Claim Missing Document
Check
Articles

Topic Classification of Islamic Questionand Answer Using Naive Bayes Classifier Naufal Furqan Hardifa; Kemas Muslim Lhaksmana; Jondri Jondri
Indonesia Journal on Computing (Indo-JC) Vol. 4 No. 2 (2019): September, 2019
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2019.4.2.346

Abstract

Topic classification is one of the most important components in an automatic Islamic question-answering system, which is capable of automatically providing the most relevant answers given a question about the Islamic issue. In our research, the Islamic question-answering system to be built collects existing Islamic questions and answers from trusted online Islamic consultation websites. To speed up the search for finding the appropriate answers, each Q & A entry should be classified into a topic. However, the question-answering system cannot directly adopt the topic classes provided by the online Islamic consultation websites, because different websites use different classifications. Since the number of Q & A entries could reach tenth thousands, an automatic topic classification method is required. In this paper, a naive Bayes classifier is implemented to classify Q & A entries. The classifier gives a satisfying result with 0.88 precision.
Deteksi Pola Ambiguitas Struktural pada Spesifikasi Kebutuhan Perangkat Lunak menggunakan Pemrosesan Bahasa Alami Chlaudiah Julinar Soplero Lelywiary; Sri Widowati; Kemas Muslim Lhaksamana
Indonesia Journal on Computing (Indo-JC) Vol. 4 No. 3 (2019): December, 2019
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2019.4.3.355

Abstract

Spesifikasi Kebutuhan Perangkat Lunak (SKPL) merupakan dokumen yang dihasilkan dari proses rekayasa kebutuhan dan memegang peranan penting dalam pengembangan perangkat lunak. Sekitar 87.7% dokumen SKPL ditulis menggunakan bahasa alami. Masalah terbesar dalam penulisan dengan bahasa alami adalah kesalahan interpretasi yang disebabkan karena terdapat kata-kata yang ambigu. Jika terjadi ambigu dan tidak dideteksi secepat mungkin, maka kesalahan interpretasi dapat mengarah pada hasil perangkat lunak tidak sesuai dengan kebutuhan pengguna. Hal ini membuat masalah ambigu dalam SKPL sangat penting untuk ditangani. Sudah terdapat berbagai penelitian mengenai solusi penanganan ambigu dalam SKPL, dan hampir sebagian besar menggunakan SKPL dalam Bahasa Inggris. Penelitian ini bertujuan untuk mendeteksi ambigu yang terjadi akibat struktur pernyataan kebutuhan perangkat lunak yang salah pada SKPL dalam Bahasa Indonesia. Adapun metode yang diusulkan adalah pola bahasa alami berdasarkan Part-of-Speech Tag Hidden Markov Model-Viterbi, dan pola tersebut dideteksi dengan Regular Expression Parsing. Pola bahasa alami yang diusulkan dievaluasi dengan nilai indeks Kappa. Hasil dari analisis pola bahasa alami memiliki nilai indeks Kappa tertinggi sebesar 0.9139, yang berarti ahli sangat sepakat terhadap hasil deteksi ambigu struktural dengan pola bahasa alami.
LBP Advantages over CNN Face Detection Method on Facial Recognition System in NOVA Robot Luqman Bramantyo Rahmadi; Kemas Muslim Lhaksmana; Donny Rhomanzah
Indonesia Journal on Computing (Indo-JC) Vol. 5 No. 2 (2020): September, 2020
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2020.5.2.456

Abstract

Network-optimized virtual assistant (NOVA) is a robot developed by Bandung Techno Park (BTP) that can interact with humans for various purposes, such as a receptionist robot. NOVA robot is still in development and one of the main focuses is adding face recognition features so that the robot can actively greet and interact with humans. Therefore, we propose a face recognition and tracking system based on neural networks. This system is developed using the Google FaceNet feature extraction method. Previously, face detection in NOVA robot was implemented by employing the multi-task cascaded convolutional networks (MTCNN) method, whereas face tracking on the system was realized by using the modification of the MOSSE object tracking method. However, we found that the implementation of MTCNN in NOVA robot cannot run better than 30 fps. Therefore, this paper aims to solve this issue by investigating conventional face detection methods that could outperform MTCNN in this regard. Tests conducted on the ChokePoint dataset demonstrates that the system with LBP can achieve 30.44 fps framerate with a precision of 95% and recall of 83%. The test results show that LBP is not only better than MTCNN in identifying faces but also more efficient to compute.
Movie Recommendation Using Conversational Mechanism and Knowledge Based Filtering Marendra Septianta; Z. K. Abdurahman Baizal; Kemas Muslim Lhaksmana
Journal of Data Science and Its Applications Vol 3 No 2 (2020): Journal of Data Science and Its Applications
Publisher : Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/jdsa.2020.3.49

Abstract

Conversational recommender system created for helping users in searching information in a domain by using conversational mechanism. These systems help user to get recommendation by selecting items that most suitable to user’s preference by asking user needed. The recommendations generated by eliciting user’s experience e.g. his favourite movies, actor and director and then gives the item that match their interest. There are many methods to get the suitable recommendation that match the user’s preference. In this paper, we use ontology which represents knowledge to get result of recommendation that fit to user preference by using knowledge-based filtering to determine the user’s need. Our system has been implemented for movie domain. We test our system performance by studying user's perception.
Meningkatkan Pengambilan Dokumen dengan Koreksi Ejaan untuk Hadits yang Lemah dan Palsu Terjemahan Bahasa Indonesia muhammad zaky ramadhan; Kemas Muslim Lhaksmana
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 4 No 3 (2020): Juni 2020
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (315.878 KB) | DOI: 10.29207/resti.v4i3.1913

Abstract

Hadith has several levels of authenticity, among which are weak (dhaif), and fabricated (maudhu) hadith that may not originate from the prophet Muhammad PBUH, and thus should not be considered in concluding an Islamic law (sharia). However, many such hadiths have been commonly confused as authentic hadiths among ordinary Muslims. To easily distinguish such hadiths, this paper proposes a method to check the authenticity of a hadith by comparing them with a collection of fabricated hadiths in Indonesian. The proposed method applies the vector space model and also performs spelling correction using symspell to check whether the use of spelling check can improve the accuracy of hadith retrieval, because it has never been done in previous works and typos are common on Indonesian-translated hadiths on the Web and social media raw text. The experiment result shows that the use of spell checking improves the mean average precision and recall to become 81% (from 73%) and 89% (from 80%), respectively. Therefore, the improvement in accuracy by implementing spelling correction make the hadith retrieval system more feasible and encouraged to be implemented in future works because it can correct typos that are common in the raw text on the Internet.
Identifying Emotion on Indonesian Tweets using Convolutional Neural Networks Naufal Hilmiaji; Kemas Muslim Lhaksmana; Mahendra Dwifebri Purbolaksono
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 3 (2021): Juni 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (504.597 KB) | DOI: 10.29207/resti.v5i3.3137

Abstract

especially with the advancement of deep learning methods for text classification. Despite some effort to identify emotion on Indonesian tweets, its performance evaluation results have not achieved acceptable numbers. To solve this problem, this paper implements a classification model using a convolutional neural network (CNN), which has demonstrated expected performance in text classification. To easily compare with the previous research, this classification is performed on the same dataset, which consists of 4,403 tweets in Indonesian that were labeled using five different emotion classes: anger, fear, joy, love, and sadness. The performance evaluation results achieve the precision, recall, and F1-score at respectively 90.1%, 90.3%, and 90.2%, while the highest accuracy achieves 89.8%. These results outperform previous research that classifies the same classification on the same dataset.
Classifying Quranic Verse Topics using Word Centrality Measure Ferdian Yulianto; Kemas Muslim Lhaksmana; Danang Triantoro Murdiansyah
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 3 (2021): Juni 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (460.166 KB) | DOI: 10.29207/resti.v5i3.3171

Abstract

Muslims believe that, as the speech of Allah, The Quran is a miracle that has specialties in itself. Some of the specialties that have studied are the regularities in the number of letters, words, vocabularies, etc. In the past, the early Islamic scholars identify these regularities manually, i.e. by counting the occurrence of each vocabulary by hand. This research tackles this problem by utilizing centrality in quranic verse topic classification. The goal of this research is to analyze the effect of The Quran word centrality measure on the topic classification of The Quran verses. To achieve this objective, the method of this research is constructing the Quran word graph, then the score of centralities included as one of the features in the verse topic classification. The effect of centrality is observed along with support vector machine (SVM) and naïve Bayes classifiers by performing two scenarios (with stopword and without stopword removal). The result shows that according to the centrality measure the word “الله” (Allah) is the most central in The Quran. The performance evaluation of the classification models shows that the use of centrality improves the hamming loss score from 0.43 to 0.21 on naïve Bayes classifier with stopword removal. Finally, both of classification method has a better performance in word graph that use stopword removal.
IMPLEMENTASI ALIGNMENT POINT PATTERN PADA SISTEM PENGENALAN SIDIK JARI MENGGUNAKAN TEMPLATE MATCHING Try Moloharto; Said Al Faraby; Kemas Muslim Lhaksmana; Adiwijaya Adiwijaya; Muhammad Yuslan Abu Bakar
JURNAL TEKNOLOGIA Vol 1 No 2 (2019): Teknologia
Publisher : Aliansi Perguruan Tinggi Badan Usaha Milik Negara (APERTI BUMN)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (886.448 KB)

Abstract

Fingerprints is one of biometric identification system. This is because fingerprints have unique and different pattern in every human, so identification using fingerprints can no longer be doubted. But, manual fingerprint recognition by human hard to apply because of the complex pattern on it. Therefore, an accurate fingerprint matching system is needed. There are 3 steps needed for fingerprint recognition system, namely image enhancement, feature extraction, and matching. In this study, crossing number method is used as a minutiae extraction process and template matching is used for matching. We also add alignment point pattern process added, which are ridge translation and rotation to increase system performance. The system provide a performance of 18,54% with a matching process without alignment point pattern, and give performance of 67,40% by adding alignment point pattern process.
Verse Search System for Sound Differences in the Qur’an Based on the Text of Phonetic Similarities Agni Octavia; Moch Arif Bijaksana; Kemas Muslim Lhaksmana
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 9, No 3 (2020): NOVEMBER
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v9i3.935

Abstract

Al-Qur'an has a lot of content, so the system of searching for verses of the Al-Qur’an is needed because if it is done manually it will be difficult. One of the search systems for the verses of the Al-Qur'an in accordance with Indonesia’s pronunciation is Lafzi. The Lafzi system can search for verse fragments using keywords in Latin characters. Lafzi has been developed into Lafzi +, wherein the Lafzi + system can be used to search verses of the Al-Qur’an with different sounds on stop signs. However, the Lafzi+ can only overcome the difference in the sound of the stop sign and cannot be applied throughout Al-Qur’an. Based on these problems, the system needs to be developed to overcome the differences in sound in the middle of the verse and can be applied throughout the Al-Qur’an. The method used in the process of searching for the verse is the N-gram method. The N-gram used in this research is trigram. The process flow of this system is first normalized in the phonetic coding process after normalized then tokenization of trigrams and then trigrams are matched between the query and the corpus and entered into the ranking process to get an output candidate. In the making process, the LIS (Longest Increasing Subsequence) method is used to get an orderly and strict trigram sequence. The highest order score will be the top output. The results of this study obtained a recall value of 100% and MAP of 87%.
Qur’an Search System for Handling Cross Verse Based on Phonetic Similarity Intan Khairunnisa Fitriani; Moch Arif Bijaksana; Kemas Muslim Lhaksmana
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol 10, No 1 (2021): MARCH
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v10i1.986

Abstract

The number of verses in the Qur'an that is not small will be difficult and time consuming if done manually. Building a search system in the Qur'anic verse using the Indonesian Arabic-Latin equivalent will be very helpful for the Muslim community in Indonesia, especially for those who are not familiar with Arabic writing. In this study, a verse search system will be built on the Al-Qur'an based on phonetic similarity, more details about the handling of the verses in the Al-Qur'an. The system was built using the Jaro-Winkler algorithm to calculate the value of similarity and using the N-Grams algorithm for ranking documents. The same study has been done before with the name Lafzi +, with MAP 90% and 93% recall. In previous studies cases such as nun wiqoyah at the end of the verse could not be handled, so the system could not handle the search for the entire Qur'an. In addition, in the previous system the application of the Jaro-Winkler method to calculate the value of similarity has also not been fully implemented. So to complete the previous research, in this study added rules other than pre-existing rules so that they can handle nun wiqoyah at the end of the verse. By applying the Jaro-Winkler method to calculate the value of similarity and N-Grams for ranking documents and adding nun wiqoyah rules, this system generates 94% MAP and 92% recall. The results of this study indicate an increase in MAP, this shows that this system can improve the accuracy of systems that have been built before.
Co-Authors Abdurrahman, Azzam Achmad Salim Aiman Adelia, Dila Adhyaksa Diffa Maulana Aditya Eka Wibowo Aditya Gifhari Soenarya Adiwijaya Aghi Wardani Agni Octavia Agus Kusnayat Ahmad Syafiq Abiyyu Ahmad, Alif Faidhil Al Faraby, Said Alberi Meidharma Fadli Hulu Amalia Elma Sari Andiani, Annisa Dwi Angraini, Nadya Arda Anisa Herdiani Annisa Miranda Arini Rohmawati Athallah, Muhammad Rafi Aura Sukma Andini Bayu Muhammad Iqbal Bonar Panjaitan Brata Mas Pintoko Chandra Jaya Riadi Chlaudiah Julinar Soplero Lelywiary Choirulfikri, Muhammad Rizqi Damayanti, Lisyana Dana Sulitstyo Kusumo Danang Triantoro Murdiansyah David Winalda Delva, Dwina Sarah Deni Saepudin Denny Darlis Dewantara, Muhammad Pascal Dida Diah Damayanti Didit Adytia dina juni restina Dino Caesaron Donni Richasdy Donny Rhomanzah Dzidny, Dimitri Irfan Edgarsa Bramandyo Widyarto Eki Rifaldi Eko Darwiyanto Ela Nadila Emrald Emrald Erwin Budi Setiawan Fakhrana Kurnia Sutrisno Farisi, Kamaludin Hanif Fathih Adawi Ahmad Ferdian Yulianto Fhira Nhita Ghina Annisa Shabrina Guido Tamara Haga Simada Ginting Harmandini, Keisha Priya Haura Athaya Salka Herodion Simorangkir Hutama, Nanda Yonda Ika Puspita Dewi Intan Khairunnisa Fitriani Iqmal Lendra Faisal Amien Irgi Aditya Rachman Isabella Vichita Kacaribu Isman Kurniawan Jofardho Adlinnas Jondri Jondri Jordan, Brilliant Kamaludin Hanif Farisi Kautsar Ramadhan Sugiharto Lukito Agung Waskito Luqman Bramantyo Rahmadi Luthfi, Muhammad Faris M. Mahfi Nurandi Karsana Mahendra Dwifebri Mahendra Dwifebri Purbolaksono Mahendra, Muhammad Hafizh Marendra Septianta Marozi, Ericho Mehdi Mursalat Ismail Meira Reynita Putri Mira Rahayu Moch Arif Bijaksana Mohamad Reza Syahziar Muhammad Abdurrohman Al Fatih Muhammad Adzhar Amrullah Muhammad Arif Kurniawan Muhammad Ilham Maulana Muhammad Rifqi Fauzi Ramdhani Muhammad Yuslan Abu Bakar Muhammad Zaid Dzulfikar muhammad zaky ramadhan Muhammad Zidny Naf'an Murman Dwi Praseti Musyafa’noer Sandi Pratama Nanda Yonda Hutama Naufal Furqan Hardifa Naufal Hilmiaji Naufal Rasyad Nibras Syihabil Haq Octaryo Sakti Yudha Prakasa Okky Zoellanda A. Tane Pamungkas, Danit Hafiz Praja, Yudhistira Imam Purwita, Naila Iffah Putri, Arla Sifhana Putrisia, Denada R. Fajrika hadnis Putra Rafi Hafizhni Anggia Rafisa Arif Irfan Rahadian, Muhammad Rafi Rastim Rastim Rayhan, Muhammad Aditya Resky Nadia Rizki Luthfan Azhari Rizki Nurhaliza Harahap Rizky Ahmad Saputra Rizky, Fariz Muhammad Salman Farisi Setya Hadi Seno Adi Putra Seto Sumargo Siddiq, Ikhsan Maulana Sindi Fatika Sari Sri Utami Sri Widowati Sukmawan Pradika Janusange Santoso Suwaldi Mardana Syadzily , Muhammad Hasan Tri Widarmanti Try Moloharto Try Moloharto Vitalis Emanuel Setiawan Wardhani, Fitri Herinda Widi Astuti Widi Astuti Youga Pratama Yuliant Sibaroni Yusuf Nugroho Doyo Yekti Zaena, Siffa Zaenal Abidin ZK Abdurahman Baizal Zulkarnaen, Imran