Article
Computer Science, Artificial Intelligence
Dacheng He, Dafang Zhang, Yanbiao Li, Wei Liang, Meng-Yen Hsieh
Summary: Named Data Networking (NDN) is a novel Internet architecture focused on data contents, which has been proven to be valuable in supporting popular topics like Internet of Things, Edge computing, Blockchain. This paper proposes a fast name lookup algorithm for NDN interest forwarding, which accelerates NDN forwarding processes and effectively prevents DoS attacks.
CONNECTION SCIENCE
(2021)
Article
Computer Science, Hardware & Architecture
Sanchita Saha Ray, Surajeet Ghosh, Bhaskar Sardar
Summary: A novel hardware architecture based on hash functions is proposed for longest prefix match (LPM) scheme in IP processing. The architecture achieves zero false positive rate and negligible false negative rate by implementing efficient hash functions and optimizing memory design. The performance of the architecture has been tested under different prefix growth trends and the results demonstrate its sustainability.
IEEE TRANSACTIONS ON COMPUTERS
(2022)
Article
Computer Science, Hardware & Architecture
Yen-Heng Lin, Sun-Yuan Hsieh
Summary: This study reviewed and experimentally evaluated trie-based methods for reducing memory access, memory consumption, and IP lookup time. The results showed that time-reducing technologies worked well for IPv4, while memory-reducing technologies worked well for IPv6. Various combinations of these technologies were applied in the experiments.
JOURNAL OF COMPUTER AND SYSTEM SCIENCES
(2023)
Article
Computer Science, Information Systems
Chunyang Zhang, Gaogang Xie
Summary: The study introduces the XorOffsetTrie method, which combines XorFilter and OffsetTrie to reduce memory accesses and improve IPv6 lookup speed. By combining XorFilter and OffsetTrie, it achieves a more efficient data structure and faster lookup speed.
COMPUTER COMMUNICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Wanming Luo, Shihao Liu, Yihao Jia, Zhe Chen, Sheng Jiang
Summary: The conventional IP address lacks extensibility due to its fixed length, while FlexIP offers variable length IP addresses to adapt to different network scenarios. The Bloom filter-based addressing scheme shows promise in efficiently handling variable length addresses, with the proposed OBF-based scheme achieving constant IP lookup time and insensitivity to address length. Simulation results indicate that the proposed addressing scheme is more suitable for FlexIP addressing than well-known schemes.
Article
Computer Science, Information Systems
Yi Zhang, Lufeng Qiao, Huali Wang
Summary: This paper proposes a new hardware-based IP route lookup architecture called PR-Trie, which supports both IPv4 and IPv6 addresses. It achieves fast longest-prefix-matching using Multibit-Trie and hash-based level matching query with only one off-chip memory access per lookup. Additionally, an optimization algorithm called BP2O is developed to improve memory efficiency using Ant Colony Optimization algorithms. Experimental results prove the superior memory efficiency of the proposal, and theoretical performance analyses demonstrate that PR-Trie outperforms classical Trie-based IP lookup algorithms.
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Naresh Nayak, Uthra Ambalavanan, Jishnu Murali Thampan, Dennis Grewe, Marco Wagner, Sebastian Schildt, Joerg Ott
Summary: Automotive electrical and electronic (E/E) engineering architectures are undergoing radical transformations to meet the current automotive trends. New networking technologies are being explored for future-proofing in-vehicular networks. Programmable data plane technologies have been successfully used in data center networking and are now being investigated for their applicability in in-vehicular networks.
IEEE VEHICULAR TECHNOLOGY MAGAZINE
(2023)
Article
Geochemistry & Geophysics
Vijay Joshi, J. Sheeba Rani
Summary: This study proposes a new lossless algorithm for on-board satellite hyperspectral data compression, which utilizes spectral and spatial correlation and has lower computational complexity. Non-binary tree traversal and nearest neighbor method are used with neighbor-driven decision-making in the pre-processing stage. The algorithm shows reduced computational complexity and lesser data dependencies compared to the CCSDS 123.0-B-1 standard, with comparable compression performance to other state-of-the-art on-board LS compression methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Computer Science, Interdisciplinary Applications
Christopher B. Marsh, Kevin R. Green, B. Wang, Raymond J. Spiteri
Summary: The study applies lookup tables (LUTs) to replace computationally intensive mathematical function evaluations in distributed hydrological models, resulting in reduced computational costs and improved runtime efficiency, contributing to enhanced model accuracy.
ENVIRONMENTAL MODELLING & SOFTWARE
(2021)
Article
Telecommunications
Wenlong Chen, Diya Liu, Jiacheng Wang, Xiaolan Tang
Summary: This paper introduces an IPv6 route lookup architecture called LPR-Trie, which accelerates routing lookup by utilizing more space and virtual node mechanism. Experimental results show that the design improves search speed and memory utilization.
CHINA COMMUNICATIONS
(2022)
Article
Telecommunications
Wenlong Chen, Diya Liu, Jiacheng Wang, Xiaolan Tang
Summary: This paper proposes an IPv6 route lookup architecture called LPR-Trie, which utilizes the analysis of IPv6 address characteristics to provide a longest prefix routing calculation algorithm for longest prefix match. Experimental results demonstrate that the design improves routing lookup speed while better utilizing memory, and the virtual node mechanism increases search speed by 244%.
CHINA COMMUNICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian
Summary: Image enhancement aims to improve the aesthetic quality of photos by adjusting color and tone, but current methods often overlook the differences between pixels, leading to unsatisfactory results. This paper proposes a novel learnable context-aware 4D LUT that achieves content-dependent enhancement by adaptively learning photo context. Experimental results show that our method outperforms other state-of-the-art methods in widely-used benchmarks.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Hardware & Architecture
Zhuo Li, Jindian Liu, Liu Yan, Beichuan Zhang, Peng Luo, Kaihua Liu
Summary: Name lookup is crucial for NDN network, and a high-performance index is needed for efficient lookup. Existing indexes, though performing well, are impacted by different distributions between current URLs and real NDN names. To address this issue, a smart mapping model and index LNI based on neural networks are proposed.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2022)
Article
Computer Science, Hardware & Architecture
Hussein Al-Omaisi, Elankovan A. Sundararajan, Raed Alsaqour, Nor Fadzilah Abdullah, Khairul Azmi Abu Bakar, Maha Abdelhaq
Summary: The vehicular named data networking (VNDN) is gaining attention as a future vehicular networking (VN) model. This paper introduces an Interest-Data-flow tracking-based forwarding scheme (IDTracS) for VNDN, aiming to improve its performance by prioritizing potential best forwarders and addressing broadcast issues. The simulation findings show that IDTracS achieves enhanced satisfaction ratio, delivery delay, and network transmission overhead compared to related protocols.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Computer Science, Information Systems
Myeongji Ko, Hyogon Kim, Sung-Gi Min
Summary: IETF IP Wireless Access in Vehicular Environments Working Group proposes a shared-prefix model for vehicular mobility management scheme in IEEE WAVE IPv6 networks. To eliminate the triangular data path between vehicles, a localized forwarding scheme is proposed for direct communication or serving RSUs within the WAVE network.
Article
Engineering, Electrical & Electronic
Janos Tapolcai, Lajos Ronyai, Eva Hosszu, Laszlo Gyimothi, Pin-Han Ho, Suresh Subramaniam
IEEE TRANSACTIONS ON COMMUNICATIONS
(2016)
Article
Computer Science, Hardware & Architecture
Peter Babarczi, Janos Tapolcai, Alija Pasic, Lajos Ronyai, Erika R. Berczi-Kovacs, Muriel Medard
IEEE-ACM TRANSACTIONS ON NETWORKING
(2017)
Article
Computer Science, Hardware & Architecture
Ori Rottenstreich, Janos Tapolcai
IEEE-ACM TRANSACTIONS ON NETWORKING
(2017)
Article
Computer Science, Information Systems
Mohammed L. Ali, Pin-Han Ho, Janos Tapolcai
OPTICAL SWITCHING AND NETWORKING
(2017)
Article
Computer Science, Hardware & Architecture
Mate Nagy, Janos Tapolcai, Gabor Retvari
IEEE-ACM TRANSACTIONS ON NETWORKING
(2018)
Article
Engineering, Electrical & Electronic
Janos Tapolcai, Gabor Retvari, Peter Babarczi, Erika R. Berczi-Kovacs
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2019)
Article
Computer Science, Hardware & Architecture
Alija Pasic, Peter Babarczi, Janos Tapolcai, Erika R. Berczi-Kovacs, Zoltan Kiraly, Lajos Ronyai
IEEE-ACM TRANSACTIONS ON NETWORKING
(2020)
Article
Computer Science, Hardware & Architecture
Balazs Vass, Laszlo Nemeth, Janos Tapolcai
Article
Computer Science, Hardware & Architecture
Janos Tapolcai, Lajos Ronyai, Balazs Vass, Laszlo Gyimothi
IEEE-ACM TRANSACTIONS ON NETWORKING
(2020)
Article
Computer Science, Information Systems
Ferenc Mogyorosi, Alija Pasic, Richard Cziva, Peter Revisnyei, Zsolt Kenesi, Janos Tapolcai
Summary: This article proposes a new protection scheme for backbone networks that utilizes Machine Learning to implement network intelligence and achieve a proactive approach to service availability without the need for reserved backup network resources. By reallocating unused capacity as protection bandwidth, the scheme aims to improve availability without affecting operational connections or the over-provisioning of network bandwidth.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2021)
Article
Engineering, Electrical & Electronic
Balazs Vass, Janos Tapolcai, Zalan Heszberger, Jozsef Biro, David Hay, Fernando A. Kuipers, Jorik Oostenbrink, Alessandro Valentini, Lajos Ronyai
Summary: The paper introduces a stochastic model for estimating hazards to an optical backbone network and understanding the complex correlation between possible link failures. It also presents standard data structures and a pre-computation process for efficient computation of cumulative failure probabilities of network elements.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2021)
Article
Computer Science, Hardware & Architecture
Balazs Vass, Janos Tapolcai, Erika R. Berczi-Kovacs
Summary: The paper proposed a limited geographic information failure model, which allows for the design of an algorithm that can efficiently compute the set of links that are expected to be close in a network. Under realistic assumptions, the obtained list of SRLGs is short, with approximately 1.2n and 2.2n elements for k = 0 and k = 1, respectively.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2021)
Article
Computer Science, Information Systems
Sandor Z. Kiss, Eva Hosszu, Janos Tapolcai, Lajos Ronyai, Ori Rottenstreich
Summary: This article discusses the importance of Bloom filters and their variants in networking applications, and introduces a new data structure called EGH filter that guarantees false positive-free operations. The EGH filter supports Bloom filter operations and ensures real-time false positive-free operations within a limited universe and restricted number of elements stored.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2021)
Article
Computer Science, Information Systems
Alija Pasic, Rita Girao-Silva, Ferenc Mogyorosi, Balazs Vass, Teresa Gomes, Peter Babarczi, Peter Revisnyei, Janos Tapolcai, Jacek Rak
Summary: This paper introduces a new framework focusing on resilience against natural disasters, targeting network planning, failure modeling, and survivable routing. It proposes a two-stage approach to optimize availability upgrade cost by upgrading a sub-network to achieve the targeted availability threshold. The framework also includes a new integer linear program for disaster-resilient network planning and an efficient heuristic scheme to reduce running time.