检索结果-内蒙古大学图书馆

Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Yi Garg, Sahil Nie, Jiangtian Zhang, Yang Xiong, Zehui Kang, Jiawen Shamim Hossain, M. School of Data Science and Technology Heilongjiang University Harbin China Electrical Engineering Department École de technologie supérieure Uni-versité du Québec Montréal Canada Energy Research Institute Interdisciplinary Graduate Programme School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Technology Wuhan University of Technology China Alibaba-NTU Joint Research Institute School of Computer Science and Engineering NTU Singapore Singapore Energy Research Institute Nanyang Technological University Singapore Department of Software Engineering College of Computer and Information Sciences King Saud University Saudi Arabia

Since edge device failures (i.e., anomalies) seriously affect the production of industrial products in Industrial IoT (IIoT), accurately and timely detecting anomalies is becoming increasingly important. Furthermore, data collected by the edge device may contain the user’s private data, which is challenging the current detection approaches as user privacy is calling for the public concern in recent years. With this focus, this paper proposes a new communication-efficient on-device federated learning (FL)-based deep anomaly detection framework for sensing time-series data in IIoT. Specifically, we first introduce a FL framework to enable decentralized edge devices to collaboratively train an anomaly detection model, which can improve its generalization ability. Second, we propose an Attention Mechanism-based Convolutional Neural Network-Long Short Term Memory (AMCNN-LSTM) model to accurately detect anomalies. The AMCNN-LSTM model uses attention mechanism-based CNN units to capture important fine-grained features, thereby preventing memory loss and gradient dispersion problems. Furthermore, this model retains the advantages of LSTM unit in predicting time series data. Third, to adapt the proposed framework to the timeliness of industrial anomaly detection, we propose a gradient compression mechanism based on Top-k selection to improve communication efficiency. Extensive experiment studies on four real-world datasets demonstrate that the proposed framework can accurately and timely detect anomalies and also reduce the communication overhead by 50% compared to the federated learning framework that does not use gradient compression scheme. Copyright © 2020, The Authors. All rights reserved.

关键词： Anomaly detection

Predicting online item-choice behavior: A shape-restricted regression approach

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Nishimura, Naoki Sukegawa, Noriyoshi Takano, Yuichi Iwanaga, Jiro Graduate School of Systems and Information Engineering University of Tsukuba Ibaraki305-8577 Japan Recruit Lifestyle Co. Ltd. Tokyo100-6640 Japan Department of Information and Computer Technology Tokyo University of Science Tokyo125-8585 Faculty of Engineering Information and Systems University of Tsukuba Ibaraki305-8577 Doctoral Program in Policy and Planning Sciences University of Tsukuba Ibaraki305-8577 Erdos Inc. Kanagawa222-0033

This paper examines the relationship between user pageview (PV) histories and their item-choice behavior on an e-commerce website. We focus on PV sequences, which represent time series of the number of PVs for each user-item pair. We propose a shape-restricted optimization model that accurately estimates item-choice probabilities for all possible PV sequences. This model imposes monotonicity constraints on item-choice probabilities by exploiting partial orders for PV sequences, according to the recency and frequency of a user's previous PVs. To improve the computational efficiency of our optimization model, we devise efficient algorithms for eliminating all redundant constraints according to the transitivity of the partial orders. Experimental results using real-world clickstream data demonstrate that our method achieves higher prediction performance than that of a state-of-the-art optimization model and common machine learning methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph theory

A framework for ensemble classification and sensitivity analysis in privacy preserving data mining

学校读者我要写书评

暂无评论

International Journal of Computational Systems engineering 2019年第5-6期5卷 260-276页

作者： Chandrakanth, P. Anbarasi, M.S. Under Quality Improvement Programme Department of Computer Science and Engineering Pondicherry Engineering College Pondicherry605014 India Department of Information Technology Pondicherry Engineering College Pondicherry605014 India

The perturbation mechanism for data streams is a challenging task. In the emerging world, data is erupting from various sources. The core applications need care on the data streams for further analysis and experimentation. As the micro data available with the core applications shall not be revealed to the public without taking any chance of breach, the perturbation challenges the analysis to get through the like results as of on the original datasets. In this paper, we have applied a concept of Perlin noise to distract the original data from the eyes of the analysts, however allowing them to perform their activities well. Applying security dynamically on such data is a challenging task. This paper deals about the concepts of generation of smooth noise and syntactic perturbation mechanism on the selective tuples as selective perturbation. © 2019 Inderscience Enterprises Ltd.

关键词： Sensitivity analysis

Ccdh: Complexity Based Causal Discovery of Hidden Common Cause (and Other Beasts) in Time Series

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Varga, Bálint Stippinger, Marcell Benkő, Zsigmond Fabó, Dániel Halász, Péter Erőss, Loránd Somogyvári, Zoltán Telcs, András Department of Computational Sciences Wigner Research Centre for Physics BudapestH-1121 Hungary János Szentágothai Doctoral School of Neurosciences Semmelweis University BudapestH-1085 Hungary Epilepsy Center Juhász Pál National Institute of Clinical Neurosciences BudapestH-1145 Hungary EPI-HELP BudapestH-1012 Hungary Department of Functional Neurosurgery National Institute of Clinical Neurosciences BudapestH-1145 Hungary Faculty of Information Technology and Bionics Péter Pázmány Catholic University BudapestH-1083 Hungary Neuromicrosystems ltd. BudapestH-1113 Hungary Department of Computer Science and Information Theory Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics BudapestH-1111 Hungary Department of Quantitative Methods University of Pannonia Faculty of Business and Economics VeszprémH-8200 Hungary

Non-interventional causal discovery is a challenging task. This is particularly true for causal relations of dynamic systems with chaotic attractors. The known solutions are data-intensive and cannot detect a hidden common driver (common cause or confounder). We propose a new method which eliminates both *** method is based on Takens' embedding theorem and complexity of the rank order patterns of the embedded series measured by the compressibility usingnon-sequential recursive pair substitution. The method works on shortsamples and is capable of detecting all kinds of causal connection (including hidden common cause). The newmethod is validated on synthetic data sets and applied to two types of humanelectrophysiological data from epileptic patients. In bothcases, the method revealed self-consistent, contradiction-free and biologically relevant causal connections between the investigatedareas. Thus the method may provide additional indication for the location ofintervention for the decision making medical panel. Given the method advantages and simplicity it might be applied in many other scientific and practical areas with success. © 2022, The Authors. All rights reserved.

关键词： Time series

Utilization of GPS Technology in The Maritime Sector on Motor Sailing Yachts

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental science 2021年第1期698卷

作者： Melani Quintania Danny Faturachman T. Husain Bayu Pasupati Ahmad Taufik Management Department Faculty of Economy Darma Persada University Indonesia Marine Engineering Department Faculty of Marine Technology Darma Persada University Indonesia Information System Department School of Management and Computer Science STMIK Widuri Jakarta – Indonesia and Student of Doctoral Management YAI Persada University Indonesia Student of Doctoral Management YAI Persada University Indonesia Information System Department School of Management and Computer Science STMIK Widuri Jakarta – Indonesia

The utilization of technology only aims to be fast, precise, and accurate in each implementation and find a better solution at that time in several sectors. This study aims to identify the use of Global Positioning Technology (GPS) technology to track the position of the motor sailing yachts, specifically with the features used on a device or smart-phone during a trip or expedition. This research uses a type of applied research to solve problems that are faced clearly, and the results can be used as a basis for solving corrective steps. The results found that GPS-Technology on motor sailing yachts in 'Pelayaran Rakyat' maritime can receive coordinates point and then send these coordinates to the vessel-tracking systems to determine the position of the motor sailing yachts between users.

关键词：

Scalable authentication and optimal flooding in a quantum network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Solomons, Naomi R. Fletcher, Alasdair I. Aktas, Djeylan Venkatachalam, Natarajan Wengerowsky, Sören Lončarić, Martin Neumann, Sebastian P. Liu, Bo Samec, Željko Stipčević, Mario Ursin, Rupert Pirandola, Stefano Rarity, John G. Joshi, Siddarth Koduru Quantum Engineering Technology Labs Quantum Engineering Centre for Doctoral Training Centre for Nanoscience and Quantum Information University of Bristol Bristol United Kingdom Department of Computer Science University of York YorkYO10 5GH United Kingdom Quantum Engineering Technology Labs H. H. Wills Physics Laboratory Department of Electrical and Electronic Engineering University of Bristol Merchant Venturers Building Woodland Road BristolBS8 1UB United Kingdom Vienna Austria Barcelona Institute of Science and Technology Castelldefels Barcelona08860 Spain Photonics and Quantum Optics Research Unit Center of Excellence for Advanced Materials and Sensing Devices Rud¯er Bošković Institute Zagreb Croatia College of Advanced Interdisciplinary Studies NUDT Changsha410073 China

The global interest in quantum networks stems from the security guaranteed by the laws of physics. Deploying quantum networks means facing the challenges of scaling up the physical hardware and, more importantly, of scaling up all other network layers and optimally utilising network resources. Here we consider two related protocols, their experimental demonstrations on an 8-user quantum network test-bed, and discuss their usefulness with the aid of example use cases. First, an authentication transfer protocol to manage a fundamental limitation of quantum communication – the need for a pre-shared key between every pair of users linked together on the quantum network. By temporarily trusting some intermediary nodes for a short period of time ( Copyright © 2021, The Authors. All rights reserved.

关键词： Network layers

Adaptive Spectrum Handoff Scheme in Cognitive Radio Ad-Hoc Networks

学校读者我要写书评

暂无评论

Adaptive Spectrum Handoff Scheme in Cognitive Radio Ad-Hoc N...

2018 International Conference on Advances in Computing and Communication engineering, ICACCE 2018

作者： Shakeel, Atif Hussain, Riaz Iqbal, Adeel Latif, Irfan Malik, Shahzad A. Omoniwa, Babatunji Department of Electrical Engineering COMSATS Institute of Information Technology Islamabad Pakistan Computer Science Programme National Mathematical Centre Abuja Nigeria

ISBN: (纸本)9781538644850

Cognitive radio improves the spectrum utilization by permitting the secondary users in accessing the underutilized spectrum band of the primary network in an opportunistic manner. Spectrum handoff is considered as one of the important phases in cognitive cycle, where the secondary users have to vacate the occupied channel on the appearance of primary user for maintaining the QoS requirements of both primary and secondary communication. It also helps secondary users to find an appropriate target channel to resume its undone transmission either through switching handoff scheme or non-switching handoff process. The process of spectrum handoff becomes more critical in cognitive radio ad-hoc networks, as the coordination among the secondary users is a challenging task. This research presents an analytical model for the performance evaluation of secondary users, in terms of extended data delivery time for both switching and non-switching spectrum handoff in ad-hoc network environment. Channel rendezvous among secondary users is achieved usings of common control channel. The results achieved are based on preemptive resume priority M/M/1 queuing network, considering varying number of secondary users, their average arrival and service time. An adaptive spectrum handoff is proposed based on the primary user traffic intensity, number of SU and total number of primary channels. © 2018 IEEE.

关键词： Switching

Framerank: A text processing approach to video summarization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lei, Zhuo Zhang, Chao Zhang, Qian Qiu, Guoping International Doctoral Innovation Center University of Nottingham Ningbo China School of Computer Science University of Nottingham Ningbo China College of Information Engineering Guangdong Key Lab for Intellignet Information Processing Shenzhen University China School of Computer Science University of Nottingham United Kingdom

Video summarization has been extensively studied in the past decades. However, user-generated video summarization is much less explored since there lack large-scale video datasets within which human-generated video summaries are unambiguously defined and annotated. Toward this end, we propose a user-generated video summarization dataset - UGSum52 - that consists of 52 videos (207 minutes). In constructing the dataset, because of the subjectivity of usergenerated video summarization, we manually annotate 25 summaries for each video, which are in total 1300 summaries. To the best of our knowledge, it is currently the largest dataset for user-generated video summarization. Based on this dataset, we present FrameRank, an unsupervised video summarization method that employs a frameto-frame level affinity graph to identify coherent and informative frames to summarize a video. We use the Kullback-Leibler(KL)-divergence-based graph to rank temporal segments according to the amount of semantic information contained in their frames. We illustrate the effectiveness of our method by applying it to three datasets SumMe, TVSum and UGSum52 and show it achieves state-of-the-art results. Copyright © 2019, The Authors. All rights reserved.

关键词： Video recording

Digital Dictionary Using Binary Search Algorithm 1

学校读者我要写书评

暂无评论

Digital Dictionary Using Binary Search Algorithm

1st International Conference on computer science and Applied Mathematic, ICCSAM 2018

作者： Fitrian, Riski Muhamad Taufik, Insan Ramadhan, Muhammad Sabir Mulyani, Neni Hutahaean, Jeperson Sitio, Arjon Samuel Sihotang, Hengki Tamando Teknik Informatika STMIK Pelita Nusantara Medan Sumatera Utara Indonesia Doctoral Program Vocational Technology Education Postgraduate Engineering Faculty Padang State University Padang West Sumatera Indonesia Sistem Informasi STMIK Royal Kisaran Sumatera Utara Indonesia Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

Digital Dictionary of computer and Network engineering can be used in the learning process of computer and nerwork enginering students. Dictionaries are generally book-shaped is hard to carry because of their thick and heavy, now can be accessed anywhere by development of web technology. Digital dictionaries can be accessed through computers, laptops dan cellphones, this is make student easily in learning process. The digital dictionary can not only be used by students of computer and network engineering, but can also by general public, as long as you have an internet connection, anyone can be use this digital dictionaries. The main process in this digital dictionary is the search process. Binary search algorithm used in the search process of binary search algoritm. Binary search algoritm search is applied to word search in this digital dictionary, because this algoritm is intended for sequintal data. Program language that will be used to build this digital dictionary is PHP and MySQL. © Published under licence by IOP Publishing Ltd.

关键词： Students