Search Results (55)

Lithium-ion batteries (LIBs) are critical components in safety-critical systems such as electric vehicles, aerospace, and grid-scale energy storage. Their degradation over time can lead to catastrophic failures, including thermal runaway and uncontrolled combustion, posing severe threats to human safety and infrastructure. Developing a robust AI framework for degradation prognostics in safety-critical systems is essential to mitigate these risks and ensure operational safety. However, sensor noise, dynamic operating conditions, and the multi-scale nature of degradation processes complicate this task. Traditional denoising and modeling approaches often fail to preserve informative temporal features or capture both abrupt fluctuations and long-term trends simultaneously. To address these limitations, this paper proposes a hybrid data-driven framework that combines Sample Entropy-guided Variational Mode Decomposition (SE-VMD) with K-means clustering for adaptive signal preprocessing. The SE-VMD algorithm automatically determines the optimal number of decomposition modes, while K-means separates high- and low-frequency components, enabling robust feature extraction. A dual-branch architecture is designed, where Gated Recurrent Units (GRUs) extract short-term dynamics from high-frequency signals, and Transformers model long-term trends from low-frequency signals. This dual-branch approach ensures comprehensive multi-scale degradation feature learning. Additionally, experiments with varying sliding window sizes are conducted to optimize temporal modeling and enhance the framework’s robustness and generalization. Benchmark dataset evaluations demonstrate that the proposed method outperforms traditional approaches in prediction accuracy and stability under diverse conditions. The framework directly contributes to Artificial Intelligence for Security by providing a reliable solution for battery health monitoring in safety-critical applications, enabling early risk mitigation and ensuring operational safety in real-world scenarios. Full article

Membership Inference Attacks (MIAs) pose a significant threat to privacy in modern machine learning systems, enabling adversaries to determine whether a specific data record was used during model training. Existing defense techniques often degrade model utility or rely on heuristic noise injection, which fails to provide a robust, mathematically grounded defense. In this paper, we propose Diffusion-Driven Data Preprocessing (D³P), a novel privacy-preserving framework leveraging generative diffusion models to transform sensitive training data before learning, thereby reducing the susceptibility of trained models to MIAs. Our method integrates a mathematically rigorous denoising process into a privacy-oriented diffusion pipeline, which ensures that the reconstructed data maintains essential semantic features for model utility while obfuscating fine-grained patterns that MIAs exploit. We further introduce a privacy–utility optimization strategy grounded in formal probabilistic analysis, enabling adaptive control of the diffusion noise schedule to balance attack resilience and predictive performance. Experimental evaluations across multiple datasets and architectures demonstrate that D³P significantly reduces MIA success rates by up to $42.3\%$ compared to state-of-the-art defenses, with a less than $2.5\%$ loss in accuracy. This work provides a theoretically principled and empirically validated pathway for integrating diffusion-based generative mechanisms into privacy-preserving AI pipelines, which is particularly suitable for deployment in cloud-based and blockchain-enabled machine learning environments. Full article

Large language models (LLMs) are powerful, but they can unintentionally memorize and leak sensitive information found in their training or input data. To address this issue, we propose SPADR, a semantic privacy anomaly detection and remediation pipeline designed to detect and remove privacy risks from text. SPADR addresses limitations in existing redaction methods by identifying deeper forms of sensitive content, including implied relationships, contextual clues, and non-standard identifiers that traditional NER systems often overlook. SPADR combines semantic anomaly scoring using a denoising autoencoder with named entity recognition and graph-based analysis to detect both direct and hidden privacy risks. It is flexible enough to work on both training data (to prevent memorization) and user input (to prevent leakage at inference time). We evaluate SPADR on the Enron Email Dataset, where it significantly reduces document-level privacy leakage while maintaining strong semantic utility. The enhanced version, SPADR (S2), reduces the PII leak rate from 100% to 16.06% and achieves a BERTScore F1 of 88.03%. Compared to standard NER-based redaction systems, SPADR offers more accurate and context-aware privacy protection. This work highlights the importance of semantic and structural understanding in building safer, privacy-respecting AI systems. Full article

AI-integrated robotics in Industry 5.0 demands advanced manufacturing systems capable of autonomously interpreting complex geometries and dynamically adjusting machining strategies in real time—particularly when dealing with aerospace components featuring large-curvature surfaces. Large-curvature aerospace components present significant challenges for precision drilling due to surface-normal deviations caused by curvature, roughness, and thin-wall deformation. This study presents a robotic drilling system that integrates adaptive PCA-based surface normal estimation with in-process pre-drilling correction and post-drilling verification. This system integrates a 660 nm wavelength linear laser projector and a 1.3-megapixel industrial camera arranged at a fixed 30° angle, which project and capture structured-light fringes. Based on triangulation, high-resolution point clouds are reconstructed for precise surface analysis. By adaptively selecting localized point-cloud regions during machining, the proposed algorithm converts raw measurements into precise normal vectors, thereby achieving an accurate solution of the normal direction of the surface of large curvature parts. Experimental validation on a 400 mm-diameter cylinder shows that using point clouds within a 100 mm radius yields deviations within an acceptable range of theoretical normals, demonstrating both high precision and reliability. Moreover, experiments on cylindrical aerospace-grade specimens demonstrate normal direction accuracy ≤ 0.2° and hole position error ≤ 0.25 mm, maintained across varying curvature radii and roughness levels. The research will make up for the shortcomings of existing manual drilling methods, improve the accuracy of hole-making positions, and meet the high fatigue service needs of aerospace and other industries. This system is significant in promoting the development of industrial automation and improving the productivity of enterprises by improving drilling precision and repeatability, enabling reliable assembly of high-curvature aerospace structures within stringent tolerance requirements. Full article

Accurate forecasting of language service demand is essential for language industry planning and resource allocation, yet it remains challenging due to small sample sizes, noisy data, and nonlinear dynamics in industry-level time series. To enhance forecasting accuracy, this study proposes a novel hybrid forecasting framework, called the Sine Cosine Algorithm-optimized wavelet analysis-based new information priority nonhomogeneous discrete grey model (SCA–WA–NIPNDGM). By integrating wavelet-based denoising with the NIPNDGM, the model effectively extracts intrinsic signals and prioritizes recent observations to capture short-term trends while addressing nonlinear parameter estimation via heuristic optimization. Empirical studies are conducted across three high-demand sectors in China from 2000 to 2024, including manufacturing; water conservancy, environmental, and public facilities management; and wholesale and retail. The findings show that the proposed model displays superior performance to 11 benchmark grey models and five optimization algorithms across six evaluation metrics, achieving test Mean Absolute Percentage Error (MAPE) values as low as 1.2%, with strong generalization, stable iterations, and fast convergence. These results underscore its effectiveness in forecasting complex time series and offer valuable insights for language service market planning under emerging AI-driven disruptions. Full article

The digital revolution has profoundly influenced the automotive industry, shifting the paradigm from conventional vehicles to smart cars (SCs). The SCs rely on in-vehicle communication among electronic control units (ECUs) enabled by assorted protocols. The Controller Area Network (CAN) serves as the de facto standard for interconnecting these units, enabling critical functionalities. However, inherited non-delineation in SCs— transmits messages without explicit destination addressing—poses significant security risks, necessitating the evolution of an astute and resilient self-defense mechanism (SDM) to neutralize cyber threats. To this end, this study introduces a lightweight intrusion mitigation mechanism based on an adaptive momentum-based deep denoising autoencoder (AM-DDAE). Employing real-time CAN bus data from renowned smart vehicles, the proposed framework effectively reconstructs original data compromised by adversarial activities. Simulation results illustrate the efficacy of the AM-DDAE-based SDM, achieving a reconstruction error (RE) of less than 1% and an average execution time of 0.145532 s for data recovery. When validated on a new unseen attack, and on an Adversarial Machine Learning attack, the proposed model demonstrated equally strong performance with RE < 1%. Furthermore, the model’s decision-making capabilities were analysed using Explainable AI techinques such as SHAP and LIME. Additionally, the scheme offers applicable deployment flexibility: it can either be (a) embedded directly into individual ECU firmware or (b) implemented as a centralized hardware component interfacing between the CAN bus and ECUs, preloaded with the proposed mitigation algorithm. Full article

Artificial intelligence (AI) is revolutionarily shaping the entire landscape of medicine and particularly the privileged field of radiology, since it produces a significant amount of data, namely, images. Currently, AI implementation in radiology is continuously increasing, from automating image analysis to enhancing workflow management, and specifically, pediatric neuroradiology is emerging as an expanding frontier. Pediatric neuroradiology presents unique opportunities and challenges since neonates’ and small children’s brains are continuously developing, with age-specific changes in terms of anatomy, physiology, and disease presentation. By enhancing diagnostic accuracy, reducing reporting times, and enabling earlier intervention, AI has the potential to significantly impact clinical practice and patients’ quality of life and outcomes. For instance, AI reduces MRI and CT scanner time by employing advanced deep learning (DL) algorithms to accelerate image acquisition through compressed sensing and undersampling, and to enhance image reconstruction by denoising and super-resolving low-quality datasets, thereby producing diagnostic-quality images with significantly fewer data points and in a shorter timeframe. Furthermore, as healthcare systems become increasingly burdened by rising demands and limited radiology workforce capacity, AI offers a practical solution to support clinical decision-making, particularly in institutions where pediatric neuroradiology is limited. For example, the MELD (Multicenter Epilepsy Lesion Detection) algorithm is specifically designed to help radiologists find focal cortical dysplasias (FCDs), which are a common cause of drug-resistant epilepsy. It works by analyzing a patient’s MRI scan and comparing a wide range of features—such as cortical thickness and folding patterns—to a large database of scans from both healthy individuals and epilepsy patients. By identifying subtle deviations from normal brain anatomy, the MELD graph algorithm can highlight potential lesions that are often missed by the human eye, which is a critical step in identifying patients who could benefit from life-changing epilepsy surgery. On the other hand, the integration of AI into pediatric neuroradiology faces technical and ethical challenges, such as data scarcity and ethical and legal restrictions on pediatric data sharing, that complicate the development of robust and generalizable AI models. Moreover, many radiologists remain sceptical of AI’s interpretability and reliability, and there are also important medico-legal questions around responsibility and liability when AI systems are involved in clinical decision-making. Future promising perspectives to overcome these concerns are represented by federated learning and collaborative research and AI development, which require technological innovation and multidisciplinary collaboration between neuroradiologists, data scientists, ethicists, and pediatricians. The paper aims to address: (1) current applications of AI in pediatric neuroradiology; (2) current challenges and ethical considerations related to AI implementation in pediatric neuroradiology; and (3) future opportunities in the clinical and educational pediatric neuroradiology field. AI in pediatric neuroradiology is not meant to replace neuroradiologists, but to amplify human intellect and extend our capacity to diagnose, prognosticate, and treat with unprecedented precision and speed. Full article

This study assesses the clinical deployment of SubtlePET™, a commercial AI-based denoising algorithm, across three radiotracers—¹⁸F-FDG, ⁶⁸Ga-PSMA-11, and ¹⁸F-FDOPA—with the goal of improving image quality while reducing injected activity, technologist radiation exposure, and scan time. A retrospective analysis on a digital PET/CT system showed that SubtlePET™ enabled dose reductions exceeding 33% and time savings of over 25%. AI-enhanced images were rated interpretable in 100% of cases versus 65% for standard low-dose reconstructions. Notably, 85% of AI-enhanced scans received the maximum Likert quality score (5/5), indicating excellent diagnostic confidence and noise suppression, compared to only 50% with conventional reconstruction. The quantitative image quality improved significantly across all tracers, with SNR and CNR gains of 50–70%. Radiotracer dose reductions were particularly substantial in low-BMI patients (up to 41% for FDG), and the technologist exposure decreased for high-exposure roles. The daily patient throughput increased by an average of 4.84 cases. These findings support the robust integration of SubtlePET™ into routine clinical PET practice, offering improved efficiency, safety, and image quality without compromising lesion detectability. Full article

Artificial intelligence (AI) currently exhibits considerable potential within the realm of biodiversity conservation. However, high-quality regionally customized datasets remain scarce, particularly within urban environments. The existing large-scale bird image datasets often lack a dedicated focus on endangered species endemic to specific geographic regions, as well as a nuanced consideration of the complex interplay between urban and natural environmental contexts. Therefore, this paper introduces Macao-ebird, a novel dataset designed to advance AI-driven recognition and conservation of endangered bird species in Macao. The dataset comprises two subsets: (1) Macao-ebird-cls, a classification dataset with 7341 images covering 24 bird species, emphasizing endangered and vulnerable species native to Macao; and (2) Macao-ebird-det, an object detection dataset generated through AI-agent-assisted labeling using grounding DETR with improved denoising anchor boxes (DINO), significantly reducing manual annotation effort while maintaining high-quality bounding-box annotations. We validate the dataset’s utility through baseline experiments with the You Only Look Once (YOLO) v8–v12 series, achieving a mean average precision (mAP50) of up to 0.984. Macao-ebird addresses critical gaps in the existing datasets by focusing on region-specific endangered species and complex urban–natural environments, providing a benchmark for AI applications in avian conservation. Full article

Semantic scene completion through AI-driven content generation is a rapidly evolving field with crucial applications in 3D reconstruction and scene understanding. This task presents considerable challenges, arising from the intrinsic data sparsity and incomplete nature of input points generated by LiDAR. This paper proposes a generative semantic scene completion method based on a discrete denoising diffusion probabilistic model to tackle these issues. In the discrete diffusion phase, a weighted K-nearest neighbor uniform transition kernel is introduced based on feature distance in the discretized voxel space to control the category distribution transition processes by capturing the local structure of data, which is more in line with the diffusion process in the real world. Moreover, to mitigate the feature information loss during point cloud voxelization, the aggregated point features are integrated into the corresponding voxel space, thereby enhancing the granularity of the completion. Accordingly, a combined loss function is designed for network training that considers both the KL divergence for global completion and the cross-entropy for local details. The evaluation, which results from multiple public outdoor datasets, demonstrates that the proposed method effectively accomplishes semantic scene completion. Full article

Side-Scan Sonar (SSS) is widely used in underwater rescue operations and the detection of seabed targets, such as shipwrecks, drowning victims, and aircraft. However, the quality of sonar images is often degraded by noise sources like reverberation and speckle noise, which complicate the extraction of effective features. Additionally, challenges such as limited sample sizes and class imbalances are prevalent in side-scan sonar image data. These issues directly impact the accuracy of deep learning-based target classification models for SSS images. To address these challenges, we propose a side-scan sonar image classification model based on joint image deblurring–denoising and a pre-trained feature fusion attention network. Firstly, by employing transform domain filtering in conjunction with upsampling and downsampling techniques, the joint image deblurring–denoising approach effectively reduces image noise while preserving and enhancing edge and texture features. Secondly, a feature fusion attention network based on transfer learning is employed for image classification. Through the transfer learning approach, a feature extractor based on depthwise separable convolutions and densely connected networks is trained to effectively address the challenge of limited training samples. Subsequently, a dual-path feature fusion strategy is utilized to leverage the complementary strengths of different feature extraction networks. Furthermore, by incorporating channel attention and spatial attention mechanisms, key feature channels and regions are adaptively emphasized, thereby enhancing the accuracy and robustness of image classification. Finally, the Gradient-weighted Class Activation Mapping (Grad-CAM) technique is integrated into the proposed model to ensure interpretability and transparency. Experimental results show that our model achieves a classification accuracy of 96.80% on a side-scan sonar image dataset, confirming the effectiveness of this method for SSS image classification. Full article

The study is focused on the application of the electronic proof of concept Digital Twin (DT) model supporting Electroencephalogram (EEG) signal detection and interpretation. The EEG DT model integrates two open source tools: a first tool used for the circuit modeling and simulation of the electrodes, and a second one implementing an Artificial Intelligence (AI)-supervised algorithm to classify and adjust a noisy EEG signal. Specifically, the DT model adopts the Random Forest (RF) AI-supervised algorithm, replacing the signal filtering process and facilitating the time–domain peak and the wave shape morphology reading of a noisy detection. In order to prove the DT’s efficacy, the RF model is trained by considering the specific case of detections of EEG of patients under the effects of alcohol. The choice of the RF algorithm is justified by its good performance parameters. For the specific dataset, the RF exhibits a probabilistic error slightly lower than that of the ANN and a better cleaning action. The goal of the paper is to provide a methodology to use ‘intelligent’ electrodes supporting EEG data processing during data acquisition and to optimize the measurement’s interpretation through a data post-processing process. The proposed EEG DT could represent an alternative to the traditional denoising signal processing approaches. Full article

Cranioplasty enables the restoration of cranial defects caused by traumatic injuries, brain tumour excisions, or decompressive craniectomies. Conventional methods rely on Computer-Aided Design (CAD) for implant design, which requires significant resources and expertise. Recent advancements in Artificial Intelligence (AI) have improved Computer-Aided Diagnostic systems for accurate and faster cranial reconstruction and implant generation procedures. However, these face inherent limitations, including the limited availability of diverse datasets covering different defect shapes spanning various locations, absence of a comprehensive pipeline integrating the preprocessing of medical images, cranial reconstruction, and implant generation, along with mechanical testing and validation. The proposed framework incorporates a robust preprocessing pipeline for easier processing of Computed Tomography (CT) images through data conversion, denoising, Connected Component Analysis (CCA), and image alignment. At its core is CRIGNet (Cranial Reconstruction and Implant Generation Network), a novel deep learning model rigorously trained on a diverse dataset of 2160 images, which was prepared by simulating cylindrical, cubical, spherical, and triangular prism-shaped defects across five skull regions, ensuring robustness in diagnosing a wide variety of defect patterns. CRIGNet achieved an exceptional reconstruction accuracy with a Dice Similarity Coefficient (DSC) of 0.99, Jaccard Similarity Coefficient (JSC) of 0.98, and Hausdorff distance (HD) of 4.63 mm. The generated implants showed superior geometric accuracy, load-bearing capacity, and gap-free fitment in the defected skull compared to CAD-generated implants. Also, this framework reduced the implant generation processing time from 40–45 min (CAD) to 25–30 s, suggesting its application for a faster turnaround time, enabling decisive clinical support systems. Full article

Automatic medical segmentation is crucial for assisting doctors in identifying disease regions effectively. As a state-of-the-art (SOTA) approach, generative AI models, particularly diffusion models, have surpassed GANs in generating high-quality images for tasks like segmentation. However, most diffusion-based architectures rely on U-Net designs with multiple residual blocks and convolutional layers, resulting in high computational costs and limited applicability on general-purpose devices. To solve this issue, we propose an enhanced denoising diffusion implicit model (DDIM) that incorporates lightweight depthwise convolution layers within residual networks and self-attention layers. This approach significantly reduces computational overhead while maintaining segmentation performance. We evaluated the proposed DDIM on two distinct medical imaging datasets: X-ray and skin lesion and polyp segmentation. Experimental results demonstrate that our model achieves, with reduced resource requirements, accuracy comparable to standard DDIMs in both visual representation and region-based scoring. The proposed lightweight DDIM offers a promising solution for medical segmentation tasks, enabling easier implementation on general-purpose devices without the need for expensive high-performance computing resources. Full article

The state of the art in IR thermal imaging methods for applications in medical diagnostics is discussed. A review of advances in IR thermal imaging technology in the years 1960–2024 is presented. Recently used artificial intelligence (AI) methods in the analysis of thermal images are the main interest. IR thermography is discussed in view of novel applications of machine learning methods for improved diagnostic analysis and medical treatment. The AI approach aims to improve image quality by denoising thermal images, using applications of AI super-resolution algorithms, removing artifacts, object detection, face and characteristic features localization, complex matching of diagnostic symptoms, etc. Full article