IJIEEB Vol. 11, No. 5, Sep. 2019
Cover page and Table of Contents: PDF (size: 699KB)
The role of materials in the proper design and operation of products has been acknowledged. An incorrectly selected material for a certain product may cause premature failure of the final product. The right choice of available materials is very important to the success and competitiveness of manufacturing organizations. In Vietnam, tropical monsoon climate conditions greatly affect mushroom cultivation. The raw materials, additives and the ratio between them will also affect the quality and yield of mushrooms. Therefore, selecting the options for growing mushrooms or choosing good materials to grow mushrooms effectively is also a matter of concern. This is a problem of many decision-making problems. In this paper we multi-objective optimization on the basis of ratio analysis (MOORA) method to evaluate mushroom cultivation options in Vietnam.[...] Read more.
This presented research paper mainly studies the frequent itemsets mining approach for finding the most important attribute to overcome the existing problems in the extraction of relevant information by using data mining approaches from a huge amount of dataset. Firstly a state of art diagram for prediction is designed and data mining classifier like naive bayes, support vector machine, decision tree, k- nearest neighbour are compared and then proposed methodology with new techniques are proposed. Moreover, a new attribute filtering association frequent itemsets mining algorithm is presented. Then, by analyzing the feasibility of the proposed algorithm, the data mining classification classifier is compared. As a result, SVM produces the best result among all the classifier with attribute filtrating and without attribute filtrating. With attribute filtrating algorithm enhances the accuracy of all the other classifier.[...] Read more.
Recently, a new dataset has been introduced about the caesarean data. In this paper, the caesarean data was classified with five different algorithms; Support Vector Machine, K Nearest Neighbours, Naïve Bayes, Decision Tree Classifier, and Random Forest Classifier. The dataset is retrieved from California University website. The main objective of this study is to compare selected algorithms’ performances. This study has shown that the best accuracy that was for Naïve Bayes while the highest sensitivity which was for Support Vector Machine.[...] Read more.
The Electronic Fiscal Device (EFD) Machines have been operating in Tanzania since the year 2010 for the purpose of helping the Tanzania Revenue Authority (TRA) to increase revenues from tax collection. Regard-less of years of its existence, there are still reported cases of tax evasion, and this study was conducted to review the current tax collection system and analyze require-ments for the development of Stock Tracking Module (STM) to be embedded in the current tax collection sys-tem. This paper earmarked some problems relating to Electronic Fiscal Device Machine Management System (EFDMS) and EFD machine. Data collection was done in Kilimanjaro and Arusha, the two regions of Tanzania that involved tax officers and Information Technology (IT) personnel from TRA and drug traders. Data collection process involved both qualitative and quantitative methods to gather data for the development of the system Stock Tracking Module (STM) such as interview, questionnaire, role-playing and observation. The major findings of the study: The efficiency of the EFDMS is at average, thus, need some improvements. The major problems encountered by TRA are; under declaration of sales by traders, non-usage of EFD machines, usage of fake EFD, overestimate of expenses, division of business and conducting business in unknown areas. The proposed solution will reduce the existing challenges and increase revenue collections, reduce manual work and human resource, and improve accuracy on tax estimation process.[...] Read more.
Recommending appropriate things to the user by analyzing available data is becoming popular day by day. There are no sufficient researches on Real-estate recommendation with historical data and surrounding environments. We have collected real-estate, historical and point of interest (POI) data from the various sources. In this research, a hybrid filtering technique is used for recommending real-estate consisting of collaborative and content-based filtering. Generally, in every website user ratings are collected for the recommendation. But we have considered historical data and surrounding environments of a real-estate location for recommendation by which it will be easy for a user to decide that which place would be better for him/her. If any user request for any specific location then the system will find the POI data using google map API. Then the system will consider historical data of that area, got from the trusted sources. So considering the minimum price and optimal facilities, our system will recommend top-k real-estate. After extensive experiments on real and synthetic data, we have proved the efficiency of our proposed recommender system.[...] Read more.
Remarkable growth in the electronics and communication field provides ubiquitous services. It also permits to save huge amount of documents on web. As a result, it is very difficult to search a specific and desired information over the Internet. Classical search engines were unable to investigate the content on web intelligently. The tradition searching results has a lot of immaterial information along with desired one as per user query. To overcome from stated problem many modifications are done in traditional search engines to make them intelligent. These search engines are able to analyze the stored data and reflects only appropriate contents as per users query. Semantic Web is an emerging and efficient approach to handle the searching queries. It gathers appropriate information from web pool based on logical reasoning. It also incorporates rule-based system. Semantic web reasonably scrutinizes webs contents using ontology. The learning process of ontology not only intelligently analyze the contents on web but also improves scrutinizing process of search engine. The paper suggests a new keyword-based semantic retrieval scheme for google search engines. The schemes accelerates the performance of searching process considerably with the help of domain-specific knowledge extraction process along with inference and rules. For this, in ontology the prefix keywords and its sematic association are pre-stored. The proposed framework accelerates the efficiency of content searching of google search engine without any additional burden of end users.[...] Read more.