Article
Computer Science, Artificial Intelligence
Nour El Islem Karabadji, Abdelaziz Amara Korba, Ali Assi, Hassina Seridi, Sabeur Aridhi, Wajdi Dhifli
Summary: Random Forest is an ensemble classification approach that constructs a group of decision trees based on bootstrap samples and random attribute selection. This paper proposes a genetic algorithm-based approach to address the challenges related to random forest construction. Experimental results show that the proposed approach outperforms existing methods. Furthermore, the proposed approach is used to build a reliable random forest model for detecting Botnet traffic in Internet of Things environment.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Md Nasim Adnan, Ryan H. L. Ip, Michael Bewong, Md Zahidul Islam
Summary: The proposed decision forest algorithm in this paper achieves better balance through effective synchronization of diversity from different sources, leading to significant improvement in accuracy according to empirical evaluations. It is also competitive in terms of complexity and other relevant parameters.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Abdullah Aljumah
Summary: In the Information and Communication Technology age, connected objects generate massive amounts of data traffic, which enables data analysis to uncover previously hidden trends and detect unusual network-load.By considering five core design principles, an intelligent model for IoT-IDS, the Temporal Convolution Neural Network (TCNN), which aggregates convolution neural network (CNN) and generic convolution is proposed.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Information Systems
Ishaani Priyadarshini, Sandipan Sahu, Raghvendra Kumar, David Taniar
Summary: Smart homes automate tasks and offer convenience through the use of devices controlled remotely via the Internet of Things. Analyzing and monitoring energy consumption is crucial in this environment. This paper conducts a comprehensive analysis of energy consumption in smart homes using machine learning models and proposes an ensemble model that outperforms baseline algorithms.
INTERNET OF THINGS
(2022)
Article
Automation & Control Systems
Gunasekaran Manogaran, Mamoun Alazab, Vijayalakshmi Saravanan, Bharat S. Rawal, P. Mohamed Shakeel, Revathi Sundarasekar, Senthil Murugan Nagarajan, Seifedine Nimer Kadry, Carlos Enrique Montenegro-Marin
Summary: This article proposes a machine learning aided information management scheme to enhance the efficiency of IoT service data management and ensure uninterrupted user request service. The scheme utilizes a neural learning process in the data plane to control resource allocation, improving service accuracy and efficiency.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Clinical Neurology
Rasmus Bach Nedergaard, Matthew Scott, Anne-Marie Wegeberg, Tina Okdahl, Joachim Starling, Birgitte Brock, Asbjarn Mohr Drewes, Christina Brock
Summary: This study used supervised machine learning to classify the severity of cardiovascular autonomic neuropathy (CAN). The results showed that beat-to-beat measures, inflammation markers, disease-duration, and age were the most important features for characterizing CAN. It was suggested that monitoring cardiac reflex responses closely and targeting systemic low-grade inflammation could help diagnose and prevent the development of CAN.
CLINICAL NEUROPHYSIOLOGY
(2023)
Article
Medicine, Research & Experimental
Mahdi Akbarzadeh, Nadia Alipour, Hamed Moheimani, Asieh Sadat Zahedi, Firoozeh Hosseini-Esfahani, Hossein Lanjanian, Fereidoun Azizi, Maryam S. Daneshpour
Summary: This study compared different machine learning classification methods in predicting the status of metabolic syndrome and identifying influential factors. The findings showed that machine learning models outperformed conventional statistical approaches and can be used to identify individuals at high risk of developing metabolic syndrome.
JOURNAL OF TRANSLATIONAL MEDICINE
(2022)
Article
Chemistry, Multidisciplinary
Monire Norouzi, Zeynep Gurkas-Aydin, Ozgur Can Turna, Mehmet Yavuz Yagci, Muhammed Ali Aydin, Alireza Souri
Summary: The Internet of Medical Things (IoMT) is improving the healthcare industry by enhancing personal healthcare benefits with medical data. However, security and data transmission issues are challenges due to the rapid growth of technology.
APPLIED SCIENCES-BASEL
(2023)
Article
Environmental Sciences
Bin Ai, Ke Huang, Jun Zhao, Shaojie Sun, Zhuokai Jian, Xiaoding Liu
Summary: The study aims to accurately map coastal reclamations in Guangdong Province using efficient technology and suitable methods and data. The results indicate that the object-oriented algorithm with rule-based approach is more efficient in detecting reclamation use in coastal Guangdong compared to other algorithms in the actual situation.
Article
Environmental Sciences
Himan Shahabi, Reza Ahmadi, Mohsen Alizadeh, Mazlan Hashim, Nadhir Al-Ansari, Ataollah Shirzadi, Isabelle D. Wolf, Effi Helmy Ariffin
Summary: This study aimed to assess the effectiveness of three machine learning algorithms (RF, DT, and SVM) for landslide susceptibility mapping. The decision tree model showed the highest accuracy in identifying areas at risk for future landslides.
Article
Computer Science, Artificial Intelligence
M. A. Ganaie, M. Tanveer, P. N. Suganthan, V. Snasel
Summary: This paper proposes two new approaches known as oblique and rotation double random forests. The oblique double random forests improve the performance of decision trees by using multisurface proximal support vector machine and different regularization techniques. The rotation double random forests enhance diversity and generalization performance by generating different feature space transformations at each node.
Article
Chemistry, Analytical
Dhanalekshmi Prasad Yedurkar, Shilpa P. Metkar, Fadi Al-Turjman, Thompson Stephan, Manjur Kolhar, Chadi Altrjman
Summary: This paper proposes a novel approach for multichannel epilepsy seizure classification using a smartphone-based Internet of Things framework. The approach utilizes an optimized feature and a support vector machine classifier to accurately locate seizure activity and achieve high classification accuracy.
Article
Environmental Sciences
Yishuo Cui, Xuehong Zhang, Nan Jiang, Tianci Dong, Tao Xie
Summary: This study developed a decision-tree-based method using Sentinel-2A MSI imagery and DEM data to classify and map marine floating raft aquaculture. The results demonstrate that this method can accurately obtain raft information and improve the classification accuracy of marine floating rafts.
FRONTIERS IN MARINE SCIENCE
(2022)
Article
Geriatrics & Gerontology
Jaime Lynn Speiser, Kathryn E. Callahan, Denise K. Houston, Jason Fanning, Thomas M. Gill, Jack M. Guralnik, Anne B. Newman, Marco Pahor, W. Jack Rejeski, Michael E. Miller
Summary: Advancements in computational algorithms and large datasets have enabled the development of machine learning prediction models for older adults, though challenges remain in terms of reproducibility and algorithm complexity. Decision tree and random forest are common machine learning methods with high interpretability, making them suitable for clinical application. However, careful consideration and evaluation by clinical experts are necessary to ensure the compatibility and reliability of the models in clinical practice.
JOURNALS OF GERONTOLOGY SERIES A-BIOLOGICAL SCIENCES AND MEDICAL SCIENCES
(2021)
Article
Computer Science, Information Systems
Mohammad Aktaruzzaman Khan, Sayed Allamah Iqbal, Maliha Sanjida Khan, Md. Golam Hafez
Summary: This study utilizes machine learning and factor analysis to predict job satisfaction. Despite the limitations of factor analysis, machine learning algorithms can overcome these challenges. The study finds that management support, equity, non-financial compensation, and financial compensation are highly effective in predicting job satisfaction.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Theory & Methods
Murali Mohan, R. M. Balajee, Hiren K. Mewada, B. R. Rajakumar, D. Binu
Summary: Cloud computing is a cost-effective service, but its vulnerability to attacks necessitates the development of a new IDS model. This research introduces a new IDS model for the cloud environment, which includes data preprocessing, clustering, feature selection, and attack detection phases.
MULTIAGENT AND GRID SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Vamsidhar Talasila, M. R. Narasingarao, V. Murali Mohan
Summary: Text-to-image synthesis is a motivating and valuable task. This research aims to develop a new method that combines text encoding and optimized GAN to generate images from text. The GAN will be trained using the Dragon Customized Whale Optimization (DC-WO) model, and the superiority of the approach will be evaluated by comparing it to existing techniques.
ADVANCES IN ENGINEERING SOFTWARE
(2022)
Article
Computer Science, Cybernetics
V. Murali Mohan, Sukhvinder Singh, Pramod Pandurang Jadhav
Summary: This study proposes an ensemble learning approach for network intrusion detection and classification in cloud computing. By preprocessing and feature extraction, models such as neural network, support vector machine, random forest, and optimized deep belief network are used for the final detection. The algorithm and classifier are evaluated by comparing the proposed method with conventional approaches.
CYBERNETICS AND SYSTEMS
(2023)
Article
Computer Science, Cybernetics
Jyothi Puligadda, Venkata Rama Rao Kolipaka, V. Murali Mohan, Vamsidhar Talasila
Summary: This article presents a VH method using graph theory to address the complexities of network modeling in vertical handovers. It utilizes an improved k-partite graph to model the VH issues in HetNets and applies an improved Dijkstra's algorithm for path selection. The analytic hierarchy process is used to estimate adaptive weights among nodes, and a hybridized model named grey wolf upgraded CSO is used for optimal weight selection in Dijkstra's algorithm. Results show that the proposed strategy is efficient based on metrics such as throughput, packet jitter, delay, and packet losses.
CYBERNETICS AND SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Vamsidhar Talasila, M. R. Narasingarao, V. Murali Mohan
Summary: This research aims to develop a new model for text-to-image synthesis, which involves three important phases: feature extraction, text encoding, and optimal image synthesis. The model utilizes improved TF-IDF, bag of words, and N-gram for text feature extraction and Bi-LSTM for training. The image encoding is done through cross-modal feature grouping, and image synthesis is performed using a modified GAN with a new loss function. The proposed model's superiority is examined through evaluation against existing schemes.
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE
(2023)
Article
Telecommunications
Rekha Gangula, Murali Mohan Vutukuru, M. Ranjeeth Kumar
Summary: In this research article, a new ID system is implemented to detect network intrusions more efficiently. Data denoising and optimization algorithms are used to address the imbalancing problems, and an ensemble classifier is employed to classify the normal and attack labels. Experimental results show that the proposed method achieves a detection rate of 98.89% and 98.41% on the UNSW-NB15 and NSL KDD datasets, respectively.
WIRELESS PERSONAL COMMUNICATIONS
(2023)
Article
Computer Science, Theory & Methods
N. M. Jyothi, S. Madhusudhanan, V Muralimohan
Summary: This research aims to assess cough events using sound processing tools in order to classify and predict the severity of Asthma. Parameters of the cough audio signal are analyzed and the Nu Support Vector Classifier is chosen as the predictor. The trained model achieves a 94% accuracy in predicting the severity of Asthma patients compared to previous work.
INTERNATIONAL JOURNAL OF NEXT-GENERATION COMPUTING
(2022)
Proceedings Paper
Computer Science, Interdisciplinary Applications
M. N. Kiranbabu, Yugandhar Garapati, Velagapudi Sreenivas, V. Murali Mohan
Summary: Monitoring services on cloud computing enabled devices requires a variety of tools to fit different applications and provide performance characteristics for specific software. We address the negotiation problem between SAAS resource users and propose an optimized algorithm.
PROCEEDINGS OF SECOND INTERNATIONAL CONFERENCE ON SUSTAINABLE EXPERT SYSTEMS (ICSES 2021)
(2022)
Proceedings Paper
Computer Science, Information Systems
R. M. Balajee, M. K. Jayanthi Kannan, V. Murali Mohan
Summary: Web design is currently focused on device screen size and user experience, utilizing predefined style sheets and responsive HTML. Customization options are limited, but product recommendations based on purchase history and gender are being implemented. Personal decision styles, geographic location, and culture also play a role in influencing shopping choices and website design.
INVENTIVE COMPUTATION AND INFORMATION TECHNOLOGIES, ICICIT 2021
(2022)
Proceedings Paper
Computer Science, Information Systems
R. M. Balajee, M. K. Jayanthi Kannan, V. Murali Mohan
Summary: The value of stored data is increasing, leading to higher risks of data hacking. To enhance data security, physical and electronic security measures should be improved. This study aims to reduce the burden of remembering input during authentication process.
INVENTIVE COMPUTATION AND INFORMATION TECHNOLOGIES, ICICIT 2021
(2022)
Proceedings Paper
Computer Science, Information Systems
R. M. Balajee, M. K. Jayanthi Kannan, V. Murali Mohan
Summary: The storage and demand for electronic data is a major problem in today's society. Data is becoming more centralized and accessible through cloud storage, but the increasing versatility of data poses a management challenge. Current research focuses on efficient searching algorithms, neglecting the combined technique of data prioritization, deletion, and rearrangement. The proposed automatic content creation-mechanism system aims to improve data management efficiency by creating new documents through the deletion of unwanted content and merging existing documents based on top keywords.
INVENTIVE COMPUTATION AND INFORMATION TECHNOLOGIES, ICICIT 2021
(2022)