Article Per Year (5 Year)
p-Index From 2021 - 2026
8.717
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering IAES International Journal of Artificial Intelligence (IJ-AI) Jurnal Informatika Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Jurnal Ilmu Komputer dan Informasi Jurnal Teknik ITS IPTEK Journal of Science IPTEK Journal of Proceedings Series IPTEK The Journal for Technology and Science Techno.Com: Jurnal Teknologi Informasi MATICS : Jurnal Ilmu Komputer dan Teknologi Informasi (Journal of Computer Science and Information Technology) Jurnal Buana Informatika TELKOMNIKA (Telecommunication Computing Electronics and Control) Bulletin of Electrical Engineering and Informatics JUTI: Jurnal Ilmiah Teknologi Informasi Jurnal Ilmiah Mikrotek Jurnal Simantec Jurnal Ilmiah Kursor Scan : Jurnal Teknologi Informasi dan Komunikasi Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Edukasi dan Penelitian Informatika (JEPIN) International Journal of Advances in Intelligent Informatics Scientific Journal of Informatics Journal of Information Systems Engineering and Business Intelligence Register: Jurnal Ilmiah Teknologi Sistem Informasi EMITTER International Journal of Engineering Technology Jurnal Inspiration Briliant: Jurnal Riset dan Konseptual Journal of Development Research Informatika Mulawarman: Jurnal Ilmiah Ilmu Komputer Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) International Journal of Artificial Intelligence Research Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi INTEGER: Journal of Information Technology Seminar Nasional Teknologi Informasi Komunikasi dan Industri JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Jurnal ULTIMATICS Explore IT : Jurnal Keilmuan dan Aplikasi Teknik Informatika Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI) CCIT (Creative Communication and Innovative Technology) Journal SPIRIT Progresif: Jurnal Ilmiah Komputer ILKOMNIKA: Journal of Computer Science and Applied Informatics Indonesian Journal of Electrical Engineering and Computer Science Journal of Intelligent Computing and Health Informatics (JICHI) Jurnal Teknik Informatika (JUTIF) Journal of Technology and Informatics (JoTI) Melek IT: Information Technology Journal Jurnal Nasional Teknik Elektro dan Teknologi Informasi Journal Research of Social Science, Economics, and Management Sewagati RESLAJ: Religion Education Social Laa Roiba Journal Jurnal Indonesia : Manajemen Informatika dan Komunikasi
Chastine Fatichah
Departemen Teknik Informatika Institut Teknologi Sepuluh Nopember Surabaya
Religion Arts Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics Mechanical Engineering Medicine & Pharmacology Public Health Social Sciences Other

Published : 150 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 150 Documents
Search

 11   12   13   14   15 
Handling Imbalance in Javanese Manuscript Character Dataset using Skeleton-based Balancing Generative Adversarial Networks Faizin, Muhammad 'Arif; Suciati, Nanik; Fatichah, Chastine
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 4 (2025): August 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i4.6572

Abstract

Javanese script is an important part of Indonesia’s cultural heritage, representing cultural values from the past. However, recognizing and classifying Javanese characters within manuscripts is challenging due to the limited availability of data and uneven distribution of character classes. The decline in formal use of Javanese script has drastically reduced the pool of manuscript samples, causing certain characters to appear rarely and skewing class frequencies. Existing methods that utilize Generative Adversarial Networks (GANs) attempt to address this problem. However, they often struggle to generate characters that are both consistent and visually accurate in terms of structural details. To address these issues, this study introduces a skeleton-based balancing GAN (SkelBAGAN), which improves the structural details of the previous method for generating characters. The proposed method introduces three main enhancements: (i) a layer for extracting the character skeleton structure, (ii) an optimized pretrained network using an autoencoder for learning the skeleton distribution, and (iii) refinement of the evaluation function, preserving both the distribution and structural fidelity in the adversarial process. The performance of the proposed model is evaluated against previous methods using the Fréchet Inception Distance (FID) to assess distribution quality and the Structural Similarity Index Measure (SSIM) to evaluate structural fidelity. The results indicate that the proposed methods outperform previous methods in balancing the FID and SSIM metrics. The integration of all enhancements in SkelBAGAN achieves the lowest FID, indicating improved generative quality while maintaining competitive SSIM values. The qualitative study indicates that SkelBAGAN outperforms previous methods in character generation. These results highlight how the skeleton-based improvement of the quality of generated characters enhances the recognition performance for underrepresented Javanese characters in imbalanced datasets. Ultimately, this work contributes to the broader effort to preserve the Javanese script as a vital element of Indonesia’s cultural identity.
Klasifikasi Kemampuan Mahasiswa Berdasarkan Automatic Essay Scoring terhadap Jawaban Essay Ujian Kompetensi dengan Metode Machine Learning Hakiki, Muhammad; Fatichah, Chastine
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 6 No. 3 (2025): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v6i3.1325

Abstract

Manually assessing student answers and grouping student abilities is very time-consuming. Therefore, a system is needed that can automatically assess student essay answers and group student abilities. This study proposes a method for classifying student abilities based on the Automatic Essay Scoring value using the LSTM method and several classification methods. The number of datasets used in this study was 98 students, while the questions tested in this competency exam were 200 questions. The parameters used for LSTM are student answers. The benefit of this study is to find out which students have mastered the lecture and which students have not mastered the lecture. The results of this study indicate that the LSTM method successfully provides automatic essay assessment with an accuracy value of 0.9, while the most superior classification method is the Decision Tree method with the ROS oversampling method, which is 0.654.
Kombinasi Metode Rule-Based dan N-Gram Stemming untuk Mengenali Stemmer Bahasa Bali Subali, Made Agus Putra; Fatichah, Chastine
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 6 No 2: April 2019
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (135.168 KB) | DOI: 10.25126/jtiik.2019621105

Abstract

Proses untuk mengekstraksi kata dasar dari kata berafiks dikenal dengan istilah stemming yang bertujuan meningkatkan recall dengan mereduksi variasi kata berafiks ke dalam bentuk kata dasarnya. Penelitian terdahulu tentang stemming bahasa Bali pernah dilakukan menggunakan metode rule-based, tapi afiks yang diluluhkan hanya prefiks dan sufiks, sedangkan variasi afiks lain tidak diluluhkan, seperti infiks, konfiks, simulfiks, dan kombinasi afiks. Penelitian tentang stemming menggunakan pendekatan rule-based telah diterapkan di berbagai bahasa yang berbeda. Metode rule-based memiliki kelebihan jika diterapkan pada domain yang sederhana, maka rule-based mudah untuk diverifikasi dan divalidasi, tapi memiliki kelemahan saat diterapkan pada domain dengan level kompleksitas yang tinggi, apabila sistem tidak dapat mengenali rules, maka tidak ada hasil yang diperoleh. Untuk mengatasi kelemahan stemming menggunakan rule-based, kami menggunakan metode n-gram stemming, dimana kata berafiks dan kata dasar diubah ke bentuk n-gram, kemudian tingkat kemiripan antara n-gram kata berafiks dan n-gram kata dasar diukur menggunakan metode dice coefficient, apabila tingkat kemiripannya memenuhi nilai ambang batas yang ditentukan, maka kata dasar yang dibandingkan dengan kata berafiks ditampilkan. Pada penelitian ini, kami mengembangkan metode stemmer yang meluluhkan seluruh variasi afiks pada bahasa Bali dengan mengombinasikan pendekatan rule-based dan metode n-gram stemming. Berdasarkan pengujian yang telah dilakukan untuk kesepuluh query metode yang diusulkan memperoleh rerata akurasi stemming lebih baik 96,67% dari metode terdahulu 75%, sedangkan untuk kelima query metode n-gram stemming dapat mengenali beberapa kata berafiks diluar rules. Penelitian berikutnya, kami akan memperhatikan semantik setiap kata dan tahap validasi menggunakan aplikasi text mining.AbstractA process for extracting a stem word from the inflected word is known as stemming which aims to increase recall by reducing the variation of the inflected word into its stem word form. Previous research on stemming the Balinese language has been done using the rule-based method, but the affixes that are removed are only prefixes and suffixes, while other variations of affixes are not removed, such as infixes, confixes, simulfiks, and combinations of affixes. Research on stemming using the rule-based approach has been applied in a variety of different languages. The rule-based method has advantages when applied to a simple field, rule-based is easy to verify and validate, but has weaknesses when applied to domains with a high level of complexity, if the system cannot recognize rules, no results are obtained. To overcome the stemming weaknesses using rule-based, we use the n-gram stemming method, where the inflected word and stem word are converted to the n-gram form, then the level of similarity between the n-gram of the inflected word and the stem word is measured using the dice coefficient method, when the level of similarity meets the defined threshold value, then the stem word is displayed. In this study, we developed a stemmer method that removes all variations of affixes in the Balinese language by combining the rule-based approach and the n-gram stemming method. Based on the experiments for the ten queries the proposed method get 96,67% stemming accuracy than the previous method 75%, while for the five queries for the n-gram stemming method can recognize some inflected words outside the rules. The next study, we will pay attention to the semantics of each word and the validation stage using text mining application.
Evaluasi Kombinasi Hipernin dan Sinonim untuk Klasifikasi Kebutuhan Non-Functional Berbasis ISO/IEC 25010 Hakim, Lukman; Rochimah, Siti; Fatichah, Chastine
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 6 No 5: Oktober 2019
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2870.836 KB) | DOI: 10.25126/jtiik.2019651422

Abstract

Kebutuhan non-fungsional dianggap mampu mendukung keberhasilan pengembangan perangkat lunak. Namun, kebutuhan non-fungsional sering diabaikan selama proses pengembangan perangkat lunak. Hal ini dikarenakan kebutuhan non-fungsional sering tercampur dengan kebutuhan fungsional. Disamping itu, standar kualitas yang beragam menyebabkan kebingungan dalam menentukan aspek kualitas. Pendekataan yang ada menggunakan ISO/IEC 9126 sebagai referensi untuk mengukur aspek kualitas. ISO/IEC 9126 merupakan standar lama yang dirilis pada tahun 2001. Peneliti sebelumnya mengungkapkan ambiguitas dalam enam sub-atribut pada struktur hirarkis ISO/IEC 9126. Hal ini menimbulkan keraguan serius tentang validitas standar secara keseluruhan. Oleh karena itu, standar kualitas yang digunakan sebagai referensi untuk mengukur aspek kualitas pada penelitian ini adalah ISO/IEC 25010. Selain itu, penelitian ini juga mengusulkan suatu sistem untuk mengidentifikasi aspek kualitas kebutuhan non-fungsional dengan menggunakan 1 level hipernim dan 20 sinonim yang disebut skenario 1. Skenario ini akan dibandingkan dengan 2 level hipernim dan 9 sinonim pada masing-masing sinonim yang disebut skenario 2. Kedua skenario tersebut akan menghasilkan dua data latih berbeda. Kedua data latih tersebut akan dibandingkan menggunakan dua model pengujian yaitu berdasarkan ground truth pakar dan sistem dengan menggunakan metode klasifikasi KNN dan SVM. Hasil pengujian menunjukkan skenario 1 terbukti memberikan nilai lebih baik dibandingkan skenario 2 pada kedua model pengujian, dimana nilai precision dari ground truth pakar, KNN, dan SVM masing-masing 49.3%, 81.0%, dan 74.6%.Abstract Non-Functional requirements are considered capable of supporting the success of software development. However, non-functional requirements are often ignored during the software development process. This is because the quality aspects of non-functional requirements are often mixed with functional requirements. in addition, the number of diverse quality standards causes confusion in determining quality aspects. The existing approach uses ISO / IEC 9126 as a reference to measure quality aspects. ISO / IEC 9126 is an old standard released in 2001. Previous researchers revealed ambiguity in six sub-attributes on the hierarchical structure of ISO / IEC 9126. This raises serious doubts about the validity of the overall standard. Therefore, the quality standard used as a reference to measure the quality aspects of this study is ISO / IEC 25010. In addition, this study also proposes a system to identify aspects of the quality of non-functional requirements using 1 hypernym level and 20 synonyms called scenario 1. This scenario will be compared with 2 hypernym levels and 9 synonyms in each synonym called scenario 2. Both scenarios will produce two different training data. The two training data will be compared using two testing models ie based on expert ground truth and systems using the KNN and SVM classification methods. The test results showed scenario 1 is proven to provide a better value than scenario 2 in both testing models, where the precision values of expert ground truth, KNN, and SVM  respectively 49.3%, 81.0%, and 74.6%.
Komparasi Kinerja Algoritma C4.5, Gradient Boosting Trees, Random Forests, dan Deep Learning pada Kasus Educational Data Mining Mutrofin, Siti; Machfud, M. Mughniy; Satyareni, Diema Hernyka; Ginardi, Raden Venantius Hari; Fatichah, Chastine
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 7 No 4: Agustus 2020
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2020742665

Abstract

Penentuan jurusan di SMA Negeri 1 Jogoroto, Jombang, Jawa Timur menggunakan kurikulum 2013, di mana penentuan jurusan siswa tidak hanya melibatkan keinginan siswa, tes peminatan yang dilakukan siswa di SMA pada minggu pertama, tetapi juga dilengkapi dengan nilai siswa semasa di SMP (nilai rapor siswa, nilai Ujian Nasional, serta rekomendasi guru Bimbingan Konseling), rekomendasi orang tua siswa. Selama ini, sekolah menggunakan proses konvensional dalam menentukan jurusan, yaitu menggunakan Microsoft Excel, yang cenderung lama serta rawan akan kekeliruan dalam melakukan penghitungan. Penentuan jurusan ini dilakukan setiap awal ajaran baru pada siswa baru kelas X. Rata-rata setiap tahun, sekolah mengelola siswa sejumlah 290 dengan waktu dan sumber daya manusia yang terbatas. Pada penelitian ini, penggunaan algoritma ID3 tidak cocok karena data bertipe numerik, sedangkan ID3 hanya mampu menggunakan data bertipe nomial maupun polinomial, sehingga diganti algoritma C4.5. Namun, beberapa penelitian mengatakan algoritma C4.5 memiliki kinerja kurang bagus dibandingkan algoritma Gradient Boosting Trees, Random Forests, dan Deep Learning. Untuk itu, dilakukan perbandingan antara keempat metode tersebut untuk melihat keefektifannya dalam menentukan jurusan di SMA. Data yang digunakan pada penelitian ini adalah data penerimaan siswa baru tahun ajaran 2018/2019. Hasil dari penelitian ini menunjukkan jika atribut yang digunakan bertipe polinomial dengan Deep Learning memiliki kinerja paling unggul untuk semua algoritma jika menggunakan fungsi activation ExpRectifier. Sedangkan jika atributnya bertipe numerik, Deep Learning memiliki kinerja paling unggul untuk semua algoritma jika menggunakan fungsi Tanh untuk semua random sampling. Namun, Deep Learning memiliki kinerja paling buruk untuk semua algoritma jika menggunakan loss Function berupa absolut.  Abstract In SMAN 1 Jombang, East Java, the process of determining the students’ majors referred to the 2013 curriculum in which not only the students’ own choices and specialization tests conducted in their first week of SMA were considered but also the student’s SMP grades (a report card, UN scores, and counseling teacher’s recommendation) and parents' recommendation. So far, the school had used Microsoft Excel which required a long time to do and was prone to calculation errors in the process of determination. The process was carried out, with limited time and human resources, at the beginning of a new academic year for grade X students, consisting of 290 students on average. In this present research, the use of ID3 algorithm was not suitable because of its numeric data type instead of nominal or polynomial data. Thus, the C4.5 algorithm was applied, instead. However, the performance of C4.5 algorithm was proved lower than the algorithms of Gradient Boosting Trees, Random Forests, and Deep Learning. Hence, a comparison of performance between them was done to see their effectiveness in the process. The data was the list of new students of the academic year 2018/2019. The results showed that if the attributes are polynomial, the Deep Learning algorithm had the best performance when using the ExpRectifier activation function. When they were numeric, Deep Learning has the most superior performance when using the Tanh function. However, Deep Learning has the worst performance when using the loss function in the form of absolute.
Seleksi Fitur Menggunakan Hybrid Binary Grey Wolf Optimizer untuk Klasifikasi Hadist Teks Arab Subkhi, M. Bahrul; Fatichah, Chastine; Zaenal Arifin, Agus
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 10 No 5: Oktober 2023
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2023106375

Abstract

Seleksi fitur pada teks Arab merupakan tugas yang menantang karena sifat Bahasa Arab yang kompleks dan kaya. Dala klasifikasi hadist teks Arab membutuhkan seleksi fitur, karena hadist teks Arab berbeda dengan dokumen  teks arab. Hadist teks Arab memiliki sanat dan matan yang menjadi pertimbangan dalam klasifikasi hadist teks  arab. Penelitian ini mengusulkan metode seleksi fitur menggunakan Hybrid Binary Grey Wolf Optimizer untuk  klasifikasi hadist teks arab. Metode HBGWO mengkombinasikan kemampuan pencarian lokal atau eksplorasi pyg  dimiliki BGWO, dan kemampuan pencarian di sekitar solusi terbaik atau eksploitasi yang dimiliki PSO. Data set  yang digunakan berupa teks Arab diambil dari islambook.com. yang terdiri dari lima kitab yaitu Shahih Bukhari,  Shahih Muslim, Sunan Ibnu Majah, Sunan Abu Dawud dan Suann at-Tirmidzi. Pada kumpulan kitab tersebut  diambil 5 kelas yaitu Tuhid, Sholat, Zakat, Puasa dan Haji berjumlah 844. Hasil penelitian menunjukkan bahwa  pemilihan fitur BGWOPSO dengan mencari fungsi fitnes dan klasifikasi menggunakan SVM mendapatkan 84%,  dapat mengungkapkan kinerja yang unggul dibandingkan dengan menggunakan klasifikasi KNN 76% dalam soal mengklasifikasikan teks hadits Arab dengan data yang tidak seimbang.   Abstract Feature selection in Arabic text is a challenging task due to the  complex and rich nature of Arabic. In the  classification of Arabic text hadith requires feature selection, because Arabic text hadith is different from Arabic  text documents. Arabic text hadith has sanat and matan which are considered in the classification of Arabic text  hadith. This study proposes a feature selection method using the Hybrid Binary Gray Wolf Optimizer for Arabic text hadith classification. The HBGWO method combines the local search or pyg exploration capabilities of the  BGWO, and the search capabilities around the best solutions or exploits that PSO has. The data set used in the form of Arabic text is taken from islambook.com. which consists of five books, namely Sahih Bukhari, Sahih  Muslim, Sunan Ibn Majah, Sunan Abu Dawud and Suann at-Tirmidhi. In this collection of books, 5 classes were  taken, namely Tuhid, Prayer, Zakat, Fasting and Hajj totaling 844. The results showed that the selection of  BGWOPSO features by looking for fitness functions and classification using SVM obtained 84%, can reveal  superior performance compared to using KNN classification 76% in terms of classifying Arabic hadith texts with unbalanced data.
Ground Coverage Classification in UAV Image Using a Convolutional Neural Network Feature Map Maulidiya, Erika; Fatichah, Chastine; Suciati, Nanik; Sari, Yuslena
Journal of Information Systems Engineering and Business Intelligence Vol. 10 No. 2 (2024): June
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.10.2.206-216

Abstract

Background: To understand land transformation at the local level, there is a need to develop new strategies appropriate for land management policies and practices. In various geographical research, ground coverage plays an important role particularly in planning, physical geography explorations, environmental analysis, and sustainable planning. Objective: The research aimed to analyze land cover using vegetation density data collected through remote sensing. Specifically, the data assisted in land processing and land cover classification based on vegetation density. Methods: Before classification, image was preprocessed using Convolutional Neural Network (CNN) architecture's ResNet 50 and DenseNet 121 feature extraction methods. Furthermore, several algorithm were used, namely Decision Tree, Naí¯ve Bayes, K-Nearest Neighbor, Random Forest, Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGBoost). Results: Classification comparison between methods showed that using CNN method obtained better results than machine learning. By using CNN architecture for feature extraction, SVM method, which adopted ResNet-50 for feature extraction, achieved an impressive accuracy of 85%. Similarly using SVM method with DenseNet121 feature extraction led to a performance of 81%. Conclusion: Based on results comparing CNN and machine learning, ResNet 50 architecture performed the best, achieving a result of 92%. Meanwhile, SVM performed better than other machine learning method, achieving an 84% accuracy rate with ResNet-50 feature extraction. XGBoost came next, with an 82% accuracy rate using the same ResNet-50 feature extraction. Finally, SVM and XGBoost produced the best results for feature extraction using DenseNet-121, with an accuracy rate of 81%.   Keywords: Classification, CNN Architecture, Feature Extraction, Ground Coverage, Vegetation Density.
RadEval: A novel semantic evaluation framework for radiology report Tsaniya, Hilya; Fatichah, Chastine; Suciati, Nanik
International Journal of Advances in Intelligent Informatics Vol 11, No 4 (2025): November 2025
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v11i4.2151

Abstract

The evaluation of automatically generated radiology reports remains a critical challenge, as conventional metrics fail to capture the semantic, clinical, and contextual correctness required for automatic medical analysis. This study proposes RadEval, a semantic-aware evaluation framework, to assess the quality of generated radiology reports. This method integrates domain-specific knowledge and contextual embeddings to evaluate the quality of generated radiology reports using a four-level scoring system. Given a reference report and a predicted report from a radiology image, RadEval performs scoring evaluation by first extracting relevant medical entities using a fine-tuned biomedical NER model. These entities are normalized through ontology mapping using RadLex concept identifiers to resolve lexical variation. Then, semantically related entities were clustered using BioBERT's contextual embeddings to capture deeper semantic similarity. In addition, predicted abnormality tags are incorporated to weight clinically significant terms during score aggregation. The final semantic score reflects a weighted combination of exact match, ontology match, and contextual similarity, modulated by tag importance. Experiments were conducted on the MIMIC-CXR dataset, which contains over 200,000 report pairs. Comparative evaluations show that RadEval outperforms traditional metrics, achieving an F1-score of 0.69, compared to 0.56 for BERTScore. Using this method, a more precise clinical interpretation of the predicted report was captured from the reference report. These findings suggest that RadEval method provides a more accurate and clinically aligned framework for evaluating the medical report generation model.
Scalability Analysis of Frequent Closed High Utility Itemset Mining on Multi-Year Retail Transaction Data Kinana Syah Sulanjari; Chastine Fatichah
Reslaj: Religion Education Social Laa Roiba Journal Vol. 7 No. 10 (2025): RESLAJ: Religion Education Social Laa Roiba Journal
Publisher : Intitut Agama Islam Nasional Laa Roiba Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47467/reslaj.v7i10.9210

Abstract

Frequent Closed High Utility Itemset Mining (FCHUIM) is a vital approach for discovering high-value patterns from transactional data. However, a major challenge arises as historical data volume grows substantially over time, particularly in dynamic retail domains. This study aims to analyze the scalability of the Closed-FHUIM algorithm with respect to increasing volumes of multi-year retail cooperative transaction data, spanning from one to five years. The evaluation focuses on four key performance metrics: execution time, memory usage, number of discovered patterns, and pattern growth rate. Experiments were conducted incrementally using annual transaction datasets. The results show that execution time grows exponentially with data volume, while the number of patterns increases significantly in the early years and plateaus in later periods. Memory usage exhibits fluctuating behavior influenced by transaction structures, and the pattern growth rate gradually declines as the data span widens. These findings suggest that although Closed-FHUIM is effective for high-utility pattern discovery, further optimization is required for deployment in large-scale and longitudinal retail scenarios.
KOMPARASI METODE SCICA DAN WICA PADA PRAPROSES DATA EEG OTAK MANUSIA UNTUK DETEKSI PENYAKIT EPILEPSI Aditya Bagusmulya; Handayani Tjandrasa; Chastine Fatichah
JUTI: Jurnal Ilmiah Teknologi Informasi Vol 14, No. 2, Juli 2016
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v14i2.a564

Abstract

Epilepsi merupakan salah satu kelainan pada otak manusia yang tidak dapat disembuhkan. Penyakit ini menimbulkan kejang pada tubuh dan sangat mengganggu aktivitas. Pada tingkat yang parah, epilepsi dapat membahayakan nyawa penderitanya. Oleh sebab itu, epilepsi harus dideteksi secara dini agar penderita segera mendapatkan penanganan yang tepat sehingga keadaannya tidak memburuk. Pada penelitian ini, deteksi epilepsi dilakukan dengan menggunakan beberapa metode, yaitu Independent Component Analysis (ICA), Wavelet Transform (WT), dan Multilayer Perceptron (MLP). Hasil deteksi diklasifikasikan ke dalam tiga kelas, yaitu normal, epilesi tidak kejang, dan epilepsi kejang. Data rekaman electroencephalogram (EEG) yang digunakan berasal dari ''Klinik für Epileptologie, Universität Bonn” yang diperoleh secara online. Data tersebut merupakan EEG single channel sehingga harus menggunakan teknik-teknik ICA untuk single channel, seperti Single Channel Independent Component Analysis (SCICA) dan Wavelet Independent Component Analysis (WICA). Penelitian ini membandingkan kedua teknik tersebut dalam melakukan praproses data sehingga akan terlihat teknik mana yang lebih baik. Hasil pendeteksian terbaik dihasilkan dari model yang menggunakan teknik SCICA sebagai penghilang derau dan ektraksi fitur Discrete Wavelet Transform Daubechies 6 dengan 4 level. Berdasarkan uji coba, metode tersebut menghasilkan akurasi sebesar 92.09%.
Co-Authors Achmad Arwan Adhi Nurilham Aditya Bagusmulya Afrizal Laksita Akbar Agung Prasetya Agus Subhan Akbar, Agus Subhan Agus Zainal Arifin Agus Zainal Arifin Ahmad Hayam Brilian, Ahmad Hayam Ahmad Saikhu Ahmad Syauqi Ahmad Syauqi Aini, Nuru Ainul Mu'alif Akwila Feliciano Akwila Feliciano Al-Haddad, Abdullah Amalia Nurani Basyarah Amelia Devi Putri Ariyanto Amirullah Andi Bramantya Andika Pratama Andrea Bemantoro J Anisa Nur Azizah Anna Kholilah Anny Yuniarti Ardian Yusuf Wicaksono Ariana Yunita Arianto Wibowo Arif Sanjani, Lukman Arijal Ibnu Jati Ario Bagus Nugroho Arya Yudhi Wijaya Asmawati, Diah Avin Maulana Ayu Ismi Hanifah Benny Afandi Bilqis Amaliah Budi Pangestu Cahyaningtyas, Zakiya Azizah Daniel Oranova Siahaan Daniel Sugianto Daniel Swanjaya Darlis Heru Murti Darlis Herumurti Davin Masasih Deni Sutaji Desmin Tuwohingide Dhimas Pamungkas Wicaksono Diana Purwitasari Diana Purwitasari Diema Hernyka Satyareni Dimas Ari Setyawan Dimas Renggana, Christiant Dini Adni Navastara, Dini Adni Djoko Purwanto Dwi Kristianto Dwi Taufik Hidayat edy susanto Eha Renwi Astuti Eka Prakarsa Mandyartha Eka Prakarsa Mandyartha Eko Prasetyo Esa Prakasa Evan Tanuwijaya Evelyn Sierra Evy Kamilah Ratnasari Fachrul Pralienka Bani Muhamad Fachrul Pralienka Bani Muhamad Faizin, Muhammad 'Arif Fajar, Aziz Fajrin, Ahmad Miftah Fandy Kuncoro Adianto Fandy Kuncoro Adianto Faried Effendy Fatonah, Nenden Siti FATRA NONGGALA PUTRA Febri Liantoni Febri Liantoni, Febri Fiqey Indriati Eka Sari Furqan Aliyuddien Ginardi, R.V. Hari Ginardi, Raden Venantius Hari Gou Koutaki Hadziq Fabroyir Handayani Tjandrasa Haniefardy, Addien Haq, Dina Zatusiva Hardika Khusnuliawati Hardika Khusnuliawati Hari Ginardi Hendra Mesra hidayat, dwi taufik Hilya Tsaniya Hilya Tsaniya Hisyam Syarif, Hisyam I Ketut Eddy Purnama Ilmi, Akhmad Bakhrul Imam Artha Kusuma Imamah Imamah Irzal Ahmad Sabilla Isye Arieshanti Ivan Agung Pandapotan Jayanti Yusmah Sari Johan Varian Alfa Keiichi Uchimura Kevin Christian Hadinata Kevin Christian Hadinata Kinana Syah Sulanjari Kinana Syah Sulanjari Kusuma, Irnayanti Dwi Kusuma, Selvia Ferdiana Lukman Hakim M Rahmat Widyanto M. Rahmat Widyanto Machfud, M. Mughniy Mambaul Izzi Martini Dwi Endah Susanti Maulani, Irham Maulidiya, Erika Mauridhi Hery Purnomo Moch Zawaruddin Abdullah Mohamad Anwar Syaefudin Muhamad, Fachrul Pralienka Bani Muhammad Bahrul Subkhi Muhammad Fikri Sunandar Muhammad Jerino Gorter Muhammad Meftah Mafazy Muhammad Muharrom Al Haromainy Muhtadin Mustika Mentari Mutmainnah Muchtar Nafiiyah, Nur Nanik Suciati Nanik Suciati Narandha Arya Ranggianto Nazarrudin, Ahmad Ricky Nur Hayatin Nur Nafi’iyah Nur Nafi’iyah Nurilham, Adhi Nurina Indah Kemalasari Nursanti Novi Arisa Nursuci Putri Husain Nurwijayanti nuzula, Muhammad Iqbal firdaus Pradany, Latifa Nurrachma Priambodo, Anas Rachmadi Putra, Ramadhan Hardani R Dimas Adityo R. Dimas Adityo R. V. Hari Ginardi R.V Hari Ginardi R.V. Hari Ginardi Rachmad Abdullah Rahayu, Putri Nur Ramadhan Rosihadi Perdana Ramadhani, Muhammad Rafi' Rangga Kusuma Dinata Rangga Kusuma Dinata Ratih Kartika Dewi Rendra Dwi Lingga P. Riduwan, Muhammad Riyanarto Sarno Rizal A Saputra Rizal A Saputra, Rizal A Rizal Setya Perdana Rizka Wakhidatus Sholikah Rizka Wakhidatus Sholikah, Rizka Wakhidatus Rizqa Raaiqa Bintana Rozi, Fahrur RR. Ella Evrita Hestiandari Rully Soelaiman Safhira Maharani Safhira Maharani Sahmanbanta Sinulingga Salim Bin Usman Salim Bin Usman Sambodho, Kriyo Santoso, Bagus Jati Sarimuddin, Sarimuddin Septiyan Andika Isanta Sherly Rosa Anggraeni Sherly Rosa Anggraeni Shofiya Syidada Siti Mutrofin Siti Mutrofin Siti Rochimah Stefani Tasya Hallatu Subali, Made Agus Putra Subhan Nooriansyah Subkhi, M. Bahrul Sudianjaya, Nella Rosa Suhariyanto Suhariyanto Surya Sumpeno Syah Dia Putri Mustika Sari Sylvi Novita Dewi Tanzilal Mustaqim Tesa Eranti Putri Thoha Haq Tsaniya, Hilya Tuwohingide, Desmin Umi Laily Yuhana, Umi Laily Umy Rizqi Vit Zuraida Wahyu Saputra, Vriza Welly Setiawan Limantoro Wibowo, Prasetyo Wijoyo, Satrio Hadi Wilda Imama Sabilla Yoga Yustiawan Yosi Kristian Yudhi Purwananto Yuhana, Umi Laili Yuita Arum Sari Yulia Niza Yulia Niza Yunan Helmi Mahendra Yuslena Sari, Yuslena Yuwanda Purnamasari Pasrun Zaenal Arifin, Agus Zakiya Azizah Cahyaningtyas Zakiya Azizah Cahyaningtyas Zeng, Xinyou