Article Per Year (5 Year)
p-Index From 2020 - 2025
3.498
P-Index
This Author published in this journals
All Journal ComEngApp : Computer Engineering and Applications Journal Jurnal Online Mahasiswa (JOM) Bidang Ilmu Sosial dan Ilmu Politik Jurnal CoreIT INOVTEK Polbeng - Seri Informatika Building of Informatics, Technology and Science JTIM : Jurnal Teknologi Informasi dan Multimedia JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Journal of Computer System and Informatics (JoSYC) Information System Journal (INFOS) Jurnal Computer Science and Information Technology (CoSciTech) Bulletin of Computer Science Research KLIK: Kajian Ilmiah Informatika dan Komputer Bulletin of Information Technology (BIT) Malcom: Indonesian Journal of Machine Learning and Computer Science Indonesian Journal of Innovation Multidisipliner Research Scientific Journal of Informatics INOVTEK Polbeng - Seri Informatika
Fitri Insani
Bogor Agricultural University
Religion Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Social Sciences Other

Published : 28 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : Building of Informatics, Technology and Science

 1 
Implementasi Metode Learning Vector Quantization (LVQ) Untuk Klasifikasi Keluarga Beresiko Stunting Aziz, Abdul; Insani, Fitri; Jasril, Jasril; Syafria, Fadhilah
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3478

Abstract

Stunting is a condition where a child's height is too short compared to children of the same age. This condition affects the health of toddlers in the short and long term, such as suboptimal body posture in adulthood, decreased reproductive health, and decreased learning capacity, resulting in suboptimal performance in school. One of the causes of stunting is a lack of nutrition, basic health facilities, and poor parenting practices. However, the current data collection and classification of families at risk of stunting still use Microsoft Excel, which is ineffective in processing large data. Therefore, the LVQ method, which is an improvement of the Vector Quantization method, is used to accelerate the classification process. In this study, 5 parameters were tested, and the optimal result was achieved by using 7 input neurons, Chebychev distance as the distance measure, a learning rate of 0.1, 7 epochs, and 30% of training data. With these parameters, an accuracy of 99.38% was obtained. Based on these results, the LVQ method can help improve accuracy in classifying families at risk of stunting
Penerapan Deep Learning Menggunakan Gated Recurrent Unit Untuk Memprediksi Harga Minyak Mentah Dunia Saputra, Nugroho Wahyu; Insani, Fitri; Agustian, Surya; Sanjaya, Suwanto
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3552

Abstract

Crude oil is a much-needed energy for the whole world. Each country is inseparable from the use of crude oil for use in various sectors, such as transportation, so that the price of world crude oil is the most important variable for the world. Fluctuations in oil prices will cause various problems, such as inflation, changes in market prices, and others. Therefore, the prediction of world crude oil prices is very important as a consideration for decision making. This study implements deep learning using the Gated Recurrent unit model. The data used is the price of Brent crude oil with a total of 5834 data, starting from January 4, 2000 to December 19, 2022. The parameters used are the number of GRU units, batch size, and lookback. The best model produced in this study is the GRU model with hyperparameters consisting of 30 lookbacks, 50 GRU units, and 256 batch sizes with the lowest MAPE value among the other models, which is 2.25%. The MAPE value states that predictions using the GRU model are said to be very good at predicting world crude oil prices
Analisis Pola Asosiasi Data Transaksi Penjualan Minuman Menggunakan Algoritma FP-Growth dan Eclat Najmi, Risna Lailatun; Irsyad, Muhammad; Insani, Fitri; Nazir, Alwis; ., Pizaini
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3592

Abstract

Every day transaction activities between companies and consumers continue to be carried out. This makes transaction data more and more and accumulate. This transaction data can be processed into more useful information using technology. Data mining is a technology that can work on a collection of transaction data into information that can be taken by companies as decision makers. The association rule method is used as a method to see the relationship between items in a transaction data. To analyze transaction data, researchers used the FP-Growth and Eclat algorithms. There are three stages of association in this study which are distinguished from the confidence value. The results in the first stage have a minimum confidence value of 0.4, the FP-Growth algorithm produces 41 association pattern rules, while the Eclat algorithm produces 32 association pattern rules. Then in the second stage the minimum trust value is 0.5, the FP-Growth algorithm produces 40 association pattern rules, for the Eclat algorithm it produces 32 association pattern rules. In the third stage, the minimum trust value is 0.6, the FP-Growth algorithm generates 32 association pattern rules, while the Eclat algorithm generates 30 association pattern rules. The results of the association pattern rules show that the Eclat algorithm is more efficient in determining the association pattern rules than the Fp-Growth algorithm
Sistem Klasifikasi Penyakit Jantung Menggunakan Teknik Pendekatan SMOTE Pada Algoritma Modified K-Nearest Neighbor Novitasari, Fitria; Haerani, Elin; Nazir, Alwis; Jasril, Jasril; Insani, Fitri
Building of Informatics, Technology and Science (BITS) Vol 5 No 1 (2023): June 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i1.3610

Abstract

The heart is a vital organ that plays a crucial role in pumping oxygenated blood and nutrients throughout the body. Heart disease refers to damage to the heart that can occur in various forms, caused by infections or congenital abnormalities. The World Health Organization (WHO) reports nearly 17.9 million deaths each year due to heart disease. In Indonesia, the prevalence of heart disease is around 1.5%, meaning that in 2018, approximately 15 out of 1,000 people, or nearly 2,784,060 individuals, were affected by this disease, according to the Basic Health Research data (Riskesdas) 2018. Many people have limited knowledge about heart health, leading to a lack of awareness of their heart conditions. This can be attributed to a lack of understanding regarding the importance of medical checkups related to heart health. Modified K-Nearest Neighbors (MKNN) is one of the data mining methods applied for classifying the risk of heart disease. The research utilized data obtained from the UCI dataset repository, which consists of 918 records with 12 attributes. To balance the imbalanced dataset with minority classes, the Synthetic Minority Over-sampling Technique (SMOTE) approach was used to generate new synthetic samples from the minority class. The objective of developing a web-based system for heart disease classification is to assist the public in assessing their risk of heart disease as early as possible, enabling them to take preventive actions sooner. The accuracy results of the MKNN algorithm with a 90:10 ratio are 80.37%, while with the MKNN+SMOTE approach, the accuracy increased to 84.00%. The use of the SMOTE approach improved the accuracy of low-performing data.
Klasifikasi Sentimen Menggunakan Metode Passive Aggressive dengan Menggunakan Model Bahasa BERT pada Dataset Kecil Subhi, Yazid Abdullah; Agustian, Surya; Irsyad, Muhammad; Insani, Fitri
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6389

Abstract

Text classification is one of the most popular tasks in natural language processing, especially in the context of sentiment classification. Insufficient training data poses a significant challenge in many text classification studies. This research focuses on optimizing classification performance using the Passive Aggressive (PA) algorithm, leveraging limited training data. It compares conventional text representation methods like TF-IDF with modern approaches employing word embeddings such as FastText and BERT. The primary dataset encompasses sentiment issues related to Kaesang Pangarep's appointment as the chairman of PSI, gathered through Twitter crawling, and classified into positive, negative, and neutral sentiment labels. Two versions of the training data, each containing only 300 balanced tweets for positive, negative, and neutral classes, were used. The data was split 80% for training and 20% for validation in the search for an optimal model. External data with different issues and pre-existing sentiment labels was used to augment the training data. Experimental results demonstrated that the BERT language model, used as input features for the Passive Aggressive method with hyperparameter tuning, outperformed TF-IDF features. Evaluation on the test data revealed that BERT features with Passive Aggressive achieved an F1-score of 0.52, surpassing the conventional TF-IDF representation with an F1-score of 0.42. The utilization of the BERT language model significantly contributed to improving text classification performance in the field of natural language processing, particularly for the Passive Aggressive method.
Co-Authors ., Pizaini Abdul Aziz Afriyanti, Liza Agustian, Surya Ahmad Fauzan Al Fiqri, M. Faiz Ananda, Rahmadan Alam Ardan Aqilah, M Alfandri Damayanti, Elok Darlianti, Sri Indah Elin Haerani Elvia Budianita Fadhilah Syafria Fahrozi, Aqshol Al Fakhira, Adzra Febi Yanto, Febi Fitria Novitasari Hasibuan, Aldiansyah Pramudia Herwanza, Niken Aisyah Maharani Iis Afrianty Iwan Iskandar Jasril Jasril Jasril Jasril Kurnia Rahman, Fikri kurnia, fitra Lestari Handayani Mai Candra, Reski Miftah Farid Muhammad Abdillah Muhammad Affandes, Muhammad Muhammad Fikry Muhammad Irsyad Muhammad Ravil Mulyadi, Syahrul Najmi, Risna Lailatun Nazir, Alwis Nazruddin Safaat H Nova Yohana Novi Yanti Okfalisa Okfalisa Oktavia, Lola Rahmad Abdillah Ruri Hartika Zain Saputra, Nugroho Wahyu Setiawan, Adil Subhi, Yazid Abdullah Suwanto Sanjaya Tri Prastio Nugroho Utari, Roid Fitrah Vernando, Julio Vitriani, Yelfi Yusra Zahri, Firman