OHetTLAL: An Online Transfer Learning Method for Fingerprint-Based Indoor Positioning

In an indoor positioning system (IPS), transfer learning (TL) methods are commonly used to predict the location of mobile devices under the assumption that all training instances of the target domain are given in advance. However, this assumption has been criticized for its shortcomings in dealing with the problem of signal distribution variations, especially in a dynamic indoor environment. The reasons are: collecting a sufficient number of training instances is costly, the training instances may arrive online, the feature spaces of the target and source domains may be different, and negative knowledge may be transferred in the case of a redundant source domain. In this work, we proposed an online heterogeneous transfer learning (OHetTLAL) algorithm for IPS-based RSS fingerprinting to improve the positioning performance in the target domain by fusing both source and target domain knowledge. The source domain was refined based on the target domain to avoid negative knowledge transfer. The co-occurrence measure of the feature spaces (Cmip) was used to derive the homogeneous new feature spaces, and the features with higher weight values were selected for training the classifier because they could positively affect the location prediction of the target. Thus, the objective function was minimized over the new feature spaces. Extensive experiments were conducted on two real-world scenarios of datasets, and the predictive power of the different modeling techniques were evaluated for predicting the location of a mobile device. The results have revealed that the proposed algorithm outperforms the state-of-the-art methods for fingerprint-based indoor positioning and is found robust to changing environments. Moreover, the proposed algorithm is not only resilient to fluctuating environments but also mitigates the model's overfitting problem.

A Novel Joint Adversarial Domain Adaptation Method for Rotary Machine Fault Diagnosis under Different Working Conditions

In real-world applications of detecting faults, many factors-such as changes in working conditions, equipment wear, and environmental causes-can cause a significant mismatch between the source domain on which classifiers are trained and the target domain to which those classifiers are applied. As such, existing deep network algorithms perform poorly under different working conditions. To solve this problem, we propose a novel fault diagnosis method named Joint Adversarial Domain Adaptation (JADA) for fault detection under different working conditions. Our approach simultaneously aligns marginal distribution and conditional distribution across the source and target through a unified adversarial learning process. JADA aims to construct domain-invariant and category-discriminative feature representation that is effective and robust for substantial distribution difference caused by working conditions. We also introduce a supervision signal, namely center loss, that penalizes the distances between the deep features and their corresponding class centers. This makes the learned features better equipped with more discriminative structures and effectively prevents mode collapse. Twenty-four transfer fault diagnosis tasks based on two experimental platforms were conducted to evaluate the effectiveness of the proposed methods. Extensive experiments verified that the JADA can significantly outperform several popular methods under different transfer diagnosis tasks.

Adversarial Entropy Optimization for Unsupervised Domain Adaptation

Domain adaptation is proposed to deal with the challenging problem where the probability distribution of the training source is different from the testing target. Recently, adversarial learning has become the dominating technique for domain adaptation. Usually, adversarial domain adaptation methods simultaneously train a feature learner and a domain discriminator to learn domain-invariant features. Accordingly, how to effectively train the domain-adversarial model to learn domain-invariant features becomes a challenge in the community. To this end, we propose in this article a novel domain adaptation scheme named adversarial entropy optimization (AEO) to address the challenge. Specifically, we minimize the entropy when samples are from the independent distributions of source domain or target domain to improve the discriminability of the model. At the same time, we maximize the entropy when features are from the combined distribution of source domain and target domain so that the domain discriminator can be confused and the transferability of representations can be promoted. This minimax regime is well matched with the core idea of adversarial learning, empowering our model with transferability as well as discriminability for domain adaptation tasks. Also, AEO is flexible and compatible with different deep networks and domain adaptation frameworks. Experiments on five data sets show that our method can achieve state-of-the-art performance across diverse domain adaptation tasks.

G Protein-Coupled Receptor Interaction Prediction Based on Deep Transfer Learning

G protein-coupled receptors (GPCRs) account for about 40% to 50% of drug targets. Many human diseases are related to G protein coupled receptors. Accurate prediction of GPCR interaction is not only essential to understand its structural role, but also helps design more effective drugs. At present, the prediction of GPCR interaction mainly uses machine learning methods. Machine learning methods generally require a large number of independent and identically distributed samples to achieve good results. However, the number of available GPCR samples that have been marked is scarce. Transfer learning has a strong advantage in dealing with such small sample problems. Therefore, this paper proposes a transfer learning method based on sample similarity, using XGBoost as a weak classifier and using the TrAdaBoost algorithm based on JS divergence for data weight initialization to transfer samples to construct a data set. After that, the deep neural network based on the attention mechanism is used for model training. The existing GPCR is used for prediction. In short-distance contact prediction, the accuracy of our method is 0.26 higher than similar methods.

Source Data-Absent Unsupervised Domain Adaptation Through Hypothesis Transfer and Labeling Transfer

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to the source data, and thus are not applicable when the data are confidential and not shareable due to privacy concerns. This paper aims to tackle a realistic setting with only a classification model available trained over, instead of accessing to, the source data. To effectively utilize the source model for adaptation, we propose a novel approach called Source HypOthesis Transfer (SHOT), which learns the feature extraction module for the target domain by fitting the target data features to the frozen source classification module (representing classification hypothesis). Specifically, SHOT exploits both information maximization and self-supervised learning for the feature extraction module learning to ensure the target features are implicitly aligned with the features of unseen source data via the same hypothesis. Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to improve the accuracy of less-confident predictions in the target domain. We denote labeling transfer as SHOT++ if the predictions are obtained by SHOT. Extensive experiments on both digit classification and object recognition tasks show that SHOT and SHOT++ achieve results surpassing or comparable to the state-of-the-arts, demonstrating the effectiveness of our approaches for various visual domain adaptation problems. Code will be available at https://github.com/tim-learn/SHOT-plus.

Subdomain Adaptation With Manifolds Discrepancy Alignment

Reducing domain divergence is a key step in transfer learning. Existing works focus on the minimization of global domain divergence. However, two domains may consist of several shared subdomains, and differ from each other in each subdomain. In this article, we take the local divergence of subdomains into account in transfer. Specifically, we propose to use the low-dimensional manifold to represent the subdomain, and align the local data distribution discrepancy in each manifold across domains. A manifold maximum mean discrepancy (M3D) is developed to measure the local distribution discrepancy in each manifold. We then propose a general framework, called transfer with manifolds discrepancy alignment (TMDA), to couple the discovery of data manifolds with the minimization of M3D. We instantiate TMDA in the subspace learning case considering both the linear and nonlinear mappings. We also instantiate TMDA in the deep learning framework. Experimental studies show that TMDA is a promising method for various transfer learning tasks.

Transfer Relation Network for Fault Diagnosis of Rotating Machinery With Small Data

Many deep-learning methods have been developed for fault diagnosis. However, due to the difficulty of collecting and labeling machine fault data, the datasets in some practical applications are relatively much smaller than the other big data benchmarks. In addition, the fault data come from different machines. Therefore, on some occasions, fault diagnosis is a multidomain problem with small data, where satisfactory transfer performance is difficult to obtain and has been rarely explored from the few-shot learning viewpoint. Different from the existing deep transfer learning solutions, a novel transfer relation network (TRN), combining a few-shot learning mechanism and transfer learning, is developed in this study. Specifically, the fault diagnosis problem has been treated as a similarity metric-learning problem instead of solely feature weighted classification. A feature net and a relation net have been, respectively, constructed for feature extraction and relation computation. The Siamese structure has been borrowed to extract the features of the source and the target domain samples with shared weights. Multikernel maximum mean discrepancy (MK-MMD) is employed on several higher layers with different tradeoff parameters to enable an efficient domain feature transfer considering different feature properties. To implement efficient diagnosis based on small data, an episode-based few-shot training strategy is adopted to train TRN. Average pooling has been adopted to suppress the noise influence from the vibration sequence which turns out to be important for the success of time sequence-based fault diagnosis. Transfer experiments on four datasets have verified the superior performance of TRN. A significant improvement of classification accuracy has been made compared with the state-of-the-art methods on the adopted datasets.

Dynamic feature learning for COVID-19 segmentation and classification

Since December 2019, coronavirus SARS-CoV-2 (COVID-19) has rapidly developed into a global epidemic, with millions of patients affected worldwide. As part of the diagnostic pathway, computed tomography (CT) scans are used to help patient management. However, parenchymal imaging findings in COVID-19 are non-specific and can be seen in other diseases. In this work, we propose to first segment lesions from CT images, and further, classify COVID-19 patients from healthy persons and common pneumonia patients. In detail, a novel Dynamic Fusion Segmentation Network (DFSN) that automatically segments infection-related pixels is first proposed. Within this network, low-level features are aggregated to high-level ones to effectively capture context characteristics of infection regions, and high-level features are dynamically fused to model multi-scale semantic information of lesions. Based on DFSN, Dynamic Transfer-learning Classification Network (DTCN) is proposed to distinguish COVID-19 patients. Within DTCN, a pre-trained DFSN is transferred and used as the backbone to extract pixel-level information. Then the pixel-level information is dynamically selected and used to make a diagnosis. In this way, the pre-trained DFSN is utilized through transfer learning, and clinical significance of segmentation results is comprehensively considered. Thus DTCN becomes more sensitive to typical signs of COVID-19. Extensive experiments are conducted to demonstrate effectiveness of the proposed DFSN and DTCN frameworks. The corresponding results indicate that these two models achieve state-of-the-art performance in terms of segmentation and classification.

Self-supervised bi-classifier adversarial transfer network for cross-domain fault diagnosis of rotating machinery

In real industrial scenarios, deep learning-based fault diagnosis has been a popular topic lately. Unfortunately, the source-trained model typically usually underperforms in target domain owning to changeable working conditions. To resolve this problem, a novel self-supervised bi-classifier adversarial transfer learning (SBATL) network by introducing self-supervised learning (SSL) and class-conditional entropy minimization is presented. Concretely, the SBATL is made up of a feature extractor, a discrepancy detector of two classifiers, and a clustering metric based on SSL, which jointly conducts self-supervised and supervised optimization in a two-stream training procedure. In the self-supervised stream, target pseudo labels obtained by SSL are used to construct the topological clustering metric for target feature optimization. In the supervised stream, the feature extractor and classifiers compete with each other in adversarial training, which bridges the discrepancy between two classifiers. Additionally, the class-conditional entropy minimization of target domain is further embedded into both streams to amend the decision boundaries of two classifiers to pass low-density regions. The results indicate that the SBATL gets better cross-domain fault diagnosis performances when compared with other popular methods.

Unsupervised domain adaptive myocardial infarction MRI classification diagnostics model based on target domain confused sample resampling

OBJECTIVE

Inefficient circulatory system due to blockage of blood vessels leads to myocardial infarction and acute blockage. Myocardial infarction is frequently classified and diagnosed in medical treatment using MRI, yet this method is ineffective and prone to error. As a result, there are several implementation scenarios and clinical significance for employing deep learning to develop computer-aided algorithms to aid cardiologists in the routine examination of cardiac MRI.

METHODS

This research uses two distinct domain classifiers to address this issue and achieve domain adaptation between the particular field and the specific part is a problem Current research on environment adaptive systems cannot effectively obtain and apply classification information for unsupervised scenes of target domain images. Insufficient information interchange between specific domains and specific domains is a problem. In this study, two different domain classifiers are used to solve this problem and achieve domain adaption. To effectively mine the source domain images for classification understanding, an unsupervised MRI classification technique for myocardial infarction called CardiacCN is proposed, which relies on adversarial instructions related to the interpolation of confusion specimens in the target domain for the conflict of confusion specimens for the target domain classification task.

RESULTS

The experimental results demonstrate that the CardiacCN model in this study performs better on the six domain adaption tasks of the Sunnybrook Cardiac Dataset (SCD) dataset and increases the mean target area myocardial infarction MRI classification accuracy by approximately 1.2 percent. The classification performance of the CardiacCN model on the target domain does not vary noticeably when the temperature-controlled duration hyper-parameter rl falls in the region of 5-30. According to the experimental findings, the CardiacCN model is more resistant to the excitable rl. The CardiacCN model suggested in this research may successfully increase the accuracy of the source domain predictor for the target domain myocardial infarction clinical scanning classification in unsupervised learning, as shown by the visualization analysis infrastructure provision nurture. It is evident from the visualization assessment of embedded features that the CardiacCN model may significantly increase the source domain classifier's accuracy for the target domain's classification of myocardial infarction in clinical scans under unsupervised conditions.

CONCLUSION

To address misleading specimens with the inconsistent classification of target-domain myocardial infarction medical scans, this paper introduces the CardiacCN unsupervised domain adaptive MRI classification model, which relies on adversarial learning associated with resampling target-domain confusion samples. With this technique, implicit image classification information from the target domain is fully utilized, knowledge transfer from the target domain to the specific domain is encouraged, and the classification effect of the myocardial ischemia medical scan is improved in the target domain of the unsupervised scene.

Explainable AI for clinical and remote health applications: a survey on tabular and time series data

Nowadays Artificial Intelligence (AI) has become a fundamental component of healthcare applications, both clinical and remote, but the best performing AI systems are often too complex to be self-explaining. Explainable AI (XAI) techniques are defined to unveil the reasoning behind the system’s predictions and decisions, and they become even more critical when dealing with sensitive and personal health data. It is worth noting that XAI has not gathered the same attention across different research areas and data types, especially in healthcare. In particular, many clinical and remote health applications are based on tabular and time series data, respectively, and XAI is not commonly analysed on these data types, while computer vision and Natural Language Processing (NLP) are the reference applications. To provide an overview of XAI methods that are most suitable for tabular and time series data in the healthcare domain, this paper provides a review of the literature in the last 5 years, illustrating the type of generated explanations and the efforts provided to evaluate their relevance and quality. Specifically, we identify clinical validation, consistency assessment, objective and standardised quality evaluation, and human-centered quality assessment as key features to ensure effective explanations for the end users. Finally, we highlight the main research challenges in the field as well as the limitations of existing XAI methods.

Supervised and Semisupervised Manifold Embedded Knowledge Transfer in Motor Imagery-Based BCI

A long calibration procedure limits the use in practice for a motor imagery (MI)-based brain-computer interface (BCI) system. To tackle this problem, we consider supervised and semisupervised transfer learning. However, it is a challenge for them to cope with high intersession/subject variability in the MI electroencephalographic (EEG) signals. Based on the framework of unsupervised manifold embedded knowledge transfer (MEKT), we propose a supervised MEKT algorithm (sMEKT) and a semisupervised MEKT algorithm (ssMEKT), respectively. sMEKT only has limited labelled samples from a target subject and abundant labelled samples from multiple source subjects. Compared to sMEKT, ssMEKT adds comparably more unlabelled samples from the target subject. After performing Riemannian alignment (RA) and tangent space mapping (TSM), both sMEKT and ssMEKT execute domain adaptation to shorten the differences among subjects. During domain adaptation, to make use of the available samples, two algorithms preserve the source domain discriminability, and ssMEKT preserves the geometric structure embedded in the labelled and unlabelled target domains. Moreover, to obtain a subject-specific classifier, sMEKT minimizes the joint probability distribution shift between the labelled target and source domains, whereas ssMEKT performs the joint probability distribution shift minimization between the unlabelled target domain and all labelled domains. Experimental results on two publicly available MI datasets demonstrate that our algorithms outperform the six competing algorithms, where the sizes of labelled and unlabelled target domains are variable. Especially for the target subjects with 10 labelled samples and 270/190 unlabelled samples, ssMEKT shows 5.27% and 2.69% increase in average accuracy on the two abovementioned datasets compared to the previous best semisupervised transfer learning algorithm (RA-regularized common spatial patterns-weighted adaptation regularization, RA-RCSP-wAR), respectively. Therefore, our algorithms can effectively reduce the need of labelled samples for the target subject, which is of importance for the MI-based BCI application.

Distribution matching and structure preservation for domain adaptation

Cross-domain classification refers to completing the corresponding classification task in a target domain which lacks label information, by exploring useful knowledge in a related source domain but with different data distribution. Domain adaptation can deal with such cross-domain classification, by reducing divergence of domains and transferring the relevant knowledge from the source to the target. To mine the discriminant information of the source domain samples and the geometric structure information of domains, and thus improve domain adaptation performance, this paper proposes a novel method involving distribution matching and structure preservation for domain adaptation (DMSP). First, it aligns the subspaces of the source domain and target domain on the Grassmann manifold; and learns the non-distorted embedded feature representations of the two domains. Second, in this embedded feature space, the empirical structure risk minimization method with distribution adaptation regularization and intra-domain graph regularization is used to learn an adaptive classifier, further adapting the source and target domains. Finally, we perform extensive experiments on widely used cross-domain classification datasets to validate the superiority of DMSP. The average classification accuracy of DMSP on these datasets is the highest compared with several state-of-the-art domain adaptation methods.

Multi-Source Contribution Learning for Domain Adaptation

Transfer learning becomes an attractive technology to tackle a task from a target domain by leveraging previously acquired knowledge from a similar domain (source domain). Many existing transfer learning methods focus on learning one discriminator with single-source domain. Sometimes, knowledge from single-source domain might not be enough for predicting the target task. Thus, multiple source domains carrying richer transferable information are considered to complete the target task. Although there are some previous studies dealing with multi-source domain adaptation, these methods commonly combine source predictions by averaging source performances. Different source domains contain different transferable information; they may contribute differently to a target domain compared with each other. Hence, the source contribution should be taken into account when predicting a target task. In this article, we propose a novel multi-source contribution learning method for domain adaptation (MSCLDA). As proposed, the similarities and diversities of domains are learned simultaneously by extracting multi-view features. One view represents common features (similarities) among all domains. Other views represent different characteristics (diversities) in a target domain; each characteristic is expressed by features extracted in a source domain. Then multi-level distribution matching is employed to improve the transferability of latent features, aiming to reduce misclassification of boundary samples by maximizing discrepancy between different classes and minimizing discrepancy between the same classes. Concurrently, when completing a target task by combining source predictions, instead of averaging source predictions or weighting sources using normalized similarities, the original weights learned by normalizing similarities between source and target domains are adjusted using pseudo target labels to increase the disparities of weight values, which is desired to improve the performance of the final target predictor if the predictions of sources exist significant difference. Experiments on real-world visual data sets demonstrate the superiorities of our proposed method.

Prototype-Based Multisource Domain Adaptation

Unsupervised domain adaptation aims to transfer knowledge from labeled source domain to unlabeled target domain. Recently, multisource domain adaptation (MDA) has begun to attract attention. Its performance should go beyond simply mixing all source domains together for knowledge transfer. In this article, we propose a novel prototype-based method for MDA. Specifically, for solving the problem that the target domain has no label, we use the prototype to transfer the semantic category information from source domains to target domain. First, a feature extraction network is applied to both source and target domains to obtain the extracted features from which the domain-invariant features and domain-specific features will be disentangled. Then, based on these two kinds of features, the named inherent class prototypes and domain prototypes are estimated, respectively. Then a prototype mapping to the extracted feature space is learned in the feature reconstruction process. Thus, the class prototypes for all source and target domains can be constructed in the extracted feature space based on the previous domain prototypes and inherent class prototypes. By forcing the extracted features are close to the corresponding class prototypes for all domains, the feature extraction network is progressively adjusted. In the end, the inherent class prototypes are used as a classifier in the target domain. Our contribution is that through the inherent class prototypes and domain prototypes, the semantic category information from source domains is transformed into the target domain by constructing the corresponding class prototypes. In our method, all source and target domains are aligned twice at the feature level for better domain-invariant features and more closer features to the class prototypes, respectively. Several experiments on public data sets also prove the effectiveness of our method.

Memory-Efficient Class-Incremental Learning for Image Classification

With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer. To utilize the memory buffer more efficiently, we propose to keep more auxiliary low-fidelity exemplar samples, rather than the original real-high-fidelity exemplar samples. Such a memory-efficient exemplar preserving scheme makes the old-class knowledge transfer more effective. However, the low-fidelity exemplar samples are often distributed in a different domain away from that of the original exemplar samples, that is, a domain shift. To alleviate this problem, we propose a duplet learning scheme that seeks to construct domain-compatible feature extractors and classifiers, which greatly narrows down the above domain gap. As a result, these low-fidelity auxiliary exemplar samples have the ability to moderately replace the original exemplar samples with a lower memory cost. In addition, we present a robust classifier adaptation scheme, which further refines the biased classifier (learned with the samples containing distillation label knowledge about old classes) with the help of the samples of pure true class labels. Experimental results demonstrate the effectiveness of this work against the state-of-the-art approaches. We will release the code, baselines, and training statistics for all models to facilitate future research.

Heterogeneous Domain Adaptation With Structure and Classification Space Alignment

Domain adaptation (DA) aims at facilitating the target model training by leveraging knowledge from related but distribution-inconsistent source domain. Most of the previous DA works concentrate on homogeneous scenarios, where the source and target domains are assumed to share the same feature space. Nevertheless, frequently, in reality, the domains are not consistent in not only data distribution but also the representation space and feature dimensions. That is, these domains are heterogeneous. Although many works have attempted to handle such heterogeneous DA (HDA) by transforming HDA to homogeneous counterparts or performing DA jointly with domain transformation, nearly all of them just concentrate on the feature and distribution alignment across domains, neglecting the structure and classification space preservation for domains themselves. In this work, we propose a novel HDA model, namely, heterogeneous classification space alignment (HCSA), which leverages knowledge from both the source samples and model parameters to the target. In HCSA, structure preservation, distribution, and classification space alignment are implemented, jointly with feature representation by transferring both the source-domain representation and model knowledge. Moreover, we design an alternating algorithm to optimize the HCSA model with guaranteed convergence and complexity analysis. In addition, the HCSA model is further extended with deep network architecture. Finally, we experimentally evaluate the effectiveness of the proposed method by showing its superiority to the compared approaches.

Deep Transfer Learning for Question Classification Based on Semantic Information Features of Category Labels

Question classification is an important component of the question answering system (QA system), which is designed to restrict the answer types and accurately locate the answers. Therefore, the classification results of the questions affect the quality and performance of the QA system. Most question classification methods in the past have relied on a large amount of manually labeled training data. However, in real situations, especially in new domains, it is very difficult to obtain a large amount of labeled data. Transfer learning is an effective approach to solve the problem with the scarcity of annotated data in new domains. We compare the effects of different deep transfer learning methods on cross-domain question classification. On the basis of the ALBERT fine-tuning model, we extract the category labels of the source domain, the question text, and the predicted category labels of the target domain as input to extract the category labels. Additionally, the semantic information of the category labels is extracted to achieve cross-domain question classification. Furthermore, WordNet is used to expand the question, which further improves the classification accuracy of the target domain. Experimental results show that the above methods can further improve the classification accuracy in new domains based on deep transfer learning.

Ani-GIFs: A benchmark dataset for domain generalization of action recognition from GIFs

Deep learning models perform remarkably well for the same task under the assumption that data is always coming from the same distribution. However, this is generally violated in practice, mainly due to the differences in data acquisition techniques and the lack of information about the underlying source of new data. Domain generalization targets the ability to generalize to test data of an unseen domain; while this problem is well-studied for images, such studies are significantly lacking in spatiotemporal visual content—videos and GIFs. This is due to (1) the challenging nature of misalignment of temporal features and the varying appearance/motion of actors and actions in different domains, and (2) spatiotemporal datasets being laborious to collect and annotate for multiple domains. We collect and present the first synthetic video dataset of Animated GIFs for domain generalization, Ani-GIFs, that is used to study the domain gap of videos vs. GIFs, and animated vs. real GIFs, for the task of action recognition. We provide a training and testing setting for Ani-GIFs, and extend two domain generalization baseline approaches, based on data augmentation and explainability, to the spatiotemporal domain to catalyze research in this direction.

A structure-protecting kernelized semi-supervised space adjustment for classification

We introduce a semi-supervised space adjustment framework in this paper. In the introduced framework, the dataset contains two subsets: (a) training data subset (space-one data (SOD)) and (b) testing data subset (space-two data (STD)). Our semi-supervised space adjustment framework learns under three assumptions: (I) it is assumed that all data points in the SOD are labeled, and only a minority of the data points in the STD are labeled (we call the labeled space-two data as LSTD), (II) the size of LSTD is very small comparing to the size of SOD, and (III) it is also assumed that the data of SOD and the data of STD have different distributions. We denote the unlabeled space-two data by ULSTD, which is equal to STD - LSTD. The aim is to map the training data, i.e., the data from the training labeled data subset and those from LSTD (note that all labeled data are considered to be training data, i.e., SOD ∪ LSTD) into a shared space (ShS). The mapped SOD, ULSTD, and LSTD into ShS are named MSOD, MULSTD, and MLSTD, respectively. The proposed method does the mentioned mapping in such a way that structures of the data points in SOD and MSOD, in STD and MSTD, in ULSTD and MULSTD, and in LSTD and MLSTD are the same. In the proposed method, the mapping is proposed to be done by a principal component analysis transformation on kernelized data. In the proposed method, it is tried to find a mapping that (a) can maintain the neighbors of data points after the mapping and (b) can take advantage of the class labels that are known in STD during transformation. After that, we represent and formulate the problem of finding the optimal mapping into a non-linear objective function. To solve it, we transform it into a semidefinite programming (SDP) problem. We solve the optimization problem with an SDP solver. The examinations indicate the superiority of the learners trained in the data mapped by the proposed approach to the learners trained in the data mapped by the state of the art methods.

Multi-source joint domain adaptation for cross-subject and cross-session emotion recognition from electroencephalography

As an important component to promote the development of affective brain–computer interfaces, the study of emotion recognition based on electroencephalography (EEG) has encountered a difficult challenge; the distribution of EEG data changes among different subjects and at different time periods. Domain adaptation methods can effectively alleviate the generalization problem of EEG emotion recognition models. However, most of them treat multiple source domains, with significantly different distributions, as one single source domain, and only adapt the cross-domain marginal distribution while ignoring the joint distribution difference between the domains. To gain the advantages of multiple source distributions, and better match the distributions of the source and target domains, this paper proposes a novel multi-source joint domain adaptation (MSJDA) network. We first map all domains to a shared feature space and then align the joint distributions of the further extracted private representations and the corresponding classification predictions for each pair of source and target domains. Extensive cross-subject and cross-session experiments on the benchmark dataset, SEED, demonstrate the effectiveness of the proposed model, where more significant classification results are obtained on the more difficult cross-subject emotion recognition task.

Progressive distribution adapted neural networks for cross-corpus speech emotion recognition

In this paper, we investigate a challenging but interesting task in the research of speech emotion recognition (SER), i.e., cross-corpus SER. Unlike the conventional SER, the training (source) and testing (target) samples in cross-corpus SER come from different speech corpora, which results in a feature distribution mismatch between them. Hence, the performance of most existing SER methods may sharply decrease. To cope with this problem, we propose a simple yet effective deep transfer learning method called progressive distribution adapted neural networks (PDAN). PDAN employs convolutional neural networks (CNN) as the backbone and the speech spectrum as the inputs to achieve an end-to-end learning framework. More importantly, its basic idea for solving cross-corpus SER is very straightforward, i.e., enhancing the backbone's corpus invariant feature learning ability by incorporating a progressive distribution adapted regularization term into the original loss function to guide the network training. To evaluate the proposed PDAN, extensive cross-corpus SER experiments on speech emotion corpora including EmoDB, eNTERFACE, and CASIA are conducted. Experimental results showed that the proposed PDAN outperforms most well-performing deep and subspace transfer learning methods in dealing with the cross-corpus SER tasks.

Comparison of deep transfer learning algorithms and transferability measures for wearable sleep staging

Background

Obtaining medical data using wearable sensors is a potential replacement for in-hospital monitoring, but the lack of data for such sensors poses a challenge for development. One solution is using in-hospital recordings to boost performance via transfer learning. While there are many possible transfer learning algorithms, few have been tested in the domain of EEG-based sleep staging. Furthermore, there are few ways for determining which transfer learning method will work best besides exhaustive testing. Measures of transferability do exist, but are typically used for selection of pre-trained models rather than algorithms and few have been tested on medical signals. We tested several supervised transfer learning algorithms on a sleep staging task using a single channel of EEG (AF7-Fpz) captured from an in-home commercial system.

Results

Two neural networks—one bespoke and another state-of-art open-source architecture—were pre-trained on one of six source datasets comprising 11,561 subjects undergoing clinical polysomnograms (PSGs), then re-trained on a target dataset of 75 full-night recordings from 24 subjects. Several transferability measures were then tested to determine which is most effective for assessing performance on unseen target data. Performance on the target dataset was improved using transfer learning, with re-training the head layers being the most effective in the majority of cases (up to 63.9% of cases). Transferability measures generally provided significant correlations with accuracy (up to \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$r = -0.53$$\end{document}r=-0.53).

Conclusion

Re-training the head layers provided the largest performance boost. Transferability measures are useful indicators of transfer learning effectiveness.

Emotion recognition based on multi-modal physiological signals and transfer learning

In emotion recognition based on physiological signals, collecting enough labeled data of a single subject for training is time-consuming and expensive. The physiological signals’ individual differences and the inherent noise will significantly affect emotion recognition accuracy. To overcome the difference in subject physiological signals, we propose a joint probability domain adaptation with the bi-projection matrix algorithm (JPDA-BPM). The bi-projection matrix method fully considers the source and target domain’s different feature distributions. It can better project the source and target domains into the feature space, thereby increasing the algorithm’s performance. We propose a substructure-based joint probability domain adaptation algorithm (SSJPDA) to overcome physiological signals’ noise effect. This method can avoid the shortcomings that the domain level matching is too rough and the sample level matching is susceptible to noise. In order to verify the effectiveness of the proposed transfer learning algorithm in emotion recognition based on physiological signals, we verified it on the database for emotion analysis using physiological signals (DEAP dataset). The experimental results show that the average recognition accuracy of the proposed SSJPDA-BPM algorithm in the multimodal fusion physiological data from the DEAP dataset is 63.6 and 64.4% in valence and arousal, respectively. Compared with joint probability domain adaptation (JPDA), the performance of valence and arousal recognition accuracy increased by 17.6 and 13.4%, respectively.

Adapting Multiple Distributions for Bridging Emotions from Different Speech Corpora

In this paper, we focus on a challenging, but interesting, task in speech emotion recognition (SER), i.e., cross-corpus SER. Unlike conventional SER, a feature distribution mismatch may exist between the labeled source (training) and target (testing) speech samples in cross-corpus SER because they come from different speech emotion corpora, which degrades the performance of most well-performing SER methods. To address this issue, we propose a novel transfer subspace learning method called multiple distribution-adapted regression (MDAR) to bridge the gap between speech samples from different corpora. Specifically, MDAR aims to learn a projection matrix to build the relationship between the source speech features and emotion labels. A novel regularization term called multiple distribution adaption (MDA), consisting of a marginal and two conditional distribution-adapted operations, is designed to collaboratively enable such a discriminative projection matrix to be applicable to the target speech samples, regardless of speech corpus variance. Consequently, by resorting to the learned projection matrix, we are able to predict the emotion labels of target speech samples when only the source label information is given. To evaluate the proposed MDAR method, extensive cross-corpus SER tasks based on three different speech emotion corpora, i.e., EmoDB, eNTERFACE, and CASIA, were designed. Experimental results showed that the proposed MDAR outperformed most recent state-of-the-art transfer subspace learning methods and even performed better than several well-performing deep transfer learning methods in dealing with cross-corpus SER tasks.

Adaptive 1-dimensional time invariant learning for inertial sensor-based gait authentication

Wearable-sensor gait signals processed using advanced machine learning algorithms are shown to be reliable for user authentication. However, no study has been reported to investigate the influence of elapsed time on wearable sensor-based gait authentication performance. This work is the first exploratory study that presents accelerometer and gyroscope signals from 144 participants with slow, normal, and fast walking speeds from 2 sessions (1-month elapse time) to evaluate IMU gait-based authentication performance. Gait signals are recorded in six positions (i.e., left and right pocket, left and right hand, handbag, and backpack). The users' identities are verified using a robust gait authentication method called Adaptive 1-Dimensional Time Invariant Learning (A1TIL). In A1TIL, 1D Local Ternary Patterns (LTP) with an adaptive threshold is proposed to extract discriminative time-invariant features from a gait cycle. In addition, a new unsupervised learning method called Kernelized Domain Adaptation (KDA) is applied to match two gait signals from different time spans for user verification. Comprehensive experiments have been conducted to assess the effectiveness of the proposed approach on a newly developed time invariant inertial sensor dataset. The promising result with an Equal Error Rate (EER) of 4.38% from slow walking speed and right pocket position across 1 month demonstrates that gait signals extracted from inertial sensors can be used as a reliable means of biometrics across time.

Multisource-Refined Transfer Network for Industrial Fault Diagnosis Under Domain and Category Inconsistencies

Unsupervised cross-domain fault diagnosis has been actively researched in recent years. It learns transferable features that reduce distribution inconsistency between source and target domains without target supervision. Most of the existing cross-domain fault diagnosis approaches are developed based on the consistency assumption of the source and target fault category sets. This assumption, however, is generally challenged in practice, as different working conditions can have different fault category sets. To solve the fault diagnosis problem under both domain and category inconsistencies, a multisource-refined transfer network is proposed in this article. First, a multisource-domain-refined adversarial adaptation strategy is designed to reduce the refined categorywise distribution inconsistency within each source-target domain pair. It avoids the negative transfer trap caused by conventional global-domainwise-forced alignments. Then, a multiple classifier complementation module is developed by complementing and transferring the source classifiers to the target domain to leverage different diagnostic knowledge existing in various sources. Different classifiers are complemented by the similarity scores produced by the adaptation module, and the complemented smooth predictions are used to guide the refined adaptation. Thus, the refined adversarial adaptation and the classifier complementation can benefit from each other in the training stage, yielding target-faults-discriminative and domain-refined-indistinguishable feature representations. Extensive experiments on two cases demonstrate the superiority of the proposed method when domain and category inconsistencies coexist.

Distribution Adaptation and Classification Framework Based on Multiple Kernel Learning for Motor Imagery BCI Illiteracy

A brain-computer interface (BCI) translates a user's thoughts such as motor imagery (MI) into the control of external devices. However, some people, who are defined as BCI illiteracy, cannot control BCI effectively. The main characteristics of BCI illiterate subjects are low classification rates and poor repeatability. To address the problem of MI-BCI illiteracy, we propose a distribution adaptation method based on multi-kernel learning to make the distribution of features between the source domain and target domain become even closer to each other, while the divisibility of categories is maximized. Inspired by the kernel trick, we adopted a multiple-kernel-based extreme learning machine to train the labeled source-domain data to find a new high-dimensional subspace that maximizes data divisibility, and then use multiple-kernel-based maximum mean discrepancy to conduct distribution adaptation to eliminate the difference in feature distribution between domains in the new subspace. In light of the high dimension of features of MI-BCI illiteracy, random forest, which can effectively handle high-dimensional features without additional cross-validation, was employed as a classifier. The proposed method was validated on an open dataset. The experimental results show that that the method we proposed suits MI-BCI illiteracy and can reduce the inter-domain differences, resulting in a reduction in the performance degradation of both cross-subjects and cross-sessions.

An efficient CNN-LSTM Network with spectral normalization and label smoothing technologies for SSVEP frequency recognition

OBJECTIVE

Steady-state visual evoked potentials(SSVEPs) based braincomputer interface(BCI) has received great interests owing to the high information transfer rate(ITR) and available large number of targets. However, the performance of frequency recognition methods heavily depends on the amount of the calibration data for intra-subject classification. Some research adopted the deep learning(DL) algorithm to conduct the inter-subject classification, which could reduce the calculation procedure, but the performance still has large room to improve compared with the intra-subject classification.

APPROACH

To address these issues, we proposed an efficient SSVEP DL NETwork (termed SSVEPNET) based on 1D convolution and long short-term memory (LSTM) module. To enhance the performance of SSVEPNT, we adopted the spectral normalization and label smoothing technologies during implementing the network architecture. We evaluated the SSVEPNET and compared it with other methods for the intra- and inter-subject classification under different conditions, i.e., two datasets, two time-window lengths (1 s and 0.5 s), three sizes of training data.

MAIN RESULTS

Under all the experimental settings, the proposed SSVEPNET achieved the highest average accuracy for the intra- and inter-subject classification on the two SSVEP datasets, when compared with other traditional and DL baseline methods. Signif icance. The extensive experimental results demonstrate that the proposed DL model holds promise to enhance frequency recognition performance in SSVEP-based BCIs. Besides, the mixed network structures with CNN and LSTM, and the spectral normalization and label smoothing could be useful optimization strategies to design efficient models for EEG data.

Reducing variations in multi-center Alzheimer's disease classification with convolutional adversarial autoencoder

Based on brain magnetic resonance imaging (MRI), multiple variations ranging from MRI scanners to center-specific parameter settings, imaging protocols, and brain region-of-interest (ROI) definitions pose a big challenge for multi-center Alzheimer's disease characterization and classification. Existing approaches to reduce such variations require intricate multi-step, often manual preprocessing pipelines, including skull stripping, segmentation, registration, cortical reconstruction, and ROI outlining. Such procedures are time-consuming, and more importantly, tend to be user biased. Contrasting costly and biased preprocessing pipelines, the question arises whether we can design a deep learning model to automatically reduce these variations from multiple centers for Alzheimer's disease classification? In this study, we used T1 and T2-weighted structural MRI from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset based on three groups with 375 subjects, respectively: patients with Alzheimer's disease (AD) dementia, with mild cognitive impairment (MCI), and healthy controls (HC); to test our approach, we defined AD classification as classifying an individual's structural image to one of the three group labels. We first introduced a convolutional adversarial autoencoder (CAAE) to reduce the variations existing in multi-center raw MRI scans by automatically registering them into a common aligned space. Afterward, a convolutional residual soft attention network (CRAT) was further proposed for AD classification. Canonical classification procedures demonstrated that our model achieved classification accuracies of 91.8%, 90.05%, and 88.10% for the 2-way classification tasks using the RAW aligned MRI scans, including AD vs. HC, AD vs. MCI, and MCI vs. HC, respectively. Thus, our automated approach achieves comparable or even better classification performance by comparing it with many baselines with dedicated conventional preprocessing pipelines. Furthermore, the uncovered brain hotpots, i.e., hippocampus, amygdala, and temporal pole, are consistent with previous studies.

Weighted Correlation Embedding Learning for Domain Adaptation

Domain adaptation leverages rich knowledge from a related source domain so that it can be used to perform tasks in a target domain. For more knowledge to be obtained under relaxed conditions, domain adaptation methods have been widely used in pattern recognition and image classification. However, most of the existing domain adaptation methods only consider how to minimize different distributions of the source and target domains, which neglects what should be transferred for a specific task and suffers negative transfer by distribution outliers. To address these problems, in this paper, we propose a novel domain adaptation method called weighted correlation embedding learning (WCEL) for image classification. In the WCEL approach, we seamlessly integrated correlation learning, graph embedding, and sample reweighting into a unified learning model. Specifically, we extracted the maximum correlated features from the source and target domains for image classification tasks. In addition, two graphs were designed to preserve the discriminant information from interclass samples and neighborhood relations in intraclass samples. Furthermore, to prevent the negative transfer problem, we developed an efficient sample reweighting strategy to predict the target with different confidence levels. To verify the performance of the proposed method in image classification, extensive experiments were conducted with several benchmark databases, verifying the superiority of the WCEL method over other state-of-the-art domain adaptation algorithms.

A Survey on Adversarial Domain Adaptation

Having a lot of labeled data is always a problem in machine learning issues. Even by collecting lots of data hardly, shift in data distribution might emerge because of differences in source and target domains. The shift would make the model to face with problems in test step. Therefore, the necessity of using domain adaptation emerges. There are three techniques in the field of domain adaptation namely discrepancy based, adversarial based and reconstruction based methods. For domain adaptation, adversarial learning approaches showed state-of-the-art performance. Although there are some comprehensive surveys about domain adaptation, we technically focus on adversarial based domain adaptation methods. We examine each proposed method in detail with respect to their structures and objective functions. The common aspect of proposed methods besides domain adaptation is considering the target labels are predicted as accurately as possible. It can be represented by some methods such as metric learning and multi-adversarial discriminators as are used in some of the papers. Also, we address the negative transfer issue for dissimilar distributions and propose the addition of clustering heuristics to the underlying structures for future research.

Combination of spectral index and transfer learning strategy for glyphosate-resistant cultivar identification

Glyphosate is one of the most widely used non-selective herbicides, and the creation of glyphosate-resistant cultivars solves the problem of limited spraying area. Therefore, it is of great significance to quickly identify resistant cultivars without destruction during the development of superior cultivars. This work took maize seedlings as the experimental object, and the spectral indices of leaves were calculated to construct a model with good robustness that could be used in different experiments. Compared with no transfer strategies, transferability of support vector machine learning model was improved by randomly selecting 14% of source domain from target domain to train and applying transfer component analysis algorithm, the accuracy on target domain reached 83% (increased by 71%), recall increased from 10 to 100%, and F1-score increased from 0.17 to 0.86. The overall results showed that both transfer component analysis algorithm and updating source domain could improve the transferability of model among experiments, and these two transfer strategies could complement each other's advantages to achieve the best classification performance. Therefore, this work is beneficial to timely understanding of the physiological status of plants, identifying glyphosate resistant cultivars, and ultimately provides theoretical basis and technical support for new cultivar creation and high-throughput selection.

Attention-wise masked graph contrastive learning for predicting molecular property

MOTIVATION

Accurate and efficient prediction of the molecular property is one of the fundamental problems in drug research and development. Recent advancements in representation learning have been shown to greatly improve the performance of molecular property prediction. However, due to limited labeled data, supervised learning-based molecular representation algorithms can only search limited chemical space and suffer from poor generalizability.

RESULTS

In this work, we proposed a self-supervised learning method, ATMOL, for molecular representation learning and properties prediction. We developed a novel molecular graph augmentation strategy, referred to as attention-wise graph masking, to generate challenging positive samples for contrastive learning. We adopted the graph attention network as the molecular graph encoder, and leveraged the learned attention weights as masking guidance to generate molecular augmentation graphs. By minimization of the contrastive loss between original graph and augmented graph, our model can capture important molecular structure and higher order semantic information. Extensive experiments showed that our attention-wise graph mask contrastive learning exhibited state-of-the-art performance in a couple of downstream molecular property prediction tasks. We also verified that our model pretrained on larger scale of unlabeled data improved the generalization of learned molecular representation. Moreover, visualization of the attention heatmaps showed meaningful patterns indicative of atoms and atomic groups important to specific molecular property.