Loiz, Andhika and Baizal, Z. K. Abdurahman (2025) KNN-Based Music Recommender System with Feedforward Neural Network. Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI), 10 (4). pp. 992-1003.
![[thumbnail of 24-KNN-Based Music Recommender System with Feedforward Neural Network.pdf]](http://eprints.uad.ac.id/style/images/fileicons/text.png) |
Text
24-KNN-Based Music Recommender System with Feedforward Neural Network.pdf Download (867kB) |
Abstract
Music, as a form of entertainment, is now an essential element in the lives of many individuals. Access to music-related information has become widespread through various websites and applications, leading to a significant increase in music data. Technological advancements have driven the development of music recommendation system research, which utilizes multiple methods, algorithms, and classification techniques to present recommendations that match user preferences. This research contributes to integrating the K-Nearest Neighbors (KNN) method for initial classification and the more advanced Feedforward Neural Network (FNN) model. In addition, this research also recommends songs with similar audio features. The main focus of this research is to design and evaluate a song recommendation system by combining such methods while comparing various hyperparameter results to find the most suitable model. The best model found will be incorporated into Content-Based Filtering (CBF) to provide song recommendations based on genre. This research uses the GTZAN dataset of 1,000 audio data from ten music genres. The K-NN model test assesses how well the model maintains consistency and achieves optimal performance. This study conducted three tests to find the best-performing model by integrating the model and hyperparameters. The results showed that the third FNN model showed the best performance after being optimized using the SGD optimizer. Furthermore, this model was combined with the CBF method using cosine similarity calculation. The system effectively recommended songs based on the blues genre, with five relevant nearest neighbors and an average score reaching 98%.
| Item Type: | Artikel Umum |
|---|---|
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisi / Prodi: | Faculty of Industrial Technology (Fakultas Teknologi Industri) > S1-Electrical Engineering (S1-Teknik Elektro) |
| Depositing User: | M.Eng. Alfian Ma'arif |
| Date Deposited: | 21 Feb 2025 07:24 |
| Last Modified: | 21 Feb 2025 07:24 |
| URI: | http://eprints.uad.ac.id/id/eprint/82032 |
Actions (login required)
 |
View Item |