Time Series Classification and Extrinsic Regression are important and challenging machine learning tasks. Deep learning has revolutionized natural language processing and computer vision and holds great promise in other fields such as time series analysis where the relevant features must often be abstracted from the raw data but are not known a priori. This paper surveys the current state of the art in the fast-moving field of deep learning for time series classification and extrinsic regression. We review different network architectures and training methods used for these tasks and discuss the challenges and opportunities when applying deep learning to time series data. We also summarize two critical applications of time series classification and extrinsic regression, human activity recognition and satellite earth observation.
Recently, frequency transformation (FT) has been increasingly incorporated into deep learning models to significantly enhance state-of-the-art accuracy and efficiency in time series analysis. The advantages of FT, such as high efficiency and a global view, have been rapidly explored and exploited in various time series tasks and applications, demonstrating the promising potential of FT as a new deep learning paradigm for time series analysis. Despite the growing attention and the proliferation of research in this emerging field, there is currently a lack of a systematic review and in-depth analysis of deep learning-based time series models with FT. It is also unclear why FT can enhance time series analysis and what its limitations in the field are. To address these gaps, we present a comprehensive review that systematically investigates and summarizes the recent research advancements in deep learning-based time series analysis with FT. Specifically, we explore the primary approaches used in current models that incorporate FT, the types of neural networks that leverage FT, and the representative FT-equipped models in deep time series analysis. We propose a novel taxonomy to categorize the existing methods in this field, providing a structured overview of the diverse approaches employed in incorporating FT into deep learning models for time series analysis. Finally, we highlight the advantages and limitations of FT for time series modeling and identify potential future research directions that can further contribute to the community of time series analysis.
Objective. When a person listens to continuous speech, a corresponding response is elicited in the brain and can be recorded using electroencephalography (EEG). Linear models are presently used to relate the EEG recording to the corresponding speech signal. The ability of linear models to find a mapping between these two signals is used as a measure of neural tracking of speech. Such models are limited as they assume linearity in the EEG-speech relationship, which omits the nonlinear dynamics of the brain. As an alternative, deep learning models have recently been used to relate EEG to continuous speech. Approach. This paper reviews and comments on deep-learning-based studies that relate EEG to continuous speech in single- or multiple-speakers paradigms. We point out recurrent methodological pitfalls and the need for a standard benchmark of model analysis. Main results. We gathered 29 studies. The main methodological issues we found are biased cross-validations, data leakage leading to over-fitted models, or disproportionate data size compared to the model's complexity. In addition, we address requirements for a standard benchmark model analysis, such as public datasets, common evaluation metrics, and good practices for the match-mismatch task. Significance. We present a review paper summarizing the main deep-learning-based studies that relate EEG to speech while addressing methodological pitfalls and important considerations for this newly expanding field. Our study is particularly relevant given the growing application of deep learning in EEG-speech decoding.
Learning-based algorithms for automated license plate recognition implicitly assume that the training and test data are well aligned. However, this may not be the case under extreme environmental conditions, or in forensic applications where the system cannot be trained for a specific acquisition device. Predictions on such out-of-distribution images have an increased chance of failing. But this failure case is oftentimes hard to recognize for a human operator or an automated system. Hence, in this work we propose to model the prediction uncertainty for license plate recognition explicitly. Such an uncertainty measure allows to detect false predictions, indicating an analyst when not to trust the result of the automated license plate recognition. In this paper, we compare three methods for uncertainty quantification on two architectures. The experiments on synthetic noisy or blurred low-resolution images show that the predictive uncertainty reliably finds wrong predictions. We also show that a multi-task combination of classification and super-resolution improves the recognition performance by 109\% and the detection of wrong predictions by 29 %.
Background: To develop an artificial intelligence system that can accurately identify acute non-traumatic intracranial hemorrhage (ICH) etiology based on non-contrast CT (NCCT) scans and investigate whether clinicians can benefit from it in a diagnostic setting. Materials and Methods: The deep learning model was developed with 1868 eligible NCCT scans with non-traumatic ICH collected between January 2011 and April 2018. We tested the model on two independent datasets (TT200 and SD 98) collected after April 2018. The model's diagnostic performance was compared with clinicians's performance. We further designed a simulated study to compare the clinicians's performance with and without the deep learning system augmentation. Results: The proposed deep learning system achieved area under the receiver operating curve of 0.986 (95% CI 0.967-1.000) on aneurysms, 0.952 (0.917-0.987) on hypertensive hemorrhage, 0.950 (0.860-1.000) on arteriovenous malformation (AVM), 0.749 (0.586-0.912) on Moyamoya disease (MMD), 0.837 (0.704-0.969) on cavernous malformation (CM), and 0.839 (0.722-0.959) on other causes in TT200 dataset. Given a 90% specificity level, the sensitivities of our model were 97.1% and 90.9% for aneurysm and AVM diagnosis, respectively. The model also shows an impressive generalizability in an independent dataset SD98. The clinicians achieve significant improvements in the sensitivity, specificity, and accuracy of diagnoses of certain hemorrhage etiologies with proposed system augmentation. Conclusions: The proposed deep learning algorithms can be an effective tool for early identification of hemorrhage etiologies based on NCCT scans. It may also provide more information for clinicians for triage and further imaging examination selection.
We study speech enhancement using deep learning (DL) for virtual meetings on cellular devices, where transmitted speech has background noise and transmission loss that affects speech quality. Since the Deep Noise Suppression (DNS) Challenge dataset does not contain practical disturbance, we collect a transmitted DNS (t-DNS) dataset using Zoom Meetings over T-Mobile network. We select two baseline models: Demucs and FullSubNet. The Demucs is an end-to-end model that takes time-domain inputs and outputs time-domain denoised speech, and the FullSubNet takes time-frequency-domain inputs and outputs the energy ratio of the target speech in the inputs. The goal of this project is to enhance the speech transmitted over the cellular networks using deep learning models.
The ongoing expansion of urban areas facilitated by advancements in science and technology has resulted in a considerable increase in the number of privately owned vehicles worldwide, including in South Korea. However, this gradual increment in the number of vehicles has inevitably led to parking-related issues, including the abuse of disabled parking spaces (hereafter referred to as accessible parking spaces) designated for individuals with disabilities. Traditional license plate recognition (LPR) systems have proven inefficient in addressing such a problem in real-time due to the high frame rate of surveillance cameras, the presence of natural and artificial noise, and variations in lighting and weather conditions that impede detection and recognition by these systems. With the growing concept of parking 4.0, many sensors, IoT and deep learning-based approaches have been applied to automatic LPR and parking management systems. Nonetheless, the studies show a need for a robust and efficient model for managing accessible parking spaces in South Korea. To address this, we have proposed a novel system called, Shine, which uses the deep learning-based object detection algorithm for detecting the vehicle, license plate, and disability badges (referred to as cards, badges, or access badges hereafter) and verifies the rights of the driver to use accessible parking spaces by coordinating with the central server. Our model, which achieves a mean average precision of 92.16%, is expected to address the issue of accessible parking space abuse and contributes significantly towards efficient and effective parking management in urban environments.
Deep learning has made tremendous progress in the last decade. A key success factor is the large amount of architectures, layers, objectives, and optimization techniques. They include a myriad of variants related to attention, normalization, skip connections, transformers and self-supervised learning schemes -- to name a few. We provide a comprehensive overview of the most important, recent works in these areas to those who already have a basic understanding of deep learning. We hope that a holistic and unified treatment of influential, recent works helps researchers to form new connections between diverse areas of deep learning. We identify and discuss multiple patterns that summarize the key strategies for many of the successful innovations over the last decade as well as works that can be seen as rising stars. We also include a discussion on recent commercially built, closed-source models such as OpenAI's GPT-4 and Google's PaLM 2.
In the last few years, artistic image-making with deep learning models has gained a considerable amount of traction. A large number of these models operate directly in the pixel space and generate raster images. This is however not how most humans would produce artworks, for example, by planning a sequence of shapes and strokes to draw. Recent developments in deep learning methods help to bridge the gap between stroke-based paintings and pixel photo generation. With this survey, we aim to provide a structured introduction and understanding of common challenges and approaches in stroke-based rendering algorithms. These algorithms range from simple rule-based heuristics to stroke optimization and deep reinforcement agents, trained to paint images with differentiable vector graphics and neural rendering.
Magnitude-based pruning is a technique used to optimise deep learning models for edge inference. We have achieved over 75% model size reduction with a higher accuracy than the original multi-output regression model for head-pose estimation.
In this paper, we perform deep neural networks for learning $\psi$-weakly dependent processes. Such weak-dependence property includes a class of weak dependence conditions such as mixing, association,$\cdots$ and the setting considered here covers many commonly used situations such as: regression estimation, time series prediction, time series classification,$\cdots$ The consistency of the empirical risk minimization algorithm in the class of deep neural networks predictors is established. We achieve the generalization bound and obtain a learning rate, which is less than $\mathcal{O}(n^{-1/\alpha})$, for all $\alpha > 2 $. Applications to binary time series classification and prediction in affine causal models with exogenous covariates are carried out. Some simulation results are provided, as well as an application to the US recession data.
Deep Learning models have shown success in a large variety of tasks by extracting correlation patterns from high-dimensional data but still struggle when generalizing out of their initial distribution. As causal engines aim to learn mechanisms independent from a data distribution, combining Deep Learning with Causality can have a great impact on the two fields. In this paper, we further motivate this assumption. We perform an extensive overview of the theories and methods for Causality from different perspectives, with an emphasis on Deep Learning and the challenges met by the two domains. We show early attempts to bring the fields together and the possible perspectives for the future. We finish by providing a large variety of applications for techniques from Causality.
The learning rate is a critical hyperparameter for deep learning tasks since it determines the extent to which the model parameters are updated during the learning course. However, the choice of learning rates typically depends on empirical judgment, which may not result in satisfactory outcomes without intensive try-and-error experiments. In this study, we propose a novel learning rate adaptation scheme called QLABGrad. Without any user-specified hyperparameter, QLABGrad automatically determines the learning rate by optimizing the Quadratic Loss Approximation-Based (QLAB) function for a given gradient descent direction, where only one extra forward propagation is required. We theoretically prove the convergence of QLABGrad with a smooth Lipschitz condition on the loss function. Experiment results on multiple architectures, including MLP, CNN, and ResNet, on MNIST, CIFAR10, and ImageNet datasets, demonstrate that QLABGrad outperforms various competing schemes for deep learning.
The current deep learning model is of a single-grade, that is, it learns a deep neural network by solving a single nonconvex optimization problem. When the layer number of the neural network is large, it is computationally challenging to carry out such a task efficiently. Inspired by the human education process which arranges learning in grades, we propose a multi-grade learning model: We successively solve a number of optimization problems of small sizes, which are organized in grades, to learn a shallow neural network for each grade. Specifically, the current grade is to learn the leftover from the previous grade. In each of the grades, we learn a shallow neural network stacked on the top of the neural network, learned in the previous grades, which remains unchanged in training of the current and future grades. By dividing the task of learning a deep neural network into learning several shallow neural networks, one can alleviate the severity of the nonconvexity of the original optimization problem of a large size. When all grades of the learning are completed, the final neural network learned is a stair-shape neural network, which is the superposition of networks learned from all grades. Such a model enables us to learn a deep neural network much more effectively and efficiently. Moreover, multi-grade learning naturally leads to adaptive learning. We prove that in the context of function approximation if the neural network generated by a new grade is nontrivial, the optimal error of the grade is strictly reduced from the optimal error of the previous grade. Furthermore, we provide several proof-of-concept numerical examples which demonstrate that the proposed multi-grade model outperforms significantly the traditional single-grade model and is much more robust than the traditional model.
Recent breakthrough technological progressions of powerful mobile computing resources such as low-cost mobile GPUs along with cutting-edge, open-source software architectures have enabled high-performance deep learning on mobile platforms. These advancements have revolutionized the capabilities of today's mobile applications in different dimensions to perform data-driven intelligence locally, particularly for smart health applications. Unlike traditional machine learning (ML) architectures, modern on-device deep learning frameworks are proficient in utilizing computing resources in mobile platforms seamlessly, in terms of producing highly accurate results in less inference time. However, on the flip side, energy resources in a mobile device are typically limited. Hence, whenever a complex Deep Neural Network (DNN) architecture is fed into the on-device deep learning framework, while it achieves high prediction accuracy (and performance), it also urges huge energy demands during the runtime. Therefore, managing these resources efficiently within the spectrum of performance and energy efficiency is the newest challenge for any mobile application featuring data-driven intelligence beyond experimental evaluations. In this paper, first, we provide a timely review of recent advancements in on-device deep learning while empirically evaluating the performance metrics of current state-of-the-art ML architectures and conventional ML approaches with the emphasis given on energy characteristics by deploying them on a smart health application. With that, we are introducing a new framework through an energy-aware, adaptive model comprehension and realization (EAMCR) approach that can be utilized to make more robust and efficient inference decisions based on the available computing/energy resources in the mobile device during the runtime.
Background: While deep learning technology, which has the capability of obtaining latent representations based on large-scale data, can be a potential solution for the discovery of a novel aging biomarker, existing deep learning methods for biological age estimation usually depend on chronological ages and lack of consideration of mortality and morbidity that are the most significant outcomes of aging. Methods: This paper proposes a novel deep learning model to learn latent representations of biological aging in regard to subjects' morbidity and mortality. The model utilizes health check-up data in addition to morbidity and mortality information to learn the complex relationships between aging and measured clinical attributes. Findings: The proposed model is evaluated on a large dataset of general populations compared with KDM and other learning-based models. Results demonstrate that biological ages obtained by the proposed model have superior discriminability of subjects' morbidity and mortality.
Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most recent developments in artificial intelligence are coming from deep learning, which has proven revolutionary in almost all fields, from computer vision to health sciences. The effects of deep learning in medicine have changed the conventional ways of clinical application significantly. Although some sub-fields of medicine, such as pediatrics, have been relatively slow in receiving the critical benefits of deep learning, related research in pediatrics has started to accumulate to a significant level, too. Hence, in this paper, we review recently developed machine learning and deep learning-based solutions for neonatology applications. We systematically evaluate the roles of both classical machine learning and deep learning in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in the assessment of neonatal diseases by using PRISMA 2020 guidelines. To date, the primary areas of focus in neonatology regarding AI applications have included survival analysis, neuroimaging, analysis of vital parameters and biosignals, and retinopathy of prematurity diagnosis. We have categorically summarized 106 research articles from 1996 to 2022 and discussed their pros and cons, respectively. In this systematic review, we aimed to further enhance the comprehensiveness of the study. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for the integration of AI into neonatal intensive care units.
Objective: Reliable tools to predict moyamoya disease (MMD) patients at risk for hemorrhage could have significant value. The aim of this paper is to develop three machine learning classification algorithms to predict hemorrhage in moyamoya disease. Methods: Clinical data of consecutive MMD patients who were admitted to our hospital between 2009 and 2015 were reviewed. Demographics, clinical, radiographic data were analyzed to develop artificial neural network (ANN), support vector machine (SVM), and random forest models. Results: We extracted 33 parameters, including 11 demographic and 22 radiographic features as input for model development. Of all compared classification results, ANN achieved the highest overall accuracy of 75.7% (95% CI, 68.6%-82.8%), followed by SVM with 69.2% (95% CI, 56.9%-81.5%) and random forest with 70.0% (95% CI, 57.0%-83.0%). Conclusions: The proposed ANN framework can be a potential effective tool to predict the possibility of hemorrhage among adult MMD patients based on clinical information and radiographic features.
A core task in precision agriculture is the identification of climatic and ecological conditions that are advantageous for a given crop. The most succinct approach is geolocation, which is concerned with locating the native region of a given sample based on its genetic makeup. Here, we investigate genomic geolocation of Populus trichocarpa, or poplar, which has been identified by the US Department of Energy as a fast-rotation biofuel crop to be harvested nationwide. In particular, we approach geolocation from a reference-free perspective, circumventing the need for compute-intensive processes such as variant calling and alignment. Our model, MashNet, predicts latitude and longitude for poplar trees from randomly-sampled, unaligned sequence fragments. We show that our model performs comparably to Locator, a state-of-the-art method based on aligned whole-genome sequence data. MashNet achieves an error of 34.0 km^2 compared to Locator's 22.1 km^2. MashNet allows growers to quickly and efficiently identify natural varieties that will be most productive in their growth environment based on genotype. This paper explores geolocation for precision agriculture while providing a framework and data source for further development by the machine learning community.
We propose a supervised deep learning (DL) approach to perform adaptive zoning on time dependent partial differential equations that model the propagation of 1D shock waves in a compressible medium. We train a neural network on a dataset composed of different static shock profiles associated with the corresponding adapted meshes computed with standard adaptive zoning techniques. We show that the trained DL model learns how to capture the presence of shocks in the domain and generates at each time step an adapted non-uniform mesh that relocates the grid nodes to improve the accuracy of Lax-Wendroff and fifth order weighted essentially non-oscillatory (WENO5) space discretization schemes. We also show that the surrogate DL model reduces the computational time to perform adaptive zoning by at least a 2x factor with respect to standard techniques without compromising the accuracy of the reconstruction of the physical quantities of interest.