17 research outputs found
IMPLEMENTASI DATA MINING UNTUK PREDIKSI DROP-OUT DENGAN MENGGUNAKAN RANDOM FOREST METHOD
No full textAkreditasi adalah salah satu tolak ukur kualitas pada sebuah Perguruan Tinggi. Beberapa unsur pengukuran tersebut adalah mahasiswa dan lulusan. Pencegahan mahasiswa yang drop-out menjadi permasalahan yang dianggap sangat penting bagi Perguruan Tinggi itu sendiri. Tingginya tingkat putus sekolah akan memberikan dampak yang buruk pada Perguruan Tinggi, seperti reputasi dan akreditasi yang kurang baik. Penelitian ini menyajikan hasil analisis studi kasus data pendidikan dengan menggunakan teknik klasifikasi pada data mining yang berfokus pada deteksi drop-out mahasiswa sarjana dan diploma pada Fakultas ABC di Perguruan Tinggi XYZ. Data mentah berasal dari data akademik siswa yang mendaftar di universitas dari tahun 2008 hingga tahun 2012. Data mentah lalu dilakukan proses preprocessing untuk mengatasi permasalahan ketidakseimbangan data. Teknik synthetic minority oversampling (SMOTE) untuk menangani ketidakseimbangan dataset dan algoritma random forest untuk memprediksi drop-out dengan data latih awal sebanyak 2492 dataset. Sebagai hasil penelitian, algoritma random forest disertai dengan SMOTE dapat memberikan hasil akurasi terbaik sebesar 93,43%. Sedangkan hasil utama dari penelitian ini dapat digunakan untuk mengurangi tingkat drop-out dengan cara melakukan prediksi dini terhadap mahasiswa berpotensi tinggi untuk drop-out dan mengidentifikasi faktor-faktor potensial yang terkait dengan penyebab mahasiswa drop-out.
Kata Kunci : drop out; random forest; synthetic minority over sampling; SMOTE; data pendidikan; data mining; classification; prediction; imbalance dataset
Accreditation is one of the quality measurements for a University. Some elements of these measurements are students and graduate students. Prevention of students to drop out is a problem that is considered very important for the university itself. High levels of drop out students will have a bad impact on the university, such as bad reputation or low-grade accreditation. This research presenting the results of a case study analysis in educational data, by analyzing the data using the data mining technique. The author using the classification method, that focuses on drop-out prediction of undergraduate and diploma students at the ABC Faculty at XYZ University. To predict drop-out classification, academic data are needed. The raw data are student's academic data that enroll in university from 2008 to 2012. The raw data preprocessing then carried out to handle imbalanced data. This research uses synthetic minority oversampling technique (SMOTE) to handle imbalance dataset and random forest algorithm to predict drop-out within 2492 data. As a research result, the random forest algorithm accompanied by SMOTE can provide the best accuracy results by 93.43%. The main results of this research can be used to reduce drop-out levels by predicting potential drop out students and identifying potential factors related to drop out students.
Keywords: drop out; random forest; synthetic minority over-sampling; SMOTE; educational data; data mining; classification; prediction; imbalance datase
Analisis Kinerja Perilaku Mobile Robot Penghindar Halangan dengan Fungsi Keanggotaan Non Linear pada Kendali Logika Fuzzy Sugeno
No full textMobile robot banyak diaplikasikan pada berbagai aspek kehidupan. Navigasi robot merupakan salah satu sistem yang mampu melakukan navigasi yang terdiri dari aktivitas pergerakan seperti menghindari halangan (obstacle avoidance). Navigasi robot mencakup berbagai aktivitas yang saling terkait seperti aktuasi, persepsi dan eksplorasi. Penentuan navigasi yang baik menjadikan robot dapat melakukan eksplorasi yang bebas dari tabrakan dengan penghalang atau robot lain. Penelitian ini dikembangkan dengan menggunakan metode kendali logika Fuzzy dengan fungsi keanggotaan non linear, karena metode logika Fuzzy memiliki kemampuan untuk lebih merepresentasikan dunia nyata. Penelitian ini menghasilkan perancangan model kendali logika Fuzzy dan kemudian diterapkan pada suatu aplikasi perangkat lunak yang dapat mengendalikan robot hingga sukses menghindari halangan dengan baik dalam lingkungan virtual kompleks yang spesifik, dimana fungsi keanggotaan non linear dapat mengendalikan robot untuk menghindari halangan pada lingkungan virtual spesifik yang kompleks dengan lebih smooth dan lebih baik
The Effect of the SMOTE Method on the Classification of Toddler Nutritional Status Using the Naïve Bayes Method
No full textThe first five years of life are a golden age for growth and development, so fulfilling nutritional intake during this period is very important to avoid stunting or growth failure. The problem of stunting is still the focus of the government because it is related to nutrition which is one of the key aspects for the development of qualified resources as well as in national development. According to the report of the Ministry of Health in 2023, it was stated that the results of the 2023 Indonesian Health Survey showed that there had been a decreasing in the prevalence of stunting over the past 10 years but it had not been able to meet the target of the 2020-2024 National Medium-Term Development Plan of 14% in 2024. This study will classify the toddler’s nutritional status using the Naive Bayes method. This method uses a probability technique with Bayes' theorem which is based on the assumption of mutually independent and equal conditions. The calculation of the Naive Bayes probability in this study uses the Multinomial distribution because the data used is discrete data. The total numbers of toddlers’ nutritional status data obtained was 245 data, with 4 invalid data. Based on the data set owned, the number of samples for each class label had an unbalanced number. One method could be used to handle this unbalanced data is the random oversampling method, Synthetic Minority Oversampling (SMOTE). SMOTE will create synthetic data randomly to balance minority data samples. The analysis and testing results showed that in Multinomial Naive Bayes with the 10-cross validation technique, the g-means value obtained on the original data set was 44.98% while in the balanced data set the g-means value was 80.06%. In Multinomial Naive Bayes with the split validation technique, the g-means value obtained on the original data set was 44.20% while in the balanced data set was 80.06%. This showed that there was an increase in the g-means value of 35%. It can be stated that the SMOTE method effectively improves the overall capability of the Multinomial Naive Bayes model
Bilingualisme Dalam Masyarakat Kelurahan Lipatkain Kecamatan Kampar Kiri Kabupaten Kampar
No full textIndonesian society in general is a bilingual society and even multilingualism this is due to a multiethnic society with various ethnic groups. He said multiligualism because the Indonesian people master and use many or more than two languages. Indonesian people have a mother tongue, first language (B1) which they have acquired or acquired since they were born. Then, using Indonesian (B2) after he started entering the education level. Indonesia has a diversity of regional languages and foreign languages, namely English, which causes people to master more than one language, which are called bilingualism and multilingualism. People in the Village of Foldkain, Kampar Kiri District, Kampar Regency generally use bilingualism in their daily life. The community uses the regional language and Indonesian language. For example, people who use Sundanese and Indonesian, Banjar and Indonesian, Javanese and Indonesian, and so on. This study examines two problems, namely (1) what are the types of bilingualism in the community of Foldkain Village, Kampar Kiri District, Kampar Regency?, and (2) What are the types of bilingualism found in the community of Foldkain Village, Kampar Kiri District, Kampar Regency?. The theory that the author uses about bilingualism is Abdul Chaer (2010), Nababan, (1992), Ibrahim (2003) which is related to the type of bilingualism and the type of bilingualism. The research approach that the author uses is a qualitative approach. The research method that the author uses is descriptive method. The results of the study are (1) the type of bilingualism found in the type of bilingualism in regional languages and in Indonesian there are 441 data. Of the 441 that the researchers studied, all of them belonged to the type of bilingualism of regional languages and Indonesian and none of them belonged to the type of bilingualism of Indonesian and foreign languages, and (2) the type of bilingualism in terms of the type of multiple bilingualism contained 441 data. multiple types of bilingualism and none of them belongs to the equivalent type of bilingualism
Social Capital Factors Supporting Rezita Meylani's Victory in the 2020 Indragiri Hulu Regent General Election
No full textRezita Meylani is a Regent of Indragiri Hulu who broke the MURI record as the youngest regent in Indonesia history. Many people believe that her victory was influenced by her status as the wife of the former Regent of Indragiri Hulu for two terms, namely Yopi Arianto. Rezita is running as a candidate for Regent of Indragiri Hulu with her partner Drs.H. Junaidi Rachmat, M.Si in the 2020 Indragiri Hulu Regent General Election contestation was supported by three parties, namely Golkar, Nasdem, and Hanura. The vice-regent pair, Rezita Meylani – Junaidi Rachmat, won the Indragiri Hulu Regional Election with 50,412 votes or 26.5%, defeating the Rizal Zamzami – Yoghi Susilo pair supported by PKS and PKB with 50,232 votes or 26.4%. Therefore, the author conducted related research. Therefore, the author conducted research related to the social capital factors that supported Rezita Meylani's victory in the 2020 Indragiri Hulu Regent general election. The indicators for looking at the social capital applied in winning the regional head, especially by Rezita Meylani, are Trust. (trust), social networks, and social norms. In collecting data, this research uses qualitative methods by collecting primary data through in-depth interviews and triangulation with secondary data through literature review. Research findings show that the strong trust of the community is then mobilized effectively in political campaigns. Rezita Meylani's closeness to the community, which has been built over many years through interaction and active involvement in various social activities, has become a valuable asset in gaining voting support. This trust translates into real support on election day, where people who have benefited from Rezita Meylani's leadership so far cast their votes as a form of support and hope for the continuation of programs that have been running well.
Evaluating Netflix’s User Experience (UX) Through The Lens Of The HEART Metrics Method
No full textNetflix is one of the most popular subscription video-on-demand (SVoD) platforms, offering a wide range of authentic, high-quality content and features that allow users to select, enjoy, and share their viewing experiences on social media. Despite its popularity, Netflix often receives complaints from users, including issues with accessing the application and various features related to viewing activities. The aim of this study is to evaluate the user experience of the Netflix application and provide recommendations for improvement based on data analysis. To achieve this, the HEART Metrics are utilized, which focus on the user's perspective, and apply the Importance-Performance Analysis (IPA) method to map performance and identify improvement priorities. The research reveals several areas that require enhancement, particularly three priority variables: the Happiness variable (Hp3), indicated by the statement "I like the appearance of the Netflix application"; the Retention variable, represented by "I enjoy using the features of the Netflix application"; and the Task Success variable (Ts4), reflected in "I can save movies in the Netflix application." To improve user satisfaction, Netflix can incorporate both light and dark themes, creating a more user-friendly interface. This update could enhance navigation, increase time spent on the platform, promote recommendations, and encourage subscription renewals
Blueprint for the 21st century online learning environment in stem education through a systematic review and qualitative synthesis
No full textThis study explores the critical role of STEM education in equipping students for the challenges of the 21st century and examines the effectiveness of Online Learning Environments (OLEs) in delivering such education. The purpose of this research is to identify the essential characteristics of effective OLEs and provide a comprehensive blueprint for their development. Utilizing a systematic review and qualitative synthesis of 228 peer-reviewed articles published between 2000 and 2023, the study adopts a rigorous methodological approach following PRISMA guidelines to analyze key trends, themes, and actionable insights. Findings reveal 46 essential features of optimal OLEs, categorized into ten themes: future-proofing, brain-based approaches, diverse learning mechanisms, high-fidelity implementation, instructional design perspectives, advanced technologies, online learning objects, pedagogical approaches, psychological considerations, and usability factors. These findings emphasize the integration of innovative technologies and pedagogical strategies to create engaging, inclusive, and adaptive learning environments tailored to diverse learner needs. The study concludes with a comprehensive blueprint designed to guide educators, policymakers, and technology developers in creating OLEs that enhance engagement and learning outcomes in STEM education. Practical implications include actionable recommendations for integrating emerging technologies, fostering professional development, and addressing accessibility challenges to democratize STEM education and prepare learners for the digital economy. © 2024 by the author; licensee Learning Gate
Bilingualisme dalam Masyarakat Kelurahan Lipatkain Kecamatan Kampar Kiri Kabupaten Kampar
No full textIndonesian society in general is a bilingual society and even multilingualism this is due to a multiethnic society with various ethnic groups. He said multiligualism because the Indonesian people master and use many or more than two languages. People in the Village of Lipatkain, Kampar Kiri District, Kampar Regency generally use bilingualism in their daily lives. The community uses the regional language and Indonesian language. This study examines two problems, namely (1) what are the types of bilingualism in the community of Lipatkain Village, Kampar Kiri District, Kampar Regency?, and (2) What are the types of bilingualism found in the community of Lipatkain Village, Kampar Kiri District, Kampar Regency?. The research approach that the author uses is a qualitative approach. The research method that the author uses is descriptive method. Based on the results of this study, there are (1) types of bilingualism found in the Village of Lipatkain, Kampar Kiri District, Kampar Regency, namely the types of bilingualism in regional languages and Indonesian while the types of Indonesian and foreign languages bilingualism are not found and, (2) the types of bilingualism found in the Village of Lipatkain. Kampar Kiri District, Kampar Regency, which is the type of multiple bilingualism, while the equivalent type of bilingualism is not foun
How Entrepreneurial Teams\u27 Heterogeneity and Learning Experiences Affect Business Performance through Self-Efficacy
No full textThis study aims to ascertain how entrepreneurial learning experiences and entrepreneurial team heterogeneity affect self-efficacy and, consequently, company performance. Members of the Jakpreneur community from the East and North Jakarta metropolitan areas made up the study\u27s demographic. Accidental sampling was the method employed, with 237 respondents who volunteered to complete the author\u27s questionnaire. Using SmartPLS software, a structural equation model is used for data analysis. The findings of the study demonstrate a direct relationship between self-efficacy and company performance entrepreneurial learning experiences and entrepreneurial team heterogeneity. Subsequently, self-efficacy can serve as a moderator to demonstrate the indirect impact of entrepreneurial team heterogeneity and entrepreneurial learning experience on business performance. Learning experiences and diversity in the team both boost self-confidence, which in turn creates a positive feedback loop between motivation and company performance
