Search

Optimizing Cox regression and its neural network variants poses substantial computational challenges in large-scale studies. Stochastic gradient descent (SGD), known for its scalability in model optimization, has recently been adapted to optimize Cox models. Unlike its conventional application, which typically targets a sum of independent individual loss, SGD for Cox models updates parameters based on the partial likelihood of a subset of data. Despite its empirical success, the theoretical foundation for optimizing Cox partial likelihood with SGD is largely underexplored. In this work, we demonstrate that the SGD estimator targets an objective function that is batch-size-dependent. We establish that the SGD estimator for the Cox neural network (Cox-NN) is consistent and achieves the optimal minimax convergence rate up to a polylogarithmic factor. For Cox regression, we further prove the $\sqrt{n}$-consistency and asymptotic normality of the SGD estimator, with variance depending on the batch size. Furthermore, we quantify the impact of batch size on Cox-NN training and its effect on the SGD estimator's asymptotic efficiency in Cox regression. These findings are validated by extensive numerical experiments and provide guidance for selecting batch sizes in SGD applications. Finally, we demonstrate the effectiveness of SGD in a real-world application where GD is unfeasible due to the large scale of data.

Speech emotion recognition (SER) plays a crucial role in human-computer interaction. The emergence of edge devices in the Internet of Things (IoT) presents challenges in constructing intricate deep learning models due to constraints in memory and computational resources. Moreover, emotional speech data often contains private information, raising concerns about privacy leakage during the deployment of SER models. To address these challenges, we propose a data distillation framework to facilitate efficient development of SER models in IoT applications using a synthesised, smaller, and distilled dataset. Our experiments demonstrate that the distilled dataset can be effectively utilised to train SER models with fixed initialisation, achieving performances comparable to those developed using the original full emotional speech dataset.

Electromyography-to-Speech (ETS) conversion has demonstrated its potential for silent speech interfaces by generating audible speech from Electromyography (EMG) signals during silent articulations. ETS models usually consist of an EMG encoder which converts EMG signals to acoustic speech features, and a vocoder which then synthesises the speech signals. Due to an inadequate amount of available data and noisy signals, the synthesised speech often exhibits a low level of naturalness. In this work, we propose Diff-ETS, an ETS model which uses a score-based diffusion probabilistic model to enhance the naturalness of synthesised speech. The diffusion model is applied to improve the quality of the acoustic features predicted by an EMG encoder. In our experiments, we evaluated fine-tuning the diffusion model on predictions of a pre-trained EMG encoder, and training both models in an end-to-end fashion. We compared Diff-ETS with a baseline ETS model without diffusion using objective metrics and a listening test. The results indicated the proposed Diff-ETS significantly improved speech naturalness over the baseline., Comment: Accepted by EMBC 2024

As the adoption of explainable AI (XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorisation of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings. Interested readers are encouraged to access our repository at https://github.com/tamlhp/awesome-privex., Comment: Revision

Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction. The robustness of SER models is crucial, particularly in privacy-sensitive and reliability-demanding domains like private healthcare. Recently, the vulnerability of deep neural networks in the audio domain to adversarial attacks has become a popular area of research. However, prior works on adversarial attacks in the audio domain primarily rely on iterative gradient-based techniques, which are time-consuming and prone to overfitting the specific threat model. Furthermore, the exploration of sparse perturbations, which have the potential for better stealthiness, remains limited in the audio domain. To address these challenges, we propose a generator-based attack method to generate sparse and transferable adversarial examples to deceive SER models in an end-to-end and efficient manner. We evaluate our method on two widely-used SER datasets, Database of Elicited Mood in Speech (DEMoS) and Interactive Emotional dyadic MOtion CAPture (IEMOCAP), and demonstrate its ability to generate successful sparse adversarial examples in an efficient manner. Moreover, our generated adversarial examples exhibit model-agnostic transferability, enabling effective adversarial attacks on advanced victim models.

Heart sound auscultation has been applied in clinical usage for early screening of cardiovascular diseases. Due to the high demand for auscultation expertise, automatic auscultation can help with auxiliary diagnosis and reduce the burden of training professional clinicians. Nevertheless, there is a limit to classic machine learning's performance improvement in the era of big data. Deep learning has outperformed classic machine learning in many research fields, as it employs more complex model architectures with a stronger capability of extracting effective representations. Moreover, it has been successfully applied to heart sound analysis in the past years. As most review works about heart sound analysis were carried out before 2017, the present survey is the first to work on a comprehensive overview to summarise papers on heart sound analysis with deep learning published in 2017--2022. This work introduces both classic machine learning and deep learning for comparison, and further offer insights about the advances and future research directions in deep learning for heart sound analysis. Our repository is publicly available at \url{https://github.com/zhaoren91/awesome-heart-sound-analysis}., Comment: Accepted by IEEE Computational Intelligence Magazine

High-dimensional data are commonly seen in modern statistical applications, variable selection methods play indispensable roles in identifying the critical features for scientific discoveries. Traditional best subset selection methods are computationally intractable with a large number of features, while regularization methods such as Lasso, SCAD and their variants perform poorly in ultrahigh-dimensional data due to low computational efficiency and unstable algorithm. Sure screening methods have become popular alternatives by first rapidly reducing the dimension using simple measures such as marginal correlation then applying any regularization methods. A number of screening methods for different models or problems have been developed, however, none of the methods have targeted at data with heavy tailedness, which is another important characteristics of modern big data. In this paper, we propose a robust distance correlation (``RDC'') based sure screening method to perform screening in ultrahigh-dimensional regression with heavy-tailed data. The proposed method shares the same good properties as the original model-free distance correlation based screening while has additional merit of robustly estimating the distance correlation when data is heavy-tailed and improves the model selection performance in screening. We conducted extensive simulations under different scenarios of heavy tailedness to demonstrate the advantage of our proposed procedure as compared to other existing model-based or model-free screening procedures with improved feature selection and prediction performance. We also applied the method to high-dimensional heavy-tailed RNA sequencing (RNA-seq) data of The Cancer Genome Atlas (TCGA) pancreatic cancer cohort and RDC was shown to outperform the other methods in prioritizing the most essential and biologically meaningful genes.

Acoustic-based fault detection has a high potential to monitor the health condition of mechanical parts. However, the background noise of an industrial environment may negatively influence the performance of fault detection. Limited attention has been paid to improving the robustness of fault detection against industrial environmental noise. Therefore, we present the Lenze production background-noise (LPBN) real-world dataset and an automated and noise-robust auditory inspection (ARAI) system for the end-of-line inspection of geared motors. An acoustic array is used to acquire data from motors with a minor fault, major fault, or which are healthy. A benchmark is provided to compare the psychoacoustic features with different types of envelope features based on expert knowledge of the gearbox. To the best of our knowledge, we are the first to apply time-varying psychoacoustic features for fault detection. We train a state-of-the-art one-class-classifier, on samples from healthy motors and separate the faulty ones for fault detection using a threshold. The best-performing approaches achieve an area under curve of 0.87 (logarithm envelope), 0.86 (time-varying psychoacoustics), and 0.91 (combination of both)., Comment: the final published version at ICASSP 2023 include small additional content as well as some minor revisions

Atrial fibrillation (AF) is the most common cardiac arrhythmia and associated with a high risk for serious conditions like stroke. The use of wearable devices embedded with automatic and timely AF assessment from electrocardiograms (ECGs) has shown to be promising in preventing life-threatening situations. Although deep neural networks have demonstrated superiority in model performance, their use on wearable devices is limited by the trade-off between model performance and complexity. In this work, we propose to use lightweight convolutional neural networks (CNNs) with parameterised hypercomplex (PH) layers for AF detection based on ECGs. The proposed approach trains small-scale CNNs, thus overcoming the limited computing resources on wearable devices. We show comparable performance to corresponding real-valued CNNs on two publicly available ECG datasets using significantly fewer model parameters. PH models are more flexible than other hypercomplex neural networks and can operate on any number of input ECG leads., Comment: Published at EUSIPCO 2023

Speech emotion recognition (SER) has been a popular research topic in human-computer interaction (HCI). As edge devices are rapidly springing up, applying SER to edge devices is promising for a huge number of HCI applications. Although deep learning has been investigated to improve the performance of SER by training complex models, the memory space and computational capability of edge devices represents a constraint for embedding deep learning models. We propose a neural structured learning (NSL) framework through building synthesized graphs. An SER model is trained on a source dataset and used to build graphs on a target dataset. A relatively lightweight model is then trained with the speech samples and graphs together as the input. Our experiments demonstrate that training a lightweight SER model on the target dataset with speech samples and graphs can not only produce small SER models, but also enhance the model performance compared to models with speech samples only and those using classic transfer learning strategies., Comment: Accepted by ICASSP 2023

Speech emotion recognition (SER) is the task of recognising human's emotional states from speech. SER is extremely prevalent in helping dialogue systems to truly understand our emotions and become a trustworthy human conversational partner. Due to the lengthy nature of speech, SER also suffers from the lack of abundant labelled data for powerful models like deep neural networks. Pre-trained complex models on large-scale speech datasets have been successfully applied to SER via transfer learning. However, fine-tuning complex models still requires large memory space and results in low inference efficiency. In this paper, we argue achieving a fast yet effective SER is possible with self-distillation, a method of simultaneously fine-tuning a pretrained model and training shallower versions of itself. The benefits of our self-distillation framework are threefold: (1) the adoption of self-distillation method upon the acoustic modality breaks through the limited ground-truth of speech data, and outperforms the existing models' performance on an SER dataset; (2) executing powerful models at different depth can achieve adaptive accuracy-efficiency trade-offs on resource-limited edge devices; (3) a new fine-tuning process rather than training from scratch for self-distillation leads to faster learning time and the state-of-the-art accuracy on data with small quantities of label information., Comment: Submitted to ICASSP 2023

As "a new frontier in evolutionary computation research", evolutionary transfer optimization(ETO) will overcome the traditional paradigm of zero reuse of related experience and knowledge from solved past problems in researches of evolutionary computation. In scheduling applications via ETO, a quite appealing and highly competitive framework "meeting" between them could be formed for both intelligent scheduling and green scheduling, especially for international pledge of "carbon neutrality" from China. To the best of our knowledge, our paper on scheduling here, serves as the 1st work of a class of ETO frameworks when multiobjective optimization problem "meets" single-objective optimization problems in discrete case (not multitasking optimization). More specifically, key knowledge conveyed for industrial applications, like positional building blocks with genetic algorithm based settings, could be used via the new core transfer mechanism and learning techniques for permutation flow shop scheduling problem(PFSP). Extensive studies on well-studied benchmarks validate firm effectiveness and great universality of our proposed ETO-PFSP framework empirically. Our investigations (1) enrich the ETO frameworks, (2) contribute to the classical and fundamental theory of building block for genetic algorithms and memetic algorithms, and (3) head towards the paradigm shift of evolutionary scheduling via learning by proposal and practice of paradigm of "knowledge and building-block based scheduling" (KAB2S) for "industrial intelligence" in China., Comment: For improvement

Respiratory sound classification is an important tool for remote screening of respiratory-related diseases such as pneumonia, asthma, and COVID-19. To facilitate the interpretability of classification results, especially ones based on deep learning, many explanation methods have been proposed using prototypes. However, existing explanation techniques often assume that the data is non-biased and the prediction results can be explained by a set of prototypical examples. In this work, we develop a unified example-based explanation method for selecting both representative data (prototypes) and outliers (criticisms). In particular, we propose a novel application of adversarial attacks to generate an explanation spectrum of data instances via an iterative fast gradient sign method. Such unified explanation can avoid over-generalisation and bias by allowing human experts to assess the model mistakes case by case. We performed a wide range of quantitative and qualitative evaluations to show that our approach generates effective and understandable explanation and is robust with many deep learning models, Comment: Submitted to INTERSPEECH 2022

Due to the development of machine learning and speech processing, speech emotion recognition has been a popular research topic in recent years. However, the speech data cannot be protected when it is uploaded and processed on servers in the internet-of-things applications of speech emotion recognition. Furthermore, deep neural networks have proven to be vulnerable to human-indistinguishable adversarial perturbations. The adversarial attacks generated from the perturbations may result in deep neural networks wrongly predicting the emotional states. We propose a novel federated adversarial learning framework for protecting both data and deep neural networks. The proposed framework consists of i) federated learning for data privacy, and ii) adversarial training at the training stage and randomisation at the testing stage for model robustness. The experiments show that our proposed framework can effectively protect the speech data locally and improve the model robustness against a series of adversarial attacks., Comment: 11 pages, 6 figures, 3 tables

Remote screening of respiratory diseases has been widely studied as a non-invasive and early instrument for diagnosis purposes, especially in the pandemic. The respiratory sound classification task has been realized with numerous deep neural network (DNN) models due to their superior performance. However, in the high-stake medical domain where decisions can have significant consequences, it is desirable to develop interpretable models; thus, providing understandable reasons for physicians and patients. To address the issue, we propose a prototype learning framework, that jointly generates exemplar samples for explanation and integrates these samples into a layer of DNNs. The experimental results indicate that our method outperforms the state-of-the-art approaches on the largest public respiratory sound database., Comment: Technical report of the paper accepted by IEEE ICASSP 2022

Aiming to automatically detect COVID-19 from cough sounds, we propose a deep attentive multi-model fusion system evaluated on the Track-1 dataset of the DiCOVA 2021 challenge. Three kinds of representations are extracted, including hand-crafted features, image-from-audio-based deep representations, and audio-based deep representations. Afterwards, the best models on the three types of features are fused at both the feature level and the decision level. The experimental results demonstrate that the proposed attention-based fusion at the feature level achieves the best performance (AUC: 77.96%) on the test set, resulting in an 8.05% improvement over the official baseline., Comment: 3 pages, Technical Report

Cardiovascular diseases are the leading cause of deaths and severely threaten human health in daily life. On the one hand, there have been dramatically increasing demands from both the clinical practice and the smart home application for monitoring the heart status of subjects suffering from chronic cardiovascular diseases. On the other hand, experienced physicians who can perform an efficient auscultation are still lacking in terms of number. Automatic heart sound classification leveraging the power of advanced signal processing and machine learning technologies has shown encouraging results. Nevertheless, human hand-crafted features are expensive and time-consuming. To this end, we propose a novel deep representation learning method with an attention mechanism for heart sound classification. In this paradigm, high-level representations are learnt automatically from the recorded heart sound data. Particularly, a global attention pooling layer improves the performance of the learnt representations by estimating the contribution of each unit in feature maps. The Heart Sounds Shenzhen (HSS) corpus (170 subjects involved) is used to validate the proposed method. Experimental results validate that, our approach can achieve an unweighted average recall of 51.2% for classifying three categories of heart sounds, i. e., normal, mild, and moderate/severe annotated by cardiologists with the help of Echocardiography.

Acoustic Scene Classification (ASC) aims to classify the environment in which the audio signals are recorded. Recently, Convolutional Neural Networks (CNNs) have been successfully applied to ASC. However, the data distributions of the audio signals recorded with multiple devices are different. There has been little research on the training of robust neural networks on acoustic scene datasets recorded with multiple devices, and on explaining the operation of the internal layers of the neural networks. In this article, we focus on training and explaining device-robust CNNs on multi-device acoustic scene data. We propose conditional atrous CNNs with attention for multi-device ASC. Our proposed system contains an ASC branch and a device classification branch, both modelled by CNNs. We visualise and analyse the intermediate layers of the atrous CNNs. A time-frequency attention mechanism is employed to analyse the contribution of each time-frequency bin of the feature maps in the CNNs. On the Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 ASC dataset, recorded with three devices, our proposed model performs significantly better than CNNs trained on single-device data., Comment: IEEE Transactions on Multimedia

High-throughput microarray and sequencing technology have been used to identify disease subtypes that could not be observed otherwise by using clinical variables alone. The classical unsupervised clustering strategy concerns primarily the identification of subpopulations that have similar patterns in gene features. However, as the features corresponding to irrelevant confounders (e.g. gender or age) may dominate the clustering process, the resulting clusters may or may not capture clinically meaningful disease subtypes. This gives rise to a fundamental problem: can we find a subtyping procedure guided by a pre-specified disease outcome? Existing methods, such as supervised clustering, apply a two-stage approach and depend on an arbitrary number of selected features associated with outcome. In this paper, we propose a unified latent generative model to perform outcome-guided disease subtyping constructed from omics data, which improves the resulting subtypes concerning the disease of interest. Feature selection is embedded in a regularization regression. A modified EM algorithm is applied for numerical computation and parameter estimation. The proposed method performs feature selection, latent subtype characterization and outcome prediction simultaneously. To account for possible outliers or violation of mixture Gaussian assumption, we incorporate robust estimation using adaptive Huber or median-truncated loss function. Extensive simulations and an application to complex lung diseases with transcriptomic and clinical data demonstrate the ability of the proposed method to identify clinically relevant disease subtypes and signature genes suitable to explore toward precision medicine., Comment: 29 pages in total, 4 figures, 2 tables and 1 supplement

Set classification aims to classify a set of observations as a whole, as opposed to classifying individual observations separately. To formally understand the unfamiliar concept of binary set classification, we first investigate the optimal decision rule under the normal distribution, which utilizes the empirical covariance of the set to be classified. We show that the number of observations in the set plays a critical role in bounding the Bayes risk. Under this framework, we further propose new methods of set classification. For the case where only a few parameters of the model drive the difference between two classes, we propose a computationally-efficient approach to parameter estimation using linear programming, leading to the Covariance-engaged LInear Programming Set (CLIPS) classifier. Its theoretical properties are investigated for both independent case and various (short-range and long-range dependent) time series structures among observations within each set. The convergence rates of estimation errors and risk of the CLIPS classifier are established to show that having multiple observations in a set leads to faster convergence rates, compared to the standard classification situation in which there is only one observation in the set. The applicable domains in which the CLIPS performs better than competitors are highlighted in a comprehensive simulation study. Finally, we illustrate the usefulness of the proposed methods in classification of real image data in histopathology., Comment: 86 pages, 5 figures

The COVID-19 outbreak was announced as a global pandemic by the World Health Organisation in March 2020 and has affected a growing number of people in the past few weeks. In this context, advanced artificial intelligence techniques are brought to the fore in responding to fight against and reduce the impact of this global health crisis. In this study, we focus on developing some potential use-cases of intelligent speech analysis for COVID-19 diagnosed patients. In particular, by analysing speech recordings from these patients, we construct audio-only-based models to automatically categorise the health state of patients from four aspects, including the severity of illness, sleep quality, fatigue, and anxiety. For this purpose, two established acoustic feature sets and support vector machines are utilised. Our experiments show that an average accuracy of .69 obtained estimating the severity of illness, which is derived from the number of days in hospitalisation. We hope that this study can foster an extremely fast, low-cost, and convenient way to automatically detect the COVID-19 disease.