Articles
<![CDATA[Comparative Analysis of ADASYN-SVM and SMOTE-SVM Methods on the Detection of Type 2 Diabetes Mellitus ]]>
<![CDATA[Ramadhan, Nur Ghaniaviyanto]]>
<![CDATA[ Scientific Journal of Informatics Vol 8, No 2 (2021): November 2021 ]]>
Publisher : <![CDATA[Universitas Negeri Semarang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.15294/sji.v8i2.32484
<![CDATA[Most people with diabetes in the world are type 2. We can detect diabetes early to prevent things that are not desirable by checking sugar and insulin levels with the doctor. In addition to using this method, people with diabetes can also be grouped based on data from diabetes examination results. However, most of the data on health examination results have several parameters that are difficult for the public to understand. These problems can be done by means of automatic classification. In addition to these problems, there is another problem in the form of an unbalanced amount of data for diabetics and non-diabetics. This problem can be done by balancing the amount of data using the model to increase the ratio of the amount of data that is small or decrease the ratio of the amount of data that is too much. Purpose: This study aims to detect type 2 diabetes mellitus using the SVM classification model and analyze the results of the comparison using the SMOTE and ADASYN data balancing technique which is the best. Methods/Study design/approach: The research method starts from collecting the diabetes dataset, then the dataset cleaning process is carried out whether there is a null value or not. After applying two oversampling methods to analyze which method is the most appropriate. After the oversampling technique was carried out, data classification was carried out using a support vector machine model to see the accuracy results. Result/Findings: The results obtained by the ADASYN-SVM method are superior to SMOTE-SVM. The ADASYNSVM method has an accuracy of 87.3%, while the SMOTE-SVM has an accuracy of 85.4%. Novelty/Originality/Value: The data used in this study came from the Karya Medika clinic, Indonesia which contains parameters related to type 2 diabetes.]]>
<![CDATA[Analysis Sentiment Based on IMDB Aspects from Movie Reviews using SVM ]]>
<![CDATA[Ramadhan, Nur Ghaniaviyanto]]>;
<![CDATA[Ramadhan, Teguh Ikhlas]]>
<![CDATA[ Sinkron : jurnal dan penelitian teknik informatika Vol. 7 No. 1 (2022): Article Research Volume 7 Issue 1: January 2022 ]]>
Publisher : <![CDATA[Politeknik Ganesha Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33395/sinkron.v7i1.11204
<![CDATA[A movie is a spectacle that can be done at a relaxed time. Currently, there are many movies that can be watched via the internet or cinema. Movies that are watched on the internet are sometimes charged to watch so that potential viewers before watching a movie will read comments from users who have watched the movie. The website that is often used to view movie comments today is IMDB. Movie comments are many and varied on the IMDB website, we can see comments based on the star rating aspect. This causes users to have difficulty analyzing other users' comments. So, this study aims to analyze the sentiment of opinions from several comments from IMDB website users using the star rating aspect and will be classified using the support vector machine method (SVM). Sentiment analysis is a classification process to understand the opinions, interactions, and emotions of a document or text. SVM is very efficient for many applications in science and engineering, especially for classification (pattern recognition) problems. In addition to the SVM method, the TF-IDF technique is also used to change the shape of the document into several words. The results obtained by applying the SVM model are 79% accuracy, 75% precision, and 87% recall. The SVM classification is also superior to other methods, namely logistic regression.]]>
<![CDATA[Improving Smart Lighting with Activity Recognition Using Hierarchical Hidden Markov Model ]]>
<![CDATA[Nur Ghaniaviyanto Ramadhan]]>;
<![CDATA[Aji Gautama Putrada]]>;
<![CDATA[Maman Abdurohman]]>
<![CDATA[ Indonesia Journal on Computing (Indo-JC) Vol. 4 No. 2 (2019): September, 2019 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.34818/INDOJC.2019.4.2.307
<![CDATA[This paper has the aim of implementing the smart lighting systems that is able to analyze daily movement activities, analyze the performance of hierarchical hidden markov models as predictions and analyze the performance of smart lighting with activity analysis using hierarchical hidden markov models. The purpose is to answer the problems that occur, namely the smart lights only turn on if users are right under the lights so users need a smart light which is able to read the movement of people when approaching the lamp or not. Secondly, there are also smart lights, but when usersare under the lights, it only lights up for a few seconds which should light up if there is a person below or a radius around the lamp so that a smart light is needed when someone is underneath and the lights will die it is outside the radius around the lamp. The model used is the hierarchical hidden markov model which is an extension of the hidden markov model which can solve the problem of evaluation, conclusion and learning with the algorithm used is the viterbi algorithm. The result obtained using HHMM are accuracy of 93%, 92% recall and 86% precision.]]>
<![CDATA[Implementation of LSTM-RNN for Bitcoin Prediction ]]>
<![CDATA[Nur Ghaniaviyanto Ramadhan]]>;
<![CDATA[Nia Annisa Ferani Tanjung]]>;
<![CDATA[Faisal Dharma Adhinata]]>
<![CDATA[ Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 3 (2021): December, 2021 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.34818/INDOJC.2021.6.3.592
<![CDATA[Bitcoin is a cryptocurrency that is used worldwide for digital payments or simply for investment purposes. Bitcoin is a new technology so there are currently very few prices prediction models available. Problems arise when someone uses bitcoin without understanding strong fundamentals. This can result in a lot of loss for the person. These problems certainly need to be overcome by predicting bitcoin prices using a machine learning approach. The purpose of this research is to predict the bitcoin USD price using the Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) model. The LSTM-RNN model was chosen because it is better than the traditional neural network model. Measurement of the results in this study using the Root Mean Square Error (RMSE). The RMSE results obtained on the application of the LSTM-RNN model 6461.14.]]>
<![CDATA[Trials and Progress Prediction of Covid-19 Vaccine Using Linear Regression and SIR Parameters ]]>
<![CDATA[Ananda Aulia Rizky]]>;
<![CDATA[Novi Rahmawati]]>;
<![CDATA[Adil El-Faruqi]]>;
<![CDATA[Faisal Dharma Adhinata]]>;
<![CDATA[Nur Ghaniaviyanto Ramadhan]]>
<![CDATA[ Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 3 (2021): December, 2021 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.34818/INDOJC.2021.6.3.594
<![CDATA[This study aims to elucidate the worldwide effectiveness of the COVID-19 vaccine to reduce the number of COVID-19 patients. Currently, almost all countries in the world are trying to overcome COVID-19 by imposing a lockdown system. The government is also looking for a solution to suppress the spread of COVID-19 by administering a vaccine. Vaccination is one of the efforts that are considered effective in overcoming COVID-19 in affected countries. At least 85 types of vaccines are still in the development stage, while the vaccines that have been agreed upon are Pfizer-Biotech messenger RNA vaccines (bnt162b2) and Moderna (mRNA-1273). The hope is that the COVID-19 outbreak can be handled immediately to restore the residents' economy with vaccination. The methodology used in this study uses data mining with linear regression and SIR techniques to evaluate whether circulating vaccines can effectively suppress the spread of COVID-19.]]>
<![CDATA[Neural Network on Stock Prediction using the Stock Prices Feature and Indonesian Financial News Titles ]]>
<![CDATA[Nur Ghaniaviyanto Ramadhan]]>;
<![CDATA[Imelda Atastina]]>
<![CDATA[ International Journal on Information and Communication Technology (IJoICT) Vol. 7 No. 1 (2021): June 2021 ]]>
Publisher : <![CDATA[School of Computing, Telkom University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21108/ijoict.v7i1.544
<![CDATA[Stocks are the most popular investments among entrepreneurs or other investors. When investing in stocks these investors tend to learn how to invest stocks correctly and when is the right time. For the problem of how to invest shares correctly can be used a variety of basic theories that already exist, but for the problem when the right time needs further learning. In this paper will purpose about stock price prediction using stock data indicators and financial headline data in Bahasa Indonesia. The machine learning model used is a multi-layer perceptron neural network (MLP-NN) with the highest accuracy produced by 80%.]]>
<![CDATA[A Proposed Hidden Markov Model Method for Dynamic Device Pairing on Internet of Things End-Devices ]]>
<![CDATA[Aji Gautama Putrada]]>;
<![CDATA[Nur Ghaniaviyanto Ramadhan]]>
<![CDATA[ Journal of ICT Research and Applications Vol. 14 No. 3 (2021) ]]>
Publisher : <![CDATA[LPPM ITB ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.5614/itbj.ict.res.appl.2020.14.3.5
<![CDATA[Dynamic device pairing is a context-based zero-interaction method to pair end-devices in an IoT System based on Received Signal Strength Indicator (RSSI) values. But if RSSI detection is done in high level, the accuracy is troublesome due to poor sampling rates. This research proposes the Hidden Markov Model method to increase the performance of dynamic device pairing detection. This research implements an IoT system consisting an Access Point, an IoT End Device, an IoT Platform, and an IoT application and performs a comparison of two different methods to prove the concept. The results show that the precision of dynamic device pairing with HMM is better than without HMM and the value is 83,93%.]]>
<![CDATA[Indonesian Online News Topics Classification using Word2Vec and K-Nearest Neighbor ]]>
<![CDATA[Nur Ghaniaviyanto Ramadhan]]>
<![CDATA[ Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 6 (2021): Desember 2021 ]]>
Publisher : <![CDATA[Ikatan Ahli Informatika Indonesia (IAII) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (384.766 KB)
|
DOI: 10.29207/resti.v5i6.3547
<![CDATA[News is information disseminated by newspapers, radio, television, the internet, and other media. According to the survey results, there are many news titles from various topics spread on the internet. This of course makes newsreaders have difficulty when they want to find the desired news topic to read. These problems can be solved by grouping or so-called classification. The classification process is carried out of course by using a computerized process. This study aims to classify several news topics in Indonesian language using the KNN classification model and word2vec to convert words into vectors which aim to facilitate the classification process. The use of KNN in this study also determines the optimal K value to be used. In addition to using the classification model, this study also uses a word embedding-based model, namely word2vec. The results obtained using the word2vec and KNN models have an accuracy of 89.2% with a value of K=7. The word2vec and KNN models are also superior to the support vector machine, logistic regression, and random forest classification models.]]>
<![CDATA[TEKNIK SMOTE DAN GINI SCORE DALAM KLASIFIKASI KANKER PAYUDARA ]]>
<![CDATA[Nur Ghaniaviyanto Ramadhan]]>;
<![CDATA[Faisal Dharma Adhinata]]>
<![CDATA[ RADIAL : Jurnal Peradaban Sains, Rekayasa dan Teknologi Vol 9 No 2 (2021): RADIAL ]]>
Publisher : <![CDATA[Universitas Bina Taruna Gorontalo ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (453.223 KB)
|
DOI: 10.37971/radial.v9i2.229
<![CDATA[Breast cancer is a malignancy in breast tissue that can originate from the epithelium of the ducts and lobules. WHO says 30% - 50% of cancer cases can be prevented. Breast cancer prevention can be done utilizing screening or early diagnosis. The purpose of the initial diagnosis is that if a lump appears, predictions can be made whether it is classified as malignant or benign. Breast cancer prediction can be done using a dataset containing cancer-related parameters. However, sometimes the dataset used also has problems such as the amount of data is not balanced and the use of irrelevant features. This study aims to improve breast cancer prediction results by balancing the number of data classes and using the rank feature. The method used is SMOTE for imbalanced data and Gini score for rank features. The classification model used is random forest and naïve Bayes. The results obtained by the random forest classification model are superior to Naïve Bayes.]]>
<![CDATA[Klasifikasi Data Malaria Menggunakan Metode Support Vector Machine ]]>
<![CDATA[Nur Ghaniaviyanto Ramadhan]]>;
<![CDATA[Azka Khoirunnisa]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 4 (2021): Oktober 2021 ]]>
Publisher : <![CDATA[STMIK Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v5i4.3347
<![CDATA[Malaria is a life-threatening disease, caused by a parasite that is transmitted to humans through the bite of an infected female Anopheles mosquito. In 2019, there were an estimated 229 million cases of malaria worldwide and the death toll reached 409,000. The area most frequently affected by malaria, according to WHO, is the African region. Malaria can be detected beforehand by using the information inpatient data and applying machine learning techniques. This study aims to detect and classify severe malaria based on the history of examining patient data using the Support Vector Machine (SVM) method with a normalization technique using min-max on the dataset and a cross-validation technique with several experiments on the K value of the results. This study also compares the Support Vector Machine method with Naïve Bayes (NB) where the accuracy of the SVM model is superior to Nave Bayes with an average accuracy gap of 25%. The accuracy generated by the application of the proposed method is 92.3%.]]>
