A Transfer-Learning Approach to Feature Extraction from Cancer Transcriptomes with Deep Autoencoders

Model fine-tuning is a widely used transfer learning approach in person Re-identification (ReID) applications, which fine-tuning a pre-trained feature extraction model into the target scenario instead of training a model from scratch. It is challenging due to the significant variations inside the target scenario, e.g., different camera viewpoint, illumination changes, and occlusion. These variations result in a gap between the distribution of each mini-batch and the distribution of the whole dataset when using mini-batch training. In this paper, we study model fine-tuning from the perspective of the aggregation and utilization of the global information of the dataset when using mini-batch training. Specifically, we introduce a novel network structure called Batch-related Convolutional Cell (BConv-Cell), which progressively collects the global information of the dataset into a latent state and uses this latent state to rectify the extracted feature. Based on BConv-Cells, we further proposed the Progressive Transfer Learning (PTL) method to facilitate the model fine-tuning process by joint training the BConv-Cells and the pre-trained ReID model. Empirical experiments show that our proposal can improve the performance of the ReID model greatly on MSMT17, Market-1501, CUHK03 and DukeMTMC-reID datasets. The code will be released later on at \url{https://github.com/ZJULearning/PTL}

Download Full-text

Classification of Neurodegenerative Diseases Based on VGG 19 Deep Transfer Learning Architecture: A Deep Learning Approach

Bioscience Biotechnology Research Communications ◽

10.21786/bbrc/13.4/51 ◽

2020 ◽

Vol 13 (4) ◽

pp. 1972-1980

Author(s):

Kirti Raj Bhatele

Keyword(s):

Deep Learning ◽

Neurodegenerative Diseases ◽

Transfer Learning ◽

Learning Approach

Download Full-text

An Efficient Radio Frequency Interference (RFI) Recognition and Characterization Using End-to-End Transfer Learning

Applied Sciences ◽

10.3390/app10196885 ◽

2020 ◽

Vol 10 (19) ◽

pp. 6885

Author(s):

Sahar Ujan ◽

Neda Navidi ◽

Rene Jr Landry

Keyword(s):

Feature Extraction ◽

Radio Frequency ◽

Transfer Learning ◽

Communication Networks ◽

Continuous Wave ◽

Critical Role ◽

Video Stream ◽

Radio Frequency Interference ◽

Wave Interference ◽

Continuous Wave Interference

Radio Frequency Interference (RFI) detection and characterization play a critical role in ensuring the security of all wireless communication networks. Advances in Machine Learning (ML) have led to the deployment of many robust techniques dealing with various types of RFI. To sidestep an unavoidable complicated feature extraction step in ML, we propose an efficient Deep Learning (DL)-based methodology using transfer learning to determine both the type of received signals and their modulation type. To this end, the scalogram of the received signals is used as the input of the pretrained convolutional neural networks (CNN), followed by a fully-connected classifier. This study considers a digital video stream as the signal of interest (SoI), transmitted in a real-time satellite-to-ground communication using DVB-S2 standards. To create the RFI dataset, the SoI is combined with three well-known jammers namely, continuous-wave interference (CWI), multi- continuous-wave interference (MCWI), and chirp interference (CI). This study investigated four well-known pretrained CNN architectures, namely, AlexNet, VGG-16, GoogleNet, and ResNet-18, for the feature extraction to recognize the visual RFI patterns directly from pixel images with minimal preprocessing. Moreover, the robustness of the proposed classifiers is evaluated by the data generated at different signal to noise ratios (SNR).

Download Full-text

Trajectory Design for UAV-Assisted Emergency Communications: A Transfer Learning Approach

GLOBECOM 2020 - 2020 IEEE Global Communications Conference ◽

10.1109/globecom42002.2020.9348212 ◽

2020 ◽

Author(s):

Xinruo Zhang ◽

Gan Zheng ◽

Sangarapillai Lambotharan

Keyword(s):

Transfer Learning ◽

Learning Approach ◽

Trajectory Design ◽

Emergency Communications

Download Full-text

A Transfer Learning Approach for Early Diagnosis of Alzheimer’s Disease on MRI Images

Neuroscience ◽

10.1016/j.neuroscience.2021.01.002 ◽

2021 ◽

Author(s):

Atif Mehmood ◽

Shuyuan yang ◽

Zhixi feng ◽

Min wang ◽

AL Smadi Ahmad ◽

...

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Early Diagnosis ◽

Transfer Learning ◽

Learning Approach

Download Full-text

Plant Recognition Using Morphological Feature Extraction and Transfer Learning over SVM and AdaBoost

Symmetry ◽

10.3390/sym13020356 ◽

2021 ◽

Vol 13 (2) ◽

pp. 356

Author(s):

Shubham Mahajan ◽

Akshay Raina ◽

Xiao-Zhi Gao ◽

Amit Kant Pandit

Keyword(s):

Feature Extraction ◽

Transfer Learning ◽

Plant Species ◽

Species Recognition ◽

Morphological Features ◽

Support Vector ◽

Additional Advantage ◽

Adaptive Boosting ◽

Vast Number ◽

Axis Length

Plant species recognition from visual data has always been a challenging task for Artificial Intelligence (AI) researchers, due to a number of complications in the task, such as the enormous data to be processed due to vast number of floral species. There are many sources from a plant that can be used as feature aspects for an AI-based model, but features related to parts like leaves are considered as more significant for the task, primarily due to easy accessibility, than other parts like flowers, stems, etc. With this notion, we propose a plant species recognition model based on morphological features extracted from corresponding leaves’ images using the support vector machine (SVM) with adaptive boosting technique. This proposed framework includes the pre-processing, extraction of features and classification into one of the species. Various morphological features like centroid, major axis length, minor axis length, solidity, perimeter, and orientation are extracted from the digital images of various categories of leaves. In addition to this, transfer learning, as suggested by some previous studies, has also been used in the feature extraction process. Various classifiers like the kNN, decision trees, and multilayer perceptron (with and without AdaBoost) are employed on the opensource dataset, FLAVIA, to certify our study in its robustness, in contrast to other classifier frameworks. With this, our study also signifies the additional advantage of 10-fold cross validation over other dataset partitioning strategies, thereby achieving a precision rate of 95.85%.

Download Full-text