Objective:According to RFM model theory of customer relationship management,data mining technology was used to group the chronic infectious disease patients to explore the effect of customer segmentation on the manage...
详细信息
Objective:According to RFM model theory of customer relationship management,data mining technology was used to group the chronic infectious disease patients to explore the effect of customer segmentation on the management of patients with different ***:170,246 outpatient data was extracted from the hospital management information system(HIS) during January 2016 to July 2016,43,448 data was formed after the data cleaning.k-means clustering algorithm was used to classify patients with chronic infectious diseases,and then C5.0 decision tree algorithm was used to predict the situation of patients with chronic infectious ***:Male patients accounted for 58.7%,patients living in Shanghai accounted for 85.6%.The average age of patients is 45.88 years old,the high incidence age is 25 to 65 years *** was gathered into three categories:1) Clusters 1—Important patients(4786 people,11.72%,R = 2.89,F = 11.72,M = 84,302.95);2) clustering 2—Major patients(23,103,53.2%,R = 5.22,F = 3.45,M = 9146.39);3) Cluster 3—Potential patients(15,559 people,35.8%,R = 19.77,F = 1.55,M = 1739.09).C5.0 decision tree algorithm was used to predict the treatment situation of patients with chronic infectious diseases,the final treatment time(weeks) is an important predictor,the accuracy rate is 99.94% verified by the confusion ***:Medical institutions should strengthen the adherence education for patients with chronic infectious diseases,establish the chronic infectious diseases and customer relationship management database,take the initiative to help them improve treatment *** governments at all levels should speed up the construction of hospital information,establish the chronic infectious disease database,strengthen the blocking of mother-to-child transmission,to effectively curb chronic infectious diseases,reduce disease burden and mortality.
In order to solve the problem of medical supply in the affected areas, we designed a disaster response system to provide medical package transportation and related route detection for five regions. To solve the first ...
详细信息
In order to solve the problem of medical supply in the affected areas, we designed a disaster response system to provide medical package transportation and related route detection for five regions. To solve the first problem, we built two optimization models for 3 D boxing. By considering the size of the medical package and cargo bay, the first model of the number of medical packages required in the affected area was established. Solve the distribution plan of medical package by MATLAB. Then, by considering the size of ISO containers and shipping containers and the number of cargo containers, a three-dimensional packing optimization model is established. Solve in MATLAB to determine the type and number of drones needed. This resulted in a complete disaster response system consisting of a drone fleet and a medical packag To solve the second problem, we use cluster analysis. First, the five disaster areas were classified into three categories to determine the three best cluster centers as the best locations for the three ISO containers. Then, the Euclidean distance was taken as the similarity between the two points, and the three optimal positions were obtained by k-means clustering algorithm as x6=(18.45,-66.40),x7=(18.40,-66.16),x8=(18.27,-68.84)Finally, according to the demand characteristics of the disaster area and the video reconnaissance capability of the drone, the corresponding ISO container was allocated.
This study describes the performance analysis of the non-homogeneity detector (NHD) with various normalisation methods for the space-time adaptive processing (STAP) of airborne radar signals under the non-homogeneous ...
详细信息
This study describes the performance analysis of the non-homogeneity detector (NHD) with various normalisation methods for the space-time adaptive processing (STAP) of airborne radar signals under the non-homogeneous clutter environments. The authors can calculate a threshold value from the statistical analysis of generalised inner product (GIP) using the normalisation method using mean, median and the k-means clustering algorithm of training data snapshots in the NHD process. The selected homogeneous data using the threshold value are used to recalculate covariance matrix of the total interference. To evaluate the performance of the covariance matrix, the authors calculated the eigenspectra and signal to interference noise ratio (SINR) loss. The accuracy of the recalculated covariance matrix is verified by the modified sample matrix inversion (MSMI) test statistic for the target detection. Projection statistics (PS) based on GIP is also used to compare the performance of detecting single and multiple targets. The authors' simulation results demonstrate that the k-means clustering algorithm as a normalisation method for both GIP and GIP-based PS can improve the STAP performance in the severe non-homogeneous clutter environment even under the multiple targets scenarios, compared to the other normalisation methods.
Power data mainly comes from power generation, transmission, consumption, scheduling and statistics. However, in the process of power data acquisition, problems such as data missing seriously affect the further analys...
详细信息
ISBN:
(纸本)9783030000189;9783030000172
Power data mainly comes from power generation, transmission, consumption, scheduling and statistics. However, in the process of power data acquisition, problems such as data missing seriously affect the further analysis. In this paper, we propose a missing data filling method based on improved k-meansclustering and Radial Basis Function neural network (kM-RBF) to solve the problem of missing power data. Firstly, the data samples are clustered by k-means, and the clustering results are used as the parameters of RBF neural network. The RBF neural network is trained with the complete data samples, and then the missing values are predicted. In order to verify the effectiveness of the algorithm, we have chosen the power consumption and power generation metadata of each province in China for analysis and simulated the absence of data. Simulation results show that the kM-RBF can obtain higher accuracy of missing data filling.
The popularization and application of PMU measurement devices in power system provides real-time data monitoring tools for power grid operators. However, the measuring time interval of measuring devices is extremely s...
详细信息
ISBN:
(纸本)9781538633601
The popularization and application of PMU measurement devices in power system provides real-time data monitoring tools for power grid operators. However, the measuring time interval of measuring devices is extremely short. The processing and analysis of the big data generated by measuring devices presents new requirements for the power system, and brings new challenges to the operators. In this paper, the method of parameter estimation of transmission line using cloud computing based on distributed intelligence is studied in depth. An efficient solution aim at processing the big data is given. The k-means clustering algorithm is used to fit the actual situation of the transmission line parameters under the temperature and humidity micro-meteorology. A new way of the mass data application is provided in this paper. The experimental example proves that the cloud computing model based on distributed intelligence can greatly improve the computational efficiency and save the computing time. In addition, the parameters of the transmission line in micro-meteorology conform to the actual operation of the power grid, and early warning can be provided to operators when the real-time operating parameters change suddenly.
RTk is one of the most precise positioning technologies, which has been widely used in many applications. However, in an urban area, GNSS receiver easily receive multipath signals caused by signal reflection and diffr...
详细信息
ISBN:
(纸本)9789811300295;9789811300288
RTk is one of the most precise positioning technologies, which has been widely used in many applications. However, in an urban area, GNSS receiver easily receive multipath signals caused by signal reflection and diffraction by both line-of-sight (LOS) and non-line-of-sight (NLOS) satellites. Multipath signals degrade the phase observation quality and makes it difficult to detect integer ambiguities in RTk positioning. This paper proposes two methods to mitigate multipath effect. In the first method, a least square equation is constructed by using the relationship between the classical satellite elevation angle noise model and the signal-to-noise ratio (SNR) noise model. The least square residual is used to determine NLOS and LOS satellites based on the k-means clustering algorithm. The second method mitigates LOS multipath signal based on the consistency check between prediction residuals and prediction covariance of Extended kalman Filter. Practical experiences show that the proposed tow methods can able mitigate multipath effect and increase the availability of integer ambiguity resolution.
With(1) the rapid development of the Internet, Internet credit business has emerged and the process is now booming. As a result, there is a problem of predicting credit demand of users. Therefore, we propose a method ...
详细信息
ISBN:
(纸本)9781450365123
With(1) the rapid development of the Internet, Internet credit business has emerged and the process is now booming. As a result, there is a problem of predicting credit demand of users. Therefore, we propose a method of using big data analysis to forecast the credit demand of users in this paper, which is used to reduce the risk of credit business and improve the utilization of funds.
The cost of monitoring facilities for the whole active distribution network challenges the electric power companies. This paper proposes a hierarchical evaluation and fault diagnose strategy using the incomplete monit...
详细信息
ISBN:
(纸本)9781538660201
The cost of monitoring facilities for the whole active distribution network challenges the electric power companies. This paper proposes a hierarchical evaluation and fault diagnose strategy using the incomplete monitoring information to decrease the cost of the monitoring facilities. The proposed strategy consists of three levels: the primary level, the middle level and the output level. The k-means clustering algorithm is employed at the primary level. Considering the local incomplete history information and the history fault record information, the k-means clustering algorithm assesses the failure probability of the target area in each cluster. A regional composite failure probability calculation algorithm is proposed at the middle level. Considering the distance from the monitoring area real-time sampling data matrix to each cluster, the proposed algorithm calculates the probability of the real-time monitoring data belonging to each cluster. Combining the cluster belonging probability and the failure probability of each cluster, the proposed algorithm calculate the composite failure probability of the each target area in the active distribution network. An evaluation algorithm based on the maximum composite probability is proposed at the output level. The maximum composite failure probability of each region is used as the overall operation state evaluation coefficient to evaluate the operation status level of the active distribution network. The proposed strategy is tested by the Matlab/Simulink model of a distribution network in Nanjing. Test results show that the proposed strategy can effectively detect the weak areas of the active distribution network. The real-time operating state of the active distribution network is evaluated scientifically.
Convolutional neural networks (CNNs) have been successfully applied in the fields of image classification. The training cost of various large CNN models increases rapidly, which has become a challenging task to balanc...
详细信息
ISBN:
(纸本)9781538666142
Convolutional neural networks (CNNs) have been successfully applied in the fields of image classification. The training cost of various large CNN models increases rapidly, which has become a challenging task to balance the recognition accuracy and the convergence speed in the training procedure of CNN models for a particular dataset. In this paper, a kM-Net model with convolutional kernels in the first layer initialized by k-means clustering algorithm is proposed. Experimental results show that when compared with some other methods on the most widely-used SVHN dataset and ASL dataset, the proposed kM Net model can not only improve the recognition accuracy, but also accelerate the convergence speed of the training procedure.
Estimating of types of states in network systems is essential for protecting network infrastructures from cyberattacks, managing network traffic, and detecting changes in network systems. It is very difficult to estim...
详细信息
ISBN:
(纸本)9781538672327
Estimating of types of states in network systems is essential for protecting network infrastructures from cyberattacks, managing network traffic, and detecting changes in network systems. It is very difficult to estimate the types of states in network systems due to their high complexity. The accuracy of the estimating the states in network systems depends heavily on the completeness of the collected sensor information. But the state of a network system at a given point in time may be never fully known due to noisy sensors;making more difficult to estimate the entire true state of a network system because certain features of the input data may be missing. In order to estimate the states in a network system in partially observable environments, an approach to estimating the types of states in partially observable cyber systems is presented. This approach involves the use of a convolutional neural network (CNN), and unsupervised learning with elbow method and k-means clustering algorithm.
暂无评论