Saputra, Ananda Hadi (2025) Pengembangan Aplikasi Pemutaran Musik Dengan Design Thinking Dan Pengenalan Emosi Wajah Pengguna. Other thesis, Institut Teknologi Sepuluh Nopember.
![]() |
Text
5025201148-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (3MB) | Request a copy |
Abstract
Emosi merupakan aspek mendasar dalam kehidupan manusia yang memengaruhi kinerja, kesejahteraan, dan interaksi sosial. Individu dengan kecerdasan emosional tinggi mampu mengelola emosi dengan lebih baik, menghadapi tantangan secara positif, dan menjaga keseimbangan psikologis. Salah satu cara efektif untuk memengaruhi emosi adalah melalui musik, yang diketahui dapat merangsang produksi dopamine dan memperbaiki suasana hati. Berdasarkan hal tersebut, penelitian ini bertujuan untuk mengembangkan aplikasi web yang dapat memutar musik sesuai dengan emosi pengguna yang terdeteksi melalui ekspresi wajah menggunakan teknologi Facial Emotion Recognition (FER). Aplikasi ini tidak hanya berfungsi sebagai alat pendukung terapi musik berbasis emosi, tetapi juga memiliki potensi untuk digunakan dalam kehidupan sehari-hari, terutama dalam membantu meningkatkan suasana hati pengguna. Pengembangan aplikasi ini dilakukan dengan metode Design Thinking, yang terdiri dari lima tahap: empathize, define, ideate, prototype, dan testing. Model FER dilatih untuk mendeteksi emosi, menggunakan dataset "Face Expression Recognition Dataset" dari Kaggle. Dalam pengujian ini, beberapa model FER berbasis pada neural network, yaitu MobileNet, Sequential, dan EfficientNetB2. Berdasarkan evaluasi, model MobileNet menunjukkan performa terbaik dengan tingkat akurasi yang lebih tinggi. Kemudian model MobileNet tersebut di deploy ke aplikasi pemutaran musik, hasil pengujian menunjukkan bahwa aplikasi ini berhasil mendeteksi emosi dengan akurasi tinggi, dengan rata-rata skor 4,04 dari pengguna. Sistem pemilihan musik berdasarkan emosi juga memperoleh respons positif, di mana 100% responden menyatakan bahwa musik yang diberikan sesuai dengan emosi mereka. Selain itu, 84% pengguna melaporkan bahwa suasana hati mereka membaik setelah menggunakan aplikasi, dengan rata-rata skor efektivitas sebesar 4,19. Dari segi pengalaman pengguna, aplikasi dinilai sangat mudah digunakan, dengan rata-rata skor kemudahan sebesar 4,81.
====================================================================================================================================
Emotions are a fundamental aspect of human life that affect performance, well-being, and social interactions. Individuals with high emotional intelligence can manage emotions better, face challenges positively, and maintain psychological balance. One effective way to influence emotions is through music, which is known to stimulate dopamine production and improve mood. Based on this, this study aims to develop a web application that can play music according to the user's emotions detected through facial expressions using Facial Emotion Recognition (FER) technology. This application not only functions as a supporting tool for emotion-based music therapy, but also has the potential to be used in everyday life, especially in helping to improve the user's mood. The development of this application was carried out using the Design Thinking method, which consists of five stages: empathize, define, ideate, prototype, and testing. The FER model was trained to detect emotions, using the "Face Expression Recognition Dataset" dataset from Kaggle. In this test, several FER models were based on neural networks, namely MobileNet, Sequential, and EfficientNetB2. Based on the evaluation, the MobileNet model showed the best performance with a higher level of accuracy. Then the MobileNet model was deployed to a music playback application, the test results showed that this application successfully detected emotions with high accuracy, with an average score of 4.04 from users. The music selection system based on emotions also received a positive response, where 100% of respondents stated that the music provided was in accordance with their emotions. In addition, 84% of users reported that their mood improved after using the application, with an average effectiveness score of 4.19. In terms of user experience, the application was considered very easy to use, with an average ease score of 4.81.
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | Emosi, Kecerdasan Emosional, Musik, Facial Emotion Recognition (FER), Design Thinking, Emotions, Emotional Intelligence, Music, Facial Emotion Recognition (FER), Design Thinking |
Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.74 Linear programming T Technology > T Technology (General) > T58.6 Management information systems |
Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis |
Depositing User: | Ananda Hadi Saputra |
Date Deposited: | 03 Feb 2025 02:30 |
Last Modified: | 03 Feb 2025 02:30 |
URI: | http://repository.its.ac.id/id/eprint/117845 |
Actions (login required)
![]() |
View Item |