Adaptive Transfer Learning Research Articles

Domain adaptation network with uncertainty modeling and its application to the online energy consumption prediction of ethylene distillation processes

Real-time monitoring of quality index especially energy consumption is of great significance to improve energy efficiency and save energy. In ethylene distillations, the energy consumption cannot be measured online due to the lack of corresponding online analytical instruments and soft sensing is an effective technology to solve the problem. Additionally, ethylene industrial processes often operate under multiple conditions due to the change of the working conditions, in which the insufficient data will lead to poor prediction performances of the soft sensing model. Therefore, in this paper, a novel soft sensing method based on transfer learning framework is proposed to deal with the above problems, which consists of a feature extractor and a predictor. Concretely, to reduce the difference of domain distribution in the feature extractor, the lower bound estimation of Wasserstein distance is proposed as a metric of the difference. In the predictor, to mitigate the performance degradation caused by the domain difference, the adaptive features for predictor are constructed by the source domain features and uncertainty modeling of the quantified domain difference, which is measured through the proposed manifold distance. Therefore, an adaptive transfer learning framework is proposed to reduce effect of the domain difference, named as Domain Adaptation Network with Uncertainty Modeling (DANUM). Finally, a soft sensing method based on DANUM is proposed to predict quality index and energy consumption in ethylene distillation processes, which shows the effectiveness of our method.

Adaptive transfer learning

In transfer learning, we wish to make inference about a target population when we have access to data both from the distribution itself, and from a different but related source distribution. We introduce a flexible framework for transfer learning in the context of binary classification, allowing for covariate-dependent relationships between the source and target distributions that are not required to preserve the Bayes decision boundary. Our main contributions are to derive the minimax optimal rates of convergence (up to poly-logarithmic factors) in this problem, and show that the optimal rate can be achieved by an algorithm that adapts to key aspects of the unknown transfer relationship, as well as the smoothness and tail parameters of our distributional classes. This optimal rate turns out to have several regimes, depending on the interplay between the relative sample sizes and the strength of the transfer relationship, and our algorithm achieves optimality by careful, decision tree-based calibration of local nearest-neighbour procedures.

An autoencoder with adaptive transfer learning for intelligent fault diagnosis of rotating machinery

Under variable working conditions, a problem arises, which is that it is difficult to obtain enough labeled data; to address this problem, an adaptive transfer autoencoder (ATAE) is established to diagnose faults in rotating machinery. First, a data adaptation module, which calculates the maximum mean discrepancy for the network hidden-layer data in reproducing kernel Hilbert space, is introduced to the autoencoder network, thus making the classification model operate under variable working conditions. Variation particle-swarm optimization is then invoked to optimize the data adaptation parameters. Finally, the k-nearest neighbors algorithm, as the classification layer of the network, identifies the state of health of the rotating machinery. The capabilities of the intelligent fault-diagnosis network are verified using vibration signals from a bearing test rig and a gearbox test rig. The experimental results suggest that, compared with state-of-the-art diagnosis methods, the proposed ATAE network can significantly boost diagnostic performance in the absence of target vibration signal labels.

WITHDRAWN: Improving electoral roll authenticity and accessibility using side-chaining and deep learning

Abstract The main issue for any organisational elections is the validity and accessibility of the electoral roll. The electoral roll requires data validation when data is added or updated, and requires effective data selection when data retrieval operations are required. It is an evolving process that needs continuous moderation from both the bureaucrats and the public. Because of their inherent properties, such as non-mutability, multi-level authentication, cryptography, and strict data update laws, Blockchain driven systems have proven to be efficient in terms of security. But due to large data chains, blockchain systems have limited retrieval performance, which slows down the read-cycles, rendering the system ineffective for big data applications. A side-chain-based solution for the efficient storage and recovery of electoral roll data is described in this paper. In comparison to single-chain systems, data updating and insertion into side chains is less reliable. This is due to the fact that as opposed to their single chain counterparts, side chains are very limited in scale, so targeting these side chains is simpler. In order to preserve the security of the side-chain scheme, this paper describes a deep learning cryptosystem (DLC). In order to create a special non-identifiable side chain structure, this DLC utilises a combination of adaptive cryptography and transfer learning. In order to ensure high fidelity and reduce the risk of attacks, this side-chain system uses a hybrid blockchain implementation. The proposed method, while retaining the same degree of accuracy and protection, is found to be 47 percent faster than the current single-chain electoral roll management solutions.

Predictive Modeling With an Adaptive Unsupervised Broad Transfer Algorithm

Deep-learning algorithms have produced promising results, however, domain adaptation remains a challenge. In addition, excessive training time and computing resource requirements need to be addressed. Deep-learning algorithms face a domain adaptation issue when the data distribution of a target domain differs from that of the source domain. The emerging concept of broad learning shows potential in addressing the domain adaptation and training time issues. An adaptive unsupervised broad transfer learning (AUBTL) algorithm is proposed to tackle the cross-domain problems. The proposed algorithm utilizes a sparse autoencoder and random orthogonal mapping to extract and augment the feature space. Then, it initializes the weights of a classifier by solving a ridge regression problem. The logit ranking strategy is applied to develop a transfer estimator to evaluate and sample data in the target domain for an adaptive transfer. Based on the sampled data, AUBTL optimizes the hyperparameter space. The performance of the AUBTL algorithm is validated with three benchmark datasets, including 20 transfer tasks. The computational results demonstrated the efficiency and accuracy of the proposed algorithm over other deep-learning algorithms considered in this research.

FT-MDnet: A Deep-Frozen Transfer Learning Framework for Person Search

Matching manually cropped pedestrian images between queries and candidates, termed as person re-identification, has achieved significant progress with deep convolutional neural networks. Recently, a topic called ‘person search’ is proposed for the end-to-end application of re-identification technologies. It integrates object detection and person re-identification and aims to both locate and match pedestrians on a gallery of raw images. However, the design and implementation of such kind of hybrid network are difficult and computationally consuming in real practical situations. In order to fasten the design and ease the implementation, this paper proposes a deep-frozen transfer learning framework, named FT-MDnet, to extract re-identification features from a pre-trained detection network in two steps. First, using a channel-wise attention mechanism, a network called adaptive transfer learning network (ATLnet) is used to convert the sharing data of the underlying detection network to a re-identification feature map. Then, a multi-branch feature representation network called multiple descriptor network (MDnet) is proposed to extract re-identification features from the re-identification feature map. Our proposed solution has been verified on different types of mainstream detection networks, including YOLOv3, YOLOv4, Mask RCNN, and CenterNet. The experimental results show that our solution outperforms all other person search solutions by a large margin. It proves that the feature representations of detection networks are highly compatible with re-identification, and the proposed framework effectively extracts these features out. To encourage further research, we have made our framework open source.

Adaptive transfer learning for EEG motor imagery classification with deep Convolutional Neural Network

In recent years, deep learning has emerged as a powerful tool for developing Brain–Computer Interface (BCI) systems. However, for deep learning models trained entirely on the data from a specific individual, the performance increase has only been marginal owing to the limited availability of subject-specific data. To overcome this, many transfer-based approaches have been proposed, in which deep networks are trained using pre-existing data from other subjects and evaluated on new target subjects. This mode of transfer learning however faces the challenge of substantial inter-subject variability in brain data. Addressing this, in this paper, we propose 5 schemes for adaptation of a deep convolutional neural network (CNN) based electroencephalography (EEG)-BCI system for decoding hand motor imagery (MI). Each scheme fine-tunes an extensively trained, pre-trained model and adapt it to enhance the evaluation performance on a target subject. We report the highest subject-independent performance with an average (N=54) accuracy of 84.19% (±9.98%) for two-class motor imagery, while the best accuracy on this dataset is 74.15% (±15.83%) in the literature. Further, we obtain a statistically significant improvement (p=0.005) in classification using the proposed adaptation schemes compared to the baseline subject-independent model.

Adaptive Transfer Learning of Cross-Spatiotemporal Canonical Correlation Analysis for Plant-Wide Process Monitoring

Multivariate statistical methods have gained significant popularity in past decades. However, process dynamics and insufficient training data usually result in degradation or even failure of a trained model. To deal with these problems, this paper proposes a novel process monitoring method, called cross-spatiotemporal adaptive boosting transfer learning (CS-AdBoostTrLM). Different from the standard methods, CS-AdBoostTrLM has the following advantages: first, source domain (SD) data, which are discarded by the factory, can be re-enabled to alleviate the issue of insufficient training data. Second, cross-spatiotemporal canonical correlation analysis is proposed to achieve the domain adaptation between the SD data and target domain data, so as to overcome the negative transfer. Third, the particle swarm optimization algorithm is used to optimize the local detection model, in such a way that the integrated detection model can converge to the optimality globally. Finally, the data from the wastewater treatment plant and chemical plant are analyzed to demonstrate the effectiveness of the proposed method.

Adaptive Multi-Channel Event Segmentation and Feature Extraction for Monitoring Health Outcomes.

To develop a multi-channel device event segmentation and feature extraction algorithm that is robust to changes in data distribution. We introduce an adaptive transfer learning algorithm to classify and segment events from non-stationary multi-channel temporal data. Using a multivariate hidden Markov model (HMM) and Fisher's linear discriminant analysis (FLDA) the algorithm adaptively adjusts to shifts in distribution over time. The proposed algorithm is unsupervised and learns to label events without requiring a priori information about true event states. The procedure is illustrated on experimental data collected from a cohort in a human viral challenge (HVC) study, where certain subjects have disrupted wake and sleep patterns after exposure to an H1N1 influenza pathogen. Simulations establish that the proposed adaptive algorithm significantly outperforms other event classification methods. When applied to early time points in the HVC data, the algorithm extracts sleep/wake features that are predictive of both infection and infection onset time. The proposed transfer learning event segmentation method is robust to temporal shifts in data distribution and can be used to produce highly discriminative event-labeled features for health monitoring. Our integrated multisensor signal processing and transfer learning method is applicable to many ambulatory monitoring applications.

A Novel Ensemble Adaptive Sparse Bayesian Transfer Learning Machine for Nonlinear Large-Scale Process Monitoring.

Process monitoring plays an important role in ensuring the safety and stable operation of equipment in a large-scale process. This paper proposes a novel data-driven process monitoring framework, termed the ensemble adaptive sparse Bayesian transfer learning machine (EAdspB-TLM), for nonlinear fault diagnosis. The proposed framework has the following advantages: Firstly, the probabilistic relevance vector machine (PrRVM) under Bayesian framework is re-derived so that it can be used to forecast the plant operating conditions. Secondly, we extend the PrRVM method and assimilate transfer learning into the sparse Bayesian learning framework to provide it with the transferring ability. Thirdly, the source domain (SD) data are re-enabled to alleviate the issue of insufficient training data. Finally, the proposed EAdspB-TLM framework was effectively applied to monitor a real wastewater treatment process (WWTP) and a Tennessee Eastman chemical process (TECP). The results further demonstrate that the proposed method is feasible.

Machine learning formation enthalpies of intermetallics

Developing fast and accurate methods to discover intermetallic compounds is relevant for alloy design. While density-functional-theory (DFT)-based methods have accelerated design of binary and ternary alloys by providing rapid access to the energy and properties of the stable intermetallics, they are not amenable for rapidly screening the vast combinatorial space of multi-principal element alloys (MPEAs). Here, a machine-learning model is presented for predicting the formation enthalpy of binary intermetallics and is used to identify new ones. The model uses easily accessible elemental properties as descriptors and has a mean absolute error of 0.025 eV/atom in predicting the formation enthalpy of stable binary intermetallics reported in the Materials Project database. The model further predicts stable intermetallics to form in 112 binary alloy systems that do not have any stable intermetallics reported in the Materials Project database. DFT calculations confirm one such stable intermetallic identified by the model, NbV2, to be on the convex hull. Furthermore, an adaptive transfer learning method is used to generalize the model to predict ternary intermetallics with a similar accuracy as DFT, which suggests that it could be extended to identify compositionally complex intermetallics that may form in MPEAs.

A New Deep Transfer Learning Method for Bearing Fault Diagnosis Under Different Working Conditions

Fault diagnosis is very important for condition based maintenance. Recently, deep learning models are introduced to learn hierarchical representations from raw data instead of using hand-crafted features, which exhibit excellent performance. The success of current deep learning lies in: 1) the training (source domain) and testing (target domain) datasets are from the same feature distribution; 2) Enough labeled data with fault information exist. However, because the machine operates under a non-stationary working condition, the trained model built on the source domain can not be directly applied on the target domain. Moreover, since no sufficient labeled or even unlabeled data are available in target domain, collecting the labeled data and building the model from scratch is time-consuming and expensive. Motivated by transfer learning (TL), we present a new fault diagnosis method, which generalizes convolutional neural network (CNN) to TL scenario. Two layers with regard to task-specific features are adapted in a layer-wise way to regularize the parameters of CNN. What's more, the domain loss is calculated by a linear combination of multiple Gaussian kernels so that the ability of adaptation is enhanced compared to single kernel. Through these two means, the distribution discrepancy is reduced and the transferable features are learned. The proposed method is validated by transfer fault diagnosis experiments. Compared to CNN without domain adaptation and shallow transfer learning methods, the proposed method gets the best performance for fault classification.

An Adaptive Deep Transfer Learning Model for Rumor Detection without Sufficient Identified Rumors

With the extensive usage of social media platforms, spam information, especially rumors, has become a serious problem of social network platforms. The rumors make it difficult for people to get credible information from Internet and cause social panic. Existing detection methods always rely on a large amount of training data. However, the number of the identified rumors is always insufficient for developing a stable detection model. To handle this problem, we proposed a deep transfer model to achieve accurate rumor detection in social media platforms. In detail, an adaptive parameter tuning method is proposed to solve the negative transferring problem in the parameter transferring process. Experiments based on real-world datasets demonstrate that the proposed model achieves more accurate rumor detection and significantly outperforms state-of-the-art rumor detection models.

Analysis and Usage: Subject-to-subject Linear Domain Adaptation in sEMG Classification.

Before the operation of a biosignal-based application, long-duration calibration is required to adjust the pre-trained classifier to a new user data (target data). For reducing such time-consuming step, linear domain adaptation (DA) transfer learning approaches, which transfer pooled data (source data) related to the target data, are highlighted. In the last decade, they have been applied to surface electromyogram (sEMG) data with the implicit assumption that sEMG data are linear. However, sEMGs typically have non-linear characteristics, and due to the discrepancy between the assumption and actual characteristics, linear DA approaches would cause a negative transfer. This study investigated how the correlation between the source and target data affects an 8-class forearm movement classification after applying linear DA approaches. As a result, we found significant positive correlations between the classification accuracy and the source-target correlation. Additionally, the source-target correlation depended on the motion class. Therefore, our results suggest that we should choose a non-linear DA approach when the source-target correlation among subjects or motion classes is low.

Deep feature importance awareness based no-reference image quality prediction

Deep-learning based image quality assessment (IQA) algorithms usually use the transfer learning method that transfers a pre-trained network for classification task to handle IQA task. Although it can overcome the problem of having insufficient IQA databases to some extent, it cannot distinguish between the important and unimportant deep features for the IQA task, which potentially leads to inaccurate prediction performance. In this paper, we propose a no-reference IQA method based on modelling of deep feature importance. A SE-VGG network is developed by using adaptive transfer learning method. It can suppress the features of local parts of salient objects of images that are not important to the IQA task, and emphasize the features of image distortion and salient objects that are important to IQA task. Moreover, the structure of the SE-VGG is investigated to improve the accuracy of the image quality assessment on a small IQA database. Experiments are conducted to evaluate the performance of the proposed method on various databases, including the LIVE, TID2013, CSIQ, LIVE multiply distorted and LIVE challenge. The results show the proposed method significantly outperforms the state-of-the-art methods. In addition, our method demonstrates a strong generalization ability.

Transfer learning from adult to children for speech recognition: Evaluation, analysis and recommendations

Children speech recognition is challenging mainly due to the inherent high variability in children’s physical and articulatory characteristics and expressions. This variability manifests in both acoustic constructs and linguistic usage due to the rapidly changing developmental stage in children’s life. Part of the challenge is due to the lack of large amounts of available children speech data for efficient modeling. This work attempts to address the key challenges using transfer learning from adult’s models to children’s models in a Deep Neural Network (DNN) framework for children’s Automatic Speech Recognition (ASR) task evaluating on multiple children’s speech corpora with a large vocabulary. The paper presents a systematic and an extensive analysis of the proposed transfer learning technique considering the key factors affecting children’s speech recognition from prior literature. Evaluations are presented on (i) comparisons of earlier GMM-HMM and the newer DNN Models, (ii) effectiveness of standard adaptation techniques versus transfer learning, (iii) various adaptation configurations in tackling the variabilities present in children speech, in terms of (a) acoustic spectral variability, and (b) pronunciation variability and linguistic constraints. Our Analysis spans over (i) number of DNN model parameters (for adaptation), (ii) amount of adaptation data, (iii) ages of children, (iv) age dependent-independent adaptation. Finally, we provide Recommendations on (i) the favorable strategies over various aforementioned - analyzed parameters, and (ii) potential future research directions and relevant challenges/problems persisting in DNN based ASR for children’s speech.

Sample generation method based on GAN and adaptive transfer learning

Sample generation method based on GAN and adaptive transfer learning

基于双模态卷积神经网络自适应迁移学习的浮选工况识别

基于双模态卷积神经网络自适应迁移学习的浮选工况识别

Cross-Dataset Activity Recognition via Adaptive Spatial-Temporal Transfer Learning

Human activity recognition (HAR) aims at recognizing activities by training models on the large quantity of sensor data. Since it is time-consuming and expensive to acquire abundant labeled data, transfer learning becomes necessary for HAR by transferring knowledge from existing domains. However, there are two challenges existing in cross-dataset activity recognition. The first challenge is source domain selection. Given a target task and several available source domains, it is difficult to determine how to select the most similar source domain to the target domain such that negative transfer can be avoided. The second one is accurately activity transfer. After source domain selection, how to achieve accurate knowledge transfer between the selected source and the target domain remains another challenge. In this paper, we propose an Adaptive Spatial-Temporal Transfer Learning (ASTTL) approach to tackle both of the above two challenges in cross-dataset HAR. ASTTL learns the spatial features in transfer learning by adaptively evaluating the relative importance between the marginal and conditional probability distributions. Besides, it captures the temporal features via incremental manifold learning. Therefore, ASTTL can learn the adaptive spatial-temporal features for cross-dataset HAR and can be used for both source domain selection and accurate activity transfer. We evaluate the performance of ASTTL through extensive experiments on 4 public HAR datasets, which demonstrates its effectiveness. Furthermore, based on ASTTL, we design and implement an adaptive cross-dataset HAR system called Client-Cloud Collaborative Adaptive Activity Recognition System (3C2ARS) to perform HAR in the real environment. By collecting activities in the smartphone and transferring knowledge in the cloud server, ASTTL can significantly improve the performance of source domain selection and accurate activity transfer.

An adaptive deep transfer learning method for bearing fault diagnosis

Bearing fault diagnosis has made some achievements based on massive labeled fault data. In practical engineering, machines are mostly in healthy and faults seldom happen, it’s difficult or expensive to collect massive labeled fault data. To solve the problem, an adaptive deep transfer learning method for bearing fault diagnosis is proposed in this paper. Firstly, a long-short term memory recurrent neural network model based on instance-transfer learning is constructed to generate some auxiliary datasets. Secondly, joint distribution adaptation, a feature-transfer learning method, which is used to reduce the differences in probability distributions between an auxiliary dataset and target domain dataset. Finally, grey wolf optimization algorithm is introduced to adaptively learn key parameters of joint distribution adaptation. The proposed method is verified with two kinds of datasets, and the results demonstrate the effectiveness and robustness of the proposed method when the labeled fault data are scarce.