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

29,922 Article Results

SCADA system in water storage tanks with NI vision LabVIEW

10.11591/ijra.v14i3.pp381-392
Kartika Kartika , Misriana Misriana , M. Fathan Naqi , Asran Asran , Misbahul Jannah , Arnawan Hasibuan , Suryati Suryati
Advances in technology have driven the need for efficient water management systems. This study presents a SCADA-based water management system that integrates LabVIEW and Arduino to monitor and regulate water levels and flow rates in a storage tank. The system uses an HC-SRF04 ultrasonic sensor for water level measurement with 99.77% accuracy and an HX710 pressure sensor, which achieves 98.54% accuracy. The LabVIEW interface displays real-time data, giving users an intuitive view of system performance. A proportional integral derivative (PID) algorithm optimizes the water pump through pulse width modulation (PWM), achieving water flow rate control. The Ziegler-Nichols method tunes the PID parameters to Kp = 16.59, Ti = 1.102, and Td = 0.2755. This tuning ensures the system maintains a consistent target flow rate of 4 liters per minute (L/min) with minimal variation. Initial testing showed a 2.5% overshoot but stabilized at the desired flow rate within 10 seconds, indicating effective control. This SCADA system reduces water and energy waste by enabling continuous real-time monitoring and control. The system provides accurate data through a LabVIEW interface, ensuring effective and informed operational decisions. This robust solution supports efficient water management for industrial and environmental applications, contributing to sustainability and resource optimization.
Volume: 14
Issue: 3
Page: 381-392
Publish at: 2025-09-01

Robot Gaussian-historical relocalization: inertial measurement unit-LiDAR likelihood field matching

10.11591/ijra.v14i3.pp438-450
Ye-Ming Shen , Min Kang , Jia-Qiang Yang , Zhong-Hou Cai
Robot localization is a foundational technology for autonomous navigation, enabling task execution and adaptation to dynamic environments. However, failure to return to the correct pose after power loss or sudden displacement (the “kidnapping” problem) can lead to critical system failures. Existing methods often suffer from slow relocalization, high computational cost, and poor robustness to dynamic obstacles. We propose a novel inertial measurement unit (IMU)-LiDAR fusion relocalization framework based on Gaussian historical constraints and adaptive likelihood field matching. By incorporating IMU-derived yaw constraints and modeling historical poses within a 3σ Gaussian region, our method effectively narrows the LiDAR search space. Curvature and normal vector-based feature extraction reduces point cloud volume by 50–70%, while dynamic obstacle filtering via multi-frame differencing and neighborhood validation enhances robustness. An adaptive spiral search strategy further refines pose estimation. Compared to ORB-SLAM3 and adaptive Monte Carlo localization (AMCL), our method maintains comparable accuracy while significantly reducing relocalization time and CPU usage. Experimental results show a relocalization success rate of 84%, average time of 1.68 seconds, and CPU usage of 38.4%, demonstrating high efficiency and robustness in dynamic environments.
Volume: 14
Issue: 3
Page: 438-450
Publish at: 2025-09-01

Adaptive deep learning framework for multi-scale plant disease detection

10.11591/ijeecs.v39.i3.pp1976-1989
Tejashwini C. Gadag , D. R. Kumar Raja
Plant disease detection is a critical task in modern agriculture, directly impacting crop yield, food security, and sustainable farming practices. Traditional methods rely on expert visual inspection, which is time-consuming, inconsistent, and inaccessible in remote areas. This study introduces an advanced deep learning (DL) framework, the adaptive multi-scale convolutional network (AMS-ConvNet), optimized for accurate and efficient plant disease identification. hierarchical feature extraction network (HFEN) integrates the multi-domain attention framework (MDAF) and adaptive scale fusion module (ASFM) to enhance feature extraction and address challenges such as complex natural backgrounds, non-uniform leaf structures, and varying environmental conditions. The proposed framework employs pre-trained knowledge adaptation (PTKA) techniques to improve generalization and overcome data scarcity. Comprehensive evaluations on multiple datasets demonstrate the model's better performance, achieving state-of-the-art metrics in precision, recall, F1-score, and accuracy. Furthermore, this approach ensures scalability and adaptability, making it suitable for real-field conditions. The study emphasizes the importance of robust, automated solutions in minimizing crop losses, reducing labor costs, and enhancing agricultural sustainability through precision disease management.
Volume: 39
Issue: 3
Page: 1976-1989
Publish at: 2025-09-01

Energy efficient clustering and routing method for Internet of Things

10.11591/ijra.v14i3.pp418-428
Bhawna Ahlawat , Anil Sangwan
The Internet of Things is crucial in monitoring environmental conditions in remote areas, but it faces significant challenges related to energy consumption, which affects network longevity and coverage. Clustering has proven effective in prolonging the life of sensor networks. Adaptive clustering in wireless sensor networks allows for more effective cluster organization via real-time rearranging of sensor nodes according to important parameters, which include energy levels and the distance between them. Fruit fly algorithm (FFA) and ant colony optimization (ACO) are emerging as encouraging techniques for creating clusters and establishing paths, respectively. This paper describes the use of the FFA to make the clustering process better by selecting the best cluster head and reducing energy consumption. This paper proposes a novel solution that integrates ACO for establishing paths with FFA for clustering. This method is tested in both homogeneous and heterogeneous settings using MATLAB, comparing its performance with two existing algorithms: low energy adaptive clustering hierarchy (LEACH) and biogeography-based optimization algorithm (BOA). According to the findings, the suggested algorithm performs noticeably better than BOA and LEACH in the context of coverage area and network service period, especially in heterogeneous settings.
Volume: 14
Issue: 3
Page: 418-428
Publish at: 2025-09-01

IntelliDrive autonomous robot powered by large language model

10.11591/ijra.v14i3.pp339-347
Imran Ulla Khan , D. R. Kumar Raja
The rapid advancements in artificial intelligence (AI) and robotics have paved the way for innovative autonomous systems capable of performing complex tasks. This project integrates robotics with Large Language Models (LLMs) to develop an intelligent, versatile and user-friendly robotic system. The robot is designed to interpret structured commands, make real-time decisions, and navigate autonomously in dynamic environments, addressing key challenges faced by traditional autonomous systems. Central to the system is a Raspberry Pi 4, which serves as the main processing unit, integrating components such as a webcam for visual data capture, an L298N motor driver for motor control, and a Bluetooth speaker for real-time feedback. The LLM API enables the robot to process natural language commands, providing context-aware task execution and adaptability to changing scenarios. Testing has demonstrated the system’s ability to perform autonomous navigation, detect obstacles, and execute tasks effectively. This research offers a foundation for various industries, including logistics, healthcare, education, and hazardous environment operations. By incorporating LLMs the robot overcomes limitations of traditional rule-based systems, enhancing dynamic decision-making and user interaction. With its modular design and scalability, it bridges the gap between human-like intelligence and mechanical precision, setting the stage for future advancements in AI-driven robotics.
Volume: 14
Issue: 3
Page: 339-347
Publish at: 2025-09-01

Extended Kalman filter based unconstrained model predictive control of a complex nonlinear system: the quadruple tank process

10.11591/ijeecs.v39.i3.pp1553-1561
Zohra Zidane
This paper proposes the model predictive controller (MPC) based on the Kalman filter for a complicated nonlinear system—the quadruple tank process (QTP). The control of a multivariable and nonlinear system like a QTP is a difficult job. A number of nonlinear design techniques are implemented to ameliorate the pursuit performance of the QTP, however, the nonlinear techniques make implementation composite and computationally unsuitable. In this work, an unconstrained MPC is planed for the QTP experiences and it is controlled for both minimum and non-minimum sentence configurations in order to follow the wanted track. Its performance can be damaged once system is pass from minimum to non-minimum phase region and inversely. The unknown states required for model predictive control design are rebuilt using an extended Kalman filter. The design of model predictive control and extended Kalman filter is based on the QTP and the achievement of the proposed controller is checked for the monitoring of references. All results of simulation are affected using the MATLAB software. The results of the simulation show the capability and power of the suggested controller in respect of monitoring the trajectory and state estimation.
Volume: 39
Issue: 3
Page: 1553-1561
Publish at: 2025-09-01

Evaluating the development and cutting capacity of a one-square computer numeric controlled milling machine

10.11591/ijra.v14i3.pp451-462
Oluwaseun Kayode Ajayi , Ayodele Temitope Oyeniran , Shengzhi Du , Babafemi Olamide Malomo , Kolawole Oluwaseun Alao , Quadri Ayomide Omotosho , Marvellous Oluwadamilare Fawole , Ayomide Isaiah Lasaki , Godwin Thompson
Traditional subtractive technology is rapidly losing significance with the advent of digital manufacturing technologies, which offer affordable machining with high accuracy and repeatability. Computer numeric controlled (CNC) machining has been around for a while; however, it has been costly to own one. Since the concept of CNC machining is now broadly understood and open-source software is available for control, designers can make use of available local materials to develop cheaper CNC machines. Hence, this presents the evaluation of the design and development of a one-square-meter CNC milling machine. The control was implemented on Arduino Uno, while open-source Universal G-code Sender (UGS) and G-code reference block library (GRBL) were used for the G-code generation and machine control, respectively. The built CNC was calibrated and tested on wood and plastic materials, and the resulting products were acceptable in accuracy up to ±0.02 mm in the first trial, but attained perfect accuracy by the third trial. Multiple tests repeatedly showed that accuracy was maintained. Since the machine is reconfigurable, future work entails automation and incorporating laser cutting capabilities into the machine.
Volume: 14
Issue: 3
Page: 451-462
Publish at: 2025-09-01

Effective vocabulary learning through augmented and virtual reality technologies

10.11591/ijeecs.v39.i3.pp1855-1864
Arifin Arifin , Nofvia De Vega , Syarifa Rafiqa
This study investigates the role of augmented reality (AR) and virtual reality (VR) technologies in enhancing vocabulary learning achievement among students. It addresses the need for innovative instructional methods that improve engagement and retention compared to traditional approaches. Utilizing a survey-based quantitative design supplemented by qualitative interviews, the research involved 220 participants from diverse educational backgrounds, providing a robust dataset for analyzing the impact of these immersive technologies on vocabulary acquisition. Structured questionnaires assessed engagement levels, learning outcomes, and user experiences with AR and VR applications designed explicitly for vocabulary enhancement. The findings reveal that 75% of participants reported improved vocabulary retention, highlighting the interactive nature of AR and VR as a significant factor influencing student attitudes toward vocabulary learning. The study concludes contextualized learning scenarios with interactive features are more effective than passive learning environments. Additionally, it suggests future research directions, including developing personalized learning paths and integrating collaborative features to enhance group learning experiences. The implications for educators emphasize the potential of AR and VR technologies to transform vocabulary instruction and foster deeper engagement among learners.
Volume: 39
Issue: 3
Page: 1855-1864
Publish at: 2025-09-01

An efficient machine learning framework for optimizing hyperspectral data analysis in detecting adulterated honey

10.11591/ijeecs.v39.i3.pp1776-1786
Ashwini N. Yeole , Guru Prasad M. S. , Santosh Kumar
Honey adulteration detection involves employing spectral data, often utilizing machine learning (ML) techniques, to identify the presence of impurities or additives in honey. This study aims to explore ML models through the collection of a hyperspectral honey dataset with limited samples and 128 features. Three distinct feature selection (FS) methods i.e., Boruta, repeated incremental pruning to produce error reduction (RIPPER), and gain ratio attribute evaluator (GRAE) are applied to extract important features for decision-making. Then, the feature-selected dataset is classified through four effective ML algorithms, such as support vector machine (SVM), random forest (RF), logistic regression (LR), and decision tree (DT). Accuracy, F1-score, Kappa Statistics, and Matthews correlation coefficient (MCC) are the performance metrics used to assess the results of ML algorithms. RIPPER FS technique gave the best results by improving its accuracy values from 79.05% (primary data) to 91.89% (augmented data) for the RF classifier model and 74.93% (primary data) to 91.89% (augmented data) for the DT classifier model. These detailed examinations of the experiments demonstrate that proper finetuning of the ML methods can play a vital role in optimizing hyperspectral data analysis for detecting adulteration levels in honey samples.
Volume: 39
Issue: 3
Page: 1776-1786
Publish at: 2025-09-01

Five-Tier BI architecture with tuned decision trees for e-commerce prediction

10.11591/ijeecs.v39.i3.pp1633-1641
Thiruneelakandan Arjunan , Umamageswari A.
In recent times, remarkable performance has been shown by large language models (LLMs) in a range of natural language processing (NLP) such as questioning, responding, document production, and translating languages. In today's competitive business landscape, understanding consumer behaviour in online buying is crucial for the success of e-commerce platforms. The work proposes a novel Five-Tier service-oriented BI architecture (FSOBIA) that leverages advanced tuned decision tree (ATDT) techniques for predicting online buying behaviour. The proposed FSOBIA offers e-commerce platforms a scalable and adaptable solution for gaining insights into consumer preferences and making informed business decisions. The goal of FSOBIA's design and implementation is to meet the needs of evolving users and quicker service. Experimental evaluations on real-world datasets in FSOBIA achieved over 95% prediction accuracy, outperforming traditional models: Decision trees (82%), and XGBoost (91%), while offering better scalability and computational efficiency.
Volume: 39
Issue: 3
Page: 1633-1641
Publish at: 2025-09-01

Optimizing timing closure and enhancing efficiency in RTL design: a focus on physical design tasks for I2C design blocks

10.11591/ijeecs.v39.i3.pp1525-1540
Madhura Ramegowda , Krutthika Hirebasur Krishnappa , Divyashree Yamadur Venkatesh , Kokila Sreenivasa
Achieving precise timing closure in integrated circuit (IC) design is a significant challenge, especially with today's rapid technology advancements and intricate design specifications. Even with intense post-synthesis optimization, timing violations persist particularly in multi-corner, multi-mode designs. This research work emphasizes the necessity for power-efficient methods and streamlined approaches to boost timing closure and physical verification. Modern IC design thrives on effective physical design optimization strategies, usually tackled top-down. Clock tree synthesis (CTS) is transformative which effectively addresses clock deviation, latency, transition time, and insertion delay. This investigation mainly focuses on improving timing closure for inter integrated circuit (I2C) design blocks using custom-designed ccopt_spec and mmmc.tcl files to support multi-corner, multi-mode settings and significantly reduces register-to-register path violations from 80 to. 0. Additionally, the development and the usage of mmmc.tcl and global files are highlighted as critical components in the design process.
Volume: 39
Issue: 3
Page: 1525-1540
Publish at: 2025-09-01

Exploring the impact of artificial intelligence driven solutions on early detection of cardiac arrest

10.11591/ijeecs.v39.i3.pp1938-1945
Tejashree Venkatesha , Saravana Kumar Sundararajan
The advancement of medical science and technology has yet not evolved up with a concrete solution towards early detection of cardiac arrest from practical deployment. It is noted that artificial intelligence (AI) has been proving a potential contributor to address this state of diagnosis emergency. In current era of research work, there has been various implementation model and review work has been carried out towards advocating AI for determining early onset of cardiac arrest; however, there are various contradiction and shortcoming which is quite challenging to be extracted. Hence, the current manuscript presents a review of existing methodology by presenting core taxonomies of recent AI-methods towards early detection of cardiac arrest. Various standard dataset has been studied too to find associated advantages and limitation that restrict the actual potential of AI to prediction. The outcome presents novel highlights of research gap, trade-off, and crisp highlights of effectiveness of existing AI approaches as a study contribution.
Volume: 39
Issue: 3
Page: 1938-1945
Publish at: 2025-09-01

An Internet of Things based mobile-controlled robot with emergency parking system

10.11591/ijra.v14i3.pp370-380
Abdul Kareem , Varuna Kumara , Vishwanath Madhava Shervegar , Karthik S. Shetty , Manvith Devadig , Mahammad Shamma , Kiran Maheshappa
This paper presents an Internet of Things (IoT) based mobile-controlled car with an emergency parking system that integrates advanced functionalities to enhance safety and user convenience, utilizing the ESP32 microcontroller as its core. The system allows users to control the car remotely via a mobile application, leveraging Wi-Fi connectivity for seamless communication. Key features include LED indicators for various operations such as reversing, left and right turns, and brake activation, ensuring clear signaling in real-time. The innovative emergency parking system detects obstacles or emergencies using sensors and halts the vehicle automatically, reducing the risk of accidents. The car's lightweight, energy-efficient design, combined with the versatility of the ESP32, ensures a responsive and reliable operation. Additionally, the system provides an intuitive user interface through the mobile app, enabling precise control and real-time feedback. The proposed system is faster in response compared to the existing systems. Moreover, the proposed system consumes less energy, and hence, it uses the battery more efficiently, extending the time of operation. Lower power consumption ensures longer operation time, reducing the need for frequent charging and making the system more practical. This paper demonstrates the integration of IoT and embedded systems to create a smart vehicle solution suitable for various applications, including robotics, automation, and personal transport. Its cost-effectiveness and scalability make it a viable choice for both hobbyists and developers.
Volume: 14
Issue: 3
Page: 370-380
Publish at: 2025-09-01

A comparative study of CNN architectures for the detection of tomato leaf diseases

10.11591/ijeecs.v39.i3.pp1587-1594
Soumia Benkrama , Benyamina Ahmed , Nour El Houda Hemdani
Recent advancements in computer vision and machine learning (ML) have revolutionised various sectors, including precision agriculture (PA). In our study, we focused on detecting tomato leaf diseases (TLD) using deep learning (DL) techniques. Using a convolutional neural network (CNN) model, we developed an agricultural image index to accurately detect TLD. By utilizing available datasets from Kaggle, we trained our model to recognize various TLDs. To determine the most effective one, we compared multiple architectures, including VGG, ResNet, and EfficientNetB1. The obtained results demonstrated a classification accuracy of over 99% on the test set. This approach has allowed us to accelerate and enhance the disease detection process, positively impacting agricultural communities by reducing crop losses and enabling early intervention in case of disease outbreaks. Our study highlights the effectiveness of CNN models in the detection of TLD, paving the way for future applications in PA.
Volume: 39
Issue: 3
Page: 1587-1594
Publish at: 2025-09-01

Inertia factor and crossover strategy based particle swarm optimization for feature selection in emotion classification

10.11591/ijeecs.v39.i3.pp1704-1713
Shilpa Somakalahalli Byreddy , Shashikumar Dandinashivara Revanna
Emotion recognition using electroencephalography (EEG) is a better choice because it can’t be easily mimicked like facial expressions or speech signals. The emotion of EEG signals is not the same and vary from human to human, as everyone has different emotional responses to similar stimuli. Existing research has achieved lesser classification accuracy as it relies on whole feature subsets that include irrelevant features for classifying emotions. This research proposes the inertia factor and crossover strategy (IFCS)-based particle swarm optimization (PSO) algorithm to select relevant features for classification, which removes irrelevant features and enhances classification performance. Then, the self-attention with gated recurrent unit (SA-GRU) method is developed to classify the valence and arousal emotion classes, which focuses much on the significant parts of emotions and reaches high classification accuracy. The proposed IFCS-PSO and SA with GRU method achieved an accuracy of 98.79% for the valence class and 98.03% for the arousal class of the DEAP dataset, outperforming traditional approaches such as convolutional neural networks (CNN).
Volume: 39
Issue: 3
Page: 1704-1713
Publish at: 2025-09-01
1 2 3
...
1994 1995
Show 126 of 1995

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