Dynamic feature fusion in the self organising tree map - applied to the segmentation of biofilm images

2006 ◽  
Author(s):  
M. Kyan ◽  
Ling Guan ◽  
S. Liss
Keyword(s):  
Feature Fusion ◽  
The Self ◽  
Dynamic Feature ◽  
Tree Map

scholarly journals Feature Fusion of a Deep-Learning Algorithm into Wearable Sensor Devices for Human Activity Recognition

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8294
Author(s):  
Chih-Ta Yen ◽  
Jia-Xian Liao ◽  
Yi-Kai Huang
Keyword(s):  
Deep Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Feature Fusion ◽  
Learning Algorithm ◽  
Human Activity Recognition ◽  
The Self ◽  
Wearable Device ◽  
Deep Learning Algorithm ◽  
Recorded Data

This paper presents a wearable device, fitted on the waist of a participant that recognizes six activities of daily living (walking, walking upstairs, walking downstairs, sitting, standing, and laying) through a deep-learning algorithm, human activity recognition (HAR). The wearable device comprises a single-board computer (SBC) and six-axis sensors. The deep-learning algorithm employs three parallel convolutional neural networks for local feature extraction and for subsequent concatenation to establish feature fusion models of varying kernel size. By using kernels of different sizes, relevant local features of varying lengths were identified, thereby increasing the accuracy of human activity recognition. Regarding experimental data, the database of University of California, Irvine (UCI) and self-recorded data were used separately. The self-recorded data were obtained by having 21 participants wear the device on their waist and perform six common activities in the laboratory. These data were used to verify the proposed deep-learning algorithm on the performance of the wearable device. The accuracy of these six activities in the UCI dataset and in the self-recorded data were 97.49% and 96.27%, respectively. The accuracies in tenfold cross-validation were 99.56% and 97.46%, respectively. The experimental results have successfully verified the proposed convolutional neural network (CNN) architecture, which can be used in rehabilitation assessment for people unable to exercise vigorously.

scholarly journals Feature Fusion-Based Siamese Region Proposal Network for Ultrasound Tracking

2021 ◽  
Author(s):  
Xinglong Zhu ◽  
Ruirui Kang ◽  
Yifan Wang ◽  
Danni Ai ◽  
Tianyu Fu ◽  
...  
Keyword(s):  
Object Tracking ◽  
Feature Fusion ◽  
Ultrasound Image ◽  
The Self ◽  
Network Module ◽  
Training Strategy ◽  
Liver Ultrasound ◽  
Unsupervised Training ◽  
Image Navigation ◽  
Ultrasound Tracking

Object tracking based on ultrasound image navigation can effectively reduce damage to healthy tissues in radiotherapy. In this study, we propose a deep Siamese network based on feature fusion. Whilst adopting MobileNetV2 as the backbone, an unsupervised training strategy is introduced to enrich the volume of the samples. The region proposal network module is designed to predict the location of the target, and a non-maximum suppression-based postprocessing algorithm is designed to refine the tracking results. Moreover, the proposed method is evaluated in the Challenge on Liver Ultrasound Tracking dataset and the self-collected dataset, which proves the need for the improvement and the effectiveness of the algorithm.

scholarly journals DAM: Hierarchical Adaptive Feature Selection Using Convolution Encoder Decoder Network for Strawberry Segmentation

2021 ◽  
Vol 12 ◽  
Author(s):  
Talha Ilyas ◽  
Muhammad Umraiz ◽  
Abbas Khan ◽  
Hyongsuk Kim
Keyword(s):  
Feature Selection ◽  
Feature Fusion ◽  
Semantic Segmentation ◽  
Dynamic Feature ◽  
Feature Maps ◽  
Adaptive Feature Selection ◽  
Convolutional Encoder ◽  
Time Segmentation ◽  
Flow Of Information ◽  
Segmentation Models

Autonomous harvesters can be used for the timely cultivation of high-value crops such as strawberries, where the robots have the capability to identify ripe and unripe crops. However, the real-time segmentation of strawberries in an unbridled farming environment is a challenging task due to fruit occlusion by multiple trusses, stems, and leaves. In this work, we propose a possible solution by constructing a dynamic feature selection mechanism for convolutional neural networks (CNN). The proposed building block namely a dense attention module (DAM) controls the flow of information between the convolutional encoder and decoder. DAM enables hierarchical adaptive feature fusion by exploiting both inter-channel and intra-channel relationships and can be easily integrated into any existing CNN to obtain category-specific feature maps. We validate our attention module through extensive ablation experiments. In addition, a dataset is collected from different strawberry farms and divided into four classes corresponding to different maturity levels of fruits and one is devoted to background. Quantitative analysis of the proposed method showed a 4.1% and 2.32% increase in mean intersection over union, over existing state-of-the-art semantic segmentation models and other attention modules respectively, while simultaneously retaining a processing speed of 53 frames per second.

Refining competition in the self-organising tree map for unsupervised biofilm image segmentation

2005 ◽  
Vol 18 (5-6) ◽  
pp. 850-860 ◽  
Author(s):  
Matthew Kyan ◽  
Ling Guan ◽  
Steven Liss
Keyword(s):  
Image Segmentation ◽  
The Self ◽  
Tree Map

Moving Target Classification in Road Monitoring Based on Multi-Feature Fusion

2013 ◽  
Vol 401-403 ◽  
pp. 1208-1211
Author(s):  
Lin Wu ◽  
Xiao Pei Wu ◽  
Juan Xu
Keyword(s):  
Aspect Ratio ◽  
Classification Accuracy ◽  
Feature Fusion ◽  
Moving Target ◽  
Dynamic Feature ◽  
Connected Component ◽  
Target Classification ◽  
Connected Component Labeling ◽  
Ratio Variation ◽  
Target Extraction

A method for moving target classification in road monitoring based on multi-feature fusion is presented in this paper. In this method, connected component labeling and merging combined with morphology are used to achieve the target extraction. Static features in moving target are extracted. To improve the low classification accuracy, a dynamic feature, lower thirds aspect ratio variation (also named as LTVar), is proposed and added. The recognition ratio obtains the relative increasing of 3.1% compared with the static features.

MEMORY-BASED CLASSIFICATION WITH DYNAMIC FEATURE SELECTION USING SELF-ORGANIZING MAPS FOR PATTERN EVALUATION

2007 ◽  
Vol 16 (05) ◽  
pp. 875-899 ◽  
Author(s):  
CHRISTOS PATERITSAS ◽  
ANDREAS STAFYLOPATIS
Keyword(s):  
Main Idea ◽  
Nearest Neighbors ◽  
The Self ◽  
Classification Task ◽  
Dynamic Feature ◽  
K Nearest Neighbors ◽  
Self Organizing Maps ◽  
Input Feature ◽  
Improved Performance ◽  
Self Organizing

Memory-based learning is one of the main fields in the area of machine learning. We propose a new methodology for addressing the classification task that relies on the main idea of the k-nearest neighbors algorithm, which is the most important representative of this field. In the proposed approach, given an unclassified pattern, a set of neighboring patterns is found, not necessarily using all input feature dimensions. Also, following the concept of the naïve Bayesian classifier, we adopt the assumption of independence of input features in the outcome of the classification task. The two concepts are merged in an attempt to take advantage of their good performance features. In order to further improve the performance of our approach, we propose a novel weighting scheme of the memory-base. Using the self-organizing maps model during the execution of the algorithm, dynamic weights of the memory-base patterns are produced. Experimental results have shown improved performance of the proposed method in comparison with the aforementioned algorithms and their variations.

Sign in / Sign up

Export Citation Format

Share Document