Review
Engineering, Biomedical
Neha, H. K. Sardana, R. Kanwade, S. Tewary
Summary: ECG and PPG are non-invasive techniques that provide electrical and hemodynamic information of the heart, mainly for diagnosing cardiac abnormalities. Automatic detection techniques can help experts accurately identify the nature of arrhythmias.
PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE
(2021)
Article
Computer Science, Hardware & Architecture
Mehdi Ayar, Ayaz Isazadeh, Farhad Soleimanian Gharehchopogh, MirHojjat Seyedi
Summary: This study introduces a chaotic-based method for feature selection, enabling quick and automatic diagnosis and classification of cardiac arrhythmias with high accuracy and time efficiency.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Computer Science, Information Systems
Xianbin Zhang, Mingzhe Jiang, Kemal Polat, Adi Alhudhaif, Jude Hemanth, Wanqing Wu
Summary: Atrial fibrillation (AF), a common arrhythmia, is associated with high morbidity and mortality. This paper proposes a novel Time-adaptive densely network named MP-DLNet-F for the intelligent auxiliary diagnosis of AF based on body surface electrocardiogram (ECG). The experimental results demonstrate the effectiveness of MP-DLNet-F in achieving high classification accuracy and improved performance on different datasets.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Meenali Janveja, Rushik Parmar, Mayank Tantuway, Gaurav Trivedi
Summary: In this paper, a Deep Neural Network (DNN) based cardiac arrhythmia (CA) classifier is proposed to accurately classify ECG beats into normal and different types of arrhythmia beats. The classifier exhibits higher classification accuracy compared to previous methods without the need for handcrafted features. It consumes low power, making it suitable for wearable healthcare device applications.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2022)
Review
Cardiac & Cardiovascular Systems
John Lee, Oluwaseun Adeola, Hasan Garan, William G. Stevenson, Hirad Yarmohammadi
Summary: This article provides a comprehensive review of the discriminatory ECG characteristics of ventricular arrhythmias in the right ventricle, with or without structural right ventricular diseases.
Article
Medicine, General & Internal
Yun Gi Kim, Jong-Il Choi, Hee-Jung Kim, Kyongjin Min, Yun Young Choi, Jaemin Shim, Ho Sung Son, Young-Hoon Kim
Summary: The watch-type, electrocardiograph-recording, wearable device (w-ECG) designed in this study demonstrated superior capability in detecting cardiac arrhythmias compared to 12-lead electrocardiography (ECG) and Holter monitoring. A significant proportion of patients received therapeutic intervention based on ECGs recorded by the w-ECG.
JOURNAL OF CLINICAL MEDICINE
(2022)
Article
Engineering, Biomedical
Zeyang Zhang, Ziheng Zhang, Cao Zou, Zhongcai Pei, Zheyuan Yang, Jing Wu, Shikun Sun, Fei Gu
Summary: This study proposes a new neural network called ECGNet for the classification of 12-lead ECG images. ECGNet utilizes dense blocks, special convolution kernels, and divergent paths to improve its performance and addresses the issue of sample imbalance with a new loss function. Extensive experiments demonstrate that ECGNet achieves extremely high prediction accuracy (91.74%) with small datasets, showing potential assistance to doctors in preoperative diagnosis of premature ventricular complexes (PVCs).
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Computer Science, Information Systems
M. R. Rajeshwari, K. S. Kavitha
Summary: This research proposes an ensemble feature selection method combined with deep neural network (DNN) for arrhythmia classification. The method utilizes whale optimization, grasshopper optimization, and Grey Wolf Optimization (GWO) methods to select relevant features from the best solution of feature selection. The proposed ensemble method finds the correlation among selected features and selects features with higher correlation as relevant features. The experimental results show that the proposed method has high sensitivity and accuracy in both arrhythmia classification and ventricular arrhythmia classification.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Taki Hasan Rafi, Young Woong-Ko
Summary: Cardiovascular disease is a major cause of morbidity and mortality, and Electrocardiogram (ECG) is a reliable tool for monitoring cardiovascular health. To address the lack of data in rare medical diseases, a new generative adversarial network-based deep learning method called HeartNet was developed. This method tackles the data insufficiency problem by synthesizing additional training samples through a generative adversarial network, significantly improving classification performance.
Article
Veterinary Sciences
L. Alibrandi, R. Tognetti, O. Domenech, M. Croce, M. Giuntoli, G. Grosso, T. Vezzosi
Summary: This study assessed the feasibility and diagnostic reliability of a new smartphone-based ECG device in dogs, and found no significant differences compared to a traditional ECG device. The results suggest that the smartphone-based device is clinically reliable for assessing heart rate and rhythm in dogs.
VETERINARY JOURNAL
(2024)
Article
Chemistry, Analytical
Katya Arquilla, Andrea K. Webb, Allison P. Anderson
Summary: This study demonstrates the potential benefits of including smaller waves in stress detection using the ECG signal. The smaller peaks derived from the ECG waveform, such as the P, Q, S, and T waves, show a stronger relationship with acute psychological stress compared to the commonly used R peak. However, the smaller peaks are more difficult to detect due to their smaller magnitude and susceptibility to noise.
Article
Mathematics
Shu-Fen Li, Mei-Ling Huang, Yan-Sheng Wu
Summary: In recent years, deep learning has been widely applied and achieved excellent results in various fields. This study combines the Taguchi method and convolutional neural networks (CNNs) to classify ECG images without feature extraction or signal conversion. The proposed model achieved a classification accuracy of 96.79% on the MIT-BIH Arrhythmia Dataset, comparable to the state-of-the-art literature. It demonstrates effective and efficient performance in identifying heartbeat diseases while minimizing misdiagnosis.
Article
Computer Science, Information Systems
Hui Yang, Zhiqiang Wei
Summary: In this study, a novel ensemble classification algorithm based on ECG morphological features is proposed for accurate detection of heart ventricular and atrial abnormalities. The method achieved an overall accuracy of 98.68% on fifteen heartbeat types and outperformed component classification algorithms and recent peer works.
Article
Computer Science, Artificial Intelligence
Zhaoyang Ge, Xiaoheng Jiang, Zhuang Tong, Panpan Feng, Bing Zhou, Mingliang Xu, Zongmin Wang, Yanwei Pang
Summary: The paper proposes an ECG abnormal event detection model based on multi-label correlation guided feature fusion, which calculates the correlation of different levels of ECG abnormalities and integrates features to achieve better experimental results.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Information Systems
Jaba Deva Krupa Abel, Samiappan Dhanalakshmi, R. Kumar
Summary: Despite the rapid growth in the field of adult ECG signal processing and monitoring systems, the analysis of fetal ECG signals lags behind and requires attention. Non-invasive fetal Electrocardiography is the safest method for monitoring fetal health by processing abdominal ECG (AECG) signals acquired by placing electrodes on the mother's abdomen. The primary challenge is the low signal-to-noise ratio of the recorded signal due to the dominant maternal ECG and other interferences present in the AECG signal. This paper provides an extensive review of existing techniques for extracting fetal ECG signals from AECG signals, including modeling methods, challenges with electrode placements, morphological analysis, and evaluation metrics.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Materials Science, Multidisciplinary
Ahmad Chaim, Heba Abunahla, Baker Mohammad, Nahla Alamoodi, Anas Alazzam
Summary: The development of flexible memristor devices using paper-based graphene oxide has great potential for wearable electronics. The PrMem device, made of cellulose and reduced graphene oxide, demonstrates resistive switching properties and eliminates the need for additional pumping structures due to its hydrophilic nature. The research opens up new possibilities for using paper-based memristor devices in various applications.
Article
Computer Science, Information Systems
M. Sami Zitouni, Cheul Young Park, Uichin Lee, Leontios J. Hadjileontiadis, Ahsan Khandoker
Summary: This paper presents a framework for emotion recognition based on multi-modal peripheral signals, which can be implemented in daily life settings. The study collected emotion data from a debate using wearable devices and converted the emotions into classes in the arousal and valence space. The proposed framework achieved classification accuracy of > 96% and > 93% for independent and combined classification scenarios, respectively.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Chemistry, Multidisciplinary
Heba N. Abunahla, Humaira Zafar, Dalaver H. Anjum, Anas Alazzam, Baker Mohammad
Summary: The study presents a novel fabrication method for graphene oxide (GO)-based memristor devices on an active/shrinkable substrate. The devices are fabricated using standard lithography process on a polymer substrate that can shrink at a certain temperature. The results demonstrate that the shrunk devices maintain their switching ability with improved electrical parameters, while the deposited GO film on the active substrate shows enhanced properties after shrinking. This novel approach offers insights into scaling thin-film electronics postfabrication and enables the realization of GO-based electronic devices with improved electrical properties.
Review
Psychology, Multidisciplinary
Nayeefa Chowdhury, Ahsan H. Khandoker
Summary: A literature review suggests that virtual reality exposure therapy (VRET) is as effective as in vivo exposure therapy (ET) for social anxiety disorder (SAD), but behavioral therapy based on classical conditioning principles has higher attrition and relapse rates. Further research is needed to compare the efficacy of the Pavlovian extinction model with other treatment models and to include neural markers as efficacy measures for treating SAD. A paradigm shift in the gold-standard treatment for SAD requires rigorous longitudinal comparative studies.
FRONTIERS IN PSYCHOLOGY
(2023)
Article
Multidisciplinary Sciences
Shiza Saleem, Ahsan H. Khandoker, Mohanad Alkhodari, Leontios J. Hadjileontiadis, Herbert F. Jelinek
Summary: Heart failure is characterized by abnormal autonomic modulation, with sympathetic activation and parasympathetic withdrawal. Beta-blockers can inhibit sympathetic overstimulation and are used for heart failure patients with reduced ejection fraction. The effect of beta-blocker therapy on heart failure with preserved ejection fraction (HFpEF) is uncertain. In this study, ECGs of 73 HFpEF patients were analyzed to evaluate the impact of beta-blockers on heart rate variability (HRV) measures associated with cardiac risk.
SCIENTIFIC REPORTS
(2023)
Editorial Material
Physiology
Ahsan H. Khandoker, Ryoichi Nagatomi, Janos Negyesi
FRONTIERS IN PHYSIOLOGY
(2023)
Review
Cardiac & Cardiovascular Systems
Mohanad Alkhodari, Zhaohan Xiong, Ahsan H. Khandoker, Leontios J. Hadjileontiadis, Paul Leeson, Winok Lapidaire
Summary: This review discusses the integration of artificial intelligence (AI) and big data analysis for personalized cardiovascular care, specifically in the management of hypertensive disorders of pregnancy (HDP). The use of AI can provide personalized recommendations based on a deeper analysis of medical history and imaging data, leading to improved knowledge on pregnancy-related disorders and personalized treatment planning.
EXPERT REVIEW OF CARDIOVASCULAR THERAPY
(2023)
Article
Chemistry, Multidisciplinary
Muhammad Umair Khan, Yawar Abbas, Moh'd Rezeq, Anas Alazzam, Baker Mohammad
Summary: This study presents a method to enhance data processing by integrating a unidirectional analogue artificial neuromorphic memristor device with a piezoelectric nanogenerator, taking inspiration from biological information processing. A self-powered unidirectional neuromorphic resistive memory device is proposed, comprising an ITO/ZnO/Yb2O3/Au structure combined with a high-sensitivity piezoelectric nanogenerator (PENG) ITO/ZnO/Al. The integration enables the creation of a self-powered artificial sensing system that converts mechanical stimuli from the PENG into electrical signals, which are subsequently processed by analogue unidirectional neuromorphic device to mimic the functionality of a neuron without requiring additional circuitry. This emulation encompasses crucial functions such as potentiation, depression, and synaptic plasticity. Furthermore, this study highlights the potential for hardware implementations of neural networks with a weight change of memristor device with nonlinearity (NL) of potentiation and depression of 1.94 and 0.89, respectively, with an accuracy of 93%. The outcomes of this research contribute to the progress of next-generation low-power, self-powered unidirectional neuromorphic perception networks with correlated learning and trainable memory capabilities.
ADVANCED FUNCTIONAL MATERIALS
(2023)
Article
Computer Science, Information Systems
Murad Almadani, Leontios Hadjileontiadis, Ahsan Khandoker
Summary: Fetal cardiac monitoring is crucial for early detection of potential fetal cardiac abnormalities, enabling prompt preventative care and safe births.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Mohammed F. Tolba, Hani Saleh, Baker Mohammad, Mahmoud Al-Qutayri, Thanos Stouraitis
Summary: This paper proposes an efficient hardware accelerator called EACNN for Convolutional Neural Networks (CNNs). EACNN is based on the co-optimization of algorithms and hardware, and uses linear approximation of weights to reduce computations and memory accesses. Experimental results show that the proposed method can reduce the number of multiplications in the network by around 61% without significant loss of accuracy (< 3%). A hardware accelerator based on EACNN achieved a 50% reduction in FPGA hardware resources.
2023 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS
(2023)
Article
Computer Science, Information Systems
Huruy Tesfai, Hani Saleh, Mahmoud Al-Qutayri, Baker Mohammad, Thanasios Stouraitis
Summary: Deep learning networks achieve high accuracy for classification tasks but are usually too computationally and memory intensive for power-constrained devices. Low-bit quantization is an effective technique to reduce this burden, but it introduces quantization error and decreases classification accuracy. We propose a quantization error-aware gradient estimation method for power-of-two and additive power-of-two quantization, which minimizes quantization error by aligning weight update with projection steps. We also apply per-channel quantization to minimize accuracy degradation caused by the rigid resolution property of power-of-two quantization. This approach enables comparable accuracy even at ultra-low bit precision.
Review
Computer Science, Information Systems
Rami Homsi, Nosayba Al-Azzam, Baker Mohammad, Anas Alazzam
Summary: Detecting cancer biomarkers at an early stage is crucial for recovery, and researchers have been interested in developing reliable and cost-effective devices for point-of-care screening. This review focuses on memristive biosensors and compares them to other electrochemical devices for cancer biomarker detection. Memristive biosensors have demonstrated lower limits of detection compared to field effect transistors and electrochemical immunosensors. The fabrication of memristive biosensors using silicon nanowires is common but exploring different materials and structures may improve reproducibility.
Article
Engineering, Electrical & Electronic
Tasneem Assaf, Arafat Al-Dweik, Youssef Iraqi, Sobia Jangsher, Anshul Pandey, Jean-Pierre Giacalone, Enas E. Abulibdeh, Hani Saleh, Baker Mohammad
Summary: Physical layer security (PLS) is used for efficient key generation and sharing in secured wireless systems. This work proposes a novel system design that integrates physically unclonable functions (PUFs) and channel reciprocity (CR) to overcome the randomness constraint of the wireless channel and enable high-rate secret key generation. The system utilizes an adaptive and controllable artificial fading (AF) level with interleaving to mitigate the impact of low randomness variations in the channel. Monte Carlo simulation results show that the proposed system operates efficiently even in nearly flat or time-invariant channels, with significantly shorter key generation and sharing time compared to conventional techniques.
IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY
(2023)
Proceedings Paper
Automation & Control Systems
Welelaw Yenieneh Lakew, Arafat Al-Dweik, Mahmoud Aldababsa, Mohamed A. Abou-Khousa, Baker Mohammad
Summary: This paper analyzes the bit error rate performance of a power domain NOMA-OFDM system with time-domain interleaving over frequency selective Rayleigh channel. Theoretical BER expressions for an arbitrary number of users using minimum mean squared error equalizer are developed. The simulation results show that the proposed power domain NOMA-OFDM system with TDI has better BER performance over frequency-selective fading multipath channels compared to the conventional NOMA-OFDM system without TDI.
2023 IEEE 97TH VEHICULAR TECHNOLOGY CONFERENCE, VTC2023-SPRING
(2023)