In order to improve the accuracy and efficiency of the clustering mining algorithm, this paper focuses on the clustering mining algorithm for large data. Firstly, the traditional clustering mining algorithm is improve...
详细信息
In order to improve the accuracy and efficiency of the clustering mining algorithm, this paper focuses on the clustering mining algorithm for large data. Firstly, the traditional clustering mining algorithm is improved to improve the accuracy, and then the improvedclusteringalgorithm is parallelized to improve the efficiency. In order to improve the accuracy of clustering, an incremental k-meansclusteringalgorithm based on density is proposed on the basis of k-meansalgorithm. Firstly, the density of data points is calculated, and each basic cluster is composed of the center points whose density is not less than the given threshold and the points within the density range. Then, the basic cluster is merged according to the distance between the two cluster centers. Finally, the points that are not divided into any cluster are divided into the clusters nearest to them. In order to improve the efficiency of the algorithm and reduce the time complexity of the algorithm, the distributed database was used to simulate the shared memory space and parallelize the algorithm on the Hadoop platform of cloud computing. The simulation results show that the clustering accuracy of the proposed algorithm is higher than that of the other two algorithms by more than 10%.
The working condition control of grate cooler always affects the efficiency of the whole cement process. In order to solve the working condition of grate cooler too parameter dimension and strong coupling problem, and...
详细信息
ISBN:
(纸本)9781665423144
The working condition control of grate cooler always affects the efficiency of the whole cement process. In order to solve the working condition of grate cooler too parameter dimension and strong coupling problem, and according to the actual production of collecting the data of grate cooler used principal component analysis combined with an improved k-means clustering algorithm, is used to identify the conditions of grate cooler, working condition of the formation of grate cooler model, through the calculation speed and stability analysis is made of the advantages of the new algorithm, the accuracy as an important parameter of working condition of the grate cooler model verified, it provides the model basis for the subsequent grate cooler automatic control.
The risk assessment of the power grid is helpful to guide decision makers to take corresponding measures to improve the security and stability of the power grid operation. Existing risk assessment methods cannot compr...
详细信息
ISBN:
(纸本)9781728167824
The risk assessment of the power grid is helpful to guide decision makers to take corresponding measures to improve the security and stability of the power grid operation. Existing risk assessment methods cannot comprehensively and accurately quantify grid risks. To this end, this paper proposes a quantification of grid risk assessment method based on an improved k-means clustering algorithm. The improved k-means clustering algorithm is used to classify key state quantities of the grid. The actual operating state quantity is matched with the classification situation to determine the risk of power grid abandonment and power restriction. Next, determine the best classification number and intra-class data of the data. According to the magnitude of the peak-valley difference, select the data of the photovoltaic and hydropower peak-valley difference and the small peak-valley difference when discarding the light, and verify the load probability of abandoning light by fitting the load data. In the load limit verification, select the load with large peak-to-valley difference and photovoltaic and hydropower data with small peak-to-valley difference, and perform load-limit verification by fitting the hydropower data. Finally, based on the actual data of the Northwest Power Grid, the quantitative comparison and analysis of the scheduling deviation between the fitted data and the actual data, and the regional power grid risk without probability improvement, verified the effectiveness and superiority of the method.
The risk assessment of the power grid is helpful to guide decision makers to take corresponding measures to improve the security and stability of the power grid operation. Existing risk assessment methods cannot compr...
详细信息
ISBN:
(数字)9781728167824
ISBN:
(纸本)9781728167831
The risk assessment of the power grid is helpful to guide decision makers to take corresponding measures to improve the security and stability of the power grid operation. Existing risk assessment methods cannot comprehensively and accurately quantify grid risks. To this end, this paper proposes a quantification of grid risk assessment method based on an improved k-means clustering algorithm. The improved k-means clustering algorithm is used to classify key state quantities of the grid. The actual operating state quantity is matched with the classification situation to determine the risk of power grid abandonment and power restriction. Next, determine the best classification number and intra-class data of the data. According to the magnitude of the peak-valley difference, select the data of the photovoltaic and hydropower peak-valley difference and the small peak-valley difference when discarding the light, and verify the load probability of abandoning light by fitting the load data. In the load limit verification, select the load with large peak-to-valley difference and photovoltaic and hydropower data with small peak-to-valley difference, and perform load-limit verification by fitting the hydropower data. Finally, based on the actual data of the Northwest Power Grid, the quantitative comparison and analysis of the scheduling deviation between the fitted data and the actual data, and the regional power grid risk without probability improvement, verified the effectiveness and superiority of the method.
The recognition of malware in network traffic is an important research problem. However, existing solutions addressing this problem rely heavily on the source code and misrecognise vulnerabilities (i.e. incur a high f...
详细信息
The recognition of malware in network traffic is an important research problem. However, existing solutions addressing this problem rely heavily on the source code and misrecognise vulnerabilities (i.e. incur a high false positive rate (FPR)) in some cases. In this paper, we initially use the k-meansclusteringalgorithm to extract malware patterns under user to root attacks in network traffic. Since the traditional k-meansalgorithm needs to determine the number of clusters in advance and it is easily affected by the initial cluster centres, we propose an improved k-means clustering algorithm (NIkclusteringalgorithm) for cluster analysis. Furthermore, we propose the use of self-similarity and our improvedclusteringalgorithm to recognise buffer overflow vulnerabilities for malware in network traffic. This motivates us to design and implement a recognition approach for buffer overflow vulnerabilities based on self-similarity and our improvedclusteringalgorithm, called Reliable Self-Similarity with improvedk-meansclustering (RSS-Ikclustering). Extensive experiments conducted on two different datasets demonstrate that the RSS-Ikclustering can achieve much fewer false positives than other notable approaches while increasing accuracy. We further apply our RSS-Ikclustering approach on a public dataset (Center for Applied Internet Data Analysis), which also exhibited a high accuracy and low FPR of 96% and 1.5%, respectively.
In the era of big data, large scale group decision-making (LSGDM) with social networks (SNs) (namely, SN-LSGDM) has become a hot topic in the field of decision science. Faced with the explosive growth of information, ...
详细信息
In the era of big data, large scale group decision-making (LSGDM) with social networks (SNs) (namely, SN-LSGDM) has become a hot topic in the field of decision science. Faced with the explosive growth of information, decision-makers (DMs) face immense challenges in processing and integrating vast amounts of data, often finding it difficult to fully comprehend all the information, leading to potentially incomplete expressions of their fuzzy preference relations (FPRs). This limitation in information processing not only affects the quality of decision-making but also increases the difficulty and cost of reaching a consensus. To overcome these challenges and enhance the efficiency and accuracy of decision-making, this paper designs a consensus model that minimizes adjustment costs in light of a dynamic trust network. Firstly, we introduce a measurement method based on k-nearest neighbor (kNN) information, which comprehensively considers the trust level of DMs and the similarity of preference relations, effectively filling in missing preference information and improving the completeness and accuracy of decision-making. In addition, an improvedkmeansclusteringalgorithm is adopted, which takes into account the mutual influences between DMs and the cost of unit adjustment. On this basis, a two-stage minimum adjustment cost consensus reaching mechanism based on three-way decision (TWD) is proposed, using comprehensive adjustment priority as the criterion for division, to achieve feedback adjustment at the individual and subgroup levels, ensuring the coordination and consistency of the decision-making plan. At the same time, an optimization model is introduced to achieve cost minimization. Through detailed case studies and comparative analysis, the feasibility and superiority of this method in practical applications have been demonstrated.
In road transport systems, various traffic risks in certain condition could produce joint actions, which increases the complexity of traffic risk assessment. Previous single risk assessment fails to reflect the superp...
详细信息
In road transport systems, various traffic risks in certain condition could produce joint actions, which increases the complexity of traffic risk assessment. Previous single risk assessment fails to reflect the superposition effect of multi-type traffic risks, so the result may underestimate or overrate the total risk strength of transport system. To address this problem, a novel risk assessment perspective that aims to evaluate the superposition effect of several traffic risks is studied. In this study, the risk quantification and standardization for single traffic risks is conducted first. Then a GARCH-VaR model is developed to explore the superposition impact of these single traffic risks. The GARCH-VaR model integrates the VaR theory and GARCH model, from which the superposition traffic risk is obtained by assigning every single traffic risk a reasonable weight. Finally, an improved k-means clustering algorithm is proposed to classify the superposition risk level. Empirical results demonstrate that the superposition risk of crash risk and congestion risk is lower than a single traffic risk in certain condition, which attributes to the weak interactions between various traffic risks. This finding illustrates the superposition risk does not necessarily go up with the increase of the risk category. Then the superposition risks are classified into high-risk level, moderate-risk level, and low-risk level, among which the classification accuracy of high-risk level is 92.85%-95.23%. The proposed method provides a theoretical reference for collaborative assessment of multi-type traffic risks, and the results could be potentially used in the comprehensive management of traffic risks.
The high proportion of distributed photovoltaic (DPV) access has changed the traditional distribution network structure and operation mode, posing a huge threat to the stable operation and economy of the distribution ...
详细信息
The high proportion of distributed photovoltaic (DPV) access has changed the traditional distribution network structure and operation mode, posing a huge threat to the stable operation and economy of the distribution network. Aiming at a reasonable access capacity of DPV in the distribution network, this paper proposes an economic access capacity evaluation method for DPV in the distribution network considering proper PV power curtailment. Firstly, a method for generating typical joint light intensity and load power operation scenarios based on an improved k-means clustering algorithm is proposed, which provides comprehensive scenario support for the evaluation. Secondly, based on active and reactive power regulation, this paper proposes a DPV access capacity enhancement method to improve the DPV access capacity. Thirdly, considering proper PV power curtailment, an evaluation model of DPV economic access capacity in the distribution network is established to solve the maximum DPV economic access capacity in the distribution network. And aiming at the nonlinear problem in the model, the second-order cone relaxation method is employed to transform the model into the second-order cone programming model, so as to solve the objective function conveniently and efficiently. Finally, based on the improved IEEE 33-node distribution network analysis, the results show that the proposed method can be more comprehensive and effective in evaluating the DPV economic access capacity in the distribution network, and proper PV power curtailment can significantly increase the DPV economic access capacity in the distribution network.
The median lifespan of brain malignance diagnosed patients is poor, which indicates that just two out of ten persons identified with brain malignance will live lasting a minimum of a decade, resulting in numerous of i...
详细信息
The median lifespan of brain malignance diagnosed patients is poor, which indicates that just two out of ten persons identified with brain malignance will live lasting a minimum of a decade, resulting in numerous of individuals perish from brain malignance every year. Therefore, early diagnosis is crucial to save lives. Deep learning has drastically altered and enhanced methods for effective and highly accurate diagnosis, prediction, and recognition in recent years. Deep Neural Networks (DNN) are utilized to identify the malignance portion from MRI references. In order to provide a huge data set more affordably, our suggested method makes use of Deep Convolutional Generative Adversarial Network (DCGAN), a pre-processing approach that generates counterfeit pictures that deceive the discriminator into pretending they are real followed by other pre-processing techniques. Then, the separation was done by extracting different Magnetic Resonance Imaging (MRI) angles of the brain were taken into account, and several networks with variable nodes and weight ages were used with the help of an improvedk-meansclustering (kMC) algorithm. Using statistical and texture-based characteristics that are retrieved using the Gray-Level Co-occurrence Matrix (GLCM), the objective of this work's performance evaluation is to differentiate typical and unusual pixels. The model, which separates the pre-processed data into three forms-meningioma, glioma, pituitary, and a plain is trained using an enhanced faster Region-based Convolutional Neural Network (R-CNN). The faster R-CNN method obtains a classification precision of 96%, and sensitivity of 89.23% for Glioma, and a sensitivity of 96.28% for pituitary.
The increasing permeation of the distributed generators in the power system brings great challenges for fault diagnosis, especially for the distribution networks with ungrounded neutral or grounded by Peterson coil as...
详细信息
The increasing permeation of the distributed generators in the power system brings great challenges for fault diagnosis, especially for the distribution networks with ungrounded neutral or grounded by Peterson coil as the fault current is limited and easily affected by the noises and interferences. A single phase-to-ground fault section identification method is proposed based on feature extraction of the synchronous waveforms and the calculation of the eigenvalues for the time-sequenced features. First, several fault features are defined and extracted from the synchronous current waveforms obtained by the fault recorders. Then, the topology related fault feature matrix is constructed using the time-series features obtained from different measurement sites, and the eigenvalues of the matrix are calculated based on the random matrix theory. Lastly, using the distribution characteristics of the eigenvalues, improved k-means clustering algorithm is utilised in classifying the fault cases and identifying the faulty sections. The effectiveness of the proposed scheme is verified by IEEE 34 nodes test system and a multi-feeder distribution network.
暂无评论