Asian Journal of Research in Computer Science
http://journalajrcos.com/index.php/AJRCOS
<p style="text-align: justify;"><strong>Asian Journal of Research in Computer Science (ISSN: 2581-8260 ) </strong>aims to publish high-quality papers in all areas of 'computer science, information technology, and related subjects'. The journal also encourages the submission of useful reports of negative results. This is a quality controlled, OPEN peer-reviewed, open access INTERNATIONAL journal.</p>en-UScontact@journalajrcos.com (Asian Journal of Research in Computer Science)contact@journalajrcos.com (Asian Journal of Research in Computer Science)Wed, 04 Mar 2020 00:00:00 +0000OJS 3.1.1.4http://blogs.law.harvard.edu/tech/rss60Optimization of Multi-Products Distribution by Tabu Search Algorithm (Case Study: Fuel Distribution)
http://journalajrcos.com/index.php/AJRCOS/article/view/30129
<p><strong>Aims: </strong>Determine the vehicle s fuel distribution as distributing case of multi-product based on the number of routes and the total mileage optimal manner using a split delivery tabu search algorithm.</p> <p><strong>Study Design:</strong> Trial percentage loading capacity of the three types of fuel to determine the percentage which gives optimum results.</p> <p><strong>Place and Duration of Study:</strong> Indonusa Surakarta Polytechnic to make the application of a tabu search algorithm to determine the route and calculate the total mileage of the vehicle. The time required 1 month.</p> <p><strong>Methodology:</strong> In this study as a central depot supplier number one, the number of consumers who have served are 19, types of products to be distributed is 3, and the type of transport vehicle used is one where vehicles are not restricted. There are 37 scenarios percentage payload capacity tested in this study to find the percentage of transport capacity which gives optimum results.</p> <p><strong>Results:</strong> The results showed that for three types of fuel distribution to 19 customers, scenarios percentage of premium transport capacity of 25%, 18% kerosene, diesel fuel 57% provide optimal results. Optimal results based on the number of routes of distribution and total mileage. The amount of the distribution as much as 5 routes with a total distance is 9.727 nautical miles.</p> <p><strong>Conclusion:</strong> Tabu search algorithm can be used to complete the Split Delivery Vehicle Routing Problem in the case of multi-product distribution by creating a scenario type of fuel carrying capacity of each product.</p>Sri Wulandari, Norma Puspitasari
##submission.copyrightStatement##
http://journalajrcos.com/index.php/AJRCOS/article/view/30129Wed, 04 Mar 2020 00:00:00 +0000Health Information Analysis of Bank OCBC NISP 2015 - 2019
http://journalajrcos.com/index.php/AJRCOS/article/view/30131
<p><strong>Aims:</strong> Examine the health information of OCBC NISP banks between the relationship of ratio data finance ROA (Return on Assets) between the relationship ROA, NPL, LDR and BOPO data.</p> <p><strong>Study Design:</strong> Statistical methods using the dependent variable is ROA (Return on Assets) and the independent variables namely NPL (Non-Performance Loan), LDR (Loan to Deposit Ratio), and BOPO (Operating Expenditures Operation Income) Data as health information analyzes Quarterly Data from 2015-2019</p> <p><strong>Place and Duration of Study:</strong> Information Systems, Faculty of Engineering, University Widyatama The research was Carried out between October 2019 to January 2020.</p> <p><strong>Methodology:</strong> Collecting the data in this study tries to analyze information between related the data relationships of NPL (Non-Performance Loan), LDR (Loan Deposit Ratio), and BOPO (Operating Expenditures Operation Income) to ROA (Return on Assets) on the bank OCBC NISP in the period 2015-2019 and using the fixed effects method.</p> <p><strong>Results:</strong> The results of this study NPL positive effect on ROA significant with a p-value of 0.6997, the coefficient NPL = +0.0536262, so any increase is in NPL 1% then the the resulting rise in ROA of 0.0536262%. For LDR positive effect on ROA and very significant with a p-value of 0.4301, the coefficient NPL = +0.00210031, so any increase is in NPL 1% then the the resulting rise of 0.00210031% ROA, and vice versa. To BOPO negative effect on ROA significant with a p-value of 0.0002, the coefficient of BOPO = -0.0793051, so any increase is in ROA of 1% then result in a Decrease of 0.0793051% ROA and vice versa.</p> <p><strong>Conclusion:</strong> The correlation between the independent ROA relationship to the NPL, LDR and ROA is related to the bank's health analysis from the coefficient value shown on the R-squared value of 0.980778 to describe a set of independent variables and the dependent variable explained by 98%.</p>Hanafi Mulyadi, T. S. Rae Virgana
##submission.copyrightStatement##
http://journalajrcos.com/index.php/AJRCOS/article/view/30131Fri, 27 Mar 2020 00:00:00 +0000Recommending Curated Content Using Implicit Feedback
http://journalajrcos.com/index.php/AJRCOS/article/view/30130
<p>Matrix factorization (MF) which is a Collaborative filtering (CF) based model, is widely used in the recommendation systems (RS). For our experiment, we collected data from a company's internal web site where curated contents are published and pushed to the employees. However, the size of the dataset is small and interaction data is also limited. We got a sparse matrix when we generated a user-item rating matrix. We have used Multi-Layer Perceptron (MLP) to calculate the rating scores from the implicit feedbacks. However, on this sparse dataset traditional content only or CF-only RSs do not work well. Here, we propose ahybrid RS that incorporates content similarity scores into an MLP-based MF-model. To integrate the content similarity scores into the MF, we have defined an objective function based on a regularization term. The experimental result shows that our proposed model demonstrates a better result than the traditional MF-based models.</p>Debashish Roy
##submission.copyrightStatement##
http://journalajrcos.com/index.php/AJRCOS/article/view/30130Wed, 11 Mar 2020 00:00:00 +0000