检索结果-内蒙古大学图书馆

10th International Symposium on Computational Intelligence and Design (ISCID)

作者： Wang, Xingang Wang, Linlin Qilu Univ Technol Sch Informat Jinan Shandong Peoples R China

ISBN: (纸本)9781538636749

Nowadays, intrusion detection is a technology to effectively avoid a number of risks of network intrusion. The k-means algorithm is widely used in intrusion detection. But, the algorithm has some shortcomings, such as random selection of k value, sensitive selection of initial cluster centers, and low accuracy in clustering high-dimensional data. In order to make up for these shortcomings of the k-means algorithm, this paper proposes an AE-kmeans architecture which combines an autoencoder with the improved k-means algorithm. The AE-kmeans architecture realizes the dimension reduction and feature extraction of these original data by introducing an autoencoder, and uses the improved k-means algorithm to cluster these processed data. These improvements of the improved k-means algorithm mainly include two aspects: the first aspect, a new method is introduced to select initial cluster centers;the second aspect, the algorithm calculates the weight of each attribute with the coefficient of variation, and then uses these weights in Euclidean distance formula, resulting in a weighted Euclidean distance formula. Finally, the AE-kmeans architecture uses kDD CUP99 data set for intrusion detection simulation experiments. The Experimental results show that the AE-kmeans architecture not only enhances the ability to deal with high-dimensional data, but also improves the detection rate and reduces the error-detection rate compared with k-means algorithm.

关键词： intrusion detection k-means clustering algorithm autoencoder AE-kmeans architecture feature extraction weighted Euclidean distance formula

来源：评论

学校读者我要写书评

暂无评论

A method of calculating urban-scale solar potential by evaluating and quantifying the relationship between urban block typology and occlusion coefficient: A case study of Wuhan in Central China

引用

SUSTAINABLE CITIES AND SOCIETY 2021年 64卷 102451-102451页

作者： Xu, Shen Li, Zhixin Zhang, Chen Huang, Zhaojian Tian, Jia Luo, Yongqiang Du, Hu Huazhong Univ Sci & Technol Sch Architecture & Urban Planning Wuhan Peoples R China Huazhong Univ Sci & Technol China EU Inst Clean & Renewable Energy Wuhan Peoples R China Huazhong Univ Sci & Technol Sch Environm Sci & Engn Wuhan Peoples R China Cardiff Univ Cardiff Wales

Relevant research shows that the potential of solar energy utilization varies greatly in different occlusion conditions. However, existing methods of assessing macro-city-scale solar roof utilization potential are not capable of considering the factor of mutual occlusion between urban buildings. To measure the overall solar photovoltaic utilization potential of the city, it is necessary to quantify the occlusion caused by the urban environmental building roof. This paper uses typical high-density blocks to quantify differences of occlusions on the building roof caused by urban blocks and building functions. Taking Wuhan as an example, a large number of urban blocks which form indicators were counted were selected as research samples, the data sets covers six types of morphological indicators to classify the urban blocks, and then the above blocks was modelled to simulate the solar radiation in order to obtain the values and combine with their morphological parameters, which will help to get roof solar occlusion factors by linear regression ways. The overall roof occlusion coefficient result of Wuhan is 0.079. By applying the above-mentioned occlusion coefficient to measure the solar energy potential of Hongshan District in Wuhan, the annual photovoltaic power generation was calculated to be able to reach 168.02GWh.

关键词： Solar energy Urban energy Occlusion coefficient k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

A comprehensive obstacle analysis framework on dispersed wind power: A case of China

引用

JOURNAL OF CLEANER PRODUCTION 2021年 297卷 126684-126684页

作者： Wu, Yunna Liu, Fangtong Deng, Zhongqing He, Jiaming Xu, Chuanbo Tao, Yao ke, Yiming North China Elect Power Univ Sch Econ & Management Beijing Peoples R China Beijing Key Lab New Energy & Low Carbon Dev Beijing Peoples R China Jinan Univ Energy & Elect Res Ctr Zhuhai Peoples R China

Dispersed wind power is undoubtedly assisting sustainable development of society but hindered by various factors. To promote the development of dispersed wind power, this paper is devoted to obstacles identification and analysis to provide effective development proposals. Firstly, a three-stage process (namely collection, screening and improvement) is developed to extract common obstacles from literature and explore unique obstacles according to the characteristics and development status of dispersed wind power. Then, DANP method is improved to analyze interaction, interrelation and relative importance among filtered obstacles, where Pythagorean fuzzy numbers and k-means clustering algorithm are introduced to modify incomplete information collection and arbitrary threshold determination, respectively. Three reasonable thresholds are determined according to clustering results, which divide the influence degree among obstacles into four categories (namely, high, moderate, low and no influence). The analysis results indicate that lagged unified planning ranks the first of obstacles, followed by financial difficulty and restricted grid access. On that basis, some practical proposals on regional coordinated development are suggested, including building unified coordination platforms and forming dispersed wind power project group. This paper does not only enrich material database for scholars, but also provide reference and guidance for government and related enterprises. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Dispersed wind power Obstacles analysis Pythagorean fuzzy numbers DANP k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent analysis technology of bamboo structure. Part II: The variability of radial distribution of fiber volume fraction

引用

INDUSTRIAL CROPS AND PRODUCTS 2021年 174卷 114164-114164页

作者： Xu, Haocheng Li, Jing Ma, Xinxin Yi, Wukun Wang, Hankun Int Ctr Bamboo & Rattan Inst New Bamboo & Rattan Based Biomat Key Lab Natl Forestry & Grassland Adm Beijing Bam Beijing 100102 Peoples R China Chinese Acad Forestry Res Inst Wood Ind Key Lab Natl Forestry & Grassland Adm Wood Sci & Beijing 100091 Peoples R China Xiaoxiang Res Inst Big Data Changsha 410000 Peoples R China

Scientific and reasonable utilization of bamboo is strongly related to the radial distribution of the fiber volume fraction. In this paper, the k-means clustering algorithm was applied to set separate thresholds for individual vascular bundles, to solve the problem that the bamboo ring cannot be binarized well. We introduced a layered model based on the WEB coordinate system, programmed via JavaScript, to layer the cross-section within the entire bamboo conveniently and accurately. It allowed uniform layering of sample areas of any thickness, any width, and any number of layers. Furthermore, this research systematically studied the bamboo rings at the breast height of Moso bamboo [Phyllostachys edulis (Carr)H. de Lebaie] grown in 12 major producing areas of China and the 50-internode sections from base to top of one bamboo with the method mentioned above. The results indicated that the thickness of a single layer should not be higher than 0.4 mm while examining the gradient structure of bamboo. The radial distribution of fiber volume fraction from 12 areas all followed the ExpDec1 function, and the mean goodness of fit (R2) was 0.988. The radial distribution of fiber volume fraction in the first 45 sections from the base to the top corresponded to the ExpDec1 function. It provided a theoretical basis for the functional improvement of bamboo and the development of new bamboo-based smart materials.

关键词： Fiber volume fraction Radial distribution k-means clustering algorithm Regional differences Axial variation ExpDec1 function

来源：评论

学校读者我要写书评

暂无评论

Stochastic optimization models for the solar system design and energy management problem in an off-grid residential house

引用

JOURNAL OF ENERGY STORAGE 2024年 100卷

作者： Hooshmand, Farnaz Tehran Polytech Amirkabir Univ Technol Dept Math & Comp Sci Tehran Iran

Solar energy is clean, eco-friendly, abundant, inexpensive, and sustainable, and using it as a source of electricity generation can significantly reduce environmental pollution. For residential houses located in isolated areas without access to the national electricity grid, photovoltaic-battery systems (PBSs) are good choices for electricity generation. This paper addresses the optimization of PBS sizing and energy managing for isolated off-grid standalone houses, considering uncertainties in solar irradiation. We propose a novel approach by formulating the problem as a two-stage stochastic programming model, enhanced with a k-means clustering algorithm for scenario generation. Additionally, we extend the model by incorporating worst-case (WC) and conditional-value-at-risk (CVaR) measures to enhance robustness against uncertainty. To address the variability in scenario occurrence probabilities, we develop a distributionally robust optimization (DRO) model, further contributing to the system reliability. Computational experiments on real-world datasets reveal that our modeling frameworks outperform existing stochastic optimization models in terms of computational efficiency. Moreover, the risk-based and DRO models improve system reliability, resulting in lower unmet demand and reduced diesel generator (DG) usage. Specifically, compared to the expected-value-based model, the WC- and CVaR-based models, despite increasing construction costs by 20 % and 10 % respectively, achieve approximately 85 % and 50 % reductions in unmet demand and 57 % and 30 % reductions in DG usage across different seasons, on average. Furthermore, although the DRO model incurs a 9.8 % higher construction cost than the expected-value-based model, it demonstrates approximately 46 % and 28 % reductions in unmet demand and DG usage, respectively, across various seasons, on average.

关键词： Photovoltaic-battery system size Energy consumption management Scenario-based stochastic programming k-means clustering algorithm Risk measures Distributionally robust optimization

来源：评论

学校读者我要写书评

暂无评论

Construction of Risk Prediction Models for Enterprise Finance Sharing Operations Using k-means and C4.5 algorithms

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2024年第1期17卷 208-208页

作者： Pan, Chun Changjiang Inst Technol Fac Econ & Management Wuhan 430212 Peoples R China

The evaluation of financial sharing centres in enterprises typically relies on outdated financial data, lacks comprehensive assessment, and presents risks such as employee misconduct. To address these challenges, we propose a risk prediction model for enterprise financial sharing operations based on the k-means clustering algorithm for performance evaluation and the C4.5 algorithm for managing employee risks. Our approach enhances the accuracy and objectivity of performance evaluation while improving the efficiency of personnel risk management. Results indicate that the k-means algorithm classifies employee performance into five levels, facilitating comprehensive performance evaluation. Furthermore, through risk management optimisation, accuracy and recall rates increase to 0.905 and 0.890, respectively. The proposed risk prediction model achieves high accuracy rates of 90.5% and 92.4% in the training and test sets, respectively. Practical application of our methodology and model in A Group's financial sharing centre demonstrates their effectiveness and potential for enhancing the operation and management of enterprise financial sharing centres.

关键词： Enterprise financial sharing Risk prediction models k-means clustering algorithm C4.5 algorithm

来源：评论

学校读者我要写书评

暂无评论

Oxygen saturation measurements using novel diffused reflectance with hyperspectral imaging: Towards facile COVID-19 diagnosis

引用

OPTICAL AND QUANTUM ELECTRONICS 2022年第5期54卷 322-322页

作者： El-Sharkawy, Yasser H. Aref, Mohamed Hisham Elbasuney, Sherif Radwan, Sara M. El-Sayyad, Gharieb S. Egyptian Armed Forces Biomed Engn Dept Mil Tech Coll Cairo Egypt Egyptian Armed Forces Nanotechnol Res Ctr Mil Tech Coll Cairo Egypt Ain Shams Univ Fac Pharm Biochem Dept Cairo Egypt Galala Univ Fac Pharm Microbiol & Immunol Dept New Galala City Suez Egypt Egyptian Armed Forces Chem Engn Dept Mil Tech Coll Cairo Egypt

Oxygen saturation level plays a vital role in screening, diagnosis, and therapeutic assessment of disease's assortment. There is an urgent need to design and implement early detection devices and applications for the COVID-19 pandemic;this study reports on the development of customized, highly sensitive, non-invasive, non-contact diffused reflectance system coupled with hyperspectral imaging for mapping subcutaneous blood circulation depending on its oxygen saturation level. The forearm of 15 healthy adult male volunteers with age range of (20-38 years) were illuminated via a polychromatic light source of a spectrum range 400-980 nm. Each patient had been scanned five times to calculate the mean spectroscopic reflectance images using hyperspectral camera. The customized signal processing algorithm includes normalization and moving average filter for noise removal. Afterward, employing k-means clustering for image segmentation to assess the accuracy of blood oxygen saturation (SpO(2)) levels. The reliability of the developed diffused reflectance system was verified with the ground truth technique, a standard pulse oximeter. Non-invasive, non-contact diffused reflectance spectrum demonstrated maximum signal variation at 610 nm according to SpO(2) level. Statistical analysis (mean, standard deviation) of diffused reflectance hyperspectral images at 610 nm offered precise calibrated measurements to the standard pulse oximeter. Diffused reflectance associated with hyperspectral imaging is a prospective technique to assist with phlebotomy and vascular approach. Additionally, it could permit future surgical or pharmacological intercessions that titrate or limit ischemic injury continuously. Furthermore, this technique could offer a fast reliable indication of SpO(2) levels for COVID-19 diagnosis.

关键词： Vein viewer Hyperspectral imaging Oxygen concentration k-means clustering algorithm Tissue characterization

来源：评论

学校读者我要写书评

暂无评论

kM-Mask RCNN: A Lightweight Instance Segmentation algorithm for Strawberries With Multiple Growth Cycles

引用

IEEE ACCESS 2024年 12卷 169291-169309页

作者： Cong, Peichao Xu, Yutao Li, Tianheng Li, Shanda Feng, Hao Zhang, Xin Guangxi Univ Sci & Technol Sch Mech & Automot Engn Liuzhou 545006 Peoples R China

Accurate and efficient detection of multi-growth-cycle strawberry fruits can improve automated harvesting. However, the small size and unbalanced distribution of strawberry fruits make accurate identification of multi-growth-cycle strawberries difficult using the existing detection models. Herein, local enhancement technology is adopted for preprocessing when compiling the dataset to ensure the balance of the number of samples in each category to solve the above problems. Second, a new instance segmentation algorithm called kM-Mask RCNN is developed, which optimally adjusts the size of the anchor frame and the anchor ratio based on the k-means clustering algorithm to improve the recognition accuracy of the algorithm on small targets and uses MobileNet V3 to replace the Resnet50 structure in the Mask RCNN backbone network to reduce the complexity of the algorithm and realize lightweight operation. Finally, the experimental results reveal five strawberry growth stages in the homemade dataset(based on StrawDI_Db1 database): 'Green ripe stage', 'White ripe stage', 'Turning stage', 'Mature', and 'Deformed', for which the kM-Mask RCNN yields mAPs of 91.19%, 88.09%, 93.70%, 93.19%, and 87.13%, respectively. The P, R, and F1-score values of this algorithm are 93.9%, 94.2%, and 94.05%, respectively. Additionally, the number of parameters, FLOPs, and fps of this algorithm are 27M, 12G, and 22.32, respectively, satisfying the real-time requirements for strawberry detection. The findings provide important theoretical support for the automated harvesting of strawberries with multiple growth cycles.

关键词： Feature extraction Accuracy Residual neural networks Robots clustering algorithms Classification algorithms Transformers Prediction algorithms Instance segmentation Manuals Convolutional neural networks k-means clustering algorithm lightweighting mask RCNN strawberry

来源：评论

学校读者我要写书评

暂无评论

Optimized FPGA-Based Implementation of Brain Tumor Detection by Combining k-means and Grey Wolf Optimization algorithms

引用

TRAITEMENT DU SIGNAL 2022年第6期39卷 1879-1891页

作者： Jarrah, Amin Amri, Screen Yarmouk Univ Hijjawi Fac Engn Technol Dept Comp Engn Irbid 21163 Jordan

There is a need for fast, accurate, and real-time algorithms to detect brain tumors effectively to support the physician's decision-making for treatment purposes. A brain tumor is a life-threatening uncontrolled growth of cells and tissues that may cause death due to inaccurate and late detection. k-means clustering is one of the clustering techniques that is widely used in brain tumor detection, but it has some drawbacks such as dependency on initial centroid values and a tendency to fall on local optima. This research proposes a new model that uses grey wolf optimization to find the optimal value of k (clusters number) of the k-means algorithm to avoid local optima. A parallel implementation of the k-means clustering algorithm on a field-programmable gate array (FPGA) is also proposed to enhance the performance by reducing the processing time and the power consumption. Moreover, the proposed algorithm is implemented using the Vivado HLS tool on Xilinx kintex7 XC7k160t FPGA 484-1 where different optimization techniques are adopted and applied, such as loop unrolling, loop pipelining, dataflow, and loop merging. The achieved speed-up of the parallel implementation compared with sequential implementation was 88.17, where the obtained average clustering accuracy was 97.11%.

关键词： brain tumor detection grey wolf optimization k-means clustering algorithm optimization techniques parallel implementation

来源：评论

学校读者我要写书评

暂无评论

Indirect solution modeling of melting behavior of SiO2 based on the image processing technology

引用

ASIA-PACIFIC JOURNAL OF CHEMICAL ENGINEERING 2024年第2期19卷 e3028-e3028页

作者： Lu, Cunhao Zhang, Yi Zhang, Jiayi Sun, Weixiang Xia, Anying Zhang, Mingli Chen, Jian Yangzhou Univ Sch Mech Engn Huayang Weststr 196 Yangzhou 225127 Jiangsu Peoples R China Shandong Jinyu Elect Technol Co LTD Innovat Workshop Jinan Shandong Peoples R China McGill Univ Montreal Neurol Inst McGill Ctr Integrat Neurosci Montreal PQ Canada Shandong Technol & Business Univ Sch Comp Sci Yantai Shandong Peoples R China

The utilization of tempered blast-furnace slag through the direct fiber forming process to produce high-value thermal insulation materials offers a dual benefit: it efficiently utilizes the latent heat in the unused slag and significantly increases the value of blast-furnace slag utilization. However, measuring the melting properties of iron slag at high temperatures is challenging. In this study, the melting behavior of SiO2 in a high-temperature molten pool was investigated. We employ dynamic visual data (video stream) captured via a non-contact charge coupled device video recording system to extract SiO2 contours through image processing. The change in image centroid characteristics is used to establish a convolution function relationship, and MATLAB's traversal search algorithm determines the centroid position of SiO2. Given that SiO2 is proportionate to crucible pixels, the area of the SiO2 is calculated through pixel statistics within these contours. A new indirect method is then proposed to process image information to obtain SiO2 volume and mass at different time points. An exponential fitting yields the melting rate function of SiO2. Finally, this indirect method has been compared with shape from shading, quantitative characterization, and dimensional analysis techniques. Besides, the strengths and limitations of each method have been discussed. Our findings reveal that the indirect solution method presented here boasts straightforward calculation steps and imposes minimal image format requirements, which provides theoretical and technical support for the direct fiber forming process of blast-furnace slag.

关键词： image processing indirect solution method k-means clustering algorithm traversal 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：