Newinera Publisher (Scientific Journal)
Not a member yet
1926 research outputs found
Sort by
Analysis of Long Short-Term Memory and Support Vector Regression Methods in Forecasting Electric Energy Sales: Case Study
Full text linkThis study aims to predict the sales of electrical energy of PT PLN (Persero) Greater Jakarta Distribution Unit by using machine learning methods, specifically Long Short-Term Memory (LSTM) and Support Vector Regression (SVR). The data used includes electrical energy sales trends from 2016 to 2023 as well as external data from the Central Statistics Agency (BPS), which includes economic and demographic factors that affect energy demand, such as economic growth, population, and seasonal factors. LSTM was chosen for its ability to handle long-term dependencies in time series data, while SVR was used as a comparison to other regression methods. The resulting model is expected to provide more accurate predictions and be useful for PT PLN in planning the distribution of electrical energy efficiently. This research also contributes to the development of the application of machine learning in forecasting, which is growing in various sectors, including the energy sector, to improve operational efficiency and data-based decision making
Product and Store Recommendation System Using K-Means Clustering and Hybrid Filtering on Marketplace
Full text linkThe development of information and communication technology has driven significant changes in the digital business landscape, particularly in the e-commerce sector. Marketplaces have become crucial platforms for connecting consumers with product providers, including supporting the growth of Micro, Small, and Medium Enterprises (MSMEs). As transaction volumes and product diversity continue to increase, new challenges have emerged in providing consumers with relevant product recommendations. This study aims to develop a product and store recommendation system by combining K-Means Clustering for customer segmentation and Hybrid Filtering to enhance recommendation accuracy. The system was developed using an experimental approach based on software engineering, with historical transaction data from the CV. Talongka Jaya marketplace as the primary data source. Customer segmentation resulted in five clusters based on purchasing behavior patterns, such as transaction frequency and product category preferences. These clustering results were then used to tailor product and store recommendations to the characteristics of each segment. The recommendation system was built by integrating Collaborative Filtering and Content-Based Filtering with optimal weights of 0.7 and 0.3, respectively. Evaluation using 5-fold cross-validation demonstrated that Hybrid Filtering achieved a Precision of 0.78 and an F1-Score of 0.74, outperforming single-method approaches. These findings confirm that the integration of clustering and hybrid filtering is effective in enhancing service personalization and improving users’ shopping experience. This research makes a significant contribution to the development of data mining-based recommendation systems for MSME marketplaces, although there remains room for further improvement through the integration of real-time data and deep learning-based sequential recommendation methods
Web-Based Population Data Information System at Suwaduk Village Office to Improve Service Efficiency
Full text linkThe rapid development of information technology has encouraged government agencies, including village offices, to utilize digital systems to improve the effectiveness of data management. At the village level, population data management is still largely done manually or using Microsoft Excel files, which have various limitations in terms of search speed, data security, and information integration. This study aims to design and build a Web-Based Population Data Collection Information System to assist village governments in recording, processing, and presenting population data more effectively and efficiently. This system was developed using the Waterfall method, which consists of the stages of needs analysis, system design, implementation, testing, and maintenance. The implementation results show that this system is able to overcome various previous problems, increasing efficiency, accuracy, and transparency in population data management. Features such as Excel data import with automatic validation, population data and family card management, data conversion history, and automatic generation of certificates, work as expected. Thus, this system has a positive impact on administrative services and data-based decision-making in Suwaduk Village
Livestock Population Map Based on Provinces in Indonesia Using the K-Medoids Method
Full text linkIndonesia is one of the countries with a large livestock population. A healthy and stable livestock population can affect the production and availability of livestock products, such as meat, milk, eggs, and skin. FAO's Domestic Animal Diversity - Information System (DAD-IS) data (2020) recorded around 206 large farms, small farms, poultry and pigs. Clustering is a technique for grouping data without unknown class labels. Clustering is used to find data that has similarities. The clustering technique is to determine the initial cluster center. This study is intended to determine the best cluster value using the selected method. The purpose of this study is to create a system that can process and group data. With data obtained from the central statistics agency. This study uses the topic of Livestock Population Map in Indonesia using K-Medoids. The algorithm used in this study is K-Medoids. The K-Medoids method is a variation of the K-Means method to retrieve k data, the number of clusters in a data set with n objects. There are several processes carried out in this study including collecting data, then entering the preprocessing stage, grouping data that has similarities between data. After clustering using K-Medoids, it was found that Cluster 0 had 3 provinces with the highest average population with types of livestock such as Dairy cattle, Beef cattle, Sheep and Goats, Cluster 1 had 29 provinces with the lowest average population, Cluster 2 had 2 provinces with the highest average number for types of livestock such as Buffalo, Horse and Pig
Development of a Class IIB Pati Prison Inmate Processing System Using Barcodes
Full text linkCorrectional facilities in Indonesia face significant challenges in inmate management due to reliance on manual, paper-based systems for room occupancy verification, leading to inefficiencies, prolonged verification times, high potential for data errors, and substantial workload for correctional officers during frequent room reshuffling activities. This study aims to develop a web-based information system leveraging barcode technology to streamline the inmate verification process at Lapas Kelas IIB Pati, minimizing human error, enhancing administrative efficiency, and accelerating data management processes. The research employed a Research and Development (R&D) approach with qualitative methodology using the Waterfall model for system development, incorporating data collection techniques including observation, semi-structured interviews with correctional officers, literature review, and document analysis. The study population comprised all data management processes for inmates and officers at Lapas Kelas IIB Pati, with purposive sampling selecting key informants, relevant documents, and existing manual systems. System validation was conducted through Blackbox Testing to verify functional specifications and User Acceptance Testing (UAT) using Likert scale questionnaires to evaluate user satisfaction. The developed system successfully automated inmate verification through QR/barcode scanning, implemented role-based access controls, and provided room transfer functionality, with all system functionalities achieving successful outcomes in testing, demonstrating operational viability and significant improvement in efficiency and data accuracy. The web-based inmate processing system effectively addresses operational challenges in correctional facility management, providing a practical solution for digital transformation in Indonesian correctional institutions
Evaluation of Slope Stability in Mining Areas Using the Morgenstern Price Method
Full text linkIndonesia’s mining sector, particularly in areas like Morowali Regency, Central Sulawesi, faces significant geotechnical challenges due to its location in the Pacific Ring of Fire. One of the key concerns in open-pit mining operations is slope instability, which can lead to landslides, threaten worker safety, damage infrastructure, and disrupt production. This study evaluates the slope stability in the Sambalagi site of PT. Wosindo Berkat Abadi using the Morgenstern-Price method, a limit equilibrium approach known for its accuracy in heterogeneous slope conditions. Field data were collected, including slope geometry, geological conditions, material strength, and hydrogeological factors. The safety factor (FK) was calculated based on geotechnical parameters such as cohesion, internal friction angle, and unit weight of the slope materials primarily saprolite and limonite. The actual slope FK value at PIT D was found to be 0.974, below the standard requirement (≥1.3) set by the Ministerial Decree No. 1827K/30/MEM/2018. To improve stability, a revised slope design was proposed, including reducing slope angles to 35°, increasing bench widths to 2 meters, and decreasing slope height per bench to 4 meters. The simulation of this revised geometry showed that it could achieve the required FK value. The study contributes to safer and more efficient mine planning by demonstrating the importance of integrating detailed geotechnical analysis in slope design, especially in tropical high-rainfall mining regions
Vigilante Law Enforcement Eigenrichting Causing Death Through a Criminological Perspective
Full text linkThe phenomenon of vigilantism (eigenrichting) resulting in death reflects a failure in the formal legal system and the rise of revenge practices in society. This research uses a normative juridical method that focuses on the analysis of positive legal norms. Data were collected from various written sources, including legislation, court decisions, legal doctrine, legal theories, and the views of legal experts. The analysis was conducted qualitatively using a descriptive approach to interpret the meaning and information contained in documents, media reports, and newspaper archives. The analysis found that low legal understanding, socio-economic inequality, and a crisis of judicial legitimacy are the main triggers for vigilante behavior. The impacts are clear: loss of life, weakened public trust in legal institutions, and increased social insecurity. Recommendations include transparent and professional law enforcement, early legal education, improving socio-economic conditions, and implementing restorative justice principles to prevent revenge-based violence
The Wurumana Institution in the Life of the Lio Ethnic Group
Full text linkThis study explores the Wurumana institution within the Lio ethnic community of Maurole Village, East Nusa Tenggara, using a descriptive qualitative approach. Data were collected through in-depth interviews, participatory observation, and document analysis. The research identifies three main functions of Wurumana: (1) fulfilling bridewealth obligations (belis), facilitating collective resource mobilization for marriage payments; (2) reinforcing kinship solidarity, strengthening communal bonds; and (3) providing a conflict resolution mechanism through customary mediation. The ritual unfolds in nine stages, beginning with family summons and ending with the presentation of rice, garments, and Lio woven textiles. The persistence of Wurumana is explained by three factors: the moral principle of jaga waka (preserving familial dignity), the authority of the Eda (traditional leaders), and the tau tei duna mea ethic (the cultural imperative of contribution, enforced through social sanctions). This study highlights the enduring relevance of Wurumana in contemporary Lio society and contributes to understanding the social organization of the Lio ethnic group
Fintech Integrated Economic Education Model: Improving Inclusive Financial Competence Among Millennial MSMEs
Full text linkThis research aims to develop and test a fintech-integrated economic education model to improve inclusive financial competence among millennial MSMEs in Makassar City. Using a descriptive qualitative approach, the study involved ten MSME actors selected purposively and explored their financial behavior, challenges, and responses to a structured training model. The model combines basic economic education, practical use of digital financial applications, and reflective learning processes. Data were collected through interviews, observations, documentation, and pre-test and post-test analysis. The results show significant behavioral changes in financial management, including routine bookkeeping, financial separation between personal and business funds, and improved budgeting practices using fintech tools. The model proves effective in contextualizing economic education and digital literacy within the everyday business practices of MSMEs. These findings underscore the importance of designing participatory, practical, and technology assisted learning models to enhance financial inclusion and empower small business actors sustainably
The Influence of Multicultural Education and Learning Motivation on Student Academic Achievement
Full text linkThis study aims to determine the extent of influence of multicultural education and student motivation on student academic achievement at St. Familia Catholic Vocational School. The method used in this study is a quantitative research method using a correlative approach with the aim of testing the hypothesis regarding the magnitude of the influence and whether or not there is a relationship between the independent variables (X1 and X2) and the dependent variable (Y). The sample in this study according to the Slovin formula was 62 people. The research instrument used was distributing questionnaires with alternative answers in the form of statements provided. Before conducting data analysis, analysis requirements were first tested, namely the normality test, linearity test and multicollinearity test. Hypothesis testing used multiple Linear Regression analysis. The results of the study showed that multiculturalism education partially influenced student academic achievement at Santa Falimia Tomohon Vocational School with a percentage of 81.9% and was in the very good category. Learning motivation partially influenced student academic achievement at Santa Falimia Tomohon Vocational School with a percentage of 54.3% and was in the good category. Multicultural education and learning motivation together influence students' academic achievement at Santa Falimia Tomohon Vocational School with an influence percentage of 91.7% and is in the very good category