Article
Computer Science, Hardware & Architecture
Shao Deng, Shanzhu Xiao, Qiuqun Deng, Huanzhang Lu
Summary: This paper presents a novel hardware/software partitioning algorithm based on node resource attributes. The algorithm initializes the system task graph and improves the partitioning performance through learning strategy enhancements. Experimental results show that the proposed algorithm achieves high partitioning performance and solution stability in large-scale systems task graph partitioning.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Xinliang Tian, Dantong Ouyang, Huisi Zhou, Luyu Jiang, Liming Zhang
Summary: Hardware and software partitioning is a crucial step in the co-design of embedded systems, and an efficient heuristic algorithm named HSLS is proposed in this research, which treats the problem as a minimum weight dominating set problem. The experimental results demonstrate that the HSLS algorithm outperforms four comparison algorithms in terms of optimal solution.
ELECTRONICS LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Joaquin A. Pacheco, Silvia Casado
Summary: This article presents a resolution method that combines multistart strategies with tabu search for solving the clique partitioning problem. The method allows exploration of unfeasible solutions, which is a novel characteristic. Computational tests show that our method outperforms previous methods in terms of both solution quality and computation time.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Hardware & Architecture
Fabian Kress, Vladimir Sidorenko, Patrick Schmidt, Julian Hoefer, Tim Hotfilter, Iris Walter, Tanja Harbaum, Jurgen Becker
Summary: Deep neural networks, especially convolutional neural networks (CNNs), play a crucial role in applications like autonomous driving and assistive robotics. However, deploying these complex networks in distributed embedded systems presents new challenges, such as performance and energy constraints on the sensor nodes. To overcome these challenges, an open-source framework called CNNParted is introduced to efficiently partition CNN inference between sensor nodes and a central edge node, considering both the CNN architecture and hardware components.
Article
Computer Science, Information Systems
Aurelien Bloch, Simone Casale-Brunet, Marco Mattavelli
Summary: Dataflow programming is a methodology for developing high-level, parametric programs that are independent of the underlying platform. It eliminates the need for rewriting application software for each configuration, making it useful for heterogeneous platforms. This paper presents a novel methodology for partitioning and mapping dataflow programs onto heterogeneous systems composed of both CPUs and GPUs, aiming to find the most efficient way to process a dataflow program.
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Hehao Niu, Zhi Lin, Kang An, Jiangzhou Wang, Gan Zheng, Naofal Al-Dhahir, Kai-Kit Wong
Summary: In this paper, a novel integration of rate-splitting multiple access (RSMA) and reconfigurable intelligent surface (RIS) is investigated for future networks to achieve a balance between spectral efficiency (SE) and energy efficiency (EE). Reflection elements with active load are used to improve resource efficiency (RE). The optimization problem is solved using a two-stage framework with a quadratic transformation and an alternating optimization algorithm with the penalty dual decomposition (PDD) method.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Myeonggyun Han, Woongki Baek
Summary: Workload consolidation is a crucial technique for improving resource utilization in service computing systems, but security issues are a concern. SDRP is a new resource partitioning method that ensures efficiency, security, and the integrity of LC workload SLO.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2022)
Article
Computer Science, Hardware & Architecture
Yuhong Song, Edwin Hsing-Mean Sha, Qingfeng Zhuge, Rui Xu, Xiaowei Xu, Bingzhe Li, Lei Yang
Summary: With the progress of AI democratization, there is potential to deploy DNNs to tiny devices, like ICDs. SC, though sacrificing model accuracy, significantly reduces power consumption. However, previous works have focused solely on either hardware circuit design or SW->HW workflow, leading to unilateral optimization. Therefore, we propose SC-NAS, the first framework that combines SC with NAS for HW/SW co-optimization, achieving low-power consumption and high accuracy.
JOURNAL OF SYSTEMS ARCHITECTURE
(2023)
Article
Computer Science, Software Engineering
Neelofar Neelofar, Kate Smith-Miles, Mario Andres Munoz, Aldeida Aleti
Summary: Search-based software testing (SBST) is a mature area with techniques developed to tackle the challenging task of software testing. SBST techniques have been successfully applied in the industry to generate test cases for large and complex software systems. However, their effectiveness depends on the problem being addressed. This paper revisits the evaluation of SBST techniques using Instance Space Analysis (ISA) to visualize and assess their strengths and weaknesses across a broad range of problem instances from common benchmark datasets. The paper also examines the diversity and quality of benchmark datasets used in experimental evaluations.
IEEE TRANSACTIONS ON SOFTWARE ENGINEERING
(2023)
Article
Management
Yukang He, Tao Jia, Weibo Zheng
Summary: This paper investigates a resource-constrained multiproject scheduling problem with stochastic activity duration. An optimisation model and a tabu search algorithm with improvement measures are proposed to minimize the maximal cash flow gap. Computational experiments are conducted to evaluate the algorithm's performance and analyze the effects of key parameters on the objective function value.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Article
Ecology
Alex Salas-Lopez, Cyrille Violle, Francois Munoz, Florian Menzel, Jerome Orivel
Summary: This study investigated the resource-based ant community structure in a tropical ecosystem. The findings suggest that competition for resources and habitat filtering have significant effects on the composition of local ant assemblages, with niche partitioning and niche filtering playing important roles.
FRONTIERS IN ECOLOGY AND EVOLUTION
(2022)
Article
Computer Science, Theory & Methods
Krishna Teja Chitty-Venkata, Arun K. Somani
Summary: In this article, we address the issue of automating the hardware-aware architectural design process of Deep Neural Networks (DNNs). The advancements in Convolutional Neural Network (CNN) algorithm design have had a significant impact in fields such as computer vision, virtual reality, and autonomous driving. However, the end-to-end design process of a CNN is a complex and time-consuming task that requires expertise in various areas. The HW-NAS approach automates the architectural design process of DNNs to improve efficiency and achieve acceptable accuracy-performance tradeoffs, considering different hardware platforms.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Artificial Intelligence
Xin Jin, Hu Qin, Chun Cheng
Summary: Motivated by practical air cargo logistics activities of a Chinese multinational manufacturer, this paper investigates an air cargo partitioning problem with a piecewise linear cost function. The problem involves choosing the higher value between the actual weight and the volumetric weight as the chargeable weight, and using a piecewise linear cost function to compute the variable transportation cost. The ACPP-PLC is formulated as a mixed-integer linear programming model, and a tailored adaptive large neighborhood search algorithm is proposed to generate high-quality solutions in a shorter time than the CPLEX solver.
Article
Computer Science, Information Systems
Marieme Diallo, Alejandro Quintero, Samuel Pierre
Summary: This paper addresses the Virtual Network Embedding (VNE) problem in cloud computing, focusing on the splitting phase by proposing an Integer Linear Program strategy to improve performance and QoS while minimizing resource provisioning expenditures. By utilizing a hybrid metaheuristic approach based on Ant Colony Optimization and Tabu Search, the proposed method efficiently finds feasible solutions with costs close to the exact solution in a highly reduced computing time.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2021)
Article
Engineering, Civil
Tingting Yang, Lingzheng Kong, Nan Zhao, Ruijin Sun
Summary: This study presents a joint sleeping scheduling and opportunistic transmission scheme in delay-tolerant maritime wireless communication networks based on software defined networking, aiming to find a better tradeoff between energy consumption and delay. Mathematical analyses and simulation results show the effectiveness of the proposed allocation scheme for maritime communication networks.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Hardware & Architecture
Yi Zhou, Fazhi He, Yimin Qiu
JOURNAL OF SUPERCOMPUTING
(2016)
Article
Computer Science, Information Systems
Yi Zhou, Fazhi He, Yimin Qiu
SCIENCE CHINA-INFORMATION SCIENCES
(2017)
Article
Computer Science, Theory & Methods
Yi Zhou, Fazhi He, Neng Hou, Yimin Qiu
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2018)
Article
Engineering, Electrical & Electronic
Yi Zhou, Fazhi He, Yimin Qiu
JOURNAL OF ELECTRONIC IMAGING
(2018)
Article
Computer Science, Information Systems
Neng Hou, Fazhi He, Yi Zhou, Yilin Chen, Xiaohu Yan
Article
Biochemistry & Molecular Biology
Qi Zhou, Yi Zhou, Fred A. Kummerow
PROSTAGLANDINS & OTHER LIPID MEDIATORS
(2009)
Article
Computer Science, Information Systems
Neng Hou, Fazhi He, Yi Zhou, Yilin Chen
FRONTIERS OF COMPUTER SCIENCE
(2020)
Article
Automation & Control Systems
Xiaomao Wang, Li Chai, Yi Zhou, Feng Dan
Summary: A cooptimization method based on software defined networking technology is proposed to enhance the performance of task scheduling and network communication in large and complex engineering systems. Simulation results show the proposed scheme outperforms the traditional method in terms of task acceptance rate, average end-to-end delay, and network load balance degree.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Yi Zhou, Weidong Li, Xiaomao Wang, Yimin Qiu, Weiming Shen
Summary: In this paper, a new type of ant colony optimization algorithm called ADACO is proposed with an innovative adaptive learning mechanism. The algorithm is validated through experiments on the traveling salesman problem (TSP) and the capacitated vehicle routing problem (CVRP), and it shows competitive performance in terms of accuracy, stability, and adaptability.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Proceedings Paper
Automation & Control Systems
Qiu Yi-min, Chen Shi-hong, Zhou Yi, Liu Xin-hai
SENSORS, MECHATRONICS AND AUTOMATION
(2014)
Proceedings Paper
Engineering, Mechanical
Yimin Qiu, Shihong Chan, Yi Zhou, Ying Wang
MEASUREMENT TECHNOLOGY AND ENGINEERING RESEARCHES IN INDUSTRY, PTS 1-3
(2013)