Garuda - Garba Rujukan Digital

IMPLEMENTASI METODE COLLABORATIVE FILTERING MENGGUNAKAN ALGORITMA COSINE SIMILARITY DAN JACCARD SIMILARITY PADA SISTEM E-COMMERCE Waskito, Muhammad Rizal; Rahajoe, Ani Dijah; Nurlaili, Afina Lina
Jurnal Informatika dan Teknik Elektro Terapan Vol 12, No 3S1 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3S1.5315

Peningkatan pesat e-commerce telah mengubah pola belanja konsumen, menciptakan kebutuhan akan sistem rekomendasi produk yang lebih personal dan relevan. Tantangan yang sering muncul adalah ketidakmampuan sistem rekomendasi dalam menangani data sparsity dan memberikan rekomendasi yang akurat, terutama ketika data pengguna terbatas. Untuk mengatasi tantangan ini, penelitian ini mengimplementasikan metode Collaborative Filtering dengan algoritma Cosine Similarity dan Jaccard Similarity. Cosine Similarity digunakan untuk mengukur kemiripan antar pengguna berdasarkan nilai yang diberikan terhadap produk, sementara Jaccard Similarity fokus pada kesamaan interaksi pengguna tanpa memperhatikan nilai rating. Hasil penelitian menunjukkan bahwa Cosine Similarity cenderung memberikan skor kemiripan yang lebih tinggi dibandingkan Jaccard Similarity, terutama dalam situasi data yang tidak lengkap, dengan rata rata selisih skor sebesar 26.14%. Selain itu, sistem yang dikembangkan mampu memanfaatkan efek Fear of Missing Out (FoMO) untuk meningkatkan relevansi dan urgensi pembelian produk. Integrasi algoritma ini meningkatkan akurasi rekomendasi dan membuka peluang untuk pengembangan lebih lanjut, seperti penerapan hybrid filtering, guna mengoptimalkan kinerja sistem rekomendasi dalam e-commerce.

Artificial Intelligence-Based Expert System for Recirculating Aquaculture Systems in Tulungagung Regency, East Java Rahajoe, Ani Dijah; Sanjaya, Yushinta Aristina; Fauziah, Anna; Zakaria, Rino; Wibowo, Arif Setyo
Plakat : Jurnal Pelayanan Kepada Masyarakat Vol 7, No 1 (2025): Volume 7, Nomor 1, Juni Tahun 2025
Publisher : Fakultas Ilmu Sosial dan Ilmu Politik, Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/plakat.v7i1.18861

Freshwater fish farming in Indonesia plays a crucial role in supporting food security and the economy. UD Tirta Mas Agung Abadi, based in East Java, is a key player in the breeding and cultivation of freshwater ornamental fish, as well as providing feed and aquaculture equipment. The main challenge lies in the complexity of parameters in the recirculating aquaculture system (RAS), such as weather, water quality, temperature, pH, dissolved oxygen, and other chemical contents. The reliance on experts also makes it difficult for farmers to take quick and measured actions in aquaculture management. The first solution proposed is the development of an intelligent system application based on artificial intelligence (expert systems) to efficiently manage RAS parameters. Trials have shown that 95% of respondents found the application met their needs. The second solution involves enhancing the capacity of freshwater ornamental fish farmers through training and mentoring, with 90% of respondents successfully implementing new techniques at their farming locations. These innovations have the potential to improve the efficiency and sustainability of freshwater fish farming in Tulungagung Regency. Budidaya ikan air tawar di Indonesia memegang peranan penting dalam mendukung ketahanan pangan dan perekonomian. UD Tirta Mas Agung Abadi, yang berbasis di Jawa Timur, merupakan salah satu pelaku utama dalam pembenihan dan pembesaran ikan hias air tawar, serta menyediakan pakan dan peralatan budidaya. Permasalahan utama yang dihadapi adalah kompleksitas parameter dalam sistem akuakultur resirkulasi (RAS) seperti cuaca, kualitas air, suhu, pH, oksigen terlarut, dan kandungan kimia lainnya. Ketergantungan pada pakar juga menyulitkan petani untuk menentukan tindakan budidaya yang cepat dan terukur. Solusi pertama yang ditawarkan adalah pengembangan aplikasi sistem cerdas berbasis kecerdasan buatan (sistem pakar) untuk mendukung pengelolaan parameter RAS secara efisien. Uji coba menunjukkan 95% responden merasa aplikasi ini memenuhi kebutuhan mereka. Solusi kedua adalah peningkatan kapasitas petani ikan hias air tawar melalui pelatihan dan pendampingan, dengan hasil 90% responden berhasil mempraktikkan teknik baru di lokasi budidaya mereka. Inovasi ini berpotensi meningkatkan efisiensi dan keberlanjutan budidaya ikan air tawar di Kabupaten Tulungagung.

Hybrid Neural Network-Based Road Damage Detection Using CNN-RNN and CNN-MLP Models Rahajoe, Ani Dijah; Suriansyah, Muhammad; Jr, Angelo A. Beltran
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 3 (2025): JUTIF Volume 6, Number 3, Juni 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.3.4435

Currently, there are many applications of image processing in various fields. One of them is the recognition of paved road images. Detection through images helps in handling infrastructure development roads. With the advancement of technology, especially in the field of deep learning, the process of detecting road damage can be done automatically and more efficiently. The road damage detection system can be integrated into the smart city system to monitor infrastructure conditions in real time. This study will use a combined deep learning algorithm between Convolutional Neural Network- Recurrent Neural Network (CNN-RNN) and as a comparison using Convolutional Neural Network- MultiLayer Perceptrons (CNN-MLP). The study aims to analyze the accuracy of using the CNN-RNN and CNN-MLP algorithms for detecting paved roads that have categories of undamaged roads, damaged roads, and damaged roads with holes. The detection of paved roads has complex details so an algorithm that has good performance with high accuracy is needed. The results of the study showed that the CNN-RNN hybrid had a better accuracy of 96.59 percent than the CNN-MLP hybrid model of 95.9 percent.

KOMBINASI RANK ORDER CENTROID (ROC) DAN MULTI ATTRIBUTE UTILITY THEORY (MAUT) UNTUK SELEKSI CALON PENERIMA KIP-KULIAH Chaurina, Agfanadita Rezkia; Rahajoe, Ani Dijah; Nurlaili, Afina Lina
Jurnal Informatika dan Teknik Elektro Terapan Vol. 13 No. 3 (2025)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v13i3.6641

The low participation rate in higher education in Indonesia remains a major challenge, particularly among students from underprivileged socioeconomic backgrounds. Programs such as KIP-Kuliah are part of the government's efforts to expand educational access, although various implementation challenges persist. At Universitas Pembangunan Nasional “Veteran” Jawa Timur, the number of KIP-Kuliah applicants consistently exceeds the available quota each year, necessitating a selection system that supports fair and accurate decision-making. This study aims to develop a web-based decision support system to assist in the selection process of KIP-Kuliah recipients more systematically. The method combines Rank Order Centroid (ROC) to assign weights to each criterion based on priority ranking and Multi-Attribute Utility Theory (MAUT) to calculate the final score for each alternative. The ranking results are then adjusted according to the recipient quota set for each study program accreditation. Evaluation results show that the system achieved a 96.67% accuracy rate compared to the institution’s manual selection results, indicating its effectiveness in supporting decision-making that is objective, efficient, and transparent.

Optimasi Model Prediksi Kelulusan Mahasiswa Berbasis Principal Component Analysis dan Modified K-Nearest Neighbor Pramnesti, Adisty Regina; Rahajoe, Ani Dijah; Mumpuni, Retno
CICES (Cyberpreneurship Innovative and Creative Exact and Social Science) Vol 11 No 2 (2025): CICES
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/cices.v11i2.3914

Angka drop-out mahasiswa di perguruan tinggi masih menjadi permasalahan serius karena berdampak pada pemborosan sumber daya dan perkembangan institusi. Identifikasi dini terhadap mahasiswa berisiko drop-out sangat penting, namun metode manual dan algoritma K-Nearest Neighbor (KNN) konvensional masih memiliki keterbatasan, seperti sensitivitas terhadap outlier dan data berdimensi tinggi. Penelitian ini mengusulkan integrasi Principal Component Analysis (PCA) dan Modified K-Nearest Neighbor (MKNN) untuk meningkatkan akurasi klasifikasi kelulusan mahasiswa. PCA digunakan untuk mereduksi 14 variabel menjadi 2 variabel utama, sedangkan MKNN memodifikasi KNN dengan teknik weight voting berbasis jarak serta validasi data latih guna mengurangi perngaruh outlier. Model diujikan dengan skema pembagian data 60:40 (latih:uji) dan parameter optimal k=9. Hasil penelitian menunjukkan bahwa kombinasi PCA dan MKNN mampu mencapai akurasi 99,31%, meningkat 0,93% dibanding KNN standar, serta menghasilkan presisi, recall, dan F1-Score sebesar 99,3%. Temuan ini menegaskan bahwa integrasi reduksi dimensi dan weight voting efektif dalam meningkatkan kinerja klasifikasi, sehingga model ini berpotensi menjadi alat prediksi drop-out yang andal di lingkungan pendidikan tinggi.

REAL-TIME DROWSY FACE DETECTION FOR ONLINE LEARNING BASED ON RANDOM FOREST AND DECISION TREE ALGORITHMS Ani Dijah Rahajoe; Subekti, Mohamad Rafli Agung; Suriansyah, Muhammad
Jurnal Teknik Informatika (Jutif) Vol. 4 No. 6 (2023): JUTIF Volume 4, Number 6, Desember 2023
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2023.4.6.1554

In the current era, technology regarding artificial intelligence has developed rapidly and has been used in various areas of life. Face detection is one of the applications of Artificial Intelligence. This research aims to detect students' faces during the online learning process and succeeded in getting positive feedback when tested on students. Student detection includes drowsy and alertness. The method is via webcam in real-time so that the screen will show whether the student is drowsy or alert. In the trial, the teacher can find out who is in a drowsy and alert condition. On the other hand, students can find out that they fall into the drowsy or alert category. So that both parties immediately respond to what should be done based on the classification results. The algorithms used are Decision Tree and Random Forest. The accuracy results of the Random Forest algorithm are better than the Decision Tree algorithm, namely 65 percent, while the Decision Tree algorithm is 58 percent. The division of training data and test data uses a Kfold of 5. When Kfold is equal to 2, both algorithms have the highest accuracy, where Random Forest has an accuracy of 85 percent, and Decision Tre has an accuracy of 65 percent.

IMPLEMENTASI METODE COLLABORATIVE FILTERING MENGGUNAKAN ALGORITMA COSINE SIMILARITY DAN JACCARD SIMILARITY PADA SISTEM E-COMMERCE Waskito, Muhammad Rizal; Rahajoe, Ani Dijah; Nurlaili, Afina Lina
Jurnal Informatika dan Teknik Elektro Terapan Vol. 12 No. 3S1 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3S1.5315

Peningkatan pesat e-commerce telah mengubah pola belanja konsumen, menciptakan kebutuhan akan sistem rekomendasi produk yang lebih personal dan relevan. Tantangan yang sering muncul adalah ketidakmampuan sistem rekomendasi dalam menangani data sparsity dan memberikan rekomendasi yang akurat, terutama ketika data pengguna terbatas. Untuk mengatasi tantangan ini, penelitian ini mengimplementasikan metode Collaborative Filtering dengan algoritma Cosine Similarity dan Jaccard Similarity. Cosine Similarity digunakan untuk mengukur kemiripan antar pengguna berdasarkan nilai yang diberikan terhadap produk, sementara Jaccard Similarity fokus pada kesamaan interaksi pengguna tanpa memperhatikan nilai rating. Hasil penelitian menunjukkan bahwa Cosine Similarity cenderung memberikan skor kemiripan yang lebih tinggi dibandingkan Jaccard Similarity, terutama dalam situasi data yang tidak lengkap, dengan rata rata selisih skor sebesar 26.14%. Selain itu, sistem yang dikembangkan mampu memanfaatkan efek Fear of Missing Out (FoMO) untuk meningkatkan relevansi dan urgensi pembelian produk. Integrasi algoritma ini meningkatkan akurasi rekomendasi dan membuka peluang untuk pengembangan lebih lanjut, seperti penerapan hybrid filtering, guna mengoptimalkan kinerja sistem rekomendasi dalam e-commerce.

Title

Found 17 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 17 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 17 Documents
Search