Search Results (178)

Against the backdrop of the rapid advancement of intelligent speech interaction and holographic display technologies, this paper introduces an interactive holographic display system. This paper applies 2D-to-3D technology to acquisition work and uses a Complex-valued Convolutional Neural Network Point Cloud Gridding (CCNN-PCG) algorithm to generate a computer-generated hologram (CGH) with depth information for application in point cloud data. During digital human hologram building, 2D-to-3D conversion yields high-precision point cloud data. The system uses ChatGLM for natural language processing and emotion-adaptive responses, enabling multi-turn voice dialogs and text-driven model generation. The CCNN-PCG algorithm reduces computational complexity and improves display quality. Simulations and experiments show that CCNN-PCG enhances reconstruction quality and speeds up computation by over 2.2 times. This research provides a theoretical framework and practical technology for holographic interactive systems, applicable in virtual assistants, educational displays, and other fields. Full article

Urinary tract infections (UTIs) are a common pathology worldwide, frequently associated with kidney stones. We aimed to determine how artificial intelligence (AI) could assist and enhance human medical activities in this field. We performed a search in PubMed using different sets of keywords. When using the keywords “AI, artificial intelligence, urinary tract infections, Escherichia coli (E. coli)”, we identified 16 papers, 12 of which fulfilled our research criteria. When using the keywords “urolithiasis, AI, artificial intelligence”, we identified 72 results, 30 of which were suitable for analysis. We identified that AI/machine learning can be used to detect Gram-negative bacilli involved in UTIs in a fast and accurate way and to detect antibiotic-resistant genes in E. coli. The most frequent AI applications for urolithiasis can be summarized into three categories: The first category relates to patient follow-up, trying to improve physical and medical conditions after specific urologic surgical procedures. The second refers to urinary stone disease (USD), focused on stone evaluation, using different AI and machine learning systems, regarding the stone’s composition in terms of uric acid, its dimensions, its volume, and its speed of detection. The third category comprises the comparison of the ChatGPT-4, Bing AI, Grok, Claude, and Perplexity chatbots in different applications for urolithiasis. ChatGPT-4 has received the most positive evaluations. In conclusion, the impressive number of papers published on different applications of AI in UTIs and urology suggest that machine learning will be exploited effectively in the near future to optimize patient follow-up, diagnosis, and treatment. Full article

Pneumonia is a respiratory condition caused by various microorganisms, including bacteria, viruses, fungi, and parasites. It manifests with symptoms such as coughing, chest pain, fever, breathing difficulties, and fatigue. Early and accurate detection is crucial for effective treatment, yet traditional diagnostic methods often fall short in reliability and speed. Chest X-rays have become widely used for detecting pneumonia; however, current approaches still struggle with achieving high accuracy and interpretability, leaving room for improvement. PneumoNet, an artificial intelligence assistant for X-ray pneumonia detection, is proposed in this work. The framework comprises (a) a new deep learning-based classification model for the detection of pneumonia, which expands on the AlexNet backbone for feature extraction in X-ray images and a new head in its final layers that is tailored for (X-ray) pneumonia classification. (b) GPT-Neo, a large language model, which is used to integrate the results and produce medical reports. The classification model is trained and evaluated on three publicly available datasets to ensure robustness and generalisability. Using multiple datasets mitigates biases from single-source data, addresses variations in patient demographics, and allows for meaningful performance comparisons with prior research. PneumoNet classifier achieves accuracy rates between 96.70% and 98.70% in those datasets. Full article

Integration of advanced artificial intelligence with neurotechnology offers transformative potential for assistive communication. This perspective article examines the emerging convergence between non-invasive brain–computer interface (BCI) spellers and large language models (LLMs), with a focus on predictive communication for individuals with motor or language impairments. First, I will review the evolution of language models—from early rule-based systems to contemporary deep learning architectures—and their role in enhancing predictive writing. Second, I will survey existing implementations of BCI spellers that incorporate language modeling and highlight recent pilot studies exploring the integration of LLMs into BCI. Third, I will examine how, despite advancements in typing speed, accuracy, and user adaptability, the fusion of LLMs and BCI spellers still faces key challenges such as real-time processing, robustness to noise, and the integration of neural decoding outputs with probabilistic language generation frameworks. Finally, I will discuss how fully integrating LLMs with BCI technology could substantially improve the speed and usability of BCI-mediated communication, offering a path toward more intuitive, adaptive, and effective neurotechnological solutions for both clinical and non-clinical users. Full article

The development of beyond 5G (B5G) future wireless communication networks (FWCN) needs novel solutions to support high-speed, reliable, and low-latency communication. Unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) are promising techniques that can enhance wireless connectivity in urban environments where tall buildings block line-of-sight (LoS) links. However, existing UAV-assisted communication strategies do not fully address key challenges like mobility management, handover failures (HOFs), and path disorders in dense urban environments. This paper introduces a deep deterministic policy gradient (DDPG)-based UAV-RIS framework to overcome these limitations. The proposed framework jointly optimizes UAV trajectories and RIS phase shifts to improve throughput, energy efficiency (EE), and LoS probability while reducing outage probability (OP) and HOF. A modified K-means clustering algorithm is used to efficiently partition the ground users (GUs) considering the newly added GUs as well. The DDPG algorithm, based on reinforcement learning (RL), adapts UAV positioning and RIS configurations in a continuous action space. Simulation results show that the proposed approach significantly reduces HOF and OP, increases EE, enhances network throughput, and improves LoS probability compared to UAV-only, RIS-only, and without UAV-RIS deployments. Additionally, by dynamically adjusting UAV locations and RIS phase shifts based on GU mobility patterns, the framework further enhances connectivity and reliability. The findings highlight its potential to transform urban wireless communication by mitigating LoS blockages and ensuring uninterrupted connectivity in dense environments. Full article

To address the challenges of high missed detection rates for minute transmission line defects, strong complex background interference, and limited computational power on edge devices in UAV-assisted power line inspection, this paper proposes a lightweight improved YOLOv12 real-time detection model. First, a Bidirectional Weighted Feature Fusion Network (BiFPN) is introduced to enhance bidirectional interaction between shallow localization information and deep semantic features through learnable feature layer weighting, thereby improving detection sensitivity for line defects. Second, a Cross-stage Channel-Position Collaborative Attention (CPCA) module is embedded in the BiFPN’s cross-stage connections, jointly modeling channel feature significance and spatial contextual relationships to effectively suppress complex background noise from vegetation occlusion and metal reflections while enhancing defect feature representation. Furthermore, the backbone network is reconstructed using ShuffleNetV2’s channel rearrangement and grouped convolution strategies to reduce model complexity. Experimental results demonstrate that the improved model achieved 98.7% mAP@0.5 on our custom transmission line defect dataset, representing a 3.0% improvement over the baseline YOLOv12, with parameters compressed to 2.31M (8.3% reduction) and real-time detection speed reaching 142.7 FPS. This method effectively balances detection accuracy and inference efficiency, providing reliable technical support for unmanned intelligent inspection of transmission lines. Full article

In the field of active safety technology for intelligent connected vehicles (ICVs), the reliability and safety of the Automatic Emergency Braking (AEB) system is recognized as critical to driving safety. However, existing evaluation methods have been constrained by the inadequacy of static weight assessments in adapting to diverse driving conditions, as well as by the disconnect between conventional evaluation frameworks and experimental validation. To address these limitations, a comprehensive Vehicle-in-the-Loop (VIL) evaluation system based on the dynamic weight analytic hierarchy process (DWAHP) was proposed in this study. A two-tier dynamic weighting architecture was established. At the criterion level, a bivariate variable–weight function, incorporating the vehicle speed and road surface adhesion coefficient, was developed to enable the dynamic coupling modeling of road environment parameters. At the scheme level, a five-dimensional indicator system—integrating braking distance, collision speed, and other key metrics—was constructed to support an adaptive evaluation model under multi-condition scenarios. By establishing a dynamic mapping between weight functions and driving condition parameters, the DWAHP methodology effectively overcame the limitations associated with fixed-weight mechanisms in varying operating conditions. Based on this framework, a dedicated AEB system performance test platform was designed and developed. Validation was conducted using both VIL simulations and real-world road tests, with a Volvo S90L as the test vehicle. The experimental results demonstrated high consistency between VIL and real-world road evaluations across three dimensions: safety (deviation: 0.1833/9.5%), reliability (deviation: 0.2478/13.1%), and riding comfort (deviation: 0.05/2.7%), with an overall comprehensive score deviation of 0.0707 (relative deviation: 0.51%). This study not only verified the technical advantages of the dynamic weight model in adapting to complex driving environments and analyzing multi-parameter coupling effects but also established a systematic methodological framework for evaluating AEB system performance via VIL. The findings provide a robust foundation for the testing and assessment of AEB system, offer a structured approach to advancing the performance evaluation of advanced driver assistance systems (ADASs), facilitate the safe and reliable validation of ICVs’ commercial applications, and ultimately contribute to enhancing road traffic safety. Full article

In order to improve the perception accuracy of the apple tree fruit recognition model and to reduce the model size, a lightweight apple target recognition method based on an improved YOLOv5s artificial intelligence algorithm was proposed, and relevant experiments were designed. The Depthwise Separable Convolution (DWConv) module has many advantages: (1) It has high computational efficiency, reducing the number of parameters and calculations in the model; (2) It makes the model lightweight and easy to deploy in hardware; (3) DWConv can be combined with other modules to enhance the multi-scale feature extraction capability of the detection network and improve the ability to capture multi-scale information; (4) It balances the detection accuracy and speed of the model; (5) DWConv can flexibly adapt to different network structures. Because of its efficient computing modes, lightweight design, and flexible structural adaptation, the DWConv module has significant advantages in multi-scale feature extraction, real-time performance improvement, and small-object detection. Therefore, this method improves the original YOLOv5s network architecture by replacing the embedded Depthwise Separable Convolution in its Backbone network, which reduces the size and parameter count of the model while ensuring detection accuracy. The experimental results show that for the test-set images, the proposed improved model has an average recognition accuracy of 92.3% for apple targets, a recognition time of 0.033 s for a single image, and a model volume of 11.1 MB. Compared with the original YOLOv5s model, the average recognition accuracy was increased by 0.8%, the recognition speed was increased by 23.3%, and the model volume was compressed by 20.7%, effectively achieving lightweight improvement of the apple detection model and improving the accuracy and speed of detection. The detection algorithm proposed in the study can be extended to the intelligent measurement of apple biological and physical characteristics, including for size measurement, shape analysis, and color analysis. The proposed method can improve the intelligence level of orchard management and horticultural technology, reduce labor costs, assist precision agriculture technology, and promote the transformation of the horticultural industry toward sustainable development. Full article

Background: Artificial intelligence (AI) is playing an increasingly important role in everyday dental practice and diagnosis, especially in the area of analysing digital pantomographic images. Through the use of innovative and modern algorithms, clinicians can more quickly and accurately identify pathological changes contained in digital pantomographic images, such as caries, periapical lesions, cysts, and tumours. It should be noted that pantomographic images are one of the most commonly used imaging modalities in dentistry, and their digital analysis enables the construction of AI models to support diagnosis. Objectives: This paper presents a systematic narrative review of studies included in scientific articles from 2020 to 2025, focusing on three main diagnostic areas: detection of caries, periapical lesions, and cysts and tumours. The results show that neural network models, such as U-Net, Swin Transformer, and CNN, are most commonly used in caries diagnosis and have achieved high performance in lesion identification. In the case of periapical lesions, AI models such as U-Net and Decision Tree also showed high performance, surpassing the performance of young dentists in assessing radiographs in some cases. Results: The studies cited in this review show that the diagnosis of cysts and tumours, on the other hand, relies on more advanced models such as YOLO v8, DCNN, and EfficientDet, which in many cases achieved more than 95% accuracy in the detection of this pathology. The cited studies were conducted at various universities and institutions around the world, and the databases (case databases) analysed in this work ranged from tens to thousands of images. Conclusions: The main conclusion of the literature analysis is that, thanks to its accessibility, speed, and accuracy, AI can significantly assist the work of physicians by reducing the time needed to analyse images. However, despite the promising results, AI should only be considered as an enabling tool and not as a replacement for the knowledge of doctors and their long experience. There is still a need for further improvement of algorithms and further training of the network, especially in identifying more complex clinical cases. Full article

Driver factors are the main cause of road traffic accidents. For the research of automotive active safety, an identification method for road hypnosis of a driver of a car with dynamic human–vehicle heterogeneous data fusion calculation is proposed. Road hypnosis is an unconscious driving state formed by the combination of external environmental factors and the psychological state of the car driver. When drivers fall into a state of road hypnosis, they cannot clearly perceive the surrounding environment and make various reactions in time to complete the driving task. The safety of humans and cars is greatly affected. Therefore, the study of the identification of drivers’ road hypnosis is of great significance. Vehicle and virtual driving experiments are designed and carried out to collect human and vehicle data. Eye movement data and EEG data of human data are collected with eye movement sensors and EEG sensors. Vehicle speed and acceleration data are collected by a mobile phone with AutoNavi navigation, which serves as an onboard sensor. In order to screen the characteristics of human and vehicles related to the road hypnosis state, the characteristic parameters of the road hypnosis in the preprocessed data are selected by the method of independent sample T-test, the hidden Markov model (HMM) is constructed, and the identification of the road hypnosis of the Ridge Regression model is combined. In order to evaluate the identification performance of the model, six evaluation indicators are used and compared with multiple regression models. The results show that the hidden Markov-Ridge Regression model is the most superior in the identification accuracy and effect of the road hypnosis state. A new technical scheme reference for the development of intelligent driving assistance systems is provided by the proposed comprehensive road hypnosis state identification model based on human–vehicle data can provide, which can effectively improve the life recognition ability of automobile intelligent cockpits, enhance the active safety performance of automobiles, and further improve traffic safety. Full article

Artificial intelligence (AI)-based object detection in radiology can assist in clinical diagnosis and treatment planning. This article examines the AI-based object detection models currently used in many imaging modalities, including X-ray Magnetic Resonance Imaging (MRI), Computed Tomography (CT), and Ultrasound (US). The key models from the convolutional neural network (CNN) as well as the contemporary transformer and hybrid models are analyzed based on their ability to detect pathological features, such as tumors, lesions, and tissue abnormalities. In addition, this review offers a closer look at the strengths and weaknesses of these models in terms of accuracy, robustness, and speed in real clinical settings. The common issues related to these models, including limited data, annotation quality, and interpretability of AI decisions, are discussed in detail. Moreover, the need for strong applicable models across different populations and imaging modalities are addressed. The importance of privacy and ethics in general data use as well as safety and regulations for healthcare data are emphasized. The future potential of these models lies in their accessibility in low resource settings, usability in shared learning spaces while maintaining privacy, and improvement in diagnostic accuracy through multimodal learning. This review also highlights the importance of interdisciplinary collaboration among artificial intelligence researchers, radiologists, and policymakers. Such cooperation is essential to address current challenges and to fully realize the potential of AI-based object detection in radiology. Full article

The integration of artificial intelligence (AI) into chest radiography (CXR) has greatly impacted both human and veterinary medicine, enhancing diagnostic speed, accuracy, and efficiency. In human medicine, AI has been extensively studied, improving the identification of thoracic abnormalities, diagnostic precision in emergencies, and the classification of complex conditions such as tuberculosis, pneumonia, and COVID-19. Deep learning-based models assist radiologists by detecting patterns, generating probability maps, and predicting outcomes like heart failure. However, AI is still supplementary to clinical expertise due to challenges such as data limitations, algorithmic biases, and the need for extensive validation. Ethical concerns and regulatory constraints also hinder full implementation. In veterinary medicine, AI is still in its early stages and is rarely used; however, it has the potential to become a valuable tool for supporting radiologists in the future. However, challenges include smaller datasets, breed variability, and limited research. Addressing these through focused research on species with less phenotypic variability (like cats) and cross-sector collaborations could advance AI in veterinary medicine. Both fields demonstrate AI’s potential to enhance diagnostics but emphasize the ongoing need for human expertise in clinical decision making. Differences in anatomy structure between the two fields must be considered for effective AI adaptation. Full article

This study proposes an advanced intelligent vehicle path-following control system using deep reinforcement learning, with a particular focus on the role of road geometry perception in motion planning and control. The system is structured around a three-degree-of-freedom (3-DOF) vehicle model, which facilitates the extraction of critical dynamic features necessary for robust control. The longitudinal control architecture integrates a Deep Deterministic Policy Gradient (DDPG) agent to optimise longitudinal velocity and acceleration, while lateral vehicle control is handled by a Deep Q-Network (DQN). To enhance situational awareness and adaptability, the system incorporates key input variables, including ego vehicle speed, speed error, lateral deviation, lateral error, and safety distance to the preceding vehicle, all in the context of road geometry and vehicle dynamics. In addition, the influence of road curvature is embedded into the control framework through perceived acceleration (sensed by vehicle occupants), allowing for more accurate and responsive adaptation to varying road conditions. The vehicle control system is tested in a simulated environment with a lead car in front with realistic speed profiles. The system outputs continuous values for acceleration and steering angle. The results of this study suggest that the proposed intelligent control system not only improves driver assistance but also has potential applications in autonomous driving. This framework contributes to the development of more autonomous, efficient, safety-aware, and comfortable vehicle control systems. Full article

The rapid adoption of electric vehicles (EVs) and the increasing reliance on renewable energy sources necessitate innovative charging infrastructure solutions to address key challenges in energy efficiency, grid stability, and sustainable transportation. Dynamic wireless charging systems, which enable EVs to charge while in motion, offer a transformative approach to mitigating range anxiety and optimizing energy utilization. However, these systems face significant operational challenges, including dynamic traffic conditions, uncertain EV arrival patterns, energy transfer efficiency variations, and renewable energy intermittency. This paper proposes a novel quantum computing-assisted optimization framework for the modeling, operation, and control of wireless dynamic charging infrastructure in urban highway networks. Specifically, we leverage Variational Quantum Algorithms (VQAs) to address the high-dimensional, multi-objective optimization problem associated with real-time energy dispatch, charging pad utilization, and traffic flow coordination. The mathematical modeling framework captures critical aspects of the system, including power balance constraints, state-of-charge (SOC) dynamics, stochastic vehicle arrivals, and charging efficiency degradation due to vehicle misalignment and speed variations. The proposed methodology integrates quantum-inspired optimization techniques with classical distributionally robust optimization (DRO) principles, ensuring adaptability to system uncertainties while maintaining computational efficiency. A comprehensive case study is conducted on a 50 km urban highway network equipped with 20 charging pad segments, supporting an average traffic flow of 10,000 EVs per day. The results demonstrate that the proposed quantum-assisted approach significantly enhances energy efficiency, reducing energy losses by up to 18% compared to classical optimization methods. Moreover, traffic-aware adaptive charging strategies improve SOC recovery by 25% during peak congestion periods while ensuring equitable energy allocation among different vehicle types. The framework also facilitates a 30% increase in renewable energy utilization, aligning energy dispatch with periods of high solar and wind generation. Key insights from the case study highlight the critical impact of vehicle alignment, speed variations, and congestion on wireless charging performance, emphasizing the need for intelligent scheduling and real-time optimization. The findings contribute to advancing the integration of quantum computing into sustainable transportation planning, offering a scalable and robust solution for next-generation EV charging infrastructure. Full article

The integration of 3D printing with smart infrastructure presents a transformative opportunity in urban planning, construction, and engineering, enhancing efficiency, flexibility, and sustainability. By leveraging additive manufacturing alongside digitalization, artificial intelligence (AI), and the Internet of Things (IoT), this technology enables the creation of customized, lightweight, and sensor-embedded structures. This work analyzes both the advantages and challenges of applying 3D printing in smart infrastructure, focusing on material optimization, rapid prototyping, and automated fabrication, which significantly reduce construction time, labor costs, and material waste. Applications such as 3D-printed bridges, modular housing, and IoT-integrated urban furniture exhibit its potential in contributing towards resilient and resource-efficient cities. However, despite these benefits, significant challenges hinder large-scale adoption. Issues of scalability, particularly in the fabrication of large and load-bearing structures, remain unresolved, requiring advancements in high-speed printing techniques, material reinforcement strategies, and hybrid construction methods. Furthermore, regulatory uncertainties and the absence of standardized guidelines create barriers to implementation. The lack of comprehensive building codes, certification protocols, and quality assurance measures for 3D-printed structures limits their widespread acceptance in mainstream construction. Overcoming these limitations necessitates research into AI-driven process optimization, multi-material printing, and international standardization efforts. By assisting towards overcoming these challenges, 3D printing has the potential to redefine urban development, making infrastructure more adaptive, cost-effective, and environmentally sustainable. This work provides a critical evaluation of the current capabilities and limitations of 3D printing in smart infrastructure towards achieving full-scale implementation and regulatory compliance. Full article