Article
Ecology
M. W. Rademan, D. J. J. Versfeld, J. A. du Preez
Summary: This study investigates the detection of cetacean vocalizations based on spectral entropy using median filtering and continuous wavelet transform. The proposed method improves the detection accuracy and specificity by determining the threshold with Kmeans clustering and provides a more interpretable detection threshold setting through soft class assignment.
ECOLOGICAL INFORMATICS
(2023)
Article
Engineering, Multidisciplinary
Snehsheel Sharma, S. K. Tiwari, Sukhjeet Singh
Summary: This paper introduces an integrated approach using permutation entropy and flexible analytical wavelet transform for the detection and classification of faults in rolling bearings of rotary machines. By comparing the classification results of two different methods, it is demonstrated that the FAWT-PE approach is more effective for fault detection and classification.
Article
Chemistry, Multidisciplinary
Qingyun Zhang, Jin Tao, Qinglin Sun, Xianyi Zeng, Matthias Dehmer, Quan Zhou
Summary: Accidental falls pose serious threats to the health and safety of the elderly, and the injuries caused are closely related to the postures during falls. A novel method using wavelet packet transform, random forest, and support vector machine was proposed for recognizing fall postures, achieving a classification accuracy of 99% in experiments on simulated falls and daily living activities dataset.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Multidisciplinary
Nitin Burud, J. M. Chandra Kishen
Summary: This work delves into the spectral realm of acoustic emission waveforms, proposing the use of wavelet entropy to estimate spectral disorder. It demonstrates the potential dual application of wavelet entropy as a signal discriminator and damage index. The increase in statistical variance of wavelet entropy distribution with stress level indicates the presence of multi-sources and multi-mechanistic fracture processes.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Nikunja Bihari Kar, Deepak Ranjan Nayak, Korra Sathya Babu, Yu-Dong Zhang
Summary: This paper proposes a new scheme for facial expression recognition using a hybrid feature descriptor and an improved classifier, which captures prominent details from facial images and is robust against illumination and noise. Experimental evaluations on Japanese female facial expression and CK+ datasets demonstrate the superiority of this method over state-of-the-art approaches.
IET IMAGE PROCESSING
(2021)
Article
Mechanics
Jie Wang, Wei Zhou, Xia-ying Ren, Ming-ming Su, Jia Liu
Summary: A real-time analytical approach for damage mode identification of carbon fiber reinforced polymer using machine learning and acoustic emission is proposed. Waveform features are extracted from acoustic emission signals using wavelet packet transform, and a waveform-based clustering model is constructed to reveal the relevance between acoustic emission signals and damage modes. Different types of composite laminates can be recognized by the developed softmax layer classifier.
COMPOSITE STRUCTURES
(2023)
Article
Medicine, Research & Experimental
Jackson Rodrigues, Ashwini Amin, Chandavalli Ramappa Raghushaker, Subhash Chandra, Manjunath B. Joshi, Keerthana Prasad, Sharada Rai, Subramanya G. Nayak, Satadru Ray, Krishna Kishore Mahato
Summary: This study assessed tumor progression in athymic nude mice using Photoacoustic spectroscopy-based machine learning tools. Progressive tumors were classified with 99.5% accuracy using multi-class Support Vector Machine (SVM) algorithms. Serum metabolomic levels during tumor progression complemented photoacoustic spectral features, depicting breast cancer pathophysiology.
LABORATORY INVESTIGATION
(2021)
Article
Ecology
Xiaoming Sun, Pengfei Liu, Zhishuai He, Yang Han, Bochao Su
Summary: Classification and diagnosis of cardiac arrhythmias are important in clinical practice. This study proposes an automatic ECG classification algorithm using transfer learning and continuous wavelet transform, which improves diagnostic accuracy and recognition.
ECOLOGICAL INFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Lidong Wang, Yimei Ma, Xudong Chang, Chuang Gao, Qiang Qu, Xuebo Chen
Summary: The paper proposes an efficient projection wavelet weighted twin support vector regression (PWWTSVR) based orthogonal frequency division multiplexing system (OFDM) channel estimation algorithm, which utilizes pilot signals and wavelet weights to estimate the nonlinear and fading channel model, achieving better performance compared to conventional methods.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Physics, Multidisciplinary
Tao Wang, Changhua Lu, Yining Sun, Mei Yang, Chun Liu, Chunsheng Ou
Summary: The study introduces an automatic ECG classification method utilizing CWT and CNN, achieving solid performance in diagnosing arrhythmia. With its simplicity and high accuracy, the method has the potential to be a clinical auxiliary diagnostic tool.
Article
Mathematics
Hari M. Srivastava, Kush Kumar Mishra, Santosh K. Upadhyay
Summary: This paper presents a systematic study on the characteristics and properties of continuous and discrete fractional Bessel wavelet transforms, based on the theory of fractional Hankel transform.
Article
Engineering, Biomedical
Parikha Chawla, Shashi B. Rana, Hardeep Kaur, Kuldeep Singh, Rajamanickam Yuvaraj, M. Murugappan
Summary: Parkinson's disease can be automatically diagnosed using EEG signals. This study presents a novel algorithm that utilizes flexible analytic wavelet transform and various classifiers to identify appropriate feature sets. The proposed system has been evaluated and shown to be extremely useful for neurologists during their diagnostic process and in clinical practices.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Software Engineering
R. Jeen Retna Kumar, M. Sundaram, N. Arumugam
Summary: The paper discusses the method and results of using wavelet transform for feature extraction in facial emotion recognition, as well as how to process and classify features through gradient transform and principal component analysis. Experimental results show that the proposed method achieved satisfactory emotion classification results on different facial expression databases.
Article
Engineering, Electrical & Electronic
Vinh Hao Le, Hui Ma, Chandima Ekanayake, Tapan Saha
Summary: This paper proposes an improved methodology for detecting and classifying multiple power quality disturbance (PQD) events, which has been evaluated and verified using synthesized signals and real-life disturbance recordings. The results show that the proposed method achieves high classification accuracy and computational efficiency.
IET GENERATION TRANSMISSION & DISTRIBUTION
(2022)
Article
Chemistry, Multidisciplinary
Wang Huan, Galina Shcherbakova, Anatoliy Sachenko, Lingyu Yan, Natalya Volkova, Bohdan Rusyn, Agnieszka Molga
Summary: This article aims to classify systems for visual information processing by evaluating the performance and informativeness of the adopted classification solutions using the wavelet method. The method uses training and calculates the ranges of changes in coefficients, selecting these ranges by employing the Shannon entropy formula. A case study demonstrated that this method significantly increases the speed of detecting coefficient intervals and resolves the contradiction between classifier performance and reliability.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Andreas S. Panayides, Marios S. Pattichis, Stephanos Leandrou, Costas Pitris, Anastasia Constantinidou, Constantinos S. Pattichis
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2019)
Article
Nutrition & Dietetics
Panayiotis Aristotelous, Manos Stefanakis, Marios Pantzaris, Constantinos S. Pattichis, Philip C. Calder, Ioannis S. Patrikios, Giorgos K. Sakkas, Christoforos D. Giannaki
Summary: This study aimed to investigate the effects of long-term supplementation with high dosages of omega-3 and omega-6 PUFAs and specific antioxidant vitamins on functional capacity and gait parameters in relapsing-remitting multiple sclerosis patients. The results showed significant improvements in some gait parameters and functional capacity in patients who received the dietary supplement compared to the placebo group.
Review
Medicine, General & Internal
Vasilios Tanos, Marios Neofytou, Ahmed Samy Abdulhady Soliman, Panayiotis Tanos, Constantinos S. Pattichis
Summary: CATIA shows promise in distinguishing normal from abnormal tissues during gastrointestinal, endometrial, and dermatologic examinations, but further research is needed to evaluate its efficacy in distinguishing benign from malignant states.
JOURNAL OF CLINICAL MEDICINE
(2021)
Article
Computer Science, Interdisciplinary Applications
Maria Matsangidou, Fotos Frangoudes, Eirini Schiza, Kleanthis C. Neokleous, Ersi Papayianni, Katerian Xenari, Marios Avraamides, Constantinos S. Pattichis
Summary: This study confirms the significant role of virtual reality in improving physical training and emotional health of dementia patients when appropriately designed. The study also highlights four key factors that should be incorporated in a virtual reality system.
Article
Computer Science, Cybernetics
Maria Matsangidou, Fotos Frangoudes, Marios Hadjiaros, Eirini Schiza, Kleanthis C. Neokleous, Ersi Papayianni, Marios Avraamides, Constantinos S. Pattichis
Summary: Virtual reality technology can improve the physical training of people with Dementia, enhancing their quality of life. This study compared traditional physical training with virtual reality training, and found that fully immersive virtual reality training can help patients execute exercises more accurately and prevent external distractions.
INTERNATIONAL JOURNAL OF HUMAN-COMPUTER STUDIES
(2022)
Article
Biochemistry & Molecular Biology
Vasilios Tanos, Marios Neofytou, Panayiotis Tanos, Constantinos S. Pattichis, Marios S. Pattichis
Summary: The study demonstrated the ability of CATIA to distinguish normal and abnormal endometrium based on texture analysis, achieving an 81% classification accuracy using support vector machine modeling.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Editorial Material
Computer Science, Information Systems
Marios S. Pattichis, Scott T. Acton, Constantinos S. Pattichis, Andreas S. Panayides
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Geriatrics & Gerontology
Maria Matsangidou, Theodoros Solomou, Fotos Frangoudes, Ersi Papayianni, Constantinos S. Pattichis
Summary: This study co-designed a virtual reality system with people with dementia and experts in dementia care, and evaluated it with a larger population of patients with mild to severe cases of dementia. The results showed that virtual reality significantly contributes to the reduction of behavioral and psychological symptoms of dementia. These findings offer insights into the design, deployment, and use of virtual reality technology in dementia care.
Article
Computer Science, Information Systems
Christos P. Loizou, Kevin Fotso, Antria Nicolaou, Marios Pantzaris, Marios S. Pattichis, Constantinos S. Pattichis
Summary: Monitoring disease evolution in Multiple Sclerosis (MS) subjects using clinical features and MRI imaging can help personalize treatment decisions and predict future disability. By analyzing MS detectable brain lesions, texture features, and AM-FM features extracted from MRI scans, it was found that these features can be used to predict disease development and severity. A model incorporating these features achieved a correct classification score of 94% in distinguishing different disability levels. However, further studies are needed to validate these findings and improve early differentiation between normal tissue and MS lesions.
Review
Computer Science, Information Systems
Marios Hadjiaros, Kleanthis Neokleous, Andria Shimi, Marios N. N. Avraamides, Constantinos S. S. Pattichis
Summary: This article explores the popular approaches and best practices for designing and implementing cognitive gaming interventions that combine Brain Computer Interface (BCI) systems with Virtual Reality (VR). It focuses on interventions targeting cognitive skills related to perception, visuospatial attention, and visuospatial memory. The article reviews commonly used techniques and algorithms for data preprocessing, feature extraction, and classification in such interventions. It also discusses issues such as BCI paradigms, action tasks and environments, user characteristics, algorithms, channels, accuracy, and notable findings. The article concludes with a discussion on current challenges, limitations, future research directions, and potential commercial applications of BCI-VR in cognitive gaming.
Proceedings Paper
Computer Science, Artificial Intelligence
Georgia D. Liapi, Efthyvoulos Kyriacou, Christos P. Loizou, Andreas S. Panayides, Constantinos S. Pattichis, Andrew N. Nicolaides
Summary: Early stroke risk stratification in individuals with carotid atherosclerosis, especially high-risk asymptomatic cases, is crucial. This study introduces a new computer-aided diagnostic system that accurately segments and characterizes atherosclerotic plaques in carotid ultrasound images and videos using a refined set of ultrasonic features.
ARTIFICIAL INTELLIGENCE APPLICATIONS AND INNOVATIONS. AIAI 2022 IFIP WG 12.5 INTERNATIONAL WORKSHOPS
(2022)
Review
Computer Science, Information Systems
Fotos Frangoudes, Maria Matsangidou, Eirini C. Schiza, Kleanthis Neokleous, Constantinos S. Pattichis
Summary: This article examines the latest advancements in the analysis and evaluation of human motion during exercise using machine learning. The results suggest that algorithms for human motion assessment should have personalized, real-time, and interpretable outcomes, and should be adaptable to different motion capture systems. Guidelines for the development of such algorithms are proposed.
Article
Engineering, Biomedical
Kyriacos P. Constantinou, Ioannis P. Constantinou, Constantinos S. Pattichis, Marios S. Pattichis
Summary: AM-FM models provide effective representations for differentiating between lesions and normal structure in medical images by offering physically meaningful descriptors. The decomposition of medical images into AM-FM components allows for the capture of local texture, brightness variations, and location descriptors. By utilizing simple classifiers to learn the features provided by AM-FM models, excellent results can be achieved in medical image analysis.
IEEE REVIEWS IN BIOMEDICAL ENGINEERING
(2021)
Review
Computer Science, Information Systems
Melpo Pittara, Maria Matsangidou, Kyriakos Stylianides, Nicolai Petkov, Costantinos S. Pattichis
Article
Computer Science, Information Systems
Andreas S. Panayides, Marios S. Pattichis, Marios Pantziaris, Anthony G. Constantinides, Constantinos S. Pattichis