cover
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota adm. jakarta selatan,
Dki jakarta
INDONESIA
Faktor Exacta
ISSN : 1979276X     EISSN : 2502339X     DOI : -
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 523 Documents
Clustering the K-means Algorithm with the Approach to Student Interpersonal Communication Patterns in Selecting Secondary Schools Wulan, Rayung; Widaningsih, Themotia Titi; Yanuar, Fit
Faktor Exacta Vol 16, No 4 (2023)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v16i4.20852

Abstract

This research aims to understand students' communication patterns in choosing secondary schools by identifying existing group patterns, and understanding the factors that influence students' decisions in choosing secondary schools. Using the k-means algorithm clustering method, the dataset was obtained from student data, psychological test scores and interpersonal communication in three grade 9 junior high schools in West Jakarta. The dataset obtained was 317, the results of data clearing were 259 students who were eligible to be tested. The results of tests carried out with 4 clusters show an accuracy value close to 0, with cluster 2 having a value of -0.150. The results show that students who choose a secondary school based on their psychological test results and interpersonal communication between parents, homeroom teachers and the school are the dominant values in the continuity of selecting a senior secondary school
COMPARISON OF DIABETES DISEASE CLASSIFICATION MODELS USING LOGISTIC REGRESSION AND RANDOM FOREST ALGORITHMS nabila, putri; Mutoi Siregar, Amril; Faisal, Sutan; Pratama, Adi Rizky
Faktor Exacta Vol 17, No 3 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i3.24388

Abstract

Diabetes is a lifelong chronic disease that disrupts blood sugar regulation. Diabetes is a life-threatening condition that, if left untreated, can lead to death and other health problems. Several medical tests, including the glycated hemoglobin (A1C) test, blood sugar test, oral glucose tolerance test, and fasting blood sugar test, can be used to detect diabetes. According to statistics, high glucose levels are one of the problems associated with diabetes. This study aims to categorize patients into diabetic and non-diabetic groups using specific diagnostic metrics included in the dataset. 1500 patient records with 9 attributes and 2 classes were used by the researchers. The study used machine learning techniques, including Logistic Regression and Random Forest, along with Confusion Matrix and Receiver Operating Characteristics (ROC) assessment. The Random Forest method produced results of 97% accuracy, 97% precision, 100% recall, and 98% f1-score, indicating that the accuracy level seems good but can still be improved. Based on the accuracy findings, Random Forest is the most effective strategy of Logistic Regression.
Application of Data Mining to Prediction of New Students' Interested Departements With an Approach Naive Bayes Algorithm Harsanti, Niken; Wibowo, Arief
Faktor Exacta Vol 17, No 2 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i2.20625

Abstract

Peramalan Nilai Tukar Rupiah Terhadap Dolar Singapura dengan Pendekatan Average Based Fuzzy Time Series Markov Chain Rahmah, Syifa Ur; Putri, Ayu Pratika; Siswanto, Siswanto; Kalondeng, Anisa
Faktor Exacta Vol 17, No 1 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i1.21164

Abstract

Exchange rates, representing a country's currency value in terms of another, signify currency relationships between nations. Indonesia's strong economic ties with Singapore see the Singapore Dollar boasting the highest exchange rate against the Indonesian Rupiah in Asia. The Rupiah-Singapore Dollar exchange rate is marked by fluctuations, necessitating precise forecasts. One effective forecasting method is the average-based Fuzzy Time Series (FTS) Markov Chain. This method calculates intervals based on averages and leverages the Markov Chain concept, employing a transition probability matrix to enhance accuracy. The average-based FTS Markov Chain predicts the Rupiah-Singapore Dollar exchange rate from May 16, 2023, to October 13, 2023, delivering an impressively low Mean Absolute Percentage Error (MAPE) of 0.3642%. Notably, the forecast for October 14, 2023, is 11.583.73. Consistently, this method, blending interval formation through FTS and probability transition matrix from the Markov Chain, provides reliable forecasts. These insights are invaluable for decision-makers, empowering them to proactively address potential fluctuations that might contribute to inflationary pressures on Indonesia's economy.
Analisis Model Matematika dan Simulasi Pada Penyebaran Hepatitis Non HepA-E Akut di Indonesia Ristiawan, Rifki; Wahyudi, Farrell; Selvia, Noni
Faktor Exacta Vol 16, No 4 (2023)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v16i4.19670

Abstract

Komparasi Metode Grey GM (1.1) Dan Grey Verhulst Untuk Prediksi Harga Sembako Zahro, Diah Ayu Fatimatus; Muqtadir, Asfan; Suryanto, Andik Adi
Faktor Exacta Vol 17, No 2 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i2.22408

Abstract

This research explores the significance of basic commodities (sembako), such as rice and sugar, as essential necessities, with a focus on price fluctuations influenced by factors like seasonal variations and weather conditions. The pressing issue of rising food demand amid Indonesia's population growth is exacerbated by price fluctuations. The study utilizes grey forecasting method, specifically GM (1.1) and grey Verhulst, to predict the prices of basic commodities in East Java. The comparative results indicate that grey Verhulst excels in forecasting the prices of certain commodities, such as Premium Rice, while GM (1.1) proves more effective for the sugar category. This finding comes from an analysis of the ARPE value that shows the accuracy of the model in the price prediction. The research aims to contribute to addressing the challenges of price changes and instability in basic commodity prices influenced by seasonal factors. The lowest error rate for grey Verhulst is 1.9471% for premium rice, with the highest at 64.535% for sugar. For GM (1.1), the lowest error rate is 2.184% for medium rice, and the highest is 6.633% for premium rice.
Klasifikasi Tingkat Kemanisan Buah Kersen Berdasarkan Fitur Warna NTSC Menggunakan Jaringan Syaraf Tiruan Berbasis Pengolahan Citra Digital Rusli, Risvan; Fachriansyah, Zaky; Ilham, Muh; Kaswar, Andi Baso; Andayani, Dyah Darma
Faktor Exacta Vol 17, No 3 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i3.23347

Abstract

The fruit of the calabura tree (Muntingia calabura) is a small red fruit originating from the Prunus genus, often found along roadsides. This fruit contains numerous nutrients beneficial for bodily health, serving as a highly potential source of nutrition. Presently, a challenge exists in determining the sweetness level of calabura fruit, relying heavily on manual human assessment. The development of classification utilizing technology is considered a crucial step. Previous research has concentrated on classifying various objects using RGB, HSV, YCbCr color feature extraction. However, it was observed that RGB, HSV, YCbCr color features are not universally suitable, particularly for calabura fruits. Hence, this study employs a method of classifying the sweetness level of calabura fruit based on NTSC color features using a Digital Image Processing-based Artificial Neural Network (ANN). This approach leverages color-based image processing features. The research involves several stages, starting from acquiring 300 calabura fruit images with 3 levels of classification to the classification process utilizing Backpropagation in the ANN. Multiple training and testing scenarios were conducted to select feature combinations with the highest accuracy and fastest computational time. Results revealed that the most effective feature used was the NTSC color feature as a skin characteristic parameter. Based on training outcomes using 210 training images, the accuracy reached 100% with a computational time of 1.66 seconds per image. Meanwhile, testing with 90 sample images showed an accuracy of 94% with a computational time of 4.23 seconds per image. Thus, it can be concluded that the employed method successfully classifies the quality of calabura fruit images based on color features and skin characteristics.
Penentuan mahasiswa berprestasi menggunakan algoritma FP-Growth dan SAW Ridwan, Wawan; Gunawan, Wawan
Faktor Exacta Vol 17, No 3 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i3.23936

Abstract

This research discusses the importance of utilizing technology in inventory management and student achievement determination. The transformation from manual systems to computerized systems has proven to increase efficiency and accuracy. In determining outstanding students, the criteria used often focus solely on academic aspects, neglecting other skills such as leadership and creativity. This study proposes the use of the FP-Growth and Simple Additive Weighting (SAW) algorithms to address this issue. FP-Growth is used to identify high-frequency patterns in student achievement data, while SAW assigns weights to each criterion variable for more accurate decision-making. The criteria for assessment include GPA, student achievements, study duration, and activity participation. The implementation is expected to provide a more effective solution in determining outstanding students and managing inventory. The FP-Growth method helps identify significant patterns in transaction data, while SAW assists in ranking alternatives based on specified criteria. This research demonstrates that the combination of these two algorithms can improve accuracy and efficiency in inventory management and student achievement determination, providing a competitive advantage for institutions. Based on the research results, the ranking of outstanding students is led by student C, followed by student B, with respective scores of 0.8875 and 0.825.
SMART ATTENDANCE WITH FACE ANTI-SPOOFING TECHNOLOGY USING HAAR CASCADE CLASSIFIER Supriatna, Ujang; Kurnia, Dian Ade; Suprapti, Tati
Faktor Exacta Vol 17, No 3 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i3.21166

Abstract

Traditional attendance systems often encounter challenges in efficiently and accurately recording attendance. This research aims to introduce an innovative solution through the development of an intelligent anti-spoofing attendance system based on facial recognition using the Haar Cascade Classifier method. Designed to overcome the inefficiencies in attendance recording, this system ensures the accuracy of educational staff attendance records. Its development method relies on the Haar Cascade Classifier, employing image processing to detect learned object features, particularly focusing on facial recognition. Research findings indicate that the implementation of this system achieves an average accuracy rate of 98.90% in attendance recording. The facial recognition technology ensures reliable attendance recording with confidence levels exceeding 80%, signifying precise facial identification that addresses various challenges and ensures attendance data integrity. Not only does the system identify educational staff with high accuracy, but it also provides prompt responses for efficient attendance logging and verification. Beyond its technical benefits, this study significantly contributes to the development of smarter and more efficient attendance technology. The system plays a crucial role in enhancing the discipline of educational staff at STMIK IKMI Cirebon and streamlining attendance management and evaluation across educational institutions.
Pemanfaatan Chi Square dan Ensemble Tree Classifier pada Model SVM, KNN dan C4.5 dalam Penjualan Online Indriyanti, Prastika; Gunawan, Wawan
Faktor Exacta Vol 17, No 3 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i3.24149

Abstract

This research aims to assist MSMEs in overcoming problems in online sales. Currently, sellers only prepare stock without knowing how well the products are sold in their market segment. In the city of Tangerang alone, there are 222,602 MSMEs with various product categories. Therefore, besides utilizing offline sales, business actors should also engage in online sales. This research conducts feature selection using the Chi-Square method and Ensemble Tree Classifier to select the top 6 and 10 features. The SVM, KNN, and C4.5 algorithms are used to build prediction models based on the selected features. Using feature selection, it was found that the influential features are Estimated Shipping Cost, Shipping Cost Paid by Buyer, Total Product Price, and Estimated Shipping Cost Discount. The evaluation results using the three algorithms, SVM, KNN, and C4.5, indicate that the highest accuracy value is obtained when using the C4.5 model with data from the ensemble tree classifier with 6 features at 0.86%, followed by the C4.5 model with 10 features, KNN with 6 features, and KNN with 10 features, all of which source data from the ensemble tree classifier with an accuracy value of 0.85%.