检索结果-内蒙古大学图书馆

Neural NILM Learning Paradigms: From Centralised to Decentralised Learning

学校读者我要写书评

暂无评论

Neural NILM Learning Paradigms: From Centralised to Decentra...

International Conference on Signal Processing and Information Security (ICSPIS)

作者： Hafsa Bousbiat Christoph Klemenjak Yassine Himeur Wilfried Elmenreich Abbes Amira Wathiq Mansoor Shadi Atalla Institute of Networked and Embedded Systems University of Klagenfurt Klagenfurt Austria College of Engineering and IT University of Dubai Dubai UAE Department of Computer Science University of Sharjah UAE

ISBN: (纸本)9781665492669

Non-intrusive Load Monitoring (NILM) is becoming a paramount in both industrial and residential sectors to achieve efficient energy consumption. Thus, research on this matter flourished in recent years, where deep neural networks gained the highest interest from the research community, commonly referred to as neural NILM. As a predominant practice, neural NILM models follow a centralised based learning scheme where the energy data is assumed to be available in a central node for training. However, this practice and the enormous amount of data required by these algorithms raise privacy and security concerns from the consumer’s side since energy data can reveal in-home activities and occupancy records if intercepted. Federated Learning (FL), also referred to as collaborative learning, is seen as viable solution to address these issues. Nonetheless, its application in neural NILM is still in its infancy and many challenges are yet to be *** current paper presents an overview of neural NILM models following both a centralised and a federated learning paradigm. Furthermore, it identifies the main challenges with regard to both learning paradigms along with potential future research directions for more robust, secure and privacy-preserving models in the neural NILM industry.

关键词： Deep learning Training Industries Load monitoring Federated learning Neural networks Signal processing algorithms

distributed AI in Zero-touch Provisioning for Edge Networks: Challenges and Research Directions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hazra, Abhishek Morichetta, Andrea Murturi, Ilir Lovén, Lauri Dehury, Chinmaya Kumar Pujol, Víctor Casamayor Donta, Praveen Kumar Dustdar, Schahram Department of Computer Science and Engineering the Indian Institute of Information Technology Sri City India Communications & Networks Lab Department of Electrical and Computer Engineering National University of Singapore Singapore119260 Singapore Distributed Systems Group TU Wien Vienna1040 Austria Center for Ubiquitous Computing University of Oulu 90014 Finland Institute of Computer Science University of Tartu Tartu51009 Estonia

Zero-touch network is anticipated to inaugurate the generation of intelligent and highly flexible resource provisioning strategies where multiple service providers collaboratively offer computation and storage resources. This transformation presents substantial challenges to network administration and service providers regarding sustainability and scalability. This article combines distributed Artificial Intelligence (DAI) with Zero-touch Provisioning (ZTP) for edge networks. This combination helps to manage network devices seamlessly and intelligently by minimizing human intervention. In addition, several advantages are also highlighted that come with incorporating distributed AI into ZTP in the context of edge networks. Further, we draw potential research directions to foster novel studies in this field and overcome the current limitations. Copyright © 2023, The Authors. All rights reserved.

关键词： Internet of things

Statistical privacy-preserving message broadcast for peer-to-peer networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mödinger, David Lorenz, Jan-Hendrik Hauck, Franz J. Institute of Distributed Systems Ulm University Germany Institute of Theoretical Computer Science Ulm University Germany

Privacy concerns are widely discussed in research and society in general. For the public infrastructure of financial blockchains, this discussion encompasses the privacy of the originator of a transaction broadcasted on the underlying peer-to-peer network. Adaptive diffusion is an approach to expose an alternative source of a message to attackers. However, this approach assumes an unsuitable attacker model and a non-realistic network model for current peer-to-peer networks on the Internet. We transform adaptive diffusion into a new statistical privacy-preserving broadcast protocol for realistic current networks. We model a class of unstructured peer-to-peer networks as organically growing graphs and provide models for other classes of such networks. We show that the distribution of shortest paths can be modelled using a normal distribution N (µ, σ2). We determine statistical estimators for µ, σ via multivariate models. The model behaves logarithmic over the number of nodes n and proportional to an inverse exponential over the number of added edges per node k. These results facilitate the computation of optimal forwarding probabilities during the dissemination phase for maximum privacy, with participants having only limited information about network topology. Copyright © 2021, The Authors. All rights reserved.

关键词： Peer to peer networks

Towards multiple ontology merging with CoMerger 19

学校读者我要写书评

暂无评论

Towards multiple ontology merging with CoMerger

19th International Semantic Web Conference on Demos and Industry Tracks: From Novel Ideas to Industrial Practice, ISWC-Posters 2020

作者： Babalou, Samira Konig-Ries, Birgitta Heinz-Nixdorf Chair for Distributed Information Systems Institute for Computer Science Friedrich Schiller University Jena Germany

To obtain a knowledge graph representing a domain of interest, it is often necessary to combine several, independently developed ontologies. Existing approaches are mostly limited to binary merge and lack scalability. This paper presents the development of an efficient multiple ontologies merging method, CoMerger. For efficient processing, rather than directly merging a large number of ontologies, we group related concepts across ontologies into partitions and merge first within and then across those partitions. Experiments on real-life datasets confirm the feasibility of our approach and demonstrate its superiority over binary strategies. Our implementation is available through a live web portal. © 2020 CEUR-WS. All rights reserved.

关键词： Ontology

Partitioned deep learning of fluid-structure interaction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Totounferoush, Amin Schumacher, Axel Schulte, Miriam Institute for Parallel and Distributed Systems Department of Computer Science University of Stuttgart Stuttgart70569 Germany

We present a partitioned neural network-based framework for learning of fluid-structure interaction (FSI) problems. We decompose the simulation domain into two smaller sub-domains, i.e., fluid and solid domains, and incorporate an independent neural network for each. A library is used to couple the two networks which takes care of boundary data communication, data mapping and equation coupling. Simulation data are used for training of the both neural networks. We use a combination of convolutional and recurrent neural networks (CNN and RNN) to account for both spatial and temporal connectivity. A quasi-Newton method is used to accelerate the FSI coupling convergence. We observe a very good agreement between the results of the presented framework and the classical numerical methods for simulation of 1d fluid flow inside an elastic tube. This work is a preliminary step for using neural networks to speed-up the FSI coupling convergence by providing an accurate initial guess in each time step for classical numerical solvers. © 2021, CC BY-NC-ND.

关键词： Deep neural networks

Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Özdenizci, Ozan Legenstein, Robert The Institute of Theoretical Computer Science Graz University of Technology Graz Austria Tu Graz Sal Dependable Embedded Systems Lab Silicon Austria Labs Graz Austria

Image restoration under adverse weather conditions has been of significant interest for various computer vision applications. Recent successful methods rely on the current progress in deep neural network architectural designs (e.g., with vision transformers). Motivated by the recent progress achieved with state-of-the-art conditional generative models, we present a novel patch-based image restoration algorithm based on denoising diffusion probabilistic models. Our patch-based diffusion modeling approach enables size-agnostic image restoration by using a guided denoising process with smoothed noise estimates across overlapping patches during inference. We empirically evaluate our model on benchmark datasets for image desnowing, combined deraining and dehazing, and raindrop removal. We demonstrate our approach to achieve state-of-the-art performances on both weather-specific and multi-weather image restoration, and experimentally show strong generalization to real-world test images. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

An Efficient Multi-band Infrared Small Objects Detection Approach for Low-Altitude Artificial Intelligence of Thing

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Peng, Yuhuai Wang, Jing Wang, Wenqian Liu, Lei Atiquzzaman, Mohammed Guizani, Mohsen Dustdar, Schahram Northeastern University School of Computer Science and Engineering Shenyang110819 China Zhiyuan Research Institute Hangzhou310024 China Northeastern University School of Computer Science and Engineering Shenyang110819 China Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China University of Oklahoma School of Computer Science NormanOK73019 United States Mohamed Bin Zayed University of Artificial Intelligence Department of Machine Learning Masdar United Arab Emirates Technische Universität Wien Distributed Systems Group Vienna1040 Austria

As a cutting-edge technology of low-altitude Artificial Intelligence of Thing (AIoT), UAV object detection significantly enhances the surveillance services capabilities of low-altitude AIoT. However, the difficulty of object detection is exacerbated by the high proportion of small and obscure objects in the captured images. To address the mentioned challenges, we present an efficient multi-band infrared small object detection approach for low-altitude intelligent surveillance services. Firstly, we propose the Multi-band infrared Image Fusion algorithm based on Cascade-GAN (MIF-CGAN), which produces fused images with high information entropy and high contrast. Then, the Transformer-based Multi-scale Dense Small Object Detection (MsDSOD) algorithm is proposed. The algorithm consists of the Global-Local Object Detection (G-LOD) network, the Object Dense Area Extraction (O-DAE) module, and the Weighted Boxes Fusion (WBF) module. It extracts small objects features at different scales from infrared images and fuses the global and local detection results to accurately identify small objects in dense scenes. Furthermore, compared to the traditional algorithms, the mean Average Precision (mAP) of MsDSOD is improved by 0.80% and the Average Precision in small object detection (APs) is improved by 0.72%. The proposed algorithm is optimally suited to deal with complex scenes with dense small objects and background occlusion. © 2014 IEEE.

关键词： Infrared imaging

Reputation systems for Supply Chains: The Challenge of Achieving Privacy Preservation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bader, Lennart Pennekamp, Jan Thevaraj, Emildeon Spiß, Maria Kanhere, Salil S. Wehrle, Klaus Cyber Analysis & Defense Fraunhofer FKIE Germany Communication and Distributed Systems RWTH Aachen University Germany Institute for Industrial Management RWTH Aachen University Germany School of Computer Science and Eng. University of New South Wales Australia

Consumers frequently interact with reputation systems to rate products, services, and deliveries. While past research extensively studied different conceptual approaches to realize such systems securely and privacy-preservingly, these concepts are not yet in use in business-to-business environments. In this paper, (1) we thus outline which specific challenges privacy-cautious stakeholders in volatile supply chain networks introduce, (2) give an overview of the diverse landscape of privacy-preserving reputation systems and their properties, and (3) based on well-established concepts from supply chain information systems and cryptography, we further propose an initial concept that accounts for the aforementioned challenges by utilizing fully homomorphic encryption. For future work, we identify the need of evaluating whether novel systems address the supply chain-specific privacy and confidentiality needs. Copyright © 2023, The Authors. All rights reserved.

关键词： Supply chains

A sustainable and secure load management model for green cloud data centres

学校读者我要写书评

暂无评论

Scientific Reports 2023年第1期13卷 1-22页

作者： Saxena, Deepika Singh, Ashutosh Kumar Lee, Chung-Nan Buyya, Rajkumar Department of Computer Applications National Institute of Technology Haryana Kurukshetra 136119 India Department of Computer Science Goethe University Frankfurt Germany Department of Computer Science and Engineering National Sun Yat-Sen University Kaohsiung 804201 Taiwan Cloud Computing and Distributed Systems (CLOUDS) Lab School of Computing and Information Systems University of Melbourne Melbourne 804201 Australia

The massive upsurge in cloud resource demand and inefficient load management stave off the sustainability of Cloud Data Centres (CDCs) resulting in high energy consumption, resource contention, excessive carbon emission, and security threats. In this context, a novel Sustainable and Secure Load Management (SaS-LM) Model is proposed to enhance the security for users with sustainability for CDCs. The model estimates and reserves the required resources viz., compute, network, and storage and dynamically adjust the load subject to maximum security and sustainability. An evolutionary optimization algorithm named Dual-Phase Black Hole Optimization (DPBHO) is proposed for optimizing a multi-layered feed-forward neural network and allowing the model to estimate resource usage and detect probable congestion. Further, DPBHO is extended to a Multi-objective DPBHO algorithm for a secure and sustainable VM allocation and management to minimize the number of active server machines, carbon emission, and resource wastage for greener CDCs. SaS-LM is implemented and evaluated using benchmark real-world Google Cluster VM traces. The proposed model is compared with state-of-the-arts which reveals its efficacy in terms of reduced carbon emission and energy consumption up to 46.9% and 43.9%, respectively with improved resource utilization up to 16.5%. © 2023, The Author(s).

关键词：