Article
Chemistry, Multidisciplinary
Chirag Chandrashekar, Pradeep Krishnadoss, Vijayakumar Kedalu Poornachary, Balasundaram Ananthakrishnan, Kumar Rangasamy
Summary: With the advancement of technology and time, various algorithms have been proposed to improve the performance of individual units or structures used in the cloud environment. Task scheduling is one of the most important sections of cloud computing, responsible for optimizing the time taken to execute processes and improving efficiency. This paper proposes an ideal and optimal task scheduling algorithm and compares it with other existing algorithms in terms of efficiency, makespan, and cost parameters.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Xingwang Huang, Yangbin Lin, Zongliang Zhang, Xiaoxi Guo, Shubin Su
Summary: This paper proposes a task scheduling method based on gradient-based optimization, which converts real vector values to integer values to solve the task scheduling problem in cloud computing systems. Experimental results show that this method has better convergence speed and accuracy in searching for optimal solutions compared to current heuristic algorithms, especially in the presence of large-scale tasks.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Muhammad Usman Sana, Zhanli Li, Fawad Javaid, Muhammad Wahab Hanif, Imran Ashraf
Summary: This study proposes a novel encoding technique using blockchain and Improved Particle Swarm Optimization (IPSO) to improve the makespan value and scheduling time. The experimental results indicate that the proposed algorithm is practical and secure in handling flexible job scheduling and outperforms the state-of-the-art task scheduling algorithms.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Automation & Control Systems
B. Mohammad Hasani Zade, N. Mansouri, M. M. Javidi
Summary: This study introduces a hybrid metaheuristic algorithm called HFHB for task scheduling problems, which combines fuzzy features and optimization algorithms to achieve significant progress in solving multi-objective problems. The algorithm demonstrates better performance compared to other algorithms in experimental evaluations.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
Anurina Tarafdar, Mukta Debnath, Sunirmal Khatua, Rajib K. Das
Summary: Cloud computing allows for various applications to be executed by users in a virtualized environment, but it also consumes significant energy; healthcare, scientific research, IoT tasks are deadline-sensitive, requiring efficient scheduling to reduce energy consumption; proposed approaches effectively address the trade-off between energy consumption and task completion time.
JOURNAL OF GRID COMPUTING
(2021)
Article
Mathematics
Ibrahim Attiya, Laith Abualigah, Doaa Elsadek, Samia Allaoua Chelloug, Mohamed Abd Elaziz
Summary: This paper investigates intelligent scheduling approaches to optimize the task scheduling of IoT applications in cloud computing. The proposed CHMPAD algorithm addresses the drawbacks of local optima and the basic ChOA algorithm. Experimental results show that CHMPAD significantly improves the average makespan time across different workloads.
Article
Computer Science, Artificial Intelligence
Mohd Sha Alam Khan, R. Santhosh
Summary: Cloud computing offers a variety of services and has powerful processing capacity, but struggles with resource allocation. A task scheduling method based on a hybrid optimization algorithm is proposed in the study to reduce waiting time effectively.
Article
Computer Science, Artificial Intelligence
Sarah E. Shukri, Rizik Al-Sayyed, Amjad Hudaib, Seyedali Mirjalili
Summary: Cloud computing is a popular technology that enables users to remotely access computing resources in a pay-as-you-go model. Task scheduling is a primary challenge in cloud computing environments, with many meta-heuristic algorithms like MVO and PSO being used. The Enhanced Multi-Verse Optimizer (EMVO) proposed in this paper outperforms both MVO and PSO algorithms in terms of minimizing makespan time and increasing resource utilization in cloud environments.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Automation & Control Systems
Mohamed Abdel-Basset, Reda Mohamed, Mohamed Elhoseny, Ali Kashif Bashir, Alireza Jolfaei, Neeraj Kumar
Summary: This article proposes an energy-aware model based on the marine predators algorithm for improving task scheduling in fog computing to enhance the required quality of service for users. Three versions are proposed, with the improved MMPA outperforming all other algorithms.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Automation & Control Systems
Lei Yin, Chang Sun, Ming Gao, Yadong Fang, Ming Li, Fengyu Zhou
Summary: In this paper, a hyper-heuristic algorithm based on reinforcement learning (HHRL) is proposed to optimize the completion time of the task sequence. The algorithm introduces population diversity in the reward table setting stage and comprehensively considers task scheduling and the selection of low-level heuristic strategies. Furthermore, a task complexity estimation method and a high-quality candidate solution migration method are proposed. Compared with other algorithms, HHRL can quickly obtain task complexity, select appropriate heuristic strategies for task scheduling, and has stronger disturbance detection ability for population diversity.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2023)
Article
Computer Science, Information Systems
Kaushik Mishra, Jharashree Pati, Santosh Kumar Majhi
Summary: This article discusses the importance of handling dynamic workloads in datacenters and the challenges that can lead to server imbalance. To address the fluctuating resource provisioning needs, a method based on binary JAYA is proposed for load scheduling and load balancing, aiming to improve resource utilization and reduce energy consumption and makespan.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Automation & Control Systems
Ibrahim Attiya, Mohamed Abd Elaziz, Laith Abualigah, Tu N. Nguyen, Ahmed A. Abd El-Latif
Summary: This article proposes a new task scheduling method, called MRFOSSA, for optimizing the scheduling of IoT application tasks in cloud computing. This method uses a hybrid swarm intelligence approach, utilizing a modified Manta ray foraging optimization algorithm and the salp swarm algorithm, to improve local search ability and outperform other metaheuristic techniques.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Hardware & Architecture
Minhaj Ahmad Khan
Summary: This paper proposes a power-aware cloudlet scheduling algorithm that aims at reducing request processing time through mapping cloudlets to virtual machines while minimizing energy consumption and cost. Experimental results show a significant overall performance improvement over other well-known cloudlet scheduling algorithms.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Computer Science, Information Systems
R. Ghafari, N. Mansouri
Summary: This paper proposes a multi-objective task scheduling algorithm DCOHHOTS based on a modified Harris hawks optimizer, aiming to optimize resource utilization and reduce makespan, energy consumption, and execution cost. The algorithm prioritizes tasks using a hierarchical process, and experimental results show that it can save up to 16% energy and increase resource utilization by 17% in heavy loads compared to existing algorithms. Furthermore, the proposed algorithm reduces makespan and execution cost by 26% and 8% respectively, compared to the conventional algorithm.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
Nimra Malik, Muhammad Sardaraz, Muhammad Tahir, Babar Shah, Gohar Ali, Fernando Moreira
Summary: This article addresses the issue of energy consumption and efficient resource utilization in virtualized cloud data centers, proposing an algorithm based on task classification and thresholds for efficient scheduling. Experiments validate the effectiveness of the proposed technique over other algorithms in terms of energy consumption, makespan, and load balancing.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Information Systems
Hakam Singh, Vipin Rai, Neeraj Kumar, Pankaj Dadheech, Ketan Kotecha, Ganeshsree Selvachandran, Ajith Abraham
Summary: This study introduces an enhanced whale optimization algorithm (EWOA) for clustering problems. By incorporating the position update equations from the water wave optimization algorithm and adding tabu and neighbourhood search mechanisms, the algorithm improves the search space and accelerates the convergence rate. Experimental results demonstrate the applicability and feasibility of the enhancements and the superiority of the proposed EWOA clustering algorithm.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Analytical
Bhaskar Kapoor, Bharti Nagpal, Praphula Kumar Jain, Ajith Abraham, Lubna Abdelkareim Gabralla
Summary: This paper proposes a hybrid optimization-controlled ensemble classifier to automatically analyze EEG signal dataset for epileptic seizure prediction, combining signal processing and machine learning. The proposed technique shows high accuracy, sensitivity, and specificity in early seizure prediction.
Article
Chemistry, Analytical
Sameer Sayyad, Satish Kumar, Arunkumar Bongale, Ketan Kotecha, Ajith Abraham
Summary: The milling machine plays a crucial role in the manufacturing industry due to its versatility in machining. The cutting tool is of utmost importance in machining as it affects machining accuracy and surface finishing, thus impacting industrial productivity. To avoid machining downtime caused by tool wear, monitoring the cutting tool's life is essential. Accurately predicting the remaining useful life (RUL) of the cutting tool is crucial for preventing unplanned machine downtime and maximizing tool life.
Review
Physics, Applied
Mohammad Yazdani-Asrami, Wenjuan Song, Antonio Morandi, Giovanni De Carne, Joao Murta-Pina, Anabela Pronto, Roberto Oliveira, Francesco Grilli, Enric Pardo, Michael Parizh, Boyang Shen, Tim Coombs, Tiina Salmi, Di Wu, Eric Coatanea, Dominic A. Moseley, Rodney A. Badcock, Mengjie Zhang, Vittorio Marinozzi, Nhan Tran, Maciej Wielgosz, Andrzej Skoczen, Dimitrios Tzelepis, Sakis Meliopoulos, Nuno Vilhena, Guilherme Sotelo, Zhenan Jiang, Veit Grosse, Tommaso Bagni, Diego Mauro, Carmine Senatore, Alexey Mankevich, Vadim Amelichev, Sergey Samoilenkov, Tiem Leong Yoon, Yao Wang, Renato P. Camata, Cheng-Chien Chen, Ana Maria Madureira, Ajith Abraham
Summary: This paper presents a roadmap for applying AI techniques and big data (BD) in various aspects of superconducting applications, such as modelling, design, monitoring, manufacturing, and operation. Short articles are provided to outline potential applications and solutions, aiming to assist researchers, engineers, and manufacturers in understanding the feasibility of using AI and BD techniques to tackle challenges in superconductivity. These potential futuristic routes and their related materials/technologies are considered for a time frame of 10-20 years.
SUPERCONDUCTOR SCIENCE & TECHNOLOGY
(2023)
Article
Multidisciplinary Sciences
Arturas Kaklauskas, Ajith Abraham, Loreta Kaklauskiene, Ieva Ubarte, Dilanthi Amaratunga, Irene Lill, Virginijus Milevicius, Ulijona Kaklauskaite
Summary: This study aimed to achieve maximum efficiency in climate change actions while minimizing the negative impact on the well-being of countries and cities. The research showed that improvements in economic, social, political, cultural, and environmental metrics of countries and cities resulted in better climate change indicators.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Shio Gai Quek, Ganeshsree Selvachandran, Angie Yih Tsyr Wong, Feng Shin Wong, Weiping Ding, Ajith Abraham
Summary: This paper introduces a fuzzy logic-based machine learning algorithm and applies it to solve the evaluation and ranking problem of public listed companies. The algorithm incorporates a genetic algorithm during the training process and is integrated into two popular decision-making methods. Empirical results demonstrate the effectiveness and consistency of the proposed methods in multi-attribute decision-making.
APPLIED SOFT COMPUTING
(2023)
Article
Engineering, Biomedical
Sonam Palden Barfungpa, Leena Samantaray, Hiren Kumar Deva Sarma, Rutuparna Panda, Ajith Abraham
Summary: Heart disease is a leading cause of high mortality. Data mining is gaining attention in healthcare for predicting heart disease with maximum accuracy, aiming to minimize treatment costs and save lives.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Biomedical
Sheetal Rajpal, Ankit Rajpal, Manoj Agarwal, Virendra Kumar, Ajith Abraham, Divya Khanna, Naveen Kumar
Summary: This study aims to discover a set of CNV biomarkers for dissecting molecular heterogeneity in breast cancer. DLmodel, a deep learning model, was built for breast cancer classification and analyzed using explainable AI methods, resulting in 44 CNV biomarkers. Cross-validation showed a classification accuracy of 0.712, and gene set analysis revealed subtype-specific enriched pathways and druggable genes. The efficacy of the identified biomarkers was validated on METABRIC, demonstrating the role of explainable AI in discovering clinically reliable biomarkers.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Electrical & Electronic
Ankit Rajpal, Subodh Kumar, Neeraj Kumar Sharma, Ajith Abraham, Anurag Mishra, Naveen Kumar
Summary: This paper proposes a chest X-ray image watermarking scheme (CXRmark) using an online sequential reduced kernel extreme learning machine (OS-RKELM). The scheme segments the lung area into the region of non-interest (RONI) and region of interest (ROI) using U-Net, and modulates the approximation coefficients using OS-RKELM with different embedding strengths for ROI and RONI. Experimental results on 461 CXR images demonstrate that CXRmark outperforms other schemes in terms of perceptual quality and robustness.
CIRCUITS SYSTEMS AND SIGNAL PROCESSING
(2023)
Review
Telecommunications
Rucha Shinde, Shruti Patil, Ketan Kotecha, Vidyasagar Potdar, Ganeshsree Selvachandran, Ajith Abraham
Summary: Healthcare institutions are integrating artificial intelligence (AI) into their operations, but limitations such as insufficient medical data, adversarial attacks, and lack of transparency hinder the realization of AI's potential. This literature review focuses on the research of utilizing blockchain technology to secure AI-integrated healthcare applications, discussing the need to protect datasets, training phases, and trained models to prevent malfunctions. The analysis of natural language processing, computer vision, and acoustic AI reveals the need for security measures, and a blockchain solution is proposed to address the privacy and security issues faced by different AI modalities.
TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES
(2023)
Article
Computer Science, Information Systems
M. Anousouya Devi, R. Ezhilarasie, K. Suresh Joseph, Ketan Kotecha, Ajith Abraham, Subramaniyaswamy Vairavasundaram
Summary: In this paper, an Improved Boykov's Graph Cut-based Conditional Random Fields and Superpixel imposed Semantic Segmentation Technique (IBGC-CRF-SPSST) is proposed for efficient cervical cancer detection. This technique combines constraint association among pixels and superpixel edge data to accurately determine the nuclei and cytoplasmic boundaries, achieving effective differentiation of healthy and unhealthy cancer cells. The inclusion of pixel-level forecasting potential of Conditional Random Fields further enhances the semantic-based segmentation accuracy. Experimental results show that the proposed IBGC-CRF-SPSST achieves excellent performance comparable to existing detection techniques, with an accuracy of 99.78%, mean processing time of 2.18 seconds, precision of 96%, sensitivity of 98.92%, and specificity of 99.32%.
Article
Computer Science, Information Systems
R. Devi Priya, S. Karthikeyan, Indra Jaganathan, Kiruba Shankar Rameshbabu, Ajith Abraham, Lubna A. Gabralla, R. Sivaraj, S. M. Nandhagopal
Summary: Tamil character recognition is a challenging task in pattern recognition due to the complexity and similarity of characters compared to other languages. Stone inscriptions provide valuable insights into the history, culture, and administration of Tamil Nadu, but their preservation and understanding are hindered by erosion and incompleteness. The recognition of Tamil characters in stone inscriptions faces difficulties mainly due to the presence of characters with holes, loops, and curves.
Article
Computer Science, Information Systems
S. Saravanan, Kannan Ramkumar, K. Narasimhan, Subramaniyaswamy Vairavasundaram, Ketan Kotecha, Ajith Abraham
Summary: Parkinson's disease is a rapidly growing neurodegenerative disorder that primarily affects the elderly population. Diagnosing Parkinson's disease in its early stages is difficult, and there is currently no antidote for the disease. This study aims to use deep learning models to improve early diagnosis accuracy and increase transparency and trustworthiness.
Article
Computer Science, Information Systems
A. Sasikumar, Logesh Ravi, Ketan Kotecha, Ajith Abraham, Malathi Devarajan, Subramaniyaswamy Vairavasundaram
Summary: Data security and integrity are crucial as data volume grows. Blockchain technology addresses challenges and safeguards personal information. This study introduces a new approach using blockchain and a highway protocol for real-time big data storage security. The proposed protocol allows blocks to configure security thresholds and achieve finality more quickly. The framework dynamically controls data manipulation and supports data-sharing. The highway protocol outperforms baseline models in terms of hit ratio, data processing period, and energy consumption.
Article
Computer Science, Information Systems
Gargi Joshi, Ananya Srivastava, Bhargav Yagnik, Mohammed Hasan, Zainuddin Saiyed, Lubna A. Gabralla, Ajith Abraham, Rahee Walambe, Ketan Kotecha
Summary: Web Information Processing (W.I.P.) has had a significant impact on modern society as many people rely on the internet for information. Social Media platforms provide both a means of disseminating information and a breeding ground for misinformation. Machine learning models have been used to detect misinformation, but the development of generalized and explainable detectors remains a challenge. Integrating domain adaptation and explainable A.I. approaches can address these challenges.