Claim Missing Document
Check
Articles

Found 7 Documents
Search
Journal : Indonesian Journal on Computing (Indo-JC)

Implementasi Newton Raphson Termodifikasi pada Prediksi Distribusi Tekanan Pipa Transmisi Gas Alam Annisa Aditsania; Isman Kurniawan
Indonesia Journal on Computing (Indo-JC) Vol. 1 No. 2 (2016): September, 2016
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/INDOJC.2016.1.2.53

Abstract

Prediksi profil distribusi tekanan disepanjang jaringan pipa transmisi merupakan salah satu prosedur penting untuk mengevaluasi performa desain jaringan pipa. Pada penelitian ini, distribusi tekanan untuk setiap segmen pipa dimodelkan menggunakan korelasi Panhandle A sebagai fungsi dari properti fluida, properti segmen pipa dan properti lingkungan jaringan pipa. Korelasi Panhandle A secara matematis dapat dipandang sebagai persamaan non-linear. Pada penelitian-penelitian terdahulu, metode Newton Raphson dipilih sebagai metode untuk mendapatkan solusi numerik, karena orde konvergensi tinggi. Sebagai upaya untuk mengoptimalkan waktu komputasi dari perhitungan distribusi jaringan, pada penelitian kali ini, metode Newton Raphson termodifikasi dipilih sebagai metode pencarian solusi numerik. Hasil simulasi menunjukan bahwa profile distribusi tekanan menggunakan metode newton Raphson termodifikasi akurat dengan error relative maksimum 0.28% untuk batas toleransi error  bila dibandingkan dengan profile distribusi tekanan data lapangan 
Pemodelan Dan Simulasi Produksi Biogas Dari Substrat Glukosa Menggunakan Anaerobic Digestion Model No. 1 (ADM1) Isman Kurniawan; Annisa Aditsania
Indonesia Journal on Computing (Indo-JC) Vol. 1 No. 1 (2016): March, 2016
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/INDOJC.2016.1.1.54

Abstract

This research focus in modeling of biogas production using Anaerobic Digestion Model No. 1 (ADM1). Initial simulation was performed using recommended parameter and its result will be used to determine the accuracy. Simulation result shows similar trend compare to experimental data even it is less accurate. The accuracy of calculation is improved by optimize the simulation parameter. The number of parameter is reduced by calculate the sensivity indices of each parameter. Optimization process using genetic algorithm result new optimized parameter value. The value of mean average percentage error (MAPE) of simulation using standard parameter and optimized parameter are 22,54% and 0,08%, respectively. It shows that simulation using optimized parameter give better accuracy. Simulation results shows the glucose concentration decrease significantly in the beginning of process and methane concentration increase simultaneously. The final concentration of methan after 500 mgCOD/L of glucose decomposed is 354,79 mgCOD/L.
Pemodelan Produksi Biogas pada Reaktor Tipe Batch Menggunakan Metode Hamming Predictor-Corrector Ali Assegaf; Rian Febrian Umbara; Isman Kurniawan
Indonesia Journal on Computing (Indo-JC) Vol. 4 No. 1 (2019): Maret, 2019
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21108/INDOJC.2019.4.1.138

Abstract

Penelitian ini memiliki tujuan untuk membuat sebuah model prediksi hasil produksi biogas pada reaktor tipe batch. Simulasi pencernaan anaerobik akan glukosa sebagai substrat utama dengan konsentrasi awal 500 mgCOD/l, dan simulasi akan dilakukan selama 120 jam. Dalam penelitian ini juga bertujuan untuk mengetahui konsentrasi mikroorganisme yang terlibat dalam proses pencernaan anaerobik, serta akan dilakukan beberapa analisis seperti perbandingan metana yang dihasilkan pada simulasi dan eksperimen, pengaruh jumlah iterasi terhadap waktu yang dibutuhkan untuk melakukan running program, perbandingan jumlah glukosa dan mikroorganisme yang digunakan dalam simulasi terhadap jumlah metana yang akan dihasilkan. Untuk memprediksi jumlah produksi biogas, terdapat sebuah model yang umum digunakan yaitu Anaerobic Digestion Model No 1 (ADM1). ADM1 dikembangkan oleh Asosiasi Water International (IWA) pada tahun 2002. Agar mendapatkan model yang memiliki akurasi yang tinggi akan digunakan sebuah metode numerik yaitu Hamming Predictor-Corrector. Setelah simulasi pencernaan anaerobik dilakukan, metana yang dihasilkan sebesar 417,48 MgCOD/l. Lalu mikroorganisme glukosa mengalami pertumbuhan yang maksimum jika dibandingkan dengan mikroorganisme lain yaitu sebesar 77 MgCOD/l. Konsentrasi awal substrat glukosa dan konsentrasi mikroorganisme yang digunakan pada proses simulasi sangat berpengaruh terhadap jumlah metana yang dihasilkan. Namun untuk konsentrasi awal mikroba yang lebih dari 30 MgCOD/l, cenderung menghasilkan metana yang konstan.
Implementation Information Gain Feature Selection for Hoax News Detection on Twitter using Convolutional Neural Network (CNN) Husnul Khotimah Farid; Erwin Budi Setiawan; Isman Kurniawan
Indonesia Journal on Computing (Indo-JC) Vol. 5 No. 3 (2020): December, 2020
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2020.5.3.506

Abstract

The development of information and communication technology is currently increased, especially related to social media. Nowadays, many people get information through social media, especially Twitter, because of its easy access and it doesn't cost much. However, it has a negative impact in the form of spreading fake news or hoaxes that are difficult to detect. In this research, the authors developed a hoax news detection model using the Convolutional Neural Network and the TF-IDF weighting method. Feature selection is performed using Information Gain with various features, such as unigram, bigram, trigram and a combination of the three. Testing is done with 3 scenarios, classification, classification by weighting, classification by weighting and feature selection. The parameter used in the information gain feature selection is the threshold 0.8. The results showed that the classification by weighting and feature selection produced the highest accuracy that is equal to 95.56% on the unigram + bigram features with a comparison of training data and test data 50:50.
Classification Model of Consumer Question about Motorbike Problems by Using Naïve Bayes and Support Vector Machine Ekky Wicaksana; Danang Triantoro Murdiansyah; Isman Kurniawan
Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 2 (2021): September, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.2.561

Abstract

The motorbike plays an important role in supporting daily activity. The motorbike is known as one of the transportation modes that is frequently used in Indonesia. The number of motorbikes used in Indonesia is continuously increasing time by time. Hence, the occurrence of motorbike problems can affect community activity and disturb the economic condition in society. Since the problem of the motorbike can occur at any time, a prevention action is required by providing an online consultation platform. However, a classification model is required to handle a wide range of questions about the motorbike problem. By classifying those questions into a specific class of problems, the solution can be delivered to the consumer faster. In this study, we developed prediction models to classify consumer questions. The data set was collected from consumer questions regarding motorbike problems that are commonly occurring. The model was developed using two machine learning algorithms, i.e., Naïve Bayes and Support Vector Machine (SVM). Text vectorization was performed by using the n-gram and term frequency-inverse document frequency (TF-IDF) method. The results show that the SVM model with the uni-trigram model performs better with the value of accuracy and F-measure, which are 0.910 and 0.910, respectively.
Implementation Information Gain Feature Selection for Hoax News Detection on Twitter using Convolutional Neural Network (CNN) Farid, Husnul Khotimah; Setiawan, Erwin Budi; Kurniawan, Isman
Indonesian Journal on Computing (Indo-JC) Vol. 5 No. 3 (2020): December, 2020
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2020.5.3.506

Abstract

The development of information and communication technology is currently increased, especially related to social media. Nowadays, many people get information through social media, especially Twitter, because of its easy access and it doesn't cost much. However, it has a negative impact in the form of spreading fake news or hoaxes that are difficult to detect. In this research, the authors developed a hoax news detection model using the Convolutional Neural Network and the TF-IDF weighting method. Feature selection is performed using Information Gain with various features, such as unigram, bigram, trigram and a combination of the three. Testing is done with 3 scenarios, classification, classification by weighting, classification by weighting and feature selection. The parameter used in the information gain feature selection is the threshold 0.8. The results showed that the classification by weighting and feature selection produced the highest accuracy that is equal to 95.56% on the unigram + bigram features with a comparison of training data and test data 50:50.
Classification Model of Consumer Question about Motorbike Problems by Using Naïve Bayes and Support Vector Machine Wicaksana, Ekky; Murdiansyah, Danang Triantoro; Kurniawan, Isman
Indonesian Journal on Computing (Indo-JC) Vol. 6 No. 2 (2021): September, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.2.561

Abstract

The motorbike plays an important role in supporting daily activity. The motorbike is known as one of the transportation modes that is frequently used in Indonesia. The number of motorbikes used in Indonesia is continuously increasing time by time. Hence, the occurrence of motorbike problems can affect community activity and disturb the economic condition in society. Since the problem of the motorbike can occur at any time, a prevention action is required by providing an online consultation platform. However, a classification model is required to handle a wide range of questions about the motorbike problem. By classifying those questions into a specific class of problems, the solution can be delivered to the consumer faster. In this study, we developed prediction models to classify consumer questions. The data set was collected from consumer questions regarding motorbike problems that are commonly occurring. The model was developed using two machine learning algorithms, i.e., Naïve Bayes and Support Vector Machine (SVM). Text vectorization was performed by using the n-gram and term frequency-inverse document frequency (TF-IDF) method. The results show that the SVM model with the uni-trigram model performs better with the value of accuracy and F-measure, which are 0.910 and 0.910, respectively.