Cluster Computing最新文献

Medical imaging is essential in modern healthcare because it assists physicians in the diagnosis of cancer. Various tissues and features in medical imaging can be recognized using image segmentation algorithms. This feature makes it possible to pinpoint and define particular areas, which makes it easier to precisely locate and characterize anomalities or lesions for cancer diagnosis. Among cancers affecting women, breast cancer is particularly prevalent, underscoring the urgent need to improve the accuracy of image segmentation for breast cancer in order to assist medical practitioners. Multi-threshold image segmentation is widely acknowledged for its direct and effective characteristics. In this context, this paper suggests a refined whale optimization algorithm to improve the segmentation accuracy of breast cancer data. This algorithm optimizes performance by combining a quantum phase interference mechanism and an enhanced solution quality strategy. This work compares the method with classical, homogeneous, state-of-the-art algorithms and runs experiments on the IEEE CEC2017 benchmark to validate its practical optimization performance. Furthermore, a multi-threshold image segmentation algorithm-based image segmentation technique is presented in this study. The Berkeley segmentation dataset and the breast invasive ductal carcinomas segmentation dataset are segmented using the approach using a non-local means two-dimensional histogram and Renyi’s entropy. Experimental results demonstrate the excellent performance of this segmentation method in image segmentation applications across both low and high threshold levels. As a result, it emerges as a valuable image segmentation technique with practical applications.

Machine learning revolutionizes accuracy in diverse fields such as disease diagnosis, speech understanding, and sentiment analysis. However, its intricate architecture often obscures the decision-making process, creating a “black box” that hinders trust and limits its potential. This lack of transparency poses significant challenges, particularly in critical fields like the healthcare system. We present OntoXAI, a Semantic Web Rule Language (SWRL) based Explainable Artificial Intelligence (XAI) approach to address these challenges. OntoXAI leverages semantic technology and machine learning (ML) to enhance prediction accuracy and generate user-comprehensible natural language explanations in the context of dengue disease classification. OntoXAI can be summarized into three key aspects. (1) Creates a knowledge base that incorporates domain-specific knowledge related to the disease. This allows for the integration of expert knowledge into the classification process. (2) OntoXAI presents a diagnostic classification system that utilizes patient symptoms as input to classify the disease accurately. By leveraging ML algorithms, it achieves high accuracy in disease classification. (3) OntoXAI introduces SWRL and ontology to integrate explainable AI techniques with Open AI API, enabling a better understanding of the classification process. By combining the power of machine learning algorithms with the ability to provide transparent, human-understandable explanations through Open AI API, this approach offers several advantages in enhancing prediction accuracy, achieving levels of up to 96%. Overall, OntoXAI represents a significant advancement in the field of explainable AI, addressing the challenges of transparency and trust in machine learning systems, particularly in critical domains like healthcare.

Features within the dataset carry a significant role; however, resource utilization, prediction-time, and model weight are increased by utilizing high-dimensional data in intrusion-detection paradigm. This paper aims to design a novel lightweight intrusion detection system in two phases utilizing a swarm intelligence-based technique. In 1st-phase, essential features are selected using particle swarm optimization algorithm by considering imbalanced dataset. Ant colony optimization algorithm is utilized in 2nd-phase for extracting information-rich and uncorrelated features. Additionally, genetic algorithm is employed for fine-tuning each detection model. Proposed model’s performance is evaluated on different base and ensemble classifiers, and it is observed that xgboost achieves best accuracy with 90.38%, 92.63%, and 97.87% on NSL-KDD, UNSW-NB15, and CSE-CIC-IDS2018 datasets, respectively. The proposed model also outperforms other traditional dimensionality reduction and state-of-the-art approaches with statistical validation. This paper also analyses objective function of each metaheuristic algorithm used in this paper, applying convergence graphs, box, and swarm plots.

Machine Type Communication Devices for Machine-to-Machine (M2M) communication in 5G cellular networks have issues with scalability, quality of service (QoS), collisions, and delays in data transmission. M2M connectivity has become prevalent in the Internet of Things. The suggested MAC protocol for M2M communication using adaptive TDMA was designed to be scalable and power-efficient. To address the problems of collision, quality of service and scalability in M2M communication by presenting a Power-efficient MAC switching protocol with Adaptive Time Division Multiple Access (PMAC-ATDMA). There are three phases to this: grouping, dynamic MAC switching, and time slot allocation. Optimization Technique: The usage of the adaptive k-means algorithm with the HHO method for selecting MTC heads based on their power status and proximity to enhance network efficiency and reduce collision. Hybrid MAC Protocol Design: A dynamic switching mechanism between CSMA/CA and Carrier Sense Multiple Access/Collision Avoidance Reservation Protocol (CSMA/CARP) based on network density and device activity, aiming to optimize collision handling and energy consumption. ATDMA assigns time slots that are used for data transmission based on the size of the data and QoS requirements. Traditional TDMA’s synchronization issue is solved by using the Markov chain model; this PMAC-ATDMA is simulated using a network simulator tool. Access delay, energy, collision likelihood, and successful packet transmissions are all taken into account throughout the evaluation process.

Deploying distributed generators (DGs) powered by renewable energy poses a significant challenge for effective power system operation. Optimally scheduling DGs, especially photovoltaic (PV) systems and wind turbines (WTs), is critical because of the unpredictable nature of wind speed and solar radiation. These intermittencies have posed considerable challenges to power grids, including power oscillation, increased losses, and voltage instability. To overcome these challenges, the battery energy storage (BES) system supports the PV unit, while the biomass aids the WT unit, mitigating power fluctuations and boosting supply continuity. Therefore, the main innovation of this study is presenting an improved moth flame optimization algorithm (IMFO) to capture the optimal scheduling of multiple dispatchable and non-dispatchable DGs for mitigating energy loss in power grids, considering different dynamic load characteristics. The IMFO algorithm comprises a new update position expression based on a roulette wheel selection strategy as well as Gaussian barebones (GB) and quasi-opposite-based learning (QOBL) mechanisms to enhance exploitation capability, global convergence rate, and solution precision. The IMFO algorithm's success rate and effectiveness are evaluated using 23rd benchmark functions and compared with the basic MFO algorithm and other seven competitors using rigorous statistical analysis. The developed optimizer is then adopted to study the performance of the 69-bus and 118-bus distribution grids, considering deterministic and stochastic DG's optimal planning. The findings reflect the superiority of the developed algorithm against its rivals, emphasizing the influence of load types and varying generations in DG planning. Numerically, the optimal deployment of BES + PV and biomass + WT significantly maximizes the energy loss reduction percent to 68.3471 and 98.0449 for the 69-bus's commercial load type and to 54.833 and 52.0623 for the 118-bus's commercial load type, respectively, confirming the efficacy of the developed algorithm for maximizing the performance of distribution systems in diverse situations.

Image segmentation is the process of splitting a digital image into distinct segments or categories based on shared characteristics like texture, color, and intensity. Its primary aim is to simplify the image for easier analysis while preserving its important features. Each pixel in the image is assigned a label, grouped together by pixels with similar traits together. Segmentation helps to delineate boundaries and identify objects such as curves or lines within the image. The process generates a series of segmented images that cover the entire original image. This article reviews emerging applications of image segmentation in medical diagnostics, specifically employing nature-inspired optimization algorithms (NIOAs). It begins by outlining different segmentation methods and NIOAs types, then by examining relevant databases and medical imaging technologies. The study draws on a diverse range of research sources. Finally, this paper briefly discusses the challenges and future trends of medical image segmentation using NIOAs to detect different diseases.

To address the real-world constrained engineering optimization problem (CEOP) and the breast cancer classification task using a high-performance heuristic approach, a novel Chaos balanced butterfly optimizer, named Chaos-BBO, was proposed with chaos regulation strategies for the smell dynamic parameter (C_1) and balance dynamic parameter (C_2). The basic BBO algorithm was inspired by the smell and light perception of the special butterfly. Notably, this article collected twelve continuum chaotic mappings with one-dimensional, which has some differences from the common ten chaos mappings. we collected twelve continuum chaotic mapping functions to expand their application scope in the swarm intelligent (SI) algorithm, and their chaotic properties were also depicted in detail. Twenty-three CEC and nine CEC2022 benchmark functions were applied to evaluate the performance of the designed Chaos-BBO, which was compared to FA, GWO algorithm, BOA, HHO algorithm, SMA, JS algorithm, AO algorithm, AHA, and HBA expert for the basic BBO algorithm. Then, Friedman rank and Wilcoxon rank-sum (WRS) tests were utilized to analyze the statistical properties and rankings of the comparison methods. Finally, the proposed Chaos-BBO was utilized to address eight CEOPs and the breast cancer classification task. The results of the numerical optimization and application tasks demonstrated the superiority of the designed Chaos-BBO approach.

Network telemetry plays a pivotal role in understanding and optimizing underlying network infrastructures by facilitating essential operations like troubleshooting and traffic load balancing. However, real-time processing of network packets, especially at speeds of 100 Gbps or more, presents significant challenges due to the uncoordinated processing performance between kernel and user-space applications. This study introduces high-performance telemetry collector (HPTCollector) aims at harmonizing the processing activities of kernel and user-space applications, thereby enhancing the performance of network telemetry systems. HPTCollector demonstrates exceptional adaptability and efficiency, achieving remarkable throughput rates. Specifically, our mechanism can process up to 31 million packets per second using just 12 CPU cores in user-space, an achievement made possible through parallel packet processing techniques. This capability ensures robust support for network telemetry processing at collector for network infrastructures with bandwidth of 350 Gbps and 2.03 Tbps, MTU size of 1500 and 9000 respectively. This breakthrough not only showcases the potential of our proposed mechanism but also sets a new benchmark in network telemetry collector performance.

Beluga whale optimization (BWO) has received widespread attention in scientific and engineering domains. However, BWO suffers from limited adaptability, weak anti-stagnation, and poor exploration capability. Consequently, this study proposes an enhanced variant of BWO called multi-strategy improved beluga whale optimization (MIBWO). First, an improved ICMIC chaotic map is introduced to enhance exploration capability and optimization accuracy. Then, a dynamic parameter nonlinear adjustment strategy is integrated to achieve a better balance between exploration and exploitation. Finally, opposition learning based on the lens imaging principle is designed to strengthen anti-stagnation capability. An ablation experiment is performed to evaluate the impact of each strategy on the optimization capability of BWO. The experimental results demonstrate the significant enhancement in the performance of BWO owing to the used strategies. To further validate the performance of MIBWO, it is benchmarked against six state-of-the-art optimization algorithms using functions from CEC2005, CEC2014, and CEC2022. Statistical tests, including Friedman rank test and Wilcoxon rank-sum test, are performed. The experimental results show the superiority of MIBWO. Finally, MIBWO is applied to optimize 2D and 3D node coverage in wireless sensor networks and solve six constrained engineering problems. The experimental results indicate that MIBWO outperforms other competitors for practical engineering applications in terms of solution quality and convergence speed.