JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
Determining the Grade of Robusta Coffee Beans of Lampung, Bengkulu, and South Sumatra Provinces by Using the Analytical Hierarchy Process (AHP)
Get PDFCoffee is an important commodity for the world business community. One of the world's leading coffee producers is Indonesia. In Indonesia, several provinces produce coffee beans, especially in Sumatra island. They generally cultivate robusta-type coffee. The determination of coffee quality here is still done manually. Recently, along with the increasing recognition of computers, several decision-support system approaches have been introduced, including the Analytical Hierarchy Process (AHP). This research aims to implement the AHP to assess Indonesian robusta coffee beans (Lampung, Bengkulu, and South Sumatra). The researchers use a systematic process, including the preparation stage, data collection using datasets, determination of criteria and alternatives, hierarchical structure, creation of matrices to compare pairs, calculation of priority vectors and eigenvector values, and accuracy testing. This research uses six criteria with 19 sub-criteria and seven alternatives. From the rankings calculated using the AHP method for coffee production areas, the best quality coffee bean is in West Lampung, with the highest value of 0.28. The results of this study are compared with those given by an expert. The results show the MAPE error of 4.42%, a very accurate category. Thus, it is shown that this method provides excellent results. Future research can be conducted to develop a more sophisticated and efficient AHP method for multi-criteria decision-making in various fields such as business management, engineering, environment, and health
Integration of SEM and Nonparametric Spline in Spatial Data Modeling and Visualization for Analysis of CO2 Reduction Using Green Space in Makassar City
Get PDFThis study aims to analyze the characteristics of green space in mitigating carbon dioxide (CO2) levels in Makassar City by integrating Structural Equation Modeling (SEM) with Nonparametric Spline methods. Data were collected from 251 observation points, which were mapped using ArcGIS, along with satellite imagery captured between September 27 and October 1, 2024. The data were used to identify land use fractions, including shrub vegetation, non-shrub vegetation, roads, residential areas, and water bodies. The variables analyzed include Net CO2, green space characteristics (shrub and non-shrub fractions), non-green space characteristics (residential, industrial, commercial, road, sea, and drainage systems), and meteorological factors (temperature, humidity, and solar radiation). The results indicate that the optimal model for green space characteristics was found at the knot point 36, with a minimum Generalized Cross Validation (GCV) value of 27,644.53. This model divides the area into two regions: those with less than 36% green space and those with more than 36% green space. An increase in green space is generally associated with a reduction in CO2 levels. Conversely, the best model for non-green space characteristics was found at the knot point 66, with a minimum GCV value of 27,644.18. An increase in non-green space above 66% associated with a significantly greater rise in CO₂ levels. This study provides data-driven recommendations for urban planning and green space management, utilizing statistical modeling and spatial data visualization to inform strategies for reducing CO2 emissions in Makassar City
Using IT2FS, DEMATEL, and TOPSIS to Build Sustainable Solutions for Vietnamese Coffee
Get PDFEnsuring the sustainability of coffee supply chains in emerging economies is a growing concern due to complex systemic barriers and limited strategic direction. The Vietnamese coffee industry is ranked second in global coffee exports and plays a vital role in Vietnam's economy. The Vietnamese coffee supply chain encompasses a vast network of smallholder farmers, local processors, and exporters, presenting challenges related to sustainability, price volatility, and quality control. This study proposes the use of Interval Type-2 Fuzzy Sets (IT2FS), Decision-Making Trial and Evaluation Laboratory (DEMATEL), and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to analyze and rank the barriers and strategic interventions in Vietnam's coffee sector. Using IT2FS-DEMATEL, we looked at the driving and dependent relationships between six main barriers and six solutions that focus on sustainability. The results showed that the DEMATEL-based structural analysis revealed that Unstable Market and Trade Conditions had the most substantial driving influence. At the same time, the Lack of Best Cultivation Quality Standards was the most dependent factor. The TOPSIS analysis ranked Establishing National Coffee Cultivation Standards as the top solution, which was remarkably close to the optimal solution vector. These results provide a thorough, evidence-based plan for determining the initial actions to take in stabilizing Vietnam's coffee supply chain during times of volatility. It gives policymakers and industry stakeholders a clear framework for developing targeted actions to enhance the sustainability and resilience of coffee supply chains
User Interface Design of Student Final Project Schedule Application
Get PDFThis study discusses the user interface (UI) design for a proposal seminar and comprehensive exam scheduling application for Visual Communication Design Study Program students at Padang State University. The main problem identified is the manual scheduling system, which leads to decreased productivity, schedule conflicts, and delays in providing information to students. The urgency of this research lies in the need for a more efficient system to manage seminar schedules that occur throughout the academic year. This study's novelty is applying the User-Centered Design (UCD) method in UI design, ensuring the interface aligns with user needs and experience. The research method consists of UCD phases, including understanding the context of use, specifying user requirements, designing solutions, and evaluating the design using heuristic evaluation and the User Experience Questionnaire (UEQ). The results indicate that the developed UI design enhances scheduling efficiency, reduces manual errors, and improves user experience. The heuristic evaluation results show that the aspects of Match between System and the Real World and Recognition Rather than Recall received the highest scores, each scoring 4.9, indicating that the system is intuitive and easy to use. Additionally, the UEQ results demonstrate significant improvements in perspicuity (+2.7), efficiency (+2.55), and dependability (+2.48), all classified as excellent, suggesting that the proposed design is highly intuitive and optimally supports students’ academic processes
Student's Attitudes and Motivation Towards the Effectiveness of Open Distance Learning (ODL) in Malaysian Universities
Get PDFOnline distance learning (ODL) has transformed the educational environment and ensured educational continuity during global crises. As ODL becomes a permanent mode of education, continuous research into its effectiveness is imperative. This study investigates the ARCS model as a mediator between student attitudes, learning platforms, and ODL effectiveness, focusing on student experiences and outcomes. Utilizing a quantitative approach, an online survey comprising 31 items across five domains, including the ARCS model, was administered to 123 participants currently or previously engaged in ODL. The findings reveal that ODL effectiveness is significantly enhanced by positive motivational factors supported by psychological and emotional attitudes. Contrary to initial assumptions, platform availability, and accessibility do not independently influence ODL effectiveness; instead, motivation positively mediates effectiveness. This study provides institutions with the flexibility to improve learning platforms and offers insights to boost student motivation. Additionally, the study underscores the importance of fostering supportive attitudes to maximize ODL benefits. Recommendations for future research include exploring other mediating factors that may impact ODL effectiveness and examining diverse student populations to generalize the findings further. By addressing these areas, educational institutions can better understand the dynamics of ODL and implement strategies to enhance student experiences and outcomes. This study contributes to the growing knowledge of ODL, highlighting critical areas for institutional improvement and student support. It emphasizes the need for a holistic approach to educational technology, where motivational and attitudinal factors are integral to achieving effective and impactful online learning
Assessing InsurTech Purchase Intentions Among Young Working Adults in Malaysia: A TRA Approach
Get PDFInsurTech is emerging as a key player in Malaysia's insurance landscape, bolstered by strong government support, regulatory initiatives, and increasing consumer demand for digital solutions. As the insurance industry undergoes digital transformation, understanding the factors driving the adoption of InsurTech platforms is crucial for both academic inquiry and industry practice. This study aims to investigate the factors influencing young working adults' intentions to purchase life insurance using InsurTech platforms. Utilizing a quantitative approach based on the Theory of Reasoned Action (TRA), the research gathered data from 118 respondents through a non-probability convenience sampling method, which was then analyzed using SPSS version 29 and multiple linear regression. The findings indicate that attitude, subjective norms, insurance literacy, and trust have significant and positive effects on the intention to purchase life insurance via InsurTech platforms among Malaysian young working adults. Notably, attitude and trust emerged as the most influential factors, highlighting the transformative role of technology in shaping consumer behavior. These results, along with broader industry trends, emphasize the growing importance of InsurTech in the insurance sector, particularly in driving purchase intentions among younger demographics. To stay competitive, insurers must focus on fostering trust and enhancing the perceived value of their digital platforms. The rapid integration of AI, IoT, and other advanced technologies not only streamlines operations and reduces costs but also enhances customer experience, ensuring that InsurTech will remain central to the industry's future. For future research, investigating the impact of emerging technologies such as blockchain and AI on trust and customer experience within InsurTech platforms would be a promising direction
Multivariate Time Series Forecasting using Hybrid Vector Autoregressive and Neural Network for Coupled Roll-Sway-Yaw Motions Prediction
Get PDFThere are six types of motion referred to as the six degrees of freedom, which define the motion of a ship. For a ship to remain stable, it must be in a symmetrical position. Therefore, a ship's stability can be determined based on its motion. Ship motions can be analyzed either in an uncoupled system or a coupled system. One of the coupled motion systems that is often studied is the roll-sway-yaw motion. In this study, we apply the Hybrid Vector Autoregressive–Neural Network (VAR-NN) model to build a multivariate time series model for predicting the roll-sway-yaw motions of a prototype ship. The Hybrid VAR-NN is a data analysis technique that integrates the linear capabilities of the VAR model with the nonlinear capabilities of the NN model to capture both linear and nonlinear trends simultaneously. The dataset for this study was generated from waves in a prototype ship experiment and divided into in-sample and out-of-sample data. The model was trained using the in-sample data, and predictions were made on the out-of-sample data using the trained model. The forecast results of the VAR-NN model were compared with those from the pure VAR and pure NN models. Model selection was based on out-of-sample performance criteria, with the Root Mean Square Error (RMSE) employed as the prediction performance metric. According to the experimental results, the Hybrid VAR-NN model outperformed the other models, demonstrating its ability to improve the prediction performance of the pure models through its hybrid approach
Crypto Forecast: Integrating Web Scraping and Data Analysis for Cryptocurrency Price Prediction
Get PDFAccurately predicting cryptocurrency prices is still a difficult task because of the extremely volatile nature of the market. This study introduces a new methodology combining web scraping, data analysis, and machine learning to further improve prediction accuracy. A live cryptocurrency monitors gathers data from various sources such as trading volumes, price volatility, and sentiment in market to create a rich data set. Feature engineering is used to convert raw data into useful inputs for machine learning algorithms to further enhance prediction functions. Utilizing Python libraries including Beautiful Soup, Pandas, Scikit-learn, and deep learning libraries, the correct predictive model is designed and strictly tested for precision, performance, data quality, usability, scalability, and cost. The proposed hybrid model is a combination of traditional statistical methods with deep learning models to overcome the constraints of conventional forecasting methodologies. The output reflects the performance of the model in identifying the trends in the market and rendering data-driven insights to traders and investors. Future studies can employ different data sources, including social media sentiment analysis, financial news articles, and web-based cryptocurrency forums, to enhance predictability. Further advancement in time series forecasting through deep learning models, including transformer models, may also enhance the precision of long-term forecasting. A deeper insight into how external forces, including government intervention, macroeconomic trends, and emerging blockchain technologies, would complement our understanding of cryptocurrency market dynamics. This study contributes to complementing predictive analytics in financial markets by providing useful insights to investors, researchers, and policymakers.
Analysis of Emission Reduction in Indonesia's Power Generation Sector for the Centennial Milestone using Grammatical Evolution and ARIMA
Get PDFThis study examines the Indonesian government's commitment to reducing electricity production, a crucial element in achieving sustainable energy. Historically, Indonesia depends on non-renewable energy sources, including coal and oil. Indonesia is presently transitioning to cleaner energy alternatives. This policy is done to align with the objective of global sustainability. This pivotal action by the Indonesian government aims to accelerate the adoption of low-carbon technology by society. Through careful planning, Indonesia aims to establish a sustainable and resilient energy framework that addresses both current and future environmental challenges. The active participation of both the state and private sectors is crucial to support this transition. For instance, investment in research and development of sustainable technology by the private sector can accelerate the improvement or creation of a more sustainable energy framework. Innovative technologies, such as solar, hydropower, and wind, can significantly contribute to reducing carbon footprints. This study conducted an extensive observation and evaluation of the contribution of Indonesia's power generation sector to achieving net-zero emissions. This study utilizes the Autoregressive Integrated Moving Average (ARIMA) and Grammatical Evolution (GE) to predict the overall electrical capacity trajectory leading up to Indonesia's Centennial in 2045. By utilizing the exponential grammar, GE outperforms ARIMA in predicting energy forecasts. This research sheds light on Indonesia's transformative efforts, contributing to a broader understanding of how to cultivate a sustainable and environmentally responsible energy future
Enhancing Batik Classification Leveraging CNN Models and Transfer Learning
Get PDFBatik is a traditional art originating from Indonesia and recognized by UNESCO. Batik motifs vary depending on the region of origin. The diverse batik motifs reflect the rich cultural heritage and unique traditions owned by each region in Indonesia. From Sabang to Merauke, each motif features a different story and values, depicting the beauty and diversity of nature and the lives of diverse local people. However, in the context of the modern era that continues to develop, batik motifs also experience renewal and creativity that always adapts to the times. As a result, the diversity of batik motifs is increasingly abundant in Indonesia. Thus, complicating efforts to identify and categorize batik motifs appropriately. Therefore, in the context of this study, we chose to combine the MobileNetV2 model with Transfer Learning to classify batik motifs. We used a dataset consisting of 3000 batik images and categorized them into three main classes, namely Kawung batik, Mega Mendung batik, and Parang batik. This approach not only leads to the introduction and understanding of traditional batik motifs but also applies the latest technology for a more in-depth and accurate analysis. The results of this model show an extremely high level of testing accuracy, reaching 0.9946%, and training accuracy of 0.8916%, and the time required by the model to train and test the entire dataset is 18 minutes 1 second. Future research can explore the integration of other technologies or new approaches to improve accuracy and efficiency in classifying batik motifs