检索结果-内蒙古大学图书馆

Indoor positioning system based on particle swarm optimization algorithm

MEASUREMENT 2019年 134卷 908-913页

作者： Guo, Hang Li, Huixia Xiong, Jian Yu, Min Nanchang Univ Sch Resources Environm & Chem Engn Key Lab Poyang Lake Environm & Resource Utilizat Minist Educ Nanchang 330031 Jiangxi Peoples R China Nanchang Univ Nanchang 330031 Jiangxi Peoples R China Univ New Brunswick Dept Geodesy & Geomat Engn Fredericton NB Canada Jiangxi Normal Univ Nanchang 330022 Jiangxi Peoples R China

In recent years, wireless sensor networks localization becomes a crucial method in the indoor positioning. Following the frontiers of technology, we studied on ZigBee wireless sensor network. Since the parameters of the path loss model are difficult to be estimated by the ordinary methods, the Particle swarm optimization (PSO) method is proposed in this paper to simulate the parameter estimation in the indoor environment. The Texas Instruments CC2530 chip was also taken to build a ZigBee wireless sensor network. The data collected from ZigBee wireless sensor network experiment could be used to estimate the model parameters. PSO algorithm for fitting the signal attenuation curve removed the poor experimental data, and the output model fit well with the signal attenuation curve. Experimental results demonstrate that the PSO algorithm works well, clear, easy to understand, and has a high reliability. Using the parametric model to locate the user's position, and with the weighted k-nearest neighbor algorithm, the two-dimensional (2D) positioning was improved effectively. The standard deviation of 2D positioning is 1.15 m, so the model has practical value. Through the experiment and analyzing the data, it is verified that the proposed PSO algorithm in this paper is better than the previous methods we presented. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： ZigBee Path loss model Particle swarm optimization algorithm Parameter estimation k-nearest neighbor algorithm

来源：评论

学校读者我要写书评

暂无评论

Correlation-based k-nearest neighbor algorithm

Correlation-based K-Nearest Neighbor Algorithm

引用

2012 IEEE 3rd International Conference on Software Engineering and Service Science（ICSESS 2012）

作者： Xinran Li International School Beijing University of Posts and Telecommunications Beijing ChinaChenhui Xiang International School Beijing University of Posts and Telecommunications Beijing China

Data classification is an important task of data mining,and developing high-powered classification algorithm is one of the key procedures for data *** paper provides an improved k-nearest neighbor algorithm-correlation-based k-nearest neighbor *** new algorithm makes data classification base on the correlation calculation,and uses a modified probability to improve the computational speed and prediction *** experimental results show that the correlation-based k-nearest neighbor algorithm is more suitable to classify massive high-dimensional data sets while comparing with traditional k-nearest neighbor algorithm.

关键词： component k-nearest neighbor algorithm correlation data classification

来源：评论

学校读者我要写书评

暂无评论

Automatic Modulation Classification for DVB-S2 System in Fading Channels 10

Automatic Modulation Classification for DVB-S2 System in Fad...

引用

10th International Scientific Conference on Communication and Information Technologies (kIT)

作者： Hung Nguyen Manh Richterova, Marie Vrsecka, Marketa Univ Def Brno Dept Commun & Informat Syst Brno Czech Republic

ISBN: (纸本)9788080405755

The modulation recognition problem has been researched extensively in the past, but the classification in the presence of an unknown channel still exists a number of open issues. Interestingly, the number of the papers for the automatic modulation classification that are recommended in the digital video broadcasting - satellite - second generation standard is very limited. Motivated by this, the automatic modulation classification technique using the high order statistic approach was present in the paper. Signal model with raised cosine filter was employed for the modulation recognition. The classifier using the k-nearest neighbor algorithm with fourth- and sixth-order cumulants of the signal are investigated and analyzed. The performance of the algorithm is evaluated at a signal-to-noise ratio of 5 dB in additive white Gaussian noise and fading channels. Simulation results showed that the recognition rates were strongly affected by fading channels.

关键词： modulation classification k-nearest neighbor algorithm cumulants fading channels

来源：评论

学校读者我要写书评

暂无评论

Memory Bandwidth Prediction in NUMA Architecture Using Supervised Machine Learning 6

Memory Bandwidth Prediction in NUMA Architecture Using Super...

引用

6th Annual Conference on Computational Science and Computational Intelligence (CSCI)

作者： Salehian, Solmaz Lu, Lunjin Oakland Univ Dept Comp Sci & Engn Rochester MI 48309 USA

ISBN: (数字)9781728155845

ISBN: (纸本)9781728155845

In this paper, we predict memory bandwidth in NUMA architecture by implementing a method based on a supervised machine learning algorithm, the k-nearest neighbor (kNN) regression method. The main motivation for using kNN in our model is its flexibility to deal with different data types, its capability to incorporate small data size, its compatibility with irregular feature vectors and its simplicity. Memory bandwidth usage is expressed in terms of total transferred data per execution time, and it changes with respect to problem size and the number of processors. We consider problem size and the number of threads as kNN features. We measure memory bandwidth components, transferred data and execution time for different ranges of problem size and number of threads. Then, considering these values as training data, we predict memory bandwidth for other problem sizes and number of threads. The objective of this paper is not to reach accurate predictions for the memory bandwidth components, but rather to use these components to achieve an acceptable level of memory bandwidth prediction. We implement this approach in NUMA architecture and verify its accuracy by applying it to different ranges of regular and irregular high performance computing applications. Using this approach, we can predict memory bandwidth in both dimensions. The highest potential prediction error is observed when training data do not have enough knowledge of specific PSs and number of threads.

关键词： High Performance Computing Irregular application Regular application k-nearest neighbor algorithm

来源：评论

学校读者我要写书评

暂无评论

Indoor Location Method Based on Data Mining 19

Indoor Location Method Based on Data Mining

引用

Proceedings of the 2019 5th International Conference on Systems, Control and Communications

作者： Shan Hu Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781450372640

In the process of WLAN indoor location, the k nearest neighbor (kNN) algorithm is often used as a matching algorithm to locate fingerprints. The disadvantage is that the location accuracy is often not high. In order to solve this problem, this paper uses kNN algorithm to sort and filter the location fingerprints in the original online positioning stage, then joins Dansity-based clustering of applications with Noise (DBSCAN) algorithm to cluster, removes the interference coordinates in the location fingerprints, only retains the core position coordinates, and finally gets the location coordinates by regression prediction. Compared with other algorithms, the proposed kNNDB algorithm has a significant improvement in positioning accuracy.

关键词： Dansity-based clustering of applications with Noise Indoor localization Received signal strength k-nearest neighbor algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Optimization Decision of Plunger Gas Lift Operation Based on Data Driven

Research on Optimization Decision of Plunger Gas Lift Operat...

引用

IEEE Eurasia Conference on IOT, Communication and Engineering (IEEE ECICE)

作者： Tan Chaodong Song Wenrong Li Loulou Qin Peng Gao Zhaomin Hua Wu China Univ Petr Beijing Peoples R China Beijing Yadan Petr Technol Dev Co Ltd Beijing Peoples R China CNOOC EnerTech Drilling& Prod Co Tianjin Peoples R China

ISBN: (纸本)9781728125015

Aiming at poor effect caused by unreasonable production system based on the analysis of production characteristics in plunger gas lift, a data-driven model for optimal decision-making is established, and control method of production and optimal time of switching well and casing pressure value was optimized. The decision-making model in this paper is based on the massive data of plunger gas lift production. The data model and pattern matrix of 16 influencing factors are constructed. Considering the time and attribute weight, the Euclidean metric between the decision-making wells and the historical wells is calculated by k-nearest neighbor algorithm. According to the similarity weight, three most similar historical wells are selected. The reasonable operation parameters of the wells to be determined can be calculated by the easy average method. The experimental verification by recursive method shows that the shut-in time after decision-making adjustment is shortened, the production of water and gas is increased, and the drainage efficiency is obviously improved.

关键词： Plunger gas lift k-nearest neighbor algorithm Operation optimization Open-Shut in Time

来源：评论

学校读者我要写书评

暂无评论

Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system

引用

EXPERT SYSTEMS WITH APPLICATIONS 2018年 92卷 334-349页

作者： Plawiak, Pawel Cracow Univ Technol Inst Telecomp Fac Phys Math & Comp Sci Warsaw 24 StF-5 PL-31155 Krakow Poland

This article presents an innovative research methodology that enables the efficient classification of cardiac disorders (17 classes) based on ECG signal analysis and an evolutionary-neural system. From a social point of view, it is extremely important to prevent heart diseases, which are the most common cause of death worldwide. According to statistical data, 50 million people are at risk for cardiac diseases worldwide. The subject of ECG signal analysis is very popular. However, due to the great difficulty of the task undertaken, and high computational complexity of existing methods, there remains substantial work to perform. This research collected 1000 fragments of ECG signals from the MIH-BIH Arrhythmia database for one lead, MLII, from 45 patients. An original methodology that consisted of the analysis of longer (10-s) fragments of the ECG signal was used (an average of 13 times less classifications). To enhance the characteristic features of the ECG signal, the spectral power density was estimated (using Welch's method and a discrete Fourier transform). Genetic optimization of parameters and genetic selection of features were tested. Pre-processing, normalization, feature extraction and selection, cross-validation and machine learning algorithms (SVM, kNN, PNN, and RBFNN) were used. The best evolutionary-neural system, based on the SVM classifier, obtained a recognition sensitivity of 17 myocardium dysfunctions at a level of 90.20% (98 errors per 1000 classifications, accuracy = 98.85%, specificity = 99.39%, time for classification of one sample = 0.0023 [s]). Against the background of the current scientific literature, these results are some of the best results to date. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： ECG Biomedical signal processing and analysis Classification Machine learning algorithms Neural networks Support vector machine k-nearest neighbor algorithm Evolutionary-neural system Genetic algorithm Feature extraction and selection Discrete Fourier transform

来源：评论

学校读者我要写书评

暂无评论

Solving customer insurance coverage sales plan problem using a multi-stage data mining approach

引用

kYBERNETES 2018年第1期47卷 2-19页

作者： Abdi, Farshid khalili-Damghani, kaveh Abolmakarem, Shaghayegh Islamic Azad Univ Dept Ind Engn South Tehran Branch Tehran Iran

Purpose - Customer insurance coverage sales plan problem, in which the loyal customers are recognized and offered some special plans, is an essential problem facing insurance companies. On the other hand, the loyal customers who have enough potential to renew their insurance contracts at the end of the contract term should be persuaded to repurchase or renew their contracts. The aim of this paper is to propose a three-stage data-mining approach to recognize high-potential loyal insurance customers and to predict/plan special insurance coverage sales. Design/methodology/approach - The first stage addresses data cleansing. In the second stage, several filter and wrapper methods are implemented to select proper features. In the third stage, k-nearest neighbor algorithm is used to cluster the customers. The approach aims to select a compact feature subset with the maximal prediction capability. The proposed approach can detect the customers who are more likely to buy a specific insurance coverage at the end of a contract term. Findings - The proposed approach has been applied in a real case study of insurance company in Iran. On the basis of the findings, the proposed approach is capable of recognizing the customer clusters and planning a suitable insurance coverage sales plans for loyal customers with proper accuracy level. Therefore, the proposed approach can be useful for the insurance company which helps them to identify their potential clients. Consequently, insurance managers can consider appropriate marketing tactics and appropriate resource allocation of the insurance company to their high-potential loyal customers and prevent switching themto competitors. Originality/value - Despite the importance of recognizing high-potential loyal insurance customers, little study has been done in this area. In this paper, data-mining techniques were developed for the prediction of special insurance coverage sales on the basis of customers' characteristics. The method allows

关键词： Data mining knowledge management Feature selection algorithm k-nearest neighbor algorithm Insurance coverage sales

来源：评论

学校读者我要写书评

暂无评论

On the Effect of k Values and Distance Metrics in kNN algorithm for Android Malware Detection

引用

ADVANCES IN DATA SCIENCE AND ADAPTIVE ANALYSIS 2021年第3N04期13卷

作者： Sahin, Durmus Ozkan Akleylek, Sedat kilic, Erdal Ondokuz Mays Univ Dept Comp Engn Atakum Samsun Turkey

There is a remarkable increase in mobile device usage in recent years. The Android operating system is by far the most preferred open-source mobile operating system around the world. Besides, the Android operating system is preferred in many devices on the Internet of Things (IoT) devices are used in many areas of daily life. Smart cities, smart environment, health, home automation, agriculture, and livestock are some of the usage areas. Health is one of the most frequently used areas. Since the Android operating system is both the widely used operating system and open-source, the vast majority of malware released on the market is now designed for Android platforms. Therefore, devices using the Android operating system are under serious threat. In this study, a system that detects malware on Android operating systems based on machine learning is proposed. Besides, feature vectors are created with permissions that have an important place in the security of the Android operating system. Feature vectors created using the k-nearest neighbor algorithm (kNN), one of the machine learning techniques, are given as input to this algorithm, and a classification of malicious software and benign software is provided. In the kNN algorithm, the k value and the distance metric used to find the closest sample directly affect the classification performance. In addition, the study examining the parameters of the kNN algorithm in detail in permission-based studies is limited. For this reason, the performance of the malware detection system is presented comparatively using five different k values and five different distance metrics under different data sets. When the results are examined, it is observed that higher classification performances are obtained when values such as 1, 3 are given to k and metrics such as Euclidean and Minkowski are chosen instead of the Chebyshev distance metric.

关键词： Machine learning k-nearest neighbor algorithm Android malware Android loT devices health device security malware detection static analysis

来源：评论

学校读者我要写书评

暂无评论

A fuzzy support vector machine based on environmental membership and its application to motor fault classification

引用

JOURNAL OF VIBRATION AND CONTROL 2018年第23期24卷 5681-5692页

作者： Li Bing Liang Yilong Cheng Wei Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710049 Shaanxi Peoples R China

To weaken the effects of the outliers or noise in classification, a fuzzy support vector machine (FSVM) based on environmental fuzzy membership is proposed. The environmental fuzzy membership considers not only the number of the similar samples nearby but also the distribution of the samples nearby. As more information of the samples is considered, the reliability and robustness of the FSVM is further enhanced, which can improve the classification performance, especially for overlapping samples. The classification performance of the proposed method is validated by numerical case studies, an experimental study for a breast cancer dataset, and an application to motor fault classification. Compared with the FSVM based on the k-nearest neighbor algorithm, the proposed method obtains more robust and accurate classification rates in all case studies.

关键词： Environmental fuzzy membership fuzzy support vector machine motor fault classification k-nearest neighbor algorithm Motor fault diagnosis

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：