Search results for "NEURAL NETWORK"
showing 10 items of 1385 documents
Classical Training Methods
2006
This chapter reviews classical training methods for multilayer neural networks. These methods are widely used for classification and function modelling tasks. Nevertheless, they show a number of flaws or drawbacks that should be addressed in the development of such systems. They work by searching the minimum of an error function which defines the optimal behaviour of the neural network. Different standard problems are used to show the capabilities of these models; in particular, we have benchmarked the algorithms in a nonlinear classification problem and in three function modelling problems.
The use of artificial intelligence techniques to optimise and control injection moulding processes
1999
In the paper a typical injection moulding process on a single-screw extrusion machine aimed to the production of axisymmetric polypropylene dishes for alimentary use has been investigated. First of all the most important process parameters have been individuated; subsequently a wide testing hyperspace has been investigated, at varying the process parameters in a large range. For each combination both some geometrical characteristics of the obtained component have been measured and the occurrence of defects has been verified. The largest part of the available data have been used to train a neural network aimed to explain the process dynamics. Furthermore an offline control system, based on f…
Cloud screening with combined MERIS and AATSR images
2009
This paper presents a cloud screening algorithm based on ensemble methods that exploits the combined information from both MERIS and AATSR instruments on board ENVISAT in order to improve current cloud masking products for both sensors. The first step is to analyze the synergistic use of MERIS and AATSR images in order to extract some physically-based features increasing the separability of clouds and surface. Then, several artificial neural networks are trained using different sets of input features and different sets of training samples depending on acquisition and surface conditions. Finally, outputs of the trained neural networks are combined at the decision level to construct a more ac…
Deep learning strategies for automatic fault diagnosis in photovoltaic systems by thermographic images
2021
Abstract Losses of electricity production in photovoltaic systems are mainly caused by the presence of faults that affect the efficiency of the systems. The identification of any overheating in a photovoltaic module, through the thermographic non-destructive test, may be essential to maintain the correct functioning of the photovoltaic system quickly and cost-effectively, without interrupting its normal operation. This work proposes a system for the automatic classification of thermographic images using a convolutional neural network, developed via open-source libraries. To reduce image noise, various pre-processing strategies were evaluated, including normalization and homogenization of pi…
Pose classification using support vector machines
2000
In this work a software architecture is presented for the automatic recognition of human arm poses. Our research has been carried on in the robotics framework. A mobile robot that has to find its path to the goal in a partially structured environment can be trained by a human operator to follow particular routes in order to perform its task quickly. The system is able to recognize and classify some different poses of the operator's arms as direction commands like "turn-left", "turn-right", "go-straight", and so on. A binary image of the operator silhouette is obtained from the gray-level input. Next, a slice centered on the silhouette itself is processed in order to compute the eigenvalues …
Artificial Neural Networks to assess energy and environmental performance of buildings: An Italian case study
2019
Abstract Approximately 40% of the European energy consumption and a large proportion of environmental impacts are related to the building sector. However, the selection of adequate and correct designs can provide considerable energy savings and reduce environmental impacts. To achieve this objective, a simultaneous energy and environmental assessment of a building's life cycle is necessary. To date, the resolution of this complex problem is entrusted to numerous software and calculation algorithms that are often complex to use. They involve long diagnosis phases and are characterised by the lack of a common language. Despite the efforts by the scientific community in the building sector, th…
Application of optimized artificial intelligence algorithm to evaluate the heating energy demand of non-residential buildings at European level
2019
Abstract A reliable preliminary forecast of heating energy demand of a building by using a detailed dynamic simulation software typically requires an in-depth knowledge of the thermal balance, several input data and a very skilled user. The authors will describe how to use Artificial Neural Networks to predict the demand for thermal energy linked to the winter climatization of non-residential buildings. To train the neural network it was necessary to develop an accurate energy database that represents the basis of the training of a specific Artificial Neural Networks. Data came from detailed dynamic simulations performed in the TRNSYS environment. The models were built according to the stan…
CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning
2020
Reinforcement Learning (RL) is a general framework concerned with an agent that seeks to maximize rewards in an environment. The learning typically happens through trial and error using explorative methods, such as \(\epsilon \)-greedy. There are two approaches, model-based and model-free reinforcement learning, that show concrete results in several disciplines. Model-based RL learns a model of the environment for learning the policy while model-free approaches are fully explorative and exploitative without considering the underlying environment dynamics. Model-free RL works conceptually well in simulated environments, and empirical evidence suggests that trial and error lead to a near-opti…
On the use of artificial intelligence tools for fracture forecast in cold forming operations
2006
Abstract The design of cold forming processes requires the availability of a procedure able to deal with the prevention of ductile fracture. In fact, the ability to predict fracture represents a powerful tool to improve the production quality in mechanical industry. In this paper, artificial intelligence (AI) techniques are applied to ductile fracture prediction in cold forming operations. The main advantage of the application of AI tools and in particular, of artificial neural networks (ANN), is the possibility to obtain a predictive tool with a wide applicability. The prediction results obtained in this paper fully demonstrate the usefulness of the proposed approach.
The SESAMO early warning system for rainfall-triggered landslides
2016
The development of Web-based information systems coupled with advanced monitoring systems could prove to be extremely useful in landslide risk management and mitigation. A new frontier in the field of rainfall-triggered landslides (RTLs) lies in the real-time modelling of the relationship between rainfall and slope stability; this requires an intensive monitoring of some key parameters that could be achieved through the use of modern and often low-cost technologies. This work describes an integrated information system for early warning of RTLs that has been deployed and tested, in a prototypal form, for an Italian pilot site. The core of the proposed system is a wireless sensor network coll…