Article
Computer Science, Information Systems
Basilio B. Fraguela, Diego Andrade, Jorge Gonzalez-Dominguez
Summary: Biclustering is a data mining technique for finding highly correlated groups of rows and columns in a 2D dataset. ScalaParBiBit is a parallel tool specifically designed for finding biclusters in binary data, with improved speed and scalability compared to existing tools.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Amir Javadpour, Arun Kumar Sangaiah, Pedro Pinto, Forough Ja'fari, Weizhe Zhang, Ali Majed Hossein Abadi, HamidReza Ahmadi
Summary: This paper proposes an algorithm that prioritizes tasks based on their execution deadline and categorizes physical machines based on their configuration status, aiming to optimize task scheduling in the cloud environment. By assigning jobs to physically close machines with the same priority class, and reducing energy consumption through the DVFS method for low-priority tasks, the proposed method achieves workload balance and machine class change. Evaluation using the CloudSim library shows an optimized energy consumption of 12% and power consumption of 20% with this method.
COMPUTER COMMUNICATIONS
(2023)
Article
Mathematics, Interdisciplinary Applications
Xingyu Miao, Jiayuan Wei, Yongqi Ge
Summary: This paper addresses the energy deception issue of EHES by designing an appropriate initial energy level of the battery and proposing three algorithms to judge the feasibility of the task set and calculate the proper initial battery capacity. Experimental results show that setting a reasonable initial energy level of the battery can effectively improve the feasibility of the task set.
Review
Chemistry, Analytical
Taiwo Samuel Ajani, Agbotiname Lucky Imoize, Aderemi A. Atayero
Summary: Embedded systems technology is undergoing transformation due to advancements in computer architecture and machine learning applications. However, implementing machine learning algorithms in resource-constrained environments like embedded and mobile devices requires innovative optimization techniques. Current research trends focus on optimizing computationally and memory-intensive algorithms for embedded and mobile computing environments, with an emphasis on key application areas and future exploration in embedded machine learning.
Article
Computer Science, Hardware & Architecture
Rohan Tabish, Jen-Yang Wen, Rodolfo Pellizzoni, Renato Mancuso, Heechul Yun, Marco Caccamo, Lui Raymond Sha
Summary: This paper proposes a Communication Core Model (CCM) to implement inter-core communication in a partitioned multicore system, bounding the amount of inter-core interference. Experimental results show that the CCM improves performance by up to 65% compared to Contention-based Communication (CBC), and the measured WCET aligns with the calculated bounds.
JOURNAL OF SYSTEMS ARCHITECTURE
(2021)
Article
Computer Science, Hardware & Architecture
Deepak Ramegowda, Man Lin
Summary: This paper presents the experience of implementing the "Cycle Conserving algorithm" on an embedded platform to handle mixed tasksets. The results show that the algorithm can successfully handle aperiodic requests while meeting the deadlines of periodic tasks and saving energy.
JOURNAL OF SYSTEMS ARCHITECTURE
(2022)
Article
Computer Science, Information Systems
Ying Chen, Ning Zhang, Yongchao Zhang, Xin Chen, Wen Wu, Xuemin (Sherman) Shen
Summary: This paper investigates task allocation and CPU-cycle frequency in mobile edge computing, proposing the TOFFEE algorithm to reduce energy consumption and limit queue length effectively. Performance evaluation shows that TOFFEE can decrease energy consumption by about 15 percent compared to the RLE algorithm and by about 38 percent compared to the RME algorithm.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2021)
Article
Computer Science, Theory & Methods
Mohsen Ansari, Sepideh Safari, Heba Khdr, Pourya Gohari-Nazari, Joerg Henkel, Alireza Ejlali, Shaahin Hessabi
Summary: This article introduces a peak-power-aware checkpointing (PPAC) technique that tolerates faults and meets power constraints in hard real-time embedded systems. By adjusting the timing of checkpoints and utilizing the available slack times on the cores, the technique reduces peak power and saves energy.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2022)
Article
Computer Science, Information Systems
Weishan Zhang, Haoyun Sun, Dehai Zhao, Liang Xu, Xin Liu, Huansheng Ning, Jiehan Zhou, Yi Guo, Su Yang
Summary: This study proposes a cloud platform for real-time video processing based on embedded devices, utilizing multiple GPUs for deep learning algorithm to process video streams, and designed self-managing services. The results show that the platform is capable of running deep learning algorithms on embedded devices and meeting the high scalability and fault tolerance required for real-time video processing.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2021)
Review
Computer Science, Information Systems
Ibrahim Alseadoon, Aakash Ahmad, Adel Alkhalil, Khalid Sultan
Summary: This study investigates the state-of-the-art research on migrating existing software systems to mobile computing platforms, aiming to analyze the progression and impacts of existing research, highlight challenges and solutions reflecting dimensions of emerging and futuristic research. The research identified three types of migration – Static, Dynamic, and State-based Migration – of existing software systems to mobile computing platforms, emphasizing the challenges and potential areas for futuristic research and development.
FRONTIERS OF COMPUTER SCIENCE
(2021)
Article
Computer Science, Information Systems
Chen Guo, Song Ci, Yanglin Zhou, Yang Yang
Summary: This paper emphasized the importance of accurate energy consumption analysis for embedded systems, studied major methods for measuring energy consumption, and summarized them into three categories. Factors contributing to energy consumption measurements and future research directions were proposed to enhance transparent energy analysis and improve energy efficiency of embedded systems.
Article
Computer Science, Theory & Methods
Roberto Rodriguez-Zurrunero, Alvaro Araujo
Summary: The article introduces a power consumption analysis study combining dynamic frequency scaling (DFS) and tick-less scheduling techniques, and proposes a new approach of an adaptive frequency scaling (AFS) OS module that can run applications at clock frequencies closer to optimal power consumption values, thus improving energy efficiency.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Engineering, Multidisciplinary
Song Li, Weibin Sun, Yanjing Sun, Yu Huo
Summary: This paper discusses an optimization framework for computation offloading in mobile edge computing systems. By optimizing communication and computation resource allocation, the proposed joint scheme significantly improves the energy efficiency of devices compared to local and server computing schemes.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Information Systems
Camilo Lozoya, Jose Miguel Diaz, Cesar Rodriguez-Esqueda, Claudia Prieto-Resendiz, Alberto Aguilar-Gonzalez
Summary: This paper presents an embedded software development framework for IoT devices that improves efficiency and reliability, shortens learning curves and module validation time.
Article
Computer Science, Theory & Methods
Samia Ijaz, Ehsan Ullah Munir, Saima Gulzar Ahmad, M. Mustafa Rafique, Omer F. Rana
Summary: The article investigates workflow scheduling in fog-cloud environments, proposing an energy-efficient task scheduling algorithm that can reduce energy consumption while meeting application completion time requirements. The algorithm works in two phases, balancing conflicting objectives by allocating tasks to fog and cloud resources, and reducing energy consumption through frequency scaling.
Review
Mathematics
Wai Khuen Cheng, Khean Thye Bea, Steven Mun Hong Leow, Jireh Yi-Le Chan, Zeng-Wei Hong, Yen-Lin Chen
Summary: Stock forecasting is an important and challenging task, and with the development of web technologies, more information is being shared by the public on the internet. This information is crucial for understanding the changes in the financial market and improving forecasting accuracy, but manually processing such a large amount of unstructured textual data is complex.
Article
Chemistry, Analytical
Wai Khuen Cheng, Wai Chun Leong, Joi San Tan, Zeng-Wei Hong, Yen-Lin Chen
Summary: In this era, a smart home solution is proposed to monitor pets' behaviors and provide interaction among dog friends. The solution includes an application to predict dogs' behaviors and a communication platform to connect different households.
Article
Mathematics
Jireh Yi-Le Chan, Seuk Wai Phoong, Wai Khuen Cheng, Yen-Lin Chen
Summary: Past studies have shown that although more advanced models and techniques are being developed for intelligent algorithm trading, the input features of these models are very similar. This study proposes a novel methodology to introduce Support Resistance input features, and empirical evidence suggests that including these features can significantly improve the profitability of machine learning models, as well as impact the profitability distribution between models with and without the Support Resistance input features.
Article
Mathematics
Jireh Yi-Le Chan, Seuk Wai Phoong, Seuk Yen Phoong, Wai Khuen Cheng, Yen-Lin Chen
Summary: This paper introduces a unique perspective on the safe haven and hedge properties of Bitcoin through the Bitcoin halving cycle. The study finds that gold lost its safe haven properties against the S&P500 in 2021, while Bitcoin did not exhibit safe haven or hedge properties against US stock market indices. The results also show that regime changes in Bitcoin's volatility dynamics are associated with low and high volatility periods rather than specific stages of the halving cycle.
Article
Energy & Fuels
Jing Yang, Yen-Lin Chen, Por Lip Yee, Chin Soon Ku, Manoochehr Babanezhad
Summary: This paper aims to optimize the design of a hybrid energy system (HES) consisting of photovoltaic technology integrated with fuel cells (HPV/FC) and hydrogen storage. Real meteorological data from Kuala Lumpur, Malaysia is used to meet the annual demand of a residential complex while minimizing the total net present cost (TNPC). An improved artificial ecosystem-based optimization algorithm (IAEO) is used to determine the optimal sizes of system components. The results show that a decrease (increase) in the reliability constraint leads to an increase (decrease) in TNPC and cost of electricity (COE).
Article
Green & Sustainable Science & Technology
Asif Ali Wagan, Abdullah Ayub Khan, Yen-Lin Chen, Por Lip Yee, Jing Yang, Asif Ali Laghari
Summary: According to US officials, game-based learning in schools and colleges, with the help of AI-enabled augmented intelligence techniques, improves children's neurodevelopment, intellectual sensing, and specific learning abilities. There has been a global increase in the use of game-based augmented learning, but it also poses challenges such as the negative effects on institutional premises, learning speed and attendance, students' adaptation, and teachers' experience. To address these challenges, a secure AI-based augmented game learning environment called B-AIQoE, incorporating blockchain technology, is proposed.
Article
Multidisciplinary Sciences
Wassim Alexan, Yen-Lin Chen, Lip Yee Por, Mohamed Gabr
Summary: With the exponential growth of image data generation, transmission, and sharing over unsecured networks, the development of novel image encryption algorithms has become extremely important. In this research, we propose a new image encryption framework based on two hyperchaotic maps and the single neuron model (SNM). The framework consists of three stages, with each stage applying a substitution box (S-box) and XORing with an encryption key. The proposed framework shows superior performance and complete asymmetry between plain and encrypted images, with a vast key space and high encryption efficiency.
Review
Chemistry, Multidisciplinary
Jing Yang, Yen-Lin Chen, Lip Yee Por, Chin Soon Ku
Summary: This article conducts a systematic literature review to analyze the information security threats in chatbots and propose solutions and future research directions. The study identifies various security threats in chatbots, such as malicious input, user profiling, contextual attacks, and data breaches, and suggests using blockchain technology, end-to-end encryption, and organizational controls to mitigate these concerns. The review emphasizes the importance of maintaining user trust and addressing privacy issues for successful adoption and continued use of chatbots. The findings provide a taxonomy framework and contribute to the growing body of literature on information security in chatbots.
APPLIED SCIENCES-BASEL
(2023)
Article
Mathematics
Jing Yang, Jiale Xiong, Yen-Lin Chen, Por Lip Yee, Chin Soon Ku, Manoochehr Babanezhad
Summary: This paper investigates the multi-objective allocation and scheduling of wind turbines and electric vehicle parking lots in an IEEE 33-bus radial distribution network. An improved golden jackal optimization (IGJO) algorithm based on Rosenbrock's direct rotational (RDR) strategy is used to find the optimal solution. The results show that the proposed method outperforms conventional optimization methods in terms of convergence tolerance and objective function value.
Article
Mathematics
Chin Soon Ku, Jiale Xiong, Yen-Lin Chen, Shing Dhee Cheah, Hoong Cheng Soong, Lip Yee Por
Summary: This study proposes an approach that integrates investor domain knowledge with a long-short-term memory (LSTM) algorithm for stock price prediction. The approach involves collecting technical indicator data from investors and using them as input for the LSTM model. The model is trained and tested using a dataset of 100 stocks, and its accuracy and performance are evaluated and compared to other strategies.
Review
Green & Sustainable Science & Technology
Xiaobo Liu, Yen-Lin Chen, Lip Yee Por, Chin Soon Ku
Summary: Vehicle routing problems with time windows (VRPTW) have gained a lot of attention due to their important role in real-life logistics and transport. As a result of the complexity of real-life situations, most problems are multi-constrained and multi-objective, which increases their difficulty. This paper aims to contribute to the effective solution of VRPTW-related problems. Data extraction and analysis of the relevant literature within the last five years (2018-2022) are compared to answer the set research questions, and the results show the prevalence of approximate methods and hybrid approaches.
Article
Mathematics
A. Hasib Uddin, Yen-Lin Chen, Bijly Borkatullah, Mst. Sathi Khatun, Jannatul Ferdous, Prince Mahmud, Jing Yang, Chin Soon Ku, Lip Yee Por
Summary: This research addresses the lack of publicly available datasets for Bangladeshi medicinal plants by presenting a comprehensive dataset comprising 5000 images of ten species collected under controlled conditions. To improve performance, various preprocessing techniques were employed and state-of-the-art deep learning models were applied. Novel neural network architectures were also developed and an ensemble approach was adopted to further enhance classification accuracy. The outcomes of this study have significant implications for the accurate identification and classification of Bangladeshi medicinal plants.
Article
Computer Science, Information Systems
Mohammad Asad Abbasi, Yen-Lin Chen, Abdullah Ayub Khan, Zulfiqar A. Memon, Nouman M. Durrani, Jing Yang, Chin Soon Ku, Lip Yee Por
Summary: The Internet of Things (IoT) enables devices and services to interact and perform tasks for each other in a distributed computing environment. This article investigates the requirements of heterogeneous IoT services and proposes a classification method based on different attributes to improve resource utilization.
Article
Computer Science, Information Systems
Ko-Feng Lee, Xiu-Zhi Chen, Chao-Wei Yu, Kai-Yi Chin, Yih-Chen Wang, Chia-Yu Hsiao, Yen-Lin Chen
Summary: In this study, an intelligent driver assistance system is developed to remind drivers to turn on head lights or wipers in night or rainy conditions. The system integrates object detection results from multiple perspectives and alarms drivers when surrounding vehicles are too close. Experimental results show that the proposed system achieves reliable performance and computational efficiency under limited computing resources.
Article
Computer Science, Information Systems
Yi-Hao Chung, Yen-Lin Chen
Summary: We propose a 3D image inpainting system using a generative adversarial network for accurate detection in rotor dynamic balancing processes. The system can repair overexposed 3D rotor images and handle complex corrupted images while maintaining image details. By incorporating 3D sensors and deep learning, the system improves success rate, reduces balancing rounds, and increases rotor production output in dynamic balancing.