Article
Computer Science, Information Systems
Ismail M. M. Ali, Karam M. M. Sallam, Nour Moustafa, Ripon Chakraborty, Michael Ryan, Kim-Kwang Raymond Choo
Summary: This article proposes a multi-objective task-scheduling optimization problem in a fog-cloud environment to minimize both makespans and total costs. An optimization model based on DNSGA-II is suggested to automatically allocate tasks to fog or cloud nodes, and discretize evolutionary operators for better task scheduling.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2022)
Article
Engineering, Electrical & Electronic
Hsien-Wen Deng, Mizanur Rahman, Mashrur Chowdhury, M. Sabbir Salek, Mitch Shue
Summary: This article explores the feasibility of using commercial cloud services for connected vehicle applications in a transportation cyberphysical systems environment. Through implementing a CV mobility application, it is demonstrated that a cloud-based TCPS environment can meet the requirements of CV applications and the potential of commercial cloud services to rapidly scale infrastructure to meet demand.
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE
(2021)
Article
Computer Science, Artificial Intelligence
Xiaoyong Tang, Cheng Shi, Tan Deng, Zhiqiang Wu, Li Yang
Summary: The study introduces a random matrix particle swarm optimization scheduling algorithm for cloud service scheduling, as well as two parallel algorithms to reduce its time complexity. Experimental results demonstrate that the GPU-accelerated algorithm performs better compared to the others.
APPLIED SOFT COMPUTING
(2021)
Article
Management
Cheng Chen, Emrah Demir, Yuan Huang
Summary: This paper investigates the routing and scheduling of autonomous delivery robots in urban logistics, proposing an algorithm to solve the VRPTWDR and demonstrating its performance and effectiveness. The research shows that self-driving parcel delivery robots can be a new alternative for last mile service.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Computer Science, Information Systems
Abdallah Moubayed, Abdallah Shami, Parisa Heidari, Adel Larabi, Richard Brunner
Summary: Vehicle-to-everything (V2X) communication and services are gaining interest for intelligent transportation systems. Multi-access/mobile edge computing is proposed as a potential solution, but it introduces challenges such as where to place V2X services given limited computational resources. This study formulates the optimal V2X service placement problem and develops a low-complexity heuristic algorithm to solve it, showing successful maintenance of QoS requirements for different V2X services with close to optimal performance.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Sara Alipour, Hamid Saadatfar, Mahdi Khazaie Poor
Summary: Cloud computing is a modern architecture for complex processes, and the rise of mobile cloud computing has led to a rapid increase in mobile data. However, the limitations of mobile devices make it difficult to process tasks for mobile users. To address this issue, a multi-objective parallel imperialist competitive algorithm is proposed to reduce execution time, processing time, energy consumption, and improve load balance.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Automation & Control Systems
Yi Xie, Yuhan Sheng, Moqi Qiu, Fengxian Gui
Summary: With the increasing data and computing requirements, the transition of scientific and business applications to cloud platforms has led to the importance of cloud workflow scheduling. Existing heuristic and metaheuristic algorithms have limitations in solving this NP-hard problem. To address this, a novel adaptive decoding biased random key genetic algorithm is proposed, which improves the search efficiency and accuracy for cloud workflow scheduling.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Yanfei Zhu, Kwang Y. Lee, Yonghua Wang
Summary: This paper explores the use of elitist genetic algorithm for electric vehicle routing problem with time window, introducing an improved neighbor routing initialization method. It enhances convergence speed by adjusting adaptive crossover and mutation probabilities. Experimental studies demonstrate the algorithm's effectiveness in both random and benchmark cases.
Article
Engineering, Civil
Jiawei Geng, Jing Cao, Haipeng Jia, Zongwei Zhu, Hai Fang, Chengxi Gao, Cheng Ji, Gangyong Jia, Guangjie Han, Xuehai Zhou
Summary: This paper introduces a distributed training framework called Heter-Train, which addresses the issue of parallel training on heterogeneous cloud-edge-vehicle clusters in intelligent transportation systems. The framework includes a communication-efficient semi-asynchronous parallel mechanism and a solution for heterogeneous communication. Experimental results demonstrate significant speedups on training time without sacrificing accuracy.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Environmental Sciences
Anh Vu Vo, Debra E. Laefer, Jonathan Byrne
Summary: This paper introduces an approach utilizing genetic algorithm and beam tracing algorithm to optimize urban aerial laser scanning tasks. The method aims to maximize vertical data capture through a low-density point cloud representation of the urban scene, and achieves fast and scalable results with a dual parallel computing framework and two layers of parallelization.
Article
Automation & Control Systems
Jianqiang Li, Junchuang Cai, Tao Sun, Qingling Zhu, Qiuzhen Lin
Summary: In this paper, a multitask-based evolutionary algorithm (MBEA) with knowledge transfer is proposed to solve the vehicle routing problem with simultaneous pickup-delivery and time windows (VRPSPDTW) in autonomous transportation. The algorithm tackles large-scale VRPSPDTW instances by utilizing multiple auxiliary tasks, facilitating the evolutionary search process. Experimental results demonstrate the effectiveness of the proposed algorithm in dealing with practical VRPSPDTW problems.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Brenner Humberto Ojeda Rios, Eduardo C. Xavier, Flavio K. Miyazawa, Pedro Amorim, Eduardo Curcio, Maria Joao Santos
Summary: Technological advances have led to a significant growth in the number of articles related to dynamic vehicle routing problems (DVRPs) over the past seven years, with 65% focusing on dynamic and stochastic problems and 35% on dynamic and deterministic problems. In terms of applications, 40% of the articles are related to goods transportation, 17.5% to services, 17.5% to transport of people, and 25% to generic applications. Heuristics and metaheuristics are the prominent solution methods, with applications expanding into new concepts of logistical operations.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Engineering, Multidisciplinary
S. Velliangiri, P. Karthikeyan, V. M. Arul Xavier, D. Baswaraj
Summary: Cloud computing is a highly scalable on-demand Internet-based computing service used by various working and non-working classes globally. Task scheduling, a critical application for end-users and cloud service providers, faces challenges in finding optimal resources. The Hybrid Electro Search with a genetic algorithm (HESGA) proposed in this paper combines the advantages of genetic and electro search algorithms, outperforming existing scheduling algorithms.
AIN SHAMS ENGINEERING JOURNAL
(2021)
Article
Management
Xiao Yu, Huimin Miao, Armagan Bayram, Meigui Yu, Xi Chen
Summary: Multimodal transportation systems combine various environmentally friendly transportation modes to meet customer needs, improve transportation efficiency, and save costs. By studying the combination of ride-sharing and public transportation services, it is found that multimodal transportation systems can significantly benefit travel distances and times.
INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH
(2021)
Article
Mathematics
Horatiu Florian, Camelia Avram, Mihai Pop, Dan Radu, Adina Astilean
Summary: In recent years, the adverse effects of traffic congestion have received special attention, and bike-sharing systems have been considered as viable solutions to these problems. However, even if the quality of bike-sharing service systems is improved, there are still challenges in terms of effective rebalancing operations. A two-step method is proposed to address these challenges, utilizing a fuzzy logic-controlled genetic algorithm for bike station prioritization and an inference mechanism for station-truck assignment. The proposed method shows superior performance compared to other algorithms and is applicable to any potential bike-sharing system.
Article
Computer Science, Artificial Intelligence
Sudarshan Nandy, Mainak Adhikari, Venki Balasubramanian, Varun G. Menon, Xingwang Li, Muhammad Zakarya
Summary: This paper proposes an intelligent healthcare framework based on the Swarm- Artificial Neural Network (Swarm-ANN) strategy for predicting cardiovascular disease. The strategy trains and evaluates a predefined number of neural networks using random generation and adjusts neuron weights through weight changes and a newly designed heuristic formulation. The results demonstrate that the proposed strategy outperforms standard learning techniques in terms of cardiovascular disease prediction accuracy.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Engineering, Civil
Monagi H. Alkinani, Abdulwahab Ali Almazroi, Mainak Adhikari, Varun G. Menon
Summary: Recent advancements in computation and communication technologies, as well as the increasing adoption of IoT and AI technologies, have led to significant developments in modern transportation systems. Processing data at the edge of the network is a potential solution to efficiently handle large amount of sensory data, meeting the real-time monitoring requirements of public traffic management systems.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Prabhat Kumar, Randhir Kumar, Govind P. Gupta, Rakesh Tripathi, Alireza Jolfaei, A. K. M. Najmul Islam
Summary: This article presents a method for secure data transmission in IoT-enabled healthcare system using blockchain and deep learning. It ensures data integrity and secure transmission through a novel scalable blockchain architecture with Zero Knowledge Proof mechanism, and addresses storage cost and security issues by integrating off-chain storage and smart contracts. Experimental results demonstrate that the proposed method outperforms existing techniques in both non-blockchain and blockchain settings, achieving accuracy close to 99%.
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
(2023)
Article
Computer Science, Information Systems
S. Asha, P. Vinod, Varun G. Menon
Summary: Advancements in artificial intelligence have resulted in an increase in digital forensics and the development of various image manipulation and processing tools. This paper proposes a new defensive framework that effectively identifies deepfakes by utilizing temporal and spatially aware features. The framework involves training a self-attenuated VGG16 neural model using facial landmarks in videos to obtain spatial attributes and generating optical flow feature vectors to extract temporal characteristics. The system achieves a detection accuracy of 98.4% and shows robustness under adversarial settings. It also demonstrates cross-dataset generalization capacity.
INTERNATIONAL JOURNAL OF INFORMATION SECURITY
(2023)
Article
Computer Science, Artificial Intelligence
Yinan Shao, Jerry Chun-Wei Lin, Gautam Srivastava, Dongdong Guo, Hongchun Zhang, Hu Yi, Alireza Jolfaei
Summary: This article introduces a method for optimizing deep reinforcement learning models using neural evolutionary algorithms to solve combinatorial optimization problems. The proposed end-to-end multi-objective neural evolutionary algorithm demonstrates competitive and robust performance on the classic travel salesman problem and knapsack problem, and also performs well in inference time.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Green & Sustainable Science & Technology
Yuping Zhang, Youyang Qu, Longxiang Gao, Tom Hao Luan, Alireza Jolfaei, James Xi Zheng
Summary: This paper proposes a differentially private smart community model with game theory-based personalized privacy protection (GPDP) and a modified reinforcement learning algorithm. The model optimizes the trade-off between personalized privacy protection and data utility, improving data analytics and decision-making performances for energy management in smart cities.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2023)
Article
Computer Science, Hardware & Architecture
Ahamed Aljuhani, Prabhat Kumar, A. K. M. Najmul Islam, Randhir Kumar, Alireza Jolfaei
Summary: The Internet of Things (IoT) technology is considered the foundation for next-generation smart villages, enabling real-time data analytics and automated decision-making in various aspects. However, IoT devices face security and privacy issues on public networks, and data congestion when communicating with cloud servers. To address these challenges, the integration of distributed fog computing (DFC) with IoT can provide efficient and secure services in smart villages. This article explores the integration, design and evaluation of an intrusion detection system in a DFC-based smart village environment, and discusses open security issues and challenges.
IEEE CONSUMER ELECTRONICS MAGAZINE
(2023)
Article
Engineering, Multidisciplinary
Kai Peng, Hualong Huang, Bohai Zhao, Alireza Jolfaei, Xiaolong Xu, Muhammad Bilal
Summary: This paper proposes an end-edge-cloud collaborative intelligent optimization method to address the challenges of computation offloading and resource allocation in IIoT scenarios. Comprehensive experiments and evaluations demonstrate the effectiveness and efficiency of the proposed method in terms of energy consumption, time consumption, resource utilization, and load balancing.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Zhangyi Shen, Feng Ding, Alireza Jolfaei, Kusum Yadav, Sahil Vashisht, Keping Yu
Summary: This paper investigates the issue of checkerboard artifacts in GAN-generated medical images and proposes a method to avoid the production of such artifacts. The method preserves the integrity of medical images and demonstrates the feasibility of detecting GAN-generated images by tracing the checkerboard artifacts.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Lili Yan, Jingyi Cui, Jian Liu, Guangquan Xu, Lidong Han, Alireza Jolfaei, Xi Zheng
Summary: This study investigates the Boolean functions that satisfy secure properties in the FLIP stream cipher. However, finding Boolean functions with optimal cryptographic properties remains an unsolved problem in the cryptographic community. This paper proposes an Improved Genetic Algorithm (IGA) to find weightwise balanced Boolean functions and obtains a large number of weightwise perfectly balanced functions with good nonlinearity profiles. The comparison of our constructions with relevant works demonstrates the significant advantage of IGA in achieving high weightwise nonlinearity functions.
PROCEEDINGS OF THE 2023 ACM ASIA CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, ASIA CCS 2023
(2023)
Article
Telecommunications
Mojtaba Alizadeh, Mohammad Hesam Tadayon, Alireza Jolfaei
Summary: The growing number of interconnected devices and services on the Internet of Things (IoT) necessitates secure processing and transmission of sensory data. Existing literature on authentication in IoT has not addressed the need for a scalable and efficient method. This paper proposes a secure and anonymous ticket-based authentication method that offers protection against security and privacy threats, as well as mutual authentication and sensor anonymity. Security and performance evaluations confirm its effectiveness.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Randhir Kumar, Prabhat Kumar, Alireza Jolfaei, A. K. M. Najmul Islam
Summary: Business Intelligence (BI) is the process of strategically planning and utilizing various tools and techniques to gain valuable data insights and make informed business decisions. The Internet of Things (IoT) has become the primary source of real-time big data used across all industries. However, integrating IoT as data sources with traditional BI systems has hindered the expansion of business outcomes due to increased security and privacy concerns in IoT ecosystems. This study proposes an integrated architecture for enhancing security and privacy in IoT-based BI applications, consisting of an intrusion detection engine and a two-level privacy engine.
2023 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS, ICCE
(2023)
Article
Engineering, Civil
Wentao Liu, Xiaolong Xu, Lianxiang Wu, Lianyong Qi, Alireza Jolfaei, Weiping Ding, Mohammad R. Khosravi
Summary: This paper proposes a CNN-MLP based intrusion detection model named FedBatch for IoT-based MTS, which is trained through Federated Learning to protect the privacy of local data. The characteristics of communication between vessels are discussed, and a lightweight local model is designed to save computing and storage overhead. An adaptive aggregation method called Batch Federated Aggregation is also proposed to mitigate the straggler problem. The simulation results on NSL-KDD dataset demonstrate the effectiveness and efficiency of FedBatch.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Mohammad R. Khosravi, Khosro Rezaee, Mohammad Kazem Moghimi, Shaohua Wan, Varun G. Menon
Summary: Unmanned aerial vehicles equipped with video surveillance can monitor crowd behavior and maintain public safety in metropolitan environments. By using fuzzy logic and deep transfer learning, accurate predictions of crowd conditions can be made, enabling the selection of optimal paths and improving citywide traffic flow and decision-making.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Ambigavathi Munusamy, Mainak Adhikari, Mohammad Ayoub Khan, Varun G. Menon, Satish Narayana Srirama, Linss T. Alex, Mohammad R. Khosravi
Summary: This paper presents a blockchain-enabled edge-centric framework for real-time data analysis in maritime transportation systems, addressing security and privacy issues. By introducing blockchain and smart contracts, the transactions of each block can be validated, and different classification models can be used to predict malicious vessels.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)