Article
Computer Science, Information Systems
Fan Hong, Donavan Wei Liang Tay, Alfred Ang
Summary: This paper describes the development of an intelligent object detection and picking system based on MobileNet, which is integrated into a six-axis robotic arm. Experimental results show that the MobileNet model achieves an accuracy of 91%, a significant improvement compared to the original sequential model.
Article
Engineering, Manufacturing
Jingxi He, Yuqiao Cen, Shrouq Alelaumi, Daehan Won
Summary: This research proposes a novel AI-based framework that identifies the optimal placement position to minimize post-reflow misalignment of mini-scale passive components. The framework adapts to different solder paste printing locations and optimizes the model parameters to improve placement accuracy.
IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY
(2022)
Article
Engineering, Industrial
Maaz Saleem Kapadia, Reha Uzsoy, Binil Starly, Donald P. Warsing
Summary: This study focuses on the order acceptance and scheduling problem in an additive manufacturing facility, using genetic algorithms to optimize the process and achieve significant profit improvements. The proposed approach outperforms statistically estimated bounds and provides high-quality solutions that meet all technological constraints.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Computer Science, Information Systems
Firoz Mahmud, Forhad Zaman, Ali Ahrari, Ruhul Sarker, Daryl Essam
Summary: This paper proposes a customized evolutionary algorithm integrated with three heuristics to tackle the resource-constrained project scheduling problem with singular activities. Testing on a wide range of benchmark problems reveals that the proposed approach outperforms existing algorithms.
Article
Computer Science, Hardware & Architecture
Jiawei Lu, Wei Zhao, Haotian Zhu, Jie Li, Zhenbo Cheng, Gang Xiao
Summary: This paper proposes an improved genetic algorithm (I-GA) to solve the virtual machine placement problem in cloud data centers, aiming to improve availability and energy efficiency. By introducing a virtual hierarchy architecture model, the algorithm achieves near-optimal solutions and significantly improves the data center's energy efficiency while maintaining high availability.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Management
Mehrnoosh Shafiee, Javad Ghaderi
Summary: This study investigates the problem of scheduling parallel-task jobs with heterogeneous resource requirements in a cluster of machines. It proposes approximation algorithms under different scenarios and validates the effectiveness of the algorithms through extensive simulation experiments using real traffic trace data.
OPERATIONS RESEARCH
(2022)
Review
Computer Science, Artificial Intelligence
Behice Meltem Kayhan, Gokalp Yildiz
Summary: This study conducted a comprehensive literature review on the application of reinforcement learning to machine scheduling problems. By analyzing the related literature, it identified different problem types, objectives, and constraints, and revealed the deficiencies and promising areas in the research.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Review
Computer Science, Interdisciplinary Applications
G. Umarani Srikanth, R. Geetha
Summary: Cloud computing is a distributed computing framework that provides services such as networks, servers, hardware, and software resources through virtualization and Service Oriented Architecture. Virtualization enables hosting and running multiple applications in the cloud, achieving scalability of resources and applications. However, cloud computing services face challenges in resource management, workload distribution, CPU utilization, job scheduling, security, QoS, and energy efficiency. This paper reviews tasks and resources scheduling in the cloud computing environment, including input parameters, adopted algorithms, deployed technologies, and machine learning approaches.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Nattakorn Promwongsa, Amin Ebrahimzadeh, Roch H. Glitho, Noel Crespi
Summary: This paper investigates the joint VNF placement and scheduling problem for latency-sensitive network services (NSs) and proposes an ILP formulation as well as two efficient heuristics to solve the problem. The simulation results show that the proposed algorithms achieve higher profits compared to existing benchmarks.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Review
Management
Christos Koulamas, George J. Kyparisis
Summary: This article reviews dynamic programming (DP) algorithms used to solve offline deterministic single-machine scheduling problems. The DP algorithms are classified based on problem properties, and insights are provided on how these properties facilitate the use of specific types of DP algorithms. The article proposes generalizations of existing DP algorithms to address more general problems and demonstrates cases where the running time of a DP algorithm can be improved. It also discusses hybrid enumerative algorithms incorporating DP formulations and the conversion of pseudo-polynomial DP algorithms to fully polynomial time approximation schemes. The article concludes with a timeline of DP algorithmic development over the past 50 years.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Article
Chemistry, Multidisciplinary
Pablo Sanabria, Tomas Felipe Tapia, Rodrigo Toro Icarte, Andres Neyem
Summary: This paper proposes using artificial intelligence to distribute jobs in Dew computing environments. It demonstrates that an AI agent, Proximal Policy Optimization (PPO), can learn to distribute jobs better than existing methods in a simulated Dew environment, even with longer job sequences during testing. The results show a performance improvement of up to 77% compared to human-designed heuristics.
APPLIED SCIENCES-BASEL
(2022)
Article
Automation & Control Systems
Levi R. Abreu, Roberto F. Tavares-Neto, Marcelo S. Nagano
Summary: In this paper, a new biased random key genetic algorithm with an iterated greedy local search procedure (BRKGA-IG) is proposed for solving open shop scheduling with routing by capacitated vehicles. The algorithm combines approximation and exact algorithms to achieve high-quality solutions in acceptable computational times. The extensive computational experiments demonstrate that the proposed metaheuristic BRKGA-IG outperforms all other tested methods, showing promise in solving large-sized instances for the new proposed problem.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Interdisciplinary Applications
Miguel Gonsalves de Freitas, Helio Yochihiro Fuchigami
Summary: This study develops a mathematical model for optimizing a single-machine environment with sequence-dependent setup times by using an analogy with the traveling salesman problem. The best formulation is identified among five evaluated formulations. The proposed model is improved by incorporating initial solutions obtained from two heuristics, resulting in lower computational times compared to state-of-the-art models.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Engineering, Multidisciplinary
James C. Chen, Hung-Yu Lee, Wen-Haiung Hsieh, Tzu-Li Chen
Summary: The study addresses the Multi-mode resource-constrained multi-project scheduling problems using a hybrid genetic algorithm and heuristic approach to minimize makespan. The proposed approach outperforms existing methods, especially when problem complexity increases.
JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS
(2022)
Article
Computer Science, Hardware & Architecture
Victor Valls, George Iosifidis, Leandros Tassiulas
Summary: This paper revisits Birkhoff's algorithm and proposes an improved version called Birkhoff+, which is shown through numerical evaluation to outperform previous algorithms in terms of efficiency, running time, and number of switching configurations.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2021)