Claim Missing Document
Check
Articles

Found 6 Documents
Search

EFESIENSI ENERGI PADA BANGUNAN MENGGUNAKAN MULTIVARIATE RANDOM FOREST Triando Hamonangan Saragih; Mohammad Reza Faisal; Muhammad Haekal
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 9, No 1 (2022)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v9i1.421

Abstract

Energy is needed by humans. Energy utilization is often carried out in daily activities, such as helping with work, household activities to lighting both at home and on the road. Recently, there has been a lot of research on concerns about the waste of energy and its lasting adverse impact on the environment. Previous research conducted by Tsanas and Xifara in 2012 has carried out energy efficiency in buildings using Statistical Machine Learning. Their research focuses on calculating outcomes one by one, not directly on all outcomes. In this study using the Multivariate Random Forest method. Multivariate Random Forest has similarities compared to Random Forest, while the Multivariate Random Forest method is more used if more than one output is produced. Based on the tests that have been carried out, it can be concluded that the best parameter that gives maximum results is the number of trees as many as 200 with a data division of 60% training data and 40% testing data with RMSE results of 2.602036 and MSE result of 6.770589. Based on the tests that have been carried out, it proves that the more the number of trees does not prove that it can provide maximum results.Keywords: Energy, Efficiency, Prediction, Multivariate Random ForestEnergi sangat dibutuhkan oleh manusia. Pemanfaatan energi sering dilakukan dalam kegiatan sehari-hari, seperti membantu pekerjaan, kegiatan rumah tangga hingga penerangan baik dalam rumah maupun di jalan. Akhir-akhir ini banyak penelitian tentang kekhawatiran mengenai pemborosan energi dan dampak buruknya yang abadi terhadap lingkungan. Penelitian sebelumnya yang dilakukan oleh Tsanas dan Xifara pada tahun 2012 telah melakukan efesiensi energi pada bangunan menggunakan Statistical Machine Learning. Penelitian mereka berfokus pada perhitungan luaran secara satu persatu, tidak secara langsung semua luaran. Pada penelitian ini menggunakan metode Multivariate Random Forest. Multivariate Random Forest memiliki kesamaan dibandingkan dengan Random Forest, sedangkan metode Multivariate Random Forest lebih digunakan jika luaran yang dihasilkan lebih dari satu. Berdasarkan pengujian yang sudah dilakukan, dapat disimpulkan bahwa parameter terbaik yang memberikan hasil maksimal yaitu pada jumlah pohon sebanyak 200 dengan pembagian data sebanyak 60% data latih dan 40% data uji dengan hasil RMSE sebesar 2.602036 dan MSE sebesar 6.770589. Berdasarkan pengujian yang sudah dilakukan membuktikan semakin banyak jumlah pohon tidak membuktikan bisa memberikan hasil yang maksimal.Kata kunci: Energi, Efesiensi, Prediksi, Multivariate Random Forest
OPTIMASI FUNGSI KEANGGOTAAN FIS TSUKAMOTO MENGGUNAKAN SIMULATED ANNEALING UNTUK IDENTIFIKASI PENYAKIT GIGI Triando Hamonangan Saragih; Rahmat Ramadhani; Muhammad Itqan Mazdadi; Ahmad Rusadi Arrahimi; Mohammad Reza Faisal
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 7, No 3 (2020)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v7i3.349

Abstract

Teeth are one of the tools in the framework related to the human stomach which fills as a food destroyer for simple processing. Diseases that attack teeth can withstand this action and cannot be distinguished quickly by young dental specialists. This problem can be solved by methods in the field of technology. The algorithm that can be used is FIS Tsukamoto in classification. Optimization of the membership function at FIS Tsukamoto is needed to improve accuracy. Optimization of FIS Tsukamoto membership function using Simulated Annealing produced the highest accuracy at 92.5% of the 100 test data.Keywords: Simulated Annealing; FIS Tsukamoto, Dental Disease, Optimization Gigi adalah salah satu alat dalam kerangka terkait perut manusia yang mengisi sebagai penghancur makanan untuk pemrosesan sederhana. Penyakit yang menyerang gigi dapat menahan tindakan ini dan tidak dapat dibedakan dengan cepat oleh dokter muda spesialis gigi. Masalah ini dapat diselesaikan dengan metode di bidang teknologi. Algoritma yang bisa digunakan yaitu FIS Tsukamoto dalam melakukan klasifikasi. Optimasi fungsi keanggotaan pada FIS Tsukamoto diperlukan untuk meningkatkan akurasi. Optimasi fungsi keanggotaan FIS Tsukamoto menggunakan Simulated Annealing menghasilkan akurasi paling tinggi yaitu 92,5% dari 100 data uji.Kata kunci: Simulated Annealing; FIS Tsukamoto, Penyakit Gigi, Optimisasi
Comparative Study of Decision Tree, K-Nearest Neighbor, and Modified K-Nearest Neighbor on Jatropha Curcas Plant Disease Identification Triando Hamonangan Saragih; Diny Melsye Nurul Fajri; Alfita Rakhmandasari
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 5, No. 1, February 2020
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (353.416 KB) | DOI: 10.22219/kinetik.v5i1.1012

Abstract

Jatropha Curcas is a very useful plant that can be used as a bio fuel for diesel engines replacing the coal. In Indonesia, there are few plantation that plant Jatropha Curcas. But there is so limited farmers that understand in detail about the disease of Jatropha Curcas and it may cause a big loss during harvesting when the disease occured with no further action. An expert system can help the farmers to identify the lant diseases of Jatropha Curcas. The objective of this research is to compare several identification and classification methods, such as Decision Tree, K-Nearest Neighbor and its modification. The comparison is based on the accuracy. Modified K-Nearest Neighbor method given the best accuracy result that is 67.74%.
AdaBoost Classifier untuk Klasifikasi Tanaman Jarak Pagar Triando Hamonangan Saragih; Muliadi Muliadi; Mohammad Reza Faisal; Muhammad Al Ichsan Nur Rizqi Said
Jurnal Komputasi Vol 9, No 2 (2021)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v9i2.2865

Abstract

Tanaman Jarak Pagar merupakan tanaman multi fungsi yang memiliki banyak kegunaan di kehidupan sehari-hari, baik itu untuk pengobatan, kecantikan hingga pengganti bahan bakar biodiesel. Penyakit yang menyerang tanaman jarak pagar dapat menurunkan kualitas yang dihasilkan jarak pagar. Minimnya pengetahuan petani dan sedikitnya jumlah pakar yang memahami tentang jarak pagar menjadi masalah yang harus diselesaikan. Pengguanaan sistem pakar menjadi solusi yang bisa ditawarkan. AdaBoost Classifier pada sistem pakar dapat digunakan sebagai mengklasifikasikan penyakit tanaman jarak pagar. Hasil yang diperoleh dari penelitian ini yaitu didapat akurasi rata-rata sebesar 50% dan maksimal terbaik sebesar 53,01% pada jumlah fold sebanyak 2. Hasil pada penelitian ini lebih baik dibanding penelitian sebelumnya, tetapi tidak bisa memberikan hasil yang maksimal. Jumlah data tiap kelas menjadi perrmalasahan mengapa hasil pada AdaBoost kurang maksimal dan harus diselesaikan pada penelitian selanjutnya.
Prediksi Tinggi Permukaan Air Waduk Menggunakan Artificial Neural Network Berbasis Sliding Window Dwi Kartini; Friska Abadi; Triando Hamonangan Saragih
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 1 (2021): Februari 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v5i1.2602

Abstract

The water level in the reservoir is an important factor in the operation of a hydroelectric turbine to control water overflow so that there is no excessive degradation. This water control has an influence on the performance and production of hydroelectric energy. The daily reservoir water level (tpaw) recording of PLTA Riam Kanan is carried out through a daily direct measurement and observation process on the reservoir measuring board which is recapitulated every month in excel form. This time series historical data continues to grow every day to become a data warehouse that is still useless if only stored. Extracting knowledge from the data warehouse can be done using one of the artificial neural network data mining techniques, namely backpropagation to predict the next day's tpaw. Historical data for the tpaw time series is presented with a sliding window concept approach based on the window sizes used, namely 7, 14, 21 and 28. Some backpropagation network testing is carried out using a combination of the number of window sizes against the comparison of the amount of training data and test data on the network. The prediction results obtained with the smallest mean squared error (mse) in network testing is 0.000577 as a high accuracy value of the prediction results. The network architecture with the smallest mse using 28 input layers, 10 hidden layers and 1 output layer can be a knowledge that can help the hydropower plant as an alternative in making turbine operation decisions based on the predicted results of reservoir water level.
Prediksi Tinggi Permukaan Air Waduk Menggunakan Artificial Neural Network Berbasis Sliding Window Dwi Kartini; Friska Abadi; Triando Hamonangan Saragih
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 1 (2021): Februari 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v5i1.2602

Abstract

The water level in the reservoir is an important factor in the operation of a hydroelectric turbine to control water overflow so that there is no excessive degradation. This water control has an influence on the performance and production of hydroelectric energy. The daily reservoir water level (tpaw) recording of PLTA Riam Kanan is carried out through a daily direct measurement and observation process on the reservoir measuring board which is recapitulated every month in excel form. This time series historical data continues to grow every day to become a data warehouse that is still useless if only stored. Extracting knowledge from the data warehouse can be done using one of the artificial neural network data mining techniques, namely backpropagation to predict the next day's tpaw. Historical data for the tpaw time series is presented with a sliding window concept approach based on the window sizes used, namely 7, 14, 21 and 28. Some backpropagation network testing is carried out using a combination of the number of window sizes against the comparison of the amount of training data and test data on the network. The prediction results obtained with the smallest mean squared error (mse) in network testing is 0.000577 as a high accuracy value of the prediction results. The network architecture with the smallest mse using 28 input layers, 10 hidden layers and 1 output layer can be a knowledge that can help the hydropower plant as an alternative in making turbine operation decisions based on the predicted results of reservoir water level.