An Improved Hybrid Feature Selection Method for Huge Dimensional Datasets

Kamala, F. Rosita; Thangaiah, P. Ranjit Jeba

doi:10.11591/ijai.v8.i1.pp77-86

Cited by 15 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, this study select corporate governance regime periods as features. It has been widely accepted that corporate governance mechanism enhance best practice in the form of corporate performance [22] and transparency [8]. The effective governance system can reduce tax avoidance as the system has the ability to govern and monitor corporate tax decisions [13].…”

Section: Research Methods 31 Dataset and Features Selectionmentioning

confidence: 99%

“…Motivated by the limitation, this paper attempts to fill the gap by developing model to predict tax avoidance strategies. In the recent Industrial 4.0 era, many recent studies have demonstrated that machine learning and big data mining approaches are effective tools for many problems [6][7][8][9][10] and also for the detection of financial fraud including tax fraud [11]. Despite the wiser used machine learning in many applications, there is limited literature on the development of related to tax avoidance.Therefore, this study has been initiated to fill the gap by looking at the experimental methods of developing tax avoidance classification model based on machine learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An application of machine learning on corporate tax avoidance detection model

Rahman

Masrom

Omar

et al. 2020

IJ-AI

View full text Add to dashboard Cite

Corporate tax avoidance reduces government revenues which could limit country development plans. Thus, the main objectives of this study is to establish a rigorous and effective model to detect corporate tax avoidance to assist government to prevent such practice. This paper presents the fundamental knowledge on the design and implementation of machine learning model based on five selected algorithms tested on the real dataset of 3,365 Malaysian companies listed on bursa Malaysia from 2005 to 2015. The performance of each machine learning algorithms on the tested dataset has been observed based on two approaches of training. The accuracy score for each algorithm is better with the cross-validation training approach. Additionationally, with the cross-validation training approach, the performances of each machine learning algorithm were tested on different group of features selection namely industry, governance, year and firm characteristics. The findings indicated that the machine learning models present better reliability with industry, governance and firm characteristics features rather than single year determinant mainly with the Random Forest and Logistic Regression algorithms.

show abstract

Section: Research Methods 31 Dataset and Features Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An application of machine learning on corporate tax avoidance detection model

Rahman

Masrom

Omar

et al. 2020

IJ-AI

View full text Add to dashboard Cite

show abstract

“…In ODP, metadata are published to describe the datasets under a specified standard format such as DCAT [21]. The portal uses the recommended DKAN framework to build the ODP [22]. The main page of the data portal does not contain any semantic vocabularies.…”

Section: Methodsmentioning

confidence: 99%

Generating RDF resources from web open data portals

Aloufi

2019

IJEECS

View full text Add to dashboard Cite

<span>Open data are available from various private and public institutions in different resource formats. There are already great number of open data that are published using open data portals, where datasets and resources are mainly presented in tabular or sheet formats. However, such formats have some barriers with application developments and web standards. One of the web recommenced standards for semantic web application is RDF. There are various research efforts have been focused on presenting open data in RDF formats. However, no framework has transformed tabular open data into RDFs considering the HTML tags and properties of the resources and datasets. Therefore, a methodology is required to generate RDF resources from this type of open data resources. This methodology applies data transformations of open data from a tabular format to RDF files for the Saudi Open Data Portal. The methodology successfully transforms open data resources in sheet format into RDF resources. Recommendations and future work are given to enhance the development of building open data.</span>

show abstract

“…Audio Feature Extraction is a process done on the collected audio data. The features will allow recognition but high dimensional feaetures casues overfitting [20]. The Cepstral features such as MLE mimics the human preception of sound [21].…”

Section: Audio Feature Extractionmentioning

confidence: 99%

Mel-log energies analysis of authentic audible intrusion activities in a Malaysian forest

Afendi¹,

Yusoff²,

Omar³

2020

Bulletin EEI

View full text Add to dashboard Cite

Wildlife has been endangered due to illegal activities. This requires more effective surveillance measures. Felling timber and poaching are regular illegal activities but challenging to detect. Hence authorities should resort to modern technologies such as employing autonoumous surveillance to stop them. The Malaysian forest audio data were recorded to lay a foundation in initiating a cheaper and practical approach. Hence this paper reports the collection, processing and analysis of audio data in preparation to develop an autonomous sound event detection system. The recording was an emulation of possible illegal activities in a reserved forest. Sounds of chainsaw and hand hatchet cutting tree trunks were taken. It was found that there was a distinct pattern in the Mel-log energies audio feature of the sound, which could be used to identify illegal activities. Thus, it is believed that a detection through audio is a possible approach to be employed as one of the methods to stop illegal activities in the tropical reserve forests like those in Malaysia.

show abstract

An Improved Hybrid Feature Selection Method for Huge Dimensional Datasets

Cited by 15 publications

References 21 publications

An application of machine learning on corporate tax avoidance detection model

An application of machine learning on corporate tax avoidance detection model

Generating RDF resources from web open data portals

Mel-log energies analysis of authentic audible intrusion activities in a Malaysian forest

Contact Info

Product

Resources

About