JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
A Design and Application of Software Liberal Arts Course based on CT-CPS Model for Developing Creative Problem-Solving Ability and Learning Motivation of Non-software Majors
Get PDFAs the importance of computing education for nurturing computational thinking skills is emphasized in preparation for the era of the 4th industrial revolution, computing education for non-majors is also expanding in liberal arts education at universities. In this study, a software liberal arts course based on the CT-CPS model was designed and applied to non-software majored university students, and the effect on creative problem-solving ability and learning motivation were analyzed. The CT-CPS (computational thinking-based creative problem solving) model is an instructional model devised by fusing each element of computational thinking ability to the creative problem-solving stages. Creative problem-solving ability test paper and learning motivation test paper were used as test tools. Moreover, quantitative analysis through independent sample t-test and paired sample t-test and qualitative analysis through subjective responses were conducted. As a result of the study, it was verified that the software class applied with the CT-CPS model had a statistically significant effect on the creative problem-solving ability and learning motivation of non-software majors. In particular, compared to the control group, the experimental group showed significant changes in the motivational elements among the sub-factors of creative problem-solving ability and the self-efficacy factor among the sub-factors of learning motivation. In addition, it was confirmed through qualitative analysis that the software class to which the CT-CPS model was applied helped develop the problem-solving ability and learning motivation based on computational thinking through the process of discovering and solving problems on their own in real life
Simultaneous Hydroponic Nutrient Control Automation System Based on Internet of Things
Get PDFHydroponic is one of the solutions of gardening methods using water as a nutrition medium. Usually, maintaining hydroponic plant quality and water nutrients are done manually and require human efforts, such as the degree of acidity or wetness (pH), TDS (Total Dissolved Solids), and nutrient temperature. With the Internet of Things technology, we can automate hydroponic control by measuring the nutrients' TDS, pH, and temperature values and controlling water nutrition by pump nutrition needs for hydroponic plants. This research uses the NFT (Nutrient Film Technique) for the hydroponic system and uses lettuce as the nutrition parameter. The lettuce parameters are pH, TDS, and Water Temperature equal to the sensor we used in the proposed IoT system. The condition has 27 classifications, and we use this classification as a reference in decision-making, using the K-Nearest Neighbor (KNN) algorithm to activate the actuator. We improve the simultaneous actuator from previous research with specified intervals and duration to achieve ideal nutritional conditions. The other improvement is that we collect more data and more testing times. The accuracy was 91.2%, with k = 3. From the evaluation results, the accuracy of KNN is quite high and has an advantage, which has better accuracy than the other algorithms and can activate actuator simultaneously. We conclude that the hydroponic nutrient automation system using the Internet of Things method is ready for real planting use with this improvement
The Utilization of Augmented Reality Technology for the Development of Tourism Information Media
Get PDFThe industrial revolution 4.0 has brought tourism trends using enriched interactive technology services. Technology in the world of tourism has helped the expansion of the industry through the promotion and mediation of independent tourists to carry out all services and transactions easily, including obtaining tourist information. This study aims to develop promotion media for geography education tourism in Soppeng Regency and test the effectiveness of the media. This study adopted the Alessi & Trollip learning multimedia development model. The developed media was tested on 20 respondents with 10-item usability scale statements and 5 response options ranging from agreeing to strongly disagree. The level of effectiveness of the media developed after being tested using the usability scale (SUS) system is included in the Good category (good) with an average score of 76.5. This level of effectiveness is included in the acceptable to users or acceptable category, with a grade scale of C and an adjective rating in the Good or good category. The results of this study also indicate that users are satisfied with the developed media but are not enthusiastic so that users can switch to other, more interesting media at any time. In the end, based on the final score obtained, it was concluded that the promotion media for geography education tourism in Soppeng Regency (battle city application) was effective and acceptable to users.Â
Predicting Dengue Outbreak based on Meteorological Data Using Artificial Neural Network and Decision Tree Models
Get PDFDengue fever is well-known as a potentially fatal disease, and the number of cases in some areas remains uncontrolled. Despite efforts to prevent the dengue outbreak from spreading further, vectors may be to blame. Identifying what weather characteristics contribute to dengue outbreaks is important to predict the dengue outbreak. This study proposes Artificial Neural Network (ANN) and Decision Tree (DT) models based on maximum temperature, minimum temperature, total rainfall, and average humidity to predict the dengue outbreak in Kota Bharu. Different numbers of hidden nodes were used in ANN to optimize the model. Both models, ANN and DT are evaluated based on accuracy, sensitivity and specificity showing that ANN (Accuracy = 68.85%, Sensitivity = 99.71%, Specificity = 1.27%), performed better than DT (Accuracy = 67.46%, Sensitivity = 98.82%, Specificity = 2.53%). This means that ANN outperforms DT when predicting a dengue outbreak in Kota Bharu. Based on the ANN model, it can be concluded that the number of hidden nodes affects the model's accuracy. Selecting the ideal number of hidden nodes for modeling the ANN model is appropriate. Even though ANN accuracy for prediction models is greater than DT, it is still low. It can be inferred that selecting a prediction model appropriate for a variety of dataset types and levels of complexity is important. Based on these models, the government may take pre-emptive actions to enhance public awareness about climate change
Developing Fire Evacuation Simulation Through Emotion-based BDI Methodology
Get PDFFire evacuation simulation is a tool to study human behavior in dealing with fire. It has been used for safety policy management studies, building safety analysis, and human safety understanding. To date, modeling the fire evacuation behavior is paying much attention in which works have been done to design and develop building model, fire model, human decision model, and human emotion decision model. As fire evacuation simulation is important, the BDI methodology is introduced by authors to ease modeling and simulation of human behavior in a fire evacuation. Continue the success of capturing and modeling the human behavior in a fire evacuation. This paper presents the influence of human emotion in fire evacuation simulation. In this paper, the emotion-based BDI methodology is presented with a walkthrough example of how emotion can influence the human decision in a fire spreading scenario. The OCEAN model of personality is used to handle the emotional properties in the methodology. Different people have different types of personalities, which can affect both decision-making and emotion in different situations. A fire evacuation simulation is developed by using the Unity3D game engine. The simulation is created based on the emotion-based BDI methodology presented. Hence, the emotion-based BDI methodology can be used to model human behavior and emotional states in a fire evacuation. Overall, the paper introduces a new insight into how to model human behavior in fire evacuation decision-making systematically
Avoiding Overfitting dan Overlapping in Handling Class Imbalanced Using Hybrid Approach with Smoothed Bootstrap Resampling and Feature Selection
Get PDFThe dataset tends to have the possibility to experience imbalance as indicated by the presence of a class with a much larger number (majority) compared to other classes(minority). This condition results in the possibility of failing to obtain a minority class even though the accuracy obtained is high. In handling class imbalance, the problems of diversity and classifier performance must be considered. Hence, the Hybrid Approach method that combines the sampling method and classifier ensembles presents satisfactory results. The Hybrid Approach generally uses the oversampling method, which is prone to overfitting problems. The overfitting condition is indicated by high accuracy in the training data, but the testing data can show differences in accuracy. Therefore, in this study, Smoothed Bootstrap Resampling is the oversampling method used in the Hybrid Approach, which can prevent overfitting. However, it is not only the class imbalance that contributes to the decline in classifier performance. There are also overlapping issues that need to be considered. The approach that can be used to overcome overlapping is Feature Selection. Feature selection can reduce overlap by minimizing the overlap degree. This research combined the application of Feature Selection with Hybrid Approach Redefinition, which modifies the use of Smoothed Bootstrap Resampling in handling class imbalance in medical datasets. The preprocessing stage in the proposed method was carried out using Smoothed Bootstrap Resampling and Feature Selection. The Feature Selection method used is Feature Assessment by Sliding Thresholds (FAST). While the processing is done using Random Under Sampling and SMOTE. The overlapping measurement parameters use Augmented R-Value, and Classifier Performance uses the Balanced Error Rate, Precision, Recall, and F-Value parameters. The Balanced Error Rate states the combined error of the majority and minority classes in the 10-Fold Validation test, allowing each subset to become training data. The results showed that the proposed method provides better performance when compared to the comparison metho
Application of ARIMA Kalman Filter with Multi-Sensor Data Fusion Fuzzy Logic to Improve Indoor Air Quality Index Estimation
Get PDFAir quality monitoring is a process that determines the number of pollutants in the air, one of which is indoor air quality. The Fuzzy Indoor Air Quality Index was developed in this research. It is a method for determining the indoor air quality index using sensor fusion and fuzzy logic. By combining several different time series determinants of air quality, a fuzzy logic-based sensor fusion method is used to build a knowledge base about indoor air quality levels. Without the use of complicated calculation models, fuzzy logic-based fusion will make it easier to determine indoor air quality levels based on various sensor parameters. The input for fuzzy-based data fusion is obtained from the ARIMA method with Kalman Filter's air quality parameter values estimation. The application of ARIMA with a Kalman Filter was used to improve the accuracy of indoor air quality estimation in this study. ARIMA(3,1,3) had a MAPE of 0.1 percent on the CO2 dataset, and ARIMA(1,0,1) had a MAPE of 0.63 percent on the TVOC dataset based on approximately three experimental days. ARIMA (3,1,3) estimation with a Kalman Filter results in a MAPE of 0.03 percent for the CO2 dataset and a MAPE of 0.24 percent for ARIMA(1,0,1) Kalman Filter estimation on TVOC dataset. As a result, the Fuzzy Indoor Air Quality Index (FIAQI) developed in this research reasonably estimates indoor air quality. This can be seen by examining the percentage of estimation errors obtained from the experiment
Investigation of RGB to HSI Conversion Methods for Early Plant Disease Detection Using Hierarchical Synthesis Convolutional Neural Networks
Get PDFAn early detection of disease can save the plant. One of the ways is by using eye-observation, which is time-consuming. Having a machine learning technology that can automate early detection would benefit modern and conventional farming. This study emphasizes the review of Hyperspectral Image (HSI) reconstruction using the Hierarchical Synthesis Convolutional Neural Networks (HSCNN) based method in early plant disease detection. Capturing hundreds of spectral bands during image acquisition enables the HSI capturing devices to provide more detailed information. Detection of disease with Red Green Blue (RGB) images needs to be done when it shows a notable spot or sign. However, the disease can be spotted with the correct range of spectral bands on HSI before a notable spot or sign is shown. The usage of HSI image is significantly important as it is rich in information and properties needed for image detection. Although HSI device is significantly important in early plant disease detection, the devices are expensive and require specialized hardware and expertise. Thus, reconstructing the Reg Green Blue (RGB) image to HSI is required. This research implemented two types of HSCNN-based methods, Densed network (HSCNN-D) and Rectified Linear Unit network (HSCNN-R), for HSI reconstructions. The results show that HSCNN-D outperformed the HSCNN-R with less Mean Relative Absolute Error (MRAE) of 2.15%
Comparison of Apache SparkSQL and Oracle Performance: Case Study of Data Cleansing Process
Get PDFA dataset with good quality is a valuable asset for a company. The data can be processed into information to help companies improve decision-making. However, the data increased more and more over time to decrease data quality. Thus, good data management is important to keep data quality meeting company standards. One of the efforts that can be done is conducting data cleansing to clean data from errors, inaccuracies, duplication, format discrepancies, etc. Apache Spark is an engine that can analyze large amounts of data. Oracle Database is a database management system used to manage databases. Both have their own reliability and can be used to analyze SQL-shaped data. This study compared Spark and Oracle performance based on query processing time. Both were tested on queries used to perform data cleansing of millions of rows of the dataset. The research focuses on finding out Spark and Oracle's performance through quantitative analysis. The results of this study showed that there were differences in query processing times on both tools. Apache Spark is rated better because it has a relatively faster query processing time than Oracle Database. It can be concluded that Oracle is more reliable in storing complex data models than in analyzing large data. For future research, it is suggested to add other comparison aspects such as memory and CPU usage. The researchers can also consider using query optimization techniques to enrich query experiments
Development of Automatic Real Time Inventory Monitoring System using RFID Technology in Warehouse
Get PDFRFID technology is one of the technologies in logistics as an important application in logistics operations and supply chain management. The application of RFID technology can be applied to the inventory control monitoring system in real-time. The inventory monitoring information system can replace the manual system with a computerized system so that the processing of monitoring data is more efficient, effective, and can be controlled directly and accurately. This study presents a case study of a real stock monitoring system based on RFID technology. The design of a real-time stock monitoring system is transitioning from manual to technology by involving computerization in its implementation. This study aims to design an RFID-based real-time stock monitoring system and integrate warehousing systems in the company. The real-time inventory stock monitoring system is still developing, so a simulation is carried out to compare the existing data with the data from the RFID system. We used the existing warehouse layout to try the efficiency of the RFID stock monitoring. Based on the research results, the RFID system increases the efficiency and effectiveness of inventory control. In further research, it is necessary to integrate the inventory optimization model with real-time inventory control with RFID. The integration of real-time monitoring technology can be used as input to the inventory optimization model to be more accurate in providing purchasing policies