cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Indonesian Journal of Electrical Engineering and Computer Science
Published by Institute of Advanced Engineering and Science
ISSN : 25024752     EISSN : 25024760     DOI : -
Core Subject :
Arjuna Subject : -
Articles 64 Documents
 1   2   3   4   5 
Search results for , issue "Vol 36, No 2: November 2024" : 64 Documents clear
Bee-inspired knowledge transfer: synthesizing data for enhanced deep learning explainability Chungnoy, Kritanat; Tanantong, Tanatorn; Songmuang, Pokpong
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1052-1069

Abstract

This paper presents the generation method for an explainable model based on the given information of a black box model using a concept of knowledge transfer to synthesize a dataset. The proposed method applies with GAN and Bee algorithm (BA) for data synthesis technique to synthesize a dataset by considering loss value in a knowledge transferring process to inherit the significance of features. The synthesized dataset is used to train for a proxy model as an explainable model. The result of the experiment indicates that knowledge transfer from Bee algo better than generative adversarial network (GAN) in terms of the coefficient of determination R2. In addition, explainable models from the synthesized data of the Bee-based method obtains F1 score superior to those from the GAN-based method in all datasets and settings. The dataset synthesized from the Bee-based method produces the explainable prediction model that has similar top-10 features according to similarity score of 0.6718 using shapley additive explanations (SHAP) feature importance which is higher than those from GAN-based method for 0.4218 in average. Additionally, experimental result to evaluate accuracy shows that F1 score from explainable models from the Bee-based method are closed to F1 score from a model generated from the original dataset.
Industrial process optimization through advanced HMI systems: exploring the integration of IoT and AI Arce Santillan, Dora Yvonne; Nolasco Sandoval, Luis Alfredo; Martinez Santillán, Albert Isaac; Avalos Yataco, Percy Jesús; Presentación Quispe, Higmmer Santiago; Hercilla Huapaya, Nelson Rene
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp817-825

Abstract

Facing the challenge of improving efficiency and stability in industrial processes, this study examines the impact of implementing advanced human-machine interface (HMI) systems, complemented by the internet of things (IoT) and artificial intelligence (AI). The integration of a PLC and HMI-controlled system has resulted in a 22.85% increase in efficiency, stabilizing production and reducing process variability. Tools such as PLCSIM and TIA PORTAL were crucial for validating control logic and programming. Additionally, the study explores the potential of AI and IoT to amplify these benefits, suggesting a significant advancement in automation that could transform operational efficiency and quality in related industries. These findings provide a relevant framework for companies looking to integrate emerging technologies into their operations, promoting continuous improvement and more informed management.
Exploring the landscape of dysarthric speechrecognition: a survey of literature Antony, Aneeta S.; Nagapadma, Rohini; Abraham, Ajish K.
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp826-836

Abstract

Automatic speech recognition (ASR) is a valued tool for individuals with dysarthria, a speech impairment characterized by various pathological traits that differ from healthy speech. However, recognizing dysarthric speech, which is spoken by individuals with speech impairments, poses unique challenges due to its diverse characteristics such as rugged pronunciation, loudness that varies at different intervals, speech that has lot of delays, pauses that are inpredictable, excessive nasal sounds, explosive pronunciation, and airflow noise. The survey reveals the various models for dysarthric speech recognition. Deep learning technologies, unfurls an improved ASR performance leaps and bounds breaking the fluency and pronunciation barriers. Various feature extractions and identification of different types of dysarthria, including spastic, mixed, ataxic, hypokinetic, and hyperkinetic are explored. The performance of contemporary deep learning approaches in dysarthric speaker recognition (DSR) is tested using various datasets to determine accuracy. In conclusion the most effective DSR strategies are identified and areas for future investigation is suggested. However, speaker-dependent difficulties restrict the generalizability of acoustic models, and a lack of speech data impedes training on large datasets. The study throws light on how the effectiveness of ASR for dysarthric speech can be improved and further areas of research in the area are highlighted.
An improved student’s facial emotions recognition method using transfer learning Rajae, Amimi; Amina, Radgui; El Hassane, Ibn El Haj
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1199-1208

Abstract

Instructors endeavour to encourage active participation and interaction among learners. However, in settings with a large number of students, such as universities or online platforms, obtaining real-time feedback and evaluating teaching methodology presents a significant challenge. In this paper, we introduce a student engagement recognition system based on a hybrid method using handcrafted features and transfer learning. The research is conducted on two databases for emotion detection based on facial cues (FER13) benchmarked dataset and our database. We use the local binary patterns (LBP) method combined with pre-trained MobileNet model for feature extraction and classification. The proposed system adeptly discerns students’ facial expressions and categorizes their engagement states as either ‘engaged’ or ‘disengaged’. We determine the most effective model by evaluating and comparing several deep learning models, including Inception-V3, VGG16, EfficientNet, ResNet, and DenseNet. Experimental results underscore the efficacy of our approach, revealing a remarkable accuracy, surpassing benchmarks set by state-of-the-art models.
An innovative machine learning optimization-based data fusion strategy for distributed wireless sensor networks Sollapure, Naganna Shankar; Govindaswamy, Poornima
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1012-1022

Abstract

Self-sufficient sensors scattered over different regions of the world comprise distributed wireless sensor networks (DWSNs), which track a range of environmental and physical factors such as pressure, temperature, vibration, sound, motion, and pollution. The use of data fusion becomes essential for combining information from various sensors and system performance. In this study, we suggested the multi-class support vector machine (SDF-MCSVM) with synthetic minority over-sampling techniques (SMOTE) data fusion for wireless sensor network (WSN) performance. The dataset includes 1,334 instances of hourly averaged answers for 12 variables from an AIR quality chemical multisensor device. To create a balanced dataset, the unbalanced data was first pre-processed using the SMOTE. The grey wolf optimization (GWO) approach is then used to reduce features in an effort to improve the efficacy and efficiency of feature selection procedures. This method is applied to classify the fused feature vectors into multiple categories at once to improve classification performance in WSNs and address unbalance datasets. The result shows the proposed method reaches high precision, accuracy, F1-score, recall, and specificity. The computational complexity and processing time were decreased in the study by using the proposed method. This is great potential for accurate and timely data fusion in dispersed WSNs with the successful integration of data fusion technologies.
Optimizing hyperspectral classification: spectral similarity-based band selection with chord k-means Chander Goud, Origanti Subhash; Sarma, Thogarachetti Hitendra; Bindu, Chigarapalle Shobha
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1309-1318

Abstract

Band selection is crucial for achieving high classification accuracy in hyperspectral image (HSI) analysis, especially when ground truth data are limited. While unsupervised algorithms are preferred in such scenarios, the effectiveness of k-means clustering depends heavily on the choice of similarity measure. This article presents a novel two-level clustering approach for band selection. In the first level, bands are clustered using k-means with various similarity measures such as Euclidean distance, spectral angle mapper (SAM), and spectral information divergence (SID). Subsequently, the second level leverages the chord metric k-means clustering to form clusters of HSI scenes upon optimal band clusters from the first level. This initial band selection reduces dimensionality and guides subsequent k-means clustering. The proposed chord-based clustering method, utilizing the chord metric, outperforms standard k-means variants, demonstrating significant improvements in accuracy. Experimental results on publicly available hyperspectral datasets confirm the effectiveness of the proposed approach as an alternative to traditional k-means algorithms, showcasing significant improvements in accuracy.
Enhancing network security using unsupervised learning approach to combat zero-day attack Perumal, Rajakumar; Karuppiah, Tamilarasi; Panneerselvam, Uppiliraja; Annamalai, Venkatesan; Kaliyaperumal, Prabu
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1284-1293

Abstract

Machine learning (ML) and advanced neural network methodologies like deep learning (DL) techniques have been increasingly utilized in developing intrusion detection systems (IDS). However, the growing quantity and diversity of cyber-attacks pose a significant challenge for IDS solutions reliant on historical attack signatures. This highlights the industry's need for resilient IDSs that can identify zero-day attacks. Current studies focusing on outlier-based zero-day detection are hindered by elevated false-negative rates, thereby constraining their practical efficacy. This paper suggests utilizing an autoencoder (AE) approach for zero-day attack detection, aiming to achieve high recall while minimizing false negatives. Evaluation is conducted using well-established IDS datasets, CICIDS2017 and CSECICIDS2018. The model's efficacy is demonstrated by contrasting its performance with that of a one-class support vector machine (OCSVM). The research underscores the OCSVM's capability in distinguishing zero-day attacks from normal behavior. Leveraging the encoding-decoding capabilities of AEs, the proposed model exhibits promising results in detecting complex zero-day attacks, achieving accuracies ranging from 93% to 99% across datasets. Finally, the paper discusses the balance between recall and fallout, offering valuable insights into model performance.
Electrocardiogram reconstruction based on Hermite interpolating polynomial with Chebyshev nodes Ray, Shashwati; Chouhan, Vandana
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp837-845

Abstract

Electrocardiogram (ECG) signals generate massive volume of digital data, so they need to be suitably compressed for efficient transmission and storage. Polynomial approximations and polynomial interpolation have been used for ECG data compression where the data signal is described by polynomial coefficients only. Here, we propose approximation using hermite polynomial interpolation with chebyshev nodes for compressing ECG signals that consequently denoises them too. Recommended algorithm is applied on various ECG signals taken from MIT-BIH arrhythmia database without any additional noise as the signals are already contaminated with noise. Performance of the proposed algorithm is evaluated using various performance metrics and compared with some recent compression techniques. Experimental results prove that the proposed method efficiently compresses the ECG signals while preserving the minute details of important morphological features of ECG signal required for clinical diagnosis.
Enhancing surface water quality prediction efficiency in northeastern thailand using machine learning Uypatchawong, Surasit; Chanamarn, Nipaporn
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1189-1198

Abstract

Water is the most vital resource for life and is necessary for most living creatures, including humans, to survive. Three rivers’ surface water quality has been predicted by this study: the Chi river, the Mun river, and the Songkhram river. In the northeastern region of Thailand. The dataset is 881 samples and 13 factors. This study investigated various machine learning methods for predicting water quality, including neural networks (NN), support vector machines (SVM), decision trees (DT), Naive Bayes (NB), and K-nearest neighbors (KNN). Furthermore, this study was conducted to find suitable factors using correlation based feature selection, correlation coefficient, and information gain. And optimize the prediction model using the Bagging Approach. The result is found that the bagging model using the DT technique (BaggingDT) has better performance than all models with an accuracy value equal to 98.64%, precision value equal to 98.70%, recall value equal to 98.60%, F-measure value equal to 98.60% and RMSE value equal to 0.0961. The obtained factors and the most appropriate model can be used to develop a surface water quality standard predicting system.
Enhanced Bengali audio categorization using audio segmentation and deep learning Khan, Niaz Ashraf; Bin Hafiz, Md. Ferdous
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp952-960

Abstract

This paper presents an enhanced approach for classifying Bengali songs into different genres by leveraging feature importance analysis and deep learning techniques. The research addresses the challenge of limited data points in the Bengali Song Dataset by employing strategies, including audio segmentation and feature importance analysis, to enhance model performance. Multiple machine learning and deep learning architectures are evaluated to identify the most effective models for Bengali song classification. Additionally, this research conducts feature importance analysis to identify significant audio features contributing to classification accuracy. The best-performing deep learning model achieves an impressive validation accuracy of 94.17%, showcasing the project efficacy of the proposed methodology. Our findings highlight the effectiveness of our proposed methodology, demonstrating significant improvements in classification accuracy and contributing to advancements in Bengali music classification research.

Page 3 of 7 | Total Record : 64

 1   2   3   4   5 

Filter by Year

2024 2024


Reset
Filter By Issues
All Issue Vol 41, No 2: February 2026 Vol 41, No 1: January 2026 Vol 40, No 3: December 2025 Vol 40, No 2: November 2025 Vol 40, No 1: October 2025 Vol 39, No 3: September 2025 Vol 39, No 2: August 2025 Vol 39, No 1: July 2025 Vol 38, No 3: June 2025 Vol 38, No 2: May 2025 Vol 38, No 1: April 2025 Vol 37, No 3: March 2025 Vol 37, No 2: February 2025 Vol 37, No 1: January 2025 Vol 36, No 3: December 2024 Vol 36, No 2: November 2024 Vol 36, No 1: October 2024 Vol 35, No 3: September 2024 Vol 35, No 2: August 2024 Vol 35, No 1: July 2024 Vol 34, No 3: June 2024 Vol 34, No 2: May 2024 Vol 34, No 1: April 2024 Vol 33, No 3: March 2024 Vol 33, No 2: February 2024 Vol 33, No 1: January 2024 Vol 32, No 3: December 2023 Vol 32, No 1: October 2023 Vol 31, No 3: September 2023 Vol 31, No 2: August 2023 Vol 31, No 1: July 2023 Vol 30, No 3: June 2023 Vol 30, No 2: May 2023 Vol 30, No 1: April 2023 Vol 29, No 3: March 2023 Vol 29, No 2: February 2023 Vol 29, No 1: January 2023 Vol 28, No 3: December 2022 Vol 28, No 2: November 2022 Vol 28, No 1: October 2022 Vol 27, No 3: September 2022 Vol 27, No 2: August 2022 Vol 27, No 1: July 2022 Vol 26, No 3: June 2022 Vol 26, No 2: May 2022 Vol 26, No 1: April 2022 Vol 25, No 3: March 2022 Vol 25, No 2: February 2022 Vol 25, No 1: January 2022 Vol 24, No 3: December 2021 Vol 24, No 2: November 2021 Vol 24, No 1: October 2021 Vol 23, No 3: September 2021 Vol 23, No 2: August 2021 Vol 23, No 1: July 2021 Vol 22, No 3: June 2021 Vol 22, No 2: May 2021 Vol 22, No 1: April 2021 Vol 21, No 3: March 2021 Vol 21, No 2: February 2021 Vol 21, No 1: January 2021 Vol 20, No 3: December 2020 Vol 20, No 2: November 2020 Vol 20, No 1: October 2020 Vol 19, No 3: September 2020 Vol 19, No 2: August 2020 Vol 19, No 1: July 2020 Vol 18, No 3: June 2020 Vol 18, No 2: May 2020 Vol 18, No 1: April 2020 Vol 17, No 3: March 2020 Vol 17, No 2: February 2020 Vol 17, No 1: January 2020 Vol 16, No 3: December 2019 Vol 16, No 2: November 2019 Vol 16, No 1: October 2019 Vol 15, No 3: September 2019 Vol 15, No 2: August 2019 Vol 15, No 1: July 2019 Vol 14, No 3: June 2019 Vol 14, No 2: May 2019 Vol 14, No 1: April 2019 Vol 13, No 3: March 2019 Vol 13, No 2: February 2019 Vol 13, No 1: January 2019 Vol 12, No 3: December 2018 Vol 12, No 2: November 2018 Vol 12, No 1: October 2018 Vol 11, No 3: September 2018 Vol 11, No 2: August 2018 Vol 11, No 1: July 2018 Vol 10, No 3: June 2018 Vol 10, No 2: May 2018 Vol 10, No 1: April 2018 Vol 9, No 3: March 2018 Vol 9, No 2: February 2018 Vol 9, No 1: January 2018 Vol 8, No 3: December 2017 Vol 8, No 2: November 2017 Vol 8, No 1: October 2017 Vol 7, No 3: September 2017 Vol 7, No 2: August 2017 Vol 7, No 1: July 2017 Vol 6, No 3: June 2017 Vol 6, No 2: May 2017 Vol 6, No 1: April 2017 Vol 5, No 3: March 2017 Vol 5, No 2: February 2017 Vol 5, No 1: January 2017 Vol 4, No 3: December 2016 Vol 4, No 2: November 2016 Vol 4, No 1: October 2016 Vol 3, No 3: September 2016 Vol 3, No 2: August 2016 Vol 3, No 1: July 2016 Vol 2, No 3: June 2016 Vol 2, No 2: May 2016 Vol 2, No 1: April 2016 Vol 1, No 3: March 2016 Vol 1, No 2: February 2016 Vol 1, No 1: January 2016 Vol 16, No 3: December 2015 Vol 16, No 2: November 2015 Vol 16, No 1: October 2015 Vol 15, No 3: September 2015 Vol 15, No 2: August 2015 Vol 15, No 1: July 2015 Vol 14, No 3: June 2015 Vol 14, No 2: May 2015 Vol 14, No 1: April 2015 Vol 13, No 3: March 2015 Vol 13, No 2: February 2015 Vol 13, No 1: January 2015 Vol 12, No 12: December 2014 Vol 12, No 11: November 2014 Vol 12, No 10: October 2014 Vol 12, No 9: September 2014 Vol 12, No 8: August 2014 Vol 12, No 7: July 2014 Vol 12, No 6: June 2014 Vol 12, No 5: May 2014 Vol 12, No 4: April 2014 Vol 12, No 3: March 2014 Vol 12, No 2: February 2014 Vol 12, No 1: January 2014 Vol 11, No 12: December 2013 Vol 11, No 11: November 2013 Vol 11, No 10: October 2013 Vol 11, No 9: September 2013 Vol 11, No 8: August 2013 Vol 11, No 7: July 2013 Vol 11, No 6: June 2013 Vol 11, No 5: May 2013 Vol 11, No 4: April 2013 Vol 11, No 3: March 2013 Vol 11, No 2: February 2013 Vol 11, No 1: January 2013 Vol 10, No 8: December 2012 Vol 10, No 7: November 2012 Vol 10, No 6: October 2012 Vol 10, No 5: September 2012 Vol 10, No 4: August 2012 Vol 10, No 3: July 2012 More Issue