检索结果-内蒙古大学图书馆

Resource investment for DDoS attack resistant SDN: a practical assessment

science China(Information sciences) 2023年第7期66卷 112-129页

作者： Bin YUAN Fan ZHANG Jun WAN Huan ZHAO Shui YU Deqing ZOU Qiangsheng HUA Hai JIN School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Shenzhen Huazhong University of Science and Technology Research Institute School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab School of Computer Science University of Technology Sydney

Software-defined networks(SDNs) present a novel network architecture that is widely used in various datacenters. However, SDNs also suffer from many types of security threats, among which a distributed denial of service(DDoS) attack, which aims to drain the resources of SDN switches and controllers,is one of the most common. Once the switch or controller is damaged, the network services can be *** defense schemes against DDoS attacks have been proposed from the perspective of attack detection;however, such defense schemes are known to suffer from a time consuming and unpromising accuracy, which could result in an unavailable network service before specific countermeasures are taken. To address this issue through a systematic investigation, we propose an elaborate resource-management mechanism against DDoS attacks in an SDN. Specifically, by considering the SDN topology, we leverage the M/M/c queuing model to measure the resistance of an SDN to DDoS attacks. Network administrators can therefore invest a reasonable number of resources into SDN switches and SDN controllers to defend against DDoS attacks while guaranteeing the quality of service(QoS). Comprehensive analyses and empirical data-based experiments demonstrate the effectiveness of the proposed approach.

关键词： SDN security DDoS attacks resource management queueing theory QoS

来源：评论

学校读者我要写书评

暂无评论

Salp swarm algorithm using lens opposition-based learning and local search for constrained optimization problems

引用

Iran Journal of computer science 2025年第2期8卷 659-686页

作者： Majumdar, Parijata Mitra, Sanjoy Department of Computer Science and Engineering Indian Institute of Information Technology Agartala Jirania 799046 India Department of Computer Science and Engineering Tripura Institute of Technology Agartala Narsingarh 799009 India

The Salp swarm algorithm (SSA) simulates how salps forage and travel in the ocean. SSA suffers from low initial population diversity, improper balancing of exploration and exploitation, and slow convergence speed. Thus, we have proposed a novel variant of SSA (LOLSSA) by integrating lens opposition learning with the fundamental evolutionary techniques of SSA to increase the initial population variety. During exploration, the information about the local best position for each individual is effectively shared with the follower, using the salp position update process to avoid getting stuck at the local optimum. At the end of each iteration, the local search algorithm is utilized to increase exploitation. Additionally, the leader’s salp position incorporates inertia weight to speed up the convergence speed. Swarm intelligence algorithms have proven their efficacy in feature selection, since they search for an optimal set of features in a large search area that will have the best impact on the accuracy of the training system. LOLSSA is thus employed for feature selection to select informative features in 11 high-dimensional datasets, where it outperforms well-known metaheuristics in average fitness, accuracy, and average number of feature reductions. In the software-as-a-service cloud computing model, a task scheduling problem is solved to satisfy the QoS requirement of both the service provider and the user. Experiments show that LOLSSA optimizes this problem in terms of different performance metrics. LOLSSA also outperforms other metaheuristics regarding 23 well-known benchmark functions, IEEE CEC-C06 2019, and CEC-06 2020 benchmark functions, and in solving engineering design problems. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Convergence speed Feature selection Global optimization Lens opposition learning Salp swarm algorithm Task scheduling problem

来源：评论

学校读者我要写书评

暂无评论

Magnifier: A Chiplet Feature-Aware Test Case Generation Method for Deep Learning Accelerators

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年第7期44卷 2803-2816页

作者： Li, Boyu Zhu, Zongwei Liu, Weihong Cao, Qianyue Li, Changlong Ji, Cheng Li, Xi Zhou, Xuehai University of Science and Technology of China School of Computer Science and Technology Hefei230026 China University of Science and Technology of China Suzhou Institute for Advanced Research Suzhou215123 China University of Science and Technology of China School of Software Engineering Hefei230026 China University of Science and Technology of China China and Suzhou Institute for Advanced Research Suzhou215123 China East China Normal University School of Computer Science and Technology Shanghai200063 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China

The development of deep learning has led to increasing demands for computation and memory, making multi-chiplet accelerators a powerful solution. Multi-chiplet accelerators require more precise consideration of hardware configurations and mapping schemes in terms of computation, memory, and communication patterns compared to monolithic designs, in order to avoid underutilization of performance. However, there is currently a lack of performance testing methods specifically tailored for multi-chiplet accelerators. Existing testing methods primarily focus on correctness testing and do not address potential performance issues from a hardware perspective. To address these issues, this paper proposes Magnifier: A test case generation method for performance testing of multi-chiplet accelerators. Firstly, we analyze typical multi-chiplet accelerator prototype from the perspectives of computation, memory, and communication patterns, and summarize a chiplet feature-Aware operator task set. Next, we define the test evaluation metric IPPstd and use a candidate operator set to construct a sampling space for model-level test cases. Finally, we build a GAN to learn the distribution of high-diversity test cases, enabling the rapid generation of high-quality test cases. We validate the proposed method on both simulated and real multi-chiplet accelerators. Experiments show that Magnifier can improve the metric of test cases by up to 3.42 times and significantly reduce generation time, providing valuable insights for optimizing the hardware and software of multi-chiplet accelerators. © 1982-2012 IEEE.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning, Ensemble Learning and Deep Learning Classifiers for Parkinson’s Disease Detection

引用

SN computer science 2024年第1期5卷 1-14页

作者： Goyal, Palak Rani, Rinkle Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Patiala India

A progressive neurodegenerative ailment called Parkinson's disease (PD) is marked by the death of dopamine-producing cells in the substantia nigra area of the brain. The exact etiology of PD remains elusive, but it is believed to involve the presence of Lewy bodies, abnormal protein aggregates, in affected brain regions, leading to the mobile symptoms of PD. Hence, as the management of PD continues to evolve, there is a growing demand for the establishment of a descriptive system that enables the early detection of PD. In this study, we conducted an extensive analysis using machine learning, ensemble learning, and deep learning models with different hyperparameters to develop accurate classification models for PD prediction. To enhance classifier performance and address overfitting, we employed principal component analysis (PCA) for feature selection along with various preprocessing techniques. The dataset used consisted of voice samples, comprising 188 PD patients and 64 normal individuals. Our results demonstrated that the Random Forest (RF) model with accuracy of 82.37% outperformed the other base classifiers Among the ensemble classifiers, the LGBM model exhibited the highest accuracy of 85.90% when compared to both base and ensemble classifiers. Notably, the deep learning model has 91.33% training accuracy and 85.02% testing accuracy, suggesting that deep learning models perform comparably equivalent on small datasets compared to machine learning classifiers. Overall, our findings underscore the effectiveness of machine learning, ensemble techniques and deep learning models in accurately predicting PD. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Deep learning Hyperparameters LGBM Machine learning Parkinson’s disease Random forest

来源：评论

学校读者我要写书评

暂无评论

Exploring Personalized Internet of Things(PIoT),social connectivity,and Artificial Social Intelligence(ASI):A survey

引用

High-Confidence Computing 2024年第3期4卷 136-162页

作者： Bisma Gulzar Shabir Ahmad Sofi Sahil Sholla Department of Information Technology National Institute of TechnologySrinagar 190001India Department of Computer Science and Engineering Islamic University of Science and TechnologyGazipur 1700India

Pervasive Computing has become more personal with the widespread adoption of the Internet of Things(IoT)in our day-to-day *** emerging domain that encompasses devices,sensors,storage,and computing of personal use and surroundings leads to Personal IoT(PIoT).PIoT offers users high levels of personalization,automation,and *** proliferation of PIoT technology has extended into society,social engagement,and the interconnectivity of PIoT objects,resulting in the emergence of the Social Internet of Things(SIoT).The combination of PIoT and SIoT has spurred the need for autonomous learning,comprehension,and understanding of both the physical and social *** research on PIoT is dedicated to enabling seamless communication among devices,striking a balance between observation,sensing,and perceiving the extended physical and social environment,and facilitating information ***,the virtualization of independent learning from the social environment has given rise to Artificial Social Intelligence(ASI)in PIoT ***,autonomous data communication between different nodes within a social setup presents various resource management challenges that require careful *** paper provides a comprehensive review of the evolving domains of PIoT,SIoT,and ***,the paper offers insightful modeling and a case study exploring the role of PIoT in post-COVID *** study contributes to a deeper understanding of the intricacies of PIoT and its various dimensions,paving the way for further advancements in this transformative field.

关键词： Personal Internet of Things(PIoT) Artificial Social Intelligence(ASI) Hyperpersonalization

来源：评论

学校读者我要写书评

暂无评论

Efficacy of Ensemble Learning Method over Individual Classifier for Rainfall Forecasting in Eastern India

引用

Journal of The Institution of Engineers (India): Series B 2024年第4期105卷 929-939页

作者： Karmakar, Rahul Kundu, Saranagta Biswas, Saroj Kumar Tripathi, Deeksha Department of Computer Science The University of Burdwan West Bengal Bardhaman India Department of Computer Science and Engineering National Institute of Technology Assam Silchar India

Severe rainfall has seriously threatened human health and survival. Natural catastrophes such as floods, droughts, and many other natural disasters are caused by heavy rains, which people worldwide have to deal with throughout the year. Accurate rainfall forecasting is essential in nations like India where cultivation is the main occupation. Machine learning (ML) techniques are more effective than many other strategies because of the unpredictable nature of rainfall. Ensemble learning (EL) methods yield higher accuracy than ML specific classifiers. Therefore, this paper proposes an EL-based prediction model for not only a specific state of India but for the entire eastern India region, which includes ten states: West Bengal, Jharkhand, Bihar, Odisha, Assam, Tripura, Mizoram, Manipur, Nagaland and Meghalaya. We acquired the rainfall data for eastern India using NASA’s power data access view for 22 years (2000–2021). In this model, apart from classification feature selection is done using Pearson correlation and ANOVA. This study looks at the accuracy of several different classifiers, including DT, LR, and SVM. The acceptable accuracy of 96.53% for rainfall prediction in eastern India was determined using an ensemble model that includes the XGBoost ensemble technique and the classifiers DT, LR, and SVM. The findings of our experiment reveal that EL-based prediction model outperforms the individual classifiers utilized in the experiment. © The Institution of Engineers (India) 2024.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A hybrid encryption for secure data deduplication the cloud

引用

International Journal of Cloud Computing 2023年第2-4期12卷 295-307页

作者： Ebinazer, Silambarasan Elkana Savarimuthu, Nickolas Bhanu, S. Mary Saira Department of Computer Science and Engineering Cyber Security IIIT Kottayam India Department of Computer Applications National Institute of Technology Tiruchirappalli India Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli India

Cloud computing (CC) is a cost-effective platform for users to store their data on the internet rather than investing in additional devices for storage. Data deduplication (DD) defines a process of eliminating redundant data in the cloud by leaving a single copy. This paper provides a hybrid encryption scheme using genetic algorithm (GA) and attribute-based encryption (ABE) to ensure secure data transmission in the cloud and preventing the data deduplication by using message locked encryption (MLE). The hybrid encryption scheme provides a secure data transmission in the cloud. From the simulation output, the time requirement is reduced up to 94% and consumes 43% bandwidth compared with existing works. The proposed method tends to be quite effective in reducing storage and bandwidth costs. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Multilevel characterization of unknown protein sequences using hierarchical long short term memory model

引用

Multimedia Tools and Applications 2025年第9期84卷 6593-6614页

作者： Agrawal, Saurabh Sisodia, Dilip Singh Nagwani, Naresh Kumar Department of Computer Science & Engineering National Institute of Technology Raipur GE Road Chhattisgarh Raipur492010 India

Multilevel characterization of the recently developed Unknown Protein Sequence (UPS) is significant for the drug-designing, disease-diagnosis, and treatment plans. UPS can demonstrate harmful as well as useful characters. Long Short Term Memory (LSTM) based Multilevel Protein Characterization (ML_PC) model using Neuro-Fuzzy Classifier (NFC) and transfer learning has been proposed in this paper for characteristics, species, and function prediction of the UPS. Gram Negative (GN) dataset with known 2286 protein sequences, is used for formation and validation of the ML_PC model. Thereafter NFC is applied at initial stage of the validated ML_PC model to filter the 518 independent protein sequences of the UPS dataset as GN or Non-GN in context with known GN dataset. However, NFC is competent to handle likelihood classification complications of supervised learning. Characteristics, species, and functions of the filtered GN UPS have been predicted in succeeding levels of the ML_PC framework through Protein Characterization (PC) model. LSTM and transfer learning based PC model has been trained and validated using augmented feature of the known GN protein sequence samples, while tested with UPS and filtered GN protein sequences. Transfer learning has been applied as requisite postprocessing to overcome overfitting in the prediction of bacterial protein species with insufficient protein sequence samples. Performance of the multilevel model is improved by 7.52% after combining with transfer learning and NFC. ML_PC model has been compatible to extract relevant biological information of the UPS in context to various categories of bacterial proteins. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

ImageNet Classification Using WordNet Hierarchy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1718-1727页

作者： Chatterjee, Ankita Mukherjee, Jayanta Das, Partha Pratim Indian Institute of Technology Kharagpur Department of Computer Science and Engineering Kharagpur721302 India Ashoka University Department of Computer Science Sonipat131029 India

Convolutional neural networks (ConvNets) have become increasingly popular for image classification tasks. All contemporary computer vision problems are being dominated by ConvNets. Conventional training methods using cross-entropy loss for training have constantly outperformed the state-of-the-art technique to set a new standard in the ImageNet classification challenge. However, growing accuracy come at the cost of enormous number of parameters and computations. Further, classical learning algorithms do not utilize the semantic relationship between the classes present in the dataset. Thus, interpreting the behavior of the model become difficult even though the results may be desirable. Hence, we demonstrate a classification method by leveraging the WordNet hierarchy on the ImageNet dataset to establish class relationships and label embedding. The model is trained using cross entropy with soft labels based on the semantic similarity between the generated output and the ground truth. Unlike categorical cross entropy, it does not treat every predicted label as equally erroneous. The method generates meaningful neighboring classes in the feature space of the true label. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Microgrids with day-ahead energy forecasting for efficient energy management in smart grids: hybrid CS-RERNN

引用

Australian Journal of Electrical and Electronics engineering 2024年第3期21卷 213-227页

作者： Shirley, C.P. Pattar, Jagannath Kavitha Rani, P. Saini, Sumit Ranga, Jarabala Elangovan, D. Venkatakrishna Reddy, Ch. Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Mechanical Engineering Madanapalle Institute of Technology & Science Madanapalle India Department of M.Tech Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India Department of Electrical Engineering School of Engineering & Technology Central University of Haryana Mahendergarh India Detartment of Electrical and Electronics Engineering Ramachandra College of Engineering Eluru India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Electrical and Electronics Engineering Chaitanya Bharathi institute of technology Hyderabad India

By integrating smart grid technology with home energy management systems, households can monitor and optimise their energy consumption. This allows for more efficient use of energy resources, reducing waste and lowering energy bills. In this manuscript, a hybrid approach is proposed for smart grid home energy management with microgrids and day-ahead energy forecasts. The proposed control approach combines the Circle Search (CS) algorithm and Recalling-Enhanced Recurrent Neural Network (RERNN). Commonly it is named as CS-RERNN technique. The novelty of this paper is to optimise energy consumption and production within microgrids, thereby contributing to the overall efficiency of the smart grid system. The proposed method is used to reduce the electricity cost, peak-to-average ratio (PAR), and maximising consumer comfort. Energy management is performed based on the CS algorithm. A smart home connected to the external power grid (PG) is managed by the proposed method. Here, load demand is predicted by using RERNN. By then, the performance of the proposed method is implemented in MATLAB platform. The proposed method shows a high efficiency of 96%, and 22 $ of low electricity bill cost compared with other existing methods such as Particle swarm optimisation (PSO), Cuckoo search algorithm (CSA, and Border collie Optimisation (BCO). ©, Engineers Australia.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：