scholarly journals MP-K-Means: Modified Partition Based Cluster Initialization Method for K-Means Algorithm

2019 ◽  
Vol 8 (4) ◽  
pp. 1140-1148 ◽  
Keyword(s):  
Clustering Algorithms ◽  
Empirical Evaluation ◽  
Arithmetic Average ◽  
Empirical Results ◽  
Initial Cluster ◽  
And Performance ◽  
Comparative Results ◽  
Clustering Validation ◽  
Range Of Values ◽  
Selection Of

In k-means algorithm, initial cluster centroids are selected arbitrarily which leads to diverse formation of clusters in each run. Consequently, accuracy and performance of k-means is majorly depends on the selection of initial centroids. Thus, the initial cluster centroids shall be chosen carefully to obtain better accuracy and performance of k-means algorithm. In view of this, a new Modified Partition based Cluster Initialization method for k-means called as MP-k-means is proposed in this paper. MP-k-means is an amended version of P-k-means [1] in which the range of values of each dimension is divided into ‘k’ equi-sized partition based on arithmetic average. This division of range into ‘k’ equi-sized partition is affected by outliers present in the data. In order to remove the effect of outliers in P-k-means, the partitioning of each dimension is made based on positional average instead of arithmetic average in MP-k-means. Six popular datasets are used for empirical evaluation of the algorithms. The empirical results are compared and validated based on various external and internal clustering validation measures. The comparative results show that MP-k-means is significantly superior to the basic k-means and P-k-means. The proposed method may also be applied to other clustering algorithms which are based on the concept of selection of initial cluster centroids.

scholarly journals HYBCIM: Hypercube Based Cluster Initialization Method for k-means

2019 ◽  
Vol 8 (10) ◽  
pp. 3584-3587 ◽  
Keyword(s):  
Clustering Algorithms ◽  
Major Effect ◽  
Processing Technique ◽  
Quality Parameters ◽  
Data Sets ◽  
Initial Cluster ◽  
And Performance ◽  
Initial Choice ◽  
Accuracy Performance ◽  
Data Processing Technique

Clustering is a data processing technique that is extensively used to find novel patterns in data in the field of data mining and also in classification techniques. The k-means algorithm is extensively used for clustering due to its ease and reliability. A major effect on the accuracy and performance of the k-means algorithm is by the initial choice of the cluster centroids. Minimizing Sum of Squares of the distance from the centroid of the cluster for cluster points within the cluster (SSW) and maximizing Sum of Square distance between the centroids of different clusters (SSB) are two generally used quality parameters of the clustering technique. To improve the accuracy, performance and quality parameters of the k-means algorithm, a new Hypercube Based Cluster Initialization Method, called HYBCIM, is proposed in this work. In the proposed method, collection of k equi-sized partitions of all dimensions is modeled as a hypercube. The motivation behind the proposed method is that the clusters may spread horizontally, vertically, diagonally or in arc shaped. The proposed method empirically evaluated on four popular data sets. The results show that the proposed method is superior to basic k-means. HYBCIM is applicable for clustering both discrete and continuous data. Though, HYBCIM is proposed for k-means but it can also be applied with other clustering algorithms which are based on initial cluster centroids.

An Initialization Method Based on Hybrid Distance for k-Means Algorithm

2017 ◽  
Vol 29 (11) ◽  
pp. 3094-3117 ◽  
Author(s):  
Jie Yang ◽  
Yan Ma ◽  
Xiangfen Zhang ◽  
Shunbao Li ◽  
Yuping Zhang
Keyword(s):  
Euclidean Distance ◽  
Distance Measure ◽  
Data Sets ◽  
Optimal Result ◽  
Real World Data ◽  
Initial Cluster ◽  
Validation Measure ◽  
Hybrid Distance ◽  
Clustering Validation ◽  
Selection Of

The traditional [Formula: see text]-means algorithm has been widely used as a simple and efficient clustering method. However, the performance of this algorithm is highly dependent on the selection of initial cluster centers. Therefore, the method adopted for choosing initial cluster centers is extremely important. In this letter, we redefine the density of points according to the number of its neighbors, as well as the distance between points and their neighbors. In addition, we define a new distance measure that considers both Euclidean distance and density. Based on that, we propose an algorithm for selecting initial cluster centers that can dynamically adjust the weighting parameter. Furthermore, we propose a new internal clustering validation measure, the clustering validation index based on the neighbors (CVN), which can be exploited to select the optimal result among multiple clustering results. Experimental results show that the proposed algorithm outperforms existing initialization methods on real-world data sets and demonstrates the adaptability of the proposed algorithm to data sets with various characteristics.

Optimal adaptive inspection and maintenance for redundant systems

2021 ◽  
pp. 1748006X2110201
Author(s):  
Chaochao Lin ◽  
Matteo Pozzi
Keyword(s):  
Engineering Systems ◽  
Discounted Cost ◽  
Markov Decision ◽  
Inspection And Maintenance ◽  
And Performance ◽  
Partially Observable ◽  
Series Systems ◽  
Selection Of ◽  
Redundant Systems

Optimal exploration of engineering systems can be guided by the principle of Value of Information (VoI), which accounts for the topological important of components, their reliability and the management costs. For series systems, in most cases higher inspection priority should be given to unreliable components. For redundant systems such as parallel systems, analysis of one-shot decision problems shows that higher inspection priority should be given to more reliable components. This paper investigates the optimal exploration of redundant systems in long-term decision making with sequential inspection and repairing. When the expected, cumulated, discounted cost is considered, it may become more efficient to give higher inspection priority to less reliable components, in order to preserve system redundancy. To investigate this problem, we develop a Partially Observable Markov Decision Process (POMDP) framework for sequential inspection and maintenance of redundant systems, where the VoI analysis is embedded in the optimal selection of exploratory actions. We investigate the use of alternative approximate POMDP solvers for parallel and more general systems, compare their computation complexities and performance, and show how the inspection priorities depend on the economic discount factor, the degradation rate, the inspection precision, and the repair cost.

scholarly journals A Multiple Criteria Decision Making Method to Weight the Sustainability Criteria of System Selection for Surface Mining

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3066
Author(s):  
Michał Patyk ◽  
Przemysław Bodziony ◽  
Zbigniew Krysa
Keyword(s):  
Decision Making ◽  
Performance Assessment ◽  
Multiple Criteria Decision Making ◽  
Surface Mining ◽  
Open Pit ◽  
Mining Equipment ◽  
Surface Mines ◽  
Mining Conditions ◽  
And Performance ◽  
Selection Of

Selection and assessment of mining equipment used in open pit rock mines relies chiefly on estimates of overall exploitation cost. The rational arrangement of mining equipment and systems comprising loading machines, haul trucks and crushing plants should be preceded by a thorough analysis of technical and economic aspects, such as investment outlays and the costs of further exploitation, which largely determine the costs of mining operations and the deposit value. Additionally, the operational parameters of the mining equipment ought to be considered. In this study, a universal set of evaluation criteria has been developed, and an evaluation method has been applied for the selection of surface mining equipment and the processing system to be operated in specific mining conditions, defined by the user. The objective of this study is to develop and apply the new methodology of multi-criteria selection of open pit rock mining equipment based on multiple criteria decision-making (MCDM) procedures, to enable the optimization of loading, handling and crushing processes. The methodology, underpinned by the principles of MCDM, provides the dedicated ranking procedures, including the ELECTRE III. The applied methodology allows the alternative options (variants) to be ranked accordingly. Ultimately, a more universal methodology is developed, applicable in other surface mines where geological and mining conditions are similar. It may prove particularly useful in selection and performance assessment of mining equipment and process line configurations in mining of low-quality rock deposits. Therefore, we undertook to develop universal criteria and applications for the selection and performance assessment of process machines for surface mines, taking into account environmental aspects as well as deposit quality.

SELECTION OF THE SHAPE OF THE LOAD CHARACTERISTICS OF ADAPTIVE FRICTION COUPLINGS WITH SEPARATE POWER CLOSURE

2020 ◽  
Author(s):  
D. A. Ramazanov ◽  
Keyword(s):  
Maximum Point ◽  
Boundary Values ◽  
Power Circuit ◽  
Machine Drive ◽  
Operational Characteristics ◽  
Friction Clutch ◽  
The Coefficient Of Friction ◽  
Load Characteristics ◽  
Range Of Values ◽  
Selection Of

It is established that in practice it is possible to use adaptive friction clutches of the second generation with a separate power circuit, having two different forms of load characteristics: in the form of a curve monotonically increasing in the range of values of the coefficient of friction; in the form of a curve having a maximum point within the specified interval, excluding its boundary values. It is shown that the choice of the type of adaptive friction clutch and its technical and operational characteristics are mainly influenced by the value of the nominal torque and the specified maximum mass of the drive. Three main requirements for adaptive friction clutches operating as part of the machine drive are formulated.

scholarly journals GENETIC DIVERGENCE AND MORPHO-AGRONOMIC PERFORMANCE OF JATROPHA CURCAS L. CLONES FOR SELECTION OF CLONAL VARIETIES

2016 ◽  
Vol 29 (4) ◽  
pp. 841-849
Author(s):  
ADRIANA QUEIROZ DE ALMEIDA ◽  
SIMONE ALVES SILVA ◽  
VANESSA DE OLIVEIRA ALMEIDA ◽  
DEOCLIDES RICARDO DE SOUZA ◽  
GILMARA DE MELO ARAÚJO
Keyword(s):  
Genetic Diversity ◽  
Multivariate Analysis ◽  
Plant Height ◽  
Genetic Divergence ◽  
Morphological Characterization ◽  
Stem Diameter ◽  
Agronomic Performance ◽  
And Performance ◽  
Lower Contribution ◽  
Selection Of

ABSTRACT The knowledge about genetic diversity of jatropha crop is important for genetic conservation resources and breeding of this species. The aim of this study was to evaluate the genetic diversity and performance of jatropha clones through morphological characterization to selection of clonal varieties for biofuels production. The clones were obtained through shoot cuttings from previous selection in a population of half-sibs progenies. The morphoagronomic analyses of clones was carried out at 180 days after transplantation and were evaluated plant height, stem diameter, number of primary branches and number of secondary branches, number of bunches and number of fruits per plant. Evaluating clones performance, significant results were found for the number of secondary branches. About analysis of genetic diversity, the measures of dissimilarity genetic varied from 0.62 to 13.11, this way, the UFRBPR14 and UFRBPR15 clones were more divergent. The Tocher method was efficient to verify formation of four groups. The characteristics that most contributed to the divergence among clones were branches number, height and number of bunches, and, stem diameter had lower contribution. The jatropha clones differed only in the secondary branches number and multivariate analysis showed divergence among the jatropha clones with formation of four groups. Also, branches number, plant height and number of bunches were characteristic that contributed to genetic divergence.

scholarly journals Derivation and Performance of Standardized Enhanced Liver Fibrosis (ELF) Test Thresholds for the Detection and Prognosis of Liver Fibrosis

2019 ◽  
Vol 3 (5) ◽  
pp. 815-826 ◽  
Author(s):  
James Day ◽  
Preya Patel ◽  
Julie Parkes ◽  
William Rosenberg
Keyword(s):  
Liver Fibrosis ◽  
Delphi Panel ◽  
Test Results ◽  
Hazard Ratios ◽  
Test Thresholds ◽  
And Performance ◽  
Using Data ◽  
Relationship Of ◽  
The Relationship ◽  
Selection Of

Abstract Introduction Noninvasive tests are increasingly used to assess liver fibrosis and determine prognosis but suggested test thresholds vary. We describe the selection of standardized thresholds for the Enhanced Liver Fibrosis (ELF) test for the detection of liver fibrosis and for prognostication in chronic liver disease. Methods A Delphi method was used to identify thresholds for the ELF test to predict histological liver fibrosis stages, including cirrhosis, using data derived from 921 patients in the EUROGOLF cohort. These thresholds were then used to determine the prognostic performance of ELF in a subset of 457 patients followed for a mean of 5 years. Results The Delphi panel selected sensitivity of 85% for the detection of fibrosis and >95% specificity for cirrhosis. The corresponding thresholds were 7.7, 9.8, and 11.3. Eighty-five percent of patients with mild or worse fibrosis had an ELF score ≥7.7. The sensitivity for cirrhosis of ELF ≥9.8 was 76%. ELF ≥11.3 was 97% specific for cirrhosis. ELF scores show a near-linear relationship with Ishak fibrosis stages. Relative to the <7.7 group, the hazard ratios for a liver-related outcome at 5 years were 21.00 (95% CI, 2.68–164.65) and 71.04 (95% CI, 9.4–536.7) in the 9.8 to <11.3 and ≥11.3 subgroups, respectively. Conclusion The selection of standard thresholds for detection and prognosis of liver fibrosis is described and their performance reported. These thresholds should prove useful in both interpreting and explaining test results and when considering the relationship of ELF score to Ishak stage in the context of monitoring.

scholarly journals Entrepreneurial Mindset and Performance of Small and Medium Scale Enterprises in Makurdi Metropolis, Benue State-Nigeria

2018 ◽  
Vol 6 (2) ◽  
pp. 124-146 ◽  
Author(s):  
Emmanuel Lubem Asenge ◽  
Hembadoon Sarah Diaka ◽  
Alexander Terna Soom
Keyword(s):  
Social Sciences ◽  
Risk Taking ◽  
Sampling Method ◽  
Critical Factor ◽  
Major Effect ◽  
Policy Makers ◽  
Medium Scale ◽  
Business Opportunities ◽  
And Performance ◽  
Selection Of

Many studies indicates that entrepreneurial mindset is a critical factor in the accumulation, evaluation and selection of the knowledge which can lead an individual into potential business opportunities thereby enhancing entrepreneurial outcomes such as firm performance. This study examined the effect of entrepreneurial mindset on the performance of small and medium scale enterprises in Benue State. The focus of the research was to measure the entrepreneurs’ mindset exhibited through innovativeness, creativity, business alertness and risk taking and how these attributes contributed to the performance of SMEs. The research focused on a population of 650 small and medium scale enterprises based in Makurdi metropolis. A questionnaire was used to collect data from a sample of 250 SMEs in Makurdi metropolis which were selected through stratified random sampling method. Collected data were analyzed using descriptive and inferential statistics with the aid of Statistical Package for Social Sciences (SPSS). Correlation and multiple regression analysis were employed to analyse the data and test the hypotheses. The study revealed that innovativeness, creativity, business alertness and risk taking were significant in affecting performance of SMEs. The study concluded that entrepreneurial mindset or lack of it has a major effect on SMEs performance and if any economy is bended towards development and growth, it would have to embrace this concept. It recommended that all the policy makers and all stake holders should re-strategize and create forums that can promote entrepreneurial mindset among the existing and potential entrepreneurs.

scholarly journals The effect of prominence and cue association on retrieval processes: A computational account

2017 ◽  
Author(s):  
Felix Engelmann ◽  
Lena A. Jäger ◽  
Shravan Vasishth
Keyword(s):  
Sentence Processing ◽  
Cognitive Processes ◽  
Meta Analysis ◽  
Empirical Evaluation ◽  
Experimental Designs ◽  
Empirical Results ◽  
Retrieval Processes ◽  
Context Dependent ◽  
Retrieval Interference ◽  
Partial Success

We present a comprehensive empirical evaluation of the ACT-R-based model of sentence processing developed by Lewis & Vasishth (2005) (LV05). The predictions of the model are compared with the results of a recent meta-analysis of published reading studies on retrieval interference in reflexive-/reciprocal-antecedent and subject-verb dependencies (Jäger, Engelmann, & Vasishth, 2017). The comparison shows that the model has only partial success in explaining the data; and we propose that its prediction space is restricted by oversimplifying assumptions. We then implement a revised model that takes into account differences between individual experimental designs in terms of the prominence of the target and the distractor in memory and context-dependent cue-feature associations. The predictions of the original and the revised model are quantitatively compared with the results of the meta-analysis. Our simulations show that, compared to the original LV05 model, the revised model accounts for the data better. The results suggest that effects of prominence and variable cue-feature associations need to be considered in the interpretation of existing empirical results and in the design and planning of future experiments. With regard to retrieval interference in sentence processing and to the broader field of psycholinguistic studies, we conclude that well-specified models in tandem with high-powered experiments are needed in order to uncover the underlying cognitive processes.

Sign in / Sign up

Export Citation Format

Share Document