Papers by Keyword: Clustering Analysis (CA)

Abstract: Aim at the problem that there is an irregular data distribution when using multi-sensor to monitor machine conditions, a genetic clustering algorithm using geodesic distance metric (GCGD) is adopted to perform machine fault detection. In GCGD, a geodesic distance based proximity measure is employed replacing Euclidean distance that cannot correctly describe the relationship between data lying in a manifold, and GCGD determines partitioning of the feature vectors from a combinatorial optimization viewpoint. Fault detection experiments of inlet valve leakage in a two-stage reciprocating compressor reveal that GCGD achieves a better performance of fault detection than the K-means algorithm and a genetic algorithm based clustering technique.

Abstract: Based on the most prosperous System on Chip (SOC) in the field of microelectronics, the open and real-time robot controller was analyzed, the application and development platform was built. By means of representative evaluation index, cohesion and coupling, the modularized design and the open architecture of robot controller were implemented. It is proved that the average distance between the same modules is short, and therefore the system is better cohesive. And the average distance between different modules is long, and therefore less coupled. Consequently, the whole system is excellent in openness. At the same time, the real-time schedule of controller tasks is analyzed from theory and experiment. It is proved that the controller based on SOC is excellent in real-time performance. The experiment showed that SOC-based robot controller is highly modularized, the parameters is clear, the architecture is easily implemented and revised, and therefore is adaptive to different controlling requirement and module building.

Abstract: Transferring plays an important role between different lines of urban rail transport and routine public transit. The convenience of a transfer station not only directly affects the efficiency of the whole traffic network, but also is a key factor that influences travel convenience. Based on GIS, through the study of the convenience at the 16 subway transfer stations in Beijing, the article tries to find the relationship of the evaluations on the transferring between metro-metro and metro-bus. Finally, by further clustering analysis on the spatial distributions of the transferring evaluations, this article reveals the existing problems of the layout of transfer stations and proposes several effective suggestions and countermeasures for them.

Abstract: Accompany with fast development of location technology, more and more trajectories datasets are collected on the real applications. So it is something of value in the theory and applied research to mine the clusters from these datasets. In this paper, a trajectory clustering algorithm, called Density-Based Spatial Clustering of Application with noise (Tra-DBSCAN for short), based on DBSCAN that is a classic clustering algorithm. In this framework, each trajectory firstly partitions into sub-trajectories as clustering object, and then line hausdorff distance is used to measure the distance between two sub-trajectories. Next, DBSCAN is introduced to cluster sub-trajectory to form cluster area, and then connecting different moments of clustering area is regarded as trajectory movement patterns. Finally, the experimental results show our framework’s effective.

Abstract: The thesis introduces traffic patterns definition and identification. Combined with actual project it has established the regional traffic signal coordination and control system based on particle swarm K-means clustering algorithm pattern identification. It puts forward system structure and working principles with discussions focused on several key problems existing in traffic pattern identification process.

Abstract: Major domestic oil fields have entered the period of high water now, however, choosing timing of profile control and water shutoff is always delay, Mostly have to wait until after the adoption of dynamic degradation. This article introduced the concept of early warning that is widely used in military and economic fields to profile control and water shut-off decision-making in high water-cut stage. Combination of actual situation of water shut-off decision-making, Presented a strong adaptive set of Warning signs of indicators, on the basis of the analysis of variation in the warning sighs of indicators, this paper proposed early warning model and processes of profile control and water shut-off. The model not only can give the current degree of a single well, but also can forecast the future degree of change in a period of time, so this modle could provide an effective basis for water shutoff and profile controle decision-makers.

Abstract: An improved fabric color separation method is put forward based on genetic fuzzy clustering algorithm.At first, adopt six basic primary colors are used to carry on color separation to images of fabric including C(blue), M(magenta), Y(yellow), G(green), K(black) and W(white),and the data set of fuzzy cluster is formed , consequently, the division of fuzzy cluster can be completed, at last Genetic-fuzzy cluster algorithm is applied to color separation of decorated Jacquard fabric. The experimental results show that the fidelity of fabric patterns after color separation using this improved method is superior to that after color separation using traditional color separation method

Abstract: From the 1990s, China's higher education has experienced a rapid development, which provides Talents guarantees for Chinese economic rise and the development of social undertakings. Colleges and universities as an important carrier of higher education, attract more investments from national financial departments at all levels, social organizations and students’ families. The college education resource management increasingly becomes a hot social concern, arousing more and more scholars' research interests. Research indicates that the value of education input can be evaluated. In china, the higher education resources are infrequent, and the using efficiency can not be evaluated by analysis educational economic income of individual. This paper did a profound research on benefit of higher education from input angle based on the main components and clustering analysis method in multivariate statistics, using SPSS and R software. The result has prominent theoretical significance and practical value for high education resources management.

Abstract: In continuous casting, it is very important to predict and detect the internal cracks of billet in time for ensuring continuous production, improving product quality and reducing production costs. In this paper, Clustering analysis method is adopted to do feature extraction and classification for on-site data, by which ladder parameter tables of processing parameters and defect grades of internal cracks are got. Fault tree analysis (FTA) method is adopted to analyze the effects of processing parameters on internal cracks. The solidification speed of billet is calculated by solidification heat-transfer model. Quality prediction model of internal cracks in continuous casting billet is established by quality prediction function, based on clustering analysis model of on-site data, FTA model and solidification heat-transfer model. Some samples of Steel Grade 1008 are selected for testing the quality prediction model. The percentage of accuracy for the quality prediction is 80 percent, which provides the foundation for industry application.

Abstract: Affinity Propagation(AP)is a new clustering algorithm, which is based on the similarity matrix between pairs of data points and messages are exchanged between data points until clustering result emerges. It is efficient and fast , and it can solve the clustering on large data sets. But the traditional Affinity Propagation has many limitations, this paper introduces the Affinity Propagation, and analyzes in depth the advantages and limitations of it, focuses on the improvements of the algorithm — improve the similarity matrix, adjust the preference and the damping-factor, combine with other algorithms. Finally, discusses the development of Affinity Propagation.