Similarity search based on a distance function in metric spaces is a fundamental problem for many applications. Queries for similar objects lead to the well-known machine learning task of nearest-neighbours identification. Many data indexing strategies, collectively known as Metric Access Methods (MAM), have been proposed to speed up queries for similar elements in this context. Moreover, since exact approaches to solve similarity queries can be complex and time-consuming, alternative options have appeared to reduce query execution time, such as returning approximate results or resorting to distributed computing platforms. In this paper, we introduce MASK (Multilevel Approximate Similarity search with $k$-means), an unconventional application of the $k$-means algorithm as the foundation of a multilevel index structure for approximate similarity search, suitable for metric spaces. We show that inherent properties of $k$-means, like representing high-density data areas with fewer prototypes, can be leveraged for this purpose. An implementation of this new indexing method is evaluated, using a synthetic dataset and a real-world dataset in a high-dimensional and high-sparsity space. Results are promising and underpin the applicability of this novel indexing method in multiple domains.
In this paper, we propose a sampling algorithm based on statistical machine learning to obtain conditional nonlinear optimal perturbation (CNOP), which is essentially different from the traditional deterministic optimization methods. The new approach does not only reduce the extremely expensive gradient (first-order) information directly by the objective value (zeroth-order) information, but also avoid the use of adjoint technique that gives rise to the huge storage problem and the instability from linearization. Meanwhile, an intuitive anlysis and a rigorous concentration inequality for the approximate gradient by sampling are shown. The numerical experiments to obtain the CNOPs by the performance of standard spatial sturctures for a theoretical model, Burgers equation with small viscosity, demonstrate that at the cost of losing accuracy, fewer samples spend time relatively shorter than the adjoint-based method and directly from definition. Finally, we reveal that the nonlinear time evolution of the CNOPs obtained by all the algorithms are almost consistent with the quantity of norm square of perturbations, their difference and relative difference on the basis of the definition method.
In this paper, a novel amplitude-modulated continuous wave (AMCW) time-of-flight (ToF) scanning sensor based on digital-parallel demodulation is proposed and demonstrated in the aspect of distance measurement precision. Since digital-parallel demodulation utilizes a high-amplitude demodulation signal with zero-offset, the proposed sensor platform can maintain extremely high demodulation contrast. Meanwhile, as all cross correlated samples are calculated in parallel and in extremely short integration time, the proposed sensor platform can utilize a 2D laser scanning structure with a single photo detector, maintaining a moderate frame rate. This optical structure can increase the received optical SNR and remove the crosstalk of image pixel array. Based on these measurement properties, the proposed AMCW ToF scanning sensor shows highly precise 3D depth measurement performance. In this study, this precise measurement performance is explained in detail. Additionally, the actual measurement performance of the proposed sensor platform is experimentally validated under various conditions.
The probability of a drought for a particular region is crucial when making decisions related to agriculture. Forecasting this probability is critical for management and challenging at the same time. The prediction model should consider multiple factors with complex relationships across the region of interest and neighbouring regions. We approach this problem by presenting an end-to-end solution based on a spatio-temporal neural network. The model predicts the Palmer Drought Severity Index (PDSI) for subregions of interest. Predictions by climate models provide an additional source of knowledge of the model leading to more accurate drought predictions. Our model has better accuracy than baseline Gradient boosting solutions, as the $R^2$ score for it is $0.90$ compared to $0.85$ for Gradient boosting. Specific attention is on the range of applicability of the model. We examine various regions across the globe to validate them under different conditions. We complement the results with an analysis of how future climate changes for different scenarios affect the PDSI and how our model can help to make better decisions and more sustainable economics.
Breathing disorders such as sleep apnea is a critical disorder that affects a large number of individuals due to the insufficient capacity of the lungs to contain/exchange oxygen and carbon dioxide to ensure that the body is in the stable state of homeostasis. Respiratory Measurements such as minute ventilation can be used in correlation with other physiological measurements such as heart rate and heart rate variability for remote monitoring of health and detecting symptoms of such breathing related disorders. In this work, we formulate a deep learning based approach to measure remote ventilation on a private dataset. The dataset will be made public upon acceptance of this work. We use two versions of a deep neural network to estimate the minute ventilation from data streams obtained through wearable heart rate and respiratory devices. We demonstrate that the simple design of our pipeline - which includes lightweight deep neural networks - can be easily incorporate into real time health monitoring systems.
Wearable sensor-based Human Action Recognition (HAR) has achieved remarkable success recently. However, the accuracy performance of wearable sensor-based HAR is still far behind the ones from the visual modalities-based system (i.e., RGB video, skeleton, and depth). Diverse input modalities can provide complementary cues and thus improve the accuracy performance of HAR, but how to take advantage of multi-modal data on wearable sensor-based HAR has rarely been explored. Currently, wearable devices, i.e., smartwatches, can only capture limited kinds of non-visual modality data. This hinders the multi-modal HAR association as it is unable to simultaneously use both visual and non-visual modality data. Another major challenge lies in how to efficiently utilize multimodal data on wearable devices with their limited computation resources. In this work, we propose a novel Progressive Skeleton-to-sensor Knowledge Distillation (PSKD) model which utilizes only time-series data, i.e., accelerometer data, from a smartwatch for solving the wearable sensor-based HAR problem. Specifically, we construct multiple teacher models using data from both teacher (human skeleton sequence) and student (time-series accelerometer data) modalities. In addition, we propose an effective progressive learning scheme to eliminate the performance gap between teacher and student models. We also designed a novel loss function called Adaptive-Confidence Semantic (ACS), to allow the student model to adaptively select either one of the teacher models or the ground-truth label it needs to mimic. To demonstrate the effectiveness of our proposed PSKD method, we conduct extensive experiments on Berkeley-MHAD, UTD-MHAD, and MMAct datasets. The results confirm that the proposed PSKD method has competitive performance compared to the previous mono sensor-based HAR methods.
Recently, deep learning methods have been successfully applied to solve numerous challenges in the field of digital pathology. However, many of these approaches are fully supervised and require annotated images. Annotating a histology image is a time-consuming and tedious process for even a highly skilled pathologist, and, as such, most histology datasets lack region-of-interest annotations and are weakly labeled. In this paper, we introduce HistoPerm, a view generation approach designed for improving the performance of representation learning techniques on histology images in weakly supervised settings. In HistoPerm, we permute augmented views of patches generated from whole-slide histology images to improve classification accuracy. These permuted views belong to the same original slide-level class but are produced from distinct patch instances. We tested adding HistoPerm to BYOL and SimCLR, two prominent representation learning methods, on two public histology datasets for Celiac disease and Renal Cell Carcinoma. For both datasets, we found improved performance in terms of accuracy, F1-score, and AUC compared to the standard BYOL and SimCLR approaches. Particularly, in a linear evaluation configuration, HistoPerm increases classification accuracy on the Celiac disease dataset by 8% for BYOL and 3% for SimCLR. Similarly, with HistoPerm, classification accuracy increases by 2% for BYOL and 0.25% for SimCLR on the Renal Cell Carcinoma dataset. The proposed permutation-based view generation approach can be adopted in common representation learning frameworks to capture histopathology features in weakly supervised settings and can lead to whole-slide classification outcomes that are close to, or even better than, fully supervised methods.
Detecting relevant changes in dynamic time series data in a timely manner is crucially important for many data analysis tasks in real-world settings. Change point detection methods have the ability to discover changes in an unsupervised fashion, which represents a desirable property in the analysis of unbounded and unlabeled data streams. However, one limitation of most of the existing approaches is represented by their limited ability to handle multivariate and high-dimensional data, which is frequently observed in modern applications such as traffic flow prediction, human activity recognition, and smart grids monitoring. In this paper, we attempt to fill this gap by proposing WATCH, a novel Wasserstein distance-based change point detection approach that models an initial distribution and monitors its behavior while processing new data points, providing accurate and robust detection of change points in dynamic high-dimensional data. An extensive experimental evaluation involving a large number of benchmark datasets shows that WATCH is capable of accurately identifying change points and outperforming state-of-the-art methods.
Nuclear fusion power created by tokamak devices holds one of the most promising ways as a sustainable source of clean energy. One main challenge research field of tokamak is to predict the last closed magnetic flux surface (LCFS) determined by the interaction of the actuator coils and the internal tokamak plasma. This work requires high-dimensional, high-frequency, high-fidelity, real-time tools, further complicated by the wide range of actuator coils input interact with internal tokamak plasma states. In this work, we present a new machine learning model for reconstructing the LCFS from the Experimental Advanced Superconducting Tokamak (EAST) that learns automatically from the experimental data of EAST. This architecture can check the control strategy design and integrate it with the tokamak control system for real-time magnetic prediction. In the real-time modeling test, our approach achieves over 99% average similarity in LCFS reconstruction of the entire discharge process. In the offline magnetic reconstruction, our approach reaches over 93% average similarity.
Image-based computational fluid dynamics have long played an important role in leveraging knowledge and understanding of several physical phenomena. In particular, probabilistic computational methods have opened the way to modelling the complex dynamics of systems in purely random turbulent motion. In the field of structural geology, a better understanding of the deformation and stress state both within the salt and the surrounding rocks is of great interest to characterize all kinds of subsurface long-terms energy-storage systems. The objective of this research is to determine the non-linear deformation of the salt boundary over time using a parallelized, stochastic filtering approach from x-ray computed tomography (CT) image time series depicting the evolution of salt structures triggered by gravity and under differential loading. This work represents a first step towards bringing together physical modeling and advanced stochastic image processing methods where model uncertainty is taken into account.