Garuda - Garba Rujukan Digital

Latent semantic analysis and cosine similarity for hadith search engine Wahyudin Darmalaksana; Cepy Slamet; Wildan Budiawan Zulfikar; Imam Fahmi Fadillah; Dian Sa’adillah Maylawati; Hapid Ali
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 1: February 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i1.14874

Search engine technology was used to find information as needed easily, quickly and efficiently, including in searching the information about the hadith which was a second guideline of life for muslim besides the Holy Qur'an. This study was aim to build a specialized search engine to find information about a complete and eleven hadith in Indonesian language. In this research, search engines worked by using latent semantic analysis (LSA) and cosine similarity based on the keywords entered. The LSA and cosine similarity methods were used in forming structured representations of text data as well as calculating the similarity of the keyword text entered with hadith text data, so the hadith information was issued in accordance with what was searched. Based on the results of the test conducted 50 times, it indicated that the LSA and cosine similarity had a success rate in finding high hadith information with an average recall value was 87.83%, although from all information obtained level of precision hadith was found semantically not many, it was indicated by the average precision value was 36.25%.

Marketplace affiliates potential analysis using cosine similarity and vision-based page segmentation Wildan Budiawan Zulfikar; Mohamad Irfan; Muhammad Ghufron; Jumadi Jumadi; Esa Firmansyah
Bulletin of Electrical Engineering and Informatics Vol 9, No 6: December 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v9i6.2018

One success factor of an online affiliate is determined by the quality of the content source. Therefore, affiliate marketplaces need to do an objective assessment to retrieve content data that will be used to choose the right product in the appropriate product filter. Usually, the selection is not made using a good and measured system so that the selection of product content is only based on parts that are not in accordance with what is seen or subjective. However, if analyzed using a good and measurable system will produce an objective product content and can have a positive impact on users because the selection is based on factual data. The purpose of this research is to analyze the potential of the affiliate marketplace by combining cosine similarity with vision-based page segmentation. This is a new breakthrough made for optimization to get the best content in accordance with the required criteria. This work will produce a number of product recommendations that are appropriate for publication and then made use of for comparison that matches the required criteria. At the limited evaluation stage, the performance of the proposed model obtained satisfactory results, in which 5 queries tested were all as expected.

Automatic Detection of Hijaiyah Letters Pronunciation using Convolutional Neural Network Algorithm Yana Aditia Gerhana; Aaz Muhammad Hafidz Azis; Diena Rauda Ramdania; Wildan Budiawan Dzulfikar; Aldy Rialdy Atmadja; Deden Suparman; Ayu Puji Rahayu
JOIN (Jurnal Online Informatika) Vol 7 No 1 (2022)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v7i1.882

Abstractâ€” Speech recognition technology is used in learning to read letters in the Qur'an. This study aims to implement the CNN algorithm in recognizing the results of introducing the pronunciation of the hijaiyah letters. The pronunciation sound is extracted using the Mel-frequency cepstral coefficients (MFCC) model and then classified using a deep learning model with the CNN algorithm. This system was developed using the CRISP-DM model. Based on the results of testing 616 voice data of 28 hijaiyah letters, the best value was obtained for accuracy of 62.45%, precision of 75%, recall of 50% and f1-score of 58%.

Diagnosis of Asthma Disease and The Levels using Forward Chaining and Certainty Factor Mohamad Irfan; Pebri Alkautsar; Aldy Rialdy Atmadja; Wildan Budiawan Zulfikar
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 6 No 5 (2022): Oktober 2022
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v6i5.4123

Asthma disease is a major global health issue that affects at least 300 million people worldwide. Even for clinicians working in emergency rooms, predicting the severity of asthma is difficult. Predicting the intensity of an asthma attack is much more challenging because it is dependent on several factors, including the person's illness's features and severity. Forward Chaining and Certainty Factor algorithms can be implemented to diagnose the degree of asthma control, so the consultation process through the system becomes more detailed. The expert system can be used as an initial reference for the diagnosis process. The forward Chaining algorithm is useful for reasoning, starting from a fact to a solution. On the other hand, the Certainty Factor algorithm is used to provide a level of confidence in the conclusions by generating from the Forward Chaining algorithm. The research implemented several phases as follows analysis, data preparation, modeling, and evaluation. On evaluation, this research conduct three stages and tested using 80 medical record data. The result of the study has produced an expert system and generated an accuracy level of 65%, a precision value of 58.3%, and a recall also produced 57.13%. Therefore, the Chaining and Certainty Factor performs reasonably well in the diagnosis of asthma disease.

Automatic Detection of Hijaiyah Letters Pronunciation using Convolutional Neural Network Algorithm Yana Aditia Gerhana; Aaz Muhammad Hafidz Azis; Diena Rauda Ramdania; Wildan Budiawan Dzulfikar; Aldy Rialdy Atmadja; Deden Suparman; Ayu Puji Rahayu
JOIN (Jurnal Online Informatika) Vol 7 No 1 (2022)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v7i1.882

Abstractâ€” Speech recognition technology is used in learning to read letters in the Qur'an. This study aims to implement the CNN algorithm in recognizing the results of introducing the pronunciation of the hijaiyah letters. The pronunciation sound is extracted using the Mel-frequency cepstral coefficients (MFCC) model and then classified using a deep learning model with the CNN algorithm. This system was developed using the CRISP-DM model. Based on the results of testing 616 voice data of 28 hijaiyah letters, the best value was obtained for accuracy of 62.45%, precision of 75%, recall of 50% and f1-score of 58%.

Implementasi Algoritma K-Nearest Neighbor (KNN) untuk Analisis Sentimen Pengguna Aplikasi Tokopedia Lillah, M. Rival Ridautal Lillah; Maylawati, Dian Sa’adillah; Zulfikar, Wildan Budiawan; Uriawan, Wisnu; Wahana, Agung
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 2 No. 2 (2023): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar

A marketplace is a platform where sellers can come together and sell their goods or services to customers without physical meetings. In the past few decades, marketplaces have become the most popular platform for business sellers to sell their products. Becoming the number 1 marketplace in Indonesia with the most visitors on average is the right marketplace in 2023, namely Tokopedia. However, most people are skeptical of products they have never purchased or used. User reviews play an important role in product marketing, especially on Tokopedia. Reviews help potential customers build trust in the products and services offered by the seller. To analyze reviews quickly and precisely, a sentiment analysis process is needed. Natural Processing Language (NLP) and text mining algorithms are used to classify reviews as positive, or negative. One of the methods used is the K-Nearest Neighbor (KNN) algorithm, which is used to classify Tokopedia user reviews in the Play Store and App Store. The dataset consists of 1000 comment data from the Play Store and 1000 data from the App Store. A total of 2000 comments consisting of 2 labels, namely positive and negative for modeling. Meanwhile, for testing, there were 885,092 comments from the Play Store and 4000 comments from the App Store. Total 889,092 for unlabeled test data. The prediction results on the app store dataset show that there are 97.0% positive label predictions and only 3.0% negative label predictions. Abstrak Marketplace adalah platform tempat penjual dapat berkumpul dan menjual barang atau jasa mereka kepada pelanggan tanpa pertemuan fisik. Dalam beberapa dekade terakhir, pasar telah menjadi platform paling populer bagi penjual bisnis untuk menjual produk mereka. Menjadi marketplace nomor 1 di Indonesia dengan rata-rata pengunjung terbanyak adalah marketplace yang tepat di tahun 2023 yaitu Tokopedia. Namun, kebanyakan orang skeptis terhadap produk yang belum pernah mereka beli atau gunakan. Ulasan pengguna memegang peran penting dalam pemasaran produk, terutama di Tokopedia. Ulasan membantu calon pelanggan membangun kepercayaan terhadap produk dan layanan yang ditawarkan oleh penjual. Untuk menganalisis ulasan dengan cepat dan tepat, diperlukan proses analisis sentimen. Natural Processing Language (NLP) dan algoritma text mining digunakan untuk mengklasifikasikan ulasan sebagai positif, atau negatif. Salah satu metode yang digunakan adalah algoritma K-Nearest Neighbor (KNN), yang digunakan untuk mengklasifikasikan ulasan pengguna Tokopedia di play store dan app store. Dataset terdiri dari 1000 data komentar dari play store dan 1000 data dari app store. Total 2000 komentar yang terdiri dari 2 label yaitu positif dan negatif untuk pemodelan. Sedangkan untuk pengujian 885.092 komentar dari play store dan 4000 komentar dari app store. Total 889.092 untuk data pengujian yang belum dilabeli. Hasil prediksi pada dataset app store menunjukkan terdapat 97,0% prediksi label positif dan hanya 3,0% prediksi label negatif.

Long Short Term Memory Approach for Sentiment Analysis on COVID-19 Vaccination Policy Tubagus Putra, Fauzan Herdika; Zulfikar, Wildan Budiawan; Lukman, Nur
CoreID Journal Vol. 2 No. 2 (2024): July 2024
Publisher : CV. Generasi Intelektual Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60005/coreid.v2i2.33

COVID-19 vaccination is one of the efforts to reduce the spread of COVID-19 and reduce the impact or severe symptoms of COVID-19. On social media, many Indonesians have expressed their opinions regarding the COVID-19 vaccine. With technology, we can classify Indonesian public opinion on the COVID-19 vaccine on social media, including pros or cons. Sentiment analysis using the LSTM (Long Short Term Memory) algorithm is one way. The data that has been taken will go through a cleaning and weighting process using Word2Vec before entering the LSTM algorithm. With the evaluation method of the K-Fold Cross Validation model, we can determine the performance of this LSTM algorithm. The results of the performance of this LSTM model show an average accuracy of 74.1% and have the best accuracy in the 4th Fold, which is 81%. The data that has been taken will be tested on this best model, and the results of the sentiment analysis of Indonesian public opinion on the COVID-19 vaccine are 49.4% Positive and 50.6% Negative.

Permodelan Topik pada Layanan Akademik Perguruan Tinggi dengan Menggunakan N-Gram Rialdy Atmadja, Aldy; Naufal Rahman, Muhammad; Zulfikar, Wildan Budiawan
INTERNAL (Information System Journal) Vol. 7 No. 2 (2024)
Publisher : Masoem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/internal.v7i2.1192

Automation of generating information in academic services are expected to provide convenience in providing academic services to students. Relevant topics can be extracted from social media by calculating the frequency of words asked by social media users. The research focuses on generating question topics on academic services at universities. Topic extraction are obtained through data taken from Instagram social media, so that relevant topics are obtained to get information that is most frequently asked by the public. The N-Gram and Term Frequency are approach to extract the topic. The initial stages in this study include conducting Web Scraping taken from Instagram social media. In this study, text preprocessing was carried out in several stages, namely cleansing, casefolding, stopwords removal and tokenizing, and stemming. The N-Gram approach is carried out by comparing three types, namely unigrams, bigrams and trigrams. The results obtained in this study prove that the bigram produces relevant word pairs in determining academic service topics on social media. This approach produces word pairs that are relevant to academic service topics including graduation list, paying UKT, independent admission, SPANPTKIN and independent test.

A Deep Learning Approach Using VGG16 to Classify Beef and Pork Images Zulfikar, Wildan Budiawan; Angelyna, Angelyna; Irfan, Mohamad; Atmadja, Aldy Rialdy; Jumadi, Jumadi
JOIV : International Journal on Informatics Visualization Vol 9, No 2 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.2.2848

There are 87.2% of the Muslim population in Indonesia, which makes Indonesia one of the countries with the largest Muslim population in the world. As a Muslim, it is supposed to carry out and stay away from the commands that Allah SWT commands, one of which is in QS. Al-maidah:3, one of the commands in the verse is not to consume haram food such as pork. Even so, it turns out that many traders in Indonesia still cheat to get more significant profits, namely by counterfeiting beef and pork. The lack of public knowledge supports this situation to differentiate between the two types of meat. Therefore, the classification process is used to distinguish the two kinds of meat using the convolutional neural network approach with VGG16 with several preprocessing stages. Two primary stages are used during the preprocessing stage: scaling and contrast enhancement. The VGG16 algorithm gets very good results by getting an accuracy value of 99.6% of the test results using 4,500 images for training data and 500 images for testing data. To compare the effectiveness of these techniques, it is recommended to use alternative CNN architectures, such as mobilNet, ResNet, and GoogleNet. More investigation is also required to gather more varied datasets, enabling the ultimate goal to achieve the best possible categorization, even when using cell phone cameras or with dim or fuzzy photos.

ANALISIS DAN EVALUASI : PERBANDINGAN KEAMANAN CMS WORDPRESS DAN JOOMLA DENGAN KONFIGURASI STANDAR Noorsyahbannie, Mochamad Najib Budi; Uriawan, Wisnu; Zulfikar, Wildan Budiawan
The Indonesian Journal of Computer Science Vol. 14 No. 1 (2025): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i1.4716

Since the industrial era 4.0, many organizations have chosen to switch to using Content Management Systems (CMS) to manage websites. This CMS makes it easy to create, design, and organize content without having to have programming knowledge. However, CMS is also vulnerable to cyber attacks such as XSS and SQL Injection. This study was conducted to analyze and evaluate vulnerabilities in WordPress and Joomla CMS through penetration testing and vulnerability scanning methods. The use of various tools such as OWASP ZAP, Burpsuite, Joomscan, WPScan, and Searchsploit were used to analyze these vulnerabilities. The results of the study showed that Joomla CMS with standard configuration did not show significant vulnerabilities, while in WordPress a stored type XSS vulnerability was found in the comment feature. Searchsploit also identified vulnerabilities in both CMSs originating from thirdparty plugins. The results of this study highlight the importance of strict input and configuration sanitation and regular maintenance on CMS to reduce the risk of exploitation.

Title

Found 11 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 11 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 11 Documents
Search