Opening new lines will bring the structural change of passenger flow characteristics in network operation of Urban Rail Transit. Based on the smart card data from Shenzhen Metro, temporal-spatial characteristics was d...
详细信息
ISBN:
(纸本)9781450360449
Opening new lines will bring the structural change of passenger flow characteristics in network operation of Urban Rail Transit. Based on the smart card data from Shenzhen Metro, temporal-spatial characteristics was discussed comprehensively from different statistics dimensions and analysis angles. At the same time, passenger flow in 28 transfer stations was analyzed by clustering algorithm and the land use nature was attained. Consequently, the passenger flow law in Shenzhen Metro will be understood better combined with visualization. Especially, when facing the risk of large passenger flow, targeted measures can be taken in advance to improve the safety and resilience of Shenzhen Metro.
In order to improve the lifetime and throughput of wireless sensor networks under the limited power, an improved clustering algorithm is proposed in this paper on the basis of LEACH protocol. The energy factor is cons...
详细信息
In order to improve the lifetime and throughput of wireless sensor networks under the limited power, an improved clustering algorithm is proposed in this paper on the basis of LEACH protocol. The energy factor is considered in this algorithm. The residual energy of all sensor nodes is referred to select cluster-heads of wireless sensor networks. The new clustering algorithm effectively improves the energy efficiency, throughput and lifetime of wireless sensor networks. The results are proved by simulations.
Real-time monitoring of surface water quality is an intractable problem. A Soft-sensor method based on fuzzy neural network(FNN) is proposed to solve this problem in this paper. Firstly, the river data was analyzed by...
详细信息
Real-time monitoring of surface water quality is an intractable problem. A Soft-sensor method based on fuzzy neural network(FNN) is proposed to solve this problem in this paper. Firstly, the river data was analyzed by principal component analysis(PCA) to obtain related variables such as dissolved oxygen(DO) and ammonia nitrogen(NH3-N). Secondly, a multi-input soft-sensor method based on FNN is designed. The training data is preprocessed by Hierarchical clustering and K-means algorithm(H-K algorithm), which improves the accuracy of the soft-sensor method. Finally, the soft-sensor method is packaged and applied to Beijing Tonghui River. The results indicate that the FNN based soft-sensor can predict surface water quality simultaneously with suitable prediction accuracy.
Recently a density peaks based clustering algorithm (dubbed as DPC) was proposed to group data by setting up a decision graph and finding out cluster centers from the graph fast. It is simple but efficient since it is...
详细信息
Recently a density peaks based clustering algorithm (dubbed as DPC) was proposed to group data by setting up a decision graph and finding out cluster centers from the graph fast. It is simple but efficient since it is noniterative and needs few parameters. However, the improper selection of its parameter cutoff distance d(c) will lead to the wrong selection of initial cluster centers, but the DPC cannot correct it in the subsequent assignment process. Furthermore, in some cases, even the proper value of d(c) was set, initial cluster centers are still difficult to be selected from the decision graph. To overcome these defects, an adaptive clustering algorithm (named as ADPC-KNN) is proposed in this paper. We introduce the idea of K-nearest neighbors to compute the global parameter d(c) and the local density pi of each point, apply a new approach to select initial cluster centers automatically, and finally aggregate clusters if they are density reachable. The ADPC-KNN requires only one parameter and the clustering is automatic. Experiments on synthetic and real-world data show that the proposed clustering algorithm can often outperform DB-SCAN, DPC, K-Means++, Expectation Maximization (EM) and single-link. (C) 2017 Elsevier B.V. All rights reserved.
We explore the use of M-ary frequency shift keying (FSK) as an integrated modulation/random access scheme for wireless sensor networks whereby multiple sensor nodes may transmit data simultaneously to a master node. S...
详细信息
We explore the use of M-ary frequency shift keying (FSK) as an integrated modulation/random access scheme for wireless sensor networks whereby multiple sensor nodes may transmit data simultaneously to a master node. Specifically, we propose exploiting the presence of multiple signal dimensions and using a clustering algorithm to estimate blindly the channel gains required for coherent multi-user detection. To demonstrate the feasibility of this concept, we simulate the bit error rates (BER) of 4FSK and 8FSK systems with three and four simultaneously transmitting sensor nodes, respectively. It was found that the BER of the proposed blind multi-user detector is very close to that achieved under perfect channel state information. This suggests that the proposed integrated modulation/randomaccess approach can significantly improve spectral efficiency and mitigate multi-user interference. Compared to no multi-user detection, less energy is wasted on the retranmissions caused by packet collisions and this helps to extend the lifetime of the sensor nodes.
We consider a type of covering problem in the e-commerce enterprise retail distribution network, the problem amounts to determining the location of the warehousing and distribution center. In order to adapt to the e-c...
详细信息
ISBN:
(纸本)9781510888050
We consider a type of covering problem in the e-commerce enterprise retail distribution network, the problem amounts to determining the location of the warehousing and distribution center. In order to adapt to the e-commerce distribution mode and ensure timely delivery, a demand point can be covered by multiple distribution centers, a set multi-coverage model with the shortest distribution distance and the minimum construction cost as the dual target is established to determine the location of the distribution center. Finally, the example is solved in IBM CPLEX, and the calculation results verify the effectiveness of the algorithm and model.
At present, with the popularization of drone technology, intelligent cluster UAV control technology has been paid more and more attention. However, with the increase of wireless group network nodes in the control proc...
详细信息
ISBN:
(纸本)9781728113012
At present, with the popularization of drone technology, intelligent cluster UAV control technology has been paid more and more attention. However, with the increase of wireless group network nodes in the control process of traditional intelligent cluster drones, the network communication performance also decreases. In this paper, based on wireless ad hoc network communication technology, an optimized weighted clustering algorithm is proposed. The effective clustering algorithm is used to divide the network into clusters, assign different weights to different nodes to form clusters, and discuss clusters in four different situations. Maintenance method. This paper designs and carries out the simulation experiment of UAV information transmission network. Experiments show that the algorithm can effectively improve the performance of large-scale mobile ad hoc networks.
Power industry is one of the important fields in the application of big data technology. Power big data is generated in every link of power production and contains rich commercial and social values. It is necessary to...
详细信息
ISBN:
(纸本)9781538685495
Power industry is one of the important fields in the application of big data technology. Power big data is generated in every link of power production and contains rich commercial and social values. It is necessary to implement the analysis of electric power user behavior based on big data technology. This paper presents a comprehensive study on the analysis of power user behavior based on big data. The characteristics and application challenges of electric power big data are first introduced, followed by the extraction of power user side big data processing mode. Finally, this paper focuses on the main methods of data mining and analysis and discusses the clustering analysis algorithms to make better analysis of electric power user behavior.
Load curve data from advanced metering infrastructure record the consumers' behavior. User consumption models help one understand a more intelligent power provisioning and clustering the load data is one of the po...
详细信息
Load curve data from advanced metering infrastructure record the consumers' behavior. User consumption models help one understand a more intelligent power provisioning and clustering the load data is one of the popular approaches for building these models. Similarity measurements are important in the clustering model, but, load curve data is a time series style data, and traditional measurement methods are not suitable for load curve data. To cluster the load curve data more accurately, this paper applied an enhanced Pearson similarity for load curve data clustering. Our method introduces the 'trend alteration point' concept and integrates it with the Pearson similarity. By introducing a weight for Pearson distance, this method helps to keep the whole contour of the load data and the partial similarity. Based on the weighed Pearson distance, a weighed Pearson-based hierarchy clustering algorithm is proposed. Years of load curve data are used for evaluation. Several user consumption models are found and analyzed. Results show that the proposed method improves the accuracy of load data clustering.
Since the first introduction of integrated circuits (ICs), there has been dramatic improvements in semiconductor manufacturing technologies. To minimize even slightest faults in manufacturing processes, many studies a...
详细信息
ISBN:
(纸本)9781538679753
Since the first introduction of integrated circuits (ICs), there has been dramatic improvements in semiconductor manufacturing technologies. To minimize even slightest faults in manufacturing processes, many studies are being conducted to systematically analyze the causes of faults. In this paper, we propose an algorithm that finds the causes of faults by clustering the fault detection results. Our experiments show that our algorithm forms good clusters of runs having similar sources of faults.
暂无评论