检索结果-内蒙古大学图书馆

21st International Conference on algorithms and Architectures for Parallel Processing (ICA3PP)

作者： Moumni, Hatem Hamdi-Larbi, Olfa Univ Tunis El Manar Fac Sci Tunis LIPS FST Lab Tunis 2092 Tunisia Taibah Univ Coll Business Madinah Medina Saudi Arabia

ISBN: (纸本)9783030953881;9783030953874

Positive or Non-negative Matrix Factorization (NMF) is an effective technique and has been widely used for Big Data representation. It aims to find two non-negative matrices W and H whose product provides an optimal approximation to the original input data matrix A, such that A approximate to W * H. Although, NMF plays an important role in several applications, such as machine learning, data analysis and biomedical applications. Due to the sparsity that is caused by missing information in many high-dimension scenes (e.g., social networks, recommender systems and DNA gene expressions), the NMF method cannot mine a more accurate representation from the explicit information. Therefore, the Sparse Non-negative Matrix Factorization (SNMF) can incorporate the intrinsic geometry of the data, which is combined with implicit information. Thus, SNMF can realize a more compact representation for the sparse data. In this paper, we study the Sparse Non-negative Matrix Factorization (SNMF). We use Multiplicative Update algorithm (MUA) that computes the factorization by applying update on both matrices W and H. Accordingly, to address these issue, we propose a two models to implement a parallel version of SNMF on GPUs using NVIDIA CUDA framework. To optimize SNMF, we use cuSPARSE optimized library to compute the algebraic operations in MUA where sparse matrices A, W and H are stored in Compressed Sparse Row (CSR) format. At last, our contribution is validated through a series of experiments achieved on two input sets i.e. a set of randomly generated matrices and a set of benchmark matrices from real applications with different sizes and densities. We show that our algorithms allow performance improvements compared to baseline implementations. The speedup on multi-GPU platform can exceed 11x as well as the Ratio can exceed 91%.

关键词： SNMF unsupervised learning algorithm Multiplicative update algorithm Sparse matrix Compressed formats Optimization

来源：评论

学校读者我要写书评

暂无评论

unsupervised Anomaly Detection via DBSCAN for KPIs Jitters in Network Managements

引用

Computers, Materials & Continua 2020年第2期62卷 917-927页

作者： Haiwen Chen Guang Yu Fang Liu Zhiping Cai Anfeng Liu Shuhui Chen Hongbin Huang Chak Fong Cheang College of Computer Science National University of Defense TechnologyChangshaChina School of Data Science and Computer Science Sun Yat-sen UniversityGuangzhouChina College of Information and Engineering Central South UniversityChangshaChina Faculty of Information Technology Macao University of Science and TechnologyMacao

For many Internet companies,a huge amount of KPIs(e.g.,server CPU usage,network usage,business monitoring data)will be generated every *** to closely monitor various KPIs,and then quickly and accurately detect anomalies in such huge data for troubleshooting and recovering business is a great challenge,especially for unlabeled *** generated KPIs can be detected by supervised learning with labeled data,but the current problem is that most KPIs are *** is a time-consuming and laborious work to label anomaly for company *** an unsupervised model to detect unlabeled data is an urgent need at *** this paper,unsupervised learning DBSCAN combined with feature extraction of data has been used,and for some KPIs,its best F-Score can reach about 0.9,which is quite good for solving the current problem.

关键词： Anomaly detection KPIs unsupervised learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Introducing a new tool to derive animal behaviour from GPS data without ancillary data: The red-footed falcon in Italy as a case study

引用

ECOLOGICAL INFORMATICS 2022年 69卷

作者： Ferrarini, Alessandro Gustin, Marco Conservat Dept Birdlife Italy Lipu Lega Italiana Protez Uccelli Via Udine 3-a I-43100 Parma Italy

Animal monitoring is a key stage in the process of understanding individual behaviour and social dynamics that characterize populations and species. Recent technological advances allow to collect large data sets on animal movement. Using such data to compute activity patterns is very challenging without expensive field surveys, video analyses and/or accelerometer sensors. We introduce here a new tool (UABE: unsupervised Animal Behaviour Examiner) that makes use of a set of methodologies (if-then-else rules, sensitivity analyses, Markov chains) to interpret GPS data in behavioural terms under worst case conditions, i.e. in absence of ancillary data. The UABE is halfway between unsupervised inductive (clustering or segmentation) and deductive (expert-based) methods. As a case study, we applied the UABE to the investigation of the red-footed falcons' activity at nest at the two largest breeding colonies in Italy during the chick-rearing period. By using accurate GPS data-loggers, we tracked four adults in June-July 2019 and 2020, and collected 5840 GPS points. Activity at nest occupied one fourth of the red-footed falcons' day, with substantial differences between months and between daytime and night-time. On an hourly basis, clear temporal patterns of activity at nest emerged. Through the combined use of frequency and continuity of the studied behaviour, the UABE also allowed to raise plausible hypotheses for the reasons behind birds' activity at nest at specific times of day. The UABE supports the creation of unsupervised ethograms of both stationary (e.g., standing at nest or roost, hovering/perching) and nonstationary (e.g., flight, walking) activity patterns. It can be applied to any species regardless of the tracking instrument used.

关键词： Behavioural ecology Biotelemetry If-then-else rules Markov chains Sensitivity analysis unsupervised learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine learning for inferring animal behavior from location and movement data

引用

ECOLOGICAL INFORMATICS 2019年 49卷 69-76页

作者： Wang, Guiming Mississippi State Univ Dept Wildlife Fisheries & Aquaculture Mail Stop 9690 Mississippi State MS 39762 USA

Movement ecology has rapidly advanced owing to recent developments of animal-attached devices and wide applications of sophisticated statistical and machine learning techniques in analysis of animal movement data. Global Positioning System (GPS) transmitters used for estimating animal locations and tri-axial accelerometers used for measuring the 3-dimensional accelerations of animal's motion aid researchers in collecting location and locomotion data at fine spatial and temporal scales. Machine learning and other advanced statistical methods bridge conceptual models to data, providing insights into ecological and physiological mechanisms underlying animal behavior and movements. This study reviews the general principles and applications of state space models, hidden Markov models, random forests, and support vector machines in the inference of animal behavior from movement data. unsupervised learning algorithms, including Bayesian state space models implemented for robust correlated random walk models and hidden Markov models, help infer different behavioral modes using GPS location data. State space models can account for measurement error in GPS locations and estimate the true locations of animals;however, without including movement-state switching, state space models do not infer behavioral modes directly. On the contrary, hidden Markov models estimate the probabilities that animals switch between different behavioral modes. Nevertheless, hidden Markov models neither directly estimate animal locations nor account for measurement error explicitly. Supervised learning algorithms integrate data on locations and directional accelerations with synchronized behavioral observations (i.e., labels) to classify behaviors to pre-defined behavioral categories. Unlike unsupervised learning, supervised learning requires behavioral observations to label locations and accelerometer data to train the learning algorithms. However, behavioral observations synchronized with relocatio

关键词： Behavioral classification Computational ecology Hidden Markov model Movement ecology State space model Supervised learning algorithm unsupervised learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Customer Service Automatic Answering System Based on Natural Language Processing 2019

Customer Service Automatic Answering System Based on Natural...

引用

International Symposium on Signal Processing Systems (SPSS) / International Conference on Natural Language Processing (ICNLP)

作者： Gong, Xia Kong, Xiangyi Zhang, Zhujun Tan, Lin Zhang, Zixiong Shao, Bing Beihang Univ Beijing 100191 Peoples R China Beijing Inst Technol Beijing 100081 Peoples R China Beijing Foreign Studies Univ Beijing 100089 Peoples R China

ISBN: (纸本)9781450362412

With the rapid development of Internet, information grows explosively, and traditional search engine have failed to meet the needs of users. This paper proposes a customer service automatic answering system with a high-quality knowledge base. First of all, based on unsupervised learning algorithm, this system extracts the question and answer pairs from documents and store them in the knowledge base. Then employing semantic analysis module and the method of Natural Language Processing (NLP), this system gains the meaning of the customers' question accurately, then retrieve the knowledge base and return a high-resolution answer to the user. Furthermore, we construct a dialog management module, which makes reasonable guesses on issues that cannot be matched, and records the dialogue history so that the question-answering system can give more intelligent responses. Finally, due to the diversity of the document structure and the complexity of Chinese natural language, this system adds an edifying function that can add, delete, and modify the question and answer pair in the knowledge. Therefore, our customer service automatic answering system can be more intelligent and efficient than the existing question and answer system.

关键词： Natural Language Processing unsupervised learning algorithm Question-answering system Customer-service

来源：评论

学校读者我要写书评

暂无评论

Aircraft fuel burn performance study: A data-enhanced modeling approach

引用

TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT 2018年 65卷 574-595页

作者： Yanto, Jefry Liem, Rhea P. HKUST Hong Kong Peoples R China

The rapid growth in commercial air transportation and the price volatility of fuel push for fuel reduction policy to be implemented. Some changes in technology (e.g., improved designs of aircraft and engines), operations (e.g., improved flight routes), or both have shown promising results on fuel reduction in air transportation. Several candidate policy scenarios related to fuel consumption need to be evaluated, which call for fast, efficient, yet accurate fuel burn computation methods, in particular to compute the total aggregate fuel burn given a set of flight missions. While fuel burn evaluation models exist, some are computationally expensive or built based on data that might be outdated. Others suffer from the lack of accuracy due to simplification assumptions and computations. As such, we develop a fuel burn evaluation model by combining a low-fidelity physics-based model with aircraft operation and performance data. For a more accurate fuel burn computation, especially for the climb and descent segments, we integrate the state-of-the-art Base of Aircraft Data (BADA) trajectory simulation results into the fuel burn model. This model offers enhanced accuracy compared to low-fidelity models, yet retains their computational efficiency. In this paper, a fuel burn database corresponding to 40 aircraft types is generated based on the Bureau of Transportation Statistics (BTS) flight missions' database 2015. A sample-based linear regression model is then derived for each aircraft type. The validation results show that the model can estimate the total aggregate fuel burn for each aircraft type with less than 1% prediction errors using flight mission data from 2016, and less than 6% prediction errors when compared with the actual fuel burn data corresponding to three commercial airlines in 2015 and 2016. The developed models are then used to investigate the two common simplifying assumptions in fuel burn evaluation, namely the cruise-only approximation and similar aircr

关键词： Aircraft fuel burn Air transportation Flight mission analysis Regression modeling Data-enhanced modeling unsupervised learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Customer Service Automatic Answering System Based on Natural Language Processing

Customer Service Automatic Answering System Based on Natural...

引用

作者： Xia GONG Zhujun ZHANG Zixiong ZHANG Xiangyi KONG Lin TAN Bing SHAO Beihang University Beijing Institute of Technology Beijing Foreign Studies University

With the rapid development of Internet, information grows explosively, and traditional search engine have failed to meet the needs of users. This paper proposes a customer service automatic answering system with a high-quality knowledge base. First of all,based on unsupervised learning algorithm, this system extracts the question and answer pairs from documents and store them in the knowledge base. Then employing semantic analysis module and the method of Natural Language Processing(NLP), this system gains the meaning of the customers' question accurately, then retrieve the knowledge base and return a high-resolution answer to the user. Furthermore, we construct a dialog management module, which makes reasonable guesses on issues that cannot be matched, and records the dialogue history so that the questionanswering system can give more intelligent responses. Finally,due to the diversity of the document structure and the complexity of Chinese natural language, this system adds an edifying function that can add, delete, and modify the question and answer pair in the knowledge. Therefore, our customer service automatic answering system can be more intelligent and efficient than the existing question and answer system.

关键词： Natural Language Processing unsupervised learning algorithm Question-answering system Customer-service

来源：评论

学校读者我要写书评

暂无评论

Restricted Boltzmann machine-based cognitive protocol for secure routing in software defined wireless networks

引用

IET NETWORKS 2017年第6期6卷 162-168页

作者： MohanaPriya, Pitchai Shalinie, Selvaraj Mercy Thiagarajar Coll Engn Dept Comp Sci & Engn Madurai Tamil Nadu India

Secure and stable routing is a critical issue in a conventional network environment, as the control and data planes are integrated. An intelligent routing is highly essential to provide an attack free network to its intended users. The programmable software defined network is an emerging network paradigm in which the security policies and the forwarding rules are implemented in the controller via North Bound Interface. This study incorporates a cognitive neural network learning algorithm namely restricted Boltzmann machine (RBM), to detect the routing-based distributed denial of service attacks in dynamic source routing (DSR) protocol. RBM is a stochastic and unsupervised learning algorithm that self-learns the network conditions by using its reasoning capability and segregates malicious routes in the route cache using context-aware trust metrics such as reputation and energy consumption implemented in North Bound Application Programming Interface. The results show that a cognitive DSR protocol provides secure routing by increased packet delivery ratio, decreased end-to-end delay, reduced energy consumption and accurate detection of malicious routes compared with the conventional DSR protocol.

关键词： Boltzmann machines routing protocols telecommunication security telecommunication computing software radio radio networks unsupervised learning cache storage application program interfaces stochastic processes restricted Boltzmann machine secure routing software defined wireless networks network environment data planes control planes intelligent routing attack free network security policies forwarding rules cognitive neural network learning algorithm RBM routing-based distributed denial of service attack detection dynamic source routing protocol unsupervised learning algorithm stochastic learning algorithm route cache end-to-end delay packet delivery ratio cognitive DSR protocol north bound application programming interface energy consumption context-aware trust metrics

来源：评论

学校读者我要写书评

暂无评论

Data Analytics-Based Anomaly Detection in Smart Distribution Network

Data Analytics-Based Anomaly Detection in Smart Distribution...

引用

International Conference on High Voltage Engineering and Power Systems (ICHVEPS)

作者： Saad, Akram Sisworahardjo, N. Univ Tennessee Dept Elect Engn Chattanooga TN 37403 USA

ISBN: (纸本)9781538609453

Monitoring energy consumption and diagnosing abnormal behavior will enable utilities to introduce strategies to improve system resiliency, stability, and to meet energy efficiency targets. The deployment of advanced metering infrastructure (AMI) enables utilities to collect various raw data from its customers and networks. This paper presents contextual anomaly detection algorithm to detect irregular power consumption and visualize anomaly scores using unsupervised learning algorithm and temporal context generated from meter readings. The proposed algorithm computes an anomaly score for each user by considering historical consumption data. The anomaly score for a user is then adjusted by analyzing other contextual variables such as seasonal variation day of the week and other users with the same historical pattern. The implementation on real-world data set provided by power utility company shows a high performance of the proposed algorithm.

关键词： contextual anomaly detection unsupervised learning algorithm temporal context

来源：评论

学校读者我要写书评

暂无评论

unsupervised learning algorithm for high-speed defect detection in rails by laser/air-coupled non-contact ultrasonic testing

Unsupervised learning algorithm for high-speed defect detect...

引用

Smart Structures and Materials 2006 Conference

作者： Rizzo, Piervincenzo Coccia, Stefano di Scalea, Francesco Lanza Bartolia, Ivan Fateh, Mahmood Univ Calif San Diego Dept Struct Engn NED & Struct Hlth Monitoring Lab 9500 Gilman DrMC 0085 La Jolla CA 92093 USA

ISBN: (纸本)0819462276

Recent train accidents and associated direct and indirect costs including cost of repair of equipment and infrastructure as well as delay and death/injury costs, have reaffirmed the need for developing rail defect detection systems more effective than those used today. In fact, rail defect detection has been identified as a priority area in the U.S. Federal Railroad Administration 5-year R&D plan. This paper proposes an unsupervised learning algorithm for defect detection in rails. The algorithm is used in a non-contact inspection system that is targeted to the detection of transverse-type cracks in the rail head (including transverse fissures and detail fractures), notoriously the most dangerous flaws in rails. The system uses ultrasonic guided waves that are generated by a pulsed laser and are detected by air-coupled sensors positioned as far away as 76 mm. (3 '') from the top of rail head. The inspection ranges is at least 500 mm (20 '') for surface head cracks as shallow as I mm. Fast data output is achieved by processing the ultrasonic defect signatures by Wavelet Transform algorithms. The features extracted after wavelet processing are analyzed by a learning algorithm based on novelty detection. This algorithm attempts to detect the presence of damage despite the normal variations in ultrasonic signal features that may be found in a field test.

关键词： non-contact rail testing wavelet transforms unsupervised learning algorithm

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：