RESUMEN

Many new reconstruction techniques have been deployed to allow low-dose CT examinations. Such reconstruction techniques exhibit nonlinear properties, which strengthen the need for a task-based measure of image quality. The Hotelling observer (HO) is the optimal linear observer and provides a lower bound of the Bayesian ideal observer detection performance. However, its computational complexity impedes its widespread practical usage. To address this issue, we proposed a self-supervised learning (SSL)-based model observer to provide accurate estimates of HO performance in very low-dose chest CT images. Our approach involved a two-stage model combining a convolutional denoising auto-encoder (CDAE) for feature extraction and dimensionality reduction and a support vector machine for classification. To evaluate this approach, we conducted signal detection tasks employing chest CT images with different noise structures generated by computer-based simulations. We compared this approach with two supervised learning-based methods: a single-layer neural network (SLNN) and a convolutional neural network (CNN). The results showed that the CDAE-based model was able to achieve similar detection performance to the HO. In addition, it outperformed both SLNN and CNN when a reduced number of training images was considered. The proposed approach holds promise for optimizing low-dose CT protocols across scanner platforms.

RESUMEN

Rice grains are often infected by Sitophilus oryzae due to improper storage, resulting in quality and quantity losses. The efficacy of terahertz time-domain spectroscopy (THz-TDS) technology in detecting Sitophilus oryzae at different stages of infestation in stored rice was employed in the current research. Terahertz (THz) spectra for rice grains infested by Sitophilus oryzae at different growth stages were acquired. Then, the convolutional denoising autoencoder (CDAE) was used to reconstruct THz spectra to reduce the noise-to-signal ratio. Finally, a random forest classification (RFC) model was developed to identify the infestation levels. Results showed that the RFC model based on the reconstructed second-order derivative spectrum with an accuracy of 84.78%, a specificity of 86.75%, a sensitivity of 86.36% and an F1-score of 85.87% performed better than the original first-order derivative THz spectrum with an accuracy of 89.13%, a specificity of 91.38%, a sensitivity of 88.18% and an F1-score of 89.16%. In addition, the convolutional layers inside the CDAE were visualized using feature maps to explain the improvement in results, illustrating that the CDAE can eliminate noise in the spectral data. Overall, THz spectra reconstructed with the CDAE provided a novel method for effective THz detection of infected grains.

Asunto(s)

RESUMEN

BACKGROUND: The denoising autoencoder (DAE) is commonly used to denoise bio-signals such as electrocardiogram (ECG) signals through dimensional reduction. Typically, the DAE model needs to be trained using correlated input segments such as QRS-aligned segments or long ECG segments. However, using long ECG segments as an input can result in a complex deep DAE model that requires many hidden layers to achieve a low-dimensional representation, which is a major drawback. METHODS: This work proposes a novel DAE model, called running DAE (RunDAE), for denoising short ECG segments without relying on the R-peak detection algorithm for alignment. The proposed RunDAE model employs a sample-by-sample processing approach, considering the correlation between consecutive, overlapped ECG segments. The performance of both the classical DAE and RunDAE models with convolutional and dense layers, respectively, is evaluated using corrupted QRS-aligned and non-aligned ECG segments with physical noise such as motion artifacts, electrode movement, baseline wander, and simulated noise such as Gaussian white noise. RESULTS: The simulation results indicate that 1. QRS-aligned segments are preferable to non-aligned segments, 2. the RunDAE model outperforms the classical DAE model in denoising ECG signals, especially when using dense layers and QRS-aligned segments, 3. training the RunDAE models with normal and arrhythmic ECG signals enhance model's properties/capabilities, and 4. the RunDAE is a multistage, non-causal, nonlinear adaptive filter. CONCLUSION: A shallow learning model, which consists of a couple of hidden layers, could achieve outstanding denoising performance using only the correlation among neighboring samples.

RESUMEN

Errors in microelectromechanical systems (MEMS) inertial measurement units (IMUs) are large, complex, nonlinear, and time varying. The traditional noise reduction and compensation methods based on traditional models are not applicable. This paper proposes a noise reduction method based on multi-layer combined deep learning for the MEMS gyroscope in the static base state. In this method, the combined model of MEMS gyroscope is constructed by Convolutional Denoising Auto-Encoder (Conv-DAE) and Multi-layer Temporal Convolutional Neural with the Attention Mechanism (MultiTCN-Attention) model. Based on the robust data processing capability of deep learning, the noise features are obtained from the past gyroscope data, and the parameter optimization of the Kalman filter (KF) by the Particle Swarm Optimization algorithm (PSO) significantly improves the filtering and noise reduction accuracy. The experimental results show that, compared with the original data, the noise standard deviation of the filtering effect of the combined model proposed in this paper decreases by 77.81% and 76.44% on the x and y axes, respectively; compared with the existing MEMS gyroscope noise compensation method based on the Autoregressive Moving Average with Kalman filter (ARMA-KF) model, the noise standard deviation of the filtering effect of the combined model proposed in this paper decreases by 44.00% and 46.66% on the x and y axes, respectively, reducing the noise impact by nearly three times.

RESUMEN

WiFi is widely used for indoor positioning because of its advantages such as long transmission distance and ease of use indoors. To improve the accuracy and robustness of indoor WiFi fingerprint localization technology, this paper proposes a positioning system CCPos (CADE-CNN Positioning), which is based on a convolutional denoising autoencoder (CDAE) and a convolutional neural network (CNN). In the offline stage, this system applies the K-means algorithm to extract the validation set from the all-training set. In the online stage, the RSSI is first denoised and key features are extracted by the CDAE. Then the location estimation is output by the CNN. In this paper, the Alcala Tutorial 2017 dataset and UJIIndoorLoc are adopted to verify the performance of the CCpos system. The experimental results show that our system has excellent noise immunity and generalization performance. The mean positioning errors on the Alcala Tutorial 2017 dataset and the UJIIndoorLoc are 1.05 m and 12.4 m, respectively.

RESUMEN

Intelligent fault diagnosis algorithm for rolling bearings has received increasing attention. However, in actual industrial environments, most rolling bearings work under severe working conditions of variable speed and strong noise, which makes the performance of many intelligent fault diagnosis methods deteriorate sharply. In this regard, this paper proposes a new intelligent diagnosis algorithm for rolling bearing faults based on a residual dilated pyramid network and full convolutional denoising autoencoder (RDPN-FCDAE). First, a continuous wavelet transform (CWT) is used to convert original vibration signals into time-frequency images. Secondly, a deep two-stage RDPN-FCDAE model is constructed, which is divided into three parts: encoding network, decoding network and classification network. In order to obtain efficient expression of data denoising feature of encoding network, time-frequency images are first input into the encoding-decoding network for unsupervised pre-training. Then pre-trained coding network and classification network are combined into residual dilated pyramid full convolutional network (RDPFCN) for parameter fine-tuning and testing. The proposed method is applied to bearing vibration datasets of test rig with different speeds and noise modes. Compared with representative machine learning and deep learning method, the results show that the algorithm proposed is superior to other methods in diagnostic accuracy, noise robustness and feature segmentation ability.

RESUMEN

Fabric defect detection is a necessary and essential step of quality control in the textile manufacturing industry. Traditional fabric inspections are usually performed by manual visual methods, which are low in efficiency and poor in precision for long-term industrial applications. In this paper, we propose an unsupervised learning-based automated approach to detect and localize fabric defects without any manual intervention. This approach is used to reconstruct image patches with a convolutional denoising autoencoder network at multiple Gaussian pyramid levels and to synthesize detection results from the corresponding resolution channels. The reconstruction residual of each image patch is used as the indicator for direct pixel-wise prediction. By segmenting and synthesizing the reconstruction residual map at each resolution level, the final inspection result can be generated. This newly developed method has several prominent advantages for fabric defect detection. First, it can be trained with only a small amount of defect-free samples. This is especially important for situations in which collecting large amounts of defective samples is difficult and impracticable. Second, owing to the multi-modal integration strategy, it is relatively more robust and accurate compared to general inspection methods (the results at each resolution level can be viewed as a modality). Third, according to our results, it can address multiple types of textile fabrics, from simple to more complex. Experimental results demonstrate that the proposed model is robust and yields good overall performance with high precision and acceptable recall rates.