cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Aris Martono
Contact Email
aris.martono@raharja.info
Phone
+6287879163970
Journal Mail Official
sensi@raharja.info
Editorial Address
Jl. Jenderal Sudirman No. 40 Modern Cikokol Tangerang - Banten 15117 Indonesia
Location
Kota tangerang,
Banten
INDONESIA
Journal Sensi: Strategic of Education in Information System
Published by UNIVERSITAS RAHARJA
ISSN : 24611409     EISSN : 26555298     DOI : https://doi.org/10.33050/sensi
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management
Riset Soft Computing dengan penelitian dari yang berfokus pada Data Mining, Neural Network, Swarm Intelligence, Decision Tree, Data Clustering, Data Classification, Rough Set, Pattern Recognition, Image Processing. Software Engineering yang fokus pada software Requirement and Specification, Software Design, Software Management, Software Testing, Formal Method, Distributed Database dan Information System, bidang riset Business Intelligence dengan penelitian yang berfokus pada information and knowledge discovery (OLAP), Ad hoc queries and reports, text mining, web mining, search engines, Decision Support and Intelligent Systems serta Visualization. dan bidang riset Teknologi Information dan Komunikasi.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 210 Documents
 17   18   19   20   21 
Credit Risk Prediction Model Using Support Vector Machine with Parameter Optimization in Banks Martono, Aris; Padeli, Padeli; Suhaepi, Muhamad Iip; Santoso, Sugeng; Sunandar, Endang
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3463

Abstract

Abstract This research aims to determine the Support Vector Machine (SVM) model with Parameter Optimization in predicting loan worthiness to avoid the risk of bad credit at the Bank. Every bank tries to market financial loan products with very strict requirements. One of the requirements is that the company's financial reports must be healthy if it borrows money from a bank to develop the company's business. In the credit analysis process, there are 19 financial factors that must be measured from dozens or even hundreds of companies proposing financial loans, making it difficult for credit analysts to make decisions about whether these companies are worthy of borrowing or not. Therefore, this research was carried out by comparing the two models, namely SVM with parameter optimization and SVM with parameter optimization and Particle Swarm Optimization (PSO) to select the best model. The research results show that the Area Under Curve (AUC) criteria with validation number of folds (nof) = 10 and nof = 5 are 98.80% and 98.80%, meaning good and stable in the SVM model with parameter optimization. Meanwhile, the SVM model with parameter optimization and PSO has better AUC for validation nof=5 (99%) but for AUC with validation nof=10 (98.30%) it is less good.
Design of Condition Based Monitoring on Traction Transformers Using the Fuzzy Mamdani Method Reimondika, Fegi Arga; Silaban, Freddy Artadima
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3472

Abstract

Condition Based Monitoring Real-Time, direct supervision of machine condition parameters to detect potential changes, focuses on nitrogen gas pressure and oil temperature of the traction transformer at ASEAN Station, using the Fuzzy Mamdani method. This method notifies the traction transformer's condition and activates fans, providing information to operators. Arduino Uno R3 functions as a receiver and processor of sensor values. These values are processed using Fuzzy Mamdani, sent to ESP8266, and displayed on localhost. Percentage errors for nitrogen gas pressure (3.7%) and temperature (1.55%) result in a total percentage of 5.25%. The Fuzzy Mamdani output is 771.53 with a percentage error of 0.0019%, compared to MATLAB 2023b testing results of 773. Real-time monitoring shows the traction transformer is in good condition, with additional control to maintain its condition and improve reliability.
Automatic Machine Control System Using Arduino Microcontroller Harfizar, Harfizar; Wardoyo, Rizky Adytya; Atmojo, Tito Tri; Supriyono, Ignatius Agus
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3473

Abstract

Filling the tank with water uses a water machine to suck and put water into it. Water tanks are used to store clean water for household needs, especially from wells. This system requires manual supervision. The machine must be turned on if the tank is empty and turned off if it is full. If you forget to turn off the machine, the water will overflow and cause waste of water and electricity. Technological developments encourage the use of microcontrollers to overcome this problem. A microcontroller is a chip that processes digital data with a special language. Microcontrollers can be used as electronic controllers and to store programs. By using this technology, the problem of wasting water can be reduced. An automatic control system with an Arduino microcontroller can turn the water machine on and off automatically when the tank is empty and full. It is hoped that this system can help humans use water and electricity effectively and efficiently.
Application of Artificial Neural Network Algorithm with Principal Component Analysis for Diagnosis of Breast Cancer Tumors Almunawar, Muhammad Irfan; Maulana, Reffy; Sumbogo, Rifqi Putrawan
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3474

Abstract

Cancer is a health disorder where abnormal cells proliferate uncontrollably and is the second leading cause of death worldwide. Breast cancer, in particular, is prevalent among women in Indonesia. This study aims to diagnose breast cancer, identifying whether it is malignant or benign, using Artificial Neural Network (ANN) algorithms to enhance the accuracy of tumor diagnosis. The fundamental principle is to develop a neural network capable of processing information efficiently without relying on Python packages such as scikit-learn. The ANN operates through forward propagation and backward propagation to optimally predict outcomes and update weights. The dataset used is from the UCI Machine Learning Repository, consisting of 569 samples and 30 features. This dataset is divided into a training set (80%) and a cross-validation set (20%). The ANN model comprises one input layer, two hidden layers, and one output layer, utilizing tanh activation functions for the hidden layers and a sigmoid activation function for the output layer. Training results indicated an accuracy of 95.6% on the training set and 93.2% on the cross-validation set. This demonstrates that the model performs well in detecting breast cancer, with a low error rate and strong generalization capability. This study successfully developed an effective and reliable ANN model for breast cancer detection with high accuracy, supporting clinical breast cancer diagnosis.
Implementation of MVC Architecture in a Web-based Mail Management System (E-Archive) Setiadi, Ade; Alfiah, Fifit; Ardiansah, Teddy; Bin Ladjamudin, Al Bahra; Haryanto, Haryanto
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3475

Abstract

Companies, business entities, and institutions—both private and government—need archival activities because they are very important. To do it well requires improvement and refinement to achieve goals. All organizations, both government and private, must have complete and accurate data and information, knowing how important archiving is to assist leaders in making decisions or dealing with problems at the Larangan District Office, Tangerang City. Especially in the general section, archiving and document activity processes are still conventional, so it take a long time to complete. Because data is spread across many places and uses many formats, the process of selecting and reporting data is difficult to process well. This web-based electronic archiving system will be created using the Laravel framework and implementing the MVC(Model-View-Controller) architecture as a powerful and widely used software design pattern that encourages separation of concerns, code reuse, and maintainability enabling the archiving of incoming mail and mail. out serves as a data storage location. Therefore, the new e-archive system is expected to reduce errors when processing data, make the search process faster, and make reports that are in accordance with existing data.
Using Machine Learning Algorithms to Predict the Training Needs of Students for SMK Pustek Tangerang Maesaroh, Siti; Ratnasari, Anita
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3476

Abstract

Students at SMK Pustek Serpong in South Tangerang have diverse backgrounds, interests, and potentials that need to be identified and developed through appropriate training programs. This research aims to utilize machine learning algorithms to improve the accuracy of predicting students' training and development needs. Student data, including demographics, academic achievements, interests, and extracurricular activities, will be used to train models such as Random Forest Classifier, SVM, Gradient Boosting Classifier, and K-NN, targeting their chosen academic majors. The problem-solving approach involves problem identification, selection of machine learning methods, dataset collection, and model implementation. The research findings show that Gradient Boosting Classifier performs best with 77% accuracy, 79% precision, 96% recall, and an F1-score of 87% for the majority class. Conversely, K-NN achieves 67.97% accuracy but exhibits lower performance in identifying minority classes with precision and recall around 28% and 23%, respectively.
Application of the Prototype Method in the Export Section Goods Delivery Document Monitoring System Sari, Meri Mayang; Iskandar, Dedy; Supriadi, Ajay; Sudarto, Ferry; Saptono, Arief
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3477

Abstract

Companies can now handle and organize data systematically thanks to advances in information technology. Monitoring is a daily assessment (evaluation) of activities and progress. On the other hand, evaluation is an assessment carried out periodically regarding all achievements. Well-managed data will help companies make decisions. PT Gajah Tunggal Tbk is engaged in the manufacturing industry which meets customer needs by making product samples. One of the problems is that document control is carried out manually, which makes obtaining product trial data difficult. Additionally, there is no storage space for product sampling documents, which results in loss or damage to copies of documents. Product sampling is used according to customer needs, allowing companies to develop new products that meet customer or customer needs. Thus, the products produced will try to meet customer satisfaction. The aim of this research is to improve the services provided by PT Gajah Tunggal Tbk by building a goods delivery document monitoring system using the prototype method. To achieve this goal, previously built systems must be evaluated. The results obtained from monitoring goods delivery documents can increase the efficiency and efficiency of the service process with shorter waiting times and simpler delivery procedures. Using the prototype method can help PT Gajah Tunggal Tbk improve the efficiency and performance of its services.
Automatic Fire Detection Alarm Monitoring System in Balaraja District Based on Internet of Things Ilamsyah, Ilamsyah; Tandilintin, Abert; Putra, Lingga Buana; Jawahir, Jawahir; Arribathi, Abdul Hamid
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3478

Abstract

The Balaraja Sub-District Office, as a Regional Apparatus Work Unit in Tangerang Regency, faces challenges in preventing fire disasters. Fires can cause significant loss of life, economic, and material losses. Currently, the sub-district lacks an effective prevention system, relying solely on post-fire handling measures. This research aims to design and implement a monitoring system and automatic fire detection alarm based on the Internet of Things (IoT) in the Balaraja Sub-District. This system is expected to detect fires early and provide rapid alarms to reduce losses. The research confines its scope to the Balaraja Sub-District, utilizing interviews and literature studies as data collection methods. The design method involves creating flowcharts and block diagrams, while the analysis method employs the PIECES framework. System testing is conducted using blackbox testing methods. The findings of this research are expected to contribute to the development of IoT technology for disaster mitigation in Indonesia, as well as enhancing the safety of employees and the surrounding community.
Analysis of House Price Using K-Means and Naïve Bayes Methods Sugiyarto, Arman Prasojo; Hayati, Nur; Mardiani, Eri
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3480

Abstract

This study aims to compare the performance of the K-Means and Naïve Bayes algorithms in analyzing house prices. The dataset used is a house price dataset obtained from observational results. The study was conducted for approximately 2 months, focusing on the implementation of the K-Means and Naïve Bayes algorithms. The data was processed and analyzed using Orange software, and the results were presented in tables and graphs. The analysis results showed that the K-Means algorithm outperformed the Naïve Bayes algorithm with an accuracy value of 30% for the variable y distance to public facilities and 22% for the variable y land area and 82% with Naïve Bayes calculation. Therefore, it can be concluded that the K-Means method is a more effective method for analyzing house prices.
Order Monitoring Information System with Object Modeling at PT. Multi Citra Rasa Rahayu, Sri; Yusup, Muhamad; Kurniasih, Kurniasih; Rosdiana, Rosdiana; Kurniawan, Rano
Journal Sensi: Strategic of Education in Information System Vol 10 No 2 (2024): Journal Sensi
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/sensi.v10i2.3482

Abstract

Information Systems are a combination of hardware components and devices. Information Systems are a collection of integrated hardware and software components and have the task of collecting, storing and processing data so as to produce digital products for the availability of information for an organization. PT. Multi Citra Rasa is a B2B company operating in the F&B sector for the food service category. One of the problems that occurs in this company is the long follow-up between departments in the customer order process, this is due to the limited information obtained. System analysis was carried out using UML (Unified Modeling Language) on the Use Case Diagram. Use Case Diagram is used to generally describe the weaknesses of the system currently running at PT Multi Citra Rasa. Data was collected through an observation process in the field, then conducting questions and answers with the users involved and looking for several references that support this research. At the system design stage, researchers also used UML in Sequence Diagrams and Class Diagrams. UML is an object-oriented system modeling, where these objects will be realized on application pages that are synchronized with user needs. Meanwhile, Class Diagrams are designed to make it easier to realize database designs into basic forms of physical data, so that in the end data processing can run optimally and the information displayed is in accordance with user requirements. This research meets the needs of company management and provides convenience to all users involved so that operational activities become more effective and efficient in the future.

Page 19 of 21 | Total Record : 210

 17   18   19   20   21 

Filter by Year

2015 2025


Reset
Filter By Issues
All Issue Vol 11 No 2 (2025): Journal SENSI Vol 11 No 1 (2025): Journal SENSI Vol 10 No 2 (2024): Journal Sensi Vol 10 No 1 (2024): Journal Sensi Vol 9 No 2 (2023): Journal Sensi Vol 9 No 1 (2023): Journal Sensi Vol 8 No 2 (2022): Journal Sensi Vol 8 No 1 (2022): Journal Sensi Vol 7 No 2 (2021): Journal Sensi Vol 7 No 1 (2021): Journal Sensi Vol 6 No 2 (2020): Journal Sensi Vol 6 No 1 (2020): Journal Sensi Vol 5 No 2 (2019): Journal Sensi Vol 5 No 1 (2019): Journal Sensi Vol 4 No 2 (2018): Journal Sensi Vol 4 No 1 (2018): Journal Sensi Vol 3 No 2 (2017): Journal Sensi Vol 3 No 1 (2017): Journal Sensi Vol 2 No 2 (2016): Journal Sensi Vol 2 No 1 (2016): Journal Sensi Vol 1 No 1 (2015): Journal Sensi More Issue