cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota adm. jakarta selatan,
Dki jakarta
INDONESIA
Faktor Exacta
Published by Universitas Indraprasta PGRI
ISSN : 1979276X     EISSN : 2502339X     DOI : -
Core Subject : Science, Engineering,
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Industrial & Manufacturing Engineering
Faktor Exacta is a peer review journal in the field of informatics. This journal was published in March (March, June, September, December) by Institute for Research and Community Service, University of Indraprasta PGRI, Indonesia. All newspapers will be read blind. Accepted papers will be available online (free access) and print version.
Arjuna Subject : -
Articles 10 Documents
 1 
Search results for , issue "Vol 18, No 2 (2025)" : 10 Documents clear
Geographc Artificial Intelligence GeoAI dan Natural Language Processing dalam Analisis Data Spatial Fahrudin, Endin; Supriyatna, Samso; Darmawan, Firman
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.28518

Abstract

Geographic Artificial Intelligence (GeoAI) and Natural Language Processing (NLP) are two rapidly advancing technologies in spatial data analysis. GeoAI integrates artificial intelligence with geographic data to identify patterns, make predictions, and support decision-making. Meanwhile, NLP enables the processing and analysis of textual data related to spatial information, such as documents, reports, or geographic descriptions. The objective of this research is to obtain a representation of spatial data patterns through a series of processes, including problem identification, needs analysis, data collection and processing, document representation, and the application of Geographic Artificial Intelligence (GeoAI), Natural Language Processing (NLP), and Fuzzy Similarity methods to spatial or textual tax data and textual land data to identify data similarities. The research explores the integration of GeoAI and NLP in spatial data analysis to enhance the efficiency and accuracy of geographic data interpretation. The methods used in this study are based on artificial intelligence, which extracts spatial information from text and performs machine learning-based spatial analysis. The results demonstrate that the combination of GeoAI and NLP can improve the understanding of spatial patterns in unstructured data and support location-based decision-making processes. This research contributes to the development of more accurate spatial data analysis techniques that can be applied in various fields, such as urban planning, disaster management, and environmental analysis.
Evaluasi Efektivitas Penggunaan FastText Embedding dan LSTM Networks dalam Deteksi Phishing Email Rukiman, Sheptianna Healtha; Rahmatulloh, Alam
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.26769

Abstract

Phishing emails represent a significant cyber threat, necessitating advanced detection methods. This study evaluates a model combining FastText word embedding and a Long Short-Term Memory (LSTM) neural network to identify these threats. Using a public dataset from Kaggle, the model was trained on 80% of the data and tested on the remaining 20%. The methodology included data preprocessing, vectorization with FastText to capture sub-word information, and sequential pattern recognition using the LSTM architecture. Performance was evaluated using accuracy, precision, recall, and F1-Score, with the model achieving a 92% detection accuracy. Key challenges identified include class imbalance and high computational requirements. Future research could focus on model optimization and data augmentation techniques to further enhance detection performance and address these limitations.
Implementasi Sistem Klasifikasi Inventaris Menggunakan Metode Clustering dengan Algoritma K-Means untuk Pengelolaan Stok Barang di D'Cafe Indramayu Dhona, Dina Rima; Yulianingsih, Yulianingsih; Saputra, Suranto
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.25182

Abstract

One effective marketing strategy to attract consumer interest is the implementation of a "buy one get one free" promotional program on select products. However, this strategy necessitates sustainable inventory availability and must be aligned with the marketing unit's objectives. This research applies the K-Means algorithm to classify products based on price parameters and stock availability levels. The analysis results reveal the formation of three primary clusters: (1) products within the low to medium price range, (2) products within the medium to high price range, and (3) products in the highest price category. This clustering is based on the proximity of each product to its cluster centroid, accompanied by quantitative information regarding the number of products within each cluster. The output from this analysis is implemented through an application developed using the Java programming language. This application is designed to be utilized by the marketing unit in formulating and optimizing sales strategies to increase sales volume and enhance inventory management effectiveness.
Broken Acces Control pada Website: System Literature Review Anita, Sri
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.27979

Abstract

Technological developments that make it easier for organizations to carry out their operations are no longer difficult, through websites organizations can display their reputation, products, services and achievements through websites that can be accessed by the public 24 hours a day. However, there is a threat that the more famous a website is, the more vulnerable it is to becoming a target for attacks. Broken Access Control is one of the causes of websites becoming victims of defacement attacks which can be detrimental both financially and reduce reputation. In this article we will discuss the causes of websites becoming infected with outbreaks, how to prevent them, and technological proposals that have implemented AI to prevent them. The method used in the research is the System Literature Review method which has been carried out by previous researchers who have successfully applied AI technology to prevent Broken Access Control attacks. The results obtained from the development of prevention technology are satisfactory with the success of detecting and rejecting 100% of the 10 simulated attacks. It is important to protect websites because it affects reputation, financial loss, violations regarding personal data protection, and damage to organizational operations which will have very detrimental impacts in the short, medium and long term.
Perbandingan Optimasi Algoritma Klasifikasi Decision Tree, Naive Bayes dan KNN Menggunakan Optimize Parameter Grid Pada Tingkat Resiko Ibu Hamil Kurniawan, Aa
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.28051

Abstract

Perbandingan Kinerja Algoritma Random Forest, AdaBoost, dan Gradient Boosting dalam Memprediksi Risiko Penyakit Hipertensi Muftisany, Hafidz; Efendi, Tino Feri; Rozaq Rais, Nendy Akbar
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.28959

Abstract

Hypertension disease risk prediction is one of the challenges in the health field that can be supported by the development of machine learning models. Hypertension is a chronic condition that can lead to various serious complications, such as heart disease and stroke, so early detection is very important. However, conventional methods of diagnosing hypertension often require extensive medical examinations and are not always accessible to all individuals. Therefore, the development of artificial intelligence-based predictive models can be a more efficient solution in supporting the early detection of hypertension.This study aims to compare the performance of three popular machine learning algorithms, namely Random Forest, AdaBoost, and Gradient Boosting, in predicting hypertension risk. The most effective algorithm will be used in future research for program development. The dataset used consists of relevant medical and demographic data, such as blood pressure, body mass index, age, gender, and family history of hypertension. The model is built using a supervised learning approach, where the data is labeled based on the patient's hypertension condition. Evaluation was conducted using accuracy, precision, recall, and F1-score metrics to assess the performance of each algorithm.The methods used in this research include data preprocessing, feature selection, model training, and model performance evaluation. In addition, this research also designs an artificial intelligence-based hypertension prediction application that is expected to provide recommendations to users based on the model's prediction results.The results of this research are expected to provide insight into the most effective machine learning algorithms in hypertension risk prediction, considering the trade-off between accuracy and computational efficiency. Hypothesized based on previous research, Random Forest algorithm is better than the other two algorithms.
Penerapan Algoritma K-Nearest Neighbors (KNN) dalam Menentukan Jenis KB Menggunakan Google Colab Hadi, Abdul; Ryansyah, Decky; Brotosaputro, Goenawan Radzi
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.28604

Abstract

This study aims to apply the K-Nearest Neighbors (KNN) algorithm to determine the appropriate contraceptive method (KB) based on demographic data and user characteristics. The main problem faced is the lack of an effective decision support system to assist potential KB users in selecting the most suitable contraceptive method according to individual conditions. Additionally, the selection of contraceptive methods is often done manually by healthcare professionals without the support of predictive technology that could enhance recommendation accuracy. This research was conducted using Google Collab as a data processing platform, utilizing Python libraries such as Pandas, NumPy, and Scikit-learn. The dataset used includes information about KB users, including age, number of children, health history, and personal preferences. The data was pre processed to handle missing values and normalized to suit the analysis. The KNN model was tested with variations of the k value to find the optimal parameter that yields the highest accuracy. The results showed that the KNN algorithm was able to recommend contraceptive methods with an accuracy of 76% at k = 5. The main finding of this study is that the KNN model can be used as a decision support tool to determine the most appropriate contraceptive method for individuals. This research is expected to support efforts to improve reproductive health services through the utilization of machine learning technology.
Sistem Penunjang Keputusan Penentuan Supplier Toko Sembako Aishar dengan Metode MABAC Syamil Bayasef, Fuad Azril; Ardana, I Made Sugi
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.26958

Abstract

Objectively selecting the right supplier is a challenge for Aishar grocery store. When faced with several alternative suppliers, it takes considerable time to determine which one to choose. Four criteria are used for selection: quality, delivery time, price, and service, with the highest weighting in descending order. Quality is given the highest weighting because it directly impacts customer loyalty, while service is given the lowest score because it is only related to the store. The MABAC method can be used to objectively and quickly select alternatives. To facilitate implementation, a website-based application was created following the SDLC stages. Application testing was conducted using the blackbox testing method, comparing manual calculations with the application's output. The application is designed to be flexible and setup-based so that changes in criteria or weighting can still be applied. The example used in this study involved selecting five suppliers using four criteria. After assessing each supplier's criteria, alternative supplier A3, Ibu Ayin, was selected with a score of 40.0782.
Ketahanan Pembelajaran Mesin terhadap Adversarial examples: Metodologi dan Pertahanan Kurniawan, Ade; Aprilia, Ely; Aulia, Achmad Indra; Siregar, Amril Mutoi; Goeirmanto, Leonard
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.26078

Abstract

This paper examines the vulnerability of machine learning models to adversarial examples: inputs that are subtly manipulated to deceive a model into making incorrect predictions. Although deep learning has demonstrated remarkable performance across various tasks, the security of these models remains a significant challenge. This study provides a comprehensive review of various methods for generating adversarial examples, a classification of attack techniques, and corresponding defense strategies, including both active and passive approaches. The findings indicate that a combination of several defense techniques is significantly more effective in enhancing model robustness compared to any single approach. This research is expected to provide a foundation for the development of more secure and reliable machine learning models for critical applications.
Prediksi Harga Emas Menggunakan Algoritma Long-Short Term Memory dengan Optimasi Adaptive Momen Estimation Hadrianto, Muh.; Rahman, Anugrah Nur Isnaeni; Haris, Aulia Syahrani; Juzril, Ahmad; Rahmadani, Novia
Faktor Exacta Vol 18, No 2 (2025)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v18i2.26841

Abstract

Prediksi harga emas merupakan salah satu aspek penting dalam analisis pasar komoditas, yang berpengaruh pada keputusan investasi. Penelitian ini bertujuan untuk menerapkan algoritma Long Short-Term Memory (LSTM) yang dioptimasi dengan Adaptive Moment Estimation (Adam) untuk memprediksi harga emas berdasarkan data historis dari tahun 2000 hingga 2024. Data yang digunakan mencakup harga emas harian yang telah melalui proses preprocessing. Hasil analisis menunjukkan bahwa model LSTM mampu memberikan prediksi yang relatif akurat dalam menangani data time series. Model ini berhasil mencapai tingkat akurasi prediksi yang tinggi, dengan nilai Mean Absolute Percentage Error (MAPE) sebesar 0.96%, Mean Squared Error (MSE) sebesar 320854.198. Prediksi harga emas menunjukkan tren kenaikan yang konsisten, memberikan wawasan berharga bagi investor dalam pengambilan keputusan. Penelitian ini diharapkan dapat menjadi referensi bagi penelitian lebih lanjut dalam pemodelan prediksi harga komoditas lainnya.

Page 1 of 1 | Total Record : 10

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 18, No 2 (2025) Vol 18, No 1 (2025) Vol 17, No 4 (2024) Vol 17, No 3 (2024) Vol 17, No 2 (2024) Vol 17, No 1 (2024) Vol 16, No 4 (2023) Vol 16, No 3 (2023) Vol 16, No 2 (2023) Vol 16, No 1 (2023) Vol 15, No 4 (2022) Vol 15, No 3 (2022) Vol 15, No 2 (2022) Vol 15, No 1 (2022) Vol 14, No 4 (2021) Vol 14, No 3 (2021) Vol 14, No 2 (2021) Vol 14, No 1 (2021) Vol 13, No 4 (2020) Vol 13, No 3 (2020) Vol 13, No 2 (2020) Vol 13, No 1 (2020) Vol 12, No 4 (2019) Vol 12, No 3 (2019) Vol 12, No 2 (2019) Vol 12, No 1 (2019) Vol 11, No 4 (2018) Vol 11, No 3 (2018) Vol 11, No 2 (2018) Vol 11, No 1 (2018) Vol 10, No 4 (2017) Vol 10, No 3 (2017) Vol 10, No 2 (2017) Vol 10, No 1 (2017) Vol 9, No 4 (2016) Vol 9, No 3 (2016) Vol 9, No 2 (2016) Vol 9, No 1 (2016) Vol 8, No 4 (2015) Vol 8, No 3 (2015) Vol 8, No 2 (2015) Vol 8, No 1 (2015) Vol 7, No 4 (2014) Vol 7, No 3 (2014) Vol 7, No 2 (2014) Vol 7, No 1 (2014) Vol 6, No 4 (2013) Vol 6, No 3 (2013) Vol 6, No 2 (2013) Vol 6, No 1 (2013) Vol 5, No 4 (2012) Vol 5, No 3 (2012) Vol 5, No 2 (2012) Vol 5, No 1 (2012) Vol 4, No 4 (2011) Vol 4, No 3 (2011): Factor Exacta Vol 4, No 2 (2011): Faktor Exacta Vol 4, No 1 (2011): Factor Exacta Vol 3, No 3 (2010): Faktor Exacta Vol 3, No 2 (2010): Faktor Exacta Vol 3, No 1 (2010) More Issue