Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks

Deep sleep staging networks have reached top performance on large-scale datasets. However, these models perform poorer when training and testing on small sleep cohorts due to data inefficiency. Transferring well-trained models from large-scale datasets (source domain) to small sleep cohorts (target domain) is a promising solution but still remains challenging due to the domain-shift issue. In this work, an unsupervised domain adaptation approach, domain statistics alignment (DSA), is developed to bridge the gap between the data distribution of source and target domains. DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers. Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA). The proposed methods merely need the well-trained source model without access to the source data, which may be proprietary and inaccessible. DSA and AdaDSA are universally applicable to various deep sleep staging networks that have BN layers. We have validated the proposed methods by extensive experiments on two state-of-the-art deep sleep staging networks, DeepSleepNet+ and U-time. The performance was evaluated by conducting various transfer tasks on six sleep databases, including two large-scale databases, MASS and SHHS, as the source domain, four small sleep databases as the target domain. Thereinto, clinical sleep records acquired in Huashan Hospital, Shanghai, were used. The results show that both DSA and AdaDSA could significantly improve the performance of source models on target domains, providing novel insights into the domain generalization problem in sleep staging tasks.<br>

Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks

Deep sleep staging networks have reached top performance on large-scale datasets. However, these models perform poorer when training and testing on small sleep cohorts due to data inefficiency. Transferring well-trained models from large-scale datasets (source domain) to small sleep cohorts (target domain) is a promising solution but still remains challenging due to the domain-shift issue. In this work, an unsupervised domain adaptation approach, domain statistics alignment (DSA), is developed to bridge the gap between the data distribution of source and target domains. DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers. Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA). The proposed methods merely need the well-trained source model without access to the source data, which may be proprietary and inaccessible. DSA and AdaDSA are universally applicable to various deep sleep staging networks that have BN layers. We have validated the proposed methods by extensive experiments on two state-of-the-art deep sleep staging networks, DeepSleepNet+ and U-time. The performance was evaluated by conducting various transfer tasks on six sleep databases, including two large-scale databases, MASS and SHHS, as the source domain, four small sleep databases as the target domain. Thereinto, clinical sleep records acquired in Huashan Hospital, Shanghai, were used. The results show that both DSA and AdaDSA could significantly improve the performance of source models on target domains, providing novel insights into the domain generalization problem in sleep staging tasks.<br>

Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks

Deep sleep staging networks have reached top performance on large-scale datasets. However, these models perform poorer when training and testing on small sleep cohorts due to data inefficiency. Transferring well-trained models from large-scale datasets (source domain) to small sleep cohorts (target domain) is a promising solution but still remains challenging due to the domain-shift issue. In this work, an unsupervised domain adaptation approach, domain statistics alignment (DSA), is developed to bridge the gap between the data distribution of source and target domains. DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers. Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA). The proposed methods merely need the well-trained source model without access to the source data, which may be proprietary and inaccessible. DSA and AdaDSA are universally applicable to various deep sleep staging networks that have BN layers. We have validated the proposed methods by extensive experiments on two state-of-the-art deep sleep staging networks, DeepSleepNet+ and U-time. The performance was evaluated by conducting various transfer tasks on six sleep databases, including two large-scale databases, MASS and SHHS, as the source domain, four small sleep databases as the target domain. Thereinto, clinical sleep records acquired in Huashan Hospital, Shanghai, were used. The results show that both DSA and AdaDSA could significantly improve the performance of source models on target domains, providing novel insights into the domain generalization problem in sleep staging tasks.<br>

IE-IQA: Intelligibility Enriched Generalizable No-Reference Image Quality Assessment

Image quality assessment (IQA) for authentic distortions in the wild is challenging. Though current IQA metrics have achieved decent performance for synthetic distortions, they still cannot be satisfactorily applied to realistic distortions because of the generalization problem. Improving generalization ability is an urgent task to make IQA algorithms serviceable in real-world applications, while relevant research is still rare. Fundamentally, image quality is determined by both distortion degree and intelligibility. However, current IQA metrics mostly focus on the distortion aspect and do not fully investigate the intelligibility, which is crucial for achieving robust quality estimation. Motivated by this, this paper presents a new framework for building highly generalizable image quality model by integrating the intelligibility. We first analyze the relation between intelligibility and image quality. Then we propose a bilateral network to integrate the above two aspects of image quality. During the fusion process, feature selection strategy is further devised to avoid negative transfer. The framework not only catches the conventional distortion features but also integrates intelligibility features properly, based on which a highly generalizable no-reference image quality model is achieved. Extensive experiments are conducted based on five intelligibility tasks, and the results demonstrate that the proposed approach outperforms the state-of-the-art metrics, and the intelligibility task consistently improves metric performance and generalization ability.

Mixup (Sample Pairing) Can Improve the Performance of Deep Segmentation Networks

Researchers address the generalization problem of deep image processing networks mainly through extensive use of data augmentation techniques such as random flips, rotations, and deformations. A data augmentation technique called mixup, which constructs virtual training samples from convex combinations of inputs, was recently proposed for deep classification networks. The algorithm contributed to increased performance on classification in a variety of datasets, but so far has not been evaluated for image segmentation tasks. In this paper, we tested whether the mixup algorithm can improve the generalization performance of deep segmentation networks for medical image data. We trained a standard U-net architecture to segment the prostate in 100 T2-weighted 3D magnetic resonance images from prostate cancer patients, and compared the results with and without mixup in terms of Dice similarity coefficient and mean surface distance from a reference segmentation made by an experienced radiologist. Our results suggest that mixup offers a statistically significant boost in performance compared to non-mixup training, leading to up to 1.9% increase in Dice and a 10.9% decrease in surface distance. The mixup algorithm may thus offer an important aid for medical image segmentation applications, which are typically limited by severe data scarcity.

Short-Term Wind Speed Forecasting Using Meta Learning-based Elman Neural Network

Adequate power provision to the customer and wind energy penetration into the electrical grid is necessitated for accurate wind speed forecasting in the short-term horizon to realize the scheduling, unit commitment, and control. According to the various meteorological parameters, the wind speed and energy production from wind energy are affected. Therefore, the author performs the multi-inputs associated Meta learning-based Elman Neural Network (MENN) forecasting model to overcome the uncertainty and generalization problem. The proposed forecasting approach applicability evaluated with real-time data concerning wind speed forecasting on a short-term time scale. Performance analysis reveals that the meta learning-based Elman neural network is robust and conscious than the existing methods, with a least mean square error of 0.0011.

Generative models for the transfer of knowledge in seismic interpretation with deep learning

Interpreting seismic data requires the characterization of a number of key elements such as the position of faults and main reflections, presence of structural bodies, and clustering of areas exhibiting a similar amplitude versus angle response. Manual interpretation of geophysical data is often a difficult and time-consuming task, complicated by lack of resolution and presence of noise. In recent years, approaches based on convolutional neural networks have shown remarkable results in automating certain interpretative tasks. However, these state-of-the-art systems usually need to be trained in a supervised manner, and they suffer from a generalization problem. Hence, it is highly challenging to train a model that can yield accurate results on new real data obtained with different acquisition, processing, and geology than the data used for training. In this work, we introduce a novel method that combines generative neural networks with a segmentation task in order to decrease the gap between annotated training data and uninterpreted target data. We validate our approach on two applications: the detection of diffraction events and the picking of faults. We show that when transitioning from synthetic training data to real validation data, our workflow yields superior results compared to its counterpart without the generative network.

Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification

Remote sensing technologies have been widely used in the contexts of land cover and land use. The image classification algorithms used in remote sensing are of paramount importance since the reliability of the result from remote sensing depends heavily on the classification accuracy. Parametric classifiers based on traditional statistics have successfully been used in remote sensing classification, but the accuracy is greatly impacted and rather constrained by the statistical distribution of the sensing data. To eliminate those constraints, new variants of support vector machine (SVM) are introduced. In this paper, we propose and implement land use classification based on improved SVM-enabled radial basis function (RBF) and SVM-Linear for image sensing. The proposed variants are applied for the cross-validation to determine how the optimization of parameters can affect the accuracy. The accuracy assessment includes both training and test sets, addressing the problems of overfitting and underfitting. Furthermore, it is not trivial to determine the generalization problem merely based on a training dataset. Thus, the improved SVM-RBF and SVM-Linear also demonstrate the outstanding generalization performance. The proposed SVM-RBF and SVM-Linear variants have been compared with the traditional algorithms (Maximum Likelihood Classifier (MLC) and Minimum Distance Classifier (MDC)), which are highly compatible with remote sensing images. Furthermore, the MLC and MDC are mathematically modeled and characterized with new features. Also, we compared the proposed improved SVM-RBF and SVM-Linear with the current state-of-the-art algorithms. Based on the results, it is confirmed that proposed variants have higher overall accuracy, reliability, and fault-tolerance than traditional as well as latest state-of-the-art algorithms.

KEMAMPUAN PENALARAN MATEMATIS SISWA DALAM MENYELESAIKAN SOAL PADA MATERI RELASI DAN FUNGSI KELAS VIII SMP

The aims of this study is to describe students' mathematical reasoning skills in solving problems on relationship materials and functions. Research method is used descriptive qualitative. The research subjects consisted of six students of grade VIII SMP Negeri 51 Palembang with two students with high ability, two medium students and two students with low ability. Data collection is carried out by providing 5 points about tests, interviews, and documentation. This study, using 5 indicators of reasoning, namely analysis, synthesis, generalization, problem solving is not routine, and justification / proof. The results showed that students who have high ability are mostly able to fulfill all aspects of mathematical reasoning ability. As for students who have moderate ability is able to meet two to three aspects of the students' mathematical reasoning ability only. Then for students who have low ability is only able to meet one to two aspects of the student's mathematical reasoning ability.

Distribution adaptation deep transfer learning method for cross-structure health monitoring using guided waves

Deep learning algorithm can effectively obtain damage information using labeled samples, and has become a promising feature extraction tool for ultrasonic guided wave detection. But it is difficult to apply the monitoring expertise of structure A to structure B in most cases due to the differences in the dispersion and receiving modes of different waveguides. For multi-structure monitoring at the system level, how to transfer a trained structural health monitoring model to another different structure remains a major challenge. In this article, a cross-structure ultrasonic guided wave structural health monitoring method based on distribution adaptation deep transfer learning is proposed to solve the feature generalization problem in different monitoring structures. First, the joint distribution adaptation method is employed to adapt both the marginal distribution and conditional distribution of the guided wave signals from different structures. Second, convolutional long short-term memory network is constructed to learn the mapping relationship from adapted training samples in source domain. Batch normalization layer is implemented to balance the input tensors of each sample to the same distribution. Finally, the multi-sensor damage indexes are utilized to visually present the damage by probability imaging. The experimental results show that proposed method can utilize the single-sensor monitoring data in one structure to implement the multi-sensor damage monitoring in another structure and achieve the damage imaging visualization. The imaging performance is significantly superior to the existing principal component analysis, transfer component analysis, and other state-of-art comparison methods.