IAES International Journal of Robotics and Automation (IJRA)
Not a member yet
460 research outputs found
Sort by
A novel approach to enhance rice foliar disease detection: custom data generators, advanced augmentation, hybrid fine-tuning, and regularization techniques with DenseNet121
Get PDFRice leaf diseases impact crop yield, leading to food shortages and economic losses. Early, automated detection is essential but often hindered by accuracy challenges. This study contributes to improving model robustness against diverse and adversarial inputs by proposing a custom data generator that applies Albumentation-based advanced augmentations, such as Gaussian blur, noise addition, brightness/contrast adjustments, and coarse dropout, to enhance model generalization. Five deep learning architectures—simple convolutional neural network (CNN), ResNet50, EfficientNetB0, Inception v3, and DenseNet121—were evaluated for classifying six categories: bacterial blight, brown spot, leaf blast, leaf scald, narrow brown spot, and healthy leaf. A hybrid model approach is proposed, fine-tuning the DenseNet121 model by unfreezing its last 20 layers, which balances transfer learning benefits with domain-specific feature extraction. Regularization techniques, including L2 regularization and a reduced dropout rate, are incorporated to control overfitting. Additionally, a custom learning rate scheduler is proposed to promote stable training. DenseNet121 achieved the highest performance, with an accuracy of 98.41%, demonstrating the effectiveness of these advanced augmentation and tuning strategies in rice leaf disease classification
Enhancing efficiency and reliability in high-power microwave amplifiers: a novel circuit driver approach
Get PDFThis 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
Development and implementation of a mobile robot for grouting floor tile joints
Get PDFMany construction tasks need time and effort from people. Thus, modern technology is one of its purposes to aid task completion. These include grouting floor tile joints. It takes time and effort to complete this process. Traditional methods for grouting floor tile joints between tiles are inefficient and require the worker to stay on his knees for extended periods, which can cause health issues. Thus, mobile robots are needed to automate floor grouting. This study describes the design and development of a mobile robot model to grout floor tile joints uniformly and effectively. Compared to manual approaches, the proposed robot can clean tiles quickly and precisely. The robot fills based on user-defined workspace coordinates. Set the robot at the start location to begin grouting. The robot then follows the user-defined code and coordinates to fill the requirement. After grout filling, the robot returned to the starting position to clean. This model was evaluated and exhibited faster, more accurate grouting and a shorter injection process than manual approaches
Enhancing health status prediction and data security using transformer-based deep learning architectures
Get PDFThis paper proposes a privacy-preserving transformer-based federated learning (PPTFL) framework designed to enhance privacy, accuracy, and computational efficiency in healthcare data analysis. Federated learning (FL) has emerged as a promising solution for distributed machine learning while preserving data privacy, especially in sensitive sectors like healthcare. However, challenges such as maintaining high accuracy and managing communication overhead remain. The proposed PPTFL framework leverages the power of transformer models to improve the performance of federated learning while integrating privacy-preserving techniques. The model demonstrates superior performance with an accuracy of 92.87%, an F1 score of 92.37%, and a privacy budget (ϵ) of 1.6, outperforming existing approaches in terms of both privacy and accuracy. The model also exhibits computational efficiency, with lower communication cost and reasonable training time. Comparative evaluations with four relevant literature models further validate the effectiveness of the proposed PPTFL framework. This work highlights the potential of PPTFL to revolutionize healthcare informatics by providing secure, accurate, and efficient solutions for federated learning applications
Performance comparison of optical flow and background subtraction and discrete wavelet transform methods for moving objects
Get PDFSelf-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 %
Long-range radio and Internet of things-inspired smart road reflectors for smart highways
Get PDFThe Internet of things (IoT) has been proven as an efficient technology for real-time monitoring of physical things through the Internet from any location. With the advancement in sensors and communication technologies, the implementation of IoT is adopted in wide extensions. Road reflectors on highway roads need to be automated and also powered with intelligence. With this motivation, we have proposed and implemented IoT and long range (LoRa) based architecture for the realization of smart road reflectors on the highway. To realize the proposed architecture, the hardware of the smart reflector and gateway is implemented on the university campus. During our implementation of the hardware, we observed the light intensity values that are sensed by smart reflectors on the server through LoRa and internet connectivity. In the future, we will be integrating additional sensors and also power the smart reflector with artificial intelligence to predict the fog status of a particular road
Analyzing the effectiveness of waiting times at the pharmacy of the King Hamad University Hospital
Get PDFThis study investigates the efficiency of waiting times at the pharmacy of King Hamad University Hospital, with a primary focus on optimizing patient experiences. Efficient pharmacy services are vital for ensuring the timely provision of medications to patients. Prolonged waiting times not only affect patient satisfaction but may also have implications for overall healthcare outcomes. To assess the effectiveness of waiting times, we conducted comprehensive analysis, including data collection, surveys, and observations. Our findings reveal valuable insights into the current state of pharmacy operations and the patient experience. We explore factors contributing to waiting times, such as prescription processing, queue management, and staff allocation. Through this analysis, we aim to provide actionable recommendations to enhance pharmacy efficiency, reduce waiting times, and improve patient satisfaction. Our study underscores the importance of optimizing pharmacy operations to ensure that patients receive timely and high-quality healthcare services. By addressing these issues, King Hamad University Hospital can not only enhance the overall patient experience but also contribute to better healthcare outcomes and increased operational efficiency. This research serves as a valuable resource for healthcare administrators, policymakers, and practitioners seeking to improve pharmacy services and patient satisfaction in hospital settings
A new era of technological change in the restaurant industry: focusing on perceived values of robot servers
Get PDFThe objective of this research is to examine the perceived values of robot servers, which include utilitarian and hedonic values, and how this influences willingness to pay more in the restaurant industry. This paper also examined the differences between the two sub-dimensions of perceived value, which are based on the demographic factors of the respondents. This research performed a data analysis based on a sample size of 295 participants, and the results indicated that the two sub-dimensions of perceived value play a crucial role in regard to the formation of willingness to pay more. Furthermore, the results showed that there were differences in perceived value in regard to the demographic factors
Comparative insights into nonlinear PID-based controller design approaches for industrial applications
Get PDFProportional-integral-derivative (PID) controllers are established in manufacturing due to their simple design, robustness, and wide-ranging industrial applications. However, traditional PID controllers often struggle with the complexity and nonlinearity behaviors inherent in many control systems. As a result, ongoing and future research is focused on developing more stable PID controllers that function efficiently without heavily depending on exact mathematical models, by fine-tuning controller parameters. This study explores several PID-based controllers, including non-linear PID (N-PID), multi-rate non-linear PID (MN-PID), and self-regulating nonlinear PID (SN-PID), assessing and contrasting their performance. The efficacy and robustness of these control mechanisms are substantiated through comparative analyses with the sliding mode control technique, employing experimental data from a pneumatic actuator system to assess performance across varying load scenarios. SN-PID outperforms sliding mode controller (SMC) by 90.97% and PID by 89.90%, followed by MN-PID (85.58% over SMC, 83.86% over PID) and N-PID (78.08% over SMC, 75.49% over PID), while PID offers only 10.63% improvement over SMC. These findings provide valuable insights and recommendations for enhancing controller performance. These insights aim to guide control engineers in selecting the most appropriate N-PID design strategy for specific applications, ultimately improving system performance and operational efficiency in industrial environments
Camera-based simultaneous localization and mapping: methods, camera types, and deep learning trends
Get PDFThe development of simultaneous localization and mapping (SLAM) technology is crucial for advancing autonomous systems in robotics and navigation. However, camera-based SLAM systems face significant challenges in accuracy, robustness, and computational efficiency, particularly under conditions of environmental variability, dynamic scenes, and hardware limitations. This paper provides a comprehensive review of camera-based SLAM methodologies, focusing on their different approaches for pose estimation, map reconstruction, and camera type. The application of deep learning also will be discussed on how it is expected to improve performance. The objective of this paper is to advance the understanding of camera-based SLAM systems and to provide a foundation for future innovations in robust, efficient, and adaptable SLAM solutions. Additionally, it offers pertinent references and insights for the design and implementation of next-generation SLAM systems across various applications