Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (2,872)

Search Parameters:
Keywords = wavelet transformation

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
17 pages, 4793 KiB  
Article
Spectral Estimation of Carotenoid Density in Populus pruinosa Leaves
by Shaoying Sun, Jiaqiang Wang and Chongfa Cai
Forests 2025, 16(3), 394; https://doi.org/10.3390/f16030394 (registering DOI) - 23 Feb 2025
Viewed by 141
Abstract
Carotenoids play a crucial role in the photosynthesis process in plants. Estimating and modeling the carotenoid content in Populus pruinosa leaves via high-spectrum technology is highly important for health status monitoring. This study involved acquiring the spectral reflectance of Populus pruinosa leaves at [...] Read more.
Carotenoids play a crucial role in the photosynthesis process in plants. Estimating and modeling the carotenoid content in Populus pruinosa leaves via high-spectrum technology is highly important for health status monitoring. This study involved acquiring the spectral reflectance of Populus pruinosa leaves at different times, followed by smoothing the data with a Savitzky—Golay filter, and then using methods such as first derivative (FD), continuous wavelet transform (CWT), and first-order derivative combined with continuous wavelet transform (CWT+FD), creating three spectral transformation methods. Two- and three-dimensional vegetation indices were then constructed in a unified manner. Two modeling methods, backpropagation neural network (BPNN) and support vector regression (SVR), were employed to estimate the leaf carotenoid density by combining the vegetation indices. The results show that after the spectral reflectance of the canopy of Populus pruinosa is processed by FD, CWT, and CWT+FD on the basis of SG smoothing, it can effectively highlight the spectral characteristics of Populus pruinosa leaves, and the local spectral absorption features are more significant. Compared with the three spectral preprocessing methods, the results showed that the correlation between the values processed by the FD + CWT method and the leaf carotenoid density is the highest. The constructed three-band vegetation index exhibited a 4.26% stronger correlation with carotenoid density than did the two-band vegetation index. Among the three-band index-based models, the SVR model outperforms the BPNN model. For chlorophyll density, the SVR model based on the three-band index processed using CWT+FD achieves the best performance. The coefficient of determination (R2) for the SVR model set was 0.782, the root-mean-square error (RMSE) was 0.022, and the relative percentage deviation (RPD) was 0.206. For the validation set, the (R2) value was 0.648, the RMSE was 0.023, and the RPD was 1.526, indicating the best model accuracy. Full article
(This article belongs to the Section Forest Inventory, Modeling and Remote Sensing)
Show Figures

Figure 1

23 pages, 619 KiB  
Article
Electroencephalogram Based Emotion Recognition Using Hybrid Intelligent Method and Discrete Wavelet Transform
by Duy Nguyen, Minh Tuan Nguyen and Kou Yamada
Appl. Sci. 2025, 15(5), 2328; https://doi.org/10.3390/app15052328 - 21 Feb 2025
Viewed by 176
Abstract
Electroencephalography-based emotion recognition is essential for brain-computer interface combined with artificial intelligence. This paper proposes a novel algorithm for human emotion detection using a hybrid paradigm of convolutional neural networks and a boosting model. The proposed algorithm employs two subsets of 18 and [...] Read more.
Electroencephalography-based emotion recognition is essential for brain-computer interface combined with artificial intelligence. This paper proposes a novel algorithm for human emotion detection using a hybrid paradigm of convolutional neural networks and a boosting model. The proposed algorithm employs two subsets of 18 and 14 features extracted from four sub-bands using discrete wavelet transform. These features are identified as the optimal subsets of the most relevant, among 42 original input features extracted from two subsets of 8 and 6 productive channels using a dual genetic algorithm combined with a wise-subject 5-fold cross validation procedure in which the first and second genetic algorithms address the efficient channels and optimal feature subsets. The feature subsets are estimated by differently intelligent models and wise-subject 5-fold cross validation procedure on the validation set. The proposed algorithm produces an accuracy of 70.43%/76.05%, precision of 69.88%/74.57%, recall of 98.70%/99.17%, and F1 score of 81.83%/85.13% for valence/arousal classifications, which suggest that the frontal and left regions of the cortex associate especially to human emotions. Full article
Show Figures

Figure 1

24 pages, 4937 KiB  
Article
DRDA-Net: Deep Residual Dual-Attention Network with Multi-Scale Approach for Enhancing Liver and Tumor Segmentation from CT Images
by Wail M. Idress, Yuqian Zhao, Khalid A. Abouda and Shaodi Yang
Appl. Sci. 2025, 15(5), 2311; https://doi.org/10.3390/app15052311 - 21 Feb 2025
Viewed by 165
Abstract
Liver cancer is a major global health challenge, significantly contributing to mortality rates. The accurate segmentation of liver and tumors from clinical CT images plays a crucial role in selecting therapeutic strategies for liver disease and treatment monitoring but remains challenging due to [...] Read more.
Liver cancer is a major global health challenge, significantly contributing to mortality rates. The accurate segmentation of liver and tumors from clinical CT images plays a crucial role in selecting therapeutic strategies for liver disease and treatment monitoring but remains challenging due to liver shape variability, proximity to other organs, low contrast between tumors and healthy tissues, and unclear lesion boundaries. To address these challenges, we propose the Deep Residual Dual-Attention Network (DRDA-Net), a novel model for end-to-end liver and tumor segmentation. DRDA-Net integrates a Residual UNet architecture with dual-attention mechanisms, multi-scale tile and patch extraction, and an Ensemble method. The dual-attention mechanisms enhance focus on key regions, addressing variations in size, shape, and intensity, while the multi-scale approach captures fine details and broader contexts. Additionally, we introduce a unique pre-processing pipeline employing a two-channel denoising technique using convolutional neural networks (CNNs) and stationary wavelet transforms (SWTs) to reduce noise while preserving structural details. Evaluated on the 3DIRCADb dataset, DRDA-Net achieved Dice scores of 97.03% and 75.4% for liver and tumor segmentation, respectively, outperforming state-of-the-art methods. These results demonstrate the model’s effectiveness in overcoming segmentation challenges and highlight its potential to improve liver cancer diagnostics and treatment planning. Full article
Show Figures

Figure 1

18 pages, 48665 KiB  
Article
A Transfer Learning Approach for Toe Walking Recognition Using Surface Electromyography on Leg Muscles
by Andrea Manni, Gabriele Rescio, Anna Maria Carluccio, Andrea Caroppo and Alessandro Leone
Sensors 2025, 25(5), 1305; https://doi.org/10.3390/s25051305 - 20 Feb 2025
Viewed by 134
Abstract
Gait is a complex motor process that involves the coordination and synchronization of various body parts through continuous interaction with the environment. Monitoring gait is crucial for the early detection of abnormalities, such as toe walking, which is characterized by limited or absent [...] Read more.
Gait is a complex motor process that involves the coordination and synchronization of various body parts through continuous interaction with the environment. Monitoring gait is crucial for the early detection of abnormalities, such as toe walking, which is characterized by limited or absent heel contact with the floor during walking. Persistent toe walking can cause severe foot, ankle, and musculature conditions; poor balance; increased risk of falling or tripping; and can affect overall quality of life, making it difficult, for example, to participate in sports or social activities. This study proposes a new approach to detect toe walking using surface Electromyography (sEMG) on lower limbs. sEMG sensors, by measuring the electrical activity of muscles, can see signals before the movement corresponding to muscle activation, contributing to an early detection of a possible problem. The sEMG signal presents significant complexity due to its noisy nature and the challenge of extracting meaningful features for classification. To address this issue and enhance the model’s robustness across different devices and configurations, a Transfer Learning (TL) approach is introduced. This method leverages pre-trained models to effectively handle the variability of sEMG data and improve classification accuracy. In particular, Continuous Wavelet Transform (CWT) is applied to sEMG-filtered signals (with time windows of 1 s) to convert them into 2D images (scalograms). Preliminary tests were performed on a public dataset using some of the most well-known pre-trained architectures, obtaining an accuracy of about 95% on InceptionResNetV2. Full article
(This article belongs to the Special Issue Biosignal Sensing Analysis (EEG, EMG, ECG, PPG) (2nd Edition))
20 pages, 6125 KiB  
Article
Intelligent Monitoring of Tunnel Fire Smoke Based on Improved YOLOX and Edge Computing
by Chaojing Li, Bochao Zhu, Guangyao Chen, Qiming Li and Zhao Xu
Appl. Sci. 2025, 15(4), 2127; https://doi.org/10.3390/app15042127 - 17 Feb 2025
Viewed by 248
Abstract
To overcome the defects of traditional fire detection methods that have a high false alarm rate and long delay, a smart tunnel fire monitoring method based on a YOLOX deep convolutional neural network and edge computing is proposed. This method first improves the [...] Read more.
To overcome the defects of traditional fire detection methods that have a high false alarm rate and long delay, a smart tunnel fire monitoring method based on a YOLOX deep convolutional neural network and edge computing is proposed. This method first improves the detection accuracy by analyzing the relationship between frequency domain and convolutional neural networks and the use of wavelet transform. Then, based on the smoke features observed in the experiments, a fuzzy loss method is proposed to accelerate the model convergence speed. To address the issue of a weak computing power of edge devices, the training model is optimized by using knowledge distillation and model quantization, thereby improving the running speed on edge devices. At the same time, a series of related lightweight methods are adopted to optimize the model, reduce the computational cost, and improve the detection speed. Finally, the accuracy of flame and smoke detection on a self-built dataset reaches 85%, which is about 1.8% higher than the baseline method YOLOX and achieves a balance between the speed and accuracy of the model. Full article
Show Figures

Figure 1

22 pages, 4409 KiB  
Article
A Method for Reducing White Noise in Partial Discharge Signals of Underground Power Cables
by Jifang Li and Qilong Zhang
Electronics 2025, 14(4), 780; https://doi.org/10.3390/electronics14040780 - 17 Feb 2025
Viewed by 258
Abstract
Online partial discharge (PD) detection for power cables is one reliable means of monitoring their health. However, strong interference by white noise poses a major challenge in the process of collecting information on partial discharge signals. To solve the problem whereby the wavelet [...] Read more.
Online partial discharge (PD) detection for power cables is one reliable means of monitoring their health. However, strong interference by white noise poses a major challenge in the process of collecting information on partial discharge signals. To solve the problem whereby the wavelet threshold estimation based on sample entropy falls into the local optimal and the wavelet noise reduction makes it difficult to process detailed information, we propose a partial discharge signal noise reduction method based on a combination of improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and discrete wavelet transform (DWT) with multiscale sample entropy (MSE). Firstly, the ICEEMDAN method was used to decompose the original sequence into multiple intrinsic mode components. The intrinsic mode function (IMF) components were grouped using the mutual information method, and high-frequency noise was eliminated using the kurtosis criterion. Next, an MSE model was established to optimize the wavelet threshold, and wavelet noise reduction was applied to the effective component. The ICEEMDAN-MSE-DWT method can retain effective information while achieving complete denoising, which alleviates the problem of information loss that occurs after denoising using the wavelet method. Lastly, as shown by our simulation and experimental results, the proposed method can effectively realize noise reduction for power cable partial discharge signals, thus providing an effective method. Full article
Show Figures

Figure 1

25 pages, 4721 KiB  
Article
Human Respiration and Motion Detection Based on Deep Learning and Signal Processing Techniques to Support Search and Rescue Teams
by Özden Niyaz, Mehmet Ziya Erenoğlu, Ahmet Serdar Türk, Sultan Aldirmaz Colak, Burcu Erkmen and Nurhan Türker Tokan
Appl. Sci. 2025, 15(4), 2097; https://doi.org/10.3390/app15042097 - 17 Feb 2025
Viewed by 206
Abstract
The quick and effective detection of humans trapped under debris is crucial in search and rescue operations. This study explores the use of antennas operating within the 150–650 MHz frequency range to identify human respiration and movement under building wreckage. A debris model [...] Read more.
The quick and effective detection of humans trapped under debris is crucial in search and rescue operations. This study explores the use of antennas operating within the 150–650 MHz frequency range to identify human respiration and movement under building wreckage. A debris model consisting of construction materials was generated at the laboratory, and attenuation characteristics were observed to set ideal operating frequencies. Time-dependent transmission coefficient data were collected over 20 s and processed using short-time Fourier transform, wavelet transform, and empirical mode decomposition for time-frequency analysis. To enhance signal clarity, denoising techniques were applied before the radar signals were categorized into three classes: empty debris, human respiration, and human movement. Generative adversarial networks augmented environmental noise data to enrich training datasets comprising nine subsets. Deep learning models, including temporal convolutional networks, long short-term memory, and convolutional neural networks, were employed for classification. Hyperparameter optimization via random search further refined model performance. Results indicate that the convolutional neural networks using short-time Fourier transform data consistently achieved the highest classification accuracy across subsets. These findings demonstrate the potential of combining radar with deep learning for reliable human detection under debris, advancing rescue efforts in disaster scenarios. Full article
Show Figures

Figure 1

20 pages, 8383 KiB  
Article
Self-Supervised Time-Series Preprocessing Framework for Maritime Applications
by Shengli Dong, Jilong Liu, Bing Han, Shengzheng Wang, Hong Zeng and Meng Zhang
Electronics 2025, 14(4), 765; https://doi.org/10.3390/electronics14040765 - 16 Feb 2025
Viewed by 247
Abstract
This study proposes a novel self-supervised data-preprocessing framework for time-series forecasting in complex ship systems. The framework integrates an improved Learnable Wavelet Packet Transform (L-WPT) for adaptive denoising and a correlation-based Uniform Manifold Approximation and Projection (UMAP) approach for dimensionality reduction. The enhanced [...] Read more.
This study proposes a novel self-supervised data-preprocessing framework for time-series forecasting in complex ship systems. The framework integrates an improved Learnable Wavelet Packet Transform (L-WPT) for adaptive denoising and a correlation-based Uniform Manifold Approximation and Projection (UMAP) approach for dimensionality reduction. The enhanced L-WPT incorporates Reversible Instance Normalization to improve training efficiency while preserving denoising performance, especially for low-frequency sporadic noise. The UMAP dimensionality reduction, combined with a modified K-means clustering using correlation coefficients, enhances the computational efficiency and interpretability of the reduced data. Experimental results validate that state-of-the-art time-series models can effectively forecast the data processed by this framework, achieving promising MSE and MAE metrics. Full article
Show Figures

Figure 1

17 pages, 916 KiB  
Article
A Multi-Scale Self-Supervision Approach for Bearing Anomaly Detection Using Sensor Data Under Multiple Operating Conditions
by Zhuoheng Dai, Lei Jiang, Feifan Li and Yingna Chen
Sensors 2025, 25(4), 1185; https://doi.org/10.3390/s25041185 - 15 Feb 2025
Viewed by 323
Abstract
Early fault detection technologies play a decisive role in preventing equipment failures in industrial production. The primary challenges in early fault detection for industrial applications include the severe imbalance of time-series data, where normal operating data vastly outnumber anomalous data, and in some [...] Read more.
Early fault detection technologies play a decisive role in preventing equipment failures in industrial production. The primary challenges in early fault detection for industrial applications include the severe imbalance of time-series data, where normal operating data vastly outnumber anomalous data, and in some cases, anomalies may be virtually absent. Additionally, the frequent changes in operational modes during machinery operation further complicate the detection process, making it difficult to effectively identify faults across varying conditions. This study proposes a bearing early anomaly detection method based on contrastive learning and reconstruction approaches to address the aforementioned issues. The raw time-domain vibration data, which were collected from sensors mounted on the bearings of the machinery, are first preprocessed using the Ricker wavelet transform to effectively remove noise and extract useful signal components. These processed signals are then fed into a BYOL-based contrastive learning network to learn more discriminative global feature representations. In addition, we design the reconstruction loss to complement contrastive learning. By reconstructing the masked original data, the reconstruction loss forces the model to learn detailed information, thereby emphasizing the preservation and restoration of local details. Our model not only eliminates the reliance on negative samples found in mainstream unsupervised methods but also captures data features more comprehensively, achieving superior fault detection accuracy under different operating conditions compared to related methods. Experiments on the widely used CWRU multi-condition-bearing fault dataset demonstrate that our method achieves an average fault detection accuracy of 96.97%. Moreover, the experimental results show that on the full-cycle IMS dataset, our method detects early faults at least 2.3 h earlier than the other unsupervised methods. Furthermore, the validation results for the full-cycle XJTU-SY dataset further demonstrate its excellent generalization ability. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Figure 1

31 pages, 16566 KiB  
Article
Storm Surge Risk Assessment Based on LULC Identification Utilizing Deep Learning Method and Multi-Source Data Fusion: A Case Study of Huizhou City
by Lichen Yu, Hao Qin, Wei Wei, Jiaxiang Ma, Yeyi Weng, Haoyu Jiang and Lin Mu
Remote Sens. 2025, 17(4), 657; https://doi.org/10.3390/rs17040657 - 14 Feb 2025
Viewed by 280
Abstract
Among the frequent natural disasters, there is a growing concern that storm surges may cause enhanced damage to coastal regions due to the increase in climate extremes. It is widely believed that storm surge risk assessment is of great significance for effective disaster [...] Read more.
Among the frequent natural disasters, there is a growing concern that storm surges may cause enhanced damage to coastal regions due to the increase in climate extremes. It is widely believed that storm surge risk assessment is of great significance for effective disaster prevention; however, traditional risk assessment often relies on the land use data from the government or manual interpretation, which requires a great amount of material resources, labor and time. To improve efficiency, this study proposes a framework for conducting fast risk assessment in a chosen area based on social sensing data and a deep learning method. The coupled Finite Volume Coastal Ocean Model (FVCOM) and Simulating Waves Nearshore (SWAN) model are applied for simulating inundation of five storm surge scenarios. Social sensing data are generated by fusing POI kernel density and night light data through wavelet transform. Subsequently, the Swin Transformer model receives two sets of inputs: one includes social sensing data, Normalized Difference Water Index (MNDWI) and Normalized Difference Chlorophyll Index (NDCI), and the other is Red, Green, Blue bands. The ensembled model can be used for fast land use identification for vulnerability assessment, and the accuracy is improved by 3.3% compared to the traditional RGB input. In contrast to traditional risk assessment approaches, the proposed method can conduct emergency risk assessments within a few hours. In the coast area of Huizhou city, the area considered to be at risk is 135 km2, 89 km2, 82 km2, 72 km2 and 64 km2, respectively, when the central pressure of the typhoon is 880, 910, 920, 930 and 940 hpa. The Daya Bay Petrochemical Zone and central Huangpu waterfront are two areas at high risk. The conducted risk maps can help decision-makers better manage storm surge risks to identify areas at potential risk, prepare for disaster prevention and mitigation. Full article
Show Figures

Figure 1

21 pages, 2447 KiB  
Article
Advancing Taxonomy with Machine Learning: A Hybrid Ensemble for Species and Genus Classification
by Loris Nanni, Matteo De Gobbi, Roger De Almeida Matos Junior and Daniel Fusaro
Algorithms 2025, 18(2), 105; https://doi.org/10.3390/a18020105 - 14 Feb 2025
Viewed by 251
Abstract
Traditionally, classifying species has required taxonomic experts to carefully examine unique physical characteristics, a time-intensive and complex process. Machine learning offers a promising alternative by utilizing computational power to detect subtle distinctions more quickly and accurately. This technology can classify both known (described) [...] Read more.
Traditionally, classifying species has required taxonomic experts to carefully examine unique physical characteristics, a time-intensive and complex process. Machine learning offers a promising alternative by utilizing computational power to detect subtle distinctions more quickly and accurately. This technology can classify both known (described) and unknown (undescribed) species, assigning known samples to specific species and grouping unknown ones at the genus level—an improvement over the common practice of labeling unknown species as outliers. In this paper, we propose a novel ensemble approach that integrates neural networks with support vector machines (SVM). Each animal is represented by an image and its DNA barcode. Our research investigates the transformation of one-dimensional vector data into two-dimensional three-channel matrices using discrete wavelet transform (DWT), enabling the application of convolutional neural networks (CNNs) that have been pre-trained on large image datasets. Our method significantly outperforms existing approaches, as demonstrated on several datasets containing animal images and DNA barcodes. By enabling the classification of both described and undescribed species, this research represents a major step forward in global biodiversity monitoring. Full article
(This article belongs to the Special Issue Algorithms in Data Classification (2nd Edition))
Show Figures

Figure 1

20 pages, 6948 KiB  
Article
Detection of Chatter in Machining Processes by the Multiscale Maximum Approximate Entropy and Continuous Wavelet Transform
by Daniel Pérez-Canales, Juan Carlos Jáuregui-Correa, José Álvarez-Ramírez and Luciano Vela-Martínez
Appl. Mech. 2025, 6(1), 15; https://doi.org/10.3390/applmech6010015 - 14 Feb 2025
Viewed by 271
Abstract
Chatter is a complex dynamic instability in machining processes and presents nonlinear and nonstationary behavior. Detection of this phenomenon before a catastrophic failure occurs has great importance in the industry today. This behavior demands online monitoring signal-processing techniques suitable for facing these kinds [...] Read more.
Chatter is a complex dynamic instability in machining processes and presents nonlinear and nonstationary behavior. Detection of this phenomenon before a catastrophic failure occurs has great importance in the industry today. This behavior demands online monitoring signal-processing techniques suitable for facing these kinds of dynamics such as approximate entropy (AE) and wavelet transform. Moreover, AE is useful for dealing with noisy signals and requires a relatively small amount of observations. In this study, we propose an improved AE methodology, the multiscale maximum approximate entropy (MMAE), to detect chatter in milling processes. The maximum AE is achieved by the calculation of the parameter r proposed by Sheng and Chon. In the past, the calculation of this parameter was a drawback of the AE technique. The results show the effectiveness of this proposed technique in detecting clearly different gradual and drastic changes in chatter conditions. Moreover, a more known technique is presented: the time–frequency maps provided by continuous wavelet transform (CWT). The results also show the efficacy of this technique in detecting different levels of chatter. The results are corroborated by the machining piece observation of the chatter phenomenon. MMAE is also compared with sample entropy (SE) and the Hurst exponent obtained by the R/S analysis. At the end, a comparison analysis of the mentioned techniques is carried out, showing that they all have advantages and disadvantages. However, the disadvantages of MMAE and CWT can be solved, as mentioned in the comparison section. Thus, the conclusion is that MMAE and CWT techniques are optimal for the online monitoring of chatter in machining processes. Full article
Show Figures

Figure 1

13 pages, 3483 KiB  
Article
Deep Learning-Based Exposure Asymmetry Multispectral Reconstruction from Digital RGB Images
by Jinxing Liang, Xin Hu, Wensen Zhou, Kaida Xiao and Zhaojing Wang
Symmetry 2025, 17(2), 286; https://doi.org/10.3390/sym17020286 - 13 Feb 2025
Viewed by 365
Abstract
Multispectral reconstruction is an important way to acquire spectral images with a high spatial resolution as snapshots. Current deep learning-based multispectral reconstruction models perform well under symmetric conditions, where the exposure of training and testing images is consistent. However, further research has shown [...] Read more.
Multispectral reconstruction is an important way to acquire spectral images with a high spatial resolution as snapshots. Current deep learning-based multispectral reconstruction models perform well under symmetric conditions, where the exposure of training and testing images is consistent. However, further research has shown that these models are sensitive to exposure changes. When the exposure symmetry is not maintained and testing images are input into the multispectral reconstruction model under different exposure conditions, the reconstructed multispectral images tend to deviate from the real ground truth to varying degrees. This limitation restricts the robustness and applicability of the model in practical scenarios. To address this challenge, we propose an exposure estimation multispectral reconstruction model of EFMST++ with data augmentation and optimized deep learning architecture, where Retinex decomposition and a wavelet transform are introduced into the proposed model. Based on the currently available dataset in this field, a comprehensive comparison is made between the proposed and existing models. The results show that after the current multispectral reconstruction models are retrained using the augmented datasets, the average MRAE and RMSE of the current most advanced model of MST++ are reduced from 0.570 and 0.064 to 0.236 and 0.040, respectively. The proposed method further reduces the average MRAE and RMSE to 0.229 and 0.037, with the average PSNR increasing from 27.94 to 31.43. The proposed model supports the use of multispectral reconstruction in open environments. Full article
(This article belongs to the Section Computer)
Show Figures

Figure 1

24 pages, 2050 KiB  
Article
An Autoregressive-Based Motor Current Signature Analysis Approach for Fault Diagnosis of Electric Motor-Driven Mechanisms
by Roberto Diversi, Alice Lenzi, Nicolò Speciale and Matteo Barbieri
Sensors 2025, 25(4), 1130; https://doi.org/10.3390/s25041130 - 13 Feb 2025
Viewed by 331
Abstract
Maintenance strategies such as condition-based maintenance and predictive maintenance of machines have gained importance in industrial automation firms as key concepts in Industry 4.0. As a result, online condition monitoring of electromechanical systems has become a crucial task in many industrial applications. Motor [...] Read more.
Maintenance strategies such as condition-based maintenance and predictive maintenance of machines have gained importance in industrial automation firms as key concepts in Industry 4.0. As a result, online condition monitoring of electromechanical systems has become a crucial task in many industrial applications. Motor current signature analysis (MCSA) is an interesting noninvasive alternative to vibration analysis for the condition monitoring and fault diagnosis of mechanical systems driven by electric motors. The MCSA approach is based on the premise that faults in the mechanical load driven by the motor manifest as changes in the motor’s current behavior. This paper presents a novel data-driven, MCSA-based CM approach that exploits autoregressive (AR) spectral estimation. A multiresolution analysis of the raw motor currents is first performed using the discrete wavelet transform with Daubechies filters, enabling the separation of noise, disturbances, and variable torque effects from the current signals. AR spectral estimation is then applied to selected wavelet details to extract relevant features for fault diagnosis. In particular, a reference AR power spectral density (PSD) is estimated using data collected under healthy conditions. The AR PSD is then continuously or periodically updated with new data frames and compared to the reference PSD through the Symmetric Itakura–Saito spectral distance (SISSD). The SISSD, which serves as the health indicator, has proven capable of detecting fault occurrences through changes in the AR spectrum. The proposed procedure is tested on real data from two different scenarios: (i) an experimental in-house setup where data are collected during the execution of electric cam motion tasks (imbalance faults are emulated); (ii) the Korea Advanced Institute of Science and Technology testbed, whose data set is publicly available (bearing faults are considered). The results demonstrate the effectiveness of the method in both fault detection and isolation. In particular, the proposed health indicator exhibits strong detection capabilities, as its values under fault conditions exceed those under healthy conditions by one order of magnitude. Full article
Show Figures

Figure 1

27 pages, 10948 KiB  
Article
The Role of Atmospheric Circulation Patterns in Water Storage of the World’s Largest High-Altitude Landslide-Dammed Lake
by Xuefeng Deng, Yizhen Li, Jingjing Zhang, Lingxin Kong, Jilili Abuduwaili, Majid Gulayozov, Anvar Kodirov and Long Ma
Atmosphere 2025, 16(2), 209; https://doi.org/10.3390/atmos16020209 - 12 Feb 2025
Viewed by 315
Abstract
This study reconstructed the annual lake surface area (LSA) and absolute lake water storage (LWS) changes of Lake Sarez, the world’s largest high-altitude landslide-dammed lake, from 1992 to 2023 using multi-source remote sensing data. All available Landsat images were used to extract the [...] Read more.
This study reconstructed the annual lake surface area (LSA) and absolute lake water storage (LWS) changes of Lake Sarez, the world’s largest high-altitude landslide-dammed lake, from 1992 to 2023 using multi-source remote sensing data. All available Landsat images were used to extract the LSA using an improved multi-index threshold method, which incorporates a slope mask and threshold adjustment to enhance the boundary delineation accuracy (Kappa coefficient = 0.94). By combining the LSA with high-resolution DEM and the GLOBathy bathymetry dataset, the absolute LWS was reconstructed, fluctuating between 12.3 × 109 and 12.8 × 109 m3. A water balance analysis revealed that inflow runoff (IRO) was the primary driver of LWS changes, contributing 54.57%. The cross-wavelet transform and wavelet coherence analyses showed that the precipitation (PRE) and snow water equivalent (SWE) were key climatic factors that directly influenced the variability of IRO, impacting the interannual water availability in the lake, with PRE having a more sustained impact. Temperature indirectly regulated IRO by affecting SWE and potential evapotranspiration. Furthermore, IRO exhibited different resonance periods and time lags with various atmospheric circulation factors, with the Pacific Decadal Oscillation and North Atlantic Oscillation having the most significant influence on its interannual variations. These findings provide crucial insights into the hydrological behavior of Lake Sarez under climate change and offer a novel approach for studying water storage dynamics in high-altitude landslide-dammed lakes, thereby supporting regional water resource management and ecological conservation. Full article
(This article belongs to the Section Meteorology)
Show Figures

Figure 1

Back to TopTop