检索结果-内蒙古大学图书馆

A positive and negative balance accounting method for carbon emissions in parks based on k-nearest neighbour clustering algorithm

引用

INTERNATIONAL JOURNAL OF ENVIRONMENTAL TECHNOLOGY AND MANAGEMENT 2025年第1-3期28卷 45-60页

作者： Song, Junzhi Southwest Jiaotong Univ Hope Coll Chengdu 610400 Peoples R China Chengdu Transportat Tourism Big Data Applicat Tech Chengdu 610400 Peoples R China

In order to improve accounting accuracy and shorten accounting time, the paper proposes a positive and negative balance accounting method for carbon emissions in parks based on k-nearest neighbour clustering algorithm. Firstly, collect and standardise the carbon emission data of the park. Then, k-nearest neighbour clustering algorithm is used to cluster the carbon emission management items. After reconstructing the data components, the reconstruction component with the highest sample entropy is decomposed twice to obtain the carbon emission coefficient of land use type. Finally, a carbon emission balance accounting model is constructed, and the accounting results are obtained by integrating various production factors in the model. The experimental shows that after applying this method, the accuracy and recall of carbon emission accounting can reach 96.09% and 99.6%, respectively. The time required for positive and negative balance accounting is only 2.5 minutes, indicating that this method has achieved the design expectations.

关键词： k-nearest neighbour algorithm k-means clustering method k-nearest neighbour clustering algorithm secondary decomposition carbon emissions

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Tumour By Segmenting the Magnetic Resonance Image Using k-nearest neighbour algorithm and Compare the Sensitivity and Accuracy With Convolutional Neural Network algorithm

Detection of Brain Tumour By Segmenting the Magnetic Resonan...

引用

2023 Intelligent Computing and Control for Engineering and Business Systems, ICCEBS 2023

作者： Sheela, M.Sahaya Nalini, N. Uganya, G. Sathesh, M. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350394580

The main objective of this research is to use the 'k-nearest neighbour' ('kNN') algorithm to detect brain tumours in MRI images and to compare its sensitivity and accuracy to that of the 'Convolutional Neural Network' ('CNN')algorithm. Brain tumours were identified in MRI scans using the 'kNN' and 'CNN' algorithm, and the sensitivity and accuracy of the identified images were compared. Group 1 with 20 samples using 'kNN' and Group 2 with 20 samples using 'CNN' were analysed by compiling the entire dataset of 40 samples with 80% of pretest power. Pursuant to the simulation, the 'kNN' algorithm has a 95% sensitivity to detect brain tumours, whereas the 'CNN' approach has a 90% sensitivity to do so. While 'CNN' algorithm only diagnoses brain tumours with 84.10% accuracy, 'kNN' algorithm does so with an accuracy of 98.5%. © 2023 IEEE.

关键词： accuracy convolutional neural network algorithm Image segmentation k-nearest neighbour algorithm machine learning sensitivity

来源：评论

学校读者我要写书评

暂无评论

A k-nearest neighbour Technique for Experience-Based Adaptation of Assembly Stations

引用

JOURNAL OF CONTROL AUTOMATION AND ELECTRICAL SYSTEMS 2014年第6期25卷 679-688页

作者： Scrimieri, Daniele Ratchev, Svetan M. Univ Nottingham Dept Mech Mat & Mfg Engn Nottingham NG7 2RD England

We present a technique for automatically acquiring operational knowledge on how to adapt assembly systems to new production demands or recover from disruptions. Dealing with changes and disruptions affecting an assembly station is a complex process which requires deep knowledge of the assembly process, the product being assembled and the adopted technologies. Shop-floor operators typically perform a series of adjustments by trial and error until the expected results in terms of performance and quality are achieved. With the proposed approach, such adjustments are captured and their effect on the station is measured. Adaptation knowledge is then derived by generalising from individual cases using a variant of the k-nearest neighbour algorithm. The operator is informed about potential adaptations whenever the station enters a state similar to one contained in the experience base, that is, a state on which adaptation information has been captured. A case study is presented, showing how the technique enables to reduce adaptation times. The general system architecture in which the technique has been implemented is described, including the role of the different software components and their interactions.

关键词： knowledge-based systems k-nearest neighbour algorithm Assembly Architectures

来源：评论

学校读者我要写书评

暂无评论

High-speed directional protection based on cross correlation of Fourier transform components of voltage and current

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2016年第4期10卷 275-287页

作者： Saleki, Ghasem Samet, Haidar Ghanbari, Teymoor Shiraz Univ Sch Elect & Comp Engn Shiraz Iran

In this study, a new algorithm for directional protection, based on cross correlation of Fourier transform components of voltage and current for each phase is proposed. The fault is detected using k-nearest neighbour algorithm. By comparing the fifth-nearest neighbour of each sample with an adaptive threshold, the fault is detected. The adaptive threshold is derived by a moving window with length equal to 1 ms. Using Fourier transform, the fifth sinusoidal component of the measured voltage and current for each phase is extracted. Then the cross correlation of the voltage and current components is calculated. The calculated cross correlation signal is passed through a low-pass filter. By comparison of the filtered signal with a predefined threshold, fault direction is determined. It is confirmed that the fault direction can be identified in less than 8 ms with high accuracy of nearly 99%. More than 6500 scenarios are considered for different fault conditions to evaluate the proposed method. Furthermore, using some experimental results the proposed method performance is confirmed. The simulation and experimental results show that the proposed method has high speed, good accuracy, and sensitivity.

关键词： Fourier transforms voltage measurement electric current measurement fault diagnosis high-speed directional protection Fourier transform component cross correlation k-nearest neighbour algorithm fifth-nearest neighbour adaptive threshold fault detection fifth sinusoidal component voltage measurement current measurement low-pass filter

来源：评论

学校读者我要写书评

暂无评论

An automatic method for arterial pulse waveform recognition using kNN and SVM classifiers

引用

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 2016年第7期54卷 1049-1059页

作者： Pereira, Tania Paiva, Joana S. Correia, Carlos Cardoso, Joao Univ Coimbra Dept Phys Instrumentat Ctr Rua Larga P-3004516 Coimbra Portugal Univ Coimbra Dept Phys Coimbra Portugal

The measurement and analysis of the arterial pulse waveform (APW) are the means for cardiovascular risk assessment. Optical sensors represent an attractive instrumental solution to APW assessment due to their truly non-contact nature that makes the measurement of the skin surface displacement possible, especially at the carotid artery site. In this work, an automatic method to extract and classify the acquired data of APW signals and noise segments was proposed. Two classifiers were implemented: k-nearest neighbours and support vector machine (SVM), and a comparative study was made, considering widely used performance metrics. This work represents a wide study in feature creation for APW. A pool of 37 features was extracted and split in different subsets: amplitude features, time domain statistics, wavelet features, cross-correlation features and frequency domain statistics. The support vector machine recursive feature elimination was implemented for feature selection in order to identify the most relevant feature. The best result (0.952 accuracy) in discrimination between signals and noise was obtained for the SVM classifier with an optimal feature subset .

关键词： Arterial pulse waveform Optical system Feature creation Recursive feature elimination k-nearest neighbour algorithm Support vector machine

来源：评论

学校读者我要写书评

暂无评论

algorithm for sheet thickness measurement and its application to thermoformed PMMA sheet

引用

JOURNAL OF ELASTOMERS AND PLASTICS 2024年第5期56卷 652-660页

作者： Patil, Jeet Vasavada, Jitesh Mahajan, Peeyush Mishra, Sushil Shri Guru Gobind Singhji Inst Engn & Technol Dept Mech Engn Nanded India Indian Inst Technol Dept Mech Engn Mumbai India SGGSIE&T Dept Mech Engn Vishnupuri Nanded 431606 India

One of the evaluative criteria utilized to ascertain the quality of a thermoformed product is the ultimate thickness of the sheet achieved through the processing. In determining the visual performance of optical products such as aircraft canopy, windscreens, etc., thickness distribution is crucial. Consequently, precise thickness measurement is the most essential aspect of quality control. To measure thickness, a variety of mechanical and optical measurement systems, in addition to several manual systems, are available. The manual intervention restricts the measurement system to lesser measurements and simplifies the system to simple geometries. Furthermore, post-processing of the image or point data is necessary to obtain thickness distribution using an optical measurement system. However, manual intervention is exceptionally time-consuming and may result in inaccurate outcomes. As a result, the current investigation put forth an algorithm based on machine learning to measure the precise thickness distributions from point data obtained through the measuring system. The algorithm's functionality is illustrated through the thermoforming of a PMMA hemispherical dome at various forming pressures. Point data for thickness measurements of the hemispherical domes were acquired using the Rapid-I system of measurement. Utilizing the proposed algorithm, the thickness distribution of the hemispherical domes was measured accurately and efficiently.

关键词： Pressure thermoforming Polymethyl methacrylate thickness measurement k-nearest neighbour algorithm machine learning

来源：评论

学校读者我要写书评

暂无评论

Using Residual Networks and Cosine Distance-Based k-NN algorithm to Recognize On-Line Signatures

引用

IEEE ACCESS 2021年 9卷 54962-54977页

作者： Abosamra, Gibrael Oqaibi, Hadi King Abdulaziz Univ Fac Comp & Informat Technol Dept Comp Informat Syst Jeddah 21589 Saudi Arabia

As a result of the urgent need to immediately identify individuals through the Internet, especially given the Coronavirus (COVID-19) pandemic at present, the recognition of online handwritten signatures has quickly evolved to become an urgent and necessary matter. However, signature identification remains challenging in the pattern recognition field due to intra-class variability and inter-class similarity. Intra-class variability is a characteristic of human behavioural activities, particularly in handwriting where no two handwritten signatures of any person can exactly coincide. The inter-class similarity is also a characteristic of human movement-based activities such as handwritten signatures particularly when the number of writers is large. In this research, an optimized transfer-learning-based architecture is proposed as a highly accurate identification technique for online-signatures using ResNet18 as a feature extraction deep-learning module. The X-Y time-series signals of the signatures were initially converted into images and used in retraining the ResNet18 model to achieve relatively high accuracy. The retrained ResNet18 model was then used to extract features that possess high discriminative distances among different classes of handwritten signatures. The model's deep layers were searched to determine the best layer that provided the most discriminative features when using a 1-nearest neighbour learning algorithm based on the cosine distance. By using an ensemble of five models trained on rotated versions of the original signatures and using only three training samples from each writer, the classification accuracy achieved 100% when applied on the genuine signatures of public datasets such as SVC 2004 TASk1 and TASk2, and a new proprietary dataset composed of 120 genuine users. When the abovementioned technique was tested on the aggregated version of the aforementioned datasets, the resultant accuracy was still above 99%. Moreover, the robustness of the

关键词： Task analysis Forgery Feature extraction Training Static VAr compensators Residual neural networks Hidden Markov models Convolutional networks cosine distance deep residual networks k-nearest neighbour algorithm machine learning online signature recognition transfer learning

来源：评论

学校读者我要写书评

暂无评论

Effective construction of classifiers with the k-NN method supported by a concept ontology

引用

kNOWLEDGE AND INFORMATION SYSTEMS 2020年第4期62卷 1497-1510页

作者： Bazan, Jan Bazan-Socha, Stanislawa Ochab, Marcin Buregwa-Czuma, Sylwia Nowakowski, Tomasz Wozniak, Miroslaw Univ Rzeszow Interdisciplinary Ctr Computat Modelling Pigonia 1 PL-35310 Rzeszow Poland Jagiellonian Univ Fac Med Dept Internal Med Med Coll Skawinska 8 PL-31066 Krakow Poland Jagiellonian Univ Med Coll Dept Angiol Skawinska 8 PL-31066 Krakow Poland Angiomed Private Med Ctr Skawinska 8 PL-31066 Krakow Poland

In analysing sensor data, it usually proves beneficial to use domain knowledge in the classification process in order to narrow down the search space of relevant features. However, it is often not effective when decision trees or the k-NN method is used. Therefore, the authors herein propose to build an appropriate concept ontology based on expert knowledge. The use of an ontology-based metric enables mutual similarity to be determined between objects covered by respective concept ontology, taking into consideration interrelations of features at various levels of abstraction. Using a set of medical data collected with the Holter method, it is shown that predicting coronary disease with the use of the approach proposed is much more accurate than in the case of not only the k-NN method using classical metrics, but also most other known classifiers. It is also proved in this paper that the expert determination of appropriate structure of ontology is of key importance, while subsequent selection of appropriate weights can be automated.

关键词： k-nearest neighbour algorithm Ontology similarity metrics Holter measurement Coronary disease

来源：评论

学校读者我要写书评

暂无评论

A DIFFERENTIAL EVOLUTION APPROACH TO DIMENSIONALITY REDUCTION FOR CLASSIFICATION NEEDS

引用

INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE 2014年第1期24卷 111-122页

作者： Martinovic, Goran Bajer, Drazen Zoric, Bruno JJ Strossmayer Univ Osijek Fac Elect Engn Osijek 31000 Croatia

The feature selection problem often occurs in pattern recognition and, more specifically, classification. Although these patterns could contain a large number of features, some of them could prove to be irrelevant, redundant or even detrimental to classification accuracy. Thus, it is important to remove these kinds of features, which in turn leads to problem dimensionality reduction and could eventually improve the classification accuracy. In this paper an approach to dimensionality reduction based on differential evolution which represents a wrapper and explores the solution space is presented. The solutions, subsets of the whole feature set, are evaluated using the k-nearest neighbour algorithm. High quality solutions found during execution of the differential evolution fill the archive. A final solution is obtained by conducting k-fold cross-validation on the archive solutions and selecting the best one. Experimental analysis is conducted on several standard test sets. The classification accuracy of the k-nearest neighbour algorithm using the full feature set and the accuracy of the same algorithm using only the subset provided by the proposed approach and some other optimization algorithms which were used as wrappers are compared. The analysis shows that the proposed approach successfully determines good feature subsets which may increase the classification accuracy.

关键词： classification differential evolution feature subset selection k-nearest neighbour algorithm wrapper method

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based microarray cancer classification and ensemble gene selection approach

引用

IET SYSTEMS BIOLOGY 2022年第3-4期16卷 120-131页

作者： Rezaee, khosro Jeon, Gwanggil khosravi, Mohammad R. Attar, Hani H. Sabzevari, Alireza Meybod Univ Dept Biomed Engn Meybod Iran Incheon Natl Univ Coll Informat Technol Dept Embedded Syst Engn Incheon South Korea Persian Gulf Univ Dept Comp Engn Bushehr Iran Zarqa Univ Dept Energy Engn Zarqa Jordan

Malignancies and diseases of various genetic origins can be diagnosed and classified with microarray data. There are many obstacles to overcome due to the large size of the gene and the small number of samples in the microarray. A combination strategy for gene expression in a variety of diseases is described in this paper, consisting of two steps: identifying the most effective genes via soft ensembling and classifying them with a novel deep neural network. The feature selection approach combines three strategies to select wrapper genes and rank them according to the k-nearest neighbour algorithm, resulting in a very generalisable model with low error levels. Using soft ensembling, the most effective subsets of genes were identified from three microarray datasets of diffuse large cell lymphoma, leukaemia, and prostate cancer. A stacked deep neural network was used to classify all three datasets, achieving an average accuracy of 97.51%, 99.6%, and 96.34%, respectively. In addition, two previously unreported datasets from small, round blue cell tumors (SRBCTs)and multiple sclerosis-related brain tissue lesions were examined to show the generalisability of the model method.

关键词： soft ensembling lab-on-a-chip ensemble gene selection approach feature selection medical computing deep learning (artificial intelligence) k-nearest neighbour algorithm diseases genetic origins microarray data diffuse large cell lymphoma deep learning-based microarray cancer classification gene expression stacked deep neural network wrapper genes data analysis feature selection approach microarray datasets cancer pattern classification genetics effective genes prostate cancer brain tumours low error levels combination strategy

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：