Journal of Applied Information, Communication and Technology

Business and System Analysis in Batik Online Platform for Plus Size

Livani Livani, Kho I Eng, James Purnama — Wed, 17 Mar 2021 16:38:23 +0000

Batik industry has mostly been producing apparels only for standard size and none of the online platform that sells batik has been supported body positivity campaign. Another problem is found in the online stores, which do not support multi stores. Most of the existed marketplaces do not provide multi store for the users. There exists platform with multi store capability. However, the users have to pay a substantial amount of fee for the activation [magento]. Therefore, the purpose of this research is to analyze the business process of creating an online platform to sell batik specifically to people with oversize condition with multi stores capability. The multi store capability (done by other research fellows) is part of a project, which includes this research. We have conducted preliminary online research and interview and surveys after the prototype has been launched to get feedback from users. Users believe the idea of the platform and the development is a good start and it has contributed to positive .

Developing a Scalable and Accurate Job Recommendation System with Distributed Cluster System using Machine Learning Algorithm

Timothy Dicky, Alva Erwin, Heru Purnomo Ipung — Wed, 17 Mar 2021 16:42:21 +0000

The purpose of this research is to develop a job recommender system based on the Hadoop MapReduce framework to achieve scalability of the system when it processes big data. Also, a machine learning algorithm is implemented inside the job recommender to produce an accurate job recommendation. The project begins by collecting sample data to build an accurate job recommender system with a centralized program architecture. Then a job recommender with a distributed system program architecture is implemented using Hadoop MapReduce which then deployed to a Hadoop cluster. After the implementation, both systems are tested using a large number of applicants and job data, with the time required for the program to compute the data is recorded to be analyzed. Based on the experiments, we conclude that the recommender produces the most accurate result when the cosine similarity measure is used inside the algorithm. Also, the centralized job recommender system is able to process the data faster compared to the distributed cluster job recommender system. But as the size of the data grows, the centralized system eventually will lack the capacity to process the data, while the distributed cluster job recommender is able to scale according to the size of the data.

Cross-Platform Analysis and Development of Online Catering Platform (Kunyahku)

Indra Swarna, James Purnama, Randy Anthony — Wed, 17 Mar 2021 16:43:56 +0000

Kunyahku is an online catering platform that provides catalogs of menus from local caterer near the user and become the distributor that will take the order and deliver them. In developing an application, the most important aspect for small start-up companies is to have a development stack that can deliver the app into multiple platform by using a single code base to reduce the cost of developers, improve efficiency and reduce the time to develop the application itself. To provide the necessity of building an application for Kunyahku, this paper is aimed to find the most suitable cross platform framework for developing the Kunyahku application. This research focuses on comparison between existing popular cross-platform and proving the suitable one to be used in development cycle in the case of Kunyahku requirements. Sets of test and comparison were conducted in order to compare the most suitable cross platform between React Native and Flutter such as render test and comparing each advantage coming out from using each of the cross-platform.
After all the requirements are gathered and then the most suitable framework will be chosen which is Flutter. Performance analysis and the benefits of using Flutter framework are elaborated and thus proving it is the most suitable development stack to be used in Kunyahku case and the development time can be reduced since it is a cross-platform technology that output the application into three different platform rather than managing separate platform for each different one. Testing shows that flutter also met all the requirements thus proving flutter address the problems of scalability and faster development compared to developing each native platform one by one.

Development of an on-Premise Indonesian Handwriting Recognition Backend System Using Open Source Deep Learning Solution For Mobile User

Gianino Masasi, James Purnama, Maulahikmah Galinium — Wed, 17 Mar 2021 16:39:32 +0000

Existing handwriting recognition solution on mobile app provides off premise service which means the handwriting is processed in overseas servers. Data sent to abroad servers are not under our control and could be possibly mishandled or misused. As recognizing handwriting is a complex problem, deep learning is needed. This research has the objective of developing an on premise Indonesian handwriting recognition using open source deep learning solution. Comparison of various deep learning solution to be used in the development are done. The deep learning solution will be used to build architectures. Various database format are also compared to decide which format is suitable to gather Indonesian handwriting database. The gathered Indonesian handwriting database and built architectures are used for experiments which consists of number of Convolutional Neural Network (CNN) layers, rotation and noise data augmentation, and Gated Recurrent Unit (GRU) vs Long Short Term Memory (LSTM). Experiment results shows that rotation data augmentation is the parameter to be change to improve word accuracy and Character Error Rate (CER). The improvement is 64.8% and 23.2% to 69.6% and 20.6% respectively.

Development of API Middleware and Mobile Application for a Job marketplace by Using RESTful API and Mobile Development Framework

Evan Tirta Wahyudi, Alva Erwin, Charles Lim — Fri, 19 Mar 2021 12:31:17 +0000

The research is conducted based on the nationwide goals of Indonesia proposed in the Nawacita document, where one of the big goals is to improve the human resource greatly. Providing a good medium such as a job marketplace can be part of improving the human resource. Since most of Indonesian citizen nowadays has easy access to internet, which can ease their way of using a job marketplace application. Creating a job marketplace application may minimize a number of unemployment in Indonesia. Addition to that, through a focus group discussion, it has been discovered that respondents find job marketplace such as JobStreet and Indeed jobs does not satisfy respondents’ UI and UX view towards the application. The objective of this research is to create a job marketplace mobile application that is useful and easy to use for users. The prototype mobile application is developed using react native, and a middleware that is developed using Express JS is made alongside to bridge data to the mobile application. To assess the prototype mobile application, two evaluation method is used which is User Experience Questionnaire (UEQ) and Questionnaire User Interface Satisfaction (QUIS). 6 respondents were allowed to examine prototype application, and answer the questionnaire. The result of the evaluation both shows positive results from both questionnaires.