6 research outputs found
Utilization of Information Technology-Based Learning Media to Support Active Learning Activities at State High School 2 Husni Thamrin
Get PDFIn general, high school students view mathematics as a difficult and boring subject. In addition to students, teachers also have difficulty in conveying material for the introduction of majors for lectures. The lack of student interest in learning mathematics is a problem for every high school teacher. This happens if the teacher's ability to use conventional learning methods such as from textbooks and explanations from the teacher only. Therefore, it is necessary to strive in the process of learning mathematics to be more interesting, more interactive and fun. This issue also applies to science materials that require understanding. For this reason, teaching aids are needed that are used to stimulate students' responsiveness in studying material according to their scientific competence. This service aims to apply knowledge and technology by conducting training in making and tutorials on mathematics learning media so that it can increase understanding and attract students' interest in learning and help improve the quality of teacher education and teaching at Husni Thamrin High School
Facial Recognition on System Prototype to Verify Users using Eigenface, Viola-Jones and Haar
Get PDFFacial recognition is one of the most popular way to authenticate user into a system. This method is preferable considering the tendency of users for using the same password across multiple sites which made the user has already made his own account securities in vulnerable states. Using biometrics might supply solutions to solve this problem and facial recognition is one of the best biometric methods can be apply as a digital account security solution. This study to design a prototype system implementing facial recognition to verify users to measure how accurate these methods are. The method used here is Viola-Jones for face detection, Eigenface and Haar feature for face recognition from the OpenCV. The system was designed in Java. Based on the test results from the system designed, system can recognize user face with 100% accuracy if faces are shot in a well desirable condition. The system is able to recognize the user's face with various expressions including with or without glasses. However, the system has difficulty in recognizing user’s face in facing up, down, sideways position or blocked by accessories or body parts such as hands. After some experiment, it was proven that the system designed is accurate, reliable and safe enough to be implemented to digital authorization process
Web-Based Student Score Application Design at Husni Thamrin Private Junior High School, Medan
Get PDFValue data processing is one of the most important parts of school operations and activities. Husni Thamrin Medan Private Middle School, one of the schools that organizes an educational process based on the 2013 Curriculum, manages value data through manual and separate input by each teacher. It is hoped that through the development of a web application-based value management system, value data processing can be carried out more easily and integratedly. To implement the use of this application, training is needed for teachers so they can get to know the features and how to use the application
Sistem Rekomendasi Podcast menggunakan Metode N-Gram dan Term Frequency
Get PDFOne of the main forms of information and entertainment presentation is in the form of on-demand audio content or often referred as podcast. The problem met is the difficulty of users to find podcasts that match their preferences among hundreds of thousands of podcasts that are now available on the internet. Besides the number of podcasts, the incompletion of podcasts metadata is one of the problems in developing a recommendation system in general.This system is designed by utilizing N-Gram and Term Frequency to generate queries from the title and description of a podcast which will then be used to find other podcasts that are similar by utilizing Cosine Similarity calculations. The testing phase is done through by testing the system using nDCG calculations to determine the relevance level of the recommendation results. From the results, the average value of the relevance level of podcast recommendations is 53.8% and the best average f1-score of the 10 best categories is 14%
Dekomposisi dan Rekombinasi Pengacakan Citra Digital dengan Logistic Mapping
Get PDFBeberapa citra digital membutuhkan privasi dan kerahasiaan, seperti citra medis, citra diagnosa medis jarak jauh, citra rahasia melalui komunikasi internet, atau citra rahasia kemiliteran. Salah satu cara untuk mengamankan informasi di dalam citra digital adalah dengan melakukan pengacakan (scrambling).Penelitian ini mengacak nilai piksel citra digital dengan mengubah nilai piksel dari sistem bilangan desimal menjadi bilangan basis empat (kuartener), kemudian mengurai (dekomposisi) keempat bit kuartener dan melakukan pengacakan terhadap keempat posisi bit berdasarkan pada bilangan acak yang dihasilkan oleh algoritma logistic mapping, kemudian bit hasil pengacakan digabungkan kembali (rekombinasi) untuk menghasilkan nilai piksel baru. Logistic mapping merupakan penghasil bilangan acak yang mampu menghasilkan deretan bilangan yang acak berdasarkan nilai kunci ?µ (3.569945 < µ < 4) dan nilai awal x0 (0 < x0 < 1).Hasil penelitian ini dapat melakukan pengacakan terhadap citra digital dengan dekomposisi dan rekombinasi nilai piksel berdasarkan pada nilai acak yang dihasilkan oleh algoritma logistic mapping. Hasil pengujian menunjukkan bahwa pasangan kunci-1 (?µ1, x1) memiliki sensitivitas paling tinggi dalam mengacak citra, kemudian diikuti oleh pasangan kunci-2 (?µ2, x2), pasangan kunci-3 (?µ3, x3) dan pasangan kunci-4 (?µ4, x4)
Prediksi Kanker Payudara Melalui Penerapan Algoritma C4.5
Get PDF[id] Kanker merupakan salah satu penyebab kematian baik di negara maju maupun di negara yang sedang berkembang. Kanker payudara merupakan kanker yang berasal dari sel-sel yang terdapat di payudara, bisa dari sel-sel saluran air susu atau sel-sel kelenjar penghasil air susu atau jaringan lain. Penyakit ini juga menjadi penyebab kematian utama karena kanker di Indonesia pada tahun 2012. Oleh sebab itu sangat penting untuk dilakukan deteksi dini terhadap penyakit kanker payudara agar dapat segera dilakukan pengobatan. Pada praktiknya, di dunia kedokteran seringkali data rekam medis seperti penyakit kanker payudara disimpan untuk berbagai tujuan. Namun kenyataannya, proses penyimpanan dan pengolahan data rekam medis di beberapa rumah sakit masih belum memanfaatkan media komputer sehingga data sering hilang ataupun rusak. Selain itu, data rekam medis yang tercatat dan terkumpul biasanya diolah dan dimanfaatkan menjadi sebuah pengetahuan untuk melakukan prediksi. Oleh karena permasalahan tersebut, maka perlu dibangun sebuah sistem informasi dengan penerapan Data Mining dalam dunia kesehatan khususnya pengelolaan data rekam medis. Tujuan penelitian menggunakan penerapan algoritma prediksi C4.5 adalah dapat menghasilkan pohon keputusan yang memiliki tingkat akurasi yang dapat diterima dan efisien dalam menangani atribut yang bertipe diskret atau numerik. Hasil penelitian menunjukkan bahwa penerapan algoritma Data Mining Decision Tree C4.5 digunakan untuk melakukan prediksi penyakit kanker payudara menggunakan data training rekam medis sebanyak 116 data dapat menghasilkan rule sebanyak 4 rule. Tingkat keakuratan dari algoritma Data Mining Decision Tree C4.5 cukup akurat karena dari 10 percobaan terdapat 9 percobaan yang mendapatkan hasil prediksi yang tepat sesuai rule yang ada.[en] Cancer is one of the causes of death in both developed and developing countries. Breast cancer is cancer that originates from cells in the breast, either from milk duct cells, milk-producing gland cells, or other tissues. This disease was also the main cause of cancer deaths in Indonesia in 2012. Therefore, it is very important to detect breast cancer early so that treatment can be carried out immediately. In practice, in the medical world, medical record data such as breast cancer is often stored for various purposes. However, the process of storing and processing medical record data in several hospitals still does not utilize computer media so that data is often lost or damaged. In addition, medical record data that is recorded and collected is usually processed and used as knowledge to make predictions. Because of these problems, it is necessary to build an information system with the application of Data Mining in the world of health, especially managing medical record data. The aim of research using the C4.5 prediction algorithm is to produce a decision tree that has an acceptable level of accuracy and is efficient in handling discrete or numerical attributes. The research results show that the application of the Data Mining Decision Tree C4.5 algorithm which is used to predict breast cancer using 116 medical record training data can produce 4 rules. The accuracy level of the Data Mining Decision Tree C4.5 algorithm is quite accurate because out of 10 experiments there were 9 experiments that obtained correct prediction results according to existing rules
