The emotional component in a music classification is more powerful than the others. This research addresses a music emotion classification. A hierarchical classification system using a Support Vector Machine (SVM) and a k-Nearest Neighbors (kNN) is proposed. The experiments using 120 pop-rock music data with the emotional label based on the AllMusicGuide website split into four classes: "Happy", "Angry", "Sad", and "Relax" show that the proposed hierarchical model is capable of increasing the absolute performance of music emotion classification by 19.33% in the SVM (Kernel: RBF) and 13.33% in the kNN (k = 5). The best combination three-level classifier, the arrangement of the three best classifiers for each level in hierarchical music emotion classification is by using the SVM (Kernel: Linear) classifier at Level 1, then kNN (k = 3) at Level 2.1 and Level 2.2.

​

Published in: 2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

Have sleep difficulties? SleepMuse provides you with deep breathing exercises accompanied by relaxing music to help lower your heart rate and bring you to a relaxed state, ready to fall asleep. ☁️

​

Our features include:
🧘‍♂️ Breathing exercise with voice instructions
🎼 A range of music options
🛌 Sleep reminder
⏰ Timer to automatically turn off the music

Fall asleep faster with SleepMuse! 💤

ConnectyBike is a solution for all people who own a motorcycle where they can track their bikes through their smartphones. With the motorbike stealing problem among college students at Telkom University, we did a design thinking process and made a "ConnectyBike" prototype.​

Be an explorer an conquer the zoo with Jeera.

Jeera helps Zoo visitors who want to see animals by providing directions for the nearest road and animal information around visitors. Thus, visitors can have a pleasant experience while exploring Zoo to see as many animals as possible.

GET DIRECTION
Visit the animals by following the directions, you can choose any animal you want to see and get the best route

ANIMAL FEEDING TIME
Who loves animal feeding time? Yup, Jeera will notifiy you. So, it won't be missed

ANIMAL FUN FACTS
Get to know animals with interesting information

“Bermain bersama Huruf”
Translation: “Playing with Letters”

Batca is a native iOS App that helps 1st to 3rd-grade Indonesian students with Dyslexia to practice their reading skills. This app gives users a series of lessons with pictures and texts to visualize both the object and the shape of the word and audio to help them know how to pronounce the word properly. There are quizzes to test their skills and also to know their learning progress.

In the fierce competition of product sale, in recent years product owners have used the services of Artists and Celebrities to co-promote the products they sell called endorsements. One way the celebrities promotes the products they endorse is through various online social media like Facebook, Twitter, or Instagram. However, there are many cases where product owners merely choose any famous celebrities to promote their products based on the fame of the artist without a proper analysis. We think that it is important to consider the chance of sales success viewed from a match between promoted items and the tastes or likeness of the artist's fans. In this paper, we propose a method to automatically recommend what types of product to endorse for an Instagram user based on his/her followers' profiling. We use Instagram to perform a user profiling to determine what the follower users like based on annotation tags of the images they upload. By using a clustering method to group the followers, we were able to provide an endorsement recommendation to a user that matched with the followers' preferences.

​

Published in: 2018 6th International Conference on Information and Communication Technology (ICoICT)