Article
Computer Science, Artificial Intelligence
Antonio Rafael Sabino Parmezan, Huei Diana Lee, Newton Spolaor, Feng Chung Wu
Summary: The paper addresses the metalearning challenge of recommending feature selection algorithms through a novel meta-feature engineering model. This model considers a broad collection of meta-features that enable the study of the relationship between dataset properties and feature selection algorithm performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Arpita Chaudhuri, Debasis Samanta, Monalisa Sarma
Summary: This paper discusses the basic methods of unsupervised feature selection and proposes a UFS scheme suitable for mixed datasets. The proposed two-phase process results in a better subset of features.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Yousef Rezaei Tabar, Kaare B. Mikkelsen, Mike Lind Rank, Martin Christian Hemmsen, Preben Kidmose
Summary: This study aimed to represent sleep EEG patterns using a minimum number of features without significant loss in performance. Through feature selection algorithms, it was found that 5 to 11 features could represent the whole feature set without performance loss. Features were divided into groups, with relative power features identified as the most informative.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Chemistry, Analytical
Xilin Li, Frank H. F. Leung, Steven Su, Sai Ho Ling
Summary: This study proposes a multi-error-reduction (MER) classification system with multi-domain features to detect obstructive sleep apnea (OSA). By utilizing a two-stage feature selection and machine learning methods, the accuracy and stability of automatic OSA diagnosis are improved.
Article
Engineering, Electrical & Electronic
Dongdong Zhou, Qi Xu, Jian Wang, Hongming Xu, Lauri Kettunen, Zheng Chang, Fengyu Cong
Summary: This study proposes two balancing methods to overcome the class imbalance problem in automatic sleep-stage classification tasks. Experimental results demonstrate that the proposed methods outperform other approaches in terms of classification accuracy.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Engineering, Biomedical
Hossein Najafzadeh, Mahdad Esmaeili, Sara Farhang, Yashar Sarbaz, Seyed Hossein Rasta
Summary: This study introduced a new method based on the adaptive neuro fuzzy inference system (ANFIS) to classify EEG signals of schizophrenia patients and control participants, achieving accuracies near 100%. Specific EEG channels were found to have the most discriminatory information between the two groups, leading to the development of a new decision support system with high accuracy in separating schizophrenia patients from healthy subjects.
PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE
(2021)
Article
Multidisciplinary Sciences
Hengyan Guo, Yang Di, Xingwei An, Zhongpeng Wang, Dong Ming
Summary: This paper proposes an automatic sleep staging system based on forehead electrophysiological signals, which extracts features and uses machine learning algorithms to classify four sleep stages. In the validation experiments, the proposed method achieved high classification accuracy and kappa coefficient. The proposed method has higher portability, which can facilitate the application of long-term monitoring of sleep quality in the future.
Article
Engineering, Biomedical
Jamileh Karimi, Babak Mohammadzadeh Asl
Summary: This study presents a signal processing/machine learning approach for classifying targeted sleep arousal regions in PSG signals, focusing on feature subset selection and consensus methods. By utilizing optimization algorithms and feature combination, the most discriminative feature set was identified to achieve automatic detection of sleep arousal regions.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Biomedical
Xiaopeng Ji, Yan Li, Peng Wen
Summary: A novel jumping knowledge spatial-temporal graph convolutional network (JK-STGCN) is proposed for classifying sleep stages. It utilizes multi-channel bio-signals and combines graph convolutions with traditional convolutions to extract spatial and temporal features. Experimental results demonstrate the competitive performance and high computation speed of this approach in sleep stage classification.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Engineering, Biomedical
Haotian Yao, Tao Liu, Ruiyang Zou, Shengnan Ding, Yan Xu
Summary: Sleep stage classification is important in diagnosing and monitoring sleep diseases. The challenges of exploring spatial-temporal relationship and data insufficiency led to the proposal of a vision Transformer-based architecture for multi-channel polysomnogram signals. The method achieved state-of-the-art performance by leveraging spatial and temporal encoders, as well as tailored image generation and transfer learning.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Computer Science, Information Systems
Yang Dai, Xiuli Li, Shanshan Liang, Lukang Wang, Qingtian Duan, Hui Yang, Chunqing Zhang, Xiaowei Chen, Longhui Li, Xingyi Li, Xiang Liao
Summary: Automatic sleep stage classification is crucial for measuring sleep quality and diagnosing sleep disorders. This study presents MultiChannelSleepNet, a transformer encoder-based model, for classifying sleep stages using multichannel polysomnography data. The proposed method achieves higher classification performance compared to state-of-the-art techniques.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Engineering, Biomedical
Rym Nihel Sekkal, Fethi Bereksi-Reguig, Daniel Ruiz-Fernandez, Nabil Dib, Samira Sekkal
Summary: This study compares traditional machine learning algorithms with deep learning methods, and the results show that support vector machine and random forest are just as valid as feature-based neural networks in predicting sleep stages classification, with performance similar to the state of the art.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Review
Neurosciences
Xiangyu Qian, Ye Qiu, Qingzu He, Yuer Lu, Hai Lin, Fei Xu, Fangfang Zhu, Zhilong Liu, Xiang Li, Yuping Cao, Jianwei Shuai
Summary: The detection of sleep arousals is crucial for diagnosing sleep disorders and reducing the risk of complications. Manual scoring by sleep experts is time-consuming, so the development of an efficient automatic detection system is important. Deep neural networks are likely to be the main method for automatic arousal detection in the future.
Article
Engineering, Biomedical
Adnan Albaba, Ivan Castro, Pascal Borzee, Bertien Buyse, Dries Testelmans, Carolina Varon, Sabine Van Huffel, Tom Torfs
Summary: The objective of this study was to design an algorithm for classifying ccBioZ segments based on signal quality to enhance confidence in extracted respiratory activity monitoring information, such as respiration rate. This was achieved through extracting and selecting features to find the best balance between classifier performance and the number of features used. Testing the algorithm on three datasets from 12 subjects showed high accuracy, sensitivity, specificity, and balanced accuracy, indicating the reliability and robustness of the approach.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Artificial Intelligence
Xiaoquan Ke, Man Wai Mak, Helen M. Meng
Summary: This paper presents a two-step feature selection approach for dementia detection using diverse features extracted from spoken language. The approach utilizes filter methods for pre-screening features and introduces a novel feature ranking method called dual dropout ranking (DDR) to select the most discriminative features. Experimental results show that the approach significantly reduces feature dimensionality while identifying small feature subsets that achieve comparable or even superior performance compared to the full feature set.
Article
Computer Science, Artificial Intelligence
Aniana Cruz, Gabriel Pires, Ana Lopes, Carlos Carona, Urbano J. Nunes
Summary: This article introduces a self-paced P300-based brain-computer interface control solution combined with dynamic time-window commands and a collaborative controller for brain-controlled wheelchairs. The proposed approach achieved high driving accuracy in experiments and received positive feedback from users, indicating potential usability improvements for BCWs in home settings.
IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Camila Dias, Diana Costa, Teresa Sousa, Joao Castelhano, Veronica Figueiredo, Andreia C. Pereira, Miguel Castelo-Branco
Summary: Error monitoring is a metacognitive process that allows us to detect and signal errors after a response has been made. This study investigated the neural substrates of error monitoring during the integration of facial expression cues using electroencephalography (EEG). The results showed that theta band activity in the midfrontal region is not only an index of error monitoring, but also a requisite for success.
Article
Chemistry, Multidisciplinary
Ricardo Pereira, Guilherme Carvalho, Luis Garrote, Urbano J. Nunes
Summary: This study presents an evaluation of two MOT methods for navigation tasks of assistive mobile robots and proposes improved data association cost matrices. The experimental results show promising improvements in the majority of evaluation metrics with the new cost matrices. Additionally, the pipeline composed of the detector and tracking module achieves satisfactory frame rate values.
APPLIED SCIENCES-BASEL
(2022)
Article
Neurosciences
Joao Estiveira, Camila Dias, Diana Costa, Joao Castelhano, Miguel Castelo-Branco, Teresa Sousa
Summary: This study aims to investigate the pre- and post-error EEG patterns and the neuronal mechanisms leading to erroneous actions. The study found significant differences in reaction time, number, and type of errors between different types of motor responses. Both saccadic responses and keypress responses led to similar EEG patterns, supporting previous evidence. Additionally, the study found pre-error decreased theta activity independent of the type of action. Source analysis results suggested different brain regions as the origin of these pre- and post-error patterns.
FRONTIERS IN HUMAN NEUROSCIENCE
(2022)
Article
Biochemical Research Methods
Sirvan Khalighi, Peronne Joseph, Deepak Babu, Salendra Singh, Thomas LaFramboise, Kishore Guda, Vinay Varadan
Summary: SYSMut is an extendable systems biology platform that can infer the biological consequences of gene mutations by integrating multiomics profiles. It has been used to identify driver genes across 29 cancers and discover new therapeutic targets in head and neck squamous cell cancer.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Behavioral Sciences
Andreia Verdade, Teresa Sousa, Joao Castelhano, Miguel Castelo-Branco
Summary: This study investigates the underlying neural circuitry of perceptual hysteresis in facial emotion recognition using dynamic transitions between emotional expressions. The findings suggest the involvement of face-selective visual areas and the right anterior insula in perceptual persistence.
COGNITIVE AFFECTIVE & BEHAVIORAL NEUROSCIENCE
(2022)
Article
Multidisciplinary Sciences
Mehdi Baratchian, Ritika Tiwari, Sirvan Khalighi, Ankur Chakravarthy, Wei Yuan, Michael Berk, Jianneng Li, Amy Guerinot, Johann de Bono, Vladimir Makarov, Timothy A. Chan, Robert H. Silverman, George R. Stark, Vinay Varadan, Daniel D. De Carvalho, Abhishek A. Chakraborty, Nima Sharifi
Summary: Antiandrogen strategies are commonly used in prostate cancer treatment, but they often lead to drug resistance. This study reveals that antiandrogen treatment activates retroelements (REs), which triggers an interferon response and inhibits tumor growth. Furthermore, the study identifies H3K9 trimethylation as an essential epigenetic adaptation to antiandrogens, as it suppresses REs and prevents the activation of interferon signaling and glucocorticoid receptor. The expression of terminal H3K9me3 writers is associated with poor patient outcomes in hormonal therapy.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)
Article
Chemistry, Analytical
Luis Garrote, Joao Perdiz, Luis A. da Silva Cruz, Urbano J. Nunes
Summary: The increasing demand for reliable and safe autonomous driving requires more granular data for object detection. Offloading computation to roadside infrastructure and compressing voluminous sensor data for transmission are solutions to the computational complexity challenges. Results indicate that point cloud compression has a minor impact on object detection performance, especially for larger objects, showing a competitive advantage when using depth maps for object detection.
Article
Engineering, Biomedical
Gabriel Pires, Aniana Cruz, Diogo Jesus, Mine Yasemin, Urbano J. Nunes, Teresa Sousa, Miguel Castelo-Branco
Summary: This study proposes a gamified brain-computer interface (BCI) based on non-volitional neurofeedback for cognitive training in individuals with autism spectrum disorders (ASDs). The results show the feasibility of the proposed methodology and indicate the potential for further clinical experimentation to assess its effectiveness in ASD participants.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Engineering, Biomedical
Mine Yasemin, Aniana Cruz, Urbano J. Nunes, Gabriel Pires
Summary: This study compares the impact of different classification pipelines on the detection accuracy of Error-related potentials (ErrPs), and identifies the most robust classification method and optimal parameters. The experimental results show that classification accuracy is highly dependent on user tasks and signal quality, providing important guidelines for the design of ErrP-based brain-computer interface (BCI) tasks.
JOURNAL OF NEURAL ENGINEERING
(2023)
Review
Neurosciences
Carolina Travassos, Alexandre Sayal, Bruno Direito, Joao Pereira, Teresa Sousa, Miguel Castelo-Branco
Summary: This study systematically reviews and analyzes the methodologies to assess the safety and compatibility of somatosensory stimulation devices in the magnetic resonance environment. The findings show a lack of uniformity in testing methodologies and suggest an assessment methodology for devices used in this environment.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Multidisciplinary Sciences
Joao Pereira, Bruno Direito, Michael Luhrs, Miguel Castelo-Branco, Teresa Sousa
Summary: Functional near-infrared spectroscopy (fNIRS) is a cost-efficient and portable alternative to functional magnetic resonance imaging (fMRI) for assessing cortical activity changes based on hemodynamic signals. This study aimed to analyze the spatial correspondence between fMRI and fNIRS in motor-network regions using a multimodal approach. The results showed significant activation in fMRI data using subject-specific fNIRS-based cortical signals as predictors of interest, indicating the possibility of translating neuronal information from fMRI to fNIRS motor-coverage setup with high spatial correspondence.
SCIENTIFIC REPORTS
(2023)
Proceedings Paper
Engineering, Biomedical
Joao Ruivo Paulo, Teresa Sousa, Joao Perdiz, Nicoli Leal, Paulo Menezes, Tingting Zhu, Gabriel Pires, Miguel Castelo-Branco
Summary: This paper presents a framework for collecting motion-related data through electroencephalography (EEG) recordings during walking and dancing imitation tasks. The results show that the modulation of mu power over the central EEG channels by action/perception cycles is discriminative of all motion-related tasks.
2023 IEEE 7TH PORTUGUESE MEETING ON BIOENGINEERING, ENBENG
(2023)
Article
Engineering, Biomedical
Joao Ruivo Paulo, Gabriel Pires, Urbano J. Nunes
Summary: This paper explores two methodologies for drowsiness detection using EEG signals in a sustained-attention driving task, focusing on cross-subject zero calibration. Comparison of both techniques on a public dataset of 27 subjects shows a superior balanced accuracy of up to 75.87% for leave-one-out cross-validation, demonstrating the possibility to pursue cross-subject zero calibration design.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2021)
Article
Computer Science, Interdisciplinary Applications
Alireza Karimi, Reza Razaghi, Siddharth Daniel D'costa, Saeed Torbati, Sina Ebrahimi, Seyed Mohammadali Rahmati, Mary J. Kelley, Ted S. Acott, Haiyan Gong
Summary: This study investigated the biomechanical properties of the conventional aqueous outflow pathway using fluid-structure interaction. The results showed that the distribution of aqueous humor wall shear stress within this pathway is not uniform, which may contribute to our understanding of the underlying selective mechanisms.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Robert V. Bergen, Jean-Francois Rajotte, Fereshteh Yousefirizi, Arman Rahmim, Raymond T. Ng
Summary: This article introduces a 3D generative model called TrGAN, which can generate medical images with important features and statistical properties while protecting privacy. By evaluating through a membership inference attack, the fidelity, utility, and privacy trade-offs of the model were studied.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Hoda Mashayekhi, Mostafa Nazari, Fatemeh Jafarinejad, Nader Meskin
Summary: In this study, a novel model-free adaptive control method based on deep reinforcement learning (DRL) is proposed for cancer chemotherapy drug dosing. The method models the state variables and control action in their original infinite spaces, providing a more realistic solution. Numerical analysis shows the superior performance of the proposed method compared to the state-of-the-art RL-based approach.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Hao Sun, Bao Li, Liyuan Zhang, Yanping Zhang, Jincheng Liu, Suqin Huang, Xiaolu Xi, Youjun Liu
Summary: In cases of moderate stenosis in the internal carotid artery, the A1 segment of the anterior cerebral artery or the posterior communicating artery within the Circle of Willis may show a hemodynamic environment with high OSI and low TAWSS, increasing the risk of atherosclerosis development and stenosis in the CoW.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Ilaria Toniolo, Paola Pirini, Silvana Perretta, Emanuele Luigi Carniel, Alice Berardo
Summary: This study compared the outcomes of endoscopic sleeve gastroplasty (ESG) and laparoscopic sleeve gastrectomy (LSG) in weight loss surgery using computational models of specific patients. The results showed significant differences between the two procedures in terms of stomach volume reduction and mechanical stimulation. A predictive model was proposed to support surgical planning and estimation of volume reduction after ESG.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Chun-You Chen, Ya-Lin Chen, Jeremiah Scholl, Hsuan-Chia Yang, Yu-Chuan (Jack) Li
Summary: This study evaluated the overall performance of a machine learning-based CDSS (MedGuard) in triggering clinically relevant alerts and intercepting inappropriate drug errors and LASA drug errors. The results showed that MedGuard has the ability to improve patients' safety by triggering clinically valid alerts.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Lingzhi Tang, Xueqi Wang, Jinzhu Yang, Yonghuai Wang, Mingjun Qu, HongHe Li
Summary: In this paper, a dynamical local feature fusion net for automatically recognizing aortic valve calcification (AVC) from echocardiographic images is proposed. The network segments high-echo areas and adjusts the selection of local features to better integrate global and local semantic representations. Experimental results demonstrate the effectiveness of the proposed approach.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
You-Lei Fu, Wu Song, Wanni Xu, Jie Lin, Xuchao Nian
Summary: This study investigates the combination of surface electromyographic signals (sEMG) and deep learning-based CNN networks to study the interaction between humans and products and the impact on body comfort. It compares the advantages and disadvantages of different CNN networks and finds that DenseNet has unique advantages over other algorithms in terms of accuracy and ease of training, while mitigating issues of gradient disappearance and model degradation.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Moritz Rempe, Florian Mentzel, Kelsey L. Pomykala, Johannes Haubold, Felix Nensa, Kevin Kroeninger, Jan Egger, Jens Kleesiek
Summary: In this study, a deep learning-based skull stripping algorithm for MRI was proposed, which works directly in the complex valued k-space and preserves the phase information. The results showed that the algorithm achieved similar results to the ground truth, with higher accuracy in the slices above the eye region. This approach not only preserves valuable information for further diagnostics, but also enables immediate anonymization of patient data before being transformed into the image domain.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Ziyang Chen, Laura Cruciani, Elena Lievore, Matteo Fontana, Ottavio De Cobelli, Gennaro Musi, Giancarlo Ferrigno, Elena De Momi
Summary: In this paper, a deep learning-based approach is proposed to recover 3D information of intra-operative scenes, which can enhance the safety of robot-assisted surgery by implementing depth estimation using stereo images.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Ao Leng, Bolun Zeng, Yizhou Chen, Puxun Tu, Baoxin Tao, Xiaojun Chen
Summary: This study presents a novel training system for zygomatic implant surgery, which offers a more realistic simulation and training solution. By integrating visual, haptic, and auditory feedback, the system achieves global rigid-body collisions and soft tissue simulation, effectively improving surgeons' proficiency.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Yingjie Wang, Xueqing Yin
Summary: This study developed an integrated computational model combining coronary flow and myocardial perfusion models to achieve physiologically accurate simulations. The model has the potential for clinical application in diagnosing insufficient myocardial perfusion.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Nitzan Avidan, Moti Freiman
Summary: This study aims to enhance the generalization capabilities of DNN-based MRI reconstruction methods for undersampled k-space data. By introducing a mask-aware DNN architecture and training method, the under-sampled data and mask are encoded within the model structure, leading to improved performance. Rigorous testing on the widely accessible fastMRI dataset reveals that this approach demonstrates better generalization capabilities and robustness compared to traditional DNN methods.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Enhao Zhang, Saeed Miramini, Lihai Zhang
Summary: This study investigates the combined effects of osteoporosis and diabetes on fracture healing process by developing numerical models. The results show that osteoporotic fractures have higher instability and disruption in mesenchymal stem cells' proliferation and differentiation compared to non-osteoporotic fractures. Moreover, when osteoporosis coexists with diabetes, the healing process of fractures can be severely impaired.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)
Article
Computer Science, Interdisciplinary Applications
Yunhao Bai, Wenqi Li, Jianpeng An, Lili Xia, Huazhen Chen, Gang Zhao, Zhongke Gao
Summary: This study proposes an effective MIL method for classifying WSI of esophageal cancer. The use of self-supervised learning for feature extractor pretraining enhances feature extraction from esophageal WSI, leading to more robust and accurate performance. The proposed framework outperforms existing methods, achieving an accuracy of 93.07% and AUC of 95.31% on a comprehensive dataset of esophageal slide images.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)