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

A fuzzy inference system for hand injury level classification using surface electromyography signals

10.11591/ijra.v14i1.pp103-112
Mark Joseph Bullo Enojas
The surface electromyography (SEMG) is extensively used in assessing injuries in the musculoskeletal parts of the body. Integrating intelligence in such applications impacted the development of intelligent medical devices. The conventional way of assessing hand injury level is manually and subjectively done by experts to identify the type of rehabilitation program recommended to the patient. This work uses SEMG data to classify hand injury levels through a fuzzy inference system (FIS). Three of the many features of the SEMG signal were selected based on its high distinction levels, namely, the root-mean-square, enhanced mean-absolute value, and the waveform length. Segmentation through a sliding window method is used for feature extraction. The FIS rules were designed based on the assessment guide of the experts. A Mamdani-type FIS classifier was used with membership functions which are a combination of trapezoidal and triangular types. A MATLAB Simulink model was also designed to test the FIS system. The setup effectively identified injury levels through tests with a healthy subject, wherein no muscle activation means an injury, while the full fist, as a full muscle activation or healthy. In between signal values vary with different injury levels. In the future, this setup will be tested on patients in a rehabilitation clinic for validation.
Volume: 14
Issue: 1
Page: 103-112
Publish at: 2025-03-01

RNN Diabetic framework for identifying diabetic eye diseases

10.11591/ijeecs.v37.i3.pp1830-1844
Arwa Albelaihi , Dina M. Ibrahim
Many areas of image identification and classification for medical imaging diagnostics have greatly benefited from deep learning (DL). Diabetic retinopathy (DR) will become the most common cause of blindness worldwide, making diabetes a major threat to public health. This research proposes an automated identification system using deep recurrent neural networks (RNNs) to identify and classify four categories of diabetic eye diseases: DR, cataract, glaucoma, and diabetic macular edema (DME). We use three different model architectures based on RNN and their types, we called our proposed system RNN Diabetic framework. These models are combined with one of the commonly used architectures that support sufficient accuracy and speed for the model which is residual network (ResNet)152V2. The three model architectures are RNN+ResNet152V2, gated recurrent unit (GRU)+ResNet152V2, and bidirectional GRU (Bi-GRU)+ResNet152V2. The proposed models were assessed as collected datasets: DIARETDB0, DIARETDB1, messidor, HEI-MED, ocular, and retina. A full analysis and evaluation of these three deep RNN architectures are presented. The experiments showed that the Bi-GRU+ResNet152V2 model worked better than the other two proposed models. In addition, we compare these three proposed models with the previous studies and find that the proposed Bi-GRU+ResNet152V2 model achieves the highest results with accuracy equal to 99.8%, 98.1% sensitivity, 98.6% specificity, 99.8% precision, 99.8% F1 score, and 99.8% areas under the curve (AUC).
Volume: 37
Issue: 3
Page: 1830-1844
Publish at: 2025-03-01

Tomato leaf disease detection using Taguchi-based Pareto optimized lightweight CNN

10.11591/ijeecs.v37.i3.pp1772-1784
Bappaditya Das , C. S. Raghuvanshi
The prospect of food security becoming a global danger by 2050 due to the exponential growth of the world population. An increase in production is indispensable to satisfy the escalating demand for food. Considering the scarcity of arable land, safeguarding crops against disease is the best alternative to maximize agricultural output. The conventional method of visually detecting agricultural diseases by skilled farmers is time-consuming and vulnerable to inaccuracies. Technology-driven agriculture is an integral strategy for effectively addressing this matter. However, orthodox lightweight convolutional neural network (CNN) models for early crop disease detection require fine-tuning to enhance the precision and robustness of the models. Discovering the optimal combination of several hyperparameters might be an exhaustive process. Most researchers use trial and error to set hyperparameters in deep learning (DL) networks. This study introduces a new systematic approach for developing a less sensitive CNN for crop leaf disease detection by hyperparameter tuning in DL networks. Hyperparameter tuning using a Taguchi-based orthogonal array (OA) emphasizes the S/N ratio as a performance metric primarily dependent on the model’s accuracy. The multi-objective Pareto optimization technique accomplished the selection of a robust model. The experimental results demonstrated that the suggested approach achieved a high level of accuracy of 99.846% for tomato leaf disease detection. This approach can generate a set of optimal CNN models’ configurations to classify leaf disease with limited resources accurately.
Volume: 37
Issue: 3
Page: 1772-1784
Publish at: 2025-03-01

Anomaly based detection in time series data on IoT systems using statistical models

10.11591/ijeecs.v37.i3.pp1845-1855
Mouna Boujrad , Mohammed Amine Kasmi , Noura Ouerdi , Yasser Lamlili El Mazoui Nadori
The internet of things (IoT) has become a real revolution that represents technological innovation in all domains, it becomes more and more integrated into human activities starting from personal needs, to professional eras including industry, logistics, healthcare. Yet this technology didn’t only bring advantages to all industries, it also creates new challenges mostly security-related, due to the specifications of the IoT environment: its heterogeneity, the restricted resources, and the continuous enormous sensitive data generated and exchanged on the IoT ecosystem. In this paper, we propose a study of statistical models (autoregression, moving-average, autoregression-movingaverage, autoregression integrated movingaverage, seasonal autoregression integrated movingaverage) to build an anomaly-based detection model for times series data, to detect abnormal behavior that can be explained by a sensor failure, or a compromised sensor. The proposed anomaly-based detection relies on defining the data behavior and creating a profile on the assumed normal state, the created profile will be used as knowledge to predict future values to which real records will be compared, any deviation from the predicted data will be considered as abnormal, that indicates an anomaly has occurred on the sensor or the exchanged data. The proposed approach will help improve accuracy, reliability, trustworthiness, and data integrity.
Volume: 37
Issue: 3
Page: 1845-1855
Publish at: 2025-03-01

A novel dataset and part-of-speech tagging approach for enhancing sentiment analysis in Kannada

10.11591/ijeecs.v37.i3.pp1661-1671
Sunil Mugalihalli Eshwarappa , Vinay Shivasubramanyan
The problem addressed in this research is the limited availability of labelled datasets and effective sentiment analysis tools for the Kannada language. Existing challenges include linguistic variations, cultural diversities, and the absence of comprehensive datasets designed specifically for sentiment analysis in Kannada. This research aims to enhance sentiment analysis capabilities for the Kannada language, addressing challenges posed by linguistic variations and limited labelled datasets. A novel Kannada dataset derived from SemEval 2014 task 4 was created using a conversion process. The dataset was processed using part-of-speech tagging, and a specialized model called K-BERT (Kannada bidirectional encoder representations from transformers) was introduced and implemented using Python within the Anaconda environment. Performance evaluation results showcased K-BERT's superiority over traditional machine learning (ML) algorithms and the BERT model, achieving an accuracy of 0.98, precision of 0.97, recall of 0.97, and F-score of 0.98 in sentiment classification for Kannada text data. This work contributes a unique Kannada dataset, introduces the K-BERT model specifically designed for Kannada sentiment analysis, and emphasizes the importance of collaborative efforts in advancing natural language processing (NLP) research for multilingual environments.
Volume: 37
Issue: 3
Page: 1661-1671
Publish at: 2025-03-01

Performance comparison of optical flow and background subtraction and discrete wavelet transform methods for moving objects

10.11591/ijra.v14i1.pp93-102
Monika Sharma , Kuldeep Singh Kaswan , Dileep Kumar Yadav
Self-driving cars and other autonomous vehicles rely on systems that can recognize and follow objects. The ways help people make safe decisions and navigate by showing things like people, cars, obstacles, and traffic lights. Computer vision algorithms encompass both object detection and tracking. Different methods are specifically developed for picture or video analysis not only to identify items within the visual content but also to accurately determine their precise locations. This can operate independently as an algorithm or as a constituent of an item-tracking system. Object tracking algorithms can be used to follow objects over video frames, providing a contrasting approach. The research article focuses on the mathematical model simulation of optical flow, background subtraction, and discrete wavelet transform (DWT) methods for moving objects. The performance evaluation of the methods is done based on simulation response time, accuracy, sensitivity, and specificity doe several images in different environments. The DWT has shown optimal behavior in terms of the response time of 0.27 seconds, accuracy of 95.34 %, selectivity of 95.96 %, and specificity of 94.68 %.
Volume: 14
Issue: 1
Page: 93-102
Publish at: 2025-03-01

Development of newton dynamometer instrumentation integrated with smart counter applications based on Hooke's law

10.11591/ijeecs.v37.i3.pp1506-1514
Yulkifli Yulkifli , Alwi Nofriandi , Washilla Audia , Asrizal Asrizal , Yenni Darvina , Afdhal Muttaqin , Rosly Jaafar
This research presents the development of an instrumentation system that employs ultrasonic sensors for Newton dynamometer applications. A key parameter measured is the change in spring length before and after loading. The methodology implemented in this study is based on Hooke's Law, applied within the instrumentation devices. The length change data is transmitted to a smartphone via a Bluetooth module integrated into the instrument. This allows for flexible data usage and input through a calculator-based application created with MIT App Inventor, tailored to the relevant supporting parameters. Before implementation, the sensors underwent characterization to assess the linearity of their output compared to a standard measuring tool, specifically a ruler. The linearity test yielded a coefficient of 0.9998, indicating excellent performance for this application. Additionally, the system achieved an average accuracy of 94.12% and an average precision of 99.94%.
Volume: 37
Issue: 3
Page: 1506-1514
Publish at: 2025-03-01

Leveraging 3D convolutional networks for effective video feature extraction in video summarization

10.11591/ijeecs.v37.i3.pp1616-1625
Bhakti Deepak Kadam , Ashwini Mangesh Deshpande
Video feature extraction is pivotal in video processing, as it encompasses the extraction of pertinent information from video data. This process enables a more streamlined representation, analysis, and comprehension of video content. Given its advantages, feature extraction has become a crucial step in numerous video understanding tasks. This study investigates the generation of video representations utilizing three-dimensional (3D) convolutional neural networks (CNNs) for the task of video summarization. The feature vectors are extracted from the video sequences using pretrained two-dimensional (2D) networks such as GoogleNet and ResNet, along with 3D networks like 3D Convolutional Network (C3D) and Two-Stream Inflated 3D Convolutional Network (I3D). To assess the effectiveness of video representations, F1-scores are computed with the generated 2D and 3D video representations for chosen generic and query-focused video summarization techniques. The experimental results show that using feature vectors from 3D networks improves F1-scores, highlighting the effectiveness of 3D networks in video representation. It is demonstrated that 3D networks, unlike 2D ones, incorporate the time dimension to capture spatiotemporal features, providing better temporal processing and offering comprehensive video representation.
Volume: 37
Issue: 3
Page: 1616-1625
Publish at: 2025-03-01

Design and development of an Arduino-based oxygen saturation, heart rate variability, and blood glucose measurement device

10.11591/ijra.v14i1.pp74-81
Yehezkiel P. Putra , Wahyu K. Wibowo , Soni Prayogi
This study presents the design and development of an Arduino-based device for measuring oxygen saturation, heart rate variability (HRV), and blood glucose levels. The primary goal is to create an affordable, portable, and accurate health monitoring solution suitable for home health care and remote medical services. The device integrates a pulse oximeter sensor to measure oxygen saturation and heart rate, an electrocardiogram (ECG) sensor for capturing HRV data, and a non-invasive sensor for regular blood glucose monitoring, all managed by an Arduino microcontroller. Data collected by the sensors is processed and displayed on a user-friendly interface, enabling real-time tracking of health metrics. The device's performance was rigorously tested and validated against standard medical equipment, demonstrating comparable accuracy in measuring the targeted health parameters. This innovative solution aims to enhance personal health monitoring, reduce the burden on healthcare systems, and promote early detection and better management of health conditions. The affordability and ease of use make this device accessible to a wider population, potentially improving health outcomes. Future developments will focus on refining sensor accuracy and expanding the device's capabilities to monitor additional health metrics.
Volume: 14
Issue: 1
Page: 74-81
Publish at: 2025-03-01

Enhancing efficiency and reliability in high-power microwave amplifiers: a novel circuit driver approach

10.11591/ijra.v14i1.pp82-92
Ali Jebelli , Nafiseh Lotfi , Maral Partovibakhsh , Arezoo Mahabadi , Mohammad Saeid Zare
This paper introduces an innovative circuit driver engineered to significantly enhance the efficiency and longevity of high-power microwave amplifiers, addressing critical limitations of traditional drivers in handling high-power systems. The proposed design features advanced voltage sequencing, which is crucial for extending component life and ensuring safe operation within the safe operating area (SOA). By integrating a sophisticated circuit board with real-time feedback sensors, controlled by a microcontroller, the system ensures continuous monitoring and rapid response to potential operational hazards. The driver automatically engages a fail-safe mode when thresholds are breached, prioritizing efficiency optimization and minimizing energy waste. Rigorous testing has confirmed the circuit driver’s capability to meet and exceed the stringent demands of high-power microwave amplifier applications. This work offers a robust, reliable solution that not only overcomes existing challenges but also sets a new standard for the performance and safety of microwave amplification systems, making it a valuable contribution to the field of power electronics.
Volume: 14
Issue: 1
Page: 82-92
Publish at: 2025-03-01

Multi-objective hunter prey optimizer technique for distributed generation placement

10.11591/ijape.v14.i1.pp146-154
Kesavan Duraisamy , Sudhakiran Ponnuru , Jovin Deglus , Sakthidasan Arulprakasam , Rajakumar Palanisamy , Raja Soosaimarian Peter
Accommodation of distributed generation (DG) units in the distribution power network (DPN) reduces the power losses (PL), improves the voltage profile (VP), and enhances the stability. The size and site for distribution generations have to be optimized to avail favorable results. Otherwise, the DPN may experience greater power losses, higher voltage deviation, and voltage instability issues. This article implements an optimization technique using a hunter-prey optimizer (HPO) algorithm to optimize single and multiple (two) DG units in the radial DPN to minimize total real power losses (RPL) and total voltage deviation (TVD). The effectiveness of the HPO algorithm is assessed on the IEEE benchmark 69-bus radial DPN and a real-world Cairo-59 bus RDS. The simulation outcome after the optimized inclusion of DGs shown significant RPL reduction and considerable voltage enhancement. Furthermore, the optimized results of HPO algorithm were compared to the different algorithms and the comparison proved that the HPO can provide a more promising and authentic outcome than other algorithms.
Volume: 14
Issue: 1
Page: 146-154
Publish at: 2025-03-01

Position tracking of DC motor with PID controller utilizing particle swarm optimization algorithm with Lévy flight and Doppler effect

10.11591/ijra.v14i1.pp67-73
Nur Iffah Mohamed Azmi , Nafrizuan Mat Yahya
This paper presents the implementation of the particle swarm optimization with the Lévy flight Doppler effect (PSO-LFDE) algorithm for optimizing proportional-integral-derivative (PID) controller parameters in a direct current (DC) motor system. Traditional optimization algorithms like particle swarm optimization, whale optimization algorithm, grey wolf optimizer, and moth flame optimization often face challenges in balancing exploration and exploitation, leading to suboptimal performance. The proposed PSO-LFDE algorithm addresses these issues by incorporating Lévy flight for enhanced exploration and the Doppler effect for refined exploitation. The algorithm is validated using MATLAB/Simulink for position control in a DC motor system with step inputs of 10, 30, and 60 cm. Key performance metrics, including rise time, settling time, peak time, and steady-state error, were compared against other optimization methods. PSO-LFDE demonstrated superior performance, achieving a 41.63% improvement in rise time and a 70.20% reduction in peak time compared to other methods. These results highlight PSO-LFDE's effectiveness in optimizing PID controller parameters and improving the dynamic response of DC motor systems, offering a robust solution for real-world control applications.
Volume: 14
Issue: 1
Page: 67-73
Publish at: 2025-03-01

Design of a prototype firefighting robot based on an Arduino microcontroller using machine learning technique

10.11591/ijra.v14i1.pp31-37
Kalagotla Chenchireddy , Radhika Dora , Vadthya Jagan , Gouse Basha Mulla , Varghese Jegathesan , Shabbier Ahmed Sydu
The design and implementation of this paper are mainly based on control of the autonomous firefighting robot. In recent years, robotics has turned out to be an ingredient in which many people have shown their interest. Robotics has gained popularity due to the advancement of many technologies of computing and nanotechnologies. The output of the fire sensor is connected to the Arduino controller that controls the movement of the vehicle and the operation of spraying water. An infrared sensing circuit is designed with the infrared sensors placed in front of the vehicle to avoid collision with the obstacles. A total of two inbuilt reduction geared direct current motors are used in the paper for the robot movement in all the directions forward, backward, right, and left directions. For more practicality, a small water tank with a pumping motor is also arranged over the chassis and the water sprinkler pipe that is firmly fixed over the plate where the sensor is arranged can deliver water with some force. When the sensor detects the fire, the sprinkler is positioned toward fire flames; the pumping motor will be energized automatically to extinguish the fire. The main advantage of the proposed system automatically controls the fire by using advanced control techniques.
Volume: 14
Issue: 1
Page: 31-37
Publish at: 2025-03-01

A novel fast MPPT strategy with high efficiency for fast changing irradiance in PV systems

10.11591/ijape.v14.i1.pp163-172
Pujari Anjappa , K. Jithendra Gowd
This paper discusses about the photovoltaic (PV) system novel non-iterative maximum power point tracking algorithm with faster converging speed under varying solar irradiation level. PV system is a scattered renewable energy resource and a safe environmental energy source. However, the PV power oscillates around MPP value due to the fluctuations of temperature and insolation effects, leading to nonlinear maximum power tracking issues. For each change in atmospheric condition, output of the PV system changes necessitating the need to search for new maximum power conditions. An efficient maximum power point tracking (MPPT) device that improves the power transmitting efficiency along with a suitable high frequency direct current (DC) to DC power converter device are required for efficient operation. Finally, a comparison is made between existing MPPT algorithms and proposed novel non-iterative MPPT algorithm. The proposed MPPT system show that the overall tracking speed of the proposed MPPT is 5.6 times, 3.8 times faster than perturb and observe (P&O) method and INC method respectively. During the variation of irradiance, the power loss is reduced by 18.84% and 11.29% in comparison with P&O and INC method. The proposed method also minimizes the steady state oscillations.
Volume: 14
Issue: 1
Page: 163-172
Publish at: 2025-03-01

Optimizing robot anomaly detection through stochastic differential approximation and Brownian motion

10.11591/ijra.v14i1.pp19-30
Branesh M. Pillai , Arush Mishra , Rijo Jacob Thomas , Jackrit Suthakorn
This paper presents an adaptive approximation method for detecting anomalous patterns in extensive data streams gathered by mobile robots operating in rough terrain. Detecting anomalies in such dynamic environments poses a significant challenge, as it requires continuous monitoring and adjustment of robot movement, which can be resource intensive. To address this, a cost-effective solution is proposed that incorporates a threshold mechanism to track transitions between different regions of the data stream. The approach utilizes stochastic differential approximation (SDA) and optimistic optimization of Brownian motion to determine optimal parameter values and thresholds, ensuring efficient anomaly detection. This method focuses on minimizing the movement cost of the robots while maintaining accuracy in anomaly identification. By applying this technique, robots can dynamically adjust their movements in response to changes in the data stream, reducing operational expenses. Moreover, the temporal performance of the data stream is prioritized, a key factor often overlooked by conventional search engines. This paper demonstrates how the approach enhances the precision of anomaly detection in resource-constrained environments, making it particularly beneficial for real-time applications in rugged terrains.
Volume: 14
Issue: 1
Page: 19-30
Publish at: 2025-03-01
1 2 3
...
2097 2098
Show 345 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