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

31,456 Article Results

Modified-vehicle detection and localization model for autonomous vehicle traffic system

10.11591/ijeecs.v37.i2.pp1183-1200
Amit Juyal , Sachin Sharma , Shuchi Bhadula
The modification of vehicles for financial gain is an evolving tendency observed in India. Recognizing and detecting of these modified illicit cars is an important but critical task in autonomous vehicles (AV). It is always possible for a cyclist or pedestrian to traverse obstacles or other fixed objects that appear in front of any moving vehicle. Vehicles that are autonomous or self-driving require a different system to quickly identify both stationary and moving objects. A deep learning model named you only look once version 5 (YOLOv5)-convolutional block attention module (CBAM) is proposed here for the Indian traffic system which is based on YOLOv5m. The proposed algorithm, YOLOv5-CBAM, has three major components. The first module, the backbone module is employed for feature extraction. The second module is to detect static as well as dynamic objects at the same time and the third CBAM module is adopted in the backbone and neck part, which mainly focuses on the more prominent features. Two cross stage partial (CSP) modules were used after every convolutional layer resulting in an additional head to the proposed model. Four head modules equipped with anchor boxes performed the final detection. For the present dataset, the proposed model showed 98.2% mean average precision (mAP), 98.4% precision, and 94.8% recall as compared to the original YOLOv5m.
Volume: 37
Issue: 2
Page: 1183-1200
Publish at: 2025-02-01

A novel CNN-ANN fusion approach for improved facial emotion detection

10.11591/ijeecs.v37.i2.pp959-967
Viraj Sawant , Husna Shaikh , Bhakti Palkar , Sanam Kazi , Wasim Jasani , Lamiya Rampurawala , Mohammed Naser Shaikh
In recent years, the field of emotion recognition has witnessed an increased interest due to the rise of deep learning techniques. However, one of the persistent difficulties in this domain, which we have attempted to address, is the variability in image sizes utilized. In this study, we have reviewed the work by different researchers and summarized their key findings. In our research, we introduce a novel technique that integrates the strengths of 1D convolutional neural networks (CNNs) and artificial neural networks (ANNs) through a late fusion model, leveraging CNNs' shared weights and automatic feature learning for spatial and temporal data, alongside ANN's comprehensive feature consideration. Our research findings highlight the effectiveness of this approach, which achieves a remarkable accuracy of 92.42%, along with other evaluation metrics demonstrating notable results. Furthermore, we conduct a comprehensive analysis of the proposed method, comparing it with advanced methods in the field of facial emotion recognition. Through this comparative analysis, we demonstrate the superiority of our proposed approach, addressing challenges that have not yet been addressed till date, thus leading to progress in this field.
Volume: 37
Issue: 2
Page: 959-967
Publish at: 2025-02-01

Lung cancer prediction with advanced graph neural networks

10.11591/ijeecs.v37.i2.pp1077-1084
Bineesh Moozhippurath , Jayapandian Natarajan
This research aims to enhance lung cancer prediction using advanced machine learning techniques. The major finding is that integrating graph convolutional networks (GCNs) with graph attention networks (GATs) significantly improves predictive accuracy. The problem addressed is the need for early and accurate detection of lung cancer, leveraging a dataset from Kaggle's "Lung Cancer Prediction Dataset," which includes 309 instances and 16 attributes. The proposed A-GCN with GAT model is meticulously engineered with multiple layers and hidden units, optimized through hyperparameter adjustments, early stopping mechanisms, and Adam optimization techniques. Experimental results demonstrate the model's superior performance, achieving an accuracy of 0.9454, precision of 0.9213, recall of 0.9743, and an F1 score of 0.9482. These findings highlight the model's efficacy in capturing intricate patterns within patient data, facilitating early interventions and personalized treatment plans. This research underscores the potential of graph-based methodologies in medical research, particularly for lung cancer prediction, ultimately aiming to improve patient outcomes and survival rates through proactive healthcare interventions.
Volume: 37
Issue: 2
Page: 1077-1084
Publish at: 2025-02-01

Performance analysis of 10 machine learning models in lung cancer prediction

10.11591/ijeecs.v37.i2.pp1352-1364
Joselyn Zapata-Paulini , Michael Cabanillas-Carbonell
Lung cancer is one of the diseases with the highest incidence and mortality in the world. Machine learning (ML) models can play an important role in the early detection of this disease. This study aims to identify the ML algorithm that has the best performance in predicting lung cancer. The algorithms that were contrasted were logistic regression (LR), decision tree (DT), k-nearest neighbors (KNN), gaussian Naive Bayes (GNB), multinomial Naive Bayes (MNB), support vector classifier (SVC), random forest (RF), extreme gradient boosting (XGBoost), multilayer perceptron (MLP) and gradient boosting (GB). The dataset used was provided by Kaggle, with a total of 309 records and 16 attributes. The study was developed in several phases, such as the description of the ML models and the analysis of the dataset. In addition, the contrast of the models was performed under the metrics of specificity, sensitivity, F1 count, accuracy, and precision. The results showed that the SVC, RF, MLP, and GB models obtained the best performance metrics, achieving 98% accuracy, 98% precision, and 98% sensitivity.
Volume: 37
Issue: 2
Page: 1352-1364
Publish at: 2025-02-01

Predicting enhanced diagnostic models: deep learning for multi-label retinal disease classification

10.11591/ijai.v14.i1.pp54-61
Sridhevi Sundararajan , Harikrishnan Ramachandran , Harshita Gupta , Yashraj Patil
In this study, we assess three convolutional neural network (CNN) architectures—VGG16, ResNet50, and InceptionV3 for multi classification of fundus images in the retinal fundus multi-disease image dataset (RFMID2), comprising of 860 images. Focusing on diabetic retinopathy, exudation, and hemorrhagic retinopathy, we preprocessed the dataset for uniformity and balance. Using transfer learning, the models were adapted for feature extraction and fine-tuned to our multi-label classification task. Their performance was measured by subset accuracy, precision, recall, F1-score, hamming loss, and Jaccard score. VGG16 emerged as the top performer, with the highest subset accuracy (84.81%) and macro precision (95.83%), indicating its superior class distinction capabilities. ResNet50 showed commendable accuracy (79.75%) and precision (86.70%), whereas InceptionV3 lagged with lower accuracy (66.67%) and precision (81.21%). These findings suggest VGG16’s depth offers advantages in multi-label classification, highlighting InceptionV3’s limitations in complex scenarios. This analysis helps optimize CNN architecture selection for specific tasks, suggesting future exploration of dataset variability, ensemble methods, and hybrid models for improved performance.
Volume: 14
Issue: 1
Page: 54-61
Publish at: 2025-02-01

Serial parallel dataflow-pipelined processing architecture based accelerator for 2D transform-quantization in video coder and decoder

10.11591/ijai.v14.i1.pp798-809
Sumalatha Shivarudraiah , Rajeswari Rajeswari
The video coder and decoder (CODEC) standards from MPEG-4 to the recent versatile video codec (VVC), adopted lossy compression methodologies, which involves transformation, quantization and entropy coding. The growing usage of video data in all means of communication demands more bandwidth and storage requirements. While compression with redundancy removal by transform coefficient coding, the focal point is the crucial sequential data flow and data processing structures. Handling the block wise data near to the processing unit prior and after computation will reduce the data waiting time of the processing unit, hence accelerating the targeted functionality. The proposed serial parallel data-flow pipelined processing architecture (SPDPA) accelerates the speed of processing unit by on chip data availability and parallel data accessing options and also with the pipeline operations of transformation, data transpose and quantization. The post implementation results of the architecture targeted to 16 nm and 28 nm field programmable gate array (FPGA) shows that there is a trade-off between power and frequency of operations for various block sizes. The design targeted to 16 nm works for higher frequencies with an average power consumption 0.64 w as compared to 28 nm FPGA which consumes less average power of 0.15 w.
Volume: 14
Issue: 1
Page: 798-809
Publish at: 2025-02-01

Dynamic spatio-temporal pattern discovery: a novel grid and density-based clustering algorithm

10.11591/ijai.v14.i1.pp397-407
Swati Pramod Meshram , Kishor P Wagh
Clustering is a robust machine- learning technique for exploration of patterns based on similarity of elements over multidimensional data. Spatio-temporal clustering aims to identify target objects to mine spatial and temporal dimensions for patterns, regularity, and trends. It has been applied in humancentric applications, such as recommendation systems, urban development and planning, clustering of criminal activities, traffic planning, and epidemiology to identify the extent of disease spread. Although the existing research work in the field of clustering relies widely on partition and densitybased methods, no major work has been carried out to handle the spatiotemporal dimension and understand the dynamics of temporal variation and connectivity between clusters. To address this, our paper proposes an algorithm to mine clustering patterns in spatiotemporal dataset using an adaptive, dynamic hybrid technique based on grid and density clustering. We adopt spatio-temporal partitioning of the virtual grid for distribution of data and reducing distance computation and increasing efficiency. Grouping the higher density regions along with neighborhood cluster density attraction rate to merge the clusters. This method has been experimentally evaluated over the Indian earthquake dataset and found to be effective with clustering silhouette index up to 0.93.
Volume: 14
Issue: 1
Page: 397-407
Publish at: 2025-02-01

Literacy extension programs of higher education institution in the Philippines: insights from stakeholders

10.11591/ijere.v14i1.29736
Matronillo Del Mundo Martin , Lhea dela Cruz Ildefonso
This descriptive research investigates the impact of extension programs from a college of teacher education on public elementary school teachers. Three programs, literacy (n=75), Catch Me and Teach Me strategy literacy program (n=64), and campus journalism (n=48), were evaluated. Participants reported profound positive impact from these programs, considering them effective or very effective. The literacy program significantly improved reading and writing skills, fostered a love for learning, and benefitted the community. However, challenges like outdated materials and overemphasis on rote memorization need addressing. The Catch Me and Teach Me strategy literacy program excelled in practical teaching strategies and hands-on learning but required additional time and support, emphasizing the need for a more personalized approach. The campus journalism program was lauded for its informativeness but faced venue, food quality, time management issues, and a desire for more diverse topics. These findings stress the importance of customized professional development, long-term impact assessment, cultural sensitivity, and community involvement. Effective, engaging training methods, feedback, and efficient resource allocation are vital for program improvement. The research aims to enhance extension services’ quality for the community's benefit, providing valuable guidance to improve these programs and cater to participants' diverse needs.
Volume: 14
Issue: 1
Page: 544-556
Publish at: 2025-02-01

Psychometric properties of emotional intelligent scale: the application for university students in Indonesia

10.11591/ijere.v14i1.28599
Amin Akbar , Zulakbal Abd Karim , Jaffry Zakaria , Suryanef Suryanef , Muh Khairul Wajedi Imami , Utami Syahdiah , Hilwa Alfiani Fitri
The current research aims to assess the psychometric properties of the emotional intelligence scale among university students in Indonesia. This research used a survey design. The current research participants were 288 university students in Palembang, West Nusa Tenggara, Kupang, Yogyakarta, and Jakarta, Indonesia. Two procedures were used to analyze the data: exploratory factor analysis (EFA) and confirmatory factor analysis (CFA). The results showed that EFA with comprehensive techniques that compromise parallel analysis yielded a 5-factor solution: empathy with five items, handling relationships with five items, motivation for oneself with six items, self-awareness with seven items, and managing emotion with eight items. The five factors solution was confirmed through CFA with the value: Chi square=2.631, Tucker-Lewis’s index (TLI)=.804, comparative fit index (CFI)=.823, root mean square error of approximation (RMSEA)=.075, and standardized root mean residual (SRMR)=.743. The scale validation and reliability were tested through average variance extracted (AVE) with the value ranged from 0.271 to 0.594, construct reliability (CR) with the value ranged from 0.706 to 0.879, and Cronbach’s alpha with the value ranged from 0.706 to 0.879. Therefore, based on psychometric analysis, the scale is valid and reliable to be used in measuring emotional intelligence among university students in Indonesia.
Volume: 14
Issue: 1
Page: 157-170
Publish at: 2025-02-01

Research trends in spatial modeling of PM2.5 concentration using machine learning: a bibliometric review

10.11591/ijeecs.v37.i2.pp1317-1327
Retno Tri Wahyuni , Dirman Hanafi , M. Razali Tomari , Dadang Syarif Sihabudin Sahid
Spatial modeling is commonly used to map research variables, including particulate matter 2.5 (PM2.5) concentrations, in specific areas. The article that surveys publications on the application of machine learning in spatial modeling of PM2.5 using bibliometric methods has not been identified yet. This paper aims to analyze trends in applying machine learning in the spatial modeling of PM2.5 using bibliometric methods. The review was conducted on publications indexed in the Scopus database over the decade (2014–2023) comprising 335 articles. The analysis included co-authorship and co-occurrence using VOSviewer. From the two stages of analysis, it can be concluded that research on this topic has constantly increased over the past 10 years, with the highest productivity coming from researchers in China. This research topic is multidisciplinary, with most publications appearing in environmental science. The research also shows a very high collaboration rate of 0.98. A deeper examination of the keywords reveals the most commonly used machine learning techniques by researchers. The random forest method is the most frequently found in the analyzed documents, followed by deep learning, long short-term memory (LSTM), extreme gradient boosting (XGBoost), and ensemble model.
Volume: 37
Issue: 2
Page: 1317-1327
Publish at: 2025-02-01

Machine learning for the detection of soil pH, macronutrients, and micronutrients with crop and fertilizer recommendations

10.11591/ijai.v14.i1.pp439-446
John Joshua Montañez , Jeffrey Sarmiento
The study aims to determine the levels of soil parameters such as soil pH, macronutrients, and micronutrients. After determining said parameters, the system appropriately recommends crops and fertilizers suitable for the soil samples. For soil pH and macronutrient levels, i.e., nitrogen, phosphorus, and potassium, these parameters can be detected using the soil test kit. Meanwhile, for soil micronutrients, i.e., copper, iron, and zinc, there is a need for the development of appropriate assays for colorimetric processes that can be done for the appropriate determination of said micronutrients. Comparison of available machine learning such as support vector machine algorithm, naïve Bayes algorithms, and K-nearest neighbor algorithm is a must to determine the well-fit algorithm that is considered fast and has high predictive power in classification and regression. The outputs of the colorimetric and spectrometric processes are the inputs in the machine learning activities intended for crop and fertilizer recommendation.
Volume: 14
Issue: 1
Page: 439-446
Publish at: 2025-02-01

Hybrid resource optimization strategy in heterogeneous wireless networks

10.11591/ijeecs.v37.i2.pp829-838
Nagaraja Gadde , Rashmi Shivaswamy , Ramesh Babu Halasinanagenahalli Siddamal , Gowrishankar Gowrishankar , Govindaih Thimma Raju , Subramani Suryakumar Prabhu Vijay
The future generation of heterogeneous wireless networks (HWNs) will combine various radio access technologies for connecting various mobile subscribers (MS) based on the quality of service (QoS) and wireless network parameters, connecting MS to the best possible wireless network (WN) has been a trending research topic in HWNs. Existing resource optimization methods are designed to meet the QoS of network criteria and user preferences are neglected. Very limited work is done for resource optimization considering user preferences. However, these models are designed considering multi-mode terminals (MMTs) running a single service at a time under a low-density network; as a result, cannot be adopted to run multiple services simultaneously and; thus, fail to meet current users’ service dynamics requirement. Further, fails to bring good tradeoffs between reducing interference and improving performance. In addressing the research problem this work introduced a hybrid resource optimization strategy (HROS) to reduce interference by establishing channel availability and enhancing resource utilization through game theory. The HROS proves the existence of nash equilibrium (NE) improves throughput by 16.32% and reduces collision by 26.16% over the existing resource optimization-based network selection (RONS) scheme.
Volume: 37
Issue: 2
Page: 829-838
Publish at: 2025-02-01

Machine learning based prediction of production using real time data of a point bottom sealing and cutting machine

10.11591/ijeecs.v37.i2.pp1376-1386
Fathima Rani Irudaya Mary Diana , Subha Rajendran , Selvadass Muthusamy
The packaging sector utilizes polypropylene based flexible materials for diverse product packaging with customization options in size and design achieved through advanced flexographic printing and point bottom sealing and cutting machines. Accurately estimating production time and quantity is vital for efficient planning and cost estimation, with factors like material dimensions, thickness, and cutting machine speed influencing production output. Understanding the intricate relationship between these parameters is essential for comprehending their impact on production time and quantity. Predicting production quantity before production begins helps in determining machine runtime and associated costs. In large-scale production systems, machine learning (ML) has proven to be a useful tool for resource allocation and predictive scheduling. An attempt has been made in this paper to develop an intelligent model for predicting the yield of a cutting machine using artificial neural network (ANN), support vector regression (SVR), regression tree ensemble (RTE) and gaussian process regression (GPR). The most crucial features for prediction were identified and the hyperparameters of the ML models were optimized to create efficient models for prediction. A comparative analysis of the four models revealed that the GPR model was simple and effective with least training time and prediction error.
Volume: 37
Issue: 2
Page: 1376-1386
Publish at: 2025-02-01

Imitation of the human upper limb by convolutional neural networks

10.11591/ijai.v14.i1.pp193-203
Paula Useche Murillo , Robinson Jimenez Moreno , Javier Eduardo Martinez Baquero
The paper outlines the development of an algorithm focused on imitating movements of a human arm and replicating strokes generated by the user's hand within a working environment. The algorithm was crafted to discern the position of either the user's left or right arm, tracking each section (fingers, wrist, elbow, and shoulder) through a detection and tracking system. These movements are then replicated onto a virtual arm, simulating the actions of a cutting tool, generating strokes as it moves. Convolutional neural networks (CNNs) were employed to detect and classify each arm section, while geometric analysis determined the rotation angles of each joint, facilitating the virtual robot's motion. The stroke replication program achieved an 84.2% accuracy in stroke execution, gauged by the closure of the polygon, distance between initial and final drawing points, and generated noise, which was under 10%, with a 99% probability of drawing a closed polygon. A Fast region-based convolutional neural network (Fast R-CNN) network detected each arm section with 60.2% accuracy, producing detection boxes with precision ranging from 17% to 59%. Any recognition shortcomings were addressed through mathematical estimation of missing points and noise filters, resulting in a 90.4% imitation rate of human upper limb movement.
Volume: 14
Issue: 1
Page: 193-203
Publish at: 2025-02-01

An ontology-based knowledge modeling for the rite of Bai Sri Su Kwan: a ritual of the Greater Mekong Subregion

10.11591/ijai.v14.i1.pp788-797
Suwannee Hoaihongthong , Vispat Chaichuay , Kanyarat Kwiecien
The development of ontologies is crucial in digital humanities research. This study focuses on creating a system to extract meaning from knowledge related to the Bai Sri Su Kwan ritual. Addressing semantic gaps, the second phase of our research outlines methods for developing an ontology for Bai Sri Su Kwan rituals. To fully understand this significant ritual in the Mekong Basin, we employed a theoretical framework with seven ontology development steps, using the Hozo Ontology Editor. Our ontology includes nine main classes: Bai Sri Su Kwan (A ritual subclass), persons, chants, belief, purpose, wish, literature, locations, and equipment. The Bai Sri Su Kwan subclass connects with all other classes in the ontology. This ontology forms the basis for a meaning search system for the Bai Sri Su Kwan ceremony in future research stages. The ontology was evaluated syntactically through human assessment and the OOPS! Ontology Pitfall Scanner. Validation results for the Bai Sri Su Kwan Ontology show no pitfalls in critical dimensions, indicating high integrity and reliability.
Volume: 14
Issue: 1
Page: 788-797
Publish at: 2025-02-01
1 2 3
...
2097 2098
Show 376 of 2098

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