Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : International Journal Of Computer, Network Security and Information System (IJCONSIST)

An Introduction to Machine Learning Games and Its Application for Kids in Fun Project Fahrudin, Tresna Maulana
IJCONSIST JOURNALS Vol 2 No 1 (2020): September
Publisher : International Journal of Computer, Network Security and Information System

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (590.691 KB) | DOI: 10.33005/ijconsist.v2i1.34

Abstract

Industrial Revolution 4.0 is the right time to democratize artificial intelligence in the world. It can be started from education, the target is the level of elementary, middle and high school. But the general curriculum still around in natural science, social science and language science. The challenge is how to introduce artificial intelligence earlier to the student and how to combine its material with the curriculum. “Machine Learning for Kids” is a web-based application which kids can explore artificial intelligence, especially in machine learning field with a fun project. The application provided to create a new project like animal classification. Kids can add a new label, such as mammal, insect, amphibian, bird, fish and etc. They have to add the animal name as an example of training data into each label. After kids added the training data, they can create the machine learning model. The experiment showed the confidence of the machine learning model test with a member of example reached 100%, the label prediction of all example was accurate. While the confidence of machine learning model test with another member of example reached between 14-17%, the label prediction of all example was also accurate. We recommended “Machine Learning for Kids” is one of the best web-based application for kids to explorer machine learning easily.
Classification of Toddler Nutritional Status Based on Antrophometric Index and Feature Discrimination using Support Vector Machine Hyperparameter Tuning Much. afif masykur mughni; Fahrudin, Tresna Maulana; Kamisutara, Made
IJCONSIST JOURNALS Vol 2 No 02 (2021): March
Publisher : International Journal of Computer, Network Security and Information System

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (537.328 KB) | DOI: 10.33005/ijconsist.v2i02.45

Abstract

Nutritional status is the study of food and is related to health. Nutritional status is a benchmark to assess the health development of toddler. The nutritional status of toddler is assessed according to three index, such as body weight to age (BW / A), body height to age (BH / A), body weight to body height (BW / BH). The issue of nutrition is still a major factor in the growth and development of toddler in Indonesia. Public Health Center (Puskesmas) and Integrated Healthcare Center (Posyandu) as public health services work together to control the growth and development of toddler in Indonesia. To help control the growth and development of toddler, we proposed a research to classify the nutritional status of toddler based on anthropometric index. The nutritional status of toddler dataset was formed into a classification model using SVM Hyperparameter Tuning. SVM is a machine learning which the classification model used a hypothesis space in the form of linear functions in a high dimensional feature space. Adjustment of the hyperparameter was involved to reach a model that can optimally solve machine learning problems. We implemented feature selection using Fisher's Discriminant Ratio as a preprocessing stage, which the most important features were body weight (BB) and height (BH). The experimental results showed the classification model using SVM on training and testing data with a ratio of 70:30 reached accuracy of 84%, while SVM Hyperparameter Tuning with parameter of Cost = 100 parameters, Gamma = 0.01, Kernel = RBF reached accuracy of 97%. They represented a significant accuracy difference of 13%.
Exploratory Data Analysis and Machine Learning Algorithms to Classifying Stroke Disease Riyantoko, Prismahardi Aji; Fahrudin, Tresna Maulana; Hindrayani, Kartika Maulida; Idhom, Mohammad
IJCONSIST JOURNALS Vol 2 No 02 (2021): March
Publisher : International Journal of Computer, Network Security and Information System

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (517.79 KB) | DOI: 10.33005/ijconsist.v2i02.49

Abstract

This paper presents data stroke disease that combine exploratory data analysis and machine learning algorithms. Using exploratory data analysis we can found the patterns, anomaly, give assumptions using statistical and graphical method. Otherwise, machine learning algorithm can classify the dataset using model, and we can compare many model. EDA have showed the result if the age of patient was attacked stroke disease between 25 into 62 years old. Machine learning algorithm have showed the highest are Logistic Regression and Stochastic Gradient Descent around 94,61%. Overall, the model of machine learning can provide the best performed and accuracy.