Deep Feature Clustering for Seeking Patterns in Daily Harmonic Variations

This article proposes an unsupervised deep learning–based approach to detect structural damage. Supervised deep learning methods have been proposed in recent years, but they require data from an intact structure and various damage scenarios of monitored structures for their training processes. However, the labeling work on the training data is typically time-consuming and costly, and sometimes collecting sufficient training data from various damage scenarios of infrastructures in service is impractical. In this article, the proposed unsupervised deep learning method based on a deep auto-encoder with an one-class support vector machine only uses the measured acceleration response data acquired from intact or baseline structures as training data, which enables future structural damage to be detected. The major contributions and novelties of the proposed method are as follows. First, an appropriate deep auto-encoder is carefully designed through comparative studies on the depth of neural networks. Second, the designed deep auto-encoder is taken as an extractor to obtain damage-sensitive features from the measured acceleration response data, and an one-class support vector machine is used as a damage detector. Third, experimental and numerical studies validate the high accuracy of the proposed method for damage detection: a 97.4% mean average for a 12-story numerical building model and a 91.0% accuracy for a laboratory-scaled steel bridge. Fourth, the proposed method also detects light damage (i.e. a 10% reduction in stiffness) with 96.9% to 99.0% accuracy, which shows its superior performance compared with the current state of the art. Fifth, it provides stable and more robust damage detection performance with reduced tuning parameters.

Establishing accurate anatomical correspondences is critical for medical image registration. Although many hand-engineered features have been proposed for correspondence detection in various registration applications, no features are general enough to work well for all image data. Although many learning-based methods have been developed to help selection of best features for guiding correspondence detection across subjects with large anatomical variations, they are often limited by requiring the known correspondences (often presumably estimated by certain registration methods) as the ground truth for training. To address this limitation, we propose using an unsupervised deep learning approach to directly learn the basis filters that can effectively represent all observed image patches. Then, the coefficients by these learnt basis filters in representing the particular image patch can be regarded as the morphological signature for correspondence detection during image registration. Specifically, a stacked two-layer convolutional network is constructed to seek for the hierarchical representations for each image patch, where the high-level features are inferred from the responses of the low-level network. By replacing the hand-engineered features with our learnt data-adaptive features for image registration, we achieve promising registration results, which demonstrates that a general approach can be built to improve image registration by using data-adaptive features through unsupervised deep learning.

Learning feature embedding directly from images without any human supervision is a very challenging and essential task in the field of computer vision and machine learning. Following the paradigm in supervised manner, most existing unsupervised metric learning approaches mainly focus on binary similarity in Euclidean space. However, these methods cannot achieve promising performance in many practical applications, where the manual information is lacking and data exhibits non-Euclidean latent anatomy. To address this limitation, we propose an Unsupervised Hyperbolic Metric Learning method with Hierarchical Similarity. It considers the natural hierarchies of data by taking advantage of Hyperbolic metric learning and hierarchical clustering, which can effectively excavate richer similarity information beyond binary in modeling. More importantly, we design a new loss function to capture the hierarchical similarity among samples to enhance the stability of the proposed method. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current unsupervised deep metric learning approaches.

With the rapid development of various satellite sensors, automatic and advanced scene classification technique is urgently needed to process a huge amount of satellite image data. Recently, a few of research works start to implant the sparse coding for feature learning in aerial scene classification. However, these previous research works use the single-layer sparse coding in their system and their performances are highly related with multiple low-level features, such as scale-invariant feature transform (SIFT) and saliency. Motivated by the importance of feature learning through multiple layers, we propose a new unsupervised feature learning approach for scene classification on very high resolution satellite imagery. The proposed unsupervised feature learning utilizes multipath sparse coding architecture in order to capture multiple aspects of discriminative structures within complex satellite scene images. In addition, the dense low-level features are extracted from the raw satellite data by using different image patches with varying size at different layers, and this approach is not limited to a particularly designed feature descriptors compared with the other related works. The proposed technique has been evaluated on two challenging high-resolution datasets, including the UC Merced dataset containing 21 different aerial scene categories with a 1 foot resolution and the Singapore dataset containing 5 land-use categories with a 0.5m spatial resolution. Experimental results show that it outperforms the state-of-the-art that uses the single-layer sparse coding. The major contributions of this proposed technique include (1) a new unsupervised feature learning approach to generate feature representation for very high-resolution satellite imagery, (2) the first multipath sparse coding that is used for scene classification in very high-resolution satellite imagery, (3) a simple low-level feature descriptor instead of many particularly designed low-level descriptor, such as SIFT descriptors and saliency, (4) evaluation on two satellite image datasets that come from different sensor sources.

Certainly, unsupervised learning plays a critical role in the vast majority of the remote sensing (RS) applications due to the labeling costs. This research study focuses on a self-supervised representation learning approach for RS change detection (CD) based on increasing mutual information between features gathered from various views of a common context (same patch) in a non-linear way, inspired from a recently introduced unsupervised Deep Learning (DL) approach named InfoMax (DIM). The investigated model can learn image representations in unsupervised fashion that significantly produce promising results on CD. Outstandingly, using self-supervised learning, DIM model can learn representations on multispectral, hyperspectral or radar data. Our research reveals promising evidence of the significant potential utility of deep unsupervised features learning in other RS tasks.

Passive sonar target recognition is a challenging task due to the complex milieu of the ocean. Most of the state of the art target recognition systems depend on hand engineered feature extraction schemes in order to effectively represent the target signatures, based on expert knowledge. Due to the whimsical nature of the sources and medium, such feature engineering methods often fail to yield invariant features from the observations. In this paper, a deep unsupervised feature learning approach capable of capturing invariant features from the sensory signal stream through multi layered hierarchical abstraction has been adopted. These abstractions learned by the higher layers are mostly invariant and can be used as the discriminative features for the purpose of classification.

BackgroundWith the advent of new media, more people – possibly including caregivers of persons with dementia – are turning to social media platforms to share their thoughts and emotions related to personal life experiences. This may potentially serve as an opportunity to leverage on social media to gain insights into the key issues faced by dementia caregivers. We examined salient concerns of dementia caregivers through Twitter posts, aiming to shed light on how to better support and engage such caregivers.MethodEnglish tweets related to “dementia” and “caregiver” (or related terms such as “Alzheimer’s disease” and “carer”) were extracted between 1st January 2013 and 31st December 2022. A supervised deep learning model (Bidirectional Encoder Representations from Transformers, BERT) was trained to select tweets describing individual’s accounts related to dementia caregiving. Then, an unsupervised deep learning approach (BERT‐based topic modelling) was applied to identify topics from selected tweets, with each topic further grouped into themes manually using thematic analysis.ResultA total of 44,527 tweets were analysed, and stratified using the emergence of COVID‐19 pandemic as a threshold. Three themes were derived: challenges of caregiving in dementia, positive aspects related to dementia caregiving, and dementia‐related stigmatization. Over time, there is a rising trend of tweets relating to dementia caregiving. Post‐pandemic, challenges of caregiving remained the top discussed topic; followed by an increase in tweets related to dementia‐related stigmatization; and a decrease in tweets related to positive aspects of caregiving (p‐value<.001).ConclusionSocial media is increasingly being used by dementia caregivers to share their thoughts. The findings uncover the worrying trend of growing dementia‐related stigmatization among the caregivers, and its manifestation in the form of devaluing others. The persistence of these issues post‐pandemic underscores the need for caregiver’s support and resources.

SUMMARYThe converted wave data (P-to-s or S-to-p), traditionally termed as receiver functions, are often contaminated with noise of different origin that may lead to the erroneous identification of phases and thus influence the interpretations. Here, we utilize an unsupervised deep learning approach called Patchunet to de-noise the converted wave data. We divide the input data into several patches, which are input to the encoder and decoder network to extract some meaningful features. The method de-noises an image patch by patch and utilizes the redundant information on similar patches to obtain the final de-noised results. The method is first tested on a suite of synthetic data contaminated with various amounts of Gaussian and realistic noise and then on the observed data from three permanent seismic stations: HYB (Hyderabad, India), LBTB (Lobatse, Botswana, South Africa) and COR (Corvallis, Oregon, USA). The method works very well even when the signal-to-noise ratio is poor or with the presence of spike noise and deconvolution artifacts. The field data demonstrate the effectiveness of the method for attenuating the random noise especially for the mantle phases, which show significant improvements over conventional receiver function based images.

Binary descriptors have been widely used for efficient image matching and retrieval. However, most existing binary descriptors are designed with hand-craft sampling patterns or learned with label annotation provided by datasets. In this paper, we propose a new unsupervised deep learning approach, called DeepBit, to learn compact binary descriptor for efficient visual object matching. We enforce three criteria on binary descriptors which are learned at the top layer of the deep neural network: 1) minimal quantization loss, 2) evenly distributed codes and 3) transformation invariant bit. Then, we estimate the parameters of the network through the optimization of the proposed objectives with a back-propagation technique. Extensive experimental results on various visual recognition tasks demonstrate the effectiveness of the proposed approach. We further demonstrate our proposed approach can be realized on the simplified deep neural network, and enables efficient image matching and retrieval speed with very competitive accuracies.

Recognizing Human action in video is an very active research topic. There are a growing variety of human action datasets with different video length, different practitioners. Make human action recognition becomes a very difficult topic. A majority researchers solve the problem by extracting key frames from the videos. Most paper use feature Clustering methods to extract key frames in videos. On one hand, the large variety of visual content in videos make handcraft feature isn't effective enough, since there are no fixed descriptors can describe all video cases. On the other hand, traditional clustering algorithms are easily influenced by the choice of initial clustering centers. An Unsupervised feature learning and clustering method for key frame extraction is proposed in this paper, which can be used for human action recognition. Stacked auto-encoder(SAE) is trained using videos from 10 different human actions, SAE is used as a feature extractor to learn features representing human actions. Affinity Propagation Clustering algorithm is used to select key frames from video sequences. We use a variety of videos to do the experiments. Experiments demonstrate that our method can be effectively summarizing video shots considering different human actions.

A novel unsupervised deep learning approach for vibration-based damage diagnosis using a multi-head self-attention LSTM autoencoder

Efficient modeling of high-dimensional data requires extracting only relevant dimensions through feature learning. Unsupervised feature learning has gained tremendous attention due to its unbiased approach, no need for prior knowledge or expensive manual processing, and ability to handle exponential data growth. Deep Autoencoder (AE) is a state-of-the-art deep neural network for unsupervised feature learning, which learns embedded-representations using a series of stacked layers. However, as the AE network gets deeper, these learned embedded-representations can deteriorate due to vanishing gradient, leading to performance degradation. This article presents ResNet Autoencoder (RAE) and its convolutional version (C-RAE) for unsupervised feature learning. The advantage of RAE and C-RAE is that it enables the user to add residual connections for increased network capacity without incurring the cost of degradation for unsupervised feature learning compared to standard AEs. While RAE and C-RAE inherit all the advantages of AEs, such as automated non-linear feature extraction and unsupervised learning, they also allow users to design larger networks without adverse effects on feature learning performance. We performed classification on learned embedded-representation to evaluate RAE and C-RAE. RAE and C-RAE were compared against AEs on MNIST, Fashion MNIST, and CIFAR10 datasets. When increasing the number of layers, C-RAE outperformed AE by showing significantly lower performance degradation of classification accuracy (less than 3%) compared to AE (33% to 65%). Further, C-RAE exhibited higher mean accuracy and lower variance of accuracy than standard AE. When comparing RAE and C-RAE with widely used feature learning methods (Convolutional AE, PCA, ICA, LLE, Factor Analysis, and SVD), C-RAE showed the highest accuracy.

In unsupervised learning of image features without labels, especially on datasets with fine-grained object classes, it is often very difficult to tell if a given image belongs to one specific object class or another, even for human eyes. However, we can reliably tell if image C is more similar to image A than image B. In this work, we propose to explore how this relative order can be used to learn discriminative features with an unsupervised metric learning method. Instead of resorting to clustering or self-supervision to create pseudo labels for an absolute decision, which often suffers from high label error rates, we construct reliable relative orders for groups of image samples and learn a deep neural network to predict these relative orders. During training, this relative order prediction network and the feature embedding network are tightly coupled, providing mutual constraints to each other to improve overall metric learning performance in a cooperative manner. During testing, the predicted relative orders are used as constraints to optimize the generated features and refine their feature distance-based image retrieval results using a constrained optimization procedure. Our experimental results demonstrate that the proposed relative orders for unsupervised learning (ROUL) method is able to significantly improve the performance ofunsupervised deep metric learning.

Anomaly Detection in Hobbing Tool Images: Using An Unsupervised Deep Learning Approach in Manufacturing Industry

Unsupervised deep learning and semi-automatic data labeling in weed discrimination