Prediksi kelulusan TOEFL peserta didik Michigan Computer English Course diperlukan untuk meninjau sejauh mana tingkat pemahaman peserta didik. Backpropagation merupakan salah satu teknik yang baik digunakan untuk prediksi, akan tetapi jika backpropagation dalam training data dengan jumlah besar serta parameter-parameter yang digunakan kurang tepat, akan terjadi proses traning data lebih lambat. Maka diperlukan metode optimasi untuk mempercepat training Bacpropagation dalam memprediksi kelulusan dengan menggunakan metode Resilient Backpropagation. Data yang diolah sebanyak 182 data peserta didik tahun 2016-2018. Tingkat akurasi pengujian semakin baik yakni 100% dengan nilai MSE semakin kecil 0.00342 serta nilai Epoch juga semakin kecil menjadi 5. Sehingga penelitian ini menjadi indikator dalam pengembangan prediksi TOEFL dimasa yang akan datang.

Marriage is the most awaited moment for everyone. Prawdding is an important thing to do before a wedding. Because prewedding photos become the latest trend for photos that will be displayed during the wedding. But in a lot of prewedding photos brides who are not satisfied with the results of these prewedding photos. This system can facilitate the bride and groom in choosing the location of prawedding photos without the need to meet in person to consult. This decision making system is made using the Weight Product method and is made with the php programming language and MySQL database. The WP method is used to find optimal alternatives from a number of alternatives. The selection of the location of the prewedding photo uses weighting for each criterion. The bride and groom can choose the desired location based on criteria such as the number of spots, themes, location distance, number of shoots with weights determined by the user based on the level of importance. The results of this system are displaying praweding locations based on the location of prawedding photos that can be ordered by the bride and groom. The selection of prewedding photo locations can be done optimally so that the results of the decision are as expected.Keywords: Decision Support System, Prewedding Location, Product Weight

The training function used in the ANN method, especially backpropagation, can produce different forecasting accuracy, depending on the method parameters given and the data to be predicted. This paper aims to analyze the ability and performance of one of the training functions in the backpropagation algorithm, namely One-step secant, which can later be used or used as a reference in the case of data forecasting. This method is able to update the values of bias and weights according to the one-step secant method. The analysis process uses a dataset of Foreign Exchange Reserves (US $ Million) in Indonesia 2011-2020. Based on this dataset, the dataset will be divided into two parts. The training data uses the 2011-2014 and 2015 dataset as the training data target. Meanwhile, the test data used 2016-2019 and 2020 as the target test data. The analysis process uses 5 experimental architectures, namely 4-5-1, 4-7-1, 4-9-1, 4-11-1 and 4-13-1. The results of the research based on the analysis obtained the best network architecture 4-11-1 with an MSE Training value of 0.00000012, MSE testing/performance of 0.00115144 (the smallest compared to other architectures) and Epoch 343 Iterations.

Indonesia is one of the countries that often experiences natural disasters, including earthquakes, floods, tsunamis, etc. All of this causes losses, both casualties, Broken, and Anguishing for the population. Based on this, this paper is proposed, which aims to predict natural disasters in the coming years in Indonesia, casualties, Broken, and their consequences. This paper is an extension of previous research, which is still an architectural model to predict Indonesia’s natural disasters and their impacts. Model 4-10-1 is the best in this study, which produces 91% accuracy. Based on this architectural model, this paper will predict natural disasters that occur and their impacts for the years to come in Indonesia. The research dataset and algorithms used remain the same, namely the natural disaster dataset for 2008-2019. Resourced from its National Emergency Management Department and the Batch Training algorithm. Specifically, the results of this proposed paper are in the form of a prediction of natural disasters that will occur, dead and disappear, injured, Anguishing and displaced, houses severely Broken, moderately Broken, lightly Broken to submerged, and Broken to facilities and infrastructure such as health facilities, facilities. worship and educational facilities.

Stunting adalah kondisi gagal tumbuh pada balita akibat kekurangan asupan gizi dan infeksi yang berkepanjangan yang mengakibatkan tinggi badan yang lebih pendek dari standar usianya. Indonesia saat ini menjadi urutan ke 4 dalam tingginya kasus prevelensi stunting menurut standar World Health Organization. Adapun tujuan dari penelitian ini untuk mengelompokkan provinsi mana yang mengalami bayi stunting dengan cluster tertinggi maupun cluster terendah yang berguna sebagai masukan bagi pemerintah untuk menangani dengan cepat penurunan stunting di Indonesia. Data yang digunakan dari penelitian ini di dapat dari Badan Pusat Statistika (BPS) dengan nama indikator Prevelensi Stunting tahun 2015-2018. Dalam penelitian ini data di olah dengan menggunakan Algoritma K-Medoids yang merupakan salah satu bagian dari algoritma clustering yang dapat memecahkan dataset ke kelompok-kelompok diantara semua objek data dengan menggunakan objek sebagai perwakilan (medoid) dalam sebuah cluster.