scholarly journals Instance Transfer Learning with Multisource Dynamic TrAdaBoost

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Qian Zhang ◽  
Haigang Li ◽  
Yong Zhang ◽  
Ming Li
Keyword(s):  
Transfer Learning ◽  
Classification Accuracy ◽  
Negative Transfer ◽  
Traditional Learning ◽  
Dynamic Factor ◽  
Similar Distribution ◽  
Target Domain ◽  
Learning Tasks ◽  
Sample Data ◽  
Better Than

Since the transfer learning can employ knowledge in relative domains to help the learning tasks in current target domain, compared with the traditional learning it shows the advantages of reducing the learning cost and improving the learning efficiency. Focused on the situation that sample data from the transfer source domain and the target domain have similar distribution, an instance transfer learning method based on multisource dynamic TrAdaBoost is proposed in this paper. In this method, knowledge from multiple source domains is used well to avoid negative transfer; furthermore, the information that is conducive to target task learning is obtained to train candidate classifiers. The theoretical analysis suggests that the proposed algorithm improves the capability that weight entropy drifts from source to target instances by means of adding the dynamic factor, and the classification effectiveness is better than single source transfer. Finally, experimental results show that the proposed algorithm has higher classification accuracy.

scholarly journals Enhanced Regional Monitoring of Wheat Powdery Mildew Based on an Instance-Based Transfer Learning Method

2019 ◽  
Vol 11 (3) ◽  
pp. 298 ◽  
Author(s):  
Linyi Liu ◽  
Yingying Dong ◽  
Wenjiang Huang ◽  
Xiaoping Du ◽  
Juhua Luo ◽  
...  
Keyword(s):  
Powdery Mildew ◽  
Transfer Learning ◽  
Kappa Coefficient ◽  
Learning Method ◽  
Training Process ◽  
Wheat Powdery Mildew ◽  
Field Samples ◽  
Monitoring Accuracy ◽  
Sample Data ◽  
Better Than

In order to monitor the prevalence of wheat powdery mildew, current methods require sufficient sample data to obtain results with higher accuracy and stable validation. However, it is difficult to collect data on wheat powdery mildew in some regions, and this limitation in sampling restricts the accuracy of monitoring regional prevalence of the disease. In this study, an instance-based transfer learning method, i.e., TrAdaBoost, was applied to improve the monitoring accuracy with limited field samples by using auxiliary samples from another region. By taking into account the representativeness of contributions of auxiliary samples to adjust the weight placed on auxiliary samples, an optimized TrAdaBoost algorithm, named OpTrAdaBoost, was generated to map regional wheat powdery mildew. The algorithm conducts this by: (1) producing uncertainty associated with each prediction based on the similarities, and calculating the representativeness contribution of all auxiliary samples by taking into account the overall uncertainty of the wheat powdery mildew map; (2) calculating the errors of the weak learners during the training process and using boosting to filter out the unreliable auxiliary samples by adjusting the weights of auxiliary samples; (3) combining all weak learners according to the weights of training instances to build a strong learner to classify disease severity. OpTrAdaBoost was tested using a dataset with 39 study area samples and 106 auxiliary samples. The overall monitoring accuracy was 82%, and the kappa coefficient was 0.72. Moreover, OpTrAdaBoost performed better than other algorithms that are commonly used to monitor wheat powdery mildew at the regional level. Experimental results demonstrated that OpTrAdaBoost was effective in improving the accuracy of monitoring wheat powdery mildew using limited field samples.

scholarly journals A Suppression Method of Concentration Background Noise by Transductive Transfer Learning for a Metal Oxide Semiconductor-Based Electronic Nose

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 1913
Author(s):  
Huixiang Liu ◽  
Qing Li ◽  
Zhiyong Li ◽  
Yu Gu
Keyword(s):  
Transfer Learning ◽  
Environmental Changes ◽  
Oxide Semiconductor ◽  
Target Domain ◽  
Fisher Linear Discriminant ◽  
Linear Discriminant ◽  
Signal Features ◽  
Changes Over Time ◽  
Independence Criterion ◽  
Better Than

Signal drift caused by sensors or environmental changes, which can be regarded as data distribution changes over time, is related to transductive transfer learning, and the data in the target domain is not labeled. We propose a method that learns a subspace with maximum independence of the concentration features (MICF) according to the Hilbert-Schmidt Independence Criterion (HSIC), which reduces the inter-concentration discrepancy of distributions. Then, we use Iterative Fisher Linear Discriminant (IFLD) to extract the signal features by reducing the divergence within classes and increasing the divergence among classes, which helps to prevent inconsistent ratios of different types of samples among the domains. The effectiveness of MICF and IFLD was verified by three sets of experiments using sensors in real world conditions, along with experiments conducted in the authors’ laboratory. The proposed method achieved an accuracy of 76.17%, which was better than any of the existing methods that publish their data on a publicly available dataset (the Gas Sensor Drift Dataset). It was found that the MICF-IFLD was simple and effective, reduced interferences, and deftly managed tasks of transfer classification.

scholarly journals Autoencoder-based transfer learning in brain–computer interface for rehabilitation robot

2019 ◽  
Vol 16 (2) ◽  
pp. 172988141984086 ◽  
Author(s):  
Chuanqi Tan ◽  
Fuchun Sun ◽  
Bin Fang ◽  
Tao Kong ◽  
Wenchang Zhang
Keyword(s):  
Transfer Learning ◽  
Negative Transfer ◽  
Brain Computer Interface ◽  
Training Data ◽  
Computer Interface ◽  
Rehabilitation Robot ◽  
Target Domain ◽  
Source Domain ◽  
Adversarial Network ◽  
The Brain

The brain–computer interface-based rehabilitation robot has quickly become a very important research area due to its natural interaction. One of the most important problems in brain–computer interface is that large-scale annotated electroencephalography data sets required by advanced classifiers are almost impossible to acquire because biological data acquisition is challenging and quality annotation is costly. Transfer learning relaxes the hypothesis that the training data must be independent and identically distributed with the test data. It can be considered a powerful tool for solving the problem of insufficient training data. There are two basic issues with transfer learning, under transfer and negative transfer. We proposed a novel brain–computer interface framework by using autoencoder-based transfer learning, which includes three main components: an autoencoder framework, a joint adversarial network, and a regularized manifold constraint. The autoencoder framework automatically encodes and reconstructs data from source and target domains and forces the neural network to learn to represent these domains reliably. The joint adversarial network aims to force the network to learn to encode more appropriately for the source domain and target domain simultaneously, thereby overcoming the problem of under transfer. The regularized manifold constraint aims to avoid the problem of negative transfer by avoiding geometric manifold structure in the target domain being destroyed by the source domain. Experiments show that the brain–computer interface framework proposed by us can achieve better results than state-of-the-art approaches in electroencephalography signal classification tasks. This is helpful in aiding our rehabilitation robot to understand the intention of patients and can help patients to carry out rehabilitation exercises effectively.

scholarly journals Sentiment Classification for Financial Texts Based on Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Shanshan Dong ◽  
Chang Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Transfer Learning ◽  
Loss Function ◽  
Classification Accuracy ◽  
Sentiment Classification ◽  
Target Domain ◽  
Text Data ◽  
Source Domain ◽  
Cross Domain

Sentiment classification for financial texts is of great importance for predicting stock markets and financial crises. At present, with the popularity of applications in the field of natural language processing (NLP) adopting deep learning, the application of automatic text classification and text-based sentiment classification has become more and more extensive. However, in the field of financial text-based sentiment classification, due to a lack of labeled samples, such applications are limited. A domain-adaptation-based financial text sentiment classification method is proposed in this paper, which can adopt source domain (SD) text data with sentiment labels and a large amount of unlabeled target domain (TD) financial text data as training samples for the proposed neural network. The proposed method is a cross-domain transfer-learning-based method. The domain classification subnetwork is added to the original neural network, and the domain classification loss function is also added to the original training loss function. Therefore, the network can simultaneously adapt to the target domain and then accomplish the classification task. The experiment of the proposed sentiment classification transfer learning method is carried out through an open-source dataset. The proposed method in this paper uses the reviews of Amazon Books, DVDs, electronics, and kitchen appliances as the source domain for cross-domain learning, and the classification accuracy rates can reach 65.0%, 61.2%, 61.6%, and 66.3%, respectively. Compared with nontransfer learning, the classification accuracy rate has improved by 11.0%, 7.6%, 11.4%, and 13.4%, respectively.

scholarly journals Session to Session Transfer Learning Method Using Independent Component Analysis with Regularized Common Spatial Patterns for EEG-MI Signals

2019 ◽  
Vol 15 (1) ◽  
pp. 13-27
Author(s):  
Zaineb Alhakeem ◽  
Ramzy Ali
Keyword(s):  
Independent Component Analysis ◽  
Transfer Learning ◽  
Classification Accuracy ◽  
Component Analysis ◽  
Independent Component ◽  
Learning Method ◽  
Common Spatial Pattern ◽  
Brain Signals ◽  
The Brain ◽  
Better Than

Training the user in Brain-Computer Interface (BCI) systems based on brain signals that recorded using Electroencephalography Motor Imagery (EEG-MI) signal is a time-consuming process and causes tiredness to the trained subject, so transfer learning (subject to subject or session to session) is very useful methods of training that will decrease the number of recorded training trials for the target subject. To record the brain signals, channels or electrodes are used. Increasing channels could increase the classification accuracy but this solution costs a lot of money and there are no guarantees of high classification accuracy. This paper introduces a transfer learning method using only two channels and a few training trials for both feature extraction and classifier training. Our results show that the proposed method Independent Component Analysis with Regularized Common Spatial Pattern (ICA-RCSP) will produce about 70% accuracy for the session to session transfer learning using few training trails. When the proposed method used for transfer subject to subject the accuracy was lower than that for session to session but it still better than other methods.

scholarly journals Phase Transitions in Transfer Learning for High-Dimensional Perceptrons

Entropy ◽  
2021 ◽  
Vol 23 (4) ◽  
pp. 400
Author(s):  
Oussama Dhifallah ◽  
Yue M. Lu
Keyword(s):  
Phase Transition ◽  
Phase Transitions ◽  
Transfer Learning ◽  
Negative Transfer ◽  
High Dimensional ◽  
Source Information ◽  
Generalization Performance ◽  
Target Task ◽  
Learning Tasks ◽  
Perceptron Learning

Transfer learning seeks to improve the generalization performance of a target task by exploiting the knowledge learned from a related source task. Central questions include deciding what information one should transfer and when transfer can be beneficial. The latter question is related to the so-called negative transfer phenomenon, where the transferred source information actually reduces the generalization performance of the target task. This happens when the two tasks are sufficiently dissimilar. In this paper, we present a theoretical analysis of transfer learning by studying a pair of related perceptron learning tasks. Despite the simplicity of our model, it reproduces several key phenomena observed in practice. Specifically, our asymptotic analysis reveals a phase transition from negative transfer to positive transfer as the similarity of the two tasks moves past a well-defined threshold.

scholarly journals General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer

2017 ◽  
Author(s):  
Yong Luo ◽  
Yonggang Wen ◽  
Tongliang Liu ◽  
Dacheng Tao
Keyword(s):  
Transfer Learning ◽  
Metric Learning ◽  
Learning Task ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Target Domain ◽  
Feature Representations ◽  
Transfer Distance ◽  
Learning Tasks ◽  
Feature Spaces

Transfer learning aims to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. Recently, transfer distance metric learning (TDML) has attracted lots of interests, but most of these methods assume that feature representations for the source and target learning tasks are the same. Hence, they are not suitable for the applications, in which the data are from heterogeneous domains (feature spaces, modalities and even semantics). Although some existing heterogeneous transfer learning (HTL) approaches is able to handle such domains, they lack flexibility in real-world applications, and the learned transformations are often restricted to be linear. We therefore develop a general and flexible heterogeneous TDML (HTDML) framework based on the knowledge fragment transfer strategy. In the proposed HTDML, any (linear or nonlinear) distance metric learning algorithms can be employed to learn the source metric beforehand. Then a set of knowledge fragments are extracted from the pre-learned source metric to help target metric learning. In addition, either linear or nonlinear distance metric can be learned for the target domain. Extensive experiments on both scene classification and object recognition demonstrate superiority of the proposed method.

scholarly journals Transfer Learning for LiDAR-Based Lane Marking Detection and Intensity Profile Generation

Geomatics ◽  
2021 ◽  
Vol 1 (2) ◽  
pp. 287-309
Author(s):  
Ankit Patel ◽  
Yi-Ting Cheng ◽  
Radhika Ravi ◽  
Yi-Chun Lin ◽  
Darcy Bullock ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Fine Tuning ◽  
Target Domain ◽  
Independent Dataset ◽  
Lane Marking ◽  
Intensity Information ◽  
Training Examples ◽  
Learning Frameworks ◽  
Mobile Mapping Systems ◽  
Better Than

Recently, light detection and ranging (LiDAR)-based mobile mapping systems (MMS) have been utilized for extracting lane markings using deep learning frameworks. However, huge datasets are required for training neural networks. Furthermore, with accurate lane markings being detected utilizing LiDAR data, an algorithm for automatically reporting their intensity information is beneficial for identifying worn-out or missing lane markings. In this paper, a transfer learning approach based on fine-tuning of a pretrained U-net model for lane marking extraction and a strategy for generating intensity profiles using the extracted results are presented. Starting from a pretrained model, a new model can be trained better and faster to make predictions on a target domain dataset with only a few training examples. An original U-net model trained on two-lane highways (source domain dataset) was fine-tuned to make accurate predictions on datasets with one-lane highway patterns (target domain dataset). Specifically, encoder- and decoder-trained U-net models are presented wherein, during retraining of the former, only weights in the encoder path of U-net were allowed to change with decoder weights frozen and vice versa for the latter. On the test data (target domain), the encoder-trained model (F1-score: 86.9%) outperformed the decoder-trained (F1-score: 82.1%). Additionally, on an independent dataset, the encoder-trained one (F1-score: 90.1%) performed better than the decoder-trained one (F1-score: 83.2%). Lastly, on the basis of lane marking results obtained from the encoder-trained U-net, intensity profiles were generated. Such profiles can be used to identify lane marking gaps and investigate their cause through RGB imagery visualization.

scholarly journals Deep Transfer Learning in Diagnosing Leukemia in Blood Cells

Computers ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 29 ◽  
Author(s):  
Mohamed Loey ◽  
Mukdad Naman ◽  
Hala Zayed
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Blood Cells ◽  
Classification Accuracy ◽  
Automated Classification ◽  
Classification Models ◽  
Fatal Disease ◽  
Microscopic Images ◽  
Traditional Approaches ◽  
Better Than

Leukemia is a fatal disease that threatens the lives of many patients. Early detection can effectively improve its rate of remission. This paper proposes two automated classification models based on blood microscopic images to detect leukemia by employing transfer learning, rather than traditional approaches that have several disadvantages. In the first model, blood microscopic images are pre-processed; then, features are extracted by a pre-trained deep convolutional neural network named AlexNet, which makes classifications according to numerous well-known classifiers. In the second model, after pre-processing the images, AlexNet is fine-tuned for both feature extraction and classification. Experiments were conducted on a dataset consisting of 2820 images confirming that the second model performs better than the first because of 100% classification accuracy.

scholarly journals Enhancing Histopathological Colorectal Cancer Image Classification by using Convolutional Neural Network

2021 ◽  
Author(s):  
Radwan Al.Shawesh ◽  
Yi Xiang Chen
Keyword(s):  
Colorectal Cancer ◽  
Transfer Learning ◽  
Classification Accuracy ◽  
Validation Dataset ◽  
Data Sets ◽  
Classification Methods ◽  
Tumor Diseases ◽  
Histopathological Images ◽  
Death Causes ◽  
Better Than

AbstractColorectal cancer (CRC) also known as bowl cancer is one of the leading death causes worldwide. Early diagnosis has become vital for a successful treatment. Now days with the new advancements in Convolutional Neural networks (CNNs) it’s possible to classify different images of CRC into different classes. Today It is crucial for physician to take advantage of the new advancement’s in deep learning, since classification methods are becoming more and more accurate and efficient. In this study, we introduce a method to improve the classification accuracy from previous studies that used the National Center for Tumor diseases (NCT) data sets. We adapt the ResNet-50 model in our experiment to classify the CRC histopathological images. Furthermore, we utilize transfer learning and fine-tunning techniques to improve the accuracy. Our Experiment results show that ResNet_50 network is the best CNN architecture so far for classifying CRC histopathological images on the NCT Biobank open source dataset. In addition to that using transfer learning allow us to obtain 97.7% accuracy on the validation dataset, which is better than all previous results we found in literature.

Sign in / Sign up

Export Citation Format

Share Document