Due to the effects of prolonged burial,freshly unearthed ancient glass is often weathered to varying degrees,and it is difficult to identify the type of *** introduce machine learning into the composition analysis and...
详细信息
Due to the effects of prolonged burial,freshly unearthed ancient glass is often weathered to varying degrees,and it is difficult to identify the type of *** introduce machine learning into the composition analysis and type identification of ancient glass *** objective is to build a reliable ancient glass classification model based on decision trees and two different k-meansclustering *** performance of the decision tree is measured by the ROC *** performance of its clusteringalgorithm was evaluated by the Calinski-Harabasz *** results show that the area of AUC in the decision tree is 1 and the highest Calinski-Harabasz index of the two clusteringalgorithms is *** predictive ability of the model was verified well.
With the development of E-commerce,the B2 C E-commerce develop *** put forward higher requirements for delivery speed and *** paper studied the vehicle routing problem with soft time windows in B2 C *** improved the t...
详细信息
With the development of E-commerce,the B2 C E-commerce develop *** put forward higher requirements for delivery speed and *** paper studied the vehicle routing problem with soft time windows in B2 C *** improved the tabu search(TS) algorithm,and used k-means clustering algorithm to determine the initial solution to improve the algorithm's convergence *** algorithm was tested by using the data in literature[7].The computing results were compared with those results in the literature [7] to verify the effectiveness of the algorithm.
In view of the characteristics of diversity,openness,complexity of Electric Power Marketing Field *** may be some security risks such as illegal terminal *** the problem of discovery and classification of Electric Pow...
详细信息
In view of the characteristics of diversity,openness,complexity of Electric Power Marketing Field *** may be some security risks such as illegal terminal *** the problem of discovery and classification of Electric Power Marketing Field Terminals is need to be solved,and then we can identify the types of illegal terminals in time and take corresponding *** paper aims at the diversity of Electric Power Marketing Field Terminals and their own differentiation characteristics,and proposes a technology without *** installing client,it can automatically realize terminal discovery,and so solve the traditional problem of non-agent terminal *** the same time,through k-means clustering algorithm terminal model identification,using unsupervised algorithm to extract and identify terminal type fingerprint information,it can achieve accurate classification of terminals,and provide timely alarm information and equipment data for network control and security protection.
In agriculture, paddy crop monitoring placed a crucial role because it supports food security control. Water shortage, high cost of fertilizers, and soil deterioration were identified as some of the difficulties encou...
详细信息
In agriculture, paddy crop monitoring placed a crucial role because it supports food security control. Water shortage, high cost of fertilizers, and soil deterioration were identified as some of the difficulties encountered when monitoring rice crops through satellite images acquired by remote sensing. This study developed a deep learning method-assisted clusteringalgorithm (DLCA) which helps to improve the paddy growth identification process and enables the transparency of agricultural activity. Convolution neural network (CNN) has been utilized to identify crop growth which helps to understand drip irrigation and water scarcity for a particular crop. The experimental research shows that the proposed model is improved in identifying the paddy growth, soil availability, high cost of fertilizers, and soil degradation in monitoring paddy crop production through the satellite image process. Overall, the findings of the experiments have been carried out, and the proposed DLCA to achieve a lower error rate of 0.03 and high accuracy of 98.52%, MCC attains 98.43%, and F1-score 99.02% compared to other popular methods.
We propose a novel approach for the crowd anomaly detection in multiple cameras with non-overlapping view. In this paper, we refer to the activities of crowd in far-field scenes. Firstly, we present a model for learni...
详细信息
ISBN:
(纸本)9781467391054
We propose a novel approach for the crowd anomaly detection in multiple cameras with non-overlapping view. In this paper, we refer to the activities of crowd in far-field scenes. Firstly, we present a model for learning all of the motion patterns under single camera view, which are regarded as the normal situation. In the surveillance region, we mark the entrances and exits under the single camera view and acquire the crowd flow model by the k-means clustering algorithm. Secondly, we analyze the crowd flow model based on the time delayed statistical data between two camera views. And then we acquire the relative location among the entrances and exits in the different regions. Thirdly, we analyze the crowd transferring probabilistic model on the global scene based on the log-likelihood function and Dirichlet distribution to detect the crowd anomaly. We set up the empirical threshold value of probability P_c. If the probability of detected model is less than P_c, the detected model is marked as the crowd anomaly. Our approach is evaluated on the simulated data set and the real data set in far-field scenes. Experimental results show the anomaly detection is precise.
We study cooperative spectrum sensing in cognitive radio networks (CRN) using machine learning techniques in this paper. A low-dimensional probability vector is proposed as the feature vector for machine learning base...
详细信息
ISBN:
(纸本)9781467398152
We study cooperative spectrum sensing in cognitive radio networks (CRN) using machine learning techniques in this paper. A low-dimensional probability vector is proposed as the feature vector for machine learning based classification, instead of the N-dimensional energy vector in a CRN with a single primary user (PU) and N secondary users (SUs). This proposed method down-converts a high-dimensional feature vector to a constant two-dimensional feature vector for machine learning techniques while keeping the same spectrum sensing performance if not better. Due to its lower dimension, the probability vector based classification is capable of having a smaller training duration and a shorter classification time for testing vectors.
Segmentation of the contents of document images into text and non-text regions is an essential pre-processing step for applications such as document analysis and classification, as well as OCR. This paper presents a n...
详细信息
ISBN:
(纸本)9781467348652
Segmentation of the contents of document images into text and non-text regions is an essential pre-processing step for applications such as document analysis and classification, as well as OCR. This paper presents a novel technique to segment the document image into text and non-text regions using a combination of Wavelet-based Gray Level Co-Occurrence Matrix (GLCM) features and k-meansclustering. A comparison between the performances of different wavelets in document image segmentation is also performed and tabulated. The technique was tested on a number of scanned article images from the MediaTeam Document Database and results show a marked improvement over the already existing method based on GLCM features.
Risk budgeting is one of the recent and successful strategies for asset portfolio selection. In this strategy, risk budgets are associated with assets, and the amount of investment is adjusted so that the contribution...
详细信息
Risk budgeting is one of the recent and successful strategies for asset portfolio selection. In this strategy, risk budgets are associated with assets, and the amount of investment is adjusted so that the contribution of each asset to the portfolio risk is proportional to its risk budget. To the best of our knowledge, no specific method has been presented in the literature to systematically determine the value of risk budgets. To fill this research gap, in this article, we consider the risk budgets as decision variables and present a bi-level programming model where the upper level decides the risk budgets and the lower level determines the risk budgeting portfolio. Three approaches are introduced to solve the model. The first is a single-level reformulation of the bi-level model, the second is a novel gradient-based algorithm, and the third is the particle swarm optimization algorithm. Moreover, the k-meansclustering method is utilized to determine the assets involved in the portfolio. Computational results over real-world datasets demonstrate the significance of the bi-level model. In addition, the results confirm the proficiency of our gradient-based algorithm from both solution quality and running time.
暂无评论