A5029857334- ECG Monitoring and Analysis
- EEG and Brain-Computer Interfaces
- Artificial Intelligence in Healthcare
- COVID-19 diagnosis using AI
- Chaos-based Image/Signal Encryption
- Spectroscopy and Chemometric Analyses
- AI in cancer detection
- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Advanced Steganography and Watermarking Techniques
- Cardiac electrophysiology and arrhythmias
- Non-Invasive Vital Sign Monitoring
- Face and Expression Recognition
- Remote-Sensing Image Classification
- Radiomics and Machine Learning in Medical Imaging
- Quantum Computing Algorithms and Architecture
- Imbalanced Data Classification Techniques
- Brain Tumor Detection and Classification
- Quantum Information and Cryptography
- Digital Media Forensic Detection
- Advanced Neural Network Applications
- Context-Aware Activity Recognition Systems
- Hand Gesture Recognition Systems
- Atrial Fibrillation Management and Outcomes
- Advanced Chemical Sensor Technologies
Cracow University of Technology
2016-2025
Polish Academy of Sciences
2019-2025
Institute of Theoretical and Applied Informatics
2019-2025
National Institute of Telecommunications
2024
Deakin University
2024
Basque Center for Applied Mathematics
2022
Ferdowsi University of Mashhad
2022
Isfahan University of Technology
2022
AGH University of Krakow
2013-2017
Abstract The heart disease is one of the most serious health problems in today’s world. Over 50 million persons have cardiovascular diseases around Our proposed work based on 744 segments ECG signal obtained from MIT-BIH Arrhythmia database (strongly imbalanced data) for lead (modified II), 29 people. In this work, we used long-duration (10 s) (13 times less classifications/analysis). spectral power density was estimated Welch’s method and discrete Fourier transform to strengthen...
Hand gesture recognition is one of the most effective modes interaction between humans and computers due to being highly flexible user-friendly. A real-time hand system should aim develop a user-independent interface with high performance. Nowadays, convolutional neural networks (CNNs) show rates in image classification problems. Due unavailability large labeled samples static images, it challenging task train deep CNN such as AlexNet, VGG-16 ResNet from scratch. Therefore, inspired by...
Credit scoring (CS) is an effective and crucial approach used for risk management in banks other financial institutions. It provides appropriate guidance on granting loans reduces risks the area. Hence, companies are trying to use novel automated solutions deal with CS challenge protect their own finances customers. Nowadays, different machine learning (ML) data mining (DM) algorithms have been improve various aspects of prediction. In this paper, we introduce a methodology, named Deep...
Abstract Authentication is the process of verifying claimed identity user. Recently, traditional authentication methods such as passwords, tokens, and so on are no longer used for they more prone to theft different types violations. Therefore, new approaches based biometric modalities heartbeat pattern obtained from electrocardiogram (ECG) signals considered. Unlike other biometrics, ECG provides assurance that person alive, considered one most accurate recent authentication. In this...
The man-machine interface (MMI) is one of the most exciting areas contemporary research. To make MMI as convenient for a human possible, it desirable that efficient algorithms recognizing body language are developed. This paper presents system quick and effective recognition gestures hand language, based on data from specialized glove equipped with ten sensors. In experiment, 10 people performed 22 gestures. Each was executed times. Collected were preprocessed in multiple ways three machine...
Hepatocellular carcinoma (HCC) is the most common liver cancer in adults. Many different factors make it difficult to diagnose humans.. In this paper, a novel diagnostics approach based on machine learning techniques presented. Logistic regression one of classic models used solve problem binary classification. typical implementations, logistic coefficients are optimized using iterative methods. Additionally, parameters such as solver, C - regularization parameter or number iterations...
Colon cancer is the second most common cause of death in women and third men. Therefore, early detection this can lead to lower infection rates. In research, we propose a new lightweight deep learning approach based on Convolutional Neural Network (CNN) for efficient colon detection. our method, input histopathological images are normalized before feeding them into CNN model, then performed. The efficiency proposed system analyzed with publicly available database compared state-of-the-art...
Kidney stone disease is a serious public health concern that getting worse with changes in diet, obesity, medical conditions, certain supplements etc. A kidney also called renal calculus, hard buildup of urine minerals form the kidneys. Computed tomography (CT) one imaging models used to identify stones by clinical experts. Due low resolution these images, sometimes detecting tedious naked eye, which may lead false alarms. In this work, computer-based diagnosis system deep learning technique...
The Brain-computer interface (BCI) is used to enhance the human capabilities. hybrid-BCI (hBCI) a novel concept for subtly hybridizing multiple monitoring schemes maximize advantages of each while minimizing drawbacks individual methods. Recently, researchers have started focusing on Electroencephalogram (EEG) and "Functional Near-Infrared Spectroscopy" (fNIRS) based hBCI. main reason due development artificial intelligence (AI) algorithms such as machine learning approaches better process...
An electrocardiogram (ECG) is a unique representation of person’s identity, similar to fingerprints, and its rhythm shape are completely different from person person. Cloning tampering with ECG-based biometric systems very difficult. So, ECG signals have been used successfully in number recognition applications where security top priority. The major challenges the existing literature (i) noise components signals, (ii) inability automatically extract feature set, (iii) performance system....