Search Results (3,345)

This paper presents an adaptive noise reduction method based on Complementary Ensemble Empirical Mode Decomposition (CEEMD) to address the non-stationary characteristics and noise interference present in friction vibration signals from mechanical equipment. and friction testing machine simulation experiments. The performance of CEEMD and Ensemble Empirical Mode Decomposition (EEMD) was compared through MATLAB R2023b simulations and experiments conducted on a friction testing machine. CEEMD achieved a computational efficiency 85.6% higher than that of EEMD and effectively reduced mode aliasing. Among them, the adaptive correlation coefficient screening method performed well in signal reconstruction, and the high correlation (correlation coefficient > 0.8) between the denoised signal and the laboratory noise signal was verified using the multi-scale permutation entropy (MPE) theory, which is of great significance for early diagnosis of mechanical faults, prediction of equipment life and timely maintenance decisions. Full article

Conventional Image Signal Processors (ISPs) employ manually crafted designs with limited adaptability, resulting in suboptimal performance in dynamic environments for both visual quality and machine vision applications. While deep learning facilitates adaptive AI-ISPs, supervised approaches encounter domain shift limitations and substantial computational demands that impede edge deployment. This work introduces an adaptive zero-shot AI-ISP that dynamically optimizes processing pipelines without requiring paired training data. The proposed architecture implements dual specialized subnetworks for illumination estimation and denoising enhancement, operating collaboratively under Retinex theory principles to achieve boundary-aware illumination mapping and noise-resilient image restoration. Additionally, a physically constrained loss function is introduced to enhance color fidelity and noise suppression. For practical implementation, an FPGA-accelerated computing engine replaces transposed convolution with optimized bilinear interpolation, effectively eliminating artifacting while achieving superior memory efficiency through customized buffering architectures. A comprehensive evaluation demonstrates highly competitive performance, achieving a PSNR of 19.91/16.62 and an SSIM of 0.591/0.475 on LSRW-Huawei/Nikon datasets, alongside NIQE scores of 2.065/3.025 on DCIM and TM-DIED datasets. The hardware implementation attains 42.5 GOPS/W power efficiency, representing 35.4× and 7.3× improvements over conventional CPU and GPU platforms, establishing a comprehensive edge deployment solution for next-generation intelligent image processing systems. Full article

Classifying which operation a Computer Numerical Control (CNC) machine is executing, not just detecting whether it is functioning correctly, is a monitoring challenge that existing sensor-based studies rarely address. Unlike tool wear estimation, operation-type classification must resolve toolpath strategies and cutting conditions within heterogeneous, noisy sensor streams in which modalities differ widely in their discriminative value. Which sensors are genuinely necessary, and how many can be removed before performance degrades, directly informs retrofit cost and monitoring system design. We present a systematic cross-validated ablation study for a nine-class CNC toolpath and condition classification task, using 120 operation files collected from a desktop CNC mill instrumented with six distributed sensor units spanning inertial, acoustic, environmental, and electrical modalities. To handle multimodal fusion under sensor noise, we introduce the Multimodal Denoising Temporal Attention Encoder with Long Short-Term Memory (MM-DTAE-LSTM), which combines learned modality weighting, cross-modal attention, and a self-supervised denoising objective, followed by recurrent temporal modeling for classification. We evaluate MM-DTAE-LSTM against five baseline model families across five cumulative sensor-ablation levels and ten temporal resolutions, using file-level cross-validation to prevent data leakage from overlapping windows. MM-DTAE-LSTM maintains 92.5% classification accuracy when nearly half the sensor channels are removed (56 of 110 features), whereas simpler baselines degrade by up to 10.7 percentage points under the same reduction. Analysis of variance reveals that pressure channels encode session-level atmospheric variation rather than machining dynamics, exposing how models that cannot suppress uninformative modalities rely on environmental confounds rather than machining physics. Together, these findings translate into concrete sensor-selection and deployment recommendations for cost-effective CNC process monitoring at under USD 500 in hardware, though generalization to industrial machines, diverse materials, and production environments requires further validation. Full article

Remote sensing imagery is a crucial component of remote sensing data. However, in its application to downstream tasks, cloud cover can hinder effective data utilization, making the removal of cloud occlusion from remote sensing images a persistent and important research direction. Recently, diffusion models have demonstrated powerful performance in conditional image generation. However, their direct application to cloud removal yields suboptimal results, as the interference pattern of random Gaussian noise differs significantly from that of actual cloud occlusion. To address this, we developed the Perlin Noise-Based Cloud Removal Diffusion Model (PCRDiff). Compared to traditional diffusion models, PCRDiff abandons random Gaussian noise and instead utilizes Perlin noise to simulate the interference pattern of cloud occlusion on images. Based on this, we designed a novel training and iterative denoising process, along with a corresponding Perlin noise intensity quantization module. Furthermore, we developed a multi-attention fusion module as the backbone of the model to enhance its performance. Extensive experiments on two commonly used benchmark datasets demonstrate that our method achieves superior performance across multiple metrics. Full article

Accurate measurement of the spatial position of targets in a fixed camera is critical in remote sensing applications. Visual spatial positioning methods that rely solely on images are susceptible to adverse factors such as inaccurate camera calibration, imprecise image target detection, and incorrect feature point selection. Complementary to images, the ubiquitous Global Navigation Satellite System (GNSS) data can provide spatial positions of targets, but most of them are low-cost GNSSs with significant positioning noise. In order to fuse these two valuable but flawed positioning measurements to improve the accuracy and stability of spatial positioning, we propose a deep learning multi-modal spatial positioning method by fusing sequential uncalibrated video images and low-cost GNSSs. Firstly, a self-supervised cascade denoising auto-encoder (SCDAE) architecture is built to endow the auto-encoder with robustness to noise in the raw inputs. Then, based on the SCDAE and Bayesian optimal estimation, a Bayesian self-supervised multi-modal fusion positioning method SCDAE-MFP is presented to achieve accurate and stable spatial positioning by self-supervised manifold learning. Specifically, to provide visual self-supervision to the SCDAE-MFP, a visual position denoising auto-encoder module based on dual unsupervised learning is proposed. Extensive experimental results on public datasets showed that SCDAE-MFP outperformed five other classical and state-of-the-art baseline methods by an average of 56.79% in reducing positioning errors. Full article

Chaotic signals commonly exhibit nonlinear and nonstationary characteristics, while noise contamination reduces signal interpretability and degrades subsequent feature extraction and dynamical analysis. To improve the stability of mode-boundary determination and mitigate reconstruction distortion, this paper proposes a hybrid denoising framework that integrates feature mode decomposition (FMD), amplitude-aware permutation entropy (AAPE), dual-tree complex wavelet transform (DTCWT), and Savitzky–Golay (SG) filtering. First, the noisy signal is decomposed into multiple mode components using FMD. Then, the AAPE of each mode is calculated to adaptively distinguish high-frequency noise-dominant modes from non-high-frequency modes. For the high-frequency noise-dominant modes, improved logarithmic threshold shrinkage is applied to the magnitudes of DTCWT complex coefficients to suppress random noise and reduce threshold-induced bias. For the non-high-frequency modes, SG filtering is employed to further attenuate residual noise while preserving local waveform structures. Finally, the processed modes are reconstructed to obtain the denoised signal. Experiments on a simulated Lorenz chaotic signal and a real-world sunspot time series demonstrate that, across different noise levels, AAPE provides more stable mode partitioning than ApEn, CC, and CMSE. Moreover, under Gaussian white noise, Poisson noise, and uniform noise, the proposed method generally achieves a higher output signal-to-noise ratio (SNR) and a lower root mean square error (RMSE) than WT, CEEMD, EEMD, CEEMDAN+LMS, and VMD, while also yielding better performance in phase-space reconstruction and temporal-detail recovery. These results verify the effectiveness and practical applicability of the proposed method for chaotic signal denoising. Full article

Background/Objectives: We aim to evaluate whether digital imaging and communications in medicine (DICOM)-level deep learning-based iodine-boosting applied to dual-source dual-energy computed tomography (DECT) source DICOM improves image quality in low-iodine-dose abdominal DECT in adults undergoing post-procedure follow-up computed tomography (CT). Methods: This retrospective study included 43 adults (April–September 2025) who underwent dynamic dual-source DECT using a low-iodine protocol. Three CT reconstructions were compared: mixed images, conventional 50-keV virtual monoenergetic images (VMIs), and 50-keV VMIs generated after applying DICOM-based deep learning iodine-boosting/denoising to the tube-specific dual-energy source DICOM series prior to VMI/iodine-map reconstruction (deep learning-based reconstruction [DLR]-VMI). Iodine material density (IMD) images were compared between the conventional and DLR-processed datasets. Quantitative attenuation and signal-to-noise ratio (SNR) were assessed using paired and repeated-measures tests. Image quality was scored by two readers using a five-point Likert scale. Results: Attenuation varied across CT reconstructions for all regions of interest in both phases (all overall p < 0.001). Liver attenuation increased from 94.9 ± 22.0 Hounsfield units (HU) (VMI) to 114.5 ± 34.6 HU (DLR-VMI) during the arterial phase and from 127.6 ± 25.6 HU to 166.6 ± 39.9 HU during the portal venous phase (both p < 0.001). Liver SNR improved with DLR-VMI compared to VMI (arterial: 9.11 ± 3.62 vs. 6.06 ± 1.90; portal: 12.74 ± 3.56 vs. 7.90 ± 1.82; both p < 0.001). On IMD images, DLR increased HU-equivalent values and liver SNR (arterial: 5.20 ± 2.89 vs. 2.61 ± 1.39; portal: 9.22 ± 2.81 vs. 4.48 ± 1.28; both p < 0.001). Qualitatively, DLR-VMI yielded the highest overall image-quality scores for both reviewers in both phases (Reviewer 1, arterial/portal: 4 (4–5)/5 (4–5); Reviewer 2, arterial/portal: 4 (3–4)/4 (4–4)). DLR also improved the overall image quality of IMD images for both reviewers (all p < 0.001). Conclusions: Raw DICOM-level iodine-boosting DLR applied to dual-source DECT-source DICOM enabled enhanced image quality and improved quantitative and qualitative metrics in low-iodine-dose abdominal DECT. Full article

Background/Objectives: Brain health monitoring is increasingly essential as modern cognitive load, stress, and lifestyle pressures contribute to widespread neural instability. The paper presents BrainTwin, a next-generation cognitive digital twin, as a patient-specific, constantly updating computer model that combines state-of-the-art MRI analytics for neuro-oncological assessment related to clinical study and management of tumors affecting the central nervous system (including their detection, progression, and monitoring) with real-time EEG-based brain health intelligence. Methods: Structural analysis is driven by an Enhanced Vision Transformer (ViT++), which improves spatial representation and boundary localization, achieving more accurate tumor prediction than conventional models. The extracted tumor volume forms the baseline for short-horizon tumor progression modeling. Parallel to MRI analysis, continuous EEG signals are captured through an in-house wearable skullcap, preprocessed using Edge AI on a Hailo Toolkit-enabled Raspberry Pi 5 for low-latency denoising and secure cloud transmission. Pre-processed EEG packets are authenticated at the fog layer, ensuring secure and reliable cloud transfer, enabling significant load reduction in the edge and cloud nodes. In the digital twin, EEG characteristics offer real-time functional monitoring through dynamic brainwave analysis, while a BiLSTM classifier distinguishes relaxed, stress, and fatigue states, which are probabilistically inferred cognitive conditions derived from EEG spectral patterns. Unlike static MRI imaging, EEG provides real-time brain health monitoring. The BrainTwin performs EEG–MRI fusion, correlating functional EEG metrics with ViT++ structural embeddings to produce a single risk score that can be interpreted by clinicians to determine brain vulnerability to future diseases. Explainable artificial intelligence (XAI) provides clinical interpretability through gradient-weighted class activation mapping (Grad-CAM) heatmaps, which are used to interpret ViT++ decisions and are visualized on a 3D interactive brain model to allow more in-depth inspection of spatial details. Results: The evaluation metrics demonstrate a BiLSTM macro-F1 of 0.94 (Precision/Recall/F1: Relaxed 0.96, Stress 0.93, Fatigue 0.92) and a ViT++ MRI accuracy of 96%, outperforming baseline architectures. Conclusions: These results demonstrate BrainTwin’s reliability, interpretability, and clinical utility as an integrated digital companion for tumor assessment and real-time functional brain monitoring. Full article

Against the backdrop of smart cities and digital cultural tourism, the accurate prediction of urban passenger flow is of great significance for public security management and resource allocation. However, existing studies mostly rely on single data sources or only perform a simple concatenation of multi-source features, lacking systematic indicator system design. Meanwhile, weekly or monthly data are commonly used with coarse temporal granularity, making it difficult to capture short-term fluctuations and lag effects. To overcome these limitations, this paper collects the daily passenger flow data of Hangzhou from 15 March 2024 to 15 March 2025; integrates multi-dimensional factors such as keyword search trends across platforms, holidays and major events, and online public opinion; and constructs three daily characteristic indicators: online search index, humanistic–meteorological index, and textual sentiment index. The data denoising, dimensionality reduction, and sentiment quantification are realized through methods including SSA, PCA, and SnowNLP. On this basis, a hybrid CNN-GRU model integrated with the attention mechanism is proposed. An improved artificial bee colony (ABC) algorithm is adopted for global hyperparameter optimization, and a weighted hybrid loss function (JQHL) is introduced to enhance the model’s adaptability to extreme values. The results show that the ABC-CNN-GRU-Attention model, incorporating multi-dimensional indicators, outperforms traditional methods on evaluation metrics, including MAE, RMSE, MAPE, R², and RPD, demonstrating a higher prediction accuracy and robustness. Full article

Against the background of highly interconnected global capital markets and rapidly propagating cross-lingual information streams, traditional anomaly detection paradigms based solely on single-modality numerical time-series sensors are insufficient for forward-looking risk sensing. From the perspective of artificial intelligence-driven sensing, this study proposes a multilingual semantic–numerical collaborative Transformer framework to construct a unified multimodal financial sensing architecture for intelligent anomaly sensing and risk perception. Within the proposed sensing paradigm, multilingual texts are conceptualized as semantic sensors that continuously emit event-driven sensing signals, while market prices, trading volumes, and order book dynamics are modeled as heterogeneous numerical sensor streams reflecting behavioral market sensing responses. These heterogeneous sensors are jointly integrated through a cross-modal sensor fusion architecture. A cross-modal temporal alignment attention mechanism is designed to explicitly model dynamic lag structures between semantic sensing signals and numerical sensor responses, enabling temporally adaptive sensor-level alignment and fusion. To enhance sensing robustness, a multilingual semantic noise-robust encoding module is introduced to suppress unreliable textual sensor noise and stabilize cross-lingual semantic sensing representations. Furthermore, a semantic–numerical collaborative risk fusion module is constructed within a shared latent sensing space to achieve adaptive sensor contribution weighting and cross-sensor feature coupling, thereby improving anomaly sensing accuracy and robustness under complex multimodal sensing environments. Extensive experiments conducted on real-world multi-market financial sensing datasets demonstrate that the proposed artificial intelligence-driven sensing framework significantly outperforms representative statistical and deep learning baselines. The framework achieves a Precision of $0.852$, Recall of $0.781$, F1-score of $0.815$, and an AUC of $0.892$, while substantially improving early warning time in practical risk sensing scenarios. In cross-market transfer settings, the proposed sensing architecture maintains stable anomaly sensing performance under bidirectional domain shifts, with AUC consistently exceeding $0.86$, indicating strong structural generalization across heterogeneous sensing environments. Ablation analysis further verifies that temporal sensor alignment, semantic sensor denoising, and collaborative cross-sensor risk coupling contribute independently and synergistically to the overall sensing performance. Overall, this study establishes a scalable multimodal intelligent sensing framework for dynamic financial anomaly sensing, providing an effective artificial intelligence-driven sensing solution for cross-market risk surveillance and adaptive financial signal sensing. Full article

In Coiled Tubing (CT) acoustic telemetry, the reliability of surface signal reception is severely challenged by the “contact dead zone” of traditional probes and complex nonstationary environmental noise. To address these issues, this paper proposes a hardware-software integrated solution for high-fidelity signal extraction. In terms of hardware, a novel pickup probe based on the micro-lever principle is developed. By utilizing a pivoted lever structure with an optimized arm ratio of 2.6 to 1 and a full pressure-balanced mechanism, the design physically overcomes the contact dead zone inherent in traditional pressure-compensating probes and effectively isolates low frequency common-mode interference through a lateral floating architecture. In terms of software, a joint denoising model combining Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and wavelet thresholding is proposed. A cross-correlation coefficient criterion is introduced to adaptively screen intrinsic mode functions and eliminate residual fluid turbulence noise. Field experiments on a 1500 ft full-scale circulation loop demonstrate that the proposed probe improves the detection sensitivity of the radial breathing mode by approximately 20.6 dB compared to the baseline, while effectively eliminating stick-slip friction noise during dynamic tripping. Furthermore, the joint algorithm increases the Signal to noise Ratio by an additional 16.9 dB under typical pumping conditions of 0.5 bpm, with a normalized cross-correlation exceeding 0.96. These results verify that the proposed method effectively solves the bottleneck of weak signal detection in deep wells, providing robust technical support for CT telemetry operations. Full article

Uniform circular arrays (UCAs) are widely used in underwater source localization due to their omnidirectional coverage. However, random sensor position errors caused by installation inaccuracies and environmental disturbances convert UCAs into non-uniform circular arrays (NCAs), severely degrading the performance of high-resolution direction of arrival (DOA) estimation algorithms. To address this issue, this paper proposes a robust DOA estimation method that integrates empirical mode decomposition (EMD) denoising with prior-weighted iterative least squares (PWLS) correction. The method first applies EMD to adaptively denoise received signals by selecting intrinsic mode functions based on a combined energy-correlation criterion. An initial DOA estimate is then obtained using the MUSIC algorithm. Finally, a PWLS correction algorithm leverages prior knowledge of deviated sensors to iteratively fit the circle center and gradually pull sensor positions toward the ideal circumference, using a differentiated relaxation mechanism to suppress outliers while preserving geometric features. Systematic Monte Carlo simulations compare five correction algorithms under multi-frequency and wideband signals. The results show that both multi-frequency and wideband signals reduce estimation errors to below 0.1°, with the proposed PWLS achieving the best accuracy under multi-frequency signals, while all algorithms approach zero error under wideband signals. The PWLS algorithm converges in about 10 iterations with high computational efficiency, providing a reliable solution for practical underwater NCA applications. Full article

To address the challenges of unstable target localization and poor multi-module coordination in automated green pepper harvesting—caused by occlusions from branches and leaves, as well as varying lighting conditions—this paper presents the design and implementation of a modular robotic picking system. At the perception level, the system integrates a YOLOv8 detector with a RealSense D435i camera to identify and locate the calyx–ectocarp junctions of green peppers. An integrated multi-target tracking and filtering framework is proposed, which fuses multi-feature association, trajectory smoothing and coordinate denoising strategies to suppress depth noise and trajectory jitter, thereby enhancing the stability and accuracy of 3D localization. At the control and execution level, a depth-first picking sequence strategy with ID freeze-state management is implemented within a multithreaded software–hardware co-design architecture. This approach avoids task conflicts and duplicate operations while supporting continuous multi-fruit harvesting. Field experiments under natural outdoor lighting and varying occlusion levels demonstrate that the proposed system achieves recognition rates of 91.57% and 80.29% and harvesting success rates of 82.85% and 77.68% for non-occluded and lightly occluded fruits, respectively. The average picking cycle per pepper fruit is 9.8 s. This system provides an effective technical solution for addressing stability control challenges in the automated harvesting process of green peppers. Full article

To address the issues of uneven grayscale distribution, weak defect features, and small target scales on the coating surface of LCD polarizers during manufacturing, an improved YOLOv10-N-based method is proposed for surface defect detection. First, a polarizer coating defect dataset is constructed based on the LCD polarizer coating process and the characteristics of coating defects. Adaptive median filtering is then employed for image denoising, while a particle-swarm-optimization-based improved histogram equalization method is adopted for image enhancement. Next, the Scale-aware Pyramid Pooling (SCPP) module is introduced into the C2f module of the backbone network to construct the C2f_SCPP feature extraction module, thereby improving the model’s ability to detect coating defects with different morphologies through multi-scale semantic feature fusion. In addition, rotation-equivariant convolution PreCM is incorporated into the SPPF module of the backbone network to build the SPPF_PreCM module, which effectively suppresses feature redundancy and scale conflicts while strengthening the representation of tiny defects. Finally, while retaining the original Distribution Focal Loss (DFL) branch of YOLOv10, WIoU is used to replace CIoU as the IoU loss term in bounding box regression, thereby improving localization accuracy and accelerating model convergence during training. Experimental results show that, compared with YOLOv10-N, the proposed method improves mAP@0.5 and mAP@0.5:0.95 by 1.8 and 2.8 percentage points, respectively, demonstrating its effectiveness for polarizer coating defect detection. However, its generalization capability under diverse production environments, varying illumination conditions, and complex noise scenarios still requires further investigation. Full article

Autoencoder-based models have become a fundamental component of unsupervised and self-supervised learning in natural language processing (NLP), enabling models to learn compact latent representations through input reconstruction. From early denoising autoencoders to probabilistic variational autoencoders (VAEs) and transformer-based masked autoencoding, reconstruction-driven objectives have played a significant role in shaping modern approaches to text representation and generation. This review provides a comprehensive analysis of the evolution of autoencoder architectures and training objectives in NLP, and synthesizes applications of VAEs across language modeling, controllable text generation, machine translation, sentiment modeling, and multilingual representation learning. Although previous surveys have examined deep generative models or representation learning in NLP, there remains a lack of a unified review that systematically connects classical autoencoder variants, variational formulations, and modern transformer-based masked autoencoders within a single conceptual framework. To address this gap, this work consolidates architectural developments, training objectives, and major application domains under a reconstruction-based learning perspective, offering a structured comparison of modeling choices, datasets, and evaluation practices. Our analysis highlights the strengths and limitations of existing approaches, discusses the ongoing influence of autoencoder-style learning in NLP, and outlines future research directions focused on improving training stability, designing more structured latent spaces, and enhancing multilingual representation learning. Full article