Sinkron : jurnal dan penelitian teknik informatika
Not a member yet
1261 research outputs found
Sort by
Composite Performance Index in Decision Making for Social Assistance
No full textThe majority of the residents in this village, approximately 90%, worked as farmers or farm laborers. Given the economic conditions, social assistance became crucial in reducing social inequality and enhancing the welfare of vulnerable communities. The role of village governance was significant in improving community welfare. The Village Hall served as the center of village administration, managing various activities, including the distribution of social assistance. The Village Hall was responsible for ensuring that social assistance was distributed fairly and effectively to recipients according to prevailing policies. However, the Village Hall faced issues such as inefficiency and inequality in the distribution of social assistance. The process of selecting social assistance recipients was still conducted conventionally, where Village Hall staff collected data on the community based on certain criteria. This method was prone to errors in decision-making and incorrect distribution of assistance, such as recipients who did not actually qualify still receiving aid, while those in need often did not receive appropriate support. These issues were caused by a lack of thorough analysis. The village government needed to establish a decision-making system that was accurate and precise. The operation of this system included all steps of problem identification, selection of relevant information, and determination of the approach used for decision-making through to the resolution of the issues. To achieve accurate results, this research applied the Composite Performance Index method. The aim of this research was to create a decision support system (DSS) for selecting social assistance recipients in the village. This DSS was expected to help staff improve the speed of social assistance classification, avoid errors, and produce accurate decisions
Study of Public Sentiment Towards Beauty Products Using A Machine Learning Approach: Random Forest Analysis On Social Media
No full textIn this digitalized era, the development of technology and the internet has brought significant changes in various aspects of life, including the way we shop. The trend of online shopping is increasingly prevalent and favored by the public, not least for cosmetic products. This research uses a quantitative approach to analyze public opinion or sentiment towards beauty products, especially beauty products. The data used in this research comes from online platforms. This research uses a beauty product dataset obtained from Kaggle. This research uses the Random Forest algorithm to analyze the data and produce findings, This algorithm is one of the advanced tools in Machine Learning that is focused on sorting data into the right categories, which in this context is used to classify public sentiment towards beauty products into categories such as positive, negative or neutral. Random Forest achieved a very high accuracy rate of 94.68% in the evaluation. However, it should be noted that the positive class has a low recall (25%) and a low F1-score (40%), indicating that the model may struggle to detect positive sentiment towards beauty products beauty products. In general, the model did well in classifying neutral and negative sentiments. Sentiment analysis shows that the majority of public sentiment towards beauty products is neutral, with a significant amount of negative and positive sentiment. It is evident that user opinions are informative or descriptive without conveying strong positive or negative emotions
Analysis Technique Data hiding using HPA DCO on SATA Hard Drive
No full textData hiding techniques in the Host Protected Area (HPA) and Device Configuration Overlay (DCO) areas of SATA Hard Disk Drives have become a frequently used anti-forensic activity to hide data and evidence. The area is inaccessible to standard operating systems and software, making it capable of hiding data. This technique utilizes the ability of the SATA Hard Disk Drive to reconfigure the storage size so as to hide evidence. When anti-forensic data hiding Host Protected Area (HPA) and Device Configuration Overlay (DCO) activities occur, it is necessary to conduct a digital forensic investigation to find clues that are useful in solving crimes. Therefore, in this research, an assessment of data hiding techniques using Host Protected Area (HPA) and Device Configuration Overlay (DCO) on SATA Hard Disk Drives is carried out. The implementation of the HPA DCO data hiding technique on a SATA Hard Disk Drive by identifying the HPA DCO area on the SATA HDD and investigating the acquisition results on the SATA HDD is the subject of this research. It is expected that the results will provide a comprehensive overview of HPA DCO data hiding techniques on a SATA HDD as well as recommendations on how to identify and investigate SATA HDDs that have HPA DCO. This effort aims to evaluate the HPA DCO data hiding technique in various cases and provide insight into the potential use of this technique in hiding data or evidence
Performance Single Linkage and K-Medoids on Data with Outliers
No full textOne way to assess the economic growth of a province is by examining its Gross Regional Domestic Product (GRDP). GRDP calculated through the production approach reflects the total value added by goods and services from various sectors within a particular region over a specified period. To determine the GRDP, 17 business sectors are considered. In 2023, the GRDP growth rate in Papua has decreased to 3.44%, down from 4.11% the previous year. To help the government improve Papua’s GRDP, an analysis is required. Clustering methods can group regencies and cities with similar characteristics. Boxplots are used to identify outliers in the data. The data contains outliers, so one method that can be used is K-Medoids. Euclidean Distance is used to calculate the distance matrix. Before calculating the distances, standardization using z-score normalization is performed to ensure that the data ranges are the same. This article aims to identify the most effective method for clustering regencies and cities in Papua using GRDP at constant price data. Both Single Linkage and K-Medoids methods are applied in this study. The DBI is used for evaluation, with lower DBI values indicating better methods. According to the DBI results, Single Linkage outperforms K-Medoids for clustering regencies and cities in Papua, with the optimal number of clusters being three.
Keywords: Euclidean Distance; Davies Bouldin Index (DBI); Gross Regional Domestic Bruto; K-Medoids; Single Linkage; z-score Normalizatio
Optimization of Stock Forecasting in Bali Retail Businesses to Support the Digital Economy Using Weighted Moving Average (WMA) Approach
No full textThe development of the digital economy provides new challenges for the retail sector, especially in stock management. Accurate stock management is a key factor in improving operational efficiency and minimizing the risk of overstock and understock. This research aims to optimize stock forecasting in retail businesses in Bali using the Weighted Moving Average (WMA) method. WMA gives greater weight to the most recent data in order to forecast future demand for goods. Sales data from 2017 to 2021 was collected and used as the basis for forecasting. The forecasting process was conducted for several products, including Dolphin and Dua Kelinci. The results show that WMA is able to provide accurate predictions, especially for products with stable demand patterns. For Dolphin products, the WMA forecast for January 2024 predicted a demand of 14.8 units, with a Mean Absolute Deviation (MAD) of 3.64. Dua Kelinci products, however, experienced more fluctuations in demand, with a forecasted January 2024 demand of 7.6 units and a MAD of 4.3. Despite some variations, WMA proved to be more accurate compared to simpler methods like Simple Moving Average (SMA). By using WMA, retailers can more efficiently manage stock, improve customer satisfaction, and reduce the risk of overstocking or understocking. This research confirms the importance of integrating advanced forecasting methods in supporting the competitiveness of the retail sector in the digital economy era
Implementation Of Technology Towards The Merdeka Curricullum Doing Diagnostic Assessment For Student with Autism Spectrum Disorder In Preschool Level
No full textThis research aims to developing an effective and applicable diagnostic assessment instrument that has been prepared based on the requirements of competency standards for graduates at the preschool institute. The instrument functions is to separate mild and moderate levels of the autism spectrum, for students with learning disabilities resembling autism spectrum symptoms in early childhood. This research used R and D methode from Borg and Gall with result is this application product containing a 23-item questionnaires that has been validated by material, language and media experts. Subject of this research is teachers of preschool institutions, and the objek is the instrument of diagnostic assessment wich researcher build. The practicality test results of this instrument have a percentage level of 92.52% in the 'very practical' category, with a validity test level of 84%, on the Likert scale showing the instrument is 'very feasible'
Application of the C4.5 Algorithm for Predicting Students' Learning Styles Based on Somatic, Auditory, Visual, and Intellectual Models
No full textEducation in Indonesia has seen significant development over the past few decades, with government efforts to improve access and quality of education throughout the country. Programs such as the 12-Year Compulsory Education and curriculum revitalization have driven an increase in school participation rates. However, challenges such as the quality gap between urban and rural areas and the low competence of teachers remain key issues in achieving more equitable and high-quality education for all segments of society. This study aims to apply the C4.5 algorithm to predict students' learning styles based on the Somatic, Auditory, Visual, and Intellectual (SAVI) model. Learning styles are an important aspect of education that affects the effectiveness of learning. By understanding individual learning styles, educators can optimize teaching methods according to students' needs. In this study, student learning style data was collected and analyzed using the C4.5 algorithm, an effective decision tree method for data classification. The results of this algorithm are decision trees that categorize students into one of four learning styles based on specific features. This study shows that the C4.5 algorithm has good accuracy in predicting learning styles, with an entropy value of 1.55 and a gain of 0.156. The implementation of the results of this study is expected to help teachers develop more optimal teaching strategies in preparing learning materials according to students' learning styles
Cluster Analysis of Food Social Assistance in DKI Jakarta: K-Means Approach to Identify Expenditure Patterns and Beneficiaries
No full textThis study aims to evaluate the effectiveness of the K-Means algorithm in grouping social assistance recipients in DKI Jakarta based on various demographic and economic factors, such as income, number of family members, and living conditions. The main objective of this study is to optimize resource allocation in social assistance programs by identifying different recipient clusters, so that aid distribution becomes more targeted. In this study, the K-Means algorithm was used with an optimal number of clusters of 3, and produced an accuracy rate of 85%, indicating that this algorithm is effective in grouping large-scale and complex data. However, there are challenges related to the sensitivity of K-Means to outliers and data imbalances that affect the results of the analysis. The results also show that areas such as Central Jakarta and South Jakarta receive more social assistance compared to other areas such as North Jakarta and East Jakarta, reflecting differences in needs in various regions. These findings emphasize the importance of selecting the right variables, such as access to health facilities and economic conditions, in producing more accurate groupings. Overall, this study provides valuable insights into efforts to optimize the distribution of social assistance in DKI Jakarta and recommends further research to address the limitations that exist in the use of the K-Means algorithm, especially in the context of data that is imbalanced or has large variations
Comparison of K-Means and Self Organizing Map Algorithms for Ground Acceleration Clustering
No full textThis study evaluates earthquake-induced ground acceleration in Indonesia, which is located in the Pacific Ring of Fire zone, using Donovan's empirical method and comparing two clustering algorithms, Self Organizing Map (SOM) and K-Means. The main problem faced is the high risk of earthquakes in Indonesia and the need for effective methods to predict potential damage to buildings and infrastructure. The research objective is to evaluate earthquake-induced ground acceleration and identify acceleration distribution patterns using clustering techniques. The solution methods used include the application of the Donovan method to calculate ground acceleration based on BMKG data, as well as the use of SOM and K-Means algorithms to cluster the ground acceleration data. GIS and Python applications are used to visualize the clustering results. The results show that the Donovan method integrated with SOM and K-Means provides significant insights into the distribution of ground acceleration, thus assisting in risk evaluation, disaster mitigation planning, and the development of more effective earthquake-resistant infrastructure development strategies in Indonesi
Machine Learning and Deep Learning Approaches for Energy Prediction: A Systematic Literature Review
No full textThis paper offers a literature review on the application of Machine Learning (ML) and Deep Learning (DL) techniques in energy prediction. Contemporary energy systems' challenges, such as load fluctuations and uncertainties linked to renewable energy sources, render traditional methods like ARIMA and linear regression insufficient. The objective of this paper is to identify the most widely used ML and DL approaches, compare their performance against conventional methods, and explore the implementation challenges along with potential solutions. The methodology for this literature review involves analyzing publications from Scopus, IEEE Xplore, and ScienceDirect covering the period from 2019 to 2024. The findings indicate that DL methods, particularly Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, are effective in handling sequential data, while hybrid models like CNN-GRU enhance prediction accuracy in innovative grid applications. Challenges identified include overfitting and data complexity, which can be addressed through regularization techniques and computational optimization using GPUs. In conclusion, this paper asserts that ML and DL play a significant role in improving prediction accuracy and facilitating the transition towards sustainable energy and smart grids. To further enhance performance in the future, the paper recommends the development of ensemble models and the integration of attention mechanisms