cover
Contact Name
Agus Perdana Windarto
Contact Email
agus.perdana@amiktunasbangsa.ac.id
Phone
+6282273233495
Journal Mail Official
jsaktiamiktunasbangsa@gmail.com
Editorial Address
Sekretariat J-SAKTI (Jurnal Sains Komputer dan Informatika) Jln. Jendral Sudirman Blok A No. 1/2/3 Kota Pematang Siantar, Sumatera Utara 21127 Telepon: (0622) 2243
Location
Kota pematangsiantar,
Sumatera utara
INDONESIA
J-SAKTI (Jurnal Sains Komputer dan Informatika)
ISSN : 25489771     EISSN : 25497200     DOI : http://dx.doi.org/10.30645/j-sakti
J-SAKTI adalah jurnal yang diterbitkan oleh LPPM STIKOM Tunas Bangsa yang berfokus di bidang Manajemen Informatika. Pengiriman artikel tidak dipungut biaya, kemudian artikel yang diterima akan diterbitkan secara online dan dapat diakses secara gratis. Topik dari J-SAKTI adalah sebagai berikut (namun tidak terbatas pada topik berikut) : Artificial Intelegence, Digital Signal Processing, Human Computer Interaction, IT Governance, Networking Technology, Optical Communication Technology, New Media Technology, Information Search Engine, Multimedia, Computer Vision, Information System, Business Intelligence, Information Retrieval, Intelligent System, Distributed Computing System, Mobile Processing, Computer Network Security, Natural Language Processing, Business Process, Cognitive Systems, Software Engineering, Programming Methodology and Paradigm, Data Engineering, Information Management, Knowledge Based Management System, Game Technology.
Articles 50 Documents
Search results for , issue "Vol 5, No 1 (2021): EDISI MARET" : 50 Documents clear
Penerapan Deep Learning untuk Prediksi Kasus Aktif Covid-19 Lailis Syafa’ah; Merinda Lestandy
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (896.278 KB) | DOI: 10.30645/j-sakti.v5i1.337

Abstract

Coronavirus disease (Covid-19) is increasingly spreading in Indonesia, so it requires an approach to predict its spread. One approach method that is often used is the Deep Learning (DL) method. DL is a branch of Machine Learning (ML) which is modeled based on the human nervous system. In this study, the prediction of active Covid-19 cases was resolved using the DL method. The dataset used is 260 data with 10 parameters. DL is able to provide an accurate prediction of active cases of Covid-19 with an MSE of 0.032 and an accuracy of 81.333%.
Analisis Kualitas Portal Komik Digital Interaktif Pikolo Dengan Metode Webqual 4.0 Akhmad Dakhilul Arifin; Sri Huning Anwariningsih; Firdhaus Hari Saputro Al Haris
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1259.083 KB) | DOI: 10.30645/j-sakti.v5i1.303

Abstract

The comic industry in Indonesia is currently in a period of growth after nearly 3 (three) decades of suspended animation. This is due to the lack of innovation in the comic industry, both in terms of facilities and content. The publication of digital comics is currently one solution so that works from comic artists can reach readers. The development of an interactive digital comic publication media application called Portal Inovasi Komik Lokal (PiKOLO) aims to provide an alternative digital comic platform that provides interactive reading features and can be a publication tool for comic artists, especially local comic artists. The PiKOLO application was developed using the Codeigniter framework, with a PHP programming base and a MySQL database. Application testing is carried out using the WebQual 4.0 method. Testing is carried out by distributing questionnaires to comic activists through social networks and comic artists' communities within a predetermined time span. The results of the test show that the PiKOLO application's usability / reusability results in a value of 4.03. As for the aspect of information quality, the average value obtained was 4.06. The service interaction aspect gets an average score of 4.04, and the overall aspect gets an average score of 4.06 from a maximum scale of 5.
Analisis Pemilihan Supplier Pada Pengadaan Suku Cadang dengan Metode Analytic Hierarchy Process Mohammad Farid Naufal; Putu Aditya Riva Putra; Selvia Ferdiana Kusuma
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (865.565 KB) | DOI: 10.30645/j-sakti.v5i1.328

Abstract

PT. Bali Age is a company which engaged in freight forwarding service. Because of this, the company is using the trucks for carry out of their operational activities. Every truck always gets a routine maintenance at their garage, so they must provide the spare parts stock by themselves. The currently procurement of spare parts are still based on paper. By implementing the decision support in a new procurement system, it can provide a supplier recommendation for this company. This supplier recommendation which provides by system, are getting from the result of the comparation value from criteria priority calculation, using AHP method. The AHP method that implemented in this system, can also provide the final result of supplier recommendation comparison value with accurately.
Sistem Pakar Menggunakan Metode Backward Chaining Untuk Mengantisipasi Permasalahan Tanaman Kacang Kedelai Berbasis Web Ilka Zufria; Heri Santoso; D Darsih
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1089.418 KB) | DOI: 10.30645/j-sakti.v5i1.294

Abstract

Soybeans (Glycine max (L.) Merill.) are an important source of protein in Indonesia, it is a part of variety of beans. The soybeans’ need is increasing as people demand for raw materials. While there are so many problems with soy plants that they cause the decline in soy production. The decline in the production of soybean plants has been due to both pest and disease factors. Therefore in this condition it would require an expert to address the problem of soy farmers, but in this condition the lack of an expert and the time of the expert is a problem, so with by existence expert system can provide an alternative to addressing problems. This system of experts can be used to help soy farmers in an effort to identify pests and crop diseases and how the prevention and treatment of pest and soy diseases. The system was used Backward Chaining methods. This application made based Web used PHP programming language.
Analisa Sistem Pendukung Keputusan Untuk Menentukan Prioritas Strategi Terbaik Sebagai Upaya Penguatan Inovasi Teknologi Dalam Negeri Ina Tews BPPT Satrio Utomo
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1090.555 KB) | DOI: 10.30645/j-sakti.v5i1.319

Abstract

INA TEWS (Indonesian Tsunami Early Warning System) is an important part of the national disaster mitigation system, and a domestic technological innovation for tsunami disaster mitigation. In the assessment of technology development priorities, INA TEWS uses the Analytical Hierarchy Process (AHP) method and the Technology Readiness Level (TRL) method to assess the level of technology readiness. There are four criteria of assesment, namely urgency of need, financing, supply of raw materials, and acceleration of innovation. INA TEWS technology is divided into four technology components, namely Technoware, Humanware, Infoware, Orgaware. Based on the preferences of expert respondents, it shows that the most prioritized criteria at this time are supply of raw materials (30.9%), urgency of need (28.4%), financing (22%) and the last is innovation creation (18.8%). For the highest priority technology components are Technoware (42.5%), Orgaware (28.4%), Humanware (19%), and finally Infoware (10.1%). Technoware components are priority and top. As seen from the test results of various sensitivity chart analysts, the Infoware component looks the lowest of all other technology components. It seems that Infoware has not become the focus of attention for management in developing INA TEWS. For this reason, the Infoware component is encouraged to immediately meet the aspect of innovation creation criteria.
Deteksi Indikasi Kelelahan Menggunakan Deep Learning Dhomas Hatta Fudholi; Royan Abida N Nayoan; Maghfirah Suyuti; Ridho Rahmadi
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (903.898 KB) | DOI: 10.30645/j-sakti.v5i1.292

Abstract

Many students experience fatigue due to lack of sleep which can be caused by a psychological conditions or bad habits. Lack of sleep can affect student’s performance academically and causes many illnesses, stress and depression. Students with fatigue causes students to not study well, increasing risk of academic failure and will lead to having low GPA. In this research, fatigue detection is carried out to find out which students are experiencing fatigue. In this study, an annotated video dataset was used with a total of 18 subjects acted drowsy and alert. Fatigue detection is based on mouth movements, therefore mouth annotation is used. Mouth annotation has 2 categories, namely annotation 0 which indicates a closed mouth and annotation 1 which indicates the mouth is yawning. Previous study proves ResNet50 has better performance than other pre-trained models such as AlexNet, Clarifia, VGG-16, and GoogLeNet-19. We also applied image augmentation which is useful for providing new image variations to the model in each epoch by changing the rotation, random shift, and random zoom. ResNet50 model is used to perform binary classification which has two outputs, namely mouth stillness and yawning. The results of the frame classification are evaluated using precision, recall and f1-score. By using ResNet model, the results of the classification of frames labeled 0 or mouth stillness, obtained a precision of 0.72, a recall of 0.88, and an f1-score of 0.79. Meanwhile, the frame classification labeled 1 or yawning has a precision value of 0.85, a recall of 0.65, and an f1-score of 0.74.
Pengidentifikasian Citra Ikan Berformalin Dengan Menggunakan Metode Multilayer Perceptron Eka Pirdia Wanti; M Muhathir
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1126.224 KB) | DOI: 10.30645/j-sakti.v5i1.342

Abstract

The richness of Indonesia's natural resources in the marine area, makes the sea an ecosystem of the existing diversity of fish. Fish is one of the types of animal protein that can be consumed by humans. Fish also contains essential vitamins and amino acids needed by the body with a biological value of up to 90% with binding tissue that makes it easier for the body to digest them. With the large number of fish that fishermen get per day, fish traders also have to make the fish they sell durable, one of which is by preserving fish with formaldehyde. Formlain is also a dangerous substance if used for food, this is because this substance can cause death if consumed long term. So that the existing problems encourage the author to identify formalin fish images using the MLP (Multilayer Perceptron) method which is a fairly reliable method in the image detection process because the search process is very directional (paying attention to backpropagation) where the feature extraction used is GLCM ( Gray Level Co-Occurrence Matrix). From this study, it was found that the Accuracy value was 62%. Where the error rate is 50%. Recall is 85%, application is 39%, precisson is 58% and F1 score is 71%.
Implementasi Tata Kelola Teknologi Informasi Perpustakaan (Studi Kasus : Universitas Islam Negeri Raden Fatah Palembang) Fathiyah Nopriani
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (929.001 KB) | DOI: 10.30645/j-sakti.v5i1.308

Abstract

The Raden Fatah State Islamic University Library in Palembang is one of the university facilities that supports learning and teaching for students and lecturers. Performance at the Raden Fatah State Islamic University library in Palembang provides the best service for the entire academic community of the university by using the Library Information System, namely SLiMS (Senayan Library Management System). During the use of SLiMS, there was no evaluation using the COBIT 5 framework. The analysis was obtained from the results of the respondents' answers, namely the SLiMS manager with several domains from COBIT 5.
Implementasi Data Science dalam Ritel Online: Analisis Customer Retention dan Clustering Customer dengan Metode K-Means Irma Permata Sari
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (895.042 KB) | DOI: 10.30645/j-sakti.v5i1.333

Abstract

Data regarding huge sales and purchase transactions are stored electronically in company databases. Leave this data alone so it will not have any impact. Lately, many companies provide promo prices to customers to attract customers. However, the decision is suitable to be taken, regardless of sales growth, to not cause more significant losses. The sales show that has been recorded each year in the sales transaction database. This research focuses on implementing data science at a retail company to analyze sales performance using the cohort analytics method to calculate customer retention and perform clustering customer using the K-Means model. As the results, we can conclude that the company has sales performcean about 37.4%, seen from customer retention and the monthly sales volume within one year. There are three groupings produced, namely ID 0, 1, and 2. Customers with Cluster Label 2 are customers with the highest number of transactions compared to other groups.
Implementasi Metode TOPSIS pada Penerima Bantuan Sosial Akibat Covid19 di Desa Kotabatu Ciomas Bogor Enok Tuti Alawiah; Dwi Andini Putri
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (898.23 KB) | DOI: 10.30645/j-sakti.v5i1.299

Abstract

During the Covid 19 pandemic in 2020, many sectors were affected, one of which was the economic sector. Kotabatu Village, Ciobas District, Bogor Regency is a village that has been affected by social impacts due to the COVID-19 pandemic. Many people are forced to lose their jobs. Therefore, the Government provides cash social assistance. But the problem is that the provision of funds must be right on target only for the people who are affected. So that a decision support system is needed to determine the right policy. In this study, the TOPSIS method will be used as the best method for preference values and will be tested on 133 population samples. The results of the research conducted on the sample obtained a final score of 0.65, namely people who lost their jobs. So the provision of assistance can prioritize people who have lost their jobs in order to get help due to the COVID-19 pandemic