Article
Computer Science, Information Systems
Vandana Roy, Prashant Kumar Shukla, Amit Kumar Gupta, Vikas Goel, Piyush Kumar Shukla, Shailja Shukla
Summary: EEG signals are considered biomedical big data, but they can be contaminated by artifacts. Proper removal of artifacts is necessary for accurate diagnosis of neurological diseases. This paper reviews 60 technical research papers to summarize important key features in EEG artifact removal.
JOURNAL OF ORGANIZATIONAL AND END USER COMPUTING
(2021)
Review
Chemistry, Analytical
Tomasz Blachowicz, Guido Ehrmann, Andrea Ehrmann
Summary: Biosignals are often detected noninvasively in sports or for medical reasons, and textile-based sensors with integrated data connections are preferred to avoid skin irritations and other limitations. Textile-based electrodes show promising developments in electrical measurements and play an important role in biosignal detection and monitoring.
Article
Chemistry, Analytical
Giovanni Mezzina, Daniela De Venuto
Summary: This paper proposes a system for detecting Levodopa wearing-off phenomenon using neuromuscular data, and analyzes its performance. Experimental results show that the system can achieve an accuracy of approximately 84% and provide inference in less than 41 ms in the best case.
Article
Multidisciplinary Sciences
Bernd Porr, Sama Daryanavard, Lucia Munoz Bohollo, Henry Cowan, Ravinder Dahiya
Summary: This article introduces a new real-time deep learning algorithm that effectively reduces non-stationary noise in biological measurements. By removing electromyogram noise, the algorithm significantly improves the signal-to-noise ratio of electroencephalograms. This concept has the potential to be applied not only to EEG, but also to various biological, industrial, and consumer applications.
Article
Engineering, Electrical & Electronic
Mustapha Deji Dere, Ji-Hun Jo, Boreom Lee
Summary: This study presents an event-driven deep neural network capable of classifying gestures from single or hybrid biosignals. The results show that hybrid biosignals outperform single-modal EEG in gesture classification offline and on-device, as well as single-modal EMG in the case of EMG electrode shift. Additionally, the study demonstrates an end-to-end approach that deploys a DNN decoder to an edge device for neuro-inspired control of the dexterous hand without requiring an Internet-of-Things (IoT) connection.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Artificial Intelligence
Aristotelis Ballas, Christos Diou
Summary: Despite their success in various fields, machine and deep learning systems have yet to establish themselves in critical healthcare applications due to the domain generalization problem. This article proposes a benchmark for evaluating domain generalization algorithms in biosignal classification and introduces a novel architecture that improves model generalizability. The open-source benchmark aims to encourage further research in biomedical domain generalization by simplifying the evaluation process.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Chemistry, Analytical
Jin-Woo Jeong, Woochan Lee, Young-Joon Kim
Summary: This paper presents a wireless physiological signal acquisition device and a smartphone-based software platform for real-time data processing and monitoring. The device is compact and can wirelessly transmit biopotentials to a smartphone or laptop for real-time monitoring, recording, and analysis. It has been demonstrated to accurately capture ECG and EMG signals, making it a useful tool for predicting and treating cardiac patients and facilitating motor recovery after a stroke.
Article
Environmental Sciences
Shih-Lung Pao, Shin-Yu Wu, Jing-Min Liang, Ing-Jer Huang, Lan-Yuen Guo, Wen-Lan Wu, Yang-Guang Liu, Shy-Her Nian
Summary: This study proposes a thermal sensation (TS) model based on physiological signals to improve the prediction accuracy of human comfort in indoor environments. Results from climate chamber experiments show that the physiological signal-based TS model outperforms the traditional PMV model, highlighting the importance of physiological signals in comfort prediction.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Genetics & Heredity
Mandy Stake, Bert Heinrichs
Summary: Early detection and prevention examinations in pediatrics can identify and treat health disorders from an early age onwards. However, these examinations are often widely spaced, leading to limited information. E-health applications and AI technologies can enable more frequent and regular recording of developmental parameters and search for new patterns. Despite the potential benefits, concerns exist about the unlimited use of big data in medicine, especially in pediatrics. This paper explores the ethical implications of e-health applications and discusses the opportunities and risks of app-based data collection and AI-based data evaluation in complementing established examinations.
FRONTIERS IN GENETICS
(2022)
Review
Biochemistry & Molecular Biology
Anuja Mishra, Mukti Agrawal, Aaliya Ali, Prakrati Garg
Summary: Facing the workaholic era, stress has become a major challenge to human health. Continuous stress monitoring is important for measuring stress levels accurately and conveniently. The development of stress biosensors has had a significant impact on human lives.
BIOTECHNOLOGY AND APPLIED BIOCHEMISTRY
(2023)
Article
Computer Science, Information Systems
Nidhi Pathak, Sudip Misra, Anandarup Mukherjee, Neeraj Kumar
Summary: The proposed healthcare device interoperability system utilizes multiple sensors wirelessly connected to edge devices, allowing for dynamic accommodation of various sensors without predefined ontologies. The system's implementation demonstrates reliability and suitability for healthcare monitoring, with an average packet delivery ratio of 0.92 for star network configuration and 0.98 for mesh network configuration.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Multidisciplinary Sciences
Menaa Nawaz, Jameel Ahmed
Summary: Real-time data collection and pre-processing enable the automatic assessment of cardiovascular activity through anomaly detection and classification of raw one-dimensional electrocardiogram (ECG) signals. The proposed intelligent end-to-end system utilizes deep learning and multi-label classification algorithms, along with improved feature-engineered parameters and wavelet time scattering features for improved accuracy and robustness. The results show high classification accuracy and F1 score using the long short-term memory (LSTM) method for classification and deep LSTM auto-encoders for anomaly detection.
Article
Computer Science, Hardware & Architecture
Guipeng Zhang, Zhenguo Yang, Wenyin Liu
Summary: In this study, a blockchain-based privacy preserving e-health system is proposed to secure and protect patients' electronic health records (EHRs) from tampering and to ensure secure payment through smart contracts. The system utilizes pairing-based cryptography to generate tamper-proof records and integrates them into blockchain transactions for verification.
Article
Automation & Control Systems
Parsa Sarosh, Shabir Ahmad Parah, Bilal Ahmad Malik, Mohammad Hijji, Khan Muhammad
Summary: This article presents a cybersecurity framework for medical images in a smart healthcare system. It introduces two novel two-dimensional chaotic maps that generate highly robust cipher images, protecting medical data against cyberattacks. The proposed solution ensures data privacy and a seamless treatment experience.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Environmental
Baixiang Ren, Yaxin Yu, Rama-Krishnan Poopal, Linlin Qiao, Baichuan Ren, Zongming Ren
Summary: We developed an infrared-based real-time online monitoring device to assess water quality by quantifying heart electrocardiogram signals in fish. The device is compact and allows long-term monitoring without causing harm or disturbance to the fish. We accurately quantified ECG indexes of carp under different experimental conditions, which showed specific responses to different chemical exposures.
ENVIRONMENTAL SCIENCE & TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Eduardo Perez-Valero, Miguel Angel Lopez-Gordo, Miguel A. Vaquero-Blasco
Summary: The study introduces a attention-driven videogame controlled by an SSVEP-BCI, where players must use their attention to deflect mobile flickering stimuli. Participants found the game both amusing and challenging, and showed varying levels of attention when passing versus missing levels.
Article
Chemistry, Analytical
Miguel A. Vaquero-Blasco, Eduardo Perez-Valero, Christian Morillas, Miguel A. Lopez-Gordo
Summary: The latest studies have shown that 360-degree VR experiences can significantly reduce stress, reduce costs, and make stress relief assistance more accessible to the general public, such as in workplaces or homes.
Article
Engineering, Biomedical
Eduardo Perez-Valero, Miguel A. Lopez-Gordo, Miguel A. Vaquero-Blasco
Summary: The study examined the impact of EEG-PSD smoothing on three-level stress classification and found that smoothing can lead to data leakage and affect classification performance. Two-level stress classification without smoothing met the criteria for practical applicability, suggesting individual processing of each epoch is necessary for realistic stress classifiers.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Mathematical & Computational Biology
Eduardo Perez-Valero, Miguel A. Vaquero-Blasco, Miguel A. Lopez-Gordo, Christian Morillas
Summary: The study introduces a quantitative stress assessment method based on EEG and regression algorithms, which predicts participants' stress levels with remarkable performance. These results could have a positive impact in fields like neuromarketing and professional training for individuals facing stressful situations.
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
(2021)
Article
Computer Science, Interdisciplinary Applications
Eduardo Perez-Valero, Miguel Angel Lopez-Gordo, Christian Morillas Gutierrez, Ismael Carrera-Munoz, Rosa M. Vilchez-Carrillo
Summary: Early detection is crucial for controlling Alzheimer's disease and delaying cognitive decline. Researchers have evaluated AD detection methods using machine learning and EEG. This study presents a preliminary evaluation of a self-driven AD multi-class discrimination approach based on commercial EEG and machine learning, showing the potential for AD detection through this self-driven approach.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Engineering, Biomedical
Laura Becerra-Fajardo, Marc Oliver Krob, Jesus Minguillon, Camila Rodrigues, Christine Welsch, Marc Tudela-Pi, Albert Comerma, Filipe Oliveira Barroso, Andreas Schneider, Antoni Ivorra
Summary: This article introduces a wireless power transfer and communication method based on volume conduction, which is used to develop distributed flexible threadlike sensors and stimulators. The study validates the feasibility of this method through the design and evaluation of advanced prototypes in an agar phantom and in vivo animal models.
JOURNAL OF NEUROENGINEERING AND REHABILITATION
(2022)
Editorial Material
Mathematical & Computational Biology
Jesus Minguillon, Ivan Volosyak, Christoph Guger, Michael Tangermann, Miguel Angel Lopez
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
(2022)
Article
Mathematical & Computational Biology
Eduardo Perez-Valero, Christian Morillas, Miguel A. Lopez-Gordo, Ismael Carrera-Munoz, Samuel Lopez-Alcalde, Rosa M. Vilchez-Carrillo
Summary: Early detection of Alzheimer's disease is crucial and current techniques are costly or invasive. Researchers have investigated AD detection using electroencephalography and machine learning algorithms. They performed a preliminary evaluation using a commercial EEG system and automated classification pipeline. The results suggest that AD can be automatically detected using this approach, which could potentially reduce costs and shorten detection times.
FRONTIERS IN NEUROINFORMATICS
(2022)
Article
Engineering, Biomedical
Aracelys Garcia-Moreno, Albert Comerma-Montells, Marc Tudela-Pi, Jesus Minguillon, Laura Becerra-Fajardo, Antoni Ivorra
Summary: This study developed threadlike wireless implantable neuromuscular microstimulators that are digitally addressable and demonstrated their feasibility in vivo. These microstimulators can be minimally invasively implanted and controlled independently, providing a potential basis for advanced motor neuroprostheses with dense networks of wireless devices.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Engineering, Biomedical
Jesus Minguillon, Marc Tudela-Pi, Laura Becerra-Fajardo, Enric Perera-Bel, Antonio J. del-Ama, Angel Gil-Agudo, Alvaro Megia-Garcia, Aracelys Garcia-Moreno, Antoni Ivorra
Summary: Wireless power transfer (WPT) is used as an alternative to batteries for miniaturization of electronic medical implants. We propose a WPT approach based on high frequency (HF) current bursts, which avoids bulky components and enables flexible threadlike implants. Our results demonstrate the feasibility of wirelessly powering threadlike implants using innocuous and imperceptible HF current bursts based on volume conduction.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Eduardo Perez-Valero, Christian Morillas, Miguel A. Lopez-Gordo, Jesus Minguillon
Summary: Alzheimer's disease (AD) is the most common form of dementia that lacks a cure, but medical treatment can slow its progression. Early-stage diagnosis is crucial for improving the living standards of patients, but existing diagnostic techniques are limited. In this study, the feasibility of using a reduced four-channel EEG montage for early-stage AD detection was evaluated. Results showed similar accuracies compared to a 16-channel montage, suggesting that a four-channel wearable EEG system could effectively support early-stage AD detection.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Laura Becerra-Fajardo, Jesus Minguillon, Albert Comerma, Antoni Ivorra
Summary: Wireless power transfer methods, such as inductive coupling and ultrasounds, are being used as an alternative to electrochemical batteries in active implantable medical devices. However, existing methods require bulky components, hindering miniaturization. To address this issue, the use of high frequency current bursts for power and bidirectional communication in threadlike implants is proposed. In vitro experiments demonstrated that multiple wireless devices can be powered and digitally linked through volume conduction. This research paves the way for the development of highly miniaturized injectable devices for neuroprosthetics.
2023 11TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING, NER
(2023)
Article
Computer Science, Information Systems
Marc Tudela-Pi, Jesus Minguillon, Laura Becerra-Fajardo, Antoni Ivorra
Summary: The study aims to investigate an innovative wireless power transfer technique based on high-frequency volume conduction for powering AIMDs. High-frequency currents are coupled into tissues via external electrodes, generating an electric field absorbed by thin, flexible, and elongated implants, potentially enabling the transfer of powers above milliwatts inside tissues.
Article
Computer Science, Interdisciplinary Applications
M. A. Lopez-Gordo, Nico Kohlmorgen, C. Morillas, Francisco Pelayo
Summary: Researchers have focused on high-level analysis of win/lose chances and player performance in the video gaming industry, but there has not been prediction at the single-action level for games like first-person shooters.