cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Agung Nugroho
Contact Email
agung@pelitabangsa.ac.id
Phone
-
Journal Mail Official
jpcs@pelitabangsa.ac.id
Editorial Address
Jl. Inspeksi Kalimalang Tegal Danas Arah Deltamas, Cikarang Pusat, Kabupaten Bekasi
Location
Kab. bekasi,
Jawa barat
INDONESIA
Journal of Practical Computer Science (JPCS)
Published by Universitas Pelita Bangsa
ISSN : -     EISSN : 28098137     DOI : https://doi.org/10.37366/jpcs
Core Subject : Science, Engineering,
Computer Science & IT Engineering
Journal of Practical Computer Science (JPCS) sebagai media kajian ilmiah dari hasil penelitian, pemikiran dan kajian dan implementasi berkaitan dengan bidang Ilmu Komputer Praktis. Fokus dan ruang lingkup Journal of Practical Computer Science (JPCS) meliputi: - Rekayasa Perangkat Lunak - Kecerdasan Buatan - Data Mining - Machine Learning - Internet of Things - Jaringan Komputer - Keamanan Informasi - Topik kajian lain yang relevan
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 5 Documents
 1 
Search results for , issue "Vol. 2 No. 2 (2022): November 2022" : 5 Documents clear
Teknik Pengenalan Wajah Menggunakan Model Ekstraksi Fitur Citra Digital Nazaruddin Ahmad; Arifiyanto Hadinegoro
Journal of Practical Computer Science Vol. 2 No. 2 (2022): November 2022
Publisher : DPPM Universitas Pelita Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37366/jpcs.v2i2.1465

Abstract

The use of information technology has been widely encountered in our daily life. Not only to process data, to record tools but also to identify and recognize human characteristics. This is called biometric technology. This technology identifies the unique and permanent parts of the human body such as fingerprints, eyes, and the shape of the human face. To identify and recognize human faces, use facial image processing and analysis, such as determining the component regions of the human face and their characteristics. Splitting the face image into facial components, then extracting it into the features of the eyes, nose, mouth, and chin. The distance between each component is measured, then combined with other features to form facial semantics. The face can be categorized into the T Zone which consists of the forehead, eyes, nose and mouth. Eyes, nose, and mouth are the most unique facial components for facial recognition because they have unique facial recognition features. For the distance of the eye and mouth triangle feature, J1 – J3 shows that there are 140 unique data with the percentage value is 93.33%. The feature distance J4 – J6 also shows that there are 126 unique face images with a percentage value of 85%. Keyword: face image, eiginfaces, image extraction, face recognition.
Prediksi Persediaan Material Menggunakan Metode Single Exponential Smoothing noeman noeman; Fadhila Fajri Putri; Rakhmat Purnomo; Robertus Suraji
Journal of Practical Computer Science Vol. 2 No. 2 (2022): November 2022
Publisher : DPPM Universitas Pelita Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37366/jpcs.v2i2.1468

Abstract

Material is an important material in manufacturing companies that make components of an item. Used to make various components which are then processed on injection machines. This of course makes warehouse and Production Planing Inventory Control (PPIC) employees have to see and ensure that the availability of materials can be fulfilled for several days or months, then make planning for spending or using materials if the existing materials have reached the availability limit. , and also inconsistent data such as lack of material. The purpose of this study is to find out how much material inventory is for the next 1 period. The method used is Single Exponential Smoothing with a constant of 0.9. Provision of constants for calculations from the High Impact Polystyrene (HIPS) 495F NATURAL material data sample which is applied to 3 other types of materials. The result of this research is that for PBT DURANEX 3300 NATURAL, the result is 777.01 with MSE 2880745.72, MAD 489.96 and MAPE 0.074%. ABS material type TOYOLAC T500-322 NATURAL got 2813.18 results with MSE 342161.98, MAD 168.85, and MAPE 0.092%. Material Type AS STYLAC 769 6A-X8113 IVORY got 663.46 results with MSE 222210.16, MAD 136.07, and MAPE 0.092%.
Penerapan Metode User Centered Design pada Rancangan User Interface Marketplace Pemasaran Produk Olahan Perikanan Fauzan Natsir; Redo Abeputra Sihombing
Journal of Practical Computer Science Vol. 2 No. 2 (2022): November 2022
Publisher : DPPM Universitas Pelita Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37366/jpcs.v2i2.1472

Abstract

Activities that support various activities in the fisheries sector, one of which is processed fish products, seeks to improve the economy of the community, especially fishermen in processing marine products. One of the efforts is to expand the distribution of processed seafood and penetrate the market through designing a user interface for the processed seafood distribution system. The method applied in this study is User Centered Design (UCD) with a design philosophy that places the user at the center of the system development process. The UCD approach is supported by techniques, tools, procedures, and processes that help design interactive systems that are more user centric. Based on usability testing that uses a usability scale system, the marketplace user interface model for marketing processed fish products is assessed with a yield of 86.5%. So that this marketplace user interface design mockup has been rated as user friendly which is indicated using high functionality and in accordance with the design. Keyword: User Centered Design (UCD), user interface, marketplace, processed fish.
Tinjauan Pustaka Sistematis: Penerapan Metode Naives Bayes untuk Klasifikasi dalam Dataset Cuaca Ahmad Zulfikri; Gunawan; Wresti Andriani
Journal of Practical Computer Science Vol. 2 No. 2 (2022): November 2022
Publisher : DPPM Universitas Pelita Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37366/jpcs.v2i2.2101

Abstract

This study aims to determine the application of the naive bays method for classification in Weather datasets using the systematic literature review method. Weather forecasting research is an interesting object to study because weather is one of the things that influences everyday life so good accuracy in weather forecasts is very much needed. This study uses the systematic literature review method, which is a process of identifying, assessing, and interpreting facts and evidence from available research with the aim of finding answers to a particular research question. Climate change and weather are problems faced by almost the whole world which classify and predict. The problem is that there are many influencing variables, so it is quite difficult and unpredictable. Climate and weather change is human-caused global warming which makes it more difficult to solve weather problems. The results of this study can be used to measure the level of accuracy and MSE of the weather. the dataset serves as a metric for determining precipitation groups and it is concluded that the system can make predictions with an accuracy probability of up to 92% on new data. for the precision class to get a result of 100% where the system can predict the suitability of the class that is relevant to the results of the selected class.
Feature Selection Menggunakan Algoritma Meta-Heuristik Salamet Nur Himawan; Rendi; Nur Budi Nugraha
Journal of Practical Computer Science Vol. 2 No. 2 (2022): November 2022
Publisher : DPPM Universitas Pelita Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37366/jpcs.v2i2.2289

Abstract

Machine learning requires data to make predictions. Data can have a large number of features. The large number of features can cause machine learning models to overfit, increase model complexity, and high computational costs. Feature selection is one method for optimizing machine learning models. Feature selection reduces the number of features used in the learning process. This research proposes a feature selection method using meta-heuristic algorithms. The machine learning model serves as the objective function for the meta-heuristic algorithm. The objective function is evaluated at each iteration to obtain the most influential features in the model. The machine learning models used are Random Forest, k-Nearest Neighbors, and Support Vector Machine. The meta-heuristic algorithms used are Differential Evolution, Flower Pollination, Grey Wolf, and Whale Optimization. The research shows that using meta-heuristic algorithms can improve the accuracy of machine learning models with fewer features. The Support Vector Machine – Differential Evolution scheme has the highest accuracy and uses the fewest features.

Page 1 of 1 | Total Record : 5

 1 

Filter by Year

2022 2022


Reset
Filter By Issues
All Issue Vol. 4 No. 1 (2024): Mei 2024 Vol. 3 No. 2 (2023): November 2023 Vol. 3 No. 1 (2023): Mei 2023 Vol. 2 No. 2 (2022): November 2022 Vol. 2 No. 1 (2022): Mei 2022 Vol 1 No 2 (2021): November 2021