Search

Many Indonesian spelling errors occur in research papers published to the public, closely related to academics in all institutions such as research institutions, government, schools, and universities. The spelling errors usually writing punctuation, writing letters, writing words, writing words originating from foreign or regional languages (uptake words), using affixed words, and writing ineffective sentences. The mistakes made by the academics then become a cycle in the academic environment. They usually provide guidance for writing an undergraduate thesis, thesis, dissertations to students, or the other forms of documents and scientific papers. Therefore, the research proposed the application to facilitate all authors of scientific papers in producing quality scientific works based on the General Guidelines for Indonesian Spelling published by the Agency for Development and Language Development. The application is named KEBI 1.0 Checker (Indonesian Spelling Error 1.0 Checker), a web-based application with a built-in algorithm to detect and correct Indonesian Spelling in scientific papers. The experiment result shows that the application has given the best accuracy performance to correct the non-standard words, and typographical errors reached 100% and 55,52%, respectively. The application also has been detected 209 meaningless words. The application processing time is relatively low, the average time needed to correct non-standard words is 0.016 seconds, and typo words are 14.58 seconds. KEBI 1.0 Checker is helpful for the end-user in academics but needs to improve the vocabulary of the large corpus in various fields of science for correcting typo words.

needs a solid validation that has verification and matching uploaded images. To solve this problem, this paper implementing a detection model using Faster R-CNN and a matching method using ORB (Oriented FAST and Rotated BRIEF) and KNN-BFM (K-Nearest Neighbor Brute Force Matcher). The goal of the implementations is to reach both an 80% mark of accuracy and prove matching using ORB only can be a replaced OCR technique. The implementation accuracy results in the detection model reach mAP (Mean Average Precision) of 94%. But, the matching process only achieves an accuracy of 43,46%. The matching process using only image feature matching underperforms the previous OCR technique but improves processing time from 4510ms to 60m). Image matching accuracy has proven to increase by using a high-quality dan high quantity dataset, extracting features on the important area of EKTP card images.

Background of this Study: This article examines how digital music handled on music streaming services, JOOX Indonesia in particular. Purposes: The aims was to bring insight that metadata management skill could help an enhancement over music streaming services through metadata and to improve the user experience when using music streaming services. Method:A single case study is chosen as the research method for this paper. The researcher did three months internship to see how the music file handled on the back end of JOOX. Semi-structured qualitative interviews and documentary analysis were used to collect and triangulate the qualitative data. Findings: The result shows JOOX using its operational self-possession procedures to handle its digital music file and using its own metadata standard with adaptation from music metadata standard. JOOX has a feature that utilizes music lyric. We found that lyric metadata embedded as a distinct entity on their backend system. Since lyric frequently used by the user as an access point when they do the retrieval, we propose to embed lyric as a field on music metadata to improve search result. Conclusion: These research shows are lyric as the essential part when users enjoy the music in music streaming services. By embed lyric on music metadata, lyric could be able as an access point for retrieval. Moreover, lyric as metadata could be part of music digital file handling.

Classification is one of the data mining topics that will predict an object to go into a certain group. The prediction process can be performed by using similarity measures, classification trees, or regression. On the other hand, Procrustes refers to a technique of matching two configurations that have been implemented for outlier detection. Based on the result, Procrustes has a potential to tackle the misclassification problem when the outliers are assumed as the misclassified object. Therefore, the Procrustes classification algorithm (PrCA) and Procrustes nearest neighbor classification algorithm (PNNCA) were proposed in this paper. The results of those algorithms had been compared to the classical classification algorithms, namely k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), AdaBoost (AB), Random Forest (RF), Logistic Regression (LR), and Ridge Regression (RR). The data used were iris, cancer, liver, seeds, and wine dataset. The minimum and maximum accuracy values obtained by the PrCA algorithm were 0.610 and 0.925, while the PNNCA were 0.610 and 0.963. PrCA was generally better than k-NN, SVM, and AB. Meanwhile, PNNCA was generally better than k-NN, SVM, AB, and RF. Based on the results, PrCA and PNNCA certainly deserve to be proposed as a new approach in the classification process.

Pada makalah ini, kami membandingkan protokol routing proaktif Optimized Link State Routing (OLSR) dan protokol routing reaktif Ad-hoc on-demand distance vector (AODV) dan Dynamic Source Routing (DSR) pada model propagasi Shadowing dan pergerakan pada mobile adhoc network (MANET). Terdapat dua skenario pengujian, yaitu dampak dari kecepatan pergerakan pengguna dan variasi waktu jeda pengguna dengan mobilitas Random Way Point (RWP). Hasil simulasi menunjukkan bahwa semakin besar kecepatan maka kinerja throughput akan menurun, sedangkan delay dan Normalized Routing Load (NRL) akan meningkat. Semakin lama waktu jeda, semakin lama topologi berubah, akibatnya parameter throughput meningkat sedangkan delay end-to-end dan NRL menurun. OLSR proaktif menunjukkan kinerja terbaik dibandingkan dengan protokol lain berdasarkan parameter throughput, sedangkan AODV reaktif mengungguli penundaan end-to-end dan parameter NRL. Kata kunci: Protokol perutean, shadowing, Mobility, MANET ABSTRACT In this paper, we compared the proactive routing protocols Optimized Link State Routing (OLSR) and the reactive routing protocols Ad-hoc on-demand distance vector (AODV) and Dynamic Source Routing (DSR) in shadowing propagation and mobility model on mobile adhoc network (MANET). There are two test scenarios, such as the impact of user movement velocity and variations in user pause time with Random Way Point (RWP) mobility. In user velocity testing, the greater the speed, the throughput performance will decrease, while the delay and Normalized Routing Load (NRL) will increase. The pause time test describes the dynamics of changing network topology. The longer the pause time, the longer the topology changes, as a result, the throughput parameter increases while the end-to-end delay and NRL decrease. The proactive OLSR shows the best performance compared to other protocols based on throughput parameters, while the reactive AODV outperforms for end-to-end delay and NRL parameters. Keywords: routing protocol, shadowing, Mobility, MANET

Electronic Menu or abbreviated as eMenu is an application that designed to improve the performance of service processes in a business sector, especially restaurants. eMenu aims to change thefood ordering service process that was originally traditional using paper, into web-based digital media. Not only handling food ordering services, eMenu also handles almost all business processes in a restaurant such as menu management, managing information on orders received by waiters and chef, payment transactions, to sales reports. To handle payment transaction, eMenu using third party application payment gateway, called Duitku. eMenu is built using Single-Page Application concept that use AJAX calls which allows time efficiency in displaying the required data. By using the Single-Page Application, the browser does not reload the entire requested page but only part of data is displayed dynamically. The Single-Page Application uses Vue.js as Front-end stack, and Laravel to manage Back-end. eMenu application is responsive design, so that user can access via smartphone or desktop computer with properly.

The main purpose of this paper is to examine the dominant topics about Business Intelligence in micro-blogging Twitter. There are 7.153 tweets collected from Twitter API. Text mining and natural language processing are used to analyze the dominant topics among those tweets. Computational method used to count the most frequent hashtag that appears together with Business Intelligence hashtag. Twitter users are large and scattered around the world with a diverse range of skills (expertise) that can give a new perspective on a subject that may not be predicted before. For example, for topics related to Business Intelligence, the very dominant general topic discussed in the scientific literature are about data management, as well as for analytics and machine learning data. The result contributes to understanding dominant topics about Business Intelligence that can help researchers to level their research.