Article
Computer Science, Information Systems
Meysam Masoudi, Cicek Cavdar
Summary: This research investigates the power minimization problem for mobile devices by data offloading in multi-cell multi-user OFDMA mobile edge computing networks. By utilizing proposed algorithms, considerable power savings can be achieved, such as about 60% for large bit stream size compared to local computing baseline.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2021)
Article
Computer Science, Hardware & Architecture
Cassio L. M. Belusso, Sandro Sawicki, Vitor Basto-Fernandes, Rafael Z. Frantz, Fabricia Roos-Frantz
Summary: Growing demand for reduced local hardware infrastructure is driving the adoption of Cloud Computing. In this study, the researchers propose D-AHP, a decision-making methodology based on Pareto Dominance and Analytic Hierarchy Process (AHP), to assist users in selecting virtual machine instances. The study finds that considering the datacenter location as a criterion for instance selection can lead to different results on which instance is more suitable for the user.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Computer Science, Information Systems
Abid Ali, Muhammad Munwar Iqbal
Summary: This study proposes a Dynamic Decision-Based Task Scheduling Technique for Microservice-based Mobile Cloud Computing Applications (MSCMCC), which can reduce the cost and improve mobile server utilization.
Article
Computer Science, Information Systems
Mahmood ul Hassan, Amin A. Al-Awady, Abid Ali, Muhammad Munawar Iqbal, Muhammad Akram, Jahangir Khan, Ali Ahmad AbuOdeh
Summary: The use of smartphones and mobile devices, as well as Mobile Cloud Applications based on cloud computing, has increased significantly. This paper proposes a Dynamic Decision-Based Task Scheduling Approach for Microservice-based Mobile Cloud Computing Applications (MSCMCC) to address the problems of overhead, lengthy boot time, and high costs in existing cloud-based frameworks. The proposed approach, including the Task Offloading and Microservices based Computational Offloading (TSMCO) framework, effectively improves mobile server utilization, reduces costs, and enhances boot time, resource utilization, and task arrival time for various applications.
PERVASIVE AND MOBILE COMPUTING
(2023)
Article
Computer Science, Information Systems
Huaming Wu, Katinka Wolter, Pengfei Jiao, Yingjun Deng, Yubin Zhao, Minxian Xu
Summary: This article explores how to achieve secure task offloading collaboration between edge computing and cloud computing using blockchain. By combining MEC and MCC, a blockchain-enabled IoT-Edge-Cloud computing architecture is proposed, providing faster computing services and stronger computational power while minimizing energy consumption and task response time.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Review
Computer Science, Hardware & Architecture
Ahmad Salah AlAhmad, Hasan Kahtan, Yehia Ibrahim Alzoubi, Omar Ali, Ashraf Jaradat
Summary: Mobile cloud computing (MCC) is a popular technology, but it currently faces critical security issues including authentication, privacy, and trust. Existing MCC models lack comprehensive protection for data, resources, and communication channels. Further research and design solutions are needed from model developers and practitioners.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Faiza Samreen, Gordon S. Blair, Yehia Elkhatib
Summary: This article presents a transfer learning based decision support system that reduces time and cost in building new models for performance of new applications and cloud infrastructures.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2022)
Article
Computer Science, Information Systems
Song Yang, Nan He, Fan Li, Stojan Trajanovski, Xu Chen, Yu Wang, Xiaoming Fu
Summary: The combination of C-RAN and MEC can improve spectrum utilization and delay-guaranteed services, shortening service delays by co-locating the BBU pool with edge cloud at the BBU node. Research has focused on user task allocation, path planning, and survivability concerns, proving the NP-hardness of these issues.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Automation & Control Systems
Shanhe Lou, Yixiong Feng, Zhiwu Li, Hao Zheng, Yicong Gao, Jianrong Tan
Summary: This article introduces an edge-based enterprise system framework for design scheme evaluation, which addresses the issues of information island and collaborative decision-making. By incorporating a multigroup decision-making algorithm and utilizing EEG data, it can effectively integrate evaluation results from designers, experts, and customers, ultimately determining the optimal design scheme.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Chun Jiang, Jiafu Wan
Summary: With the development of Industry 4.0 and cloud computing technology, personalized customization as a new production mode is rapidly evolving. The proposed thing-edge-cloud collaborative computing decision-making method aims to optimize task processing and equipment utilization in personalized customization production, addressing uncertainties and challenges in the production system.
Article
Computer Science, Information Systems
Mohammed S. Zalat, Saad M. Darwish, Magda M. Madbouly
Summary: The fast development of mobile applications has increased the need for more resources and processing power on mobile devices. Mobile Cloud Computing combines cloud computing with mobile devices to enable resource-intensive applications to run on mobile devices. Computation offloading is used to overcome the performance limits of mobile devices, allowing heavy tasks to be offloaded to servers. However, most existing techniques for offloading choices are based on profile data and do not support multi-site offloading. This research proposes a novel strategy that combines genetic algorithms and Markov Decision Process to enhance the multi-site offloading mechanism by optimizing the offloading location and transition probability.
Article
Multidisciplinary Sciences
Iqbal H. Sarker, Asif Irshad Khan, Yoosef B. Abushark, Fawaz Alsolami
Summary: This paper discusses the challenges and importance of adding personalized decision-making intelligence to mobile applications, proposing the use of machine-learning rules as knowledge base instead of traditional rules. Experimental results show that context-aware machine learning rules discovered from users' mobile phone data can help build a mobile expert system to solve specific problems.
Article
Computer Science, Information Systems
Zhipeng Cai, Zhuojun Duan, Wei Li
Summary: This paper investigates the joint problem of sensing task assignment and schedule in Mobile Crowdsensing Systems (MCSs) and proposes four auction schemes, with task owner-centric and mobile user-centric approaches. These schemes differ in their methods for processing auction procedures and computing payments.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2021)
Article
Computer Science, Information Systems
Joao Correia, Alexandre Bernardino, Ricardo Ribeiro
Summary: Unmanned aerial vehicles (UAVs) are increasingly being used in various fields, but low-cost commercial UAVs may not have enough computational power to run state-of-the-art algorithms, impacting performance. Remote computational systems can be a solution, but they introduce latency, which is undesirable for real-time tasks. Furthermore, for simple tasks, using a local algorithm with worse performance may be acceptable to avoid latency. Hence, a method to decide which algorithm to use is crucial.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Jie Huang, Ao Zhou, Shangguang Wang
Summary: Mobile-edge computing (MEC) is seen as a promising solution to alleviate pressure on the core network and reduce service response time. However, it is challenging to make appropriate service deployment decisions due to limited resources and diverse service requirements. In this article, the authors focus on the hierarchical MEC network and propose an iterative algorithm to minimize monetary cost through service caching, resource allocation, and task scheduling.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Honglong Chen, Zhe Li, Zhu Wang, Zhichen Ni, Junjian Li, Ge Xu, Abdul Aziz, Feng Xia
Summary: The rapid growth of edge data generated by mobile devices has led to information overload, which can be alleviated by recommender systems. The Ti-PMF model combines multiple models to improve rating prediction accuracy.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jiaying Liu, Feng Xia, Xu Feng, Jing Ren, Huan Liu
Summary: Anomaly detection in citation networks is an important research area that has received little attention. The proposed GLAD model combines text semantic mining and graph neural networks to effectively identify anomalies in citation networks. Experimental results demonstrate the effectiveness of GLAD in the task of anomalous citation detection.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Cybernetics
Shuo Yu, Sihan He, Zhen Cai, Ivan Lee, Mehdi Naseriparsa, Feng Xia
Summary: This study investigates the differences in reactions to the COVID-19 pandemic across various countries using social media posts on Twitter and Weibo. The findings highlight noticeable variations in public reactions to certain policies among different countries, emphasizing the significant impact of sentiment analysis on policy-making.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Engineering, Multidisciplinary
Feng Xia, Shuo Yu, Chengfei Liu, Jianxin Li, Ivan Lee
Summary: This paper proposes a solution called CHIEF for efficient motif clustering in large networks, and validates the significance of higher-order motifs.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Editorial Material
Automation & Control Systems
H. O. N. G. L. O. N. G. CHEN, J. O. E. L. RODRIGUES, F. E. N. G. XIA, S. A. J. A. L. DAS
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Jiaying Liu, Feng Xia, Jing Ren, Bo Xu, Guansong Pang, Lianhua Chi
Summary: The explosion of data in the information society drives the need for more effective ways to extract meaningful information. Extracting semantic and relational information has become an important mining technique in practical applications. Current research on relation mining has mainly focused on explicit connections and ignored latent information, such as latent entity relations. This article proposes a novel research topic of identifying implicit relationships across heterogeneous networks. A graph convolutional network (GCN) model called MIRROR is introduced to infer implicit ties by incorporating attributes from heterogeneous neighbors and utilizing network structure. Empirical evaluations show that MIRROR achieves state-of-the-art performance in target relations mining, and the underlying information revealed contributes to enriching existing knowledge and gaining novel domain insights.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2023)
Article
Computer Science, Information Systems
Zhi Liu, Yang Chen, Feng Xia, Jixin Bian, Bing Zhu, Guojiang Shen, Xiangjie Kong
Summary: Predicting traffic accidents can help traffic management departments respond promptly to sudden situations, improve driver vigilance, and reduce accident-related losses. However, current methods for traffic accident prediction do not consider the dynamic spatio-temporal correlation of traffic data, resulting in unsatisfactory accuracy. To address this, we propose a multi-task learning framework (TAP) based on ST-VGAE for traffic accident profiling. Experimental results on real datasets show that TAP outperforms other state-of-the-art methods.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2023)
Article
Computer Science, Information Systems
Teng Guo, Xiaomei Bai, Shihao Zhen, Shagufta Abid, Feng Xia
Summary: Helping freshmen adapt to university life is a long-term goal for academic institutions. This article proposes a prediction framework (MASTER) to tackle the issue of maladaptation in students, using the SMOTE algorithm to address data label imbalance and introducing the priority forest algorithm for prioritized interventions.
JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Falih Gozi Febrinanto, Feng Xia, Kristen Moore, Chandra Thapa, Charu Aggarwal
Summary: Graph learning is a popular approach for machine learning on graph-structured data, but most methods assume static graphs and cannot handle dynamically growing or evolving graphs. This survey paper provides a comprehensive overview of recent advancements in graph lifelong learning and discusses potential applications and open research problems.
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE
(2023)
Article
Computer Science, Artificial Intelligence
Ciyuan Peng, Feng Xia, Mehdi Naseriparsa, Francesco Osborne
Summary: With the explosive growth of AI and big data, the organization and representation of knowledge becomes crucial. Knowledge graphs, as graph data, effectively accumulate and convey knowledge of the real world, gaining rapid attention in academia and industry. This paper presents a systematic overview focusing on the opportunities and challenges of knowledge graphs. It reviews the opportunities in terms of AI systems and potential application fields, and thoroughly discusses technical challenges such as embeddings, acquisition, completion, fusion, and reasoning. The survey aims to provide insights for future research and development of knowledge graphs.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Editorial Material
Computer Science, Artificial Intelligence
Feng Xia, Leman Akoglu, Charu Aggarwal, Huan Liu
Summary: Deep anomaly analytics is an evolving field that utilizes deep learning to detect anomalies in datasets. Its application has grown due to the need to detect anomalies in complex data. It has the potential to transform industries such as healthcare, finance, and cybersecurity by providing insights and detecting threats. However, challenges such as time series and graph anomaly detection, model efficiency, and solving real-world problems exist. This editorial provides an overview of deep anomaly analytics and highlights key challenges in the field.
IEEE INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Cybernetics
Dongyu Zhang, Ciyuan Peng, Xiaojun Chang, Feng Xia
Summary: This article explores the impact of facial perception on the social centrality of students in social networks and compares it with academic performance. The experimental results demonstrate that both facial perception and academic performance are closely correlated with students' social centrality.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Biochemical Research Methods
Zhichen Ni, Honglong Chen, Zhe Li, Xiaomeng Wang, Na Yan, Weifeng Liu, Feng Xia
Summary: With the development of AI and IoT, computation intensive and delay sensitive tasks in vehicles pose challenges to driver biometric monitoring. Edge computing offers a solution by offloading tasks to Edge Servers in RSUs, but some tasks may be too complex for ESs. To address this, we propose a collaborative vehicular network where cloud, edge, and terminal cooperate. Vehicles offload computation intensive tasks to the cloud, and we construct a virtual resource pool to integrate resources from multiple ESs. Our proposed MSCET schedule optimizes system utility and outperforms existing schedules according to extensive simulations.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Computer Science, Cybernetics
Xingfa Shen, Wentao Lv, Jianhui Qiu, Achhardeep Kaur, Fengjun Xiao, Feng Xia
Summary: Online dating is a thriving business that raises concerns about privacy and trust. In order to maintain the safety of users, detecting malicious users is crucial. This study proposes a trust-aware detection framework based on real dating site data, which improves detection precision and recall rate through a user trust model and a data-balancing method.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Engineering, Civil
Kai Lin, Honglong Chen, Zhe Li, Na Yan, Huansheng Xue, Feng Xia
Summary: In the past decade, IoT technology has made significant advancements in various fields. Intelligent transportation systems (ITS), as a core application of IoT, have gained great attention from researchers. Radio frequency identification (RFID) is an essential technology in IoT and plays a crucial role in identifying tagged vehicles in ITS. However, the existing commercial-off-the-shelf (COTS) RFID tags cannot support the hash function, which poses a challenge for unknown tag identification protocols. To address this issue, we propose two approaches to efficiently identify unknown COTS RFID tags.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
