Connected autonomous vehicles (CAVs) currently promise cooperation between vehicles, providing abundant and real-time information through wireless communication technologies. In this paper, a two-level fusion of classifiers (TLFC) approach is proposed by using deep learning classifiers to perform accurate road detection (RD). The proposed TLFC-RD approach improves the classification by considering four key strategies such as cross fold operation at input and pre-processing using superpixel generation, adequate features, multi-classifier feature fusion and a deep learning classifier. Specifically, the road is classified as drivable and non-drivable areas by designing the TLFC using the deep learning classifiers, and the detected information using the TLFC-RD is exchanged between the autonomous vehicles for the ease of driving on the road. The TLFC-RD is analyzed in terms of its accuracy, sensitivity or recall, specificity, precision, F1-measure and max F measure. The TLFC- RD method is also evaluated compared to three existing methods: U-Net with the Domain Adaptation Model (DAM), Two-Scale Fully Convolutional Network (TFCN) and a cooperative machine learning approach (i.e., TAAUWN). Experimental results show that the accuracy of the TLFC-RD method for the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset is 99.12% higher than its competitors.
In a recent trend, electric vehicles (EV) have been facing various power quality issues, so fuel cells (FC) are considered the best choice for integrating EV technology to enhance performance. A fuel cell electric vehicle (FCEV) is a type of EV that uses a fuel cell combined with a small battery or super-capacitor to power its on-board electric motor. However, the power obtained from the FC system is much less and is not enough to drive the EV. So, another energy source is required to deliver the demanded power, which should contain high voltage gain with high conversion efficiency. The traditional converter produces a high output voltage at a high duty cycle, which generates various problems, such as reverse recovery issues, voltage spikes, and less lifespan. High switching frequency and voltage gain are essential for the propulsion of FC-based EV. Therefore, this paper presents an improved radial basis function (RBF)-based high-gain converter (HGC) to enhance the voltage gain and conversion efficiency of the entire system. The RBF neural model was constructed using the fast recursive algorithm (FRA) strategy to prune redundant hidden-layer neurons. The improved RBF technique reduces the input current ripple and voltage stress on the power semiconductor devices to increase the conversion ratio of the HGC without changing the duty cycle value. In the end, the improved RBF with HGC achieved an efficiency of 98.272%, vehicle speed of 91 km/h, and total harmonic distortion (THD) of 3.12%, which was simulated using MATLAB, and its waveforms for steady-state operation were analyzed and compared with existing methods.
1 June 2025 in International Journal of Computational and Experimental Science and Engineering
The convergence of quantum computing and artificial intelligence (AI) has introduced innovative opportunities to accelerate deep learning, particularly within decentralized cloud architectures. This study develops an adaptive quantum AI model leveraging hybrid quantum-classical algorithms to optimize deep learning processes such as training, inference, and resource allocation. The proposed model integrates Variational Quantum Circuits (VQCs) and Quantum Approximate Optimization Algorithms (QAOAs), which enable efficient handling of high-dimensional data and complex optimization tasks inherent in distributed environments. By addressing challenges like latency, energy efficiency, and computational overhead, the quantum AI model demonstrates significant performance gains in decentralized cloud systems.Experimental evaluations on benchmark datasets reveal a 40% reduction in training time, a 30% improvement in resource efficiency, and a 20% increase in prediction accuracy compared to classical deep learning frameworks. This study highlights the transformative potential of quantum computing in AI-driven decentralized cloud architectures, offering insights into its application for computationally intensive tasks across industries such as healthcare, finance, and logistics. Future work will focus on refining quantum hardware compatibility, developing quantum error correction methods, and exploring federated learning applications to expand the scope of quantum AI in privacy-preserving and distributed systems.
1 January 2024 in Journal of Intelligent Systems and Internet of Things
The agricultural industry faces significant challenges in improving efficiency and productivity, particularly in monitoring crop health and environmental conditions. Traditional methods are often labor-intensive, time-consuming, and lack real-time data, leading to suboptimal decision-making. Recent advancements in Internet of Things (IoT) and Artificial Intelligence (AI) technologies offer promising solutions. Long Range (LoRa) communication, a type of low-power wide-area network (LPWAN), enables long-distance data transmission with minimal power consumption, making it ideal for rural and expansive agricultural areas. When combined with deep learning, which can analyze large volumes of data to generate predictive insights, these technologies have the potential to revolutionize agricultural practices by providing farmers with timely and accurate information to optimize crop management and resource utilization. This study introduces an intelligent mote for agricultural applications, leveraging Long Range (LoRa) communication and deep learning techniques to improve precision farming. Traditional agricultural monitoring methods are labor-intensive and lack real-time insights. To address this, the mote is equipped with sensors to monitor temperature, humidity, soil moisture, and light intensity, transmitting real-time data over long distances with minimal power consumption using LoRaWAN. The collected data is processed by deep learning models to predict crop yield and identify potential issues. Field tests demonstrated a 15% improvement in yield prediction accuracy and a 20% reduction in water usage compared to traditional methods. These results highlight the effectiveness of integrating LoRa and deep learning in enhancing agricultural resource management and productivity.
30 October 2026 in Journal of Plant Diseases and Protection