cover
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.josyc@gmail.com
Editorial Address
Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
Journal of Computer System and Informatics (JoSYC)
ISSN : 27147150     EISSN : 27148912     DOI : -
Journal of Computer System and Informatics (JoSYC) covers the whole spectrum of Artificial Inteligent, Computer System, Informatics Technique which includes, but is not limited to: Soft Computing, Distributed Intelligent Systems, Database Management and Information Retrieval, Evolutionary computation and DNA/cellular/molecular computing, Fault detection, Green and Renewable Energy Systems, Human Interface, Human-Computer Interaction, Human Information Processing Hybrid and Distributed Algorithms, High Performance Computing, Information storage, Security, integrity, privacy and trust, Image and Speech Signal Processing, Knowledge Based Systems, Knowledge Networks, Multimedia and Applications, Networked Control Systems, Natural Language Processing Pattern Classification, Speech recognition and synthesis, Robotic Intelligence, Robustness Analysis, Social Intelligence, Ubiquitous, Grid and high performance computing, Virtual Reality in Engineering Applications Web and mobile Intelligence, Big Data
Articles 38 Documents
Search results for , issue "Vol 5 No 4 (2024): August 2024" : 38 Documents clear
Sistem Pakar Diagnosa Gangguan Tidur pada Anak Menggunakan Naïve Bayes Kurniawan, Bagus Dwi; Akbar, Mutaqin
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5267

Abstract

Humans have a need for sleep that can be said to be very important, especially as children begin to develop. Sleep helps children become smarter, producing hormones that boost energy storage, increase muscle stamina, agility, intelligence, cognitive function, and long-term memory storage are all positively affected by sleep. To identify sleep disorders in children, parents usually need to consult a pediatrician, which can be expensive and time consuming. With an expert system, the system can relieve and help parents in detecting sleep disorders in their children by selecting symptom options in the system, then the system will give the final result of the child's sleep disorder with the highest probability based on the symptoms presented, as well as providing the appropriate solution. This expert system uses the Naïve Bayes method, which is a simple probabilistic classification. This method uses machine learning that relies on probability calculations. The system covers 31 symptoms of child sleep disturbances as well as the types of sleep disorders studied include Sleep Apnea, Insomnia, Narcolepsy, Enuresis, Night Terror, Nightmare, and Sleepwalking. Based on testing with 20 case data from experts, the system achieved a 95% accuracy level. Although there are some expert system results that show two disturbances with one of which corresponds to the result of an expert showing one disturbence, the result is still considered "Suitable".
Deteksi Outlier Hasil Clustering Algoritma K-Medoids Menggunakan Metode Boxplot Pada Data KIP Kuliah Simorangkir, Elsya Sabrina Asmita; Siahaan, Andysah Putera Utama; Marlina, Leni; Nasution, Darmeli; Sitorus, Zulham
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5479

Abstract

In the process of forming clusters with the K-Medoids algorithm, cluster result anomalies often occur, such as outliers. This value appears as a revelation in existing data patterns. Outliers occur due to measurement errors, rare events, or due to other unexpected factors. In this research, the dataset used is data on prospective KIP recipient students at Budi Darma University, where there is a high level of interest in KIP Kuliah while the quota is limited, which means that KIP Kuliah administrators sometimes have difficulty determining which students are eligible to receive KIP Kuliah. For this reason, the K-Medoids clustering technique was used to cluster data on 54 prospective students who were eligible to receive KIP Kuliah Merdeka and those who were not eligible. From the cluster results, outlier detection was carried out using the box plot method with the aim of finding out whether each cluster member was actually in the appropriate cluster or not. The result is that the data cluster is divided into 2 (K-2). In the max min centroid selection, cluster I consists of 52 members and cluster II consists of 2 members, where the outlier data consists of 3 data, while in random centroid selection (python), cluster I consists of 36 members and cluster II 18 members with data The outlier consists of 4 members. The accuracy of the clustering results between max min and random centroid selection has an accuracy of 64.81%, and the outlier accuracy is 75%.
Pemanfaatan Algoritma Floyd Warshall dalam Menentukan Jalur Terpendek Bencana Banjir Erwadi, Yetman; Handayani, Sri; Saputera, Surya Ade; Fernandez, Sandhy
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5483

Abstract

Bengkulu Province experienced floods and landslides that caused loss of life and property. These events mainly occur in the Central Bengkulu region and Bengkulu City, caused by damage to the Bengkulu River Watershed (DAS). During the rainy season, the river overflows. In this case the community is also confused when evacuating related to flood disasters, the community is confused in determining which route is the closest for the evacuation route because at the location of the flood disaster there are many routes that can be passed. From the problem the purpose of this research is to create an application that can determine which path is the closest in order to evacuate quickly. From the results of the analysis of this application, it is clear that the implementation of the Floyd-Warshall algorithm in this web application has a very important purpose, namely to assist the community in finding the shortest path to the evacuation point during a flood. The Floyd-Warshall algorithm is known to be effective in finding shortest paths in weighted graphs, as implemented in the context of this application to calculate the shortest distance between every pair of vertices or points within a defined area. The Floyd-Warshall algorithm can only compute shortest paths within areas that are well-defined in terms of vertices and edges, for the test results of the distance obtained in test 1 as far as 0.76 KM, in test 2 as far as 0.40 KM and in test 3 as far as 0.41 KM.
Perbandingan Support Vector Machine dan Naïve Bayes Terkait Kepuasan Pengguna Bus Listrik Kota Medan Mesanda, Zery; Ikhsan, Muhammad
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5556

Abstract

The city government has introduced an initiative to use electric buses as a cleaner and more sustainable alternative. The success of a public transportation system is not only determined by the availability of fleet and infrastructure, but also by the level of user satisfaction. User satisfaction is an important indicator that reflects the extent to which the service meets users' expectations and needs. Therefore, an in-depth understanding of the factors that influence user satisfaction, as well as the ability to predict and manage them, is key in improving the quality of public transportation services, including usage. In an effort to understand and improve trolleybus user satisfaction in Medan City, an adequate predictive analysis approach is required. By using methods such as Support Vector Machine (SVM) and Naïve Bayes, we can develop predictive models that can identify patterns and trends in user data, thus enabling relevant parties to take appropriate actions to improve services. In this context, the comparison between SVM and Naïve Bayes methods will provide valuable insights into the effectiveness of each method in predicting the satisfaction of electric bus users in Medan City. Based on the comparison results, the Naive Bayes algorithm shows slightly better performance compared to the Support Vector Machine in this sentiment analysis. The accuracy value generated by applying the Naive Bayes method is 58%, while applying the Support Vector Machine method is 57%. Nonetheless, both algorithms provide valuable insights into the sentiment of Medan people towards Electric Buses.
Prediksi Bahan Baku Kerupuk Rambak UMKM Tiga Berlian dengan Single Moving Average Sebastian, Devara Avila; Yudatama, Uky; Primadewi, Ardhin
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5604

Abstract

The "Tiga Berlian" rambak cracker MSME is an MSME in the snack food sector located in Banyuwangi Bandongan Village which produces crackers made from cowhide. Rambak crackers are a superior product with total demand per month reaching 150 kg. Tiga Berlian UMKM has difficulty in predicting and calculating raw material supplies for the coming period so excess raw material stock often occurs, such as cowhide or buffalo as the main raw material that is wasted due to uncertain demand. Single Moving Average (SMA) is used as a prediction method for raw materials in Tiga Berlian. Calculations with several periods (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, and 11) will be tested for accuracy using MAD, MSE and MAPE. The 11 predictions made with Tiga Berlian raw material data for 12 months, the 11th-period calculation resulted in a MAD value of 2.56198, a MAPE value of 2.561983, and an MSE value of 72.20135 as the smallest and most relevant accuracy value.
Implementasi Metode Analytic Hierarchy Process (AHP) dalam Sistem Rekomendasi Mitigasi Bencana Alam Nugraha, Nur Budi; Santosa, Yaqutina Marjani; Puspaningrum, Alifia; Saiful, Ibnu
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5626

Abstract

Flood disasters are a serious threat faced by various regions in Indonesia, including Indramayu Regency, West Java, as one of the most vulnerable areas. The geographical characteristics of Indramayu, which are dominated by lowlands and surrounded by large rivers such as Cimanuk and Cipunagara, cause this area to experience annual flooding, especially during the rainy season. The impact of this disaster extends from material losses to significant social and economic disruption for local communities. This research aims to develop an effective and targeted flood disaster mitigation recommendation system. Using a quantitative approach, this study focuses on developing a system based on the Analytical Hierarchy Process (AHP) method. The research methodology includes several key stages. First, identify and determine criteria and sub-criteria that are relevant to flood disaster mitigation. Second, weighting criteria using pairwise comparisons. Third, consistency calculations to ensure the validity of the assessment. Finally, the construction of a decision hierarchy that integrates all analysis elements. The results of the AHP analysis are then integrated into a system specifically designed to support decision making in disaster mitigation. The system combines geographic, demographic and historical disaster data to provide comprehensive and contextual recommendations. The system being developed is expected to facilitate several key aspects of disaster management in terms of quick and effective decision making by the authorities, increasing public awareness and knowledge about disaster management and understanding disaster distribution patterns.
Perbandingan Metode Deep Learning dengan Model LSTM dan GRU untuk Prediksi Perubahan Iklim Mustofa, Amin; Setiawan, Hendra
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5671

Abstract

Climate plays a critical role in determining the quality of life in Indonesia, which demands in-depth understanding through the Koppen climate classification and the latest technology. From agriculture to urban infrastructure, public health, to ecosystem sustainability, every aspect of our lives is affected by climate conditions. Deep Learning methods such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) are used to predict time series data because of their adaptive ability in learning complex data patterns. The LSTM and GRU models were tested with 2010-2021 data using batch_size 64, epochs 150, optimizer adam, and showed high accuracy (<10%). LSTM recorded MAPE: Rainfall 5.50%, Humidity 7.60%, Temperature 4.36%, Sunlight 8.29%. GRU recorded MAPE: Rainfall 5.01%, Humidity 6.86%, Temperature 4.35%, Sunlight 8.28%. Predictions for 2028 show that the Special Region of Yogyakarta has a Tropical Monsoon (Am), Tropical Savannah (As) and Tropical Rain Forest (Af) climate. These climate changes have significant impacts: increased rainfall increases the risk of flooding, threatening infrastructure and lives, while the As climate reduces agricultural productivity and increases food insecurity. Changes in rainfall and temperature affect people's health, with high humidity increasing the risk of tropical diseases and high temperatures causing heat stress. Climate change in the Am type increases the risk of floods and landslides, while in the Af type it threatens tropical rainforest ecosystems.
Penerapan Algoritma Support Vector Machine Untuk Mendeteksi Autisme Khoiriah, Miftahul; Kurniawan, Rakhmat
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5692

Abstract

Autism is a type of developmental disorder that can cause a neurological condition to disrupt brain function and impact a person's growth process, communication skills and social interaction abilities. In general, autism spectrum disorders can be detected in babies as early as 6 months. Things that interfere with a child's development occur because the structure of brain function is disturbed. This widespread disability is described as a spectrum disorder due to the considerable variation in how an individual manifests symptoms and their severity. By carrying out this detection, it can make it easier for parents to know whether their child has autism or not so they know what action to take. This research was conducted using a quantitative research methodology, where the research approach focuses on collecting and analyzing data that can be measured in numerical form using statistical techniques to obtain numbers and generalize. This approach involves the relationship between phenomena and cause and effect using a larger sample. After the previous stages are completed, then continue testing the prediction results using testing and accuracy data to obtain classification results. From the classification results above, the resulting classification value reaches 100% using test data and using accuracy values. Support Vector Machine (SVM) algorithm ) with a linear kernel has been applied to a dataset of autism in children. This model succeeded in separating classes well, showing that SVM is an effective algorithm for this classification problem.
Prediksi Penjualan Produk Pepsodent Unilever dengan Algoritma K-Nearest Neighbor Maulida, Dzikra; Nasution, Yusuf Ramadhan
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5718

Abstract

In the era of globalisation and increasingly fierce market competition, companies are striving to improve their operational efficiency and marketing strategies to maintain market share and increase revenue. PT Unilever Tbk, as one of the multinational companies that operates various types of consumer products, including dental care products such as Pepsodent, requires reliable sales prediction to maximise its product performance in the market. The main objectives of this research are to apply the K-Nearest Neighbor method to Unilever pepsodent products in a prediction model that can preprocess pepsodent product data for the last 1 year using Rapid Miner and to measure the accuracy of Pepsodent product sales predictions. The data used is the number of stocks, types of pepsodent, sales, seasonal factors. From the results of analysis and evaluation, it can be concluded that the prediction accuracy in the K-NN algorithm is able to provide fairly accurate sales predictions for Pepsodent Whitening products with a value of 161, 186, 165 equally 114. Pepsodent Economy with a value of 982 predictions 1021, a value of 638 and 774 predictions are both 927. Pepsodent Herbal with a value of 173 predicted 193 and a value of 129 and 118 predicted values are both 207. Accurate sales predictions are helpful in production planning and marketing strategies, which in turn can improve operational efficiency and customer satisfaction. The K-NN algorithm proved to be effective in this case, although proper selection of the K parameter is essential to obtain the best results.
Sentiment Analysis Study Tour Bus Ban on Twitter Using Support Vector Machine Method Purba, Ony Hizri Kaifa; Zufria, Ilka
Journal of Computer System and Informatics (JoSYC) Vol 5 No 4 (2024): August 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i4.5726

Abstract

Study tour is an activity outside the classroom that has the purpose of learning about the process of something directly. This activity is usually carried out by the school once a year. This activity is not only a learning tool for students, but also a recreational activity.In this activity, there are many things that need to be prepared, such as transportation, lodging, meals, and so on. This is sometimes troublesome, because not all tourists or business people have the time and willingness to prepare it. Therefore, they need services during their trip. Especially now that it is even semester, where every school usually holds a study tour, as well as a final class farewell. As a response to concerns, some parents may choose to find alternative activities that are considered safer for their children, such as joining activities in the city or at school. Based on this need, it makes opportunities for business people engaged in the tour agency industry. SVM (Support Vector Machine) is a machine learning method that works on the principle of Structural Risk Minimization (SRM) with the aim of finding the best hyperlane separating two classes in the input space. Simply put, SVM (Support Vector Machine) has the concept of finding the best hyperlane, which serves as the boundary of two classes The results of sentiment classification on Study Tour Buses using the Support Vector Machine algorithm that matches the actual data amount to 176 data out of a total of 240 test data. It is known that of the 1200 data obtained regarding sentiment towards there are 519 reviews that are positive and 681 reviews that are negative.The accuracy value of the Study Tour Bus sentiment classification using the Support Vector Machine (SVM) algorithm obtained is 73%.

Page 1 of 4 | Total Record : 38