Research on rock sample lithology identification algorithm based on ResNet self-supervised learning

2021 ◽  
Author(s):  
Dongxing Zhao ◽  
Han Wang ◽  
Wei He ◽  
Kun Ding ◽  
Haiyan Zhang
Keyword(s):  
Supervised Learning ◽  
Rock Sample ◽  
Identification Algorithm ◽  
Lithology Identification

Semi-supervised learning for lithology identification using Laplacian support vector machine

2020 ◽  
Vol 195 ◽  
pp. 107510 ◽  
Author(s):  
Zerui Li ◽  
Yu Kang ◽  
Deyong Feng ◽  
Xing-Mou Wang ◽  
Wenjun Lv ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Supervised Learning ◽  
Support Vector ◽  
Lithology Identification

Tire Rolling Kinematics Model for an Intelligent Tire Based on an Accelerometer

2020 ◽  
Vol 48 (4) ◽  
pp. 287-314
Author(s):  
Yan Wang ◽  
Zhe Liu ◽  
Michael Kaliske ◽  
Yintao Wei
Keyword(s):  
Elastic Deformation ◽  
Estimation Algorithm ◽  
Force Sensor ◽  
Euler Method ◽  
Rolling Contact ◽  
Body Motion ◽  
Identification Algorithm ◽  
Active Perception ◽  
Kinematics Model ◽  
Ring Model

ABSTRACT The idea of intelligent tires is to develop a tire into an active perception component or a force sensor with an embedded microsensor, such as an accelerometer. A tire rolling kinematics model is necessary to link the acceleration measured with the tire body elastic deformation, based on which the tire forces can be identified. Although intelligent tires have attracted wide interest in recent years, a theoretical model for the rolling kinematics of acceleration fields is still lacking. Therefore, this paper focuses on an explicit formulation for the tire rolling kinematics of acceleration, thereby providing a foundation for the force identification algorithms for an accelerometer-based intelligent tire. The Lagrange–Euler method is used to describe the acceleration field and contact deformation of rolling contact structures. Then, the three-axis acceleration vectors can be expressed by coupling rigid body motion and elastic deformation. To obtain an analytical expression of the full tire deformation, a three-dimensional tire ring model is solved with the tire–road deformation as boundary conditions. After parameterizing the ring model for a radial tire, the developed method is applied and validated by comparing the calculated three-axis accelerations with those measured by the accelerometer. Based on the features of acceleration, especially the distinct peak values corresponding to the tire leading and trailing edges, an intelligent tire identification algorithm is established to predict the tire–road contact length and tire vertical load. A simulation and experiments are conducted to verify the accuracy of the estimation algorithm, the results of which demonstrate good agreement. The proposed model provides a solid theoretical foundation for an acceleration-based intelligent tire.

A Supervised Learning Approach for Dynamic Sampling (SLADS) in Raman Hyperspectral Imaging

2018 ◽  
Vol 2018 (15) ◽  
pp. 132-1-1323
Author(s):  
Shijie Zhang ◽  
Zhengtian Song ◽  
G. M. Dilshan P. Godaliyadda ◽  
Dong Hye Ye ◽  
Atanu Sengupta ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Hyperspectral Imaging ◽  
Learning Approach ◽  
Dynamic Sampling

An IoT Device Identification Method based on Semi-supervised Learning

2020 ◽  
Author(s):  
Linna Fan ◽  
Shize Zhang ◽  
Yichao Wu ◽  
Zhiliang Wang ◽  
Chenxin Duan ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Device Identification ◽  
Identification Method

Localization and Non-Localization Node Identification Using Dream in MANET

2016 ◽  
Vol 2 (2) ◽  
Author(s):  
Amit Singh ◽  
Nitin Mishra ◽  
Angad Singh
Keyword(s):  
Ad Hoc Network ◽  
Ad Hoc ◽  
Mobile Ad Hoc Network ◽  
Fundamental Problem ◽  
Identification Algorithm ◽  
Mobile Nodes ◽  
Position Information ◽  
Location Services ◽  
Wireless Router ◽  
Mobile Ad Hoc

 A Wireless Mobile Ad-hoc Network consists of variety of mobile nodes that temporally kind a dynamic infrastructure less network. To modify communication between nodes that don’t have direct radio contact, every node should operate as a wireless router and potential forward knowledge traffic of behalf of the opposite node. In MANET Localization is a fundamental problem. Current localization algorithm mainly focuses on checking the localizability of a network and/or how to localize as many nodes as possible. It could provide accurate position information foe kind of expanding application. Localization provide information about coverage, deployment, routing, location, services, target tracking and rescue If high mobility among the mobile nodes occurs path failure breaks. Hence the location information cannot be predicted. Here we have proposed a localization based algorithm which will help to provide information about the localized and non-localized nodes in a network. In the proposed approach DREAM protocol and AODV protocol are used to find the localizability of a node in a network. DREAM protocol is a location protocol which helps to find the location of a node in a network whereas AODV is a routing protocol it discover route as and when necessary it does not maintain route from every node to every other. To locate the mobile nodes in a n/w an node identification algorithm is used. With the help of this algorithm localized and non-localized node can be easily detected in respect of radio range. This method helps to improve the performance of a module and minimize the location error and achieves improved performance in the form of UDP packet loss, received packet and transmitted packets, throughput, routing overhead, packet delivery fraction. All the simulation done through the NS-2 module and tested the mobile ad-hoc network.

Sign in / Sign up

Export Citation Format

Share Document