Article
Computer Science, Interdisciplinary Applications
Xiaohuan Liu, Degan Zhang, Ting Zhang, Jie Zhang, Jiaxu Wang
Summary: The hybrid path planning algorithm in this paper combines optimized reinforcement learning and improved particle swarm optimization to achieve efficient path planning results. By optimizing RL hyperparameters, designing a pre-set operation for PSO, and proposing a correction variable, the algorithm selects the optimal path effectively.
ENGINEERING COMPUTATIONS
(2022)
Article
Computer Science, Interdisciplinary Applications
Youngsu Kim, Kyungho Lee, Byeongwook Nam, Youngsoo Han
Summary: The manual pipe routing of ships depends on the expertise of the individuals involved, making automation and optimization studies necessary. This study presents a methodology that uses curriculum learning to enable a rapid response to frequent pipe-routing modifications.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2023)
Review
Computer Science, Information Systems
Muhammad Morshed Alam, Sangman Moh
Summary: This article provides a comprehensive review of existing QL-based position-aware routing protocols for FANETs. It discusses the relationship between dynamic topology, mobility models, and QL-based routing in FANETs, and extensively reviews the advantages and limitations of the existing protocols. The article also compares the protocols qualitatively in terms of operational features, characteristics, and performance metrics, and discusses important open issues and research challenges.
Article
Computer Science, Information Systems
Sudip Misra, Pallav Kumar Deb, Naimisha Koppala, Anandarup Mukherjee, Shiwen Mao
Summary: S-Nav is a safe navigation system based on Q-learning that recommends safe travel routes in a road network by minimizing passage through COVID-19 hotspots. The system ensures minimal passage through these zones and reduces the risk of exposure to the virus for commuters.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Automation & Control Systems
Vivek S. Borkar, Alexandre Reiffers-Masson
Summary: In this article, a variant of the classical DeGroot model of opinion propagation with random interactions is considered. The study focuses on a situation where a certain subset of agents can be controlled by a control parameter. The problem is mapped to a shortest path problem and analyzed using a nonclassical policy gradient scheme. The article also discusses the case when only certain interactions between agents are observed.
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS
(2022)
Article
Computer Science, Information Systems
Omer Amar, Ilana Sarfati, Kobi Cohen
Summary: This study investigates the problem of adaptive routing in wireless communication networks using online learning. It aims to develop an algorithm to learn optimal paths for data transmission, maximizing network throughput without complete knowledge of link states. The proposed algorithm, OLSB, is designed based on a novel learning strategy and achieves efficient adaptive path selection. Theoretical analysis and extensive numerical simulations demonstrate its high efficiency and performance.
Article
Computer Science, Artificial Intelligence
Tomas Kulvicius, Minija Tamosiunaite, Florentin Worgotter
Summary: This paper presents a method for solving path-finding problems by transforming cost values into synaptic weights in a neural network. The method allows for online weight adaptation using network learning mechanisms, and has been demonstrated to be effective in navigating in environments with obstacles and following specific sequences of path nodes.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Telecommunications
Sipra Swain, Pabitra Mohan Khilar, Biswa Ranjan Senapati
Summary: Unmanned Aerial Vehicles (UAVs) with visual sensors are widely used for various applications such as area mapping and crop management. This paper proposes a cluster-based routing approach with a dynamic planning algorithm to tackle changing environmental situations. The approach includes modules for path planning, network topology construction, cluster management, and data routing, and achieves better performance compared to existing methods.
VEHICULAR COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Rezoan Ahmed Nazib, Sangman Moh
Summary: Vehicular-ad hoc networks (VANETs) are important, and reinforcement learning (RL) algorithms can improve the efficiency of VANET routing.
Article
Management
Michael S. Hughes, Brian J. Lunday, Jeffrey D. Weir, Kenneth M. Hopkinson
Summary: This research introduces the MSPP-PD model to balance agent routing efficiency with group vulnerability. It examines the distinguishability of different MSPP-PD variants in optimal agent routing solutions and the impact of penalty function metrics on identifying these solutions.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Computer Science, Theory & Methods
Jiayu Liu, Huaxi Gu, Wenting Wei, Ziqi Chen, Yawen Chen
Summary: Reconfigurable units like FPGAs are widely used as high-performance hardware accelerators to address power bottleneck in current multi-core processors. This study introduces a new routing algorithm called the Shortest Cycle Routing Algorithm to improve the computation efficiency of standard BFS for inter-accelerator communications. The algorithm reduces the time and space complexities for searching the shortest cycles of an acceleration task from O(n(k)) to O(1), highlighting the benefits of locality and path diversity for adaptive routing strategies.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Transportation Science & Technology
Mohsen Dastpak, Fausto Errico, Ola Jabali, Federico Malucelli
Summary: This article discusses the problem of an Electric Vehicle (EV) finding the shortest route from an origin to a destination and proposes a problem model that considers the occupancy indicator information of charging stations. A Markov Decision Process formulation is presented to optimize the EV routing and charging policy. A reoptimization algorithm is developed to establish the sequence of charging station visits and charging amounts based on system updates. Results from a comprehensive computational study show that the proposed method significantly reduces waiting times and total trip duration.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Computer Science, Interdisciplinary Applications
Changyong Zhang
Summary: This paper focuses on the necessity and importance of solving the unique shortest path routing problem using a complete formulation. It investigates the problem characteristics including objective functions, constraints, and solution qualities. Furthermore, it compares the routing performance achieved by solving the unique shortest path routing problem with that obtained from two default methods and two relaxed problems. The study shows that solving the problem using a complete formulation and an exact algorithm greatly improves the routing performance and approaches the lower bounds competitively.
COMPUTERS & INDUSTRIAL ENGINEERING
(2023)
Article
Computer Science, Information Systems
Shengyu Zhang, Kwan L. Yeung
Summary: This paper proposes a scalable two-layer routing architecture to address the dynamic nature of low-Earth orbit satellite constellations (LEO-SCs). Two stable routing algorithms are designed to minimize route changes.
COMPUTER COMMUNICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira, Flavio de Oliveira Silva
Summary: The Internet is crucial for global applications and businesses, but security is a major challenge. The Darknet, a parallel network within the Internet, requires real-time classification due to malicious activities. Our paper proposes a novel approach using CNN and RL techniques for intelligent and adaptive packet sampling rates in high-performance networks. With a TOR traffic prediction accuracy of 99.84%, our method shows successful classification in high-throughput networks.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Yulin Shao, Qi Cao, Soung Chang Liew, He Chen
Summary: This paper investigates the minimum-age scheduling problem in wireless sensor networks and proposes a greedy policy to minimize the expected age-of-information. By introducing a relaxed greedy policy and formulating the sampling process of each arm as a partially observable Markov decision process, the paper validates that the relaxed greedy policy is an effective approximation to the greedy policy in terms of expected age-of-information.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Jiaxin Liang, He Chen, Soung Chang Liew
Summary: This article investigates the suitability of SDR-based wireless systems for industrial IoT applications. Through a quantitative investigation of synchronization accuracy and end-to-end latency, the experiments show that SDR can be applied to IIoT applications that require tight synchrony and moderately low latency to a certain extent.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Hardware & Architecture
Lihao Zhang, Taotao Wang, Soung Chang Liew
Summary: This paper designs and validates new block propagation protocols for the Bitcoin blockchain's P2P network, aiming to increase TPS without changing the consensus protocol. The improvements in compact-block relaying and the use of rateless erasure codes show that TPS can be increased by 100x without compromising security and consensus-building.
Article
Engineering, Electrical & Electronic
Yulin Shao, Deniz Gunduz, Soung Chang Liew
Summary: This paper investigates the problem of misaligned over-the-air computation for federated edge learning and proposes a whitened matched filtering and sampling scheme to obtain oversampled, independent samples from misaligned signals, with two main estimators designed to estimate the arithmetic sum of transmitted symbols. Simulation results show different impacts on test accuracy between the aligned-sample estimator and the ML estimator under various EsN0 scenarios.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Gongpu Chen, Soung Chang Liew, Yulin Shao
Summary: This paper proposes using the uncertainty of information, measured by Shannon's entropy, as a metric for information freshness. The system considered in the paper involves a central monitor observing multiple binary Markov processes through multiple communication channels.
IEEE TRANSACTIONS ON INFORMATION THEORY
(2022)
Article
Computer Science, Information Systems
Shakeel Salamat Ullah, Soung Chang Liew, Gianluigi Liva, Taotao Wang
Summary: This paper presents the implementation and experimental evaluation of a short-packet physical-layer network coding (PNC) system. Implementation of short-packet PNC systems is challenging due to the limited number of pilot symbols and stringent delay requirements. The paper proposes a low-complexity and low-overhead design to address these issues and applies it successfully in short-packet communications.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Yulin Shao, Deniz Gunduz, Soung Chang Liew
Summary: Over-the-air computation (OAC) is an important component of future wireless networks, enabling efficient function computation in multiple-access edge computing. Traditional OAC using maximum likelihood (ML) estimation is susceptible to noise and error propagation. To address this, a Bayesian approach is proposed in this paper, where each edge device transmits statistical information to the fusion center for misalignment handling. Numerical and simulation results show the superior performance of the proposed Bayesian estimators in different scenarios.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Guangyu Zhu, Caili Guo, Tiankui Zhang, Yulin Shao
Summary: This paper focuses on a cache-enable device-to-device (D2D) communication network with user mobility and proposes a mobility-aware coded caching scheme to reduce network traffic. By assigning dynamic cache memory to mobile users, content exchange is enabled via relaying even among users who never meet. The use of network coding effectively reduces network traffic and improves decoding efficiency. The numerical results demonstrate the superiority of the proposed algorithm compared to random and greedy algorithms and the standard Ford-Fulkerson algorithm in terms of broadcasting data and successful decoding ratio.
PHYSICAL COMMUNICATION
(2023)
Article
Computer Science, Information Systems
Lihao Zhang, Soung Chang Liew
Summary: This article introduces a multistream networking paradigm called soft-source-information-combining (SSIC) for wireless IoT applications with high reliability requirements. The SSIC networking involves the dispatching of packet duplicates over multiple streams established on different wireless networks to enhance reliability. The challenges addressed in this article include descrambling the soft information from different streams and developing an SSIC framework compatible with current TCP/IP networks. The experiments conducted on a Wi-Fi testbed demonstrate the effectiveness of SSIC in decreasing packet delivery failure rate and achieving 99.99% reliable packet delivery for short-range communication.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Lihao Zhang, Soung Chang Liew, He Chen
Summary: This article introduces a networking paradigm called just-in-time (JIT) communication, which supports client-server applications with strict request-response latency requirements. The JIT framework has two main features: pulling requests from clients just before transmission opportunities and ensuring the server has a transmission opportunity right after processing a request. The study demonstrates that a TDMA network with a power-of-2 time slots per superframe is optimal for implementing JIT functions on the server side. Experimental results confirm that JIT networks can significantly reduce request-response latency compared to networks without JIT support.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Yulin Shao, Deniz Gunduz
Summary: Recent progress in DeepJSCC, a deep learning-based joint source-channel coding, has introduced a new paradigm of semantic communications. It leverages semantic-aware features directly from the source signal and utilizes discrete-time analog transmission. Compared to traditional digital communications, DeepJSCC-based semantic communications offer superior receiver reconstruction performance, graceful degradation with diminishing channel quality, but also exhibit a large peak-to-average power ratio (PAPR) in the transmitted signal. This letter explores PAPR reduction techniques to retain DeepJSCC's superior image reconstruction performance while suppressing PAPR to an acceptable level, paving the way for practical implementation of DeepJSCC in semantic communication systems.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Gongpu Chen, Lihao Zhang, Soung-Chang Liew
Summary: This paper investigates the stochastic properties of stressed periods in IoT systems using random access protocols for wireless communication. A fluid flow model is used to approximate the evolution of buffer occupancy at the transmitting node, and a relationship between buffer occupancy and delay is derived. Stressed periods are formally defined as time intervals where the buffer occupancy exceeds a certain threshold, and the probability distributions of stressed period duration and delay are obtained. Real network experiments validate the accuracy of the proposed model and its applicability in analyzing the worst-case performance of IoT systems.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Yulin Shao, Soung Chang Liew, Deniz Gunduz
Summary: This article investigates a fundamental problem of NoisyNNs, which is how to reconstruct the DNN weights from noise. A denoising approach is proposed to maximize the inference accuracy of the reconstructed models. Experimental results demonstrate that our denoiser outperforms the maximum likelihood estimation in small-scale problems and shows significantly better performance when applied to advanced learning tasks with modern DNN architectures.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2023)