检索结果-内蒙古大学图书馆

FEATURE SELECTION USING THE CONCEPT OF PEAFOWL MATING IN IDS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ghosh, Partha Sharma, Joy Pandey, Nilesh Dept. of Information Technology Netaji Subhash Engineering College Kolkata India Dept. of Computer Science and Engineering Netaji Subhash Engineering College Kolkata India

Cloud computing has high applicability as an Internet based service that relies on sharing computing resources. Cloud computing provides services that are Infrastructure based, Platform based and Software based. The popularity of this technology is due to its superb performance, high level of computing ability, low cost of services, scalability, availability and flexibility. The obtainability and openness of data in cloud environment make it vulnerable to the world of cyber-attacks. To detect the attacks Intrusion Detection System is used, that can identify the attacks and ensure information security. Such a coherent and proficient Intrusion Detection System is proposed in this paper to achieve higher certainty levels regarding safety in cloud environment. In this paper, the mating behavior of peafowl is incorporated into an optimization algorithm which in turn is used as a feature selection algorithm. The algorithm is used to reduce the huge size of cloud data so that the IDS can work efficiently on the cloud to detect intrusions. The proposed model has been experimented with NSL-KDD dataset as well as Kyoto dataset and have proved to be a better as well as an efficient IDS. © 2024, CC BY.

关键词： Intrusion detection

EVERYTHING YOU WANTED TO KNOW ABOUT CONSUMER LIGHT MANAGEMENT IN SMART ENERGY

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mohanty, Prajnyajit Pati, Umesh C. Mahapatra, Kamalakanta Mohanty, Saraju P. Dept. of Electronics and Communication Engineering National Institute of Technology Rourkela769008 India Dept. of Computer Science and Engineering University of North Texas United States

Consumer lighting plays a significant role in the development of smart cities and smart villages. With the advancement of (IoT) technology, smart lighting solutions have become more prevalent in residential areas as well. These solutions provide consumers with increased energy efficiency, added convenience, and improved security. On the other hand, the growing number of IoT devices has become a global concern due to the carbon footprint and carbon emissions associated with these devices. The overuse of batteries increases maintenance and cost to IoT devices and simultaneously possesses adverse environmental effects, ultimately exacerbating the pace of climate change. Therefore, in tandom with the principles of Industry 4.0, it has become crucial for manufacturing and research industries to prioritize sustainable measures adhering to smart energy as a prevention to the negative impacts. Consequently, it has undoubtedly garnered global interest from scientists, researchers, and industrialists to integrate state-of-the-art technologies in order to solve the current issues in consumer light management systems making it a complete sustainable, and smart solution for consumer lighting application. This manuscript provides a thorough investigation of various methods as well as techniques to design a state-of-the-art IoT-enabled consumer light management system. It critically reviews the existing works done in consumer light management systems, emphasizing the significant limitations and the need for sustainability. The top-down approach of developing sustainable computing frameworks for IoT-enabled consumer light management has been reviewed based on the multidisciplinary technologies involved and state-of-the-art works in the respective domains. Lastly, this article concludes by highlighting possible avenues for future research. © 2024, CC BY.

关键词： Smart manufacturing

Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Saltori, Cristiano Galasso, Fabio Fiameni, Giuseppe Sebe, Nicu Poiesi, Fabio Ricci, Elisa The Dept. of Information Engineering and Computer Science University of Trento Italy The Dept. of Computer Science Sapienza University of Rome Italy Nvidia Ai Technology Center Italy Trento Italy

Deep-learning models for 3D point cloud semantic segmentation exhibit limited generalization capabilities when trained and tested on data captured with different sensors or in varying environments due to domain shift. Domain adaptation methods can be employed to mitigate this domain shift, for instance, by simulating sensor noise, developing domain-agnostic generators, or training point cloud completion networks. Often, these methods are tailored for range view maps or necessitate multi-modal input. In contrast, domain adaptation in the image domain can be executed through sample mixing, which emphasizes input data manipulation rather than employing distinct adaptation modules. In this study, we introduce compositional semantic mixing for point cloud domain adaptation, representing the first unsupervised domain adaptation technique for point cloud segmentation based on semantic and geometric sample mixing. We present a two-branch symmetric network architecture capable of concurrently processing point clouds from a source domain (e.g. synthetic) and point clouds from a target domain (e.g. real-world). Each branch operates within one domain by integrating selected data fragments from the other domain and utilizing semantic information derived from source labels and target (pseudo) labels. Additionally, our method can leverage a limited number of human point-level annotations (semi-supervised) to further enhance performance. We assess our approach in both synthetic-to-real and real-to-real scenarios using LiDAR datasets and demonstrate that it significantly outperforms state-of-the-art methods in both unsupervised and semi-supervised settings. © 2023, CC BY.

关键词： Mixing

Power Saving and Power Generating in Automobile (Self-Charging Kit)

学校读者我要写书评

暂无评论

Power Saving and Power Generating in Automobile (Self-Chargi...

2023 International Conference on Disruptive Technologies, ICDT 2023

作者： Singh, Jay Datta, Priyanka Kumar, Nagendra Sharma, Kailash Saxena, Abhinav Verma, Aditya Ambika Pathy, A. Gl Bajaj Institute of Technology & Management Eee Department Gr Noida India Jss Academy of Technical Education Dept. of Eee U.P. Noida India Graphic Era Hill University Computer Science and Engineering Dehradun India Galgotias College of Engineering and Technology Dept. of Eee Gr. Noida India

ISBN: (纸本)9798350323887

Nowadays most well Grounded and Slashed source of Energy is wind energy and it is easily within reach, convenient and easy to employ. So, as we are growing day by day with technology, it's our responsibility to protect our nature for these Engineers and scientist are unfailingly working on different technologies to make human Life reliable and easy to access energy. So, we are also giving a little contribution to our society to make environment pollution free and help for humanities. This research paper is tiny contributions to our society in this confounding field so authors trust that in future this wondrous innovation could assist us with vanquishing all Reliable energy issues so that forthcoming Age could utilize that innovation. So here authors come with innovative solution Power Saving and Power Generating in Automobile using Wind Energy. © 2023 IEEE.

关键词： Wind power

Performance of Intrusion Detection System Using Bagging Ensemble with SDN-Base Classifier 7

学校读者我要写书评

暂无评论

Performance of Intrusion Detection System Using Bagging Ense...

7th IEEE International Conference on Information technology and Digital Applications, ICITDA 2022

作者： Amarudin Ferdiana, Ridi Widyawan Universitas Gadjah Mada Dept. of Electrical Engineering and Information Technology Yogyakarta Indonesia Universitas Teknokrat Indonesia Engineering and Computer Science Lampung Indonesia

ISBN: (数字)9781665461368

ISBN: (纸本)9781665461368

Intrusion Detection System (IDS) is a system for detecting suspicious activity on a network. Many machine learning-based IDS approaches have been built to detect intrusion. However, along with the development of types of attacks, currently the application of IDS has not been maximally successful when detecting various types of attacks. To overcome this problem, better techniques are needed to detect attacks. This research applies an ensemble-based Bagging-SDN machine learning model. Bagging-SDN is built from three base-learners, namely Support Vector Machine (SVM), Decision Tree (DT), and Naïve Bayes (NB). These three base learners are known as SDN (SVM, DT, NB). Furthermore, Bagging-SDN was validated using the UNSW-NB15 dataset. Based on the experiment, it was found that the Bagging-SDN performance was superior to the old method based on single classifier. Best Bagging-SDN performance when using Decision Tree (DT) as a base-learner. Bagging-SDN performance was able to increase the accuracy 80.09% compared to the earlier technique which only reached 75.89%. As for further research, the development of machine learning-based IDS still needs to be improved. For example, build ensemble classifier methods to improve performance using other technique like boosting, stacking and another base-learner. So, the IDS still has satisfactory performance in detecting new types of attacks. © 2022 IEEE.

关键词： Decision trees

The State-Dependent Channel with a Rate-Limited Cribbing Helper

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lapidoth, Amos Steinberg, Yossef Dept. of Information Technology and Electrical Engineering ETH Zurich Zurich8092 Switzerland Dept. of Electrical and Computer Engineering Technion - IIT Haifa3200003 Israel

The capacity of a memoryless state-dependent channel is derived for a setting in which the encoder is provided with rate-limited assistance from a cribbing helper that observes the state sequence causally and the past channel inputs strictly-causally. Said cribbing may increase capacity but not to the level achievable by a message-cognizant helper. Copyright © 2024, The Authors. All rights reserved.

关键词：

Stripe Removal from Hyperspectral Food Images acquired by Handheld Camera using ℓ2,1 Norm Minimization and SSTV Regularization

学校读者我要写书评

暂无评论

Stripe Removal from Hyperspectral Food Images acquired by Ha...

IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications technology (IAICT)

作者： K S Shanthini Sudhish N George Sony George Binu Melit Devassy Dept. of Electronics and Communication Engineering National Institute of Technology Calicut India Dept. of Computer Science Norwegian University of Science and Technology Norway

Hyperspectral imaging offers the capacity to quickly and noninvasively monitor a food product’s physical, chemical and morphological properties. Specim IQ is a handheld push broom camera with basic data handling and data analysis capabilities within the camera software. However, the recordings of the Specim IQ camera showed a line pattern (stripes) that was evident in all images. Stripes significantly reduce the visual quality of the images and lower the results of further processing. Hence an efficient destriping model is developed, which specifically addresses this issue. The proposed model uses a spatial gradient term to analyze the directional characteristics and group sparsity to describe the structural characteristics of the stripe component. In addition to this, a spatial spectral total variation regularization is used to ensure piecewise smoothness in the spatial and spectral domains and to remove Gaussian noise. The ensuing optimisation problem is solved using the alternating direction method of multipliers (ADMM). The proposed method is tested in real stripe noise environments, and the findings demonstrate that it outperforms some of the best approaches in terms of visual quality and quantitative evaluations. When compared with the other approaches, the proposed method attained the highest noise reduction (NR) and lowest mean relative deviation (MRD) values (NR=1.67, MRD=1.02%).

关键词：

Augmented memory replay-based continual learning approaches for network intrusion detection 23

学校读者我要写书评

暂无评论

Augmented memory replay-based continual learning approaches ...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Suresh Kumar Amalapuram Sumohana S Channappayya Bheemarjuna Reddy Tamma Dept. of Computer Science and Engineering Indian Institute of Technology Hyderabad India Dept. of Electrical Engineering Indian Institute of Technology Hyderabad India

Intrusion detection is a form of anomalous activity detection in communication network traffic. Continual learning (CL) approaches to the intrusion detection task accumulate old knowledge while adapting to the latest threat knowledge. Previous works have shown the effectiveness of memory replay-based CL approaches for this task. In this work, we present two novel contributions to improve the performance of CL-based network intrusion detection in the context of class imbalance and scalability. First, we extend class balancing reservoir sampling (CBRS), a memory-based CL method, to address the problems of severe class imbalance for large datasets. Second, we propose a novel approach titled perturbation assistance for parameter approximation (PAPA) based on the Gaussian mixture model to reduce the number of virtual stochastic gradient descent (SGD) parameter computations needed to discover maximally interfering samples for CL. We demonstrate that the proposed approaches perform remarkably better than the baselines on standard intrusion detection benchmarks created over shorter periods (KDDCUP'99, NSL-KDD, CICIDS-2017/2018, UNSW-NB15, and CTU-13) and a longer period with distribution shift (AnoShift). We also validated proposed approaches on standard continual learning benchmarks (SVHN, CIFAR-10/100, and CLEAR-10/100) and anomaly detection benchmarks (SMAP, SMD, and MSL). Further, the proposed PAPA approach significantly lowers the number of virtual SGD update operations, thus resulting in training time savings in the range of 12 to 40% compared to the maximally interfered samples retrieval algorithm.

关键词：

A Quantitative Study on Performance of Proof of Stake (PoS)-based Blockchain Network

学校读者我要写书评

暂无评论

A Quantitative Study on Performance of Proof of Stake (PoS)-...

Blockchain Computing and Applications (BCCA), International Conference on

作者： Richard Churchill Jongho Seol Nohpill Park Dept. of Computer Science Oklahoma State University Stillwater OK USA Dept. of Information Technology Middle Georgia State University Macon GA USA

ISBN: (数字)9798350351538

ISBN: (纸本)9798350351545

A new quantitative model to estimate the performance of a PoS (Proof of Stake) consensus protocol-based blockchain (e.g., Ethereum) is proposed in this paper. The proposed new PoS-based chain model has the number of validators (m) in the network as a central variable in the model such that m = 1 in PoW and m ≫ 1 in PoS. A unified binomial distribution is assumed with respect to the number of validators and then a multinomial distribution is assumed with respect to the number of transaction slots pending on the current block to be posted [14], thereby establishing a quantitative model to express the steady-state probability to have 0 ≤ i ≤ n number of trasactions slots with 1 ≤ j ≤ number of validators across the blockchain network given transaction slots arrival rate (λ) and block posting rate $\left( {\frac{\mu }{j}} \right)$ by number of validators. Extensive numerical simulations will be conducted to evaluate a few base performance metrics such as average transaction waiting time, average size of block and throughput, to mention a few. The simulation results will reveal a quantitative insight into the PoS in comparison to PoW. Ultimately, the proposed quantitative model will establish a theoretical foundation to guide the PoS-based chain developers with specific respect to performance.

关键词： Measurement Proof of stake Computational modeling Simulation Throughput Numerical simulation Numerical models Steady-state