Search Results (11)

A decision-level multimodal fusion deep learning strategy is proposed for the effective fault detection of rolling bearings based on long-term fault signals collected from multiple sensors. First, key features are extracted from the multimodal signal set using singular spectrum analysis (SSA), and these features are transformed into a composite dataset that combines short-time Fourier transform (STFT) images and time series data. Based on this, a recursive gated convolutional neural network (RGCNN) is designed to process the STFT image data, while a 1D convolutional neural network (1DCNN) is specifically optimized for training with time series data. Furthermore, decision-level multimodal feature fusion is achieved by applying a weighted average method to integrate the features from different deep learning models, aiming to obtain more comprehensive fault prediction results. The proposed method, multimodal fusion fault detection (MFFD), is validated on the Paderborn and Ottawa rolling bearing datasets, which include various typical faults. Experimental results demonstrate the effectiveness of the proposed approach. Compared to traditional single-modality deep learning models, the proposed method shows significant improvements in fault diagnosis accuracy and generalization capability. Full article

In order to improve the efficiency of the deep network model in processing the radiated noise signals of underwater acoustic targets, this paper introduces a Singular Spectrum Analysis and Channel Attention Convolutional Neural Network (SSA-CACNN) model. The front end of the model is designed as an SSA filter, and its input is the time-domain signal that has undergone simple preprocessing. The SSA method is utilized to separate the noise efficiently and reliably from useful signals. The first three orders of useful signals are then fed into the CACNN model, which has a convolutional layer set up at the beginning of the model to further remove noise from the signal. Then, the attention of the model to the feature signal channels is enhanced through the combination of multiple groups of convolutional operations and the channel attention mechanism, which facilitates the model’s ability to discern the essential characteristics of the underwater acoustic signals and improve the target recognition rate. Experimental Results: The signal reconstructed by the first three-order waveforms at the front end of the SSA-CACNN model proposed in this paper can retain most of the features of the target. In the experimental verification using the ShipsEar dataset, the model achieved a recognition accuracy of 98.64%. The model’s parameter count of 0.26 M was notably lower than that of other comparable deep models, indicating a more efficient use of resources. Additionally, the SSA-CACNN model had a certain degree of robustness to noise, with a correct recognition rate of 84.61% maintained when the signal-to-noise ratio (SNR) was −10 dB. Finally, the pre-trained SSA-CACNN model on the ShipsEar dataset was transferred to the DeepShip dataset with a recognition accuracy of 94.98%. Full article

Monitoring heart rate (HR) is vital for health management and athletic performance, and wearable technology enables scientists to obtain real-time cardiovascular insights. This study compares Machine Learning (ML) techniques, including Long Short-Term Memory (LSTM) networks, Physics-Informed Neural Networks (PINNs), and 1D Convolutional Neural Networks (1D CNNs). Then, we develop a hybrid Singular Spectrum Analysis (SSA)-Augmented ML technique to predict HR using wearable sensor data. Additionally, we investigate the impact of incorporating auxiliary physiological inputs, such as breathing rate (BR) and RR intervals, on predictive accuracy. The study utilizes the cardiorespiratory data acquired through wearable sensors while practising sports, including 126 recordings from 81 participants (53 males, 28 females) engaged in 10 different sports. Physiological signals were collected at 1 Hz using the BioHarness 3.0 (Zephyr Technology, Mangaluru, India). The dataset includes individuals with varied levels of sports experience (beginner, intermediate, and advanced), allowing for a more comprehensive evaluation of HR variability across different expertise levels. Our results demonstrate that the hybrid SSA-LSTM model reaches the lowest prediction error by effectively capturing HR dynamics. Furthermore, integrating HR, BR, and RR data significantly enhances accuracy over single or dual parameter inputs. These findings support adopting multivariate machine learning models for health monitoring, improving HR prediction accuracy for fitness and preventive healthcare. Full article

As an emerging research hotspot in contemporary remote sensing, hyperspectral change detection (HCD) has attracted increasing attention in remote sensing Earth observation, covering land mapping changes and anomaly detection. This is primarily attributable to the unique capacity of hyperspectral imagery (HSI) to amalgamate both the spectral and spatial information in the scene, facilitating a more exhaustive analysis and change detection on the Earth’s surface, proving to be successful across diverse domains, such as disaster monitoring and geological surveys. Although numerous HCD algorithms have been developed, most of them face three major challenges: (i) susceptibility to inherent data noise, (ii) inconsistent accuracy of detection, especially when dealing with multi-scale changes, and (iii) extensive hyperparameters and high computational costs. As such, we propose a singular spectrum analysis-driven-lightweight network for HCD, where three crucial components are incorporated to tackle these challenges. Firstly, singular spectrum analysis (SSA) is applied to alleviate the effect of noise. Next, a 2-D self-attention-based spatial–spectral feature-extraction module is employed to effectively handle multi-scale changes. Finally, a residual block-based module is designed to effectively extract the spectral features for efficiency. Comprehensive experiments on three publicly available datasets have fully validated the superiority of the proposed SSA-LHCD model over eight state-of-the-art HCD approaches, including four deep learning models. Full article

In this study, data collected from 2000 to 2019 on vapor pressure deficit ($VPD$) and its relationship with micrometeorological variables (fire occurrences, aerosol concentration, temperature, and carbon flux) were analyzed in six locations situated in different Brazilian ecosystems: Rio Branco, AC; Manaus, AM; Alta Floresta, MT (within the Amazon Rainforest); Baia das Pedras, MT (Pantanal); Fazenda Miranda, MT (Cerrado); and Petrolina, PE (northeastern semiarid region). Temporal series analysis of $VPD$ was conducted by determining the principal component of singular spectrum analysis (SSA) for this variable in all locations. It was observed that the main component of SSA for $VPD$ is sensitive to local land-use changes, while no evidence of large-scale influences related to global climate change was observed. A strong coupling between $VPD$ values and local maximum temperature with monthly fire occurrence and logarithmic aerosol concentration profiles was also observed. The results of the study are discussed in the context of the ecosystems’ carbon sequestration capacity. The combined results of the study indicate a scenario in which local land-use changes can compromise the capacity of Brazilian ecosystems to absorb carbon. Full article

Recently, the rapid development of deep learning has greatly improved the performance of image classification. However, a central problem in hyperspectral image (HSI) classification is spectral uncertainty, where spectral features alone cannot accurately and robustly identify a pixel point in a hyperspectral image. This paper presents a novel HSI classification network called MS-RPNet, i.e., multiscale superpixelwise RPNet, which combines superpixel-based S³-PCA with two-dimensional singular spectrum analysis (2D-SSA) based on the Random Patches Network (RPNet). The proposed frame can not only take advantage of the data-driven method, but can also apply S³-PCA to efficiently consider more global and local spectral knowledge at the super-pixel level. Meanwhile, 2D-SSA is used for noise removal and spatial feature extraction. Then, the final features are obtained by random patch convolution and other steps according to the cascade structure of RPNet. The layered extraction superimposes the different sparial information into multi-scale spatial features, which complements the features of various land covers. Finally, the final fusion features are classified by SVM to obtain the final classification results. The experimental results in several HSI datasets demonstrate the effectiveness and efficiency of MS-RPNet, which outperforms several current state-of-the-art methods. Full article

The grounded electrical source airborne transient electromagnetic (GREATEM) system is widely used in groundwater resources detection, geothermal resource detection, geological structure detection, and other fields due to its wide detection range, high detection efficiency, and high resolution. The field data received by the GREATEM system is easily affected by various noises, such as instrument system noise, power frequency noise, sferics noise, and other noise, which reduce the data signal-to-noise ratio (SNR) and affects the data interpretation accuracy. This paper proposes a singular spectrum analysis (SSA) for the GREATEM data de-noising in response to this problem. First, we calculate the electromagnetic response of a uniform half-space using a GREATEM system with an electrical source to verify the effectiveness of the SSA algorithm for GREATEM data de-noising. To determine the appropriate parameters for SSA, we propose a particle swarm optimization algorithm to choose the window length. Later, SSA is used to decompose a synthetic quasi-two-dimensional earth model of GREATEM data. After SSA, the SNR of the reconstructed signal increased by 36 dB, and the RMSE does not exceed 4.9 × 10⁻⁶, which verifies the feasibility of the SSA for de-noising GREATEM data. Finally, through field measurement data processing, the effectiveness of the method is further confirmed. Full article

In the processing of remotely sensed data, classification may be preceded by feature extraction, which helps in making the most informative parts of the data emerge. Effective feature extraction may boost the efficiency and accuracy of the following classification, and hence various methods have been proposed to perform it. Recently, Singular Spectrum Analysis (SSA) and its 2-D variation (2D-SSA) have emerged as popular, cutting-edge technologies for effective feature extraction in Hyperspectral Images (HSI). Using 2D-SSA, each band image of an HSI is initially decomposed into various components, and then the image is reconstructed using the most significant eigen-tuples relative to their eigen-values, which represent strong spatial features for the classification task. However, instead of performing reconstruction on the whole image, it may be more effective to apply reconstruction to object-specific spatial regions, which is the proposed objective of this research. As an HSI may cover a large area, multiple objects are generally present within a single scene. Hence, spatial information can be highlighted accurately by specializing the reconstruction based on the local context. The local context may be defined by the so-called superpixels, i.e., finite sets of pixels that constitute a homogeneous set. Each superpixel may undergo tailored reconstruction, with a process expected to perform better than non-spatially-adaptive approaches. In this paper, a Superpixel-based SSA (SP-SSA) method is proposed where the image is first segmented into multiple regions using a superpixel segmentation approach. Next, each segment is individually reconstructed using 2D-SSA. In doing so, the spatial contextual information is preserved, leading to better classifier performance. The performance of the reconstructed features is evaluated using an SVM classifier. Experiments on four popular benchmark datasets reveal that, in terms of the classification accuracy, the proposed approach overperforms the standard SSA technique and various common spatio-spectral classification methods. Full article

Multimodal biometrics technology has recently gained interest due to its capacity to overcome certain inherent limitations of the single biometric modalities and to improve the overall recognition rate. A common biometric recognition system consists of sensing, feature extraction, and matching modules. The robustness of the system depends much more on the reliability to extract relevant information from the single biometric traits. This paper proposes a new feature extraction technique for a multimodal biometric system using face–iris traits. The iris feature extraction is carried out using an efficient multi-resolution 2D Log-Gabor filter to capture textural information in different scales and orientations. On the other hand, the facial features are computed using the powerful method of singular spectrum analysis (SSA) in conjunction with the wavelet transform. SSA aims at expanding signals or images into interpretable and physically meaningful components. In this study, SSA is applied and combined with the normal inverse Gaussian (NIG) statistical features derived from wavelet transform. The fusion process of relevant features from the two modalities are combined at a hybrid fusion level. The evaluation process is performed on a chimeric database and consists of Olivetti research laboratory (ORL) and face recognition technology (FERET) for face and Chinese academy of science institute of automation (CASIA) v3.0 iris image database (CASIA V3) interval for iris. Experimental results show the robustness. Full article

Drawing a distinction between the suspended solid size and concentration impacts on physical clogging process in the Managed Aquifer Recharge (MAR) systems has been fraught with difficulties. Therefore, the current study was then aimed to statistically investigate and differentiate the impacts of clay-, silt- and sand-sized suspended solids at three concentration levels including 2, 5 and 10 g/L, compared with the clean water (0 g/L), on infiltration rate reducibility. The treatments were compared by virtue of Cohen’s d effect size measure. Furthermore, the competency of Singular Spectrum Analysis (SSA) was evaluated in reconstruction of infiltration rate. Results showed that clay-sized suspended solids were found to be the most important determining factor in physical clogging occurrence. The effect size measure highlighted that a lower concentration level of clay-sized suspended solids, that is, 2 g/L could be more important in trigging the physical clogging than a higher concentration level of silt-sized suspended solids namely 5 g/L. Also, we recognized that concentration level of clay-sized suspended sediments could non-linearly decrease the infiltrability. Also, findings revealed that SSA represented a high level of competency in reconstruction of the infiltration rate under all treatments. Hence, SSA can be quite beneficial to MAR systems for forecasting applications. Full article

Different from microwave radar, laser radar could be more sensitive to the micro-Doppler (m-D) effect due to its wave length. This limits the application of conventional methods, such as time–frequency based approach, since the processing needs a receiver with much higher sampling frequency than microwave radar. In this paper, a micro-Doppler feature extraction algorithm is proposed for the inverse synthetic aperture imaging laser radar (ISAIL). Singular-spectrum analysis (SSA) is employed for separation and reconstruction of the micro-Doppler and rigid body signal. Clear ISAIL image is obtained by minimum entropy criteria after echo signal decomposition. After theoretical derivation, the computation efficiency and ability of the proposed method is proved by the results of simulation and real data of An-26. Full article