Articles
<![CDATA[Recent systematic review on student performance prediction using backpropagation algorithms ]]>
<![CDATA[Edi Ismanto]]>;
<![CDATA[Hadhrami Ab Ghani]]>;
<![CDATA[Nurul Izrin Md Saleh]]>;
<![CDATA[Januar Al Amien]]>;
<![CDATA[Rahmad Gunawan]]>
<![CDATA[ TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 20, No 3: June 2022 ]]>
Publisher : <![CDATA[Universitas Ahmad Dahlan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.12928/telkomnika.v20i3.21963
<![CDATA[A comprehensive systematic study was carried out in order to identify various deep learning methods developed and used for predicting student academic performance. Predicting academic performance allows for the implementation of various preventive and supportive measures earlier in order to improve academic performance and reduce failure and dropout rates. Although machine learning schemes were once popular, deep learning algorithms are now being investigated to solve difficult predictions of student performance in larger datasets with more data attributes. Deep neural network prediction methods with clear modelling and parameter measurements formulated on publicly available and recognised datasets are the focus of the research. Widely used for academic performance prediction, backpropagation algorithms have been trained and tested with various datasets, especially those related to learning management systems (LMS) and massive open online courses (MOOC). The most widely used prediction method appears to be the standard artificial neural network approach. The long-short-term memory (LSTM) approach has been reported to achieve an accuracy of around 87 percent for temporal student performance data. The number of papers that study and improve this method shows that there is a clear rise in deep learning-based academic performance prediction over the last few years]]>
<![CDATA[Implementasi Algoritma Brute Force Pada Pencarian Berita Berbasis Web ]]>
<![CDATA[Andriansyah]]>;
<![CDATA[Soni]]>;
<![CDATA[Baidarus]]>;
<![CDATA[Rahmad Gunawan]]>
<![CDATA[ Jurnal CoSciTech (Computer Science and Information Technology) Vol 2 No 2 (2021): Jurnal Computer Science and Information Technology (CoSciTech) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37859/coscitech.v2i2.3342
<![CDATA[Pada web berita yang jadi suatu kabar terpercaya dalam mengenali suatu data, namun terdapat sebagian kekurangan pada berita berbasis website khususnya pada pencarian. Perihal tersebut beberapa kendala yang dihadapi yaitu lambat sistem dalam membaca dari tiap- tiap kata kunci yang kita cari pada database yang terdapat dalam sistem tersebut. Penelitian ini bertujuan untuk mengimplementasi Algoritma Brute Force Pada Pencarian Berita Berbasis Web. Algoritma Brute Force bertujuan pencarian seluruh kemunculan string pendek yaitu pattern di string yang lebih panjang yang di inginkan. Hasil dari penelitian ini implementasi algoitma Brute Force pada website berita bisa menuntaskan permasalahan dalam melaksanakan pencarian informasi berita, sebab algoritma ini menciptakan informasi yang dicari.]]>
<![CDATA[Akurasi dan Prediksi Kejadian Hopperburn Wereng Batang Coklat (Nilaparvata Lugens Stal) menggunakan Citra Sentinel-2 ]]>
<![CDATA[Rahmad Gunawan]]>;
<![CDATA[Reflinaldon Reflinaldon]]>;
<![CDATA[Yaherwandi Yaherwandi]]>
<![CDATA[ Jurnal Proteksi Tanaman Vol 5 No 2 (2021): December 2021 ]]>
Publisher : <![CDATA[Plant Protection Departement, Faculty of Agriculture, Universitas Andalas ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.25077/jpt.5.2.107-117.2021
<![CDATA[Forecasting of brown planthopper attack or BPH (Nilaparvata lugens Stal) using artificial intelligence and vegetation index of Sentinel-2 Satellite Imagery improves forecasting the incidence of hopperburn. This study aimed to determine the accuracy and correlation of the random forest classification of Sentinel-2 imagery to the incidence of hopperburn reported by Plant Pest Organisms Observer (PPOO) and determine the best method for predicting it. The study was done through observation and secondary data processing about the age of the plant, the incidence of hopperburn by BPH, interviews with farmers, and PPOO. The results showed that the hopperburn NDVI index ranged from 0.23 - 3.8. The random forest classification accuracy was high (Kappa Index = 0.82). The relationship between the hopperburn area from the PPOO report and the predicted area from Sentinel-2 images classified as (R2 = 0.53, R = 0.728) with the equation Y = -1.5 + 0.82 X. The correlation can be improved using spatial regression Geographically Weighted Regression (GWR4) with the best gaussian distance of 1.76 km (R2 = 0.6, R = 0.77). The best prediction for the NDVI stage of hopperburn attack time series with random forest (RMSE = 0.12819) was better than the prediction of the hopperburn attack time series with the exponential smoothing method from the PPOO report (RMSE 3.302184).]]>
<![CDATA[Perangkat Media Terapi Bagi Anak Penderita Fobia Jarum Suntik (Trypanophobia) Menggunakan Teknologi Augmented Reality ]]>
<![CDATA[Evans Fuad]]>;
<![CDATA[Rahmad Gunawan]]>;
<![CDATA[Januar Al Amien]]>;
<![CDATA[Ulva Elviani]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 3, No 1 (2019): Januari 2019 ]]>
Publisher : <![CDATA[STMIK Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v3i1.1063
<![CDATA[Phobia is a condition in which a person experiences excessive fear of a particular object, giving rise to irrational fears that can threaten personal safety. Based on the data obtained from the Siak District Health Office in conducting immunizations at SDN 003 Benteng Hilir, out of 25 class 1 (one) elementary school students who were immunized, 18 of them suffered from needle phobia (Trypanophobia). Therefore, to overcome this problem, it is necessary to build an application as a medium for the therapy of needle phobia. The application that will be built in this study applies augmented reality technology as a mobile-based therapeutic medium. The approach used is systematic desentisiasi to the stage of flooding, where the medical team will guide patients in conducting therapy which begins with providing information about phobias through the application then directs the mobile to the marker bracelet that has been installed in the patient's hand so that the patient can interact with the syringe object directly. Based on the results of tests conducted in blackbox, it can be concluded that the application of trypanophobia can provide sufficiently clear information to patients and can help the medical team quickly control the patient's fear before injection]]>
<![CDATA[Peramalan Kedatangan Wisatawan ke Suatu Negara Menggunakan Metode Support Vector Machine (SVM) ]]>
<![CDATA[Harun Mukhtar]]>;
<![CDATA[Rahmad Gunawan]]>;
<![CDATA[Amin Hariyanto]]>;
<![CDATA[Syahril]]>;
<![CDATA[Wide Mulyana]]>
<![CDATA[ Jurnal CoSciTech (Computer Science and Information Technology) Vol 3 No 3 (2022): Jurnal Computer Science and Information Technology (CoSciTech) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37859/coscitech.v3i3.4211
<![CDATA[Tourism is one of the most promising ecosystems for economic sectors worldwide. A strong tourism sector directly contributes to the country's national income, fights unemployment, and improves the balance of payments. Tourism development can be seen from the increase in arrivals to a nation; based on data obtained from the UNWTO from 1995-2019, it has increased and decreased. The sudden increase and decrease in tourists will have positive and negative impacts. Forecasting is an activity to predict events that will occur in the future by taking data from the past. So this study will expect tourist arrivals to a country using the Support Vector Machine (SVM) method. SVM has properties about maximizing margins and kernel tricks to map nonlinear data. The results obtained in this study indicate that SVM Confidence is 86.3%, has a MAPE value of 56.00%, and an RMSE worth of 11126.36 from the total data of 53 countries. And forecasting is carried out in 5 countries with the highest tourist visits. The results obtained are excellent: SVM Confidence of 99.13%, a MAPE value of 2.78%, and an RMSE value of 2783.57.]]>
<![CDATA[Sistem pakar kerusakan honda beat street 2021 menggunkan metode forward chaining dan certainty factor ]]>
<![CDATA[Yulia Fatma]]>;
<![CDATA[Rahmad Gunawan]]>;
<![CDATA[Edi Rian Kartiko]]>;
<![CDATA[Sunanto]]>
<![CDATA[ Computer Science and Information Technology Vol 3 No 3 (2022): Jurnal Computer Science and Information Technology (CoSciTech) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37859/coscitech.v3i3.4377
<![CDATA[Kebutuhan masyarakat terhadap kendaraan bermotor sangatlah besar khususnya sepeda motor Honda Beat Street 2021, sebab sepeda motor dianggap sebagai sarana transportasi yang sangat memudahkan pengendara untuk menuju tempat dengan pertimbanganwaktu yang lebih cepat dibandingkan dengan menggunakan kendaraan yang beroda empat. Kurangnya pengetahuan masyarakat tentang kerusakan sepeda motor Honda Beat Street 2021 menimbulkan kerugian bagi pengguna dalam hal waktu dan biaya. Dalam masalah tersebut sepeda motor yang mengalami kerusakan dapat diatasi oleh seorang pakar dengan pengetahuan dan pengalamannya. Untuk itu perlu dibuatkan sebuah sistem pakar yang dapat mendiagnosa kerusakan yang terjadi sepeda motor Honda Beat Street 2021, dimana sistem pakar ini bertujuan untuk mentransfer pengetahuan yang dimiliki seorang pakar ke dalam komputer sehingga pengguna lebih menghemat waktu dan biaya. Sistem pakar kerusakan sepeda motor Honda Beat Street 2021 ini dibangun dengan bahasa pemrograman web PHP dan database MySQL. Proses inferensi sistem pakar ini menggunakan metode forward chaining dan proses perhitungan nilai kepastian menggunakan metode certainty factor. Para pengguna dapat mendiagnosis kerusakan yang terjadi pada sepeda motor Honda Beat Street 2021 mereka dengan mudah dan mengetahui cara penanganan kerusakan dengan memilih gejala yang ada pada sistem. Informasi pengetahuan dasar pada sistem dapat diupdate, ditambah, atau dihapus oleh admin (pakar). Presentase hasil diagnosa dengan menggunakan proses perhitungan Certainty Factor (CF) sangat dipengaruhi pada nilai CF yang diberikan oleh pakar. Uji coba sistem untuk 10 kasus menghasilkan tingkat akurasi sebesar 90%.]]>
<![CDATA[K-Nearest Neighbor (KNN) untuk Menganalisis Sentimen terhadap Kebijakan Merdeka Belajar Kampus Merdeka pada Komentar Twitter ]]>
<![CDATA[Febby Apri Wenando]]>;
<![CDATA[Rahman Septiadi]]>;
<![CDATA[Rahmad Gunawan]]>;
<![CDATA[Harun Mukhtar]]>;
<![CDATA[Syahril]]>
<![CDATA[ Computer Science and Information Technology Vol 3 No 2 (2022): Jurnal Computer Science and Information Technology (CoSciTech) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37859/coscitech.v3i2.3841
<![CDATA[On December 11, 2019, the Minister of Education and Culture of the Republic of Indonesia Nadiem Anwar Makarim issued a policy of "Merdeka Belajar". Netizens on Twitter have debated this Merdeka Belajar and became a trending topic. This study tries to analyze the sentiment of tweets about opinions on this policy by classifying whether it is a positive opinion or a negative opinion. The classification method applied is the K-Nearest Neighbor algorithm. In this study, four main processes were carried out, namely text-preprocessing, word-weighting (TF-IDF), classification and validation using k-fold cross validation. Tests were carried out with a dataset of 700 data, training was carried out using 630 training data and 70 testing data. In testing, the highest accuracy of the K-Nearest Neighbor algorithm was obtained at the k-8 value, namely 84.28%. Furthermore, validation is carried out using k-fold cross validation with a value of fold = 10 to get an accuracy of 84.42%.]]>
<![CDATA[Pendekatan Machine Learning Dengan Menggunakan Algoritma Xgboost (Extreme Gradient Boosting) Untuk Peningkatan Kinerja Klasifikasi Serangan Syn ]]>
<![CDATA[Rahmad Gunawan Gunawan]]>;
<![CDATA[Erik Suanda Handika]]>;
<![CDATA[Edi Ismanto]]>
<![CDATA[ Jurnal CoSciTech (Computer Science and Information Technology) Vol 3 No 3 (2022): Jurnal Computer Science and Information Technology (CoSciTech) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37859/coscitech.v3i3.4356
<![CDATA[Denial of Service (DoS) adalah salah satu serangan cyber populer yang ditargetkan pada situs web organisasi terkenal dan berpotensi memiliki biaya ekonomi dan waktu yang tinggi. Dalam makalah ini, beberapa metode pembelajaran mesin termasuk model ensemble dan pengklasifikasi deep learning berbasis autoencoder dibandingkan dan disetel menggunakan optimasi Bayesian. Kerangka autoencoder memungkinkan untuk mengekstrak fitur baru dengan memetakan input asli ke ruang baru. Metode tersebut dilatih dan diuji baik untuk klasifikasi biner dan multi-kelas pada kumpulan data Digiturk dan Labris, yang baru-baru ini diperkenalkan untuk mendeteksi berbagai jenis serangan DdoS. Semakin penting koneksi data melalui Internet membuat kebutuhan akan keamanan jaringan data semakin meningkat. Salah satu tools yang penting adalah Intrusion detection systems (IDS). Sistem Deteksi Intrusi (IDS) adalah proses pemantauan lalu lintas jaringan dalam sistem untuk mendeteksi pola dan aktivitas yang mencurigakan yang memungkinkan ada serangan dalam sistem itu. beberapa jenis serangan, yaitu Botnet, UDP, SYN, broadcast, sleep deprivation, dan serangan bertubi-tubi. klasifikasi pertama, hasilnya menunjukkan bahwa baik Precision (PR) dan Recall (RE) adalah 89% untuk Algoritma Random Forest. Akurasi rata-rata (AC) dari model yang kami usulkan adalah 89% yang luar biasa dan cukup baik. Pada klasifikasi kedua, hasilnya menunjukkan bahwa baik Precision (PR) dan Recall (RE)sekitar 90% untuk algoritma XGBoost. Akurasi rata-rata (AC) dari model yang kami sarankan adalah 90% pada dataset CICDDoS2019.]]>
<![CDATA[Analisis Sentimen Komentar YouTube TvOne Tentang Ustadz Abdul Somad Dideportasi Dari Singapura Menggunakan Algoritma SVM ]]>
<![CDATA[Desti Mualfah]]>;
<![CDATA[Ramadhoni]]>;
<![CDATA[Rahmad Gunawan]]>;
<![CDATA[Danang Mulyadipa Suratno]]>
<![CDATA[ JURNAL FASILKOM Vol 13 No 01 (2023): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) ]]>
Publisher : <![CDATA[Unversitas Muhammadiyah Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37859/jf.v13i01.4920
<![CDATA[Interactions in social media can be seen from comments as feedback from every activity on social media, starting from statuses in the form of text, images or videos. One area of computer technology that can study the meaning of text is text mining. Sentiment analysis or opinion mining is a solution to solving problems to automatically classify opinions into positive and negative. Comments from YouTube video viewers on the TvOne channel about Ustadz Abdul Somad being deported from Singapore. From the various responses in the comment column, information is obtained from unstructured data, so there is a needfor a technique to define the value of information. The focus in this research is to verify the truth and explore the value of structured information so that itcan describe events and topics that are connected from the comments in the YouTube videos which are the object of this research. From the test results above, it can be seen that the performance values from the test results using the Support Vector Machine method get 95.02% Accuracy, 95.02% Recall, 95.18% Precision and 95.01% F1-Score.]]>
<![CDATA[ANALISA KINERJA ALGORITMA MACHINE LEARNING UNTUK PREDIKSI VIRUS HEPATITIS C ]]>
<![CDATA[Gunawan, Rahmad Gunawan]]>;
<![CDATA[Ilham Pratama, Muhammad]]>
<![CDATA[ Computer Science and Information Technology Vol 4 No 3 (2023): Jurnal Computer Science and Information Technology (CoSciTech) ]]>
Publisher : <![CDATA[Universitas Muhammadiyah Riau ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37859/coscitech.v4i3.6513
<![CDATA[Hepatitis C (HCV) is an RNA virus and one of the blood-borne human pathogens known as Hepatitis C. According to the World Health Organization (WHO), it is estimated that nearly 3% or 120-130 million of the world's population are infected with HCV and 3-4 million new infection cases. Early diagnosis of HCV has not been effective so most of the factors that contribute to the disease are still unclear. This study aims to implement a machine learning algorithm to identify factors that contribute to hepatitis C virus and hepatitis C virus prediction problems by comparing each algorithm to determine the best algorithm for predicting hepatitis C virus in the HCV UCI Machine Learning Repository dataset. Six classification algorithms are proposed: Naive Bayes, Decision Tree, Logistic Regression, K-Nearest Neighbor, Support Vector Machine, and Random Forest. The results show that from the accuracy value of each algorithm, the best algorithm for predicting hepatitis C virus is random forest with an accuracy rate of 98.37% and it was found that the features that contributed the most to the prediction model for HCV-infected and non-HCV patients were AST (Aspartate aminotransferase) and ALP (alkaline phosphatase).]]>
