scholarly journals A Domain-Independent Ontology Learning Method Based on Transfer Learning

Electronics ◽  
2021 ◽  
Vol 10 (16) ◽  
pp. 1911
Author(s):  
Kai Xie ◽  
Chao Wang ◽  
Peng Wang
Keyword(s):  
Transfer Learning ◽  
Language Processing ◽  
Critical Role ◽  
Parameters Estimation ◽  
Learning Performance ◽  
Machine Learning Techniques ◽  
Learning Method ◽  
Ontology Learning ◽  
Target Domain ◽  
Real World Datasets

Ontology plays a critical role in knowledge engineering and knowledge graphs (KGs). However, building ontology is still a nontrivial task. Ontology learning aims at generating domain ontologies from various kinds of resources by natural language processing and machine learning techniques. One major challenge of ontology learning is reducing labeling work for new domains. This paper proposes an ontology learning method based on transfer learning, namely TF-Mnt, which aims at learning knowledge from new domains that have limited labeled data. This paper selects Web data as the learning source and defines various features, which utilizes abundant textual information and heterogeneous semi-structured information. Then, a new transfer learning model TF-Mnt is proposed, and the parameters’ estimation is also addressed. Although there exist distribution differences of features between two domains, TF-Mnt can measure the relevance by calculating the correlation coefficient. Moreover, TF-Mnt can efficiently transfer knowledge from the source domain to the target domain and avoid negative transfer. Experiments in real-world datasets show that TF-Mnt achieves promising learning performance for new domains despite the small number of labels in it, by learning knowledge from a proper existing domain which can be automatically selected.

scholarly journals Experimental Evaluation of PSO Based Transfer Learning Method for Meteorological Visibility Estimation

Atmosphere ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 828
Author(s):  
Wai Lun Lo ◽  
Henry Shu Hung Chung ◽  
Hong Fu
Keyword(s):  
Transfer Learning ◽  
Experimental Evaluation ◽  
Estimation Method ◽  
Image Features ◽  
Parameters Estimation ◽  
Image Feature ◽  
Support Vector ◽  
Learning Method ◽  
Feature Vectors ◽  
Visibility Estimation

Estimation of Meteorological visibility from image characteristics is a challenging problem in the research of meteorological parameters estimation. Meteorological visibility can be used to indicate the weather transparency and this indicator is important for transport safety. This paper summarizes the outcomes of the experimental evaluation of a Particle Swarm Optimization (PSO) based transfer learning method for meteorological visibility estimation method. This paper proposes a modified approach of the transfer learning method for visibility estimation by using PSO feature selection. Image data are collected at fixed location with fixed viewing angle. The database images were gone through a pre-processing step of gray-averaging so as to provide information of static landmark objects for automatic extraction of effective regions from images. Effective regions are then extracted from image database and the image features are then extracted from the Neural Network. Subset of Image features are selected based on the Particle Swarming Optimization (PSO) methods to obtain the image feature vectors for each effective sub-region. The image feature vectors are then used to estimate the visibilities of the images by using the Multiple Support Vector Regression (SVR) models. Experimental results show that the proposed method can give an accuracy more than 90% for visibility estimation and the proposed method is effective and robust.

scholarly journals Deep Transfer Learning Method Based on 1D-CNN for Bearing Fault Diagnosis

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Jun He ◽  
Xiang Li ◽  
Yong Chen ◽  
Danfeng Chen ◽  
Jing Guo ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Learning Method ◽  
Target Domain ◽  
Source Domain ◽  
Second Order Statistics ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis

In mechanical fault diagnosis, it is impossible to collect massive labeled samples with the same distribution in real industry. Transfer learning, a promising method, is usually used to address the critical problem. However, as the number of samples increases, the interdomain distribution discrepancy measurement of the existing method has a higher computational complexity, which may make the generalization ability of the method worse. To solve the problem, we propose a deep transfer learning method based on 1D-CNN for rolling bearing fault diagnosis. First, 1-dimension convolutional neural network (1D-CNN), as the basic framework, is used to extract features from vibration signal. The CORrelation ALignment (CORAL) is employed to minimize marginal distribution discrepancy between the source domain and target domain. Then, the cross-entropy loss function and Adam optimizer are used to minimize the classification errors and the second-order statistics of feature distance between the source domain and target domain, respectively. Finally, based on the bearing datasets of Case Western Reserve University and Jiangnan University, seven transfer fault diagnosis comparison experiments are carried out. The results show that our method has better performance.

scholarly journals Understanding How Feature Structure Transfers in Transfer Learning

2017 ◽  
Author(s):  
Tongliang Liu ◽  
Qiang Yang ◽  
Dacheng Tao
Keyword(s):  
Transfer Learning ◽  
Domain Adaptation ◽  
Common Knowledge ◽  
Learning Performance ◽  
Learning To Learn ◽  
Target Domain ◽  
Feature Structure ◽  
Analysis Scheme ◽  
Feature Structures ◽  
Regularization Matrix

Transfer learning transfers knowledge across domains to improve the learning performance. Since feature structures generally represent the common knowledge across different domains, they can be transferred successfully even though the labeling functions across domains differ arbitrarily. However, theoretical justification for this success has remained elusive. In this paper, motivated by self-taught learning, we regard a set of bases as a feature structure of a domain if the bases can (approximately) reconstruct any observation in this domain. We propose a general analysis scheme to theoretically justify that if the source and target domains share similar feature structures, the source domain feature structure is transferable to the target domain, regardless of the change of the labeling functions across domains. The transferred structure is interpreted to function as a regularization matrix which benefits the learning process of the target domain task. We prove that such transfer enables the corresponding learning algorithms to be uniformly stable. Specifically, we illustrate the existence of feature structure transfer in two well-known transfer learning settings: domain adaptation and learning to learn.

scholarly journals A Novel Method of Hyperspectral Data Classification Based on Transfer Learning and Deep Belief Network

2019 ◽  
Vol 9 (7) ◽  
pp. 1379 ◽  
Author(s):  
Ke Li ◽  
Mingju Wang ◽  
Yixin Liu ◽  
Nan Yu ◽  
Wei Lan
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Spatial Information ◽  
Hyperspectral Data ◽  
Deep Belief Network ◽  
Learning Method ◽  
Target Domain ◽  
Data Set ◽  
Belief Network ◽  
Target Data

The classification of hyperspectral data using deep learning methods can obtain better results than the previous shallow classifiers, but deep learning algorithms have some limitations. These algorithms require a large amount of data to train the network, while also needing a certain amount of labeled data to fine-tune the network. In this paper, we propose a new hyperspectral data processing method based on transfer learning and the deep learning method. First, we use a hyperspectral data set that is similar to the target data set to pre-train the deep learning network. Then, we use the transfer learning method to find the common features of the source domain data and target domain data. Second, we propose a model structure that combines the deep transfer learning model to utilize a combination of spatial information and spectral information. Using transfer learning, we can obtain the spectral features. Then, we obtain several principal components of the target data. These will be regarded as the spatial features of the target domain data, and we use the joint features for the classifier. The data are obtained from a hyperspectral public database. Using the same amount of data, our method based on transfer learning and deep belief network obtains better classification accuracy in a shorter amount of time.

scholarly journals Inductive and Transductive Transfer Learning for Zero-day Attack Detection

2019 ◽  
Vol 8 (11) ◽  
pp. 1765-1768
Keyword(s):  
Transfer Learning ◽  
Domain Adaptation ◽  
Attack Detection ◽  
Supervised Machine Learning ◽  
Intrusion Detection Systems ◽  
Machine Learning Techniques ◽  
Target Domain ◽  
Detection Systems ◽  
Learning Techniques ◽  
Manifold Alignment

Upon application of supervised machine learning techniques Intrusion Detection Systems (IDSs) are successful in detecting known attacks as they use predefined attack signatures. However, detecting zero-day attacks is challenged because of the scarcity of the labeled instances for zero-day attacks. Advanced research on IDS applies the concept of Transfer Learning (TL) to compensate the scarcity of labeled instances of zero-day attacks by making use of abundant labeled instances present in related domain(s). This paper explores the potential of Inductive and Transductive transfer learning for detecting zero-day attacks experimentally, where inductive TL deals with the presence of minimal labeled instances in the target domain and transductive TL deals with the complete absence of labeled instances in the target domain. The concept of domain adaptation with manifold alignment (DAMA) is applied in inductive TL where the variant of DAMA is proposed to handle transductive TL due to non-availability of labeled instances. NSL_KDD dataset is used for experimentation

scholarly journals Knowledge Graph-Based Image Recognition Transfer Learning Method for On-Orbit Service Manipulation

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Ao Chen ◽  
Yongchun Xie ◽  
Yong Wang ◽  
Linfeng Li
Keyword(s):  
Visual Perception ◽  
Transfer Learning ◽  
Image Recognition ◽  
Training Data ◽  
Training Dataset ◽  
Knowledge Graph ◽  
Learning Method ◽  
Target Domain ◽  
Space Images ◽  
Average Recall

Visual perception provides state information of current manipulation scene for control system, which plays an important role in on-orbit service manipulation. With the development of deep learning, deep convolutional neural networks (CNNs) have achieved many successful applications in the field of visual perception. Deep CNNs are only effective for the application condition containing a large number of training data with the same distribution as the test data; however, real space images are difficult to obtain during large-scale training. Therefore, deep CNNs can not be directly adopted for image recognition in the task of on-orbit service manipulation. In order to solve the problem of few-shot learning mentioned above, this paper proposes a knowledge graph-based image recognition transfer learning method (KGTL), which learns from training dataset containing dense source domain data and sparse target domain data, and can be transferred to the test dataset containing large number of data collected from target domain. The average recognition precision of the proposed method is 80.5%, and the average recall is 83.5%, which is higher than that of ResNet50-FC; the average precision is 60.2%, and the average recall is 67.5%. The proposed method significantly improves the training efficiency of the network and the generalization performance of the model.

scholarly journals Syntax-based transfer learning for the task of biomedical relation extraction

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Joël Legrand ◽  
Yannick Toussaint ◽  
Chedy Raïssi ◽  
Adrien Coulet
Keyword(s):  
Transfer Learning ◽  
Language Processing ◽  
Domain Adaptation ◽  
Relation Extraction ◽  
Training Data ◽  
Learning Performance ◽  
Promising Alternative ◽  
Syntactic Features ◽  
The Impact ◽  
Biomedical Relation Extraction

Abstract Background Transfer learning aims at enhancing machine learning performance on a problem by reusing labeled data originally designed for a related, but distinct problem. In particular, domain adaptation consists for a specific task, in reusing training data developedfor the same task but a distinct domain. This is particularly relevant to the applications of deep learning in Natural Language Processing, because they usually require large annotated corpora that may not exist for the targeted domain, but exist for side domains. Results In this paper, we experiment with transfer learning for the task of relation extraction from biomedical texts, using the TreeLSTM model. We empirically show the impact of TreeLSTM alone and with domain adaptation by obtaining better performances than the state of the art on two biomedical relation extraction tasks and equal performances for two others, for which little annotated data are available. Furthermore, we propose an analysis of the role that syntactic features may play in transfer learning for relation extraction. Conclusion Given the difficulty to manually annotate corpora in the biomedical domain, the proposed transfer learning method offers a promising alternative to achieve good relation extraction performances for domains associated with scarce resources. Also, our analysis illustrates the importance that syntax plays in transfer learning, underlying the importance in this domain to privilege approaches that embed syntactic features.

scholarly journals An Unknown Radar Emitter Identification Method Based on Semi-Supervised and Transfer Learning

Algorithms ◽  
2019 ◽  
Vol 12 (12) ◽  
pp. 271 ◽  
Author(s):  
Yuntian Feng ◽  
Guoliang Wang ◽  
Zhipeng Liu ◽  
Runming Feng ◽  
Xiang Chen ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Training Data ◽  
Identification Accuracy ◽  
Support Vector ◽  
Learning Method ◽  
Target Domain ◽  
Identification Method ◽  
Svm Model ◽  
Testing Data ◽  
Task Simulation

Aiming at the current problem that it is difficult to deal with an unknown radar emitter in the radar emitter identification process, we propose an unknown radar emitter identification method based on semi-supervised and transfer learning. Firstly, we construct the support vector machine (SVM) model based on transfer learning, using the information of labeled samples in the source domain to train in the target domain, which can solve the problem that the training data and the testing data do not satisfy the same-distribution hypothesis. Then, we design a semi-supervised co-training algorithm using the information of unlabeled samples to enhance the training effect, which can solve the problem that insufficient labeled data results in inadequate training of the classifier. Finally, we combine the transfer learning method with the semi-supervised learning method for the unknown radar emitter identification task. Simulation experiments show that the proposed method can effectively identify an unknown radar emitter and still maintain high identification accuracy within a certain measurement error range.

scholarly journals A Novel Deep Forest-Based Active Transfer Learning Method for PolSAR Images

2020 ◽  
Vol 12 (17) ◽  
pp. 2755
Author(s):  
Xingli Qin ◽  
Jie Yang ◽  
Lingli Zhao ◽  
Pingxiang Li ◽  
Kaimin Sun
Keyword(s):  
Active Learning ◽  
Transfer Learning ◽  
Main Idea ◽  
Representation Learning ◽  
Learning Method ◽  
Target Domain ◽  
Forest Model ◽  
Training Samples ◽  
Deep Forest ◽  
Active Transfer

The information extraction of polarimetric synthetic aperture radar (PolSAR) images typically requires a great number of training samples; however, the training samples from historical images are less reusable due to the distribution differences. Consequently, there is a significant manual cost to collecting training samples when processing new images. In this paper, to address this problem, we propose a novel active transfer learning method, which combines active learning and the deep forest model to perform transfer learning. The main idea of the proposed method is to gradually improve the performance of the model in target domain tasks with the increase of the levels of the cascade structure. More specifically, in the growing stage, a new active learning strategy is used to iteratively add the most informative target domain samples to the training set, and the augmented features generated by the representation learning capability of the deep forest model are used to improve the cross-domain representational capabilities of the feature space. In the filtering stage, an effective stopping criterion is used to adaptively control the complexity of the model, and two filtering strategies are used to accelerate the convergence of the model. We conducted experiments using three sets of PolSAR images, and the results were compared with those of four existing transfer learning algorithms. Overall, the experimental results fully demonstrated the effectiveness and robustness of the proposed method.

scholarly journals Heterogeneous Transfer Learning with Weighted Instance-Correspondence Data

2020 ◽  
Vol 34 (04) ◽  
pp. 4099-4106
Author(s):  
Yuwei He ◽  
Xiaoming Jin ◽  
Guiguang Ding ◽  
Yuchen Guo ◽  
Jungong Han ◽  
...  
Keyword(s):  
Transfer Learning ◽  
State Of The Art ◽  
Learning Method ◽  
Target Domain ◽  
High Quality ◽  
Source Domain ◽  
Data Generator ◽  
Data Pair ◽  
Quality Variation

Instance-correspondence (IC) data are potent resources for heterogeneous transfer learning (HeTL) due to the capability of bridging the source and the target domains at the instance-level. To this end, people tend to use machine-generated IC data, because manually establishing IC data is expensive and primitive. However, existing IC data machine generators are not perfect and always produce the data that are not of high quality, thus hampering the performance of domain adaption. In this paper, instead of improving the IC data generator, which might not be an optimal way, we accept the fact that data quality variation does exist but find a better way to use the data. Specifically, we propose a novel heterogeneous transfer learning method named Transfer Learning with Weighted Correspondence (TLWC), which utilizes IC data to adapt the source domain to the target domain. Rather than treating IC data equally, TLWC can assign solid weights to each IC data pair depending on the quality of the data. We conduct extensive experiments on HeTL datasets and the state-of-the-art results verify the effectiveness of TLWC.

Sign in / Sign up

Export Citation Format

Share Document