Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal ILKOM Jurnal Ilmiah International Journal of Engineering, Science and Information Technology
Shili, Hechmi
Unknown Affiliation
Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Social Sciences Transportation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Contextual Relevance-Driven Question Answering Generation: Experimental Insights Using Transformer-Based Models Suryanto, Tri Lathif Mardi; Wibawa, Aji Prasetya; Hariyono, Hariyono; Shili, Hechmi
International Journal of Engineering, Science and Information Technology Vol 5, No 4 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i4.989

Abstract

This study investigates the impact of contextual relevance and hyperparameter tuning on the performance of Transformer-based models in Question-Answer Generation (QAG). Utilising the FlanT5 model, experiments were conducted on a domain-specific dataset to assess how variations in learning rate and training epochs affect model accuracy and generalisation. Six QAG models were developed (QAG-A to QAG-F), each evaluated using ROUGE metrics to measure the quality of generated question-answer pairs. Results show that QAG-F and QAG-D achieved the highest performance, with QAG-F reaching a ROUGE-LSum of 0.4985. The findings highlight that careful tuning of learning rates and training duration significantly improves model performance, enabling more accurate and contextually appropriate question generation. Furthermore, the ability to generate both questions and answers from a single input enhances the interactivity and utility of NLP systems, particularly in knowledge-intensive domains. This study underscores the importance of contextual modelling and hyperparameter optimisation in generative NLP tasks, offering practical insights for improving chatbot development, educational tools, and digital heritage applications.
Classification of Multiclass Ensemble SVM for Human Activities based on Sensor Accelerometer and Gyroscope Wungo, Supriyadi La; Mardewi, Mardewi; Aziz, Firman; Ishak, Pertiwi; SHILI, Hechmi
ILKOM Jurnal Ilmiah Vol 15, No 1 (2023)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v15i1.1270.107-117

Abstract

Human Activity Recognition is technology introduced to recognize human activities. Several technologies that have been applied are Accelerometer sensors, Gyroscope sensors, Cameras, and GPS. The selection of the Support Vector Machine algorithm is due to its capabilities to minimize errors in training data sets and the Curse of dimensionality which can estimate parameters as well as its ability to find the best hyperplane that separates two classes. The SVM algorithm was originally developed for the classification of two classes. Problem raised if there are more than two classes. In addition, the performance will not optimal for the large-scale data. Therefore, modification the current design is needed. An ensemble technique can be used to combine the Support Vector Machine algorithm with the bagging algorithm. This study proposes the application of an ensemble SVM algorithm to classify human activities based on accelerometers and gyroscope sensors on smartphones.  The total data is 13725 records with 4575 representatives of each class. From the results of the overall data partition carried out in the calcification process using the ensemble SVM algorithm, the best performance was generated when comparing datasets with 80% training data and 20% test data from a total of 13725 records because it succeeded in increasing accuracy, precision, and sensitivity.
Co-Authors Aji Prasetya Wibawa Firman Aziz Hariyono Hariyono Ishak, Pertiwi Mardewi, Mardewi Wungo, Supriyadi La