No abstract

Klasifikasi kebutuhan daya listrik untuk masing-masing daerah sangat diperlukan agar dapat menggambarkan kondisi daya yang dibutuhkan. Hal ini sangat penting untuk pelanggan baru yang ingin mengetahui daya yang diberikan, sebaliknya pelanggan lama juga dapat melihat dan  menurunkan daya atau menambah daya sesuai dengan kebutuhan. Adapun variable yang di gunakan pada penelitian ini adalah luas rumah, besaran daya listrik yang akan digunakan dan telah digunakan, pendapatan gabungan orang tua (kotor) / bulan, jumlah daya lampu yang ada dirumah, kemudian dilanjutkan dengan klasifikasi perkiraan daya listrik yang berikan. Klasifikasi yang digunakan adalah penentuan golongan Tarif/Daya  R-1/450 VA subsidi, R-1/900 VA subsidi, R-1/900 VA-RTM (Rumah Tangga mampu) non subsidi, R-1/1300 VA non subsidi, dan Tarif/Daya  R-1/2200 VA non subsidi. Selanjutnya untuk pengujian menggunakan data training sampel sebanyak 20 data sampel dari masing-masing pelanggan yang akan dilihat pengujiannya dengan tetangga yang paling dekat. Untuk sampel daya terdiri dari variable pengujian dan klasifikasi jenis pengelompokan. Pengujian K-Nearest Neighbors (KNN) untuk luas rumah nilai nya 3, besaran daya 3, pendapatan bernilai 2, jumlah daya keseluruhan, 3 dan konsumsi energi yang digunakan adalah 4. Hasil dari penelitian ini adanya aplikasi teknologi dalam model KNN dalam pengelompokan penentuan kebutuhan daya untuk masing-masing daerah di Kota Lhokseumawe.

Nowadays, Undernutrition is the main cause of child death in developing countries. There are many people and organizations try to mitigate or minimize case of child death. Thus, this paper aimed to has excellent method to handle undernutrition case by exploring the efficacy of machine learning (ML) approaches to predict Stunting in East Aceh administrative zones of Indonesia and to identify the most important predictors. The study employed ML techniques using retrospective cross-sectional survey data from East Aceh, a national-representative data is collected from government by using 2019 about stunting data. We explored Random forest commonly used ML algorithms. Random Forest (RF) as an extension of bagging that in addition for taking random sample of data and also uses random subset of features which mitigates over fitting. Our results showed that the considered machine learning classification algorithms by random forest can effectively predict the stunting status in East Aceh administrative zones. Persistent stunting status was found in the east part of Aceh. The identification of high-risk zones can provide more useful information and data to decision-makers for trying to reduce child undernutrition.

Electrical load forecasting is usually a univariate time series forecasting problem. In this case, we use the machine learning approach based on Long Short Term Memory and Support Vector Machine. Accurate the peak electric load forecasting. The time series or data set of the peak electric load recorded from the Substation system in Lhoksumewe, Indonesia. The main aim of this paper to predict and evaluate the performance of peak electric load at the substation for six months. The results obtained in the study, the LSTM and SVM are proving useful for peak electrical load forecasting. The resulting point both of machine learning technique based on LSTM and SVM are a possibility for analysis data for such purposes.

Predicting disease is usually done based on the experience and knowledge of the doctor. Diagnosis of such a disease is traditionally less effective. The development of medical diagnosis based on machine learning in terms of disease prediction provides a more accurate diagnosis than the traditional way. In terms of predicting disease can use artificial neural networks. The artificial neural network consists of various algorithms, one of which is the Backpropagation Algorithm. In this paper it is proposed that disease prediction systems use the Backpropagation algorithm. Backpropagation algorithms are often used in disease prediction, but the Backpropagation algorithm has a slight drawback that tends to take a long time in obtaining optimum accuracy values. Therefore, a combination of algorithms can overcome the shortcomings of the Backpropagation algorithm by using the success of the Gravitational Search Algorithm (GSA) algorithm, which can overcome the slow convergence and local minimum problems contained in the Backpropagation algorithm. So the authors propose to combine the Backpropagation algorithm using the Gravitational Search Algorithm (GSA) in hopes of improving accuracy results better than using only the Backpropagation algorithm. The results resulted in a higher level of accuracy with the same number of iterations than using Backpropagation only. Can be seen in the first trial of breast cancer data with parameters namely hidden layer 5, learning rate of 2 and iteration as much as 5000 resulting in accuracy of 99.3 % with error 0.7% on Backpropagation Algorithm, while in combination BP & GSA got accuracy of 99.68 % with error of 0.32%.