Article
Chemistry, Analytical
Amad Zafar, Shaik Javeed Hussain, Muhammad Umair Ali, Seung Won Lee
Summary: A wrapper-based metaheuristic feature selection framework was proposed for brain-computer interface (BCI) applications using functional near-infrared spectroscopy (fNIRS). Seven metaheuristic optimization algorithms were tested, and it was found that utilizing the features selected from these algorithms significantly improved classification accuracy. The grey wolf optimization (GWO) algorithm performed the best.
Article
Chemistry, Analytical
Asma Gulraiz, Noman Naseer, Hammad Nazeer, Muhammad Jawad Khan, Rayyan Azam Khan, Umar Shahbaz Khan
Summary: This study investigates the use of fNIRS-BCI systems for gait analysis and successfully distinguishes between walking and resting states using blood oxygenation and channel selection. The proposed methodology shows a higher classification accuracy and suggests potential applications in rehabilitation training for patients with motor dysfunction.
Article
Neurosciences
Rebecca J. St George, Oshadi Jayakody, Rebecca Healey, Monique Breslin, Mark R. Hinder, Michele L. Callisaya
Summary: The study found that older adults have higher levels of PFC activation during walking compared to younger adults. Fear of falling is a confounding factor. The interference between gait and a concurrent cognitive task is higher when the cognitive task requires inhibition.
Article
Psychiatry
Xiaoli Liu, Qianqian Chen, Fang Cheng, Wenhao Zhuang, Wenwu Zhang, Yiping Tang, Dongsheng Zhou
Summary: This study found working memory defects in adolescents with major depressive disorder compared to healthy controls based on mean oxy-hemoglobin changes, which can be useful for distinguishing adolescents with MDD from healthy controls.
JOURNAL OF PSYCHIATRIC RESEARCH
(2024)
Article
Psychology, Biological
Shumeng Hou, Ning Liu, Jun Zou, Xuejiao Yin, Xinyue Liu, Shi Zhang, Jiesheng Chen, Zhen Wei
Summary: This study investigated the neural mechanism underlying the different behavioral reactions of children with autism spectrum disorder (ASD) towards humanoid robots and humans. The results showed that children with ASD had lower neural activity in the right dorsolateral prefrontal cortex (DLPFC) when interacting with robots compared to humans. The neural activity in the left DLPFC was negatively correlated between the human and robot conditions in ASD children, while it was positively correlated in neurotypical children. The study highlights the importance of selective attention resources and the difficulty for children with ASD to ignore the attraction of robots.
INTERNATIONAL JOURNAL OF PSYCHOPHYSIOLOGY
(2022)
Article
Psychiatry
Juan Li, Junlin Mu, Chenyu Shen, Guanqun Yao, Kun Feng, Xiaoqian Zhang, Pozi Liu
Summary: Schizophrenia patients showed reduced left lateralization during CFT, potentially related to semantic deficits. The Chinese-CFT may be a more sensitive indicator of frontal-temporal dysfunction in schizophrenia.
FRONTIERS IN PSYCHIATRY
(2021)
Article
Geriatrics & Gerontology
Diego Orcioli-Silva, Rodrigo Vitorio, Victor Spiandor Beretta, Nubia Ribeiro da Conceicao, Priscila Nobrega-Sousa, Anderson Souza Oliveira, Lilian Teresa Bucken Gobbi
Summary: This study investigated the impact of PD motor subtypes on cortical activity during walking and obstacle avoidance. PIGD patients were found to require additional cognitive resources from the PFC for walking, while both TD and PIGD patients showed changes in brain activation related to motor/sensorimotor areas.
JOURNALS OF GERONTOLOGY SERIES A-BIOLOGICAL SCIENCES AND MEDICAL SCIENCES
(2021)
Article
Behavioral Sciences
Borja Blanco, Sarah Lloyd-Fox, Jannath Begum-Ali, Laura Pirazzoli, Amy Goodwin, Luke Mason, Greg Pasco, Tony Charman, Emily J. H. Jones, Mark H. Johnson, BASIS STAARS Team
Summary: This study investigates cortical specialization differences in infants at elevated likelihood of ASD and/or ADHD using fNIRS, revealing both common and distinct neurodevelopmental profiles. The findings contribute to understanding neurodiversity and provide important insights into the mechanisms underlying ASD and ADHD.
Article
Engineering, Biomedical
Jaeyoung Shin
Summary: Many feature selection methods were evaluated in fNIRS-related studies. The LIME algorithm, a feature selection method for fNIRS datasets, was assessed for its performance in terms of classification accuracy. Comparative analysis showed that LIME outperformed other methods and achieved significantly better classification accuracy than the benchmark methods. These findings suggest the effectiveness of LIME as a feature selection approach for fNIRS datasets.
BIOMEDICAL ENGINEERING LETTERS
(2023)
Article
Engineering, Mechanical
Si Chen, Kuo Li, Xiaoqi Qiao, Weimin Ru, Lin Xu
Summary: This paper studies the relationship between fractal surfaces and tactile perception. A multimodal tactile experiment was conducted using an EEG-fNIRS simultaneous joint imaging platform. The results show that fractal surfaces can be characterized by MFCC, sample entropy, and permutation entropy, and these three samples also have different brain functional reflections from fNIRS results.
TRIBOLOGY INTERNATIONAL
(2023)
Article
Biology
Kathleen Kang, Robert Rosenkranz, Kaan Karan, Ercan Altinsoy, Shu-Chen Li
Summary: This study investigates how congruence cues and congruence-based expectations shape perception in virtual reality (VR) by assessing brain responses during vehicle riding experiences in VR scenarios. The results suggest that plausible scenarios elicit greater cortical responses, and weaker but plausible stimulations result in greater responses in the sensorimotor cortex.
COMMUNICATIONS BIOLOGY
(2022)
Article
Neurosciences
Yoko Hasegawa, Ayumi Sakuramoto, Tatsuya Suzuki, Joe Sakagami, Masako Shiramizu, Yoshihisa Tachibana, Hiromitsu Kishimoto, Yumie Ono, Takahiro Ono
Summary: Distinct brain regions are associated with different emotional states. Our study found that hemodynamic response in the bilateral primary sensorimotor cortex significantly increased during gum chewing. Differential processing in the left prefrontal cortex might be responsible for the emotional states caused by palatable and unpalatable foods.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Psychiatry
Yufei Ren, Gang Cui, Xiaoqian Zhang, Kun Feng, Chenchao Yu, Pozi Liu
Summary: This study utilized fNIRS to characterize the cognitive, emotional, and behavioral regulation of the prefrontal working memory network for the first time. They identified functional brain imaging waveforms related to psychiatric disorders and represented three joint networks within the prefrontal working memory.
FRONTIERS IN PSYCHIATRY
(2022)
Article
Hospitality, Leisure, Sport & Tourism
Nicola J. Robinson, Catharine Montgomery, Laura Swettenham, Amy Whitehead
Summary: This study utilized functional Near Infrared Spectroscopy and Think Aloud method to investigate changes in cortical haemodynamics, conscious cognition, and physiological performance during a self-paced interval endurance activity. Trained cyclists showed higher power output compared to untrained cyclists, and conscious cognition may vary over time.
PSYCHOLOGY OF SPORT AND EXERCISE
(2021)
Article
Engineering, Biomedical
Yilei Zheng, Bohao Tian, Zhiqi Zhuang, Yuru Zhang, Dangxiao Wang
Summary: The study aims to validate the effectiveness of facilitating cortical excitability using a closed-loop visuomotor task. A novel visuomotor task was developed and the difficulty levels were adapted based on functional near-infrared spectroscopy measurements. Results showed that this task can increase neural activity in sensorimotor areas, with the potential to improve hand motor functions.
JOURNAL OF NEURAL ENGINEERING
(2022)
Review
Computer Science, Artificial Intelligence
Rayyan Azam Khan, Yigang Luo, Fang-Xiang Wu
Summary: The computer-aided diagnosis of hepatic lesions, focusing on ultrasonography, computed tomography, and magnetic resonance imaging, is reviewed in this study. The analysis covers preprocessing, attribute analysis, and classification techniques, with particular emphasis on the use of deep learning-based convolutional neural networks for classification. The study suggests that incorporating biopsy samples or pathological factors can improve prediction performance, and notes that further advancements in machine learning models are expected to address data limitation problems and enhance prediction performance.
Article
Computer Science, Artificial Intelligence
Rayyan Azam Khan, Yigang Luo, Fang-Xiang Wu
Summary: In this study, a deep-learning-based model is proposed for precise segmentation in hepatocellular carcinoma and metastasis clinical diagnosis. The model utilizes multi-scale approach, novel objective function, and extensive validation to achieve competitive performance. The results demonstrate the applicability and effectiveness of the proposed methodology in relevant medical segmentation applications.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Rayyan Azam Khan, Yigang Luo, Fang-Xiang Wu
Summary: This study proposes a deep learning-based multi-scaled generative adversarial network (GAN) for processing images with heterogeneous blur. By concatenating images of different scales and using residual image learning, the method is effective in reducing blur while preserving structural properties. Experimental results demonstrate its superior performance in image analysis.
IET IMAGE PROCESSING
(2022)
Article
Chemistry, Analytical
Asma Gulraiz, Noman Naseer, Hammad Nazeer, Muhammad Jawad Khan, Rayyan Azam Khan, Umar Shahbaz Khan
Summary: This study investigates the use of fNIRS-BCI systems for gait analysis and successfully distinguishes between walking and resting states using blood oxygenation and channel selection. The proposed methodology shows a higher classification accuracy and suggests potential applications in rehabilitation training for patients with motor dysfunction.
Article
Chemistry, Analytical
Muzzamil Ghaffar, Shakil R. Sheikh, Noman Naseer, Zia Mohy Ud Din, Hafiz Zia Ur Rehman, Muhammad Naved
Summary: This research proposes two novel non-intrusive load monitoring techniques using spectral clustering to extract individual appliance energy usage from the aggregate energy profile of a building. The performance evaluation shows that these techniques are competitive and viable, with advantages of low complexity, high accuracy, no training data requirement, and fast processing time.
Article
Chemistry, Analytical
Huma Hamid, Noman Naseer, Hammad Nazeer, Muhammad Jawad Khan, Rayyan Azam Khan, Umar Shahbaz Khan
Summary: This research presents a framework for brain signal classification using deep learning and machine learning approaches on functional near-infrared spectroscopy signals. The results demonstrate that deep learning approaches achieve higher classification accuracies compared to conventional machine learning approaches. Additionally, the control commands generated by these classifiers can be used for gait rehabilitation with lower limb exoskeletons.
Article
Clinical Neurology
Reza Mahini, Peng Xu, Guoliang Chen, Yansong Li, Weiyan Ding, Lei Zhang, Nauman Khalid Qureshi, Timo Hamalainen, Asoke K. Nandi, Fengyu Cong
Summary: The study developed a new method to estimate the optimal number of clusters using consensus clustering, which involves applying various clustering methods multiple times to find the average inner-similarity expectation for determining the optimal cluster number.
Article
Computer Science, Artificial Intelligence
Nabeeha Ehsan Mughal, Muhammad Jawad Khan, Khurram Khalil, Kashif Javed, Hasan Sajid, Noman Naseer, Usman Ghafoor, Keum-Shik Hong
Summary: In this study, a novel RP-based CNN-LSTM algorithm was proposed for the integrated classification of fNIRS EEG for hybrid BCI applications. The results show that the model can extract essential features without downsampling and leverage LSTM to learn the time-dependence relation of brain activity, achieving high accuracies.
FRONTIERS IN NEUROROBOTICS
(2022)
Article
Computer Science, Artificial Intelligence
Mathias Mantelli, Farzan M. M. Noori, Diego Pittol, Renan Maffei, Jim Torresen, Mariana Kolberg
Summary: This paper focuses on the problem of object search in unknown indoor environments and proposes a method that reduces search costs by utilizing semantic information and temporal reasoning. The method shows high efficiency and robustness in finding target objects, as demonstrated by simulation experiments and tests on real datasets.
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
(2022)
Article
Engineering, Biomedical
Rayyan Azam Khan, Yigang Luo, Fang-Xiang Wu
Summary: In this study, a multilevel generative adversarial network (GAN) is proposed to enhance computed tomographic (CT) images for liver cancer diagnosis. The performance of the proposed method is investigated using three publicly available datasets, and it achieves good results in terms of performance metrics and computer-aided diagnosis. The effectiveness of the proposed multi-level GAN in producing enhanced biomedical images with preserved structural details and reduction in artifacts is demonstrated, and it shows consistently better performance among three datasets for computer-aided diagnosis.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Multidisciplinary
Aaqib Majeed, Naser Golsanami, Bin Gong, Qazi Adnan Ahmad, Samia Rifaqat, Ahmad Zeeshan, Farzan Majeed Noori
Summary: This study investigates the 2D bioconvection magneto-hydrodynamic (MHD) flow and heat transfer of a non-Newtonian (Casson) nanofluid model. The impact of thermal radiation, velocity slip, Brownian motion, and thermophoresis containing gyrotactic microorganisms over a nonlinear surface is demonstrated. The study shows the effects of different cases and convergence parameters on the electrically conducting flow. Numerical analysis using the Bvp4c scheme reveals significant agreement with previous results.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Computer Science, Information Systems
Muzzamil Ghaffar, Shakil Rehman Sheikh, Noman Naseer, Syed Ali Usama, Bashir Salah, Soliman Abdul Karim Alkhatib
Summary: The widespread use of smart meter data in modern grids is driving stakeholders to utilize it for demand response management and achieving energy sustainability goals. Non-Intrusive Load Monitoring (NILM) is being used as a method to disaggregate individual devices from a combined load profile. This study combines two spectral clustering strategies using voting-based consensus clustering technique to achieve the benefits of both strategies and achieves enhanced overall performance.
Proceedings Paper
Engineering, Electrical & Electronic
David Andreas Bordvik, Jie Hou, Farzan M. Noori, Md Zia Uddin, Jim Torresen
Summary: This paper investigates the use of depth images and radar presence data for detecting emergencies in home monitoring systems. The data is represented using recurrence plots and wavelet transformations, and fused at data-level, feature-level, and decision-level. The decision-level fusion, which combines depth images and presence data, achieved the highest accuracy of 99.98%.
2022 INTERNATIONAL CONFERENCE ON ELECTRONICS, INFORMATION, AND COMMUNICATION (ICEIC)
(2022)
Article
Health Care Sciences & Services
Yngve Lamo, Suresh K. Mukhiya, Fazle Rabbi, Amin Aminifar, Svein Lillehaug, Jim Torresen, Minh Pham, Ulysse Cote-Allard, Farzan M. Noori, Frode Guribye, Yavuz Inal, Eivind Flobakk, Jo D. Wake, Sunniva Myklebost, Astri J. Lundervold, Aasa Hammar, Emilie Nordby, Smiti Kahlon, Robin Kenter, Ragnhild J. T. Sekse, Kristine F. Griffin, Petter Jakobsen, Ketil Joachim Odegaard, Yngvar S. Skar, Tine Nordgreen
Summary: This paper summarizes the research findings related to information technology after 5 years of the INTROducing Mental health through Adaptive Technology project. The aim was to improve mental healthcare by introducing new technologies for adaptive interventions. The challenges of internet-delivered psychological treatments, including artificial intelligence, human-computer interaction, and software engineering, are emphasized. The main findings include a reference architecture for adaptive internet-delivered psychological treatment systems, a development process aligned with intervention design, and software artifacts.
Article
Computer Science, Information Systems
Arshia Arif, M. Jawad Khan, Kashif Javed, Hasan Sajid, Saddaf Rubab, Noman Naseer, Talha Irfan Khan
Summary: This study presents a novel method for more accurate detection of the hemodynamic response using a multimodal brain-computer interface (BCI). An integrated classifier is developed to achieve better classification accuracy by combining EEG and fNIRS signals. The results show that the combined EEG-fNIRS VPA method yields significantly higher classification accuracy compared to other classifiers, demonstrating the feasibility of improving classification performance using multimodal VPA for EEG-fNIRS hybrid data.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)