing with sensitive data.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Information Systems
Yifeng Huang, Long Cheng, Lianting Xue, Cong Liu, Yuancheng Li, Jianbin Li, Tomas Ward
Summary: The article discusses utilizing a deep adversarial imitation reinforcement learning (AIRL) framework to address the scheduling of time-sensitive cloud jobs, aiming to maximize job successful rate and reduce job response time. Experimental results demonstrate that AIRL generally outperforms existing cloud job scheduling approaches across different real-time workload and computing resource configurations.
IEEE SYSTEMS JOURNAL
(2022)
Article
Health Care Sciences & Services
Lili Zhang, Greta Monacelli, Himanshu Vashisht, Winfried Schlee, Berthold Langguth, Tomas Ward
Summary: This study aims to assess impairments in adaptive learning ability among people with tinnitus through investigating their decision-making performance. Computational modeling methods will be used to quantify tinnitus severity and understand its cognitive impact. The study will also explore the fluctuation of tinnitus symptoms on decision-making through a longitudinal experimental design.
JMIR RESEARCH PROTOCOLS
(2022)
Article
Engineering, Biomedical
Divya Jain, Valentina Graci, Megan E. Beam, Hasan Ayaz, Laura A. Prosser, Christina L. Master, Catherine C. McDonald, Kristy B. Arbogast
Summary: Adolescents with concussion show poorer gait performance and lower neural efficiency under high cognitive demand, suggesting a reduced ability for the concussed adolescent brain to compensate when attention is divided between two tasks.
CLINICAL BIOMECHANICS
(2023)
Article
Neurosciences
Jesse A. Mark, Hasan Ayaz, Daniel E. Callan
Summary: This study aims to assess the effects of transcranial direct-current stimulation (tDCS) and feedback training on task performance, brain activity, and connectivity. The active stimulation improved piloting performance and increased brain activity and connectivity in flight-related areas. These findings can guide neurostimulation in pilot training and be applied in other complex real-world tasks.
Article
Computer Science, Artificial Intelligence
Kai Liu, Hongbo Liu, Tao Wang, Guoqiang Hu, Tomas E. E. Ward, C. L. Philip Chen
Summary: A graph neural network (GNN) is a powerful architecture for semi-supervised learning. This article proposes a novel framework called graph coneighbor neural network (GCoNN) for node classification. GCoNN consists of two modules: GCoNN(G) and GCoNN(G)?. GCoNN(G) establishes the fundamental prototype for attribute learning while GCoNNi learns neighbor dependence through pseudolabels generated by GCoNN(G).
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Psychiatry
Megan N. N. Parker, Helen Burton Murray, Amani D. D. Piers, Alexandra Muratore, Michael R. R. Lowe, Stephanie M. M. Manasse, Hasan Ayaz, Adrienne S. S. Juarascio
Summary: This study examined the neural correlates of food-related reappraisal in adults with obesity, with and without binge eating (BE). Using functional near-infrared spectroscopy (fNIRS), the study found no significant differences in inhibitory prefrontal cortex activity between the group with BE and the control group.
EATING AND WEIGHT DISORDERS-STUDIES ON ANOREXIA BULIMIA AND OBESITY
(2023)
Article
Engineering, Electrical & Electronic
Lei Wang, Meltem Izzetoglu, Juan Du, Hasan Ayaz
Summary: This study comprehensively investigated NIRS measurements using phantoms and simulated head models of different age groups with intracranial hematoma development. The results showed a high correlation between phantom measurements and simulated model-based measurements, and indicated that younger head models were more affected by the presence of hematoma.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)