Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal of Soft Computing Exploration Scientific Journal of Informatics
Mardiansyah, M Fadil
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

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

Found 2 Documents
Search

 1 
Optimization of breast cancer classification using feature selection on neural network Jumanto, Jumanto; Mardiansyah, M Fadil; Pratama, Rizka Nur; Hakim, M. Faris Al; Rawat, Bibek
Journal of Soft Computing Exploration Vol. 3 No. 2 (2022): September 2022
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v3i2.78

Abstract

Cancer is currently one of the leading causes of death worldwide. One of the most common cancers, especially among women, is breast cancer. There is a major problem for cancer experts in accurately predicting the survival of cancer patients. The presence of machine learning to further study it has attracted a lot of attention in the hope of obtaining accurate results, but its modeling methods and predictive performance remain controversial. Some Methods of machine learning that are widely used to overcome this case of breast cancer prediction are Backpropagation. Backpropagation has an advantage over other Neural Networks, namely Backpropagation using supervised training. The weakness of Backpropagation is that it handles classification with high-dimensional datasets so that the accuracy is low. This study aims to build a classification system for detecting breasts using the Backpropagation method, by adding a method of forward selection for feature selection from the many features that exist in the breast cancer dataset, because not all features can be used in the classification process. The results of combining the Backpropagation method and the method of forward selection can increase the detection accuracy of breast cancer patients by 98.3%.
Improving Sentiment Analysis with a Context-Aware RoBERTa–BiLSTM and Word2Vec Branch Hardyanto, Wahyu; Aryani, Nila Prasetya; Andestian, Defin; Sugiyanto; Setyaningrum, Wahyu; Mardiansyah, M Fadil; Islam, Muhamad Anbiya Nur; Purwinarko, Aji
Scientific Journal of Informatics Vol. 12 No. 4: November 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i4.35918

Abstract

Purpose: We improve the accuracy of Twitter sentiment analysis with a hybrid model combining Word to Vector (Word2Vec) and the Robustly Optimized BERT Pretraining Approach (RoBERTa). The idea is that Word2Vec is strong for slang/novel vocabulary (distributional semantics), while RoBERTa excels in contextual meaning; combining the two mitigates each other's weaknesses. Methods/Study design/approach: The Sentiment140 dataset contains 1.6 million balanced tweets. The split is stratified; Word2Vec is trained solely on the training data. RoBERTa is pretrained (frozen in the first stage, then fine-tuned with some layers in the second stage). The Word2Vec and RoBERTa vectors are concatenated and processed using Bidirectional Long Short-Term Memory (BiLSTM) with sigmoid activation. Training utilizes TensorFlow and the Adam optimizer, incorporating dropout and early stopping. The decision threshold is optimized during the validation process. The process supports caching and training resumes. Result/Findings: The hybrid model achieved an accuracy of 88.09%, an F1-score of 88.09 %, and an Area Under the Curve (AUC) ≈ 95.19% on the Receiver Operating Characteristic (ROC). No overfitting was observed, and the hybrid model outperformed both single baselines. The confusion matrix and ROC curve corroborate the findings. Novelty/Originality/Value: The novelty lies in the fusion of distributional and contextual representations with resource-efficient fine-tuning. Limitations: Computational requirements and hyperparameter tuning are not yet extensive. Further directions: systematic hyperparameter search and cross-validation across other large sentiment datasets to assess generalization.
Co-Authors Aji Purwinarko, Aji Andestian, Defin Aryani, Nila Prasetya Hakim, M. Faris Al Islam, Muhamad Anbiya Nur Jumanto Jumanto, Jumanto Pratama, Rizka Nur Rawat, Bibek SUGIYANTO Wahyu Hardyanto Wahyu Setyaningrum