
Abdulhamit SubasiUniversity of Turku | UTU · Faculty of Medicine
Abdulhamit Subasi
PhD
About
349
Publications
154,641
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
15,467
Citations
Introduction
Abdulhamit Subasi is specialized in Artificial Intelligence, Machine Learning, Biomedical Signal and Image Processing. He is also author of the books, “Practical Guide for Biomedical Signals Analysis Using Machine Learning Techniques” and “Practical Machine Learning for Data Analysis Using Python”. Since 2020, he has been working as a Professor of medical physics at Faculty of Medicine, University of Turku, Turku, Finland .
Additional affiliations
September 2020 - present
August 2015 - September 2020
November 2012 - July 2015
Publications
Publications (349)
This study presents a novel hybridization of the Wavelet Packet Decomposition (WPD) with Ensemble Learning (EL) for an enhanced arrhythmia diagnosis. The ECG signals are per-processed using the Multi-Scale Principle Component Analysis (MSPCA). Onward features are mined using the WPD. Finally, several EL based models are used for an automated identi...
This paper offers a thorough examination of the use of Bagging Ensemble Machine Learning in conjunction with Dual-Tree Complex Wavelet Transform (DTCWT) for ECG signal analysis. The objective is to attain a high precision arrhythmia classification by processing the ECG signals. The suggested approach seeks to address a number of issues with convent...
This study describes a unique method for detecting anomalies in cardiac signals by combining the Random Subspace Method with the Multiple Signal Classification (MUSIC) algorithm. MUSIC uses the spatial characteristics of ECG signals to detect irregular cardiac events, like ischemia bouts and arrhythmia. Furthermore, the detection model's robustness...
This chapter highlights the revolutionary role that Artificial Intelligence has played in enhancing the Brain-Computer Interface, with a focus on multimodal sensing, signal processing, and feature extraction. The evolution of Brain-Computer Interfaces from mono-modalities to multi-modalities is described, emphasizing the shift toward personalized s...
This chapter focuses on EEG signal processing to contribute to the realization of effective brain-computer interfaces. It uses the MSPCA for noise removal. Onward, the Wavelet Decomposition is used for feature extraction. The dimension reduction is carried out using statistical analysis. The selected ensemble learning techniques are used to identif...
This chapter presents the key feature extraction methods used in Brain-Computer Interfaces. Simple methods include digital filtering, and Fourier transform. Parametric-model based methods like AR, MA, and ARMA are covered with sub-space-based methods, and eigenvectors. The time-frequency analysis methods like the STFT and various variants of wavele...
The cover of our upcoming book Artificial Intelligence Applications for Brain-Computer Interfaces. This book will be a valuable resource for researchers, engineers, academicians and professionals who are interested in learning more about the impact of Signal Processing and Artificial Intelligence in contemporary Brain-Computer Interfaces.
Artificial Intelligence Applications for Brain-Computer Interfaces (BCIs) focuses on the advancements, challenges, and prospects for future technologies over non-invasive BCIs, including the processing and analysis of multimodal signals, integrated stimulation-acquisition devices, and implantable neuro-technologies. The book not only provides cross...
This study conducts an in-depth analysis of feature selection methods in AI, underscoring their importance in social science and public health research. Using the Finnish National Drug Survey's 2022 dataset, which comprises 76 selected features, the study aims to identify the main predictors of cannabis use among Finnish populations over the last 1...
Employing a minimal array of electroencephalography (EEG) channels for neonatal sleep stage classification is essential for data acquisition in the Internet of Medical Things (IoMT), as single-channel and edge-based features can reduce data transfer and processing requirements, enhancing cost-effectiveness and practicality. In this paper, we evalua...
Substance use poses a significant public health challenge worldwide, including in Finland. This study seeks to predict patterns of substance use, aiming to identify the driving factors behind these trends using artificial intelligence techniques. This research utilizes data from the 2022 Finnish National Drug Survey, comprising 3,857 participants,...
Artificial Intelligence and Multimodal Signal Processing in Human-Machine Interaction presents an overview of the emerging approach of exploiting multiple information modalities in human-machine interaction (HMI). The book not only provides cross-disciplinary research in multimodal signal sensing, processing, analysis, internet of things (IoTs), ar...
This chapter provides a brief overview and practical application of AI algorithms for ECG signal-based emotion identification. The ECG signals are analyzed using the CWT. The Random Forest Classifier is used to process the prepared features set in order to categorize the emotions. The findings are presented and contrasted with the counterparts.
Multimodal HCI systems often comprise both visual and audio types of sensor data. Nonetheless, a recent trend involves modeling and implementing modern HCIs using physiological signals. The feature extraction techniques are crucial in this situation. The goal of feature extraction is to produce an accurate representation that can be used with machi...
This chapter investigates the use of Wavelet Packet Decomposition (WPD) and Ensemble Classifiers to improve the accuracy and efficiency of P300 speller systems. Ensemble learning, capable of learning from extensive datasets, enhances P300 recognition performance. While the traditional machine learning models are effective, they may be prone to over...
A prosthetic hand is an alluring solution for the subjects who lost their hands. The sEMG is an essential part for designing the prosthetic hands for industrial and assistive applications. This study applies the signal processing and ensemble-learning techniques to the sEMG signals for an automated categorization of the hand movements.
In affective computing and human-machine interaction (HMI), emotion recognition is essential. Electroencephalography (EEG) is a promising tool for human emotion detection and interpretation. Artificial Intelligence (AI) is becoming increasingly common as a means of automation and complex problems solver. This chapter presents a novel Auto-Regressiv...
Using a blend of Ensemble Machine Learning Methods and Discrete Wavelet Transform (DWT), this study suggests an EEG-based secure authentication system. Because of their distinct qualities and resilience to spoofing attempts, EEG signals present a promising option for safe authentication systems. EEG signals are transformed into features by applying...
The cover of our upcoming book Artificial Intelligence and Multimodal Signal Processing in Human-Machine Interaction.
This book will be a valuable resource for researchers, engineers, academicians and professionals who are interested in learning more about the impact of Multimodal Signal Processing and AI in contemporary Human-Machine Interaction...
Unraveling the complexities of Gene Regulatory Networks (GRNs) is crucial for understanding cellular processes and disease mechanisms. Traditional computational methods often struggle with the dynamic nature of these networks. This study explores the use of Graph Neural Networks (GNNs), a powerful approach for modeling graph-structured data like GR...
Although deep learning (DL) algorithms have been proved to be effective in diverse research domains, their application in developing models for tabular data remains limited. Models trained on tabular data demonstrate higher efficacy using traditional machine learning models than DL models, which are largely attributed to the size and structure of t...
The global prevalence of diabetes, affecting an estimated 537 million individuals, underscores the urgent need for frequent blood glucose monitoring. Traditional methods, often reliant on finger pricking, not only cause discomfort but also pose challenges such as slow wound healing for diabetic patients. Acknowledging these critical issues, our res...
Batteries are the most suitable energy storage devices for Electric Vehicles (EVs). Batteries are expensive and have a high initial cost. Besides a notable research is in progress, in the domain of battery technology, to make batteries more affordable. Additionally, BMSs are evolving in the objective of attaining a longer battery life and optimal p...
Die Hauptzwecke der biomedizinischen Signale sind die Erkennung oder Diagnose von Krankheiten oder physiologischen Zuständen. Diese Signale werden auch in der biomedizinischen Forschung eingesetzt, um biologische Systeme zu modellieren und zu studieren. Das Ziel der Signalerfassung, Vorverarbeitung und Merkmalsextraktion besteht darin, eine genaue...
Dieses Buch präsentiert Fortschritte in der biomedizinischen Technologie. IoT und Machine Learning haben neue Ansätze im mobilen Gesundheitswesen ermöglicht, mit Fokus auf kontinuierlicher Überwachung kritischer Gesundheitssituationen. Intelligente Hybridisierung von IoT, drahtlosen Implantaten und Cloud-Computing wird derzeit von verschiedenen Ein...
This chapter aims to show how to use PYTHON to build an effective ecosystem for real-time emotion identification from ECG signals. A range of people who were subjected to controlled emotional stimuli were used to evaluate the system's performance. The outcomes demonstrated the promise of ECG-based emotion identification by validating the system's a...
Mobile healthcare is an appealing approach based on the Internet of Medical Things (IoMT) and cloud computing. It can lead to unobstructed, economical, and patient-centric healthcare solutions. The key performance indicators of such systems are dimensionality reduction, computational effectiveness, low latency, and accuracy. In this context, a nove...
We welcome book chapter contributions centered but not exclusively on the following themes: Authors are welcome to propose a new book chapter title related to the book topics. Potential topics include but are not limited to the following:
➢ Chapter 1: Introduction to brain-computer interface: Research trends and opportunities.
➢ Chapter 2: Pre-...
In smart healthcare facilities designed especially for the elderly, non-contact electrocardiogram (ECG) measurements could provide essential information about an elderly person’s health by enabling long-term health analytics. In this research work, we propose an Internet of Things (IoT) based non-contact ECG measurement system. The non-contact meas...
The Electroencephalography (EEG)-based precise emotion identification is one of the most challenging tasks in pattern recognition. In this paper, an innovative EEG signal processing method is devised for an automated emotion identification. The Symlets-4 filters based “Multi Scale Principal Component Analysis” (MSPCA) is used to denoise and reduce...
We welcome book chapter contributions centered but not exclusively on the following themes: Authors are welcome to propose a new book chapter title related to the book topics. Potential topics include but are not limited to the following:
➢ Chapter 1: Introduction to the human-machine interaction and its applications
➢ Chapter 2: Artificial int...
Background: Identifying the most important predictors of substance use is crucial for developing effective prevention policies. Traditional statistical methods have some limitations in this regard. To address these limitations, the researchers utilized artificial intelligence (AI) methods to identify the top 10 most important predictors of cannabis...
COVID-19 represents a novel variant of the coronavirus disease, having rapidly disseminated across the globe. In recent studies pertaining to computer vision, image processing, and classification techniques, numerous methodologies have been introduced employing chest X-ray images and computerized tomography (CT) images. This investigation introduce...
We have implemented a deep learning model with L2 regularization and trained it on Electromyography (EMG) data. The data comprises of EMG signals collected from control group, myopathy and ALS patients. Our proposed deep neural network consists of eight layers; five fully connected, two batch normalization and one dropout layers. The data is divide...
Facial expressions demonstrate the important information about our emotions and show the real intentions. In this study, a novel texture transformation method using graph structures is presented for facial expression recognition. Our proposed method consists of five steps. First the face image is segmented and resized. Then the proposed graph-based...
This book presents the modern technological advancements and revolutions in the biomedical sector. Progress in the contemporary sensing, Internet of Things (IoT) and machine learning algorithms and architectures have introduced new approaches in the mobile healthcare. A continuous observation of patients with critical health situation is required....
Coronavirus disease 2019 (COVID-19) is spreading rapidly around the world. Therefore, the classification of computed tomography (CT) scans alleviates the workload of experts, whose workload increased considerably during the pandemic. Convolutional neural network (CNN) architectures are successful for the classification of medical images. In this st...
The primary purposes of the biomedical signals are the detection or diagnosis of disease or physiological states. These signals are also employed in biomedical research to model and study biological systems. The objective of the signal acquisition, preconditioning and feature extraction is to attain a precise realization of model or recognition of...
Electroencephalography (EEG) signals are named letters of the brain, and their translation is a complex issue. This work recommends a new hand-crafted feature-based EEG signal classification model, including a new local histogram-based feature generation function, the cube pattern. The recommended model comprises preprocessing/signal denoising, fea...
Credit scoring is one the most important parts of credit risk management in reducing the risk of client defaults and bankruptcies. Deep learning has received much attention in recent years, but it has not been implemented so intensively in credit scoring compared to other financial domains. In this article, stacked unidirectional and bidirectional...
Stroke is one of the common causes of death worldwide. Stroke is the inability of a focus to be fed in the brain due to clogged or bleeding of the vessels feeding the brain. Because early stroke treatment and diagnosis are related to a favorable patient outcome, time is a critical aspect of successful stroke treatment. In this chapter, we examine t...
Brain hemorrhage is one of the most serious medical diseases, requiring immediate treatment through posttraumatic healthcare. For this life-threatening disease, immediate care involves an urgent diagnosis. Intracranial bleeding is frequently associated with severe headaches and loss of consciousness. When a patient shows these symptoms, expert radi...
Limited electroencephalography (EEG) channel number is useful for neonatal sleep classification, particularly in the Internet of Medical Things (IoMT) field, where compact and lightweight devices are essential to monitoring health effectively. A streamlined and cost-effective IoMT solution can be achieved by utilizing fewer EEG channels, thereby re...
A brain stroke is a life-threatening medical disorder caused by the inadequate blood supply to the brain. After the stroke, the damaged area of the brain will not operate normally. As a result, early detection is crucial for more effective therapy. Computed tomography (CT) images supply a rapid diagnosis of brain stroke. However, while doctors are...
Dear All,
We have launched a Special Issue of Machine Learning and Knowledge Extraction (MAKE) - MDPI https://www.mdpi.com/journal/make.
You are invited to submit your valuable works to this Special Issue: https://www.mdpi.com/journal/make/special_issues/biomedical
Special Issue Title: Machine Learning for Biomedical Data Processing
Emotions are strongly admitted as a main source to establish meaningful interactions between humans and computers. Thanks to the advancements in electroencephalography (EEG), especially in the usage of portable and cheap wearable EEG devices, the demand for identifying emotions has extremely increased. However, the overall scientific knowledge and...
Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these...
We welcome book chapter contributions centered but not exclusively) on the following themes: Authors are welcome to propose a new book chapter title related to the book topics. Potential topics include but are not limited to the following:
Chapter 1: Introduction to non-invasive biomedical signals for healthcare
Chapter 2: Signal Acquisition, Pre...
Globally, 14-20% of road accidents are mainly due
to driver fatigue caused of which are instance sickness, travelling
for long distance, boredom as a resistance of driving along
the same route consistently and lack of enough sleep etc. This
paper presents a flexible analytic wavelet transform (FAWT)
based advanced machine learning method using sing...
Classification of brain hemorrhage computed tomography (CT) images provides a better diagnostic implementation for emergency patients. Attentively, each brain CT image must be examined by doctors. This situation is time‐consuming, exhausting, and sometimes leads to making errors. Hence, we aim to find the best algorithm owing to a requirement for a...
Electroencephalography (EEG) signals collected from human brains have generally been used to diagnose diseases. Moreover, EEG signals can be used in several areas such as emotion recognition, driving fatigue detection. This work presents a new emotion recognition model by using EEG signals. The primary aim of this model is to present a highly accur...
Hands play a significant role in grasping and manipulating different objects. The loss of even a single hand have impact on the human activity. In this regard, a prosthetic hand is an appealing solution for the subjects who lost their hands. The surface electromyogram (sEMG) plays a vital role in the design of prosthesis hands. The ensemble classif...
Reservoir permeability is a crucial parameter for reservoir characterization and the estimation of current and future production from hydrocarbon reservoirs. Permeability can be conventionally estimated from traditional approaches such as core analysis and well-test data, which are time-consuming and expensive. Many scientists tried to estimate per...