cover
Contact Name
Miftahul Huda
Contact Email
hudablue11@gmail.com
Phone
+6282273233495
Journal Mail Official
aguspw.amcs@gmail.com
Editorial Address
Sekretariat KESATRIA: Jurnal Penerapan Sistem Informasi (Komputer & Manajemen) Jln. Jendral Sudirman Blok A No. 1/2/3 Kota Pematang Siantar, Sumatera Utara 21127
Location
Kota pematangsiantar,
Sumatera utara
INDONESIA
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen)
ISSN : -     EISSN : 2720992X     DOI : 10.30645
KESATRIA: Jurnal Penerapan Sistem Informasi (Komputer & Manajemen) adalah sebuah jurnal peer-review secara online yang diterbitkan bertujuan sebagai sebuah forum penerbitan tingkat nasional di Indonesia bagi para peneliti, profesional, Mahasiswa dan praktisi dari industri dalam bidang Ilmu Kecerdasan Buatan. KESATRIA: Jurnal Penerapan Sistem Informasi (Komputer & Manajemen) menerbitkan hasil karya asli dari penelitian terunggul dan termaju pada semua topik yang berkaitan dengan sistem informasi. KESATRIA: Jurnal Penerapan Sistem Informasi (Komputer & Manajemen) terbit 4 (empat) nomor dalam setahun. Artikel yang telah dinyatakan diterima akan diterbitkan dalam nomor In-Press sebelum nomor regular terbit.
Articles 419 Documents
Metode Multi Attribute Utility Theory Dalam Pemilihan Dosen Terbaik Berdasarkan Kinerja Huda, Ramzil; Defit, Sarjon; Sovia, Rini
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.492

Abstract

Assessment of lecturer performance is a critical element in ensuring academic effectiveness and productivity, as well as relevance to teaching, research, and commitment to society. The study applied the Multi Attribute Utility Theory (MAUT) in the decision support system (SPK) for the selection of the best lecturers at the School of Technology. SPK helped in decision-making on semi-structured problems by using models that can combine and process different types of data. MAUT's selection is based on its ability to integrate a wide range of assessment criteria such as formal education, functional departments, certification, number of publications, author's role in research, publication history, grant fund acquisition, amount of dedication, role in devotion, scope of devotedness, active role in inter-campus ministry, and Active role in external ministry. Of the 26 lecturers assessed on the basis of 12 criteria, the system successfully identified three lecturers with the highest score, showing the objectivity and effectiveness of MAUT in performance assessment. The lecturer with code A5 scored the highest score of 0.925, followed by A14 with 0.775, and A7 with 0.702. These results provide important insights for decision-making to the leadership of the School of Technology in giving awards and guiding the career development of lecturers.
Comparative Analysis of Deep Learning Models for Predicting Fan Actuator Status in IoT-Enabled Smart Greenhouses Airlangga, Gregorius
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.524

Abstract

In this study, we propose a comprehensive comparison of deep learning models for predicting the status of fan actuators in an IoT-enabled smart greenhouse environment. The dataset, consisting of 37,923 observations, captures environmental variables such as temperature, humidity, and soil nutrient levels, alongside actuator statuses. The aim is to accurately predict the binary status of the fan actuator (on or off) based on these environmental conditions. To address the challenge of class imbalance in the dataset, we apply the Synthetic Minority Oversampling Technique (SMOTE) to generate synthetic samples of the minority class, ensuring a balanced distribution for training. Three deep learning architectures Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) are implemented and evaluated using 10-fold cross-validation. The performance of each model is assessed using accuracy, precision, recall, and F1 score metrics. Results indicate that all models demonstrate strong predictive capabilities, with the LSTM excelling in capturing temporal dependencies, the CNN effectively extracting spatial patterns, and the MLP achieving overall high accuracy in structured data. The findings of this study provide valuable insights into the strengths and weaknesses of these models for actuator status prediction, which can guide future developments in smart greenhouse automation systems
Analisis Perbandingan Metode Contrast Stretching Dan Histogram Equalization Untuk Memperbaiki Kualitas Citra Digital Avily, Maulina Adina
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.483

Abstract

Currently, many people take pictures using digital instruments. However, the resulting images are sometimes not of good quality. To effectively communicate the information contained in the images, a method must be used to enhance image quality. To make an image sharper than the original, the Contrast Stretching technique increases or decreases the contrast (lighting). To produce better images, a technique is used to calculate intensity values and distribute the pixels evenly. This research was conducted to improve image quality using the same technique, but with a different input image, specifically RGB (color image), and the comparison method used was Contrast Stretching. The metrics used in this study are Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR). The software used is MATLAB R2015a.
Optimisasi Pengembangan Aplikasi Koperasi Tenaga Kerja Bongkar Muat Pelabuhan Laut Nabire Berbasis Web Dengan Pendekatan Metode Spiral Prayitno, Gunawan; Womsiwor, Marselina
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.515

Abstract

Manual management of cooperatives at Nabire Sea Port creates various obstacles, such as recording errors, time inefficiencies, and lack of transparency in financial management and distribution of loading and unloading tasks. This research aims to optimize the development of web-based loading and unloading labor cooperative applications using the spiral development method. The spiral method was chosen because its approach is iterative and allows for continuous improvement based on user feedback at each stage of development. The research results show that this application has succeeded in increasing the operational efficiency of cooperatives in terms of managing membership, savings, loans and task distribution. This web-based application also provides more transparent and real-time data access, which facilitates the decision-making process by cooperative administrators. Another advantage of the spiral method is its ability to identify and reduce the risk of system failure early, although this method requires more time and resources than other development methods. The development of a cooperative application using a spiral approach provides an effective digital solution in managing the Stevedoring and Unloading Workers' cooperative at Nabire Sea Port. However, challenges in the form of limited technological infrastructure and user training need to be overcome to achieve more optimal results in the future
Analisis Prediksi Jangka Panjang COVID 19 Fase ke 3 di Indonesia menggunakan Deep Learning Herferry, Ibrahim Ade; Ferdiansyah, F; Kunang, Yesi Novaria; Purnamasari, Susan Dian
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.474

Abstract

This research is motivated by the ongoing impact of the COVID-19 pandemic, which continues to pose challenges for Indonesia, affecting both the economy and daily life. Therefore, this study will discuss long-term predictions for the third phase of COVID-19 in Indonesia using a Deep Learning model. The analysis aims to assist various stakeholders in developing better planning strategies to address COVID-19 in Indonesia. In conducting this research, the author employs neural networks to create a hybrid model combining GRU and LSTM algorithms. Utilizing RMSE and MAPE values, it can be concluded that the model's performance in predicting COVID-19 cases is influenced by the number of epochs used. Furthermore, the model demonstrates optimal performance at 150 epochs for predicting the number of COVID-19 cases in the next 7 days
Implementasi Algoritma C4.5 untuk Memprediksi Tingkat Ketepatan Kelulusan Mahasiswa Sari, Imrah; Defit, Sarjon; Sumijan, S
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.506

Abstract

Timeliness of graduation not only reflects the competence of graduates but also affects the assessment of study programme accreditation. To achieve this goal, it is important to predict and classify the timeliness of graduation to support more effective academic decision making. In this research, the Knowledge Discovery in Database (KDD) process is used, which aims to find knowledge from big data. One of the main stages in KDD is data mining, which focuses on pattern extraction with various algorithms. This research uses the C4.5 algorithm, a classification method that builds a decision tree to identify attributes that affect the timeliness of student graduation. This study uses data from students in 2017, 2018, and 2019 from the Bachelor of Nursing and Bachelor of Public Health study programmes at Syedza Saintika University, with a total sample of 46 student records. The C4.5 algorithm is applied to form a decision tree model, which produces classification rules based on attributes such as Grade Point Average (GPA), Study Programme, Gender, and Region of Origin. The results of the C4.5 algorithm implementation show a prediction accuracy of 89.13%, with GPA as the most dominant factor in influencing graduation accuracy. This research proves that the C4.5 algorithm is effective in predicting the timeliness of student graduation.
Penerapan Algoritma K-Means Untuk Klasterisasi Akseptor Keluarga Berencana Modern di Sumatera Barat Wicaksono, Putut; Defit, Sarjon; Nurcahyo, Gunadi Widi
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.497

Abstract

The Regulation of the National Population and Family Planning Agency number 11 of 2020 concerning modern contraceptive methods including the Female Operation Method (MOW)/female sterilization, Male Operation Method (MOP)/male sterilization, IUD/spiral/Intrauterine Contraceptive Device (IUD), implant/implant, injection, pill, and condom. This study aims to apply and test the K-Means algorithm by measuring the level of accuracy in clustering Districts/Cities based on the use of modern contraceptives. The method used in this study is the K-Means Clustering algorithm to produce 3 clusters, namely district/city clusters with high, medium, and low acceptor usage. The stages of the K-Means Clustering algorithm are as follows: Determining the number of clusters, Determining the initial centroid point randomly, Calculating the closest distance between data and centroid, Grouping data into each cluster, If the cluster changes, the process continues to the next iteration, if there is no change, the iteration process is stopped. The data set processed in this study came from the BKKBN of West Sumatra Province. This study used a data set of 383,609 from 19 districts/cities based on the use of modern contraceptives. The results of this study indicate that the performance of the K-Means method in cluster analysis produces 3 clusters consisting of low modern contraceptive users of 5 districts/cities in cluster 0 or 26.32%, moderate modern contraceptive users of 7 districts/cities in cluster 1 or 36.84%. users of modern contraceptives are high as many as 7 districts/cities in cluster 2 or 36.84%. Therefore, this study can be a reference for district/city governments in intervening in population control and family planning programs.
Automated Detection of Black Pod Disease in Cocoa Fruits Using Convolutional Neural Network Lestari, Febbi Sena; Harliana, H; Putra, Fatra Nonggala
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 6, No 1 (2025): Edisi Januari
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v6i1.543

Abstract

Black pod disease is a severe disease affecting cocoa fruit, caused by the Phytophthora Palmivora fungus. This infection turns the fruit's surface dark brown to black, while the inside becomes rotten. Currently, identifying infected cocoa fruits is done manually through visual observation, which is prone to errors and inconsistency. This study aims to implement a Convolutional Neural Network (CNN) algorithm to classify images of black pod disease in cocoa fruits. The dataset consists of 1,500 images obtained through documentation and literature review, with 750 images of healthy cocoa fruits and 750 images of infected fruits. To determine the optimal configuration, the CNN model was tested across 15 scenarios with varying batch sizes and epochs. The results show that the fifth scenario, with a batch size of 32 and 50 epochs, achieved the best performance, with an accuracy of 97.33%, precision of 97.41%, recall of 97.33%, and an f1-score of 97.33%. Additionally, the model was further tested using 20 original images, achieving an accuracy of 90%. These results demonstrate that the CNN model developed effectively classifies cocoa fruit images affected by black pod disease, highlighting its potential for use in developing more accurate and efficient cocoa disease detection applications
Implementasi Sistem ERP Proses Sales Management Berbasis Odoo Dengan Metode Rapid Application Development Di UMKM Dapurbeta Fajarrachman, Nandika; Budiyono, Avon
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.488

Abstract

Technological developments have a significant impact on Indonesian society, especially business actors. Digitalization of the sales process is important to improve performance and competitiveness, especially for MSMEs in the food and beverage industry. MSMEs can take advantage of digital technologies such as social media and Point of Sale systems to optimize marketing and sales. Dapurbeta, an MSME in the food and beverages sector, faces challenges in sales management which includes the sales process of catering, restaurants, TVS, and Motorist, which have not been integrated. Dapurbeta's marketing is still conventional, making it difficult to reach a wider market. To overcome this problem, Dapurbeta implemented an Odoo-based ERP system with rapid application development (RAD) research method. Odoo was chosen because of its ease of configuration according to Dapurbeta's needs. This research focused on fit and gap analysis and resulted in customized business processes, creating several modules, such as sales, point of sales, and social marketing. These modules are configured according to Dapurbeta's needs so that they are expected to increase sales and marketing.
Implementasi Metode SMART Dalam Sistem Pendukung Keputusan Untuk Penentuan Sanksi Tindakan Bullying Putri, Fetty Ade; Rahman, Maulia; Salsabillah, Tasya
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.520

Abstract

Bullying is an act that is currently the biggest challenge in Indonesia, especially in schools and Islamic boarding schools. In schools, bullying is usually increasingly rampant because the school does not respond or even ignores violent behavior by its students. Apart from that, giving inappropriate sanctions also causes students who bully to feel safe in carrying out their actions continuously. To be able to provide appropriate sanctions have a deterrent effect, a decision support system is needed that can make it easier for schools to provide sanctions to perpetrators of bullying. By applying the SMART Method, each criterion has a weight that shows how important that criterion is compared to the others. As a result, the system shows that the alternative with alternative code A3 is recommended to receive sanctions in the form of Drop Out because it has a score of 0.800