Identification of the Core Neural Network Subserving PTSD in Animal Models and Their Modulation

2018 ◽  
pp. 45-85
Author(s):  
Maxwell Bennett ◽  
Jim Lagopoulos
Keyword(s):  
Neural Network ◽  
Animal Models ◽  
The Core

IDENTIFICATION OF COHERENT STRUCTURES IN TURBULENT SHEAR FLOWS WITH A FUZZY ARTMAP NEURAL NETWORK

1996 ◽  
Vol 07 (05) ◽  
pp. 559-568 ◽  
Author(s):  
J. FERRE-GINE ◽  
R. RALLO ◽  
A. ARENAS ◽  
FRANCE GIRALT
Keyword(s):  
Neural Network ◽  
Template Matching ◽  
Phase Relationship ◽  
Fuzzy Artmap ◽  
Turbulent Shear ◽  
Training Procedure ◽  
Full Data ◽  
The Core ◽  
Data Files ◽  
Number Of Classes

An implementation of a Fuzzy Artmap neural network is used to detect and to identify (recognise) structures (patterns) embedded in the velocity field of a turbulent wake behind a circular cylinder. The net is trained to recognise both clockwise and anticlockwise eddies present in the u and v velocity fields at 420 diameters downstream of the cylinder that generates the wake, using a pre-processed part of the recorded velocity data. The phase relationship that exists between the angles of the velocity vectors of an eddy pattern is used to reduce the number of classes contained in the data, before the start of the training procedure. The net was made stricter by increasing the vigilance parameter within the interval [0.90, 0.95] and a set of net-weights were obtained for each value. Full data files were scanned with the net classifying patterns according to their phase characteristics. The net classifies about 27% of the recorded signals as eddy motions, with the strictest vigilance parameter and without the need to impose external initial templates. Spanwise distances (homogeneous direction of the flow) within the centres of the eddies identified suggest that they form pairs of counter-rotating vortices (double rollers). The number of patterns selected with Fuzzy Artmap is lower than that reported for template matching because the net classifies eddies according to the recirculating pattern present at the core or central region, while template matching extends the region over which correlation between data and template is performed. In both cases, the topology of educed patterns is in agreement.

scholarly journals The Research of Temperature Compensation for Thermopile Sensor Based on Improved PSO-BP Algorithm

2015 ◽  
Vol 2015 ◽  
pp. 1-6 ◽  
Author(s):  
Yuanjiang Li ◽  
Yuehua Li ◽  
Feng Li ◽  
Bin Zhao ◽  
QingQing Li
Keyword(s):  
Neural Network ◽  
Thermal Radiation ◽  
Bp Neural Network ◽  
Temperature Compensation ◽  
Safety Monitoring ◽  
Bp Algorithm ◽  
Bp Network ◽  
The Core ◽  
Thermopile Sensor ◽  
Improved Pso

When thermopile sensor is used for safety monitoring of equipment in industrial environments, particularly for measuring the thermal radiation information of device, the measured result of this kind of sensor is usually affected by ambient temperature due to its unique structure. An improved PSO-BP algorithm is proposed for temperature compensation of thermopile sensor and correcting the error in the condition of the system accuracy requirements reduced by temperature. The core of improved PSO-BP algorithm is to improve the certainty of initial weights and thresholds that belonged to BP neural network and then train the samples by using BP neural network for enhancing the generalization ability and stability of system. The experimental results show that the proposed PSO-BP network outperforms other similar algorithms with faster convergence speed, lower errors, and higher accuracy.

Experimenting with Recognition Accelerator for Pavement Distress Identification

1996 ◽  
Vol 1536 (1) ◽  
pp. 130-135 ◽  
Author(s):  
Sudhakar Nallamothu ◽  
Kelvin C. P. Wang
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Artificial Neural Network ◽  
Coulomb Energy ◽  
Processing Unit ◽  
Basic Principles ◽  
Pavement Distress ◽  
The Core ◽  
Artificial Neural Network Ann ◽  
Computer Board

A study was conducted using a computer board embedded with an artificial neural network (ANN) microchip for pattern recognition of pavement distress classification. The basic principles behind ANNs and pattern recognition are discussed. The hardware architecture of the Ni1000 recognition accelerator chip, which is the core of the ANN computer board, is presented, and the principle of operation of the restricted coulomb energy algorithm used in the chip is discussed. It is demonstrated that the Ni1000 Recognition Accelerator chip can be used for pattern recognition of pavement distress. Distresses in pavement images have been successfully classified using the Ni1000 recognition accelerator. The Ni1000 has the potential to be used as the core processing unit for distress classification at highway speeds.

scholarly journals Daily activity recognition based on recurrent neural network using multi-modal signals

2018 ◽  
Vol 7 ◽  
Author(s):  
Akira Tamamori ◽  
Tomoki Hayashi ◽  
Tomoki Toda ◽  
Kazuya Takeda
Keyword(s):  
Neural Network ◽  
Activity Recognition ◽  
Recurrent Neural Network ◽  
Bottom Layer ◽  
Prototype System ◽  
Recording Device ◽  
Feed Forward Neural Network ◽  
The Core ◽  
Linear Transform ◽  
Indoor And Outdoor

Our aim is to develop a smartphone-based life-logging system. Human activity recognition (HAR) is one of the core techniques to realize it. Recent studies reported the effectiveness of feed-forward neural network (FF-NN) and recurrent neural network (RNN) as a classifier for HAR task. However, there are still unresolved problems in those studies: (1) a life-logging system using only a smartphone for recording device has not been developed, (2) only indoor activities have been utilized for evaluation, (3) insufficient investigations/evaluations of RNN. In this study, we address these unresolved problems as follows: (1) we build a prototype system for life-logging and conduct data recording experiment on this system to include both indoor and outdoor activities. The experimental results of HAR on this new dataset showed that RNN-based classifier was still effective. (2) From the results of a HAR experiment, it was demonstrated that a multi-layered Simple Recurrent Unit with a non-linear transform at the bottom layer and a highway-connection was the most effective. (3) We could grasp the reason for the improvement of RNN from FF-NN by observing the posterior probabilities over test data.

scholarly journals Investigation of optimal configurations of a convolutional neural network for the identification of objects in real-time

2019 ◽  
pp. 417-423
Author(s):  
M A Isayev ◽  
D A Savelyev
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Real Time ◽  
State Of The Art ◽  
Average Precision ◽  
The Core ◽  
Particular Solution ◽  
Optimal Configurations

The comparison of different convolutional neural networks which are the core of the most actual solutions in the computer vision area is considers in hhe paper. The study includes benchmarks of this state-of-the-art solutions by some criteria, such as mAP (mean average precision), FPS (frames per seconds), for the possibility of real-time usability. It is concluded on the best convolutional neural network model and deep learning methods that were used at particular solution.

scholarly journals Simpler Machine Learning Using Spreadsheets: Neural Network Predict

2020 ◽  
Vol 4 (1) ◽  
pp. 124
Author(s):  
Leong Thin-Yin ◽  
Leong Yonghui Jonathan
Keyword(s):  
Social Sciences ◽  
Neural Network ◽  
Machine Learning ◽  
Business Analytics ◽  
The Core ◽  
Core Content ◽  
The Social ◽  
Business Application ◽  
Recursive Computation ◽  
Sales Pitch

Machine Learning as a phenomenon has gone viral, with many technologists and software vendors promoting it. However, offered tools remain highly technical and not accessible to those without rigorous training in Computer Science or Business Analytics. It would be more useful if end-users can understand it beyond the sales pitch or blind application, and perhaps, even work from scratch to build simple models without much additional training. With better assimilation and acceptance of this AI methodology as an acquired skill and not just head knowledge, many more may want to invest the intensive effort to learn the required tough mathematics and cryptic programming. Or, after simple trial explorations, be willing to put aside substantial budgets to employ skilled professionals for full-scale business application. With simplicity and accessibility in mind, this paper renders Neural Network, a key machine learning methodology, on the ubiquitous and easily comprehensible spreadsheet without macros or add-ins, employing only elementary operations and if so desired, optionally leveraging on its built-in Solver. We will show that backpropagation can be achieved using the elegant though obscure recursive computation feature, with no need for Solver. We will demonstrate the application of neural network on a familiar problem: early and prior prediction of students’ graduation GPA. The paper can be used to form the core content for introducing machine learning to non-technical audiences, particularly those majoring in Business and the Social Sciences.

scholarly journals Simultaneous Monocular Visual Odometry and Depth Reconstruction with Scale Recovery

2020 ◽  
Author(s):  
Guoliang Liu
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Visual Odometry ◽  
Input Image ◽  
View Synthesis ◽  
Depth Image ◽  
The Core ◽  
Depth Prediction ◽  
Camera Pose ◽  
Depth Reconstruction

In this paper, we propose a deep neural networkthat can estimate camera poses and reconstruct thefull resolution depths of the environment simultaneously usingonly monocular consecutive images. In contrast to traditionalmonocular visual odometry methods, which cannot estimatescaled depths, we here demonstrate the recovery of the scaleinformation using a sparse depth image as a supervision signalin the training step. In addition, based on the scaled depth,the relative poses between consecutive images can be estimatedusing the proposed deep neural network. Another novelty liesin the deployment of view synthesis, which can synthesize anew image of the scene from a different view (camera pose)given an input image. The view synthesis is the core techniqueused for constructing a loss function for the proposed neuralnetwork, which requires the knowledge of the predicted depthsand relative poses, such that the proposed method couples thevisual odometry and depth prediction together. In this way,both the estimated poses and the predicted depths from theneural network are scaled using the sparse depth image as thesupervision signal during training. The experimental results onthe KITTI dataset show competitive performance of our methodto handle challenging environments.<br>

scholarly journals Analysis of Financial Statement and Prewarning of Audit Risks Based on Artificial Neural Network

2021 ◽  
Vol 15 ◽  
pp. 1015-1024
Author(s):  
Yanxia Zhang
Keyword(s):  
Neural Network ◽  
Evaluation Index System ◽  
Financial Statement ◽  
Analysis Framework ◽  
Scientific Evaluation ◽  
Audit Risk ◽  
The Core ◽  
Income Statement ◽  
Proposed Model ◽  
Key Steps

The marketization of social capital has resulted in frequent audit failures, and financial statement frauds. One of the key steps of auditing is the identification of material misstatement risk of financial statement. However, there is no unified analysis framework or quantitative method for identifying this risk. Therefore, this paper aims to analyze financial statement and prewarn audit risks in an accurate manner. Firstly, the items of financial statement were analyzed in three aspects of the target enterprise: balance statement, income statement, and cash flow statement. Next, the authors probed deep into the core indices of the post audit risk verification and evaluation of the business process, constructed a scientific evaluation index system for audit risks of financial statement, and quantified the 89 tertiary indices, 21 secondary indices, and 3 primary indices. After that, an audit risk prediction model for financial statement was established based on neural network. Experimental results show the effectiveness of the proposed model for audit risk prewarning, and applicable to other tasks of financial auditing.

Sign in / Sign up

Export Citation Format

Share Document