Diabetic or silent killer diseases are an alarming scourge for the world and are classed as serious diseases. In Indonesia, the increase in diabetics occurred by 2% in vulnerable times between 2013 to 2018. This affects all sectors, both medical services and the financial sector. The Neural Network method as a data mining algorithm is present to overcome the burden that arises as an early detection analysis of the onset of disease. However, Neural Network has slow training capabilities and can identify important attributes in the data resulting in a decrease in performance. Pearson correlation is good at handling data with mixed-type attributes and is good at measuring information between attributes and attributes with labels. With this, the purpose of this study will be to use the Pearson correlation method as a selection of features to improve neural network performance in diabetes detection and measure the extent of accuracy obtained from the method. The dataset used is diabetes data 130-US hospital UCI with a record number of 101767 and the number of attributes as many as 50 attributes. The results of this study found that Pearson correlation can improve neural network accuracy performance from 94.93% to 96.00%. As for the evaluation results on the AUC value increased from 0.8077 to 0.8246. Thus Pearson's Correlation algorithm can work well for feature selection on neural network methods and can provide solutions to improved diabetes detection accuracy.

Batik tulis adalah hasil seni budaya yang memiliki keindahan visual dan mengandung makna filosofis pada setiap motifnya. Batik tulis memiliki morif yang sangat beragam dan memiliki tingkat kompleksitas yang tingi sehingga menjadi kesulitan tersendiri dalam pengelompokan kelas batik tertentu. Klasifikasi citra ke dalam kelas tertentu juga menjadi permasalahan yang pelik dalam bidang pengenalan pola. Metode machine learning dapat digunakan untuk mengenali kelas batik melalui pengenalan citra batik. Namun belum banyak penelitian terkait studi komparasi klasifikasi citra batik. Sehingga penelitian ini berfokus pada data set citra batik tulis yang menggunakan dua motif yaitu motif klasik dan motif kontemporer. Pada penelitian ini, fitur ekstraksi menjadi dasar klasifikasi dengan metode Backpropagation Neural Network dan k-Nearest Neighbor. Tujuan dari penelitian ini untuk menemukan pola baru dalam data dengan menghubungkan pola data yang sudah ada dengan data yang baru. Selanjutnya, penelitian ini melakukan perbandingan metode klasifikasi antara Backpropagation Neural Network dan k-Nearest Neighbor untuk mencari metode klasifikasi terbaik untuk klasifikasi Batik tulis Bakaran. Hasil dari studi komparasi menunjukkan bahwa metode Backpropagation Neural Network memperoleh nilai akurasi 90,11% sedangkan metode k-Nearest Neighbor mendapatkan nilai akurasi 96,00%. Sehingga dapat di simpulkan bahwa metode k-Nearest Neighbor merupakan metode terbaik untuk klasifikasi citra batik.

Preterm labor is a delivery outside the baby's birth period that causes death for the baby as well as complications to the baby's mother. It is also a burden on medical personnel with an increasing trend of as much as 8%. Data mining classification is present as a problem solver for the early prevention of premature memorization. By utilizing the C4.5 classification algorithm and the naïve bayes algorithm which are considered good in performance. To choose the best algorithm in the classification of preterm labor it must be well measured its performance. From the results of comparing the naïve bayes algorithm with the C4.5 algorithm, an accuracy of 98.75% was obtained with an AUC of 0.5. Meanwhile, the achievement of the naïve bayes algorithm was 81.88% and the AUC was 0.945. Therefore, from the results of the comparison of the accuracy values of the two algorithms, it is concluded that the C4.5 algorithm is able to be superior in handling premature memorization data compared to the naïve bayes algortima

This study aims to describe the impact of students’ habits of playing online games on social care in grade 5 at SD Negeri Nglames 01, Madiun Regency. This research uses a qualitative approach with a type of case study. Sources of data used in this study are primary data sources and secondary data sources, while the data collection techniques are observation, interviews and documentation. The validation used to test the truth is the triangulation of research sources. Data analysis used the interactive model of Miles and Huberman. From the research that has been done, it shows that as many as 83% of students play online games with a play duration of more than 5 hours in one day, 17% of other students play online games with a playing duration of 4 to 5 hours in one day. The habits of students playing online games are influenced by friends, family activities and concerns, the environment they live in. Another negative impact due to the habit of playing online games affects sleep quality, diet, and some children imitate the style of play played and practiced with their peers in real life. The positive impact due to the habit of playing online games is to increase the vocabulary of foreign languages, namely English. The negative impact is more dominant due to the habit of playing online games.

Premature labor is a condition of the birth of a baby less than 37 weeks with a fetal weight of less than 2500 grams. Where the rate of premature infant delivery leading to death increased from 2000 to 2014 by 8.5%. Classification for early handling of premature labor is one of the solutions that is often studied. Some of the classification algorithms that are often used are C4.5 and Random Forest. From the two algorithms, the best algorithm will be selected by looking at the highest level of accuracy to be selected. From the calculation results of the Random Forest algorithm, an accuracy of 99.38% was obtained with an AUC of 0.988. Meanwhile, the achievement of the C4.5 algorithm is 98.75% with an AUC of 0.5. Therefore, from the results that can be compared with the accuracy values of the two algorithms, it is concluded that the Random Forest algorithm is better accurate to overcome premature data when compared to the C4.5 algorithm