Retinal Vessel Detection in Wide-Field Fluorescein Angiography with Deep Neural Networks: A Novel Training Data Generation Approach

2018 ◽  
Author(s):  
Li Ding ◽  
Ajay Kuriyan ◽  
Rajeev Ramchandran ◽  
Gaurav Sharma
Keyword(s):  
Neural Networks ◽  
Fluorescein Angiography ◽  
Deep Neural Networks ◽  
Retinal Vessel ◽  
Training Data ◽  
Wide Field ◽  
Data Generation ◽  
Vessel Detection

scholarly journals On regularization properties of artificial datasets for deep learning

2019 ◽  
Vol 0 (9/2019) ◽  
pp. 13-18
Author(s):  
Karol Antczak
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Real Data ◽  
Training Data ◽  
Generation Process ◽  
Data Generation ◽  
Artificial Data ◽  
High Level ◽  
Artificial Datasets

The paper discusses regularization properties of artificial data for deep learning. Artificial datasets allow to train neural networks in the case of a real data shortage. It is demonstrated that the artificial data generation process, described as injecting noise to high-level features, bears several similarities to existing regularization methods for deep neural networks. One can treat this property of artificial data as a kind of “deep” regularization. It is thus possible to regularize hidden layers of the network by generating the training data in a certain way.

scholarly journals Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

scholarly journals A Novel Deep Learning Pipeline for Retinal Vessel Detection In Fluorescein Angiography

2020 ◽  
Vol 29 ◽  
pp. 6561-6573 ◽  
Author(s):  
Li Ding ◽  
Mohammad H. Bawany ◽  
Ajay E. Kuriyan ◽  
Rajeev S. Ramchandran ◽  
Charles C. Wykoff ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fluorescein Angiography ◽  
Retinal Vessel ◽  
Vessel Detection

scholarly journals Synthesis and Parameterization of Gas Sensor Models

2021 ◽  
Vol 25 (1) ◽  
pp. 138-161
Author(s):  
O. G. Bondar ◽  
E. O. Brezhneva ◽  
O. G. Dobroserdov ◽  
K. G. Andreev ◽  
N. V. Polyakov
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Mathematical Models ◽  
Output Signal ◽  
Electrochemical Sensors ◽  
Training Data ◽  
Data Generation ◽  
Technical Documentation ◽  
Cross Sensitivity ◽  
Artificial Neural

Purpose of research: search and analysis of existing models of gas-sensitive sensors. Development of mathematical models of gas-sensitive sensors of various types (semiconductor, thermocatalytic, optical, electrochemical) for their subsequent use in the training of artificial neural networks (INS). Investigation of main physicochemical patterns underlying the principles of sensor operation, consideration of the influence of environmental factors and cross-sensitivity on the sensor output signal. Comparison of simulation results with actual characteristics produced by the sensor industry. The concept of creating mathematical models is described. Their parameterization, research and assessment of adequacy are carried out.Methods. Numerical methods, computer modeling methods, electrical circuit theory, the theory of chemosorption and heterogeneous catalysis, the Freundlich and Langmuir equations, the Buger-Lambert-Behr law, the foundations of electrochemistry were used in creating mathematical models. Standard deviation (MSE) and relative error were calculated to assess the adequacy of the models.Results. The concept of creating mathematical models of sensors based on physicochemical patterns is described. This concept allows the process of data generation for training artificial neural networks used in multi-component gas analyzers for the purpose of joint information processing to be automated. Models of semiconductor, thermocatalytic, optical and electrochemical sensors were obtained and upgraded, considering the influence of additional factors on the sensor signal. Parameterization and assessment of adequacy and extrapolation properties of models by graphical dependencies presented in technical documentation of sensors were carried out. Errors (relative and RMS) of discrepancy of real data and results of simulation of gas-sensitive sensors by basic parameters are determined. The standard error of reproduction of the main characteristics of the sensors did not exceed 0.5%.Conclusion. Multivariable mathematical models of gas-sensitive sensors are synthesized, considering the influence of main gas and external factors (pressure, temperature, humidity, cross-sensitivity) on the output signal and allowing to generate training data for sensors of various types.

scholarly journals Maximizing the Prediction Accuracy in Tweet Sentiment Extraction using Tensor Flow based Deep Neural Networks

2021 ◽  
Vol 3 (2) ◽  
pp. 61-79
Author(s):  
S Thivaharan ◽  
G Srivatsun
Keyword(s):  
Neural Networks ◽  
Social Media ◽  
Prediction Accuracy ◽  
Deep Neural Networks ◽  
Modern Technology ◽  
The Other ◽  
Data Generation ◽  
Class Prediction ◽  
The Social ◽  
Communication Devices

The amount of data generated by modern communication devices is enormous, reaching petabytes. The rate of data generation is also increasing at an unprecedented rate. Though modern technology supports storage in massive amounts, the industry is reluctant in retaining the data, which includes the following characteristics: redundancy in data, unformatted records with outdated information, data that misleads the prediction and data with no impact on the class prediction. Out of all of this data, social media plays a significant role in data generation. As compared to other data generators, the ratio at which the social media generates the data is comparatively higher. Industry and governments are both worried about the circulation of mischievous or malcontents, as they are extremely susceptible and are used by criminals. So it is high time to develop a model to classify the social media contents as fair and unfair. The developed model should have higher accuracy in predicting the class of contents. In this article, tensor flow based deep neural networks are deployed with a fixed Epoch count of 15, in order to attain 25% more accuracy over the other existing models. Activation methods like “Relu” and “Sigmoid”, which are specific for Tensor flow platforms support to attain the improved prediction accuracy.

scholarly journals Deep Neural Networks Techniques using for Learning Automata Based Incremental Learning Method

2021 ◽  
Vol 12 (6) ◽  
pp. 69-73
Author(s):  
C. Swetha Reddy Et.al
Keyword(s):  
Neural Networks ◽  
Language Processing ◽  
Visual Recognition ◽  
Deep Neural Networks ◽  
Learning Automata ◽  
Training Data ◽  
Neuron Models ◽  
Effectiveness Of Training ◽  
Learning Machine ◽  
Incremental Learning Method

Surprisingly comprehensive learning methods are implemented in many large learning machine data, such as visual recognition and visual language processing. Much of the success of advanced training in recent years is due to leadership training, which requires a set of information for specific tasks, before such training. However, in reality, selected tasks related to personal study are gradually accumulated over time as it is difficult to collect and submit training data manually. It provides a way to continue learning some information columns and examples of steps that are specific to the new class and called additional learning. In this post, we recommend the best machine training method for further training for deep neural networks. The basic idea is to learn a deep system with strong connections that can be "activated" or "turned off" at different stages. The approach you suggest allows you to reduce the distribution of old services as you learn new for example new training, which increases the effectiveness of training in the additional training phase. Experiments with MNIST and CIFAR-100 show that our approach can be implemented in other long-term phases in deep neuron models and achieve better results from zero-base training.

Sign in / Sign up

Export Citation Format

Share Document