Article
Chemistry, Analytical
Ch Anwar ul Hassan, Jawaid Iqbal, Rizwana Irfan, Saddam Hussain, Abeer D. Algarni, Syed Sabir Hussain Bukhari, Nazik Alturki, Syed Sajid Ullah
Summary: This study investigated heart disease prediction using machine learning algorithms and compared the performance of different algorithms. The results showed that the random forest algorithm achieved high accuracy in heart disease prediction.
Article
Quantum Science & Technology
Siddharth Dangwal, Ritvik Sharma, Debanjan Bhowmik
Summary: This work introduces a novel algorithm (Fast-QTrain) for fast training of variational classifiers. The algorithm utilizes parallel processing of samples from a classical data set to achieve training speedup. It employs a quantum RAM and other quantum circuits for the forward pass, and calculates the loss using a swap test circuit instead of classical methods. The proposed algorithm significantly reduces the training cost and time complexity compared to other variational algorithms and classical machine learning algorithms. It has been demonstrated to work accurately on a popular classical data set and can be generalized to multi-class classification.
QUANTUM INFORMATION PROCESSING
(2022)
Article
Quantum Science & Technology
Soumik Adhikary
Summary: The study introduces a supervised quantum classifier training algorithm that utilizes the property of quantum entanglement, achieving successful binary classification on benchmark datasets.
QUANTUM INFORMATION PROCESSING
(2021)
Article
Green & Sustainable Science & Technology
Papiya Debnath, Pankaj Chittora, Tulika Chakrabarti, Prasun Chakrabarti, Zbigniew Leonowicz, Michal Jasinski, Radomir Gono, Elzbieta Jasinska
Summary: The study aims to develop a method for forecasting the magnitude range of earthquakes using machine learning technology, categorizing earthquakes into fatal, moderate, and mild ranges. By using seven different machine learning classifier algorithms to build the model, it was found that the Simple Logistic and LMT classifiers performed well in each case.
Article
Computer Science, Interdisciplinary Applications
Julia Vazquez-Escobar, J. M. Hernandez, Miguel Cardenas-Montes
Summary: Particle physics experiments require processing complex data to detect rare signals, and machine learning algorithms help automate event classification and produce suitable datasets for physics research. In this study, three methods for estimating uncertainties in machine learning algorithm predictions were compared, demonstrating their ability to provide precise and robust predictions.
COMPUTER PHYSICS COMMUNICATIONS
(2021)
Article
Medicine, General & Internal
Mubarak Taiwo Mustapha, Dilber Uzun Ozsahin, Ilker Ozsahin, Berna Uzun
Summary: This study proposes a new approach combining artificial intelligence and multi-criteria decision-making for a more robust evaluation of machine learning models for early detection of breast cancer. The Support Vector Machine is ranked as the most favorable model, indicating the effectiveness of the proposed method in decision-making.
Article
Computer Science, Artificial Intelligence
Babymol Kurian, V. L. Jyothi
Summary: Breast cancer is the most common cancer worldwide. Machine learning techniques are used to improve the prognosis of breast cancer at an earlier stage. The research focuses on using an ensemble of machine learning classifiers to predict breast cancer using genetic sequences of BRCA1 and BRCA2. Five ensemble models from six machine learning classifiers were combined for the prediction, and the soft voting classifiers achieved the highest classification performance metrics with a classification precision of 94%.
Article
Computer Science, Artificial Intelligence
Shafaq Abbas, Zunera Jalil, Abdul Rehman Javed, Iqra Batool, Mohammad Zubair Khan, Abdulfattah Noorwali, Thippa Reddy Gadekallu, Aqsa Akbar
Summary: Breast cancer is a major cause of death in the current age, affecting one in eight women globally. Machine learning algorithms have proven to outperform existing solutions for breast cancer prediction, demonstrating improved accuracy.
PEERJ COMPUTER SCIENCE
(2021)
Article
Quantum Science & Technology
Xi He, Feiyu Du, Mingyuan Xue, Xiaogang Du, Tao Lei, A. K. Nandi
Summary: Transfer learning is a crucial subfield of machine learning that aims to accomplish a task in the target domain with the knowledge acquired from the source domain. This paper presents two quantum implementations of domain adaptation classifiers that achieve quantum speedup compared to classical classifiers. One implementation uses quantum basic linear algebra subroutines to predict labels with logarithmic resources. The other implementation efficiently accomplishes the domain adaptation task through a variational hybrid quantum-classical procedure.
QUANTUM INFORMATION PROCESSING
(2023)
Article
Multidisciplinary Sciences
Laura Diosan, Anca Andreica, Irina Voiculescu
Summary: This study aims to describe, analyze, compare and evaluate three image descriptors for classifying breast cancer images. The results show that using Multi-Objective Evolutionary Algorithms (MOEAs) is an efficient approach for solving specific learning problems. However, different statistical tests may rank algorithms differently in terms of performance. Therefore, selecting the right objectives and criteria is crucial to address these flaws.
Article
Computer Science, Information Systems
Usman Naseem, Junaid Rashid, Liaqat Ali, Jungeun Kim, Qazi Emad Ul Haq, Mazhar Javed Awan, Muhammad Imran
Summary: Breast cancer is the second most common cause of death among women, and early detection is crucial for improving prognosis and recovery. This study proposes a system for automatic detection of breast cancer diagnosis and prognosis using ensemble of classifiers, achieving a high accuracy rate.
Article
Computer Science, Artificial Intelligence
Thomas Baumhauer, Pascal Schoettle, Matthias Zeppelzauer
Summary: This paper introduces the research of machine unlearning and proposes linear filtration as a method for class-wide deletion requests in classification models. The experiments demonstrate its advantages in an adversarial setting over naive deletion schemes.
Article
Computer Science, Artificial Intelligence
Dheeraj Peddireddy, Vipul Bansal, Vaneet Aggarwal
Summary: In recent years, Variational Quantum Circuits (VQC) have been widely used in machine learning tasks and it is important to understand the boundaries of their classical simulation. This manuscript proposes an algorithm that compresses the quantum state within a circuit using a noisy tensor ring representation, allowing for implementation of VQC based algorithms on a classical simulator with reduced storage and computational complexity. The proposed tensor ring VQC (TRVQC) demonstrates comparable performance to implementations using Matrix Product States (MPS) for supervised learning tasks on Iris and MNIST datasets.
APPLIED SOFT COMPUTING
(2023)
Article
Engineering, Civil
Muhammad Jehanzaib, Sabab Ali Shah, Ho Jun Son, Sung-Hwan Jang, Tae-Woong Kim
Summary: This study applied machine learning classifiers to predict hydrological drought alert levels, and the results showed that these classifiers can effectively predict hydrological drought classes and provide warnings of drought conditions.
KSCE JOURNAL OF CIVIL ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Noor Kamal Al-Qazzaz, Iyden Kamil Mohammed, Halah Kamal Al-Qazzaz, Sawal Hamid Bin Mohd Ali, Siti Anom Ahmad
Summary: A novel approach using data mining techniques to analyze biomarkers in blood and saliva for early detection of breast cancer has been proposed. The application of dimensionality reduction techniques and different classification schemes improved the accuracy and efficiency of diagnosis, with better results for saliva samples.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Gotam Singh Lalotra, Vinod Kumar, Abhishek Bhatt, Tianhua Chen, Mufti Mahmud
Summary: Cloud computing introduces a new distributed environment with reduced financial expenditure on internet communication. The iReTADS method, utilizing data summarization technique to decrease network traffic and provide network security, offers a new approach to addressing network traffic monitoring and security issues.
SECURITY AND COMMUNICATION NETWORKS
(2022)
Article
Computer Science, Information Systems
Ravi Mohan Sharma, Chaitanya. P. Agrawal, Vinod Kumar, Adugna Necho Mulatu
Summary: With the rapid development of smartphone technology and mobile applications, the mobile phone has become a powerful tool for accessing the Internet and obtaining various services. However, vulnerabilities in applications pose a significant threat to the security of Android devices. A study was conducted to detect malicious applications on Android smartphones, focusing on permissions and intent-based mechanisms. Machine learning techniques were used to train and test the dataset, showcasing the accuracy and performance of seven different techniques.
MOBILE INFORMATION SYSTEMS
(2022)
Article
Environmental Sciences
Arvind Yadav, Devendra Joshi, Vinod Kumar, Hitesh Mohapatra, Celestine Iwendi, Thippa Reddy Gadekallu
Summary: This article develops an artificial intelligence model based on genetic algorithm and artificial neural network for predicting suspended sediment yield (SSY) in the Godavari River Basin in India. The model shows the highest correlation coefficient and lowest error values compared to traditional models, making it a superior alternative for SSY prediction.
Article
Mathematical & Computational Biology
Vinod Kumar, Sougatamoy Biswas, Dharmendra Singh Rajput, Harshita Patel, Basant Tiwari
Summary: The COVID-19 pandemic has had significant adverse effects globally, increasing the need for early detection and prediction of patients. In this study, a novel method called PCA-IELM, utilizing PCA and incremental extreme learning machine, is proposed for automatic diagnosis of COVID-19 from X-ray images. The technique shows superior prediction performance compared to other methods and has a faster training speed.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Computer Science, Hardware & Architecture
Vinod Kumar, Gotam Singh Lalotra, Ravi Kant Kumar
Summary: People with pre-existing health conditions such as thyroid disease and Hepatitis C Virus (HCV) are at a higher risk of developing COVID-19 and its variants. Early and accurate identification of these disorders is crucial, particularly in countries like India. To improve accuracy in imbalanced datasets, various data balancing techniques were applied to machine learning algorithms.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Computer Science, Information Systems
Ashok Sharma, Ravindra Parshuram Bachate, Parveen Singh, Vinod Kumar, Ravi Kant Kumar, Amar Singh, Madan Kadariya
Summary: This paper presents a PB3C-based mechanism for automatically evolving the optimal architecture of LSTM in regional speech recognition systems. The proposed approach is validated on Marathi speech recognition system and outperforms two other methods.
MOBILE INFORMATION SYSTEMS
(2022)
Article
Environmental Sciences
Arvind Yadav, Mohammad Kamrul Hasan, Devendra Joshi, Vinod Kumar, Azana Hafizah Mohd Aman, Hesham Alhumyani, Mohammed S. Alzaidi, Haripriya Mishra
Summary: This research aimed to develop a single hybrid artificial intelligence model for estimating the suspended sediment yield (SSY) in the Mahanadi River, India. The model combined data from 11-gauge stations into a hybrid generalized model using artificial neural network (ANN) and genetic algorithm (GA) optimization. The results showed that the proposed model outperformed the conventional approaches in terms of correlation and error, making it the most suitable model for estimating SSY in the MR Basin, particularly at the Tikarapara measuring station.
Article
Health Care Sciences & Services
Vinod Kumar, Gotam Singh Lalotra, Ponnusamy Sasikala, Dharmendra Singh Rajput, Rajesh Kaluri, Kuruva Lakshmanna, Mohammad Shorfuzzaman, Abdulmajeed Alsufyani, Mueen Uddin
Summary: Healthcare is crucial for every individual, and clinical datasets play a significant role in developing intelligent healthcare systems. However, class imbalance in real-world datasets poses challenges in training classifiers. This study evaluates the performance of six classifiers on five imbalanced clinical datasets and explores different class balancing techniques. The results demonstrate the superiority of the SMOTEEN method among all the tested techniques.
