cover
Contact Name
Saluky
Contact Email
luke4line@yahoo.com
Phone
-
Journal Mail Official
jurnalsistemcerdas@gmail.com
Editorial Address
-
Location
Kota bekasi,
Jawa barat
INDONESIA
Jurnal Sistem Cerdas
ISSN : -     EISSN : 26228254     DOI : -
Jurnal Sistem Cerdas dengan eISSN : 2622-8254 adalah media publikasi hasil penelitian yang mendukung penelitian dan pengembangan kota, desa, sektor dan kesistemam lainnya. Jurnal ini diterbitkan oleh Asosiasi Prakarsa Indonesia Cerdas (APIC) dan terbit setiap empat bulan sekali.
Arjuna Subject : Umum - Umum
Articles 176 Documents
Sistem Keamanan Kartu NFC Menggunakan Metode AES pada Sistem Pembayaran Elektronik Bhaskoro, Susetyo Bagas; Anggraeni, Pipit; Nijam, E. Nashrul
Jurnal Sistem Cerdas Vol. 6 No. 2 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i2.326

Abstract

To maintain data security, a method is needed that can improve data security, one of which is by using cryptographic techniques. In an effort to meet the needs of data security, cryptography focuses on understanding and applying techniques to protect messages. There are several methods used in cryptography, one of which is the AES method which is recognized as the best encryption algorithm for several reasons, such as using a sufficiently secure key, high processing speed, and ensuring data integrity and confidentiality. In this study, the AES method is used to secure data in the form of nominal balances stored on NFC cards. Based on the test results, it can be seen that the NFC card can function as a balance storage with a maximum limit of IDR 1,000,000. Then based on the confusion matrix method, the security system on the NFC card has an accuracy value of 81,81%, 83.3% precision, and 93,75% recall.
Web-Based Anomaly Detection for Smart Urban Living: Drone Photography and Videography Hermanus, Davy Ronald; Suhono Harso Supangkat; Fadhil Hidayat
Jurnal Sistem Cerdas Vol. 6 No. 2 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i2.330

Abstract

Smart cities aim to enhance the quality of life for urban dwellers through technological advancements. Machine Learning (ML) plays a crucial role in various domains of Smart X, including education, transportation, healthcare, environment, and living. However, integrating ML into daily life poses challenges. This paper presents a web-based ML application prototype that effectively augments the daily quality of life for communities. It specifically explores the advantages of web-based photography-videography-enabled drones for citizen needs and city inspections. The application utilizes ML to detect anomalies and identify normal objects, addressing the common challenge of distinguishing normalcy from abnormality. Examples include assessing the structural integrity of house components, analyzing medical images, and evaluating the quality of fruits or hydroponic plants. The study employs exploratory and experimental methods, utilizing teachable machine learning and the Python-based Streamlit application. Experimental results demonstrate that web-based photo and video analysis expedites the detection of normal and abnormal images and videos, surpassing the limitations of visual examination with the naked eye. This research contributes to advancing ML applications in smart living for urban communities.
Rekognisi Huruf Tulisan Tangan Menggunakan Convolutional Neural Network Rahmawan, Fadhel; Habibi, Roni; Setyawan, M. Yusril Helmi
Jurnal Sistem Cerdas Vol. 6 No. 3 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i3.240

Abstract

The development of technology in the field of computer vision in recent years with the application of Technological developments in the field of computer vision in recent years with the application of convolutional neural networks have shown sophisticated performance with a high level of accuracy, such as object detection. The problem in the world of computer vision that has been looking for a solution for a long time is object classification in general images. How to duplicate the human ability to understand images, so that computers can recognize objects in images like humans. Therefore, the need for deep learning is one branch of machine learning where the algorithm used is inspired by the workings of the human brain. Some people may be more familiar with Convolution Neural Network. CNN is used to recognize and classify patterns in handwriting. The network assumes that the input used is an image. The network has a special layer called the convolution layer. In this layer, the images are inserted according to the predefined filters. In this study, various combinations of CNN architectural designs were carried out such as the number of convolution layers, stride size, number of epochs, type of kernel size optimizer. The research data comes from the National Institute of Standards and Technology (NIST) database, then the data is divided into three, namely 60% training data, 20% validation and 20% testing. The results of this experiment produce a very good accuracy value using 2 convolution layers, 50 epochs, with Adam optimizer producing an accuracy value of 99.5% when testing the model. Then evaluate the model using the confusion matrix, assigning a high value with an average value of 100% accuracy, while for the average value of precision with a value of 100%, for an average recall value of 100%, and finally an average value of f1 score of 100%.
Evaluasi Algoritma Klasifikasi Machine Learning Kategori Nilai Akhir Tunjangan Kinerja Pegawai Tarigan, Ira Dwita Syafitri; Roni Habibi; Rd. Nuraini Siti Fatonah
Jurnal Sistem Cerdas Vol. 6 No. 3 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i3.246

Abstract

Allowance is a gift of appreciation for services in the form of an imbalance in work performance or performance dipsplayes. AT the moment the agency has not used the final value category for employee salary allowances, the program needed to determine the final category of employee benefits with a Machine Learning approach using the C4.5 and Naive Bayes Gaussian algorithms and evaluation of prediction results using Confusion Matrix and K-FOLD Cross Validation. The purpose of this research is to results of classification predictions in the category of using the final salary of employees of Confusion Matrix and K-FOLD Cross Validation. After mining the data, the performance of each algorithm is evaluated determine mining success rate process on the C4.5 and Naive Bayes Gaussian algorithms. Then the result is obtained and the C4.5 algorithms is a better algorithm in determining the category of employee salary allowance values.
Convolutional Neural Network Untuk Perbandingan Optimizer Pada Citra Batang Pohon Zuzzaifa, Nur; Rianto, Rianto
Jurnal Sistem Cerdas Vol. 6 No. 3 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i3.268

Abstract

In the surrounding environment, there are various types of trees with different characteristics. One characteristic of a tree that is difficult to distinguish is its trunk. After researchers made observations, the trunks of Pine and Tabebuya trees had the same characteristics, namely cracking. The problem of incorrectly identifying the characteristics of a tree's trunk can be overcome by classification. Deep Learning with the Convolutional Neural Network (CNN) algorithm is a method commonly used in image classification. The stages in this research include image data retrieval, data preprocessing, CNN architecture formation, model training, and model validation. Image retrieval was carried out directly by researchers, then the 1000 best images were selected. The image dataset is then divided into 75% training data and 25% validation data. Testing was carried out by comparing the Stochastic Gradient Descent (SGD) optimizer and the Adaptive Learning Rate Optimization Method (RMSprop) using epochs 10, 15, 20, 30, 50, and 80. The results showed that the SGD optimizer produced the highest accuracy compared to the RMSProp optimizer. The most optimal result when applying the SGD optimizer is 0.9360 with epochs 80, while for the RMSProp optimizer it is 0.9160 with epochs 20.
Analisis Prediksi Stroke Menggunakan Pendekatan Decision Tree dengan Seleksi Fitur dan Neural Network Indah Werdiningsih; Purwanti, Endah; Mardiyana, Iin; Handayani, Arum Tiyas; Suryadewi, Kharristantie Sekarlangit; Nurjanah, Endang; Akhlaqulkarimah, Fildzah; Pramiyas, Naurah Hedy; Yahrani, Fakhrana Almas Syah
Jurnal Sistem Cerdas Vol. 6 No. 3 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i3.310

Abstract

Currently, stroke is the second cause of death globally. According to data from the World Health Organization (WHO), 7.9% of deaths in Indonesia are caused by stroke. Based on these data, analysis of the factors influencing the case growth rate is very useful. This paper analyzes various factors in electronic health records for effective stroke prediction with different machine-learning algorithms including Decision Tree and Neural Networks. This research uses a dataset consisting of 12 features, namely ID, gender, age, history of hypertension, history of heart disease, marital status, type of work, type of residence, average glucose level, BMI (Body Mass Index) number, and status. smoking, and prediction of stroke. These features were analyzed using the Neural Network and Decision Tree methods so that selected features were produced for further analysis using the Neural Network method. The feature selection results consist of 5 features: age, history of hypertension, marital status, average glucose level, and BMI (Body Mass Index) number. The highest accuracy results were obtained using the Neural Network method with a feature selection of 88.75, the second highest was obtained with the neural network method of 87.1875, and the lowest accuracy was obtained with the Decision Tree method which had an accuracy result of 81.25. Based on these accuracy results, it can be obtained that the most optimal results are shown by the Neural Network method with feature selection.
Sistem Monitoring Ruang Server Berbasis IoT Menggunakan Komunikasi Lora Ebyte E32 Wibowo, Irwan Setyo; Adit, Muhammad Aditiya Firdaus; Laksana, Teguh Teuja
Jurnal Sistem Cerdas Vol. 6 No. 3 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i3.331

Abstract

The critical issue in server room management, emphasizing the potential damage caused by elevated temperatures to hardware within the server room environment. The proposed solution involves leveraging Internet of Things (IoT) technology, specifically utilizing LoRa (Long Range) communication, to monitor key environmental parameters such as temperature, humidity, and fire incidents. The sensors chosen for this purpose are the DHT11 for measuring temperature and humidity, and a Fire sensor for detecting potential fire hazards. The research focuses on three main aspects: testing the transmission distance, evaluating data delivery, and integrating sensor data into the Blynk dashboard, which serves as the central monitoring system. The testing process involves assessing the performance of the system under different conditions. Firstly, the transmission distance is tested, presumably to determine the maximum distance over which the sensors can reliably communicate with the monitoring system. Secondly, data delivery is examined, likely to ensure the timely and accurate transfer of information from the sensors to the monitoring dashboard. Lastly, the research involves the integration of sensor data into the Blynk dashboard, indicating a comprehensive approach to visualizing and interpreting the collected data. The results of the testing reveal that the optimal performance is achieved when the transmission distance is below 600 meters. This distance is achieved using a 5dBi antenna, connected to the Blynk dashboard, which is identified as the preferred monitoring system. The findings suggest that this IoT-based solution utilizing LoRa communication and specific sensors effectively addresses the challenges associated with server room management, providing a reliable and real-time monitoring mechanism to mitigate potential hardware damage due to environmental factors.
Rancang Bangun Antena Rotasi Dengan Kalibrasi Berbasis Program Kalman Filter Rahman, Imam Arief; Rangkuti, Syahban; Agil Abdul Ghani Alghifari K
Jurnal Sistem Cerdas Vol. 6 No. 3 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i3.333

Abstract

The Internet of Things (IoT) has changed how we interact with our environment. Low-Power Wide-Area Networks (LPWAN) such as LoRa play an important role in the IoT ecosystem due to their low power consumption, long-distance communication, and cost-effectiveness. However, detecting the azimuth and elevation angles of the transmitter is a challenge in LoRa communication. This paper proposes a rotary antenna system with an Inertial Measurement Unit (IMU) to precisely track azimuth and elevation angles at LoRa. The research carried out is to test the tool by comparing the algorithm without the Kalman Filter and the one with the Kalman Filter, where the test's success with the lowest error is up to 0.75% and 0%, respectively.
Perancangan Sistem Kanban untuk Mengurangi Keterlambatan Komponen Rear Spar Niken Ayu Pramudita; Prasetio, Murman Dwi; Suryadhini, Pratya Poeri
Jurnal Sistem Cerdas Vol. 6 No. 3 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i3.339

Abstract

Kanban literally means a visual note that usually takes the form of a card placed in a rectangular vinyl envelope and containing part information sent from one process to the previous process. The application of kanban is believed to optimize the production process. In this study, the kanban system was designed to reduce delays in Rear Spar components at PT. XYZ, a manufacturing company that produces aircraft, such as NC212 aircraft. The Rear Spar component on NC212 aircraft is often delayed. The main cause of Rear Spar delays is the unclear information and material flow so that operators on the Fabrication Line do not know when parts must be in the Assembly Line so that there is no priority for part work and some parts are late to be delivered to the Assembly Line. The design of the kanban system is carried out using the Constant-Quantity Withdrawal System method which consists of four stages, namely: calculating the lead time, calculating the necessary number of parts during the lead time, calculating safety inventory, and calculating the number of kanban cards. After calculating the number of kanban cards, the number of Assembly Line kanban cards to the Assembly Store is one sheet of production kanban and one sheet of withdrawal kanban. As for the number of Assembly Store kanban cards to the Fabrication Line is one sheet of production kanban for each part. The design of the kanban system is continued with the design of the kanban card, kanban mechanism, and kanban post position. The results obtained after simulating the design results using the simulation scenario made by the author are that the part making process is reduced by 41 minutes.
Perbandingan Analisis Sentimen Aplikasi Traveloka dan Tiket.com pada Twitter dengan Metode Support Vector Machine Rukmana, Putri Utami; Pratiwi, Oktariani Nurul; Fakhrurroja, Hanif
Jurnal Sistem Cerdas Vol. 6 No. 3 (2023)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v6i3.350

Abstract

The emergence of the COVID-19 pandemic in Indonesia resulted in an economic crisis, including in the world of tourism, which caused a decline in the national economy. With the existence of Online Travel Agencies (OTA) such as Traveloka and Tiket.com, it is hoped that they can help improve the tourism sector for the Indonesian economy. As a popular OTA and to see the opinion of the Indonesian people, it can be seen from public opinion in the form of tweets on the Twitter application. The tweets data will be taken and sentiment analysis will be carried out on the OTA Traveloka and Tiket.com applications which will be classified into certain classes based on opinions and modeling will be carried out using the Support Vector Machine (SVM) algorithm method. This research aims to determine the level of accuracy of the SVM algorithm and find out how sentiment analysis compares between Traveloka and Tiket.com. In the sentiment analysis comparison, in terms of price, Traveloka is superior and in terms of service, Tiket.com is superior. After modeling by comparing splitting data and handling imbalanced data using Synthetic Minority Oversampling Technique (SMOTE), the best SVM accuracy results for the Tiket.com price dataset were 68%, for Traveloka prices it was 97%, for Tiket.com services it was 92%, and for Traveloka services it is 89%.