Garuda - Garba Rujukan Digital

Perancangan Sistem Informasi Manajemen Ijazah dan Transkrip Nilai Baru di Institut Teknologi Garut Nuraeni, Fitri; Kurniadi, Dede; Hadi Wijaya, Tryana
Jurnal Algoritma Vol 20 No 2 (2023): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.20-2.1395

Submission of diplomas and grade transcripts is an important process in the management of education in tertiary institutions. However, at the Garut Institute of Technology (ITG), the process of submitting diplomas and grade transcripts is still conventional, resulting in obstacles such as long queues and difficulty accessing students who are outside the campus. To overcome these problems, this study aims to design and develop an efficient and integrated management information system for filing new diplomas and grade transcripts. The method used in this study is the Extreme Programming (XP) method. Software development is carried out by utilizing web technology and features such as validation, submission monitoring, email notifications, and submission logs. Students can apply for diplomas and transcripts online through the platform provided, fill out the online submission form, and upload the required documents. Related units, such as BAAK, Libraries, BAK, CDC, LP3B, and Study Programs, can carry out validation and verification processes online. Students can also monitor the progress of their submissions through the monitoring feature and receive notifications via email.

Rancang Bangun Aplikasi Sistem Pakar Diagnosis Penyakit Ikan Air Tawar Menggunakan Forward Chaining Mulyani, Asri; Nuraeni, Fitri; Zaelani, Jaka Muhammad
Jurnal Algoritma Vol 21 No 1 (2024): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.21-1.1420

Diseases in freshwater fish can be grouped into several types, namely diseases caused by bacteria and viruses. This greatly affects the survival of fish, deaths in large numbers result in huge losses for fish farmers because it can cause yields that are not optimal. This research aims to design a web-based expert system for freshwater fish disease diagnosis using the Forward Chaining inference method. The design method used is the Rational Unified Process (RUP). This expert system aims to diagnose freshwater fish diseases. This expert system was developed by involving knowledge from fish experts and a knowledge base that includes freshwater fish symptoms and diseases. The result of this research is a web-based application that uses the Forward Chaining inference method to determine freshwater fish diseases based on the input symptoms. This application involves designing use case diagrams, class diagrams, activity diagrams, sequence diagrams, menu structures and interfaces. Alpha testing has resulted in an accurate system for producing drug administration recommendations based on a knowledge base that has been defined by fish experts. This research concludes that the use of the Forward Chaining inference method in an expert system for diagnosing freshwater fish diseases provides efficient and accurate results in providing recommendations for drug administration. With the existence of an expert system for diagnosing freshwater fish diseases that involves knowledge base sources from fish experts, fish farmers can be more effective in dealing with the symptoms and diseases suffered by fish. This is expected to support a sustainable increase in crop yields.

Aplikasi Sistem Prediksi Mahasiswa Penerima Beasiswa Berbasis Web dengan Menerapkan Model Klasifikasi K-Nearest Neighbors Kurniadi, Dede; Nuraeni, Fitri; Hazar, Aura Fitria
Jurnal Algoritma Vol 21 No 1 (2024): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.21-1.1424

The Indonesian Smart College Card Scholarship or KIP-K is one of the many scholarships provided by the government to continue their education to a higher level for students who excel but are constrained by costs. One of the universities in Garut that provides new student admissions through this scholarship route is the Garut Institute of Technology. Every year, the Garut Institute of Technology always experiences an increase in the number of KIP-K scholarship applicants, however this is not commensurate with the number of quotas obtained so a selection process must be carried out so that the scholarship can be right on target. The selection process itself is carried out manually without the help of a special system that can help select more precisely and efficiently. The aim of this research is to build a web-based prediction system application by applying the K-Nearest Neighbors classification model to help select prospective KIP-K scholarship recipients at the Garut Institute of Technology based on test scores, economic conditions, academic and non-academic achievements of each participant. The classification model is applied in the system as a process of classifying the eligibility of prospective recipients so that the selection process is more focused on participants who are categorized as eligible. The system was built using the waterfall approach method so that system development is more structured. This research produces an application in the form of a web-based prediction system that can help classify eligibility and select prospective KIP-K scholarship recipients at the Garut Institute of Technology with a system accuracy level in predicting participant eligibility of 91.86%.

Algoritma K-Nearest Neighbor pada Kasus Dataset Imbalanced untuk Klasifikasi Kinerja Karyawan Perusahaan Nuraeni, Fitri; Kurniadi, Dede; Diazki, Moch Haiqal
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 11 No 3: Juni 2024
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.938144

Perusahaan perlu menilai kinerja karyawan mereka untuk berbagai tujuan, termasuk promosi jabatan. Namun, data karyawan yang semakin rumit dapat membuat proses penilaian ini menjadi sulit. Penelitian ini bertujuan untuk membuat model machine learning yang dapat memprediksi apakah karyawan berpotensi untuk dipromosikan atau tidak. Penelitian ini menggunakan metode Machine Learning LifeCycle (MLLC) dan algoritma K-Nearest Neighbor. Untuk mengatasi masalah ketidakseimbangan label kelas dalam dataset, teknik SMOTE (Synthetic Minority Over-sampling Technique) digunakan. Hasil dari penelitian ini, model dibangun dengan melakukan pemisahan data menggunakan cross validation dan menggunakan nilai k=2 dalam implementasi algoritma K-Nearest Neighbor. Hasil evaluasi model menunjukkan kinerja yang sangat baik dengan nilai akurasi 94%, nilai presisi 90,8%, dan nilai recall 97,4%. Selain itu, evaluasi confusion matrix menunjukkan bahwa hanya 562 dari 9377 data testing yang tidak sesuai dengan hasil klasifikasi. Model ini juga memiliki kurva ROC yang baik yang hampir menyentuh sudut kiri atas dan nilai AUC sebesar 94,1% atau 0,94 yang termasuk ke dalam kategori excellent.

Rancang Bangun Aplikasi Sistem Pakar Diagnosis Penyakit Ikan Air Tawar Menggunakan Forward Chaining Mulyani, Asri; Nuraeni, Fitri; Zaelani, Jaka Muhammad
Jurnal Algoritma Vol 21 No 1 (2024): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.21-1.1420

Diseases in freshwater fish can be grouped into several types, namely diseases caused by bacteria and viruses. This greatly affects the survival of fish, deaths in large numbers result in huge losses for fish farmers because it can cause yields that are not optimal. This research aims to design a web-based expert system for freshwater fish disease diagnosis using the Forward Chaining inference method. The design method used is the Rational Unified Process (RUP). This expert system aims to diagnose freshwater fish diseases. This expert system was developed by involving knowledge from fish experts and a knowledge base that includes freshwater fish symptoms and diseases. The result of this research is a web-based application that uses the Forward Chaining inference method to determine freshwater fish diseases based on the input symptoms. This application involves designing use case diagrams, class diagrams, activity diagrams, sequence diagrams, menu structures and interfaces. Alpha testing has resulted in an accurate system for producing drug administration recommendations based on a knowledge base that has been defined by fish experts. This research concludes that the use of the Forward Chaining inference method in an expert system for diagnosing freshwater fish diseases provides efficient and accurate results in providing recommendations for drug administration. With the existence of an expert system for diagnosing freshwater fish diseases that involves knowledge base sources from fish experts, fish farmers can be more effective in dealing with the symptoms and diseases suffered by fish. This is expected to support a sustainable increase in crop yields.

Aplikasi Sistem Prediksi Mahasiswa Penerima Beasiswa Berbasis Web dengan Menerapkan Model Klasifikasi K-Nearest Neighbors Kurniadi, Dede; Nuraeni, Fitri; Hazar, Aura Fitria
Jurnal Algoritma Vol 21 No 1 (2024): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.21-1.1424

The Indonesian Smart College Card Scholarship or KIP-K is one of the many scholarships provided by the government to continue their education to a higher level for students who excel but are constrained by costs. One of the universities in Garut that provides new student admissions through this scholarship route is the Garut Institute of Technology. Every year, the Garut Institute of Technology always experiences an increase in the number of KIP-K scholarship applicants, however this is not commensurate with the number of quotas obtained so a selection process must be carried out so that the scholarship can be right on target. The selection process itself is carried out manually without the help of a special system that can help select more precisely and efficiently. The aim of this research is to build a web-based prediction system application by applying the K-Nearest Neighbors classification model to help select prospective KIP-K scholarship recipients at the Garut Institute of Technology based on test scores, economic conditions, academic and non-academic achievements of each participant. The classification model is applied in the system as a process of classifying the eligibility of prospective recipients so that the selection process is more focused on participants who are categorized as eligible. The system was built using the waterfall approach method so that system development is more structured. This research produces an application in the form of a web-based prediction system that can help classify eligibility and select prospective KIP-K scholarship recipients at the Garut Institute of Technology with a system accuracy level in predicting participant eligibility of 91.86%.

IMPLEMENTATION OF MULTIPLE LINEAR REGRESSION ALGORITHM IN PREDICTING RED CHILI PRICES IN GARUT REGENCY Yoga Handoko Agustin; Fitri Nuraeni; Rika Lestari
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 2 (2024): JITK Issue November 2024
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i2.5882

Vegetables, including red chili peppers, play an important role in food and economic balance. Significant price fluctuations and inflation are often problems for farmers and traders. Garut Regency, as the center of red chili production in West Java, faces similar challenges. This research aims to implement a Multiple Linear Regression algorithm to predict the price of red chili peppers in the Garut Regency, highlighting the novelty of using a combination of One Hot Encoding, Feature Engineering, Standard Scaler, and Hyperparameter Tuning techniques. The method used is CRISP-DM with 6 stages: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. The data used is the price and production of red chili peppers per week in 2018-2023, with a total of 702 records. This research involved 8 trials with data transformation and normalization scenarios. The model evaluation used MSE, RMSE, MAPE, R-squared, and statistical hypothesis testing metrics. Results showed 5 significantly influential attributes: year, month, production, net harvested area, and productivity. The best model yielded MSE 202,134,650, RMSE 14,217, MAPE 29.16%, and R-squared 0.320. This approach is simpler yet effective and is able to provide fairly accurate predictions. This research is expected to contribute to providing predictive models that help farmers and traders anticipate price fluctuations, as well as provide insights for policymakers in price management.

Klasifikasi Perputaran Karyawan Perusahaan Menggunakan Algoritma Random Forest dan Random Over-sampling Kurniadi, Dede; Nuraeni, Fitri; Faturrohman, Nadhif; Mulyani, Asri
Edu Komputika Journal Vol 10 No 2 (2023): Edu Komputika Journal
Publisher : Jurusan Teknik Elektro Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukomputika.v10i2.73782

Pergantian karyawan merupakan permasalahan yang berat dalam suatu perusahaan, karena pergantian karyawan dapat menyebabkan kinerja perusahaan menurun akibat kekurangan karyawan. Penelitian ini bertujuan untuk membangun model untuk mengklasifikasikan apakah karyawan akan meninggalkan perusahaan atau tidak untuk mencegah pergantian karyawan. Metode yang digunakan dalam penelitian ini adalah Machine Learning Life Cycle (MLLC). Model dibangun menggunakan algoritma Random Forest dan Random Over-sampling untuk mengatasi data yang tidak seimbang dengan rasio pembagian data untuk data pelatihan sebesar 90% dan data pengujian sebesar 10%. Selain itu untuk mengetahui kinerja model yang dibangun dilakukan evaluasi dengan menggunakan Confusion Matrix dan kurva AUC-ROC. Hasil penelitian ini menunjukkan bahwa model yang dibangun berdasarkan hasil evaluasi mempunyai kinerja yang sangat baik dan hampir sempurna, dengan nilai akurasi sebesar 99,8%, recall sebesar 100%, dan presisi sebesar 99,6%. Hanya terdapat 4 dari 2000 data pengujian yang tidak diklasifikasikan dengan benar, dengan nilai AUC yang dihasilkan sebesar 99,8%, sehingga model termasuk dalam kategori Excellent berdasarkan nilai AUC.

Aplikasi Sistem Pakar Diagnosa Penyakit Kucing Menggunakan Metode Forward Chaining Fatimah, Dini Destiani Siti; Nuraeni, Fitri; Tanpidzia, Mochammad Kahfi
Jurnal Algoritma Vol 21 No 2 (2024): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.21-2.1555

Saat ini banyak masyarakat yang telah menganggap menjaga hewan peliharaan sebagai salah satu hobi yang populer, hal ini dikarenakan hewan peliharaan mampu menjadi teman yaang setia bagi mereka. Di antara berbagai pilihan hewan peliharaan, kucing menjadi pilihan favorite di kalangan masyarakat karena kucing dikenal sebagai hewan mamalia yang mudah bersahabat dan mampu beradaptasi dengan baik. Meski demikian hal tersebut tidak diimbangi dengan pengetahuan pemeliharaan kucing. Banyak dari para pemilik kucing belum sepenuhnya memprioritaskan pengawasan terhadap kondisi kesehatan kucing peliharaan mereka, yang mengakibatkan renta terhadap risiko penyakit. Langkah pencegahan yang efektif untuk melindungi kucing dari penyakit dan mengenali gejalanya adalah dengan menjadwalkan kunjungan rutin ke dokter hewan. Namun banyak pemelihara kucing yang mengabaikan hal tersebut dikarenakan kuangnya biaya dan keterbatasan waktu. Oleh karena itu, perlu adanya media yang dapat diakses dengan mudah dari dimana saja dan kapan saja, yaitu melalui sistem pakar. Supaya pemilik kucing dapat menangani penyakit yang dialami oleh kucing dengan baik dan benar. Penelitian ini memiliki tujuan untuk membangun sebuah sistem pakar berbasis website dengan mengadopsi metode Expert System Development Life Cycle (ESDLC) sebagai kerangka kerja pengembangan sistem dan Forward Chaining yang menjadi metode inferensi. Penelitian ini diharapkan dapat membantu dan mempermudah pemilik kucing dalam proses mendiagnosis penyakit pada kucing.

Implementasi Superenkripsi Dsa dan Aes 128 Bit Dalam Pengamanan File Surat Digital Nuraeni, Fitri; Amrulloh, Muhammad Fawaz; Mulyani, Asri; Kurniadi, Dede
Jurnal Algoritma Vol 22 No 1 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-1.1832

Digital signatures are important for companies to overcome distance and time constraints. Therefore, a digital signature system is needed that is not only efficient but also has a high level of security to prevent data falsification or document legality. This research contributes to improving data security and integrity by implementing DSA and AES 128 Bit superencryption in the “Paperless Room” Digital Signature application. The implementation of the technology used is such as ReactJS, NodeJS, NextJS, cryptography modules in JavaScript, and PostgreSQL databases. Evaluation is done through penetration testing and measurement of encryption and decryption performance. The results show that this superencryption successfully improves efficiency and security, with an average encryption time of 165.67 ms and decryption of 98.17 ms, as well as an entropy value of 6.2837 which reflects a high level of security. In comparison, using DSA alone requires a longer encryption time of 242.97 ms and decryption of 312.83 ms, with a lower entropy of 4.8663. These findings confirm that DSA and AES-128 superencryption offer an optimal combination of efficiency and security for securing digital mail files in an enterprise environment.

Title

Found 75 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 75 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 75 Documents
Search