Improving Effectiveness of SVM Classifier for Large Scale Data

Balicki, Jerzy; Szymański, Julian; Kępa, Marcin; Draszawka, Karol; Korłub, Waldemar

doi:10.1007/978-3-319-19324-3_60

Cited by 4 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classifier uses the one-vs-near approach instead of the one-vs-all approach in order to limit the dataset during the learning phase [16]. For each category, for which the classifier is trained, the dataset is limited to its closest neighbours.…”

Section: Two Stage Classificationmentioning

confidence: 99%

Two Stage SVM and kNN Text Documents Classifier

Kępa

Szymański

2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

The paper presents an approach to the large scale text documents classification problem in parallel environments. A two stage classifier is proposed, based on a combination of k-nearest neighbors and support vector machines classification methods. The details of the classifier and the parallelisation of classification, learning and prediction phases are described. The classifier makes use of our method named onevs-near. It is an extension of the one-vs-all approach, typically used with binary classifiers in order to solve multiclass problems. The experiments were performed on a large scale dataset, with use of many parallel threads on a supercomputer. Results of the experiments show that the proposed classifier scales well and gives reasonable quality results. Finally, it is shown that the proposed method gives better performance compared to the traditional approach.

show abstract

Section: Two Stage Classificationmentioning

confidence: 99%

Two Stage SVM and kNN Text Documents Classifier

Kępa

Szymański

2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, the impact of climate change on natural hazards is simulated. It is worth mentioning one more interesting project is IBM Blue Brain that try to simulate the human brain, one should reckon with modeling 100 billion neurons and 1 trillion neural connections(Balicki et al, 2015; Hanschel, Monnin, 2005).…”

mentioning

confidence: 99%

Untitled

2023

SPSUTOM

View full text Add to dashboard Cite

This study aims to investigate the effects of working capital management on firm profitability of listed manufacturing companies in Malaysia. Design/methodology/approach: This study uses account payables, inventory turnover, account receivables, cash conversion cycle, firm size, growth, leverage and current ratio as accounting information variables. Secondary data was collected for all variables over a ten-year period, i.e. 2009 to 2018 and was obtained from the annual report published via Bursa Malaysia (Malaysian Stock Exchange) official website. Data was analyzed by using IBM SPSS Statistics Subscription software. Descriptive statistics, correlation analysis and multiple regression analysis were utilized in this study. Findings: The results revealed that inventory turnover in days, account receivables and firm size have a positive significant relationship with manufacturing firms' profitability, while account payables and cash conversion cycle have a positive insignificant relationship. Research limitations/implications:The sample size is too small for any generalization. A mixed method approach in the future could contribute to a holistic finding. Practical implications: Since these variables contained significant influence on firm profitability, it is recommended that listed manufacturing companies should prepare a complete and timely manner of accounting information based on the regulation context in Malaysia. Social implications: It provides an empirical evidence on the importance of working capital management amongst the manufacturing concerns in Malaysia and its impact on its business sustainability. Originality/value: This study contributes to the limited research on working capital management involving manufacturing companies in Malaysia.

show abstract