scholarly journals Online Visual Tracking of Weighted Multiple Instance Learning via Neutrosophic Similarity-Based Objectness Estimation

Symmetry ◽  
2019 ◽  
Vol 11 (6) ◽  
pp. 832 ◽  
Author(s):  
Keli Hu ◽  
Wei He ◽  
Jun Ye ◽  
Liping Zhao ◽  
Hua Peng ◽  
...  
Keyword(s):  
Learning Algorithm ◽  
Training Sample ◽  
Multiple Instance Learning ◽  
Superior Performance ◽  
Video Sequences ◽  
Neutrosophic Set ◽  
Object A ◽  
Object Properties ◽  
Shape Distance ◽  
Object Area

An online neutrosophic similarity-based objectness tracking with a weighted multiple instance learning algorithm (NeutWMIL) is proposed. Each training sample is extracted surrounding the object location, and the distribution of these samples is symmetric. To provide a more robust weight for each sample in the positive bag, the asymmetry of the importance of the samples is considered. The neutrosophic similarity-based objectness estimation with object properties (super straddling) is applied. The neutrosophic theory is a new branch of philosophy for dealing with incomplete, indeterminate, and inconsistent information. By considering the surrounding information of the object, a single valued neutrosophic set (SVNS)-based segmentation parameter selection method is proposed, to produce a well-built set of superpixels which can better explain the object area at each frame. Then, the intersection and shape-distance criteria are proposed for weighting each superpixel in the SVNS domain, mainly via three membership functions, T (truth), I (indeterminacy), and F (falsity), for each criterion. After filtering out the superpixels with low response, the newly defined neutrosophic weights are utilized for weighting each sample. Furthermore, the objectness estimation information is also applied for estimating and alleviating the problem of tracking drift. Experimental results on challenging benchmark video sequences reveal the superior performance of our algorithm when confronting appearance changes and background clutters.

scholarly journals Optimising Performance for NB-IoT UE Devices through Data Driven Models

2021 ◽  
Vol 10 (1) ◽  
pp. 21
Author(s):  
Omar Nassef ◽  
Toktam Mahmoodi ◽  
Foivos Michelinakis ◽  
Kashif Mahmood ◽  
Ahmed Elmokashfi
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Gradient Descent ◽  
Deep Neural Network ◽  
Narrow Band ◽  
Learning Algorithm ◽  
Base Station ◽  
User Equipment ◽  
Data Driven ◽  
Superior Performance

This paper presents a data driven framework for performance optimisation of Narrow-Band IoT user equipment. The proposed framework is an edge micro-service that suggests one-time configurations to user equipment communicating with a base station. Suggested configurations are delivered from a Configuration Advocate, to improve energy consumption, delay, throughput or a combination of those metrics, depending on the user-end device and the application. Reinforcement learning utilising gradient descent and genetic algorithm is adopted synchronously with machine and deep learning algorithms to predict the environmental states and suggest an optimal configuration. The results highlight the adaptability of the Deep Neural Network in the prediction of intermediary environmental states, additionally the results present superior performance of the genetic reinforcement learning algorithm regarding its performance optimisation.

scholarly journals AIRBORNE HYPERSPECTRAL REMOTE SENSING FOR IDENTIFICATION GRASSLAND VEGETATION

2015 ◽  
Vol XL-3/W3 ◽  
pp. 427-431 ◽  
Author(s):  
P. Burai ◽  
T. Tomor ◽  
L. Bekő ◽  
B. Deák
Keyword(s):  
Image Classification ◽  
Learning Algorithm ◽  
Training Sample ◽  
Hyperspectral Data ◽  
Training Dataset ◽  
Classification Methods ◽  
Grassland Vegetation ◽  
Training Samples ◽  
Almost All ◽  
Noise Fraction

In our study we classified grassland vegetation types of an alkali landscape (Eastern Hungary), using different image classification methods for hyperspectral data. Our aim was to test the applicability of hyperspectral data in this complex system using various image classification methods. To reach the highest classification accuracy, we compared the performance of traditional image classifiers, machine learning algorithm, feature extraction (MNF-transformation) and various sizes of training dataset. Hyperspectral images were acquired by an AISA EAGLE II hyperspectral sensor of 128 contiguous bands (400–1000 nm), a spectral sampling of 5 nm bandwidth and a ground pixel size of 1 m. We used twenty vegetation classes which were compiled based on the characteristic dominant species, canopy height, and total vegetation cover. Image classification was applied to the original and MNF (minimum noise fraction) transformed dataset using various training sample sizes between 10 and 30 pixels. In the case of the original bands, both SVM and RF classifiers provided high accuracy for almost all classes irrespectively of the number of the training pixels. We found that SVM and RF produced the best accuracy with the first nine MNF transformed bands. Our results suggest that in complex open landscapes, application of SVM can be a feasible solution, as this method provides higher accuracies compared to RF and MLC. SVM was not sensitive for the size of the training samples, which makes it an adequate tool for cases when the available number of training pixels are limited for some classes.

scholarly journals Multiple Instance Learning Networks for Fine-Grained Sentiment Analysis

2018 ◽  
Vol 6 ◽  
pp. 17-31 ◽  
Author(s):  
Stefanos Angelidis ◽  
Mirella Lapata
Keyword(s):  
Sentiment Analysis ◽  
Neural Model ◽  
Multiple Instance Learning ◽  
Superior Performance ◽  
Learning Networks ◽  
Scoring Method ◽  
Fine Grained ◽  
Opinion Extraction ◽  
Elicitation Study ◽  
Discourse Units

We consider the task of fine-grained sentiment analysis from the perspective of multiple instance learning (MIL). Our neural model is trained on document sentiment labels, and learns to predict the sentiment of text segments, i.e. sentences or elementary discourse units (EDUs), without segment-level supervision. We introduce an attention-based polarity scoring method for identifying positive and negative text snippets and a new dataset which we call SpoT (as shorthand for Segment-level POlariTy annotations) for evaluating MIL-style sentiment models like ours. Experimental results demonstrate superior performance against multiple baselines, whereas a judgement elicitation study shows that EDU-level opinion extraction produces more informative summaries than sentence-based alternatives.

Robust objectness tracking with weighted multiple instance learning algorithm

2018 ◽  
Vol 288 ◽  
pp. 43-53 ◽  
Author(s):  
Honghong Yang ◽  
Shiru Qu ◽  
Fumin Zhu ◽  
Zunxin Zheng
Keyword(s):  
Learning Algorithm ◽  
Multiple Instance Learning

Least Squares Support Vector Machine for Fault Diagnosis Optimization

2013 ◽  
Vol 347-350 ◽  
pp. 505-508
Author(s):  
Si Yang Liang ◽  
Jian Hong Lv
Keyword(s):  
Fault Diagnosis ◽  
Least Squares ◽  
Learning Algorithm ◽  
Test Sample ◽  
Digital Circuit ◽  
Training Sample ◽  
Support Vector ◽  
Vector Machines ◽  
Sample Data ◽  
Diagnosis Method

In order to improve the diagnostic accuracy of digital circuit, the fault diagnosis method based on support vector machines (SVM) is proposed. The input is fault characteristics of digital circuit; the output is the fault style. The connection of fault characteristics and style was established. Network learning algorithm using least squares, the training sample data is formed by the simulation, the test sample data is formed by the untrained simulation. The method achieved the classification of faulted digital circuits, and the results show that the method has the features of fast and high accuracy.

mi-DS: Multiple-Instance Learning Algorithm

2013 ◽  
Vol 43 (1) ◽  
pp. 143-154 ◽  
Author(s):  
Dat T. Nguyen ◽  
Cao D. Nguyen ◽  
Rosalyn Hargraves ◽  
Lukasz A. Kurgan ◽  
Krzysztof J. Cios
Keyword(s):  
Learning Algorithm ◽  
Multiple Instance Learning

scholarly journals FORECASTING OF THE SURFACE ROUGHNESS IN FINISHING MILLING USING NEURAL NETWORKS

2019 ◽  
Vol 4 (10) ◽  
pp. 135-141
Author(s):  
Е. Ерыгин ◽  
E. Erygin ◽  
Т. Дуюн ◽  
T. Duyun
Keyword(s):  
Neural Network ◽  
Cutting Tool ◽  
Learning Algorithm ◽  
Network Modeling ◽  
Training Sample ◽  
Neural Network Modeling ◽  
Network Learning ◽  
The Neural Network ◽  
And Training ◽  
Positive Results

This article describes the task of predicting roughness when finishing milling using neural network modeling. As a basis for the creation and training of an artificial neural network, a progressive formu-la for determining the roughness during finishing milling is chosen. The thermoEMF of the processing and processed materials is used as one of the parameters for calculating the roughness. The use of thermoEMF allows to take into account the material of the workpiece and the cutting tool, which af-fects the accuracy of the results. A training sample is created with data for five inputs and one output. The architecture, features and network learning algorithm are described. A neural network that de-termines the roughness for finishing milling has been created and configured. The process of learning and debugging of the neural network by means of graphs is clearly displayed. The network operability is checked on the test data, which allows obtaining positive results.

scholarly journals Adaptive force/ position control for dual-arm system based on neural network radial basis function without using a force sensor

2020 ◽  
pp. 1-7
Author(s):  
Luu Thi Hue, Duong Minh Duc, Pham Thuc Anh Nguyen Pham
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Position Control ◽  
Learning Algorithm ◽  
Contact Point ◽  
Force Sensor ◽  
Object A ◽  
Contact Points ◽  
Radial Basis ◽  
Dual Arm

The paper has developed an adaptive algorithm using neural network for controlling dual-arm robotic system in stable holding a rectangle object and moving it to track the desired trajectories. Firstly, an overall dynamic of the system including the dual-arm robot and the object is derived based on Euler-Lagrangian principle. Then based on the dynamics, a controller has proposed to achieve the desired trajectories of the holding object. A radial basis neural network has been applied to compensate uncertainties of system parameters. The adaptive learning algorithm has been derived owning to Lyapunov stability principle to guarantee asymptotical convergence of the closed loop system. Besides, force control at contact point is implemented without the measurements of forces and moments at contact points. Finally, simulation work on Matlab has been carried out to confirm the accuracy and the effectiveness of the proposed controller.

Sign in / Sign up

Export Citation Format

Share Document