The Journal of Supercomputing最新文献

Medical researches encounter time, cost, solubility, and data challenges in new drug development. Within the realm of theory, chemical graph theory plays a crucial role in drug design. The SARS-CoV-2 pandemic prompts urgent exploration of drugs like favipiravir, baricitinib, fluvoxamine, nirmatrelvir, molnupiravir, lopinavir, and remdesivir. Developing effective treatments of COVID-19 is a top priority for health authorities, as they strive to curb the pandemic’s impact on public health and prevent future outbreaks. This article characterized CoM-polynomial and their derivatives to determine the topological characteristics of several antiviral drugs. Using this approach, we examine physicochemical properties with quadratic regression method. The results indicate significant correlation between the investigated topological coindices and the physicochemical properties of potential antiviral medicines.

Data integration combines information from different sources to provide a comprehensive view for making informed business decisions. The ETL (Extract, Transform, and Load) process is essential in data integration. In the past two decades, modeling the ETL process has become a priority for effectively managing information. This paper aims to explore ETL approaches to help researchers and organizational stakeholders overcome challenges, especially in Big Data integration. It offers a comprehensive overview of ETL methods, from traditional to Big Data, and discusses their advantages, limitations, and the primary trends in Big Data integration. The study emphasizes that many technologies have been integrated into ETL steps for data collection, storage, processing, querying, and analysis without proper modeling. Therefore, more generic and customized design modeling of the ETL steps should be carried out to ensure reusability and flexibility. The paper summarizes the exploration of ETL modeling, focusing on Big Data scalability and processing trends. It also identifies critical dilemmas, such as ensuring compatibility across multiple sources and dealing with large volumes of Big Data. Furthermore, it suggests future directions in Big Data integration by leveraging advanced artificial intelligence processing and storage systems to ensure consistency, efficiency, and data integrity.

Timing determinism in embedded real-time systems requires meeting timing constraints not only for individual tasks but also for chains of tasks that involve multiple messages. End-to-end analysis is a commonly used approach for solving such problems. However, the temporal properties of tasks often have uncertainty, which makes end-to-end analysis challenging and prone to errors. In this paper, we focus on enhancing the precision and safety of end-to-end timing analysis by introducing a novel probabilistic method. Our approach involves establishing a probabilistic model for end-to-end timing analysis and implementing two algorithms: the maximum data age detection algorithm and the end-to-end timing deadline miss probability detection algorithm. The experimental results indicate that our approach surpasses traditional analytical methods in terms of safety and significantly enhances the capability to detect the probability of missing end-to-end deadlines.

The colored traveling salesman problem (CTSP) generalizes the well-known multiple traveling salesman problem by utilizing colors to describe the accessibility of cities to individual salesmen. Many centralized algorithms have been developed to solve CTSP instances. This work presents a distributed solving framework and method for CTSP for the first time. The framework consists of multiple container-based computing nodes that rely on specific cloud infrastructures to perform distributed optimization in a pipeline style. In the framework, we develop a distributed Delaunay-triangulation-based variable neighborhood search (DDVNS) algorithm for solving a CTSP case decomposed into many traveling salesman problems. DDVNS exploits a two-stage initialization to generate an initial solution for all TSPs. After that, Delaunay-triangulation-based variable neighborhood search (DVNS) is employed to find local optima. Furthermore, the obtained solutions are improved by reallocating multicolor cities and iterating the search progress, ultimately leading to a group of CTSP solutions. Finally, extensive experiments show that DDVNS outperforms the state-of-the-art centralized VNS algorithms in terms of search efficiency and solution quality. Notably, we can achieve the best solution in a superscale case with 16 salesmen and 160,000 cities within 15 minutes, breaking the best record of CTSPs.

At CRYPTO 2019, Gohr first proposed neural distinguishers (NDs) on SPECK32, which are superior to the distinguishers based on the differential distribution table (DDT). Benamira et al. noted that NDs rely on the differential distribution of the last three rounds, and Bao et al. pointed out that NDs depend on the strong correlations between the bit values of ciphertext pairs satisfying the expected differential. Hence, one may guess that there exist deep relations between NDs and the differential-linear imbalances. To approximate NDs under a single ciphertext pair, we utilize differential-linear imbalances to construct simplified distinguishers. These newly constructed distinguishers offer comparable distinguishing advantages to that of NDs but with reduced time complexities. For instance, one such simplified distinguisher has only (2^{-1.35}) of the original time complexity of NDs. Our experiments demonstrate that these new distinguishers achieve a matching rate of 98.2% for 5-round SPECK32 under a single ciphertext pair. Furthermore, we achieve the highest accuracies for 7-round and 8-round SPECK32 up to date by using a maximum of 512 ciphertext pairs. Finally, by replacing NDs with simplified distinguishers, we significantly reduce the time complexities of differential-neural attacks on 11–14 rounds of SPECK32.

The deployment of increasingly diverse services on edge devices is becoming increasingly prevalent. Efficiently deploying functionally heterogeneous services to resource heterogeneous edge nodes while achieving superior user experience is a challenge that every edge system must address. In this paper, we propose a container-node graph (CN-Graph)-based container optimal matching deployment algorithm, edge Kuhn-Munkres algorithm (EKM) based on container-node graph, designed for heterogeneous environment to optimize system performance. Initially, containers are categorized by functional labels, followed by construction of a CN-Graph model based on the relationship between containers and nodes. Finally, the container deployment problem is transformed into a weighted bipartite graph optimal matching problem. In comparison with the mainstream container deployment algorithms, Swarm, Kubernetes, and the recently emerged ECSched-dp algorithm, the EKM algorithm demonstrates the ability to effectively enhance the average runtime performance of containers to 3.74 times, 4.10 times, and 2.39 times, respectively.

As a new paradigm, the Internet of drones (IoD) is making the future easy with its flexibility and wide range of applications. However, these drones are prone to security attacks during communication because of this flexibility. The traditional authentication mechanism uses a centralized server which is a single point of failure to its network and a performance bottleneck. Also, privacy-preserving mechanisms involving a single authority are vulnerable to identity attacks if compromised. Moreover, cross-domain authentication schemes are getting more costly as the security requirements increase. So, this work proposes a blockchain-based cross-domain authentication scheme to make drone communication more secure and efficient. In this work, an elliptic curve digital signature algorithm (ECDSA) based message authentication scheme and a session key generation scheme are modeled. A two-phase pseudonym generation procedure is used to secure the identity of the drones. Hyperledger Fabric is used to implement the blockchain network, and the analysis is done using Hyperledger Caliper. Blockchain analysis through caliper shows the blockchain’s performance for various loads of transactions. Security analysis of the proposed scheme shows that the scheme is secure from various security attacks. The performance analysis shows that the proposed scheme is more lightweight and efficient than most similar authentication schemes.

MEC (Multi-access Edge Computing) is vital in 5G and beyond (B5G) for reducing latency and enhancing network efficiency through local processing, crucial for real-time applications and improved security. This drives the adoption of advanced architectures like Fog Radio Access Network (F-RAN), which uses distributed resources from Radio Resource Heads (RRHs) or fog nodes to enable parallel computation. Each user equipment (UE) task can be processed by RRHs, fog access points, cloud servers, or the UE itself, depending on resource capacities. We propose MoNoR, a centralized approach for optimal task processing in F-RAN. MoNoR optimizes the selection of offloading modes, assignment of tasks to computation nodes, and allocation of radio resources using global network information. Given the computational complexity of this endeavor, we employ an evolutionary optimization technique rooted in Genetic Algorithms to address the problem efficiently. Simulations show MoNoR's superiority in minimizing latency over previous F-RAN offloading strategies.

The node localization problem of wireless sensor networks (WSNs) is addressed in this article with a node localization algorithm designed using fuzzy logic and a nature-inspired algorithm. The coordinates of target nodes are obtained using fuzzy logic reasoning and nature-inspired algorithms. The fuzzy logic concept is used to remove the nonlinearities that arise due to signal strength measurement in the process of range estimation. The triangular and trapezoidal membership functions are used with the Mamdani fuzzy inference system for distance improvement between sensor nodes. Further, particle swarm optimization (PSO) and the Jaya algorithm (JA) determine the target nodes’ location coordinates. The comparison of the proposed fuzzy logic-based PSO (FL-PSO) and fuzzy logic-based JA (FL-JA) algorithms is made with PSO and Jaya algorithm-based node localization algorithms for localization error. The influence of anchor nodes and degree of irregularity is verified during localization analysis on the FL-PSO and FL-JA node localization algorithms. The proposed FL-PSO and FL-JA node localization algorithms are evaluated for scalability, computation time, mean absolute deviation, and complexity to determine their efficacy. The simulations are carried out on MATLAB software in addition to the fuzzy logic toolbox.

The development of computer technology and wireless communication has introduced the wireless body area network (WBAN) to the world. In WBAN, the patient’s vital signs are monitored by small sensors embedded in the body. Sensor nodes work with a limited energy source, so energy consumption is a major issue in these networks. The increase in temperature caused by data transmissions can cause serious damage to body tissue. This paper proposes an Energy-Temperature Aware Routing (ETAR) protocol to solve this problem. In ETAR, routing is done directly and multi-hop using relay nodes. Multi-hop data forwarding plays a significant role in reducing energy consumption. In the proposed method, relay nodes are selected using a fuzzy inference system. Energy, temperature, and distance parameters are defined as the inputs of the fuzzy system. Therefore, in each round, a node with more remaining energy, lower temperature, and less distance from its neighbors is selected as the relay node. The proposed protocol reduces the adverse effects of temperature on the body by setting temperature limits for sensors. The performance of ETAR was evaluated for homogeneous and heterogeneous networks. In homogenous network, this protocol improves energy consumption by 44% and 55% compared to THE and EEMR. Network lifetime is enhanced by 46% and 55% compared to THE and EEMR. The throughput is improved by 40% compared to THE and 34% compared to EEMR, respectively. In a heterogeneous network, this protocol improves energy consumption by 47% and 52% compared to THE and EEMR. Network lifetime is enhanced by 62% and 65% compared to THE and EEMR, respectively. The throughput is improved by 100% compared to THE and 97% compared to EEMR.