Student in one of the stakeholder in a university. Therefore, student’s perception in the quality of learning facilities and infrastructures become important to ensure the university’s performance. The Faculty of Engineering of University of Palangka Raya has not comprehensively evaluated the students’ satisfactory of the learning’s facilities. In this research, methods from data mining approach was implemented to classify whether the students satisfy or not with the quality of the learning’s facility in Engineering Faculty. This research compared three data mining algorithm, Decision Tree C4.5, Support Vector Machine, and Naïve Bayes to obtain the best algorithm for the prediction system. 948 responses were collected, 61% of the respondent were satisfied with the quality of the learning facilities and infrastructures, while 39% of the respondents were dissatisfied. The Decision Tree c4.5 had the best performance with accuracy of 88% and precision of 98% compared to the Naïve Bayes and support vector machine.
Weather phenomenon and erratic rainfall are some of the symptoms of global climate change. These challenges attempt to increase rice production in tidal swamps or submerge land in the long term. An effort to form tolerant rice varieties to stress in tidal swampland has been carried out through crossing between superior varieties and local rice. This study aims to analyze the results of several promising rice lines and search for the potential rice lines to be released as new tidal swampland varieties. The experiment was carried out in tidal swamp rice area centers, in Karang Agung, South Sumatra, Balandean, South Kalimantan and in Indramayu, West Java Indonesia. Fourteen rice lines and four check varieties namely IR42, IR64, Inpara 8 and Inpara 9 were used. Field experiments used a Randomized Complete Block Design (RCBD) with four replications. Results showed that the environment, genotype, and interaction between environmental genotypes had a significant influence on all characters. The appearances of the lines were superior in Karang Agung and less well on Balandean. The yield was positively correlated with plant height, the number of productive tillers and filled grains per panicle. There were five lines with a high yield equivalent to the best check varieties, namely Inpara 9, IR 102860-8: 66-BB, IR 102860-8: 42-BB, IR 101465-8: 23, IR 101465-5: 25, and B13522E-KA-5-B.
Forest fire detection system is one of important tools in preventing and mitigating forest and land fires. In Indonesia, the detection of forest and land fires relies on hotspot information captured from satellites. However, the location obtained by the satellite has a horizontal error of 2 km from the ground check data. Therefore, these information are less relevant to the actual location. In this research, an android app is proposed to extract Exchangeable Image Format (EXIF) photo metadata. The metadata has image information such as latitude and longitude, to obtain the location of forest fires reported by the application user. In addition, this research implemented one of the image processing methods to classify fire and smoke in images of fires. Color filtering method is used based on the color space of Red Green Blue (RGB), Hue Saturation Value (HSV) and YCbCr. This classification process aims to ease the burden on the admin in confirming user reports. The results of the fire and smoke classification process are described using a confusion matrix. This matrix produces an accuracy rate of 75%, a precision of 80% and a recall of 80% for a fire classification and an accuracy of 70%, a precision of 92% and a recall of 87% for smoke classification. There are 25% and 30% of misclassified data of fire and smoke. This is because the color filtering method classifies each color pixel from the image, therefore many pixels that are not classified as fire or smoke images are classified because there are other objects that have a range of colors to classify fire and smoke
Twitter is one of the popular social media platforms in Indonesia. This platform has been used as a media communication and public engagement tool for many purposes, especially in political and governance domains. During the process of 2019 Indonesian Presidential Election, many people use Twitter to express their opinion/sentiment towards the election process. In this paper, we investigate the nature of people’s opinion towards the Indonesian Presidential Election after the 1st debate. The goal of this study is to perform exploratory sentiment based analysis of Twitter data, and that was gathered after the 1st debate. We used lexicon sentiment analysis to calculate the sentiment of political tweets collected after the 1st debate. The identification of positive and negative opinion was automatically conducted using the available dictionary. Our result shows that sentiment of the netizen towards the 1st Presidential debate was mostly negative. In addition to this result, a predictive model was generated using CART and logistic regression to predict the netizens’ sentiment. This experiment shows that the accuracy of the prediction model reaches 90%. Therefore, our study suggests that Twitter data can be used to analyse citizens’ sentiment toward the Indonesian Presidential Debate and can generate a model to predict citizens’ future sentiment toward the next debate.
Department of Informatics Engineering, University of Palangka Raya (UPR) has implemented the KKNI curriculum since 2020. As the output of KKNI Curriculum, student will receive a Surat Keterangan Pendamping Ijazah (SKPI) after they graduated. Currently, there is no system to processes the SKPI in the Department of Informatics UPR. Therefore in this article a design of a system that can handle or help record and print student achievements as stated in the SKPI is introduced. In this article waterfall methodology is used to develop the system. The stages are the analysis, design, coding, testing and maintenance stages. The result of this research is a SKPI information system that can process and print a description of student achievement. In addition, it can also print student activities such as organizational data, competitions, seminars, training, and student courses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.