Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

29,939 Article Results

Experimental research on text CAPTCHA of fine-grained security features

10.11591/ijeecs.v38.i1.pp535-545
Qian Wang , Shafaf Ibrahim , Xing Wan , Zainura Idrus
CAPTCHA is a cybersecurity measure that distinguishes between humans and automated scripts. Researchers have employed various security features to thwart automated program identification by hackers. However, previous research on the attack resistance of CAPTCHAs has used roughly quantitative analysis instead of a fine-grain quantitative study. This study implemented comparative experiments based on CAPTCHA recognition algorithms to find the best-mixed security features. A multi-stage best parameter selection (MBPS) mechanism was proposed in this study. Experiment results indicated that mixed security features of “overlap + scale + rotate + bg (background)” were the best, with an average machine recognition accuracy of only 4.81%. The contrast experiment result illustrated that the anti-attack ability of mixed security features was better than adding adversarial noise, with machine recognition accuracy decreased by 2.2%. Moreover, by investigating the efficacy of security feature parameters, this study provides practical guidelines for designing robust CAPTCHAs. Furthermore, this study also presents valuable insights into the security of image generation technology.
Volume: 38
Issue: 1
Page: 535-545
Publish at: 2025-04-01

Performance analysis of different BERT implementation for event burst detection from social media text

10.11591/ijeecs.v38.i1.pp439-446
Dharmendra Mangal , Hemant Makwana
The language models play very important role in natural language processing (NLP) tasks. To understand natural languages, the learning models are required to be trained on large corpus. This requires a lot of time and computing resources. The detection of information like events, and locations from text is an important NLP task. As events detection is to be done in real-time so that immediate actions can be taken, hence we need efficient decision-making models. The pertained models like bi-directional encoders representation from transformers (BERT) gaining popularity to solve NLP problems. As BERT based models are pre-trained on large language corpus it requires very less time to adapt for domain specific NLP task. Different implementations of BERT have been proposed to enhance efficiency and applicability of the base model. The selection of right implementation is essential for overall performance of NLP based system. This work presents the comparative insights of five widely used BERT implementations named as BERT-base, BERT-large, Distill BERT, Robust BERT approach (RoBERTa-base) and RoBERT-large for event detection from the text extracted from social media streams. The results show that Distill-BERT model outperforms on basis of performance metric like precision, recall, and F1-score while the fastest to train also.
Volume: 38
Issue: 1
Page: 439-446
Publish at: 2025-04-01

IDCCD: evaluation of deep learning for early detection caries based on ICDAS

10.11591/ijeecs.v38.i1.pp381-392
Rina Putri Noer Fadilah , Rasmi Rikmasari , Saiful Akbar , Arlette Suzy Setiawan
Dental caries is a common oral disease in children, influenced by environmental, psychological, behavioral, and biological factors. The American academy of pediatric dentistry recommends screening from the time the first tooth erupts or at one year of age to prevent caries, which mostly affects children from racial and ethnic minorities. In Indonesia, the 2023 health survey reported a caries prevalence of 84.8% in children aged 5-9 years. This research introduces early caries detection using three deep learning models: faster-RCNN, you only look once (YOLO) V8, and detection transformer (DETR), using Indonesian dental caries characteristic datasets (IDCCD) focused on Indonesian data with international caries detection and assessment system (ICDAS) classification D0 to D6. The results showed that YOLO V8-s and DETR gave good results, with mean average precision (mAP) of 41.8% and 41.3% for intersection over union (IoU) 50, and 24.3% and 26.2% for IoU 50:90. Precision-recall (PR) curves show that both models have high precision at low recall (0 to 0.2), but precision decreases sharply as recall increases. YOLO V8-s showed a slower and more regular decrease in precision, indicating a more stable performance compared to DETR.
Volume: 38
Issue: 1
Page: 381-392
Publish at: 2025-04-01

Secure financial application using homomorphic encryption

10.11591/ijeecs.v38.i1.pp595-602
Vijaykumar Bidve , Aruna Pavate , Rahul Raut , Shailesh Kediya , Pakiriswamy Sarasu , Koteswara Rao Anne , Aryani Gangadhara , Ashfaq Shaikh
In today’s digital age, the security and privacy of financial transactions are paramount. With the advent of technologies like homomorphic encryption, it is now possible to perform computations on encrypted data without the need to decrypt it first, offering a promising avenue for secure financial applications. This research paper explores the implementation and implications of utilizing homomorphic encryption in financial applications to safeguard sensitive data while maintaining computational integrity. By employing homomorphic encryption techniques, financial institutions can enhance the confidentiality of their clients’ information, protect against data breaches, and enable secure computations on encrypted data. The paper discusses the principles of homomorphic encryption, its applications in financial systems, challenges, and potential solutions. Additionally, it examines real-world examples and case studies where homomorphic encryption has been employed successfully, highlighting its effectiveness in ensuring the privacy and security of financial transactions. Overall, this paper aims to provide insights into the role of homomorphic encryption in creating secure financial applications and its potential to revolutionize the way sensitive financial data is handled and processed.
Volume: 38
Issue: 1
Page: 595-602
Publish at: 2025-04-01

Tree-based models and hyperparameter optimization for assessing employee performance

10.11591/ijeecs.v38.i1.pp569-577
Rendra Gustriansyah , Shinta Puspasari , Ahmad Sanmorino , Nazori Suhandi , Dewi Sartika
The Palembang city fire and rescue service (FRS) is encountering challenges in adhering to national standards for fire response time. Hence, the Palembang city FRS is committed to enhancing employee performance through quarterly performance assessments based on various criteria such as attendance, work targets, behavior, education, and performance reports. This study proposes tree-based models in machine learning (ML) and hyperparameter optimization to assess the performance of Palembang city FRS employees. Tree-based models encompass decision trees (DT), random forests (RF), and extreme gradient boosting (XGB). The predictive performance of each model was evaluated using the confusion matrix (CM), the area under the receiver operating characteristic (AUROC), and the kappa coefficient (KC). The results indicate that RF performs better than DT and XGB in the sensitivity, AUROC, and KC metrics by 1.0000, 0.9874, and 0.8584, respectively.
Volume: 38
Issue: 1
Page: 569-577
Publish at: 2025-04-01

New family of error-correcting codes based on genetic algorithms

10.11591/ijai.v14.i2.pp1077-1086
El Mehdi Bellfkih , Said Nouh , Imrane Chemseddine Idrissi , Khalid Louartiti , Jamal Mouline
This paper introduces a novel error-correcting code (ECC) construction and decoding approach utilizing genetic algorithms (GAs). Classical ECCs often struggle with efficiency in correcting multiple errors due to time-consuming matrix-based encoding and decoding processes. Our GA-based method optimizes generator vectors to maximize the minimum distance between codewords, enhancing error correction capabilities. Specifically, we construct a new family of ECCs with code length 31, dimension 12, and minimum distance 7, reducing complexity from O(kn) to O(k(n−k)) by encoding message blocks with vectors instead of matrices. In the decoding phase, the GA effectively corrects errors in received codewords. Experimental results show that at a signal-to-noise ratio (SNR) of 7.7 dB, our method achieves a bit error rate (BER) of 10−5 after only 9 generations of the GA. These results demonstrate improved error correction and decoding performance compared to traditional methods. This study contributes an innovative approach using GAs for error correction, offering simpler encoding and robust performance in coding schemes.
Volume: 14
Issue: 2
Page: 1077-1086
Publish at: 2025-04-01

A comprehensive overview of LLM-based approaches for machine translation

10.11591/ijeecs.v38.i1.pp344-356
Bhuvaneswari Kumar , Varalakshmi Murugesan
Statistical machine translation (SMT) used parallel corpora and statistical models, to identify translation patterns and probabilities. Although this method had advantages, it had trouble with idiomatic expressions, context-specific subtleties, and intricate linguistic structures. The subsequent introduction of deep neural networks such as recurrent neural networks (RNNs), long short-term memory (LSTMs), transformers with attention mechanisms, and the emergence of large language model (LLM) frameworks has marked a paradigm shift in machine translation in recent years and has entirely replaced the traditional statistical approaches. The LLMs are able to capture complex language patterns, semantics, and context because they have been trained on enormous volumes of text data. Our study summarizes the most significant contributions in the literature related to LLM prompting, fine-tuning, retrieval augmented generation, improved transformer variants for faster translation, multilingual LLMs, and quality estimation with LLMs. This new research direction guides the development of more efficient and innovative solutions to address the current challenges of LLMs, including hallucinations, translation bias, information leakage, and inaccuracy due to language inconsistencies.
Volume: 38
Issue: 1
Page: 344-356
Publish at: 2025-04-01

Boosting industrial internet of things intrusion detection: leveraging machine learning and feature selection techniques

10.11591/ijai.v14.i2.pp1232-1241
Lahcen Idouglid , Said Tkatek , Khalid Elfayq
The rapid integration of industrial internet of things (IIoT) technologies into Industry 4.0 has revolutionized industrial efficiency and automation, but it has also exposed critical vulnerabilities to cyber threats. This paper delves into a comprehensive evaluation of machine learning (ML) classifiers for detecting anomalies in IIoT environments. By strategically applying feature selection techniques, we demonstrate significant enhancements in both the accuracy and efficiency of these classifiers. Our findings reveal that feature selection not only boosts detection rates but also minimizes computational demands, making it a cornerstone for developing resilient intrusion detection systems (IDS) tailored for Industry 4.0. The insights garnered from this study pave the way for deploying more robust security frameworks, safeguarding the integrity and reliability of IIoT infrastructures in modern industrial settings.
Volume: 14
Issue: 2
Page: 1232-1241
Publish at: 2025-04-01

Comparing machine learning models for Indonesia stock market prediction

10.11591/ijeecs.v38.i1.pp508-516
Selly Anastassia Amellia Kharis , Arman Haqqi Anna Zili , Maulana Malik , Wahyu Nuryaningrum , Agustiani Putri
The financial market hold a significant role in the economy and the ability to accurately predict stock prices poses a major challenge, particularly in volatile markets like Indonesia. This study investigates the application of three supervised machine learning algorithms: random forest (RF), support vector regression (SVR), K-nearest neighbor (KNN) to predict the closing prices of stocks. The data used in this research consists of BBCA, PWON, and TOWR stocks. This study adopted daily historical stock prices from March 2017 to February 2020, which were normalized and segmented into training and testing datasets. The models were trained using machine learning techniques, and their predictive accuracy was evaluated using root mean square error (RMSE) and mean absolute error (MAE). The historical stock data includes Open, High, Low, and Close prices. The result indicated that SVR consistently outperforms RF and KNN in terms of RMSE and MAE across different stocks. The SVR method produced RMSE values of 4.79% for BBCA stock, 10.61% for PWON stock, and 15.14% for TOWR stock, and produces MAE values of 3.52% for BBCA stock, 8.49% for PWON stock, and 13.78% for TOWR stock.
Volume: 38
Issue: 1
Page: 508-516
Publish at: 2025-04-01

Exploration of various approaches for detection of autism spectrum disorder

10.11591/ijeecs.v38.i1.pp632-640
Kavitha Gangaraju , Yogisha H K
Autism spectrum disorder (ASD) presents a complex and diverse set of challenges, necessitating innovative and data-driven approaches for effective understanding, diagnosis, and intervention. This review explores recent advancements in methodologies, technologies, and frameworks aimed at addressing ASD and also highlights novel data collection methods, focusing on the integration of wearable internet of things (IoT) sensors for real-time behavioral monitoring and data capture from individuals with ASD. Additionally, the utilization of machine learning (ML), deep learning (DL), and hybrid techniques for data analysis, feature optimization, and prediction of ASD are extensively discussed, showcasing significant progress in early diagnosis and personalized intervention planning. The challenges such as class imbalance, feature selection, and data collection efficiency are identified and addressed using the proposed ASD framework. The review also emphasizes the development of recommendation systems designed to the unique behavioral profiles and needs of individuals with ASD. The findings reveal that integrating these advanced technologies and methodologies can lead to more accurate diagnoses and effective interventions, contributing to the broader field of ASD research.
Volume: 38
Issue: 1
Page: 632-640
Publish at: 2025-04-01

Enhancing attack detection in IoT through integration of weighted emphasis formula with XGBoost

10.11591/ijeecs.v38.i1.pp641-648
Januar Al Amien , Hadhrami Ab Ghani , Nurul Izrin Md Saleh , Soni Soni
This research addresses the challenge of detecting attacks in the internet of things (IoT) environment, where minority classes often go unnoticed due to the dominance of majority classes. The primary objective is to introduce and integrate the imbalance ratio formula (IRF) into the XGBoost algorithm, aiming to provide greater emphasis on minority classes and ensure the model's focus on attack detection, particularly in binary and multiclass scenarios. Experimental validation using the IoTID20 dataset demonstrates the significant enhancement in attack detection accuracy achieved by integrating IRF into XGBoost. This enhancement contributes to the consistent improvement in distinguishing attacks from normal traffic, thereby resulting in a more reliable attack detection system in complex IoT environments. Moreover, the implementation of IRF enhances the robustness of the XGBoost model, enabling effective handling of imbalanced datasets commonly encountered in IoT security applications. This approach advances intrusion detection systems by addressing the challenge of class imbalance, leading to more accurate and efficient detection of malicious activities in IoT networks. The practical implications of these findings include the enhancement of cybersecurity measures in IoT deployments, potentially mitigating the risks associated with cyber threats in interconnected smart environments.
Volume: 38
Issue: 1
Page: 641-648
Publish at: 2025-04-01

Enhanced hippopotamus optimization algorithm for power system stabilizers

10.11591/ijeecs.v38.i1.pp22-31
Widi Aribowo , Toufik Mzili , Aliyu Sabo
This article presents techniques for modifying the power system stabilizer's (PSS) parameters. An enhanced version of the hippocampal optimization algorithm (HO) is presented here. HO represents a novel approach in metaheuristic methodology, having been inspired by the observed clinging behavior in hippos. The notion of the HO is defined using a trinary-phase model that includes their position updates in rivers or ponds, defensive techniques against predators, and mathematically described evasive methods. To confirm the efficacy of the recommended approach, this article provides comparison simulations of the PSS objective function and transient response. This study employs validation through a comparison between Original HO and conventional methods. Simulation results demonstrate that, when compared to competing algorithms, the suggested approach yields optimal results and, in some cases, exhibits fast convergence. It is known that, in comparison to the original HO approach, the recommended way can lower the average undershoot of the rotor angel and speed by 12.049% and 26.97%, respectively.
Volume: 38
Issue: 1
Page: 22-31
Publish at: 2025-04-01

Flexible hybrid graphene-based NFC tag antenna for temperature monitoring application

10.11591/ijeecs.v38.i1.pp227-242
Najwa Mohd Faudzi , Ahmad Rashidy Razali , Asrulnizam Abd Manaf , Nurul Huda Abd Rahman , Ahmad Azlan Ab Aziz , Syed Muhammad Hafiz , Suraya Sulaiman , Nora’zah Abdul Rashid , Amirudin Ibrahim , Aiza Mahyuni Mozi
A hybrid graphene-based material, composed of reduced graphene oxide (rGO) and silver nanoparticle (AgNP), has been proposed for a near field communication (NFC) tag antenna with an integrated, flexible temperature monitoring circuit. The limited availability of high-conductivity graphene-based materials in the market has restricted the use of graphene in NFC tag applications. Therefore, this paper proposes a hybrid graphene-based composition featuring a high conductivity of 3.95×106 S/m. The feasibility of this material for NFC tags had not been validated previously, which is the main motivation for this research. The synthesis of the materials, along with the design, fabrication, and characterization of the NFC tag, is also presented. Results show that the inkjet-printed tag achieves a good reading range of up to 3 cm and demonstrates robustness against bending from 60⁰ to 190⁰, maintaining a maximum reading range of 1.3 cm. Performance on various materials, such as plastic, paper, and carton, also shows minimal impact on frequency shifting. Additionally, the graphene-based NFC tag integrates well with the temperature circuit, effectively monitoring temperatures in the 20-60 ⁰C range in real-time. This makes the developed tag suitable for applications such as food safety monitoring systems through NFC-integrated packaging.
Volume: 38
Issue: 1
Page: 227-242
Publish at: 2025-04-01

Enhancing patient navigation and referral through tele-referral system with geographical information systems

10.11591/ijeecs.v38.i1.pp281-291
Winston G. Domingo , Virdi C. Gonzales , Jennifer A. Gamay
A tele-referral system with a geographic information system (GIS) integrates telehealth services with spatial data to enhance healthcare delivery. Resource constraints can significantly impact the effectiveness of a tele-referral system with GIS. Addressing delayed or missed referrals is critical to ensuring timely patient care and improving health outcomes. Implementing a tele-referral system with GIS can significantly enhance healthcare delivery by leveraging spatial data and telehealth technologies to improve access, efficiency, and outcomes. One major issue is the lack of access to specialists, particularly in underprivileged communities. Patients face accessing specialized care due to a cumbersome referral process or long wait times, as well as the lack of patient engagement. The results showed that the GIS-enabled tele-referral system significantly reduced patient waiting times and improved the coordination of care. By incorporating these functionalities and strategies, the tele-referral system with GIS can effectively address issues related to delayed or missed referrals, ensuring timely patient care and improving overall health outcomes. By incorporating these strategies and functionalities, the tele-referral system with GIS can effectively address limited access to specialists, ensuring timely patient care and optimal use of available resources.
Volume: 38
Issue: 1
Page: 281-291
Publish at: 2025-04-01

Predicting peak demand for electricity consumption using time series data and machine learning model

10.11591/ijeecs.v38.i1.pp668-676
Suriya S. , Agusthiyar R.
Energy consumption is influenced by various factors, including the proliferation of electronic devices, technological advancements, economic growth, agricultural development, and population increase. Each of these factors contributes to the rising demand for energy. This paper addresses the challenge of predicting peak energy demand (ED) by utilizing historical time series data from the past five years, combined with temperature data from Tamil Nadu’s official sources. We employed feature engineering techniques to prepare the data for machine learning models, specifically XGBoost regressor, lasso, and ridge regression. The time series data was then analyzed using both univariate and multivariate models, including auto regressive integrated moving average (ARIMA) and vector autoregressive (VAR) models. The results show that our models can effectively forecast ED, providing critical insights for policymakers and stakeholders involved in energy planning and resource management.
Volume: 38
Issue: 1
Page: 668-676
Publish at: 2025-04-01
1 2 3
...
1995 1996
Show 213 of 1996

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration