Exploitation of Artificial Intelligence Methods for Prediction of Atmospheric Corrosion

2012 ◽  
Vol 326-328 ◽  
pp. 65-68 ◽  
Author(s):  
David Seidl ◽  
Zora Jančíková ◽  
Pavel Koštial ◽  
Ivan Ružiak ◽  
Ivan Kopal ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Carbon Steel ◽  
Small Error ◽  
Atmospheric Environment ◽  
Corrosion Loss ◽  
Artificial Intelligence Methods ◽  
Environment Temperature ◽  
Structural Carbon ◽  
Structural Carbon Steel

The contribution deals with the use of artificial neural networks for prediction of corrosion loss of structural carbon steel. Nowadays there is certain chance to predict a corrosion loss of materials by artificial intelligence methods, especially by neural networks. A model of neural network for prediction of corrosion loss of structural carbon steel based on the input environmental parameters affecting the corrosion of metals in the atmospheric environment (temperature, relative humidity, air pollution by sulphur dioxide and the exposition time) was created. The model enables to predict corrosion loss of steel with a sufficiently small error.

scholarly journals Critical Assessment of Artificial Intelligence Methods for Prediction of hERG Channel Inhibition in the ‘Big Data’ Era

2020 ◽  
Author(s):  
Vishal Babu Siramshetty ◽  
Dac-Trung Nguyen ◽  
Natalia J. Martinez ◽  
Anton Simeonov ◽  
Noel T. Southall ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Big Data ◽  
Recurrent Neural Networks ◽  
Deep Neural Networks ◽  
Prediction Models ◽  
Chemical Space ◽  
Superior Performance ◽  
Gradient Boosting ◽  
Artificial Intelligence Methods

The rise of novel artificial intelligence methods necessitates a comparison of this wave of new approaches with classical machine learning for a typical drug discovery project. Inhibition of the potassium ion channel, whose alpha subunit is encoded by human Ether-à-go-go-Related Gene (hERG), leads to prolonged QT interval of the cardiac action potential and is a significant safety pharmacology target for the development of new medicines. Several computational approaches have been employed to develop prediction models for assessment of hERG liabilities of small molecules including recent work using deep learning methods. Here we perform a comprehensive comparison of prediction models based on classical (random forests and gradient boosting) and modern (deep neural networks and recurrent neural networks) artificial intelligence methods. The training set (~9000 compounds) was compiled by integrating hERG bioactivity data from ChEMBL database with experimental data generated from an in-house, high-throughput thallium flux assay. We utilized different molecular descriptors including the latent descriptors, which are real-valued continuous vectors derived from chemical autoencoders trained on a large chemical space (> 1.5 million compounds). The models were prospectively validated on ~840 in-house compounds screened in the same thallium flux assay. The deep neural networks performed significantly better than the classical methods with the latent descriptors. The recurrent neural networks that operate on SMILES provided highest model sensitivity. The best models were merged into a consensus model that offered superior performance compared to reference models from academic and commercial domains. Further, we shed light on the potential of artificial intelligence methods to exploit the chemistry big data and generate novel chemical representations useful in predictive modeling and tailoring new chemical space.<br>

scholarly journals Demand Modelling in Telecommunications

10.14311/1121 ◽  
2009 ◽  
Vol 49 (2) ◽  
Author(s):  
M. Chvalina
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Network Models ◽  
Short Term ◽  
Neural Network Models ◽  
Term Forecast ◽  
Artificial Intelligence Methods ◽  
Demand Modelling

This article analyses the existing possibilities for using Standard Statistical Methods and Artificial Intelligence Methods for a short-term forecast and simulation of demand in the field of telecommunications. The most widespread methods are based on Time Series Analysis. Nowadays, approaches based on Artificial Intelligence Methods, including Neural Networks, are booming. Separate approaches will be used in the study of Demand Modelling in Telecommunications, and the results of these models will be compared with actual guaranteed values. Then we will examine the quality of Neural Network models. 

scholarly journals The safety assessment of lifting equipment using artificial intelligence methods

2020 ◽  
Vol 224 ◽  
pp. 02018
Author(s):  
A Lyapin
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Safety Assessment ◽  
Data Sources ◽  
Artificial Intelligence Methods ◽  
Artificial Neural ◽  
Lifting Equipment

The article is devoted to the problem of using artificial neural networks to assess the risk of developing emergencies during the operation of lifting crane equipment. The data sources are telemetric measurements from microcontroller load limiters, as well as data from technical and daily inspections of equipment condition, in the last case the data may be fuzzy.

scholarly journals Identification of the Flow Properties of a 0.54% Carbon Steel during Continuous Cooling

Metals ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 104
Author(s):  
Christoph Rößler ◽  
David Schmicker ◽  
Oleksii Sherepenko ◽  
Thorsten Halle ◽  
Markus Körner ◽  
...  
Keyword(s):  
Carbon Steel ◽  
Flow Properties ◽  
Carreau Fluid ◽  
Cooling Process ◽  
Material Parameters ◽  
Essential Step ◽  
Deformation Processes ◽  
Structural Carbon ◽  
Experimental Effort ◽  
Structural Carbon Steel

The determinination of material properties is an essential step in the simulation of manufacturing processes. For hot deformation processes, consistently assessed Carreau fluid constitutive model derived in prior works by Schmicker et al. might be used, in which the flow stress is described as a function of the current temperature and the current strain rate. The following paper aims to extend the prior mentioned model by making a distinction, whether the material is being heated or cooled, enhancing the model capabilities to predict deformations within the cooling process. The experimental identifaction of the material parameters is demonstrated for a structural carbon steel with 0.54% carbon content. An approach to derive the flow properties during cooling from the same samples used at heating is presented, which massively reduces the experimental effort in future applications.

scholarly journals Pattern recognition techniques for the identification of Activities of Daily Living using mobile device accelerometer

2018 ◽  
Author(s):  
Ivan Miguel Pires ◽  
Nuno M. Garcia ◽  
Nuno Pombo ◽  
Francisco Flórez-Revuelta ◽  
Susanna Spinsante ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Pattern Recognition ◽  
Data Processing ◽  
Activities Of Daily Living ◽  
Mobile Devices ◽  
Daily Living ◽  
Pattern Recognition Techniques ◽  
Artificial Intelligence Methods ◽  
Processing Power

This paper focuses on the recognition of Activities of Daily Living (ADL) applying pattern recognition techniques to the data acquired by the accelerometer available in the mobile devices. The recognition of ADL is composed by several stages, including data acquisition, data processing, and artificial intelligence methods. The artificial intelligence methods used are related to pattern recognition, and this study focuses on the use of Artificial Neural Networks (ANN). The data processing includes data cleaning, and the feature extraction techniques to define the inputs for the ANN. Due to the low processing power and memory of the mobile devices, they should be mainly used to acquire the data, applying an ANN previously trained for the identification of the ADL. The main purpose of this paper is to present a new method based on ANN for the identification of a defined set of ADL with a reliable accuracy. This paper also presents a comparison of different types of ANN in order to choose the type for the implementation of the final model. Results of this research probes that the best accuracies are achieved with Deep Neural Networks (DNN) with an accuracy higher than 80%. The results obtained are similar with other studies, but we compared tree types of ANN in order to discover the best method in order to obtain these results with less memory, verifying that, after the generation of the model, the DNN method, when compared with others, is also the fastest to obtain the results with better accuracy.

scholarly journals A SURVEY OF ARTIFICIAL INTELLIGENCE METHODS IN INTRUSION DETECTION TASKS

InterConf ◽  
2021 ◽  
pp. 443-449
Author(s):  
Oleksandr Shmatko ◽  
German Zviertsev
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Intrusion Detection ◽  
Continuous Administration ◽  
Network Attacks ◽  
Artificial Intelligence Methods ◽  
The Neural Network

There are many methods for detecting network attacks, but since attacks are constantly changing, special databases of rules or signatures to detect attacks require continuous administration, it becomes necessary to add new rules. One of the ways to eliminate this problem is to use neural networks as a mechanism to detect network attacks. In contrast to the signature-based approach, the neural network analyzes information and provides information about the attacks that it is trained to recognize. In addition, neural networks have the advantage of being able to adapt to previously unknown attacks and detect them. That is why the development of software based on neural networks is relevant.

Neural modeling of the truck vehicle operation system

2019 ◽  
Vol 126 ◽  
pp. 123-135
Author(s):  
Paulina Owczarek ◽  
Katarzyna Jóźwiak
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Computer Software ◽  
Total Weight ◽  
Neural Modeling ◽  
Operation System ◽  
Maintenance System ◽  
Transport Services ◽  
Artificial Intelligence Methods ◽  
Vehicle Operation

The purpose of the work is to develop a model of a truck maintenance system using artificial intelligence methods. Based on a thorough analysis of the literature, criteria and characteristics have been defined that affect the maintenance system of vehicles. Trucks with a permissible total weight of 3.5 tons were tested, which provide transport services in Poland and constitute a fleet of transport companies from the SME sector. MLP (Multi-Layered Perceptron) neural networks were modeled by using computer software.

Sign in / Sign up

Export Citation Format

Share Document