Article
Computer Science, Information Systems
Arti Rana, Ankur Dumka, Rajesh Singh, Mamoon Rashid, Nazir Ahmad, Manoj Kumar Panda
Summary: Parkinson's disease is a neurodegenerative disease that is difficult to diagnose. This research proposes a new diagnostic method using supervised classification algorithms, with high accuracy.
Article
Computer Science, Artificial Intelligence
T. Senthilkumar, S. Kumarganesh, P. Sivakumar, K. Periyarselvam
Summary: Alzheimer's disease is a common form of dementia in older people, and this study uses neuroimaging techniques for preliminary detection, preprocessing the dataset with various methods, extracting and categorizing features, and reducing noise. The research findings show that the proposed method is faster and more successful at identifying complete long-term risk patterns compared to existing methods.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2022)
Article
Computer Science, Information Systems
Nur Aqilah Paskhal Rostam, Nurul Hashimah Ahamed Hassain Malim
Summary: The Quran and Al-Hadith complement each other in interpreting Islamic teachings. This research proposes a method using text categorisation to classify selected categories and found that Support Vector Machine (SVM) achieved better accuracy in addressing the interrelationship for single- and multi-label classifications.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2021)
Article
Computer Science, Hardware & Architecture
Ilhan Firat Kilincer, Fatih Ertam, Abdulkadir Sengur
Summary: The study reviewed literature studies using widely used data sets to develop IDS systems, and found that more successful results were obtained in some studies when using classification with support vector machine (SVM), K-Nearest neighbor (KNN), and Decision Tree (DT) algorithms among other classical machine learning approaches. This study is considered useful for developing IDS systems based on artificial intelligence utilizing machine learning approaches.
Article
Medicine, General & Internal
Samra Shahzadi, Naveed Anwer Butt, Muhammad Usman Sana, Inaki Elio Pascual, Mercedes Briones Urbano, Isabel de la Torre Diez, Imran Ashraf
Summary: This study used independent component analysis to investigate the impact of Alzheimer's disease on different brain regions at different stages. Machine learning algorithms were used to categorize the stages of the disease. The study found that certain regions were impacted in all stages, and AdaBoost algorithm achieved excellent classification results.
Review
Computer Science, Information Systems
Nitin Ahire, R. N. Awale, Suprava Patnaik, Abhay Wagh
Summary: This comprehensive review discusses the application of machine learning techniques in classifying EEG signals for dyslexia. It also analyzes an improved framework to enhance the performance and accuracy of the classifier in distinguishing between dyslexics and controls. The study provides an overview of input pre-processing, feature selection, feature extraction techniques, and machine learning algorithms for early disorder detection.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Acoustics
T. Mary Little Flower, T. Jaya
Summary: A novel technique using Ramanujan Fourier Transform (RFT) for Speech Emotion Recognition (SER) analysis is proposed. The RFT is applied after numerically encoding the speech emotion data, and it projects the obtained numerical series onto a collection of fundamental functions consisting of Ramanujan sums (RS). Multiple SER databases are considered for accuracy testing. The research shows that the RFT feature-based speech emotion classification using multiclass SVM classifier outperforms other classifiers in terms of accuracy. The results pave the way for real-world applications of speech emotion analysis.
Article
Chemistry, Analytical
Subhajit Chatterjee, Yung-Cheol Byun
Summary: Alzheimer's disease is a type of dementia that affects thinking, behavior, and memory. Current classification techniques struggle to train reliable classifiers due to limited sample size and noise in data. We propose an ensemble voting method that improves diagnosis of Alzheimer's disease in older adults.
Article
Neurosciences
Daniel Agostinho, Francisco Caramelo, Ana Paula Moreira, Isabel Santana, Antero Abrunhosa, Miguel Castelo-Branco
Summary: This study investigated whether the combination of T1 Weighted MRI and diffusion tensor imaging (DTI) can achieve comparable performance to the combination of quantitative structural MRI (sMRI) with amyloid-PET. Results showed that the combination of sMRI and DTI had similar performance to sMRI and amyloid PET, indicating the importance of white matter changes in Alzheimer's Disease.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Environmental Sciences
Ricardo Martinez Prentice, Miguel Villoslada Pecina, Raymond D. Ward, Thaisa F. Bergamo, Chris B. Joyce, Kalev Sepp
Summary: In the study, high-resolution images obtained by multispectral cameras mounted on Unmanned Aerial Vehicles were used to classify coastal wetland sites. The Random Forest classifier outperformed the K-Nearest Neighbors algorithm, especially in pixel-based classification. The findings suggest that for heterogeneous environments like wetlands, pixel-based classification provides a more realistic interpretation of plant community distribution.
Article
Chemistry, Multidisciplinary
Baraa Tareq Hammad, Norziana Jamil, Ismail Taha Ahmed, Zuhaira Muhammad Zain, Shakila Basheer
Summary: The development of malware poses a serious security risk, and existing classification techniques have low accuracy due to the difficulty in finding accurate features and dealing with data imbalance. A proposed method for malware classification achieves extremely high accuracy, surpassing traditional hand-crafted and deep feature techniques.
APPLIED SCIENCES-BASEL
(2022)
Article
Neurosciences
Yixuan Liu, Jie Li, Hongfei Ji, Jie Zhuang
Summary: This study utilized CEST technology to investigate Alzheimer's disease and found differences in glutamate content in the brains of AD mice through ROI and pixel-dimensional analysis. Additionally, by using a neural network for classification, we preliminarily evaluated the potential of glutamate imaging as a biomarker for AD detection.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Alicja Miniak-Gorecka, Krzysztof Podlaski, Tomasz Gwizdalla
Summary: This article introduces a self-optimizing neural network approach based on decision networks for the classification of multi-dimensional patterns. The approach utilizes feature vectors and discriminants to create decision patterns and discusses the influence of neighborhood topology. Experimental results demonstrate the superior performance of the proposed approach in terms of generalization and accuracy compared to the support vector machine method.
PEERJ COMPUTER SCIENCE
(2022)
Article
Environmental Sciences
Sarah Letaief, Pierre Camps, Claire Carvallo
Summary: Environmental magnetism techniques are being increasingly used to map the deposition of particulate pollutants on various accumulative surfaces. This study evaluates the effectiveness of these techniques in tracing the source signals of pollutants using a k-nearest neighbors algorithm. The algorithm successfully predicts the dominant traffic-related sources for different types of accumulative surfaces and demonstrates the possibility of quantifying their contributions to the overall magnetic signal measured. These results suggest the potential for magnetic mapping to complement traditional methods of measuring air quality and improving pollutant dispersion models.
ENVIRONMENTAL RESEARCH
(2023)
Article
Ecology
Farid Hassanbaki Garabaghi, Recep Benzer, Semra Benzer, Aysel Caglan Gunal
Summary: In this study, a support vector machine algorithm was used to classify healthy and unhealthy crayfish based on physiological characteristics. Different kernel functions had varying effects on the performance of the model, with the Pearson VII function-based universal kernel exhibiting outstanding performance.
ECOLOGICAL INFORMATICS
(2022)
Article
Engineering, Electrical & Electronic
Muhammed Yildirim, Ahmet Cinar
Summary: Colon cancer is a prevalent type of carcinoma that affects millions of people globally each year, early and accurate diagnosis is crucial for successful treatment. A novel method called CNN-based MA_ColonNET has been developed for detecting colon cancer image data, achieving a high success rate of 99.75%.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2022)
Article
Otorhinolaryngology
Orkun Eroglu, Yesim Eroglu, Muhammed Yildirim, Turgut Karlidag, Ahmed Cinar, Abdulvahap Akyigit, Irfan Kaygusuz, Hanefi Yildirim, Erol Keles, Sinasi Yalcin
Summary: The role of artificial intelligence modelling in differentiating chronic otitis media with and without cholesteatoma on computed tomography images was evaluated. The study demonstrated that using CT images, the differentiation between COM with and without cholesteatoma can be accurately diagnosed with a high level of accuracy. This can aid in early diagnosis, selection of appropriate treatment, and reduction of complications.
AMERICAN JOURNAL OF OTOLARYNGOLOGY
(2022)
Article
Computer Science, Software Engineering
Emine Cengil, Ahmet Cinar, Muhammed Yildirim
Summary: The article presents a study on multi-classification of white blood cells, utilizing two different transfer learning methods, and demonstrates two different combinations of classifiers.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
Article
Engineering, Electrical & Electronic
Orkun Eroglu, Muhammed Yildirim
Summary: Otitis media with effusion (OME) is a condition where fluid accumulates in the middle ear, causing various issues like hearing loss and speech retardation. This study utilized deep models to evaluate eardrum images of patients with OME. The proposed model achieved a high accuracy value in classifying features extracted from the images.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2022)
Article
Environmental Sciences
Muhammed Yildirim, Ahmet cinar, Emine CengIl
Summary: In this study, a hybrid model was developed for weather image classification using artificial intelligence methods. By combining and optimizing features extracted by CNN models and classifying them with SVM, the hybrid model outperformed existing pre-trained architectures, demonstrating the success of feature concatenation using CNN architectures for classification.
GEOCARTO INTERNATIONAL
(2022)
Article
Computer Science, Hardware & Architecture
Muhammed Yildirim, Orkun Eroglu, Yesim Eroglu, Ahmet Cinar, Emine Cengil
Summary: This paper proposes a hybrid approach for diagnosing COVID-19 on chest X-ray images and distinguishing it from other viral pneumonia. The model achieved high accuracy in classifying the images and shows promising results in the diagnosis of COVID-19.
NEW GENERATION COMPUTING
(2022)
Article
Computer Science, Software Engineering
Muhammed Yildirim
Summary: This article introduces a new deep convolutional neural network architecture for the classification and diagnosis of heart valve diseases based on heart sounds. By using the MFCC method to obtain feature maps from heart sounds and classifying them in the developed deep architecture, high accuracy rates were achieved.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Muhammed Yildirim
Summary: In this study, a hybrid model using heart sounds for early diagnosis and treatment of heart diseases was developed. Spectrograms obtained with the Mel-spectrogram method and augmented with interpolation were used as input. The model achieved high accuracy through optimized feature maps and classification.
TRAITEMENT DU SIGNAL
(2022)
Article
Computer Science, Hardware & Architecture
Kadir Yildirim, Muhammed Yildirim, Hasan Eryesil, Muhammed Talo, Ozal Yildirim, Murat Karabatak, Mehmet Sezai Ogras, Hakan Artas, U. Rajendra Acharya
Summary: Prostate cancer is the most common cancer among men, and accurate diagnosis is commonly achieved through digital rectal examination and prostate-specific antigen tests. To reduce unnecessary biopsies, multiparametric magnetic resonance imaging (mpMRI) is used. However, there is low-level agreement and subjectivity in the interpretation of mpMRI scores. This study proposes a hybrid model to accurately interpret mpMRI examinations and predict scores, achieving a 96.09% accuracy rate.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Muhammet Serdar Bugday, Mehmet Akcicek, Harun Bingol, Muhammed Yildirim
Summary: Urinary system stone disease is a common global disease, with ureteral stones accounting for 20% of all urinary system stones. The developed hybrid model uses Grad-CAM technology to obtain heat maps and extract feature maps from kidney images. The features are concatenated using multimodal fusion and then reduced using Relief dimension reduction technique for faster and more effective performance. The SVM classifier achieved an accuracy of 91.1% for HUN diagnosis, outperforming state-of-the-art models.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2023)
Article
Medicine, General & Internal
Faruk Oztekin, Oguzhan Katar, Ferhat Sadak, Muhammed Yildirim, Hakan Cakar, Murat Aydogan, Zeynep Ozpolat, Tuba Talo Yildirim, Ozal Yildirim, Oliver Faust, U. Rajendra Acharya
Summary: Dental caries is a common dental health issue that can cause pain and infections, reducing quality of life. Applying machine learning models for caries detection can lead to early treatment, but lack of explainability may hinder their acceptance. In this study, an explainable deep learning model for detecting dental caries was developed and evaluated. The ResNet-50 model showed slightly better performance compared to EfficientNet-B0 and DenseNet-121, achieving an accuracy of 92.00% and a sensitivity of 87.33%. The heat maps provided by the model helped explain the classification results, enabling dentists to validate and reduce misclassification.
Article
Biology
Sinem Akyol, Muhammed Yildirim, Bilal Alatas
Summary: Quality sleep is crucial for daily life, and sleep disorders can be diagnosed using computer-aided systems. A study utilized 700 sound data samples with three different feature extraction methods and optimized the feature maps using improved metaheuristic algorithms and machine learning methods, achieving a high accuracy rate.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Information Systems
Ugur Demiroglu, Bilal Senol, Muhammed Yildirim, Yesim Eroglu
Summary: This article presents a hybrid method for predicting and diagnosing lung cancer from CT images to minimize potential human errors. It utilizes DarkNet-53 and DenseNet-201 deep model architectures for feature extraction and combines them with classical machine learning classifiers. The performance and computation cost are optimized using the Neighborhood Component Analysis (NCA) optimization method. The proposed hybrid model achieves high accuracy in lung cancer classification.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Medicine, General & Internal
Muhammed Yildirim, Harun Bingol, Emine Cengil, Serpil Aslan, Muhammet Baykara
Summary: Urine sediment examination is an important diagnostic tool for detecting diseases in advance. In this study, a hybrid model combining textural and CNN-based features was developed to classify urine sediment images, achieving a high accuracy rate of 96.0%.