The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
It is of significant importance for any classification and recognition system, which claims near or better than human performance to be immune to small perturbations in the dataset. Researchers found out that neural networks are not very robust to small perturbations and can easily be fooled to persistently misclassify by adding a particular class of noise in the test data. This, so-called adversarial...
Business analytics techniques help mine and analyze business/financial data. For instance, a structural support vector machine (SSVM) can be used to perform classification on complex inputs such as the nodes of a graph structure. We connect collaborating companies in the information technology sector in an undirected graph and use an SSVM to predict positive or negative movement in their stock prices...
Adversarial examples are augmented data points generated by imperceptible perturbation of input samples. They have recently drawn much attention with the machine learning and data mining community. Being difficult to distinguish from real examples, such adversarial examples could change the prediction of many of the best learning models including the state-of-the-art deep learning models. Recent attempts...
Engineering design process requires modeling and optimization to find optimum design parameters. While direct optimization only exploits time consuming but accurate fine model, surrogate based optimization exploits less accurate but fast coarse model to reduce the overall computational effort. In this work, space mapping with inverse difference technique is applied to antenna design problem together...
With the growth of information organized in hierarchical databases, it is essential to develop automated approaches for classifying data instances (e.g., documents, proteins and images) into hierarchies. Several classification approaches have been developed that exploit the hierarchical structure prevalent within these underlying databases. One commonly used approach is to train local one-versus-rest...
Reservoir management is a key component in effective water supply management. In real systems, reservoir operation is typically governed by a decision rule, an input output relationship that prescribes reservoir release as a function of inflows, storage and other inputs. In this study, fuzzy inference decision rules (FIDRs) for reservoir operation are developed. Due to their highly flexible nature...
Here I apply three reinforcement learning methods to the full, continuous action, swing-up acrobot control benchmark problem. These include two approaches from the literature: CACLA and NM-SARSA and a novel approach which I refer to as Nelder Mead-SARSA. Nelder Mead-SARSA, like NMSARSA, directly optimises the state-action value function for action selection, in order to allow continuous action reinforcement...
Modern process plants are becoming more and more complex with high demands placed on design, engineering and operation. Throughout the life-cycle of process plants there is always the typical conflict involving costs, time and quality. One way of resolving this conflict is to employ simulation technology as it can be used to answer questions relating to engineering and operation earlier and with lower...
The recognition of continuous dimensional emotion remains a challenging task due to large variations in the expression of emotion, and the difficulty of modeling emotion as temporal processes. This work proposes the use of a Nonlinear AutoRegressive with eXogenous inputs recurrent neural network (NARX-RNN) to learn emotional patterns in a given a dataset. The application of particle swarm optimisation...
This paper describes a Model Predictive Control (MPC) algorithm in which a Radial Basis Function (RBF) neural network is used as a dynamic model of the controlled process and it reports training and selection of the RBF model of the benchmark system for MPC. In order to obtain a computationally uncomplicated control scheme, the RBF model is successively linearised on-line, which leads to an easy to...
Having an accurate statistical model of room impulse responses with a minimum number of parameters is of crucial importance in applications such as dereverberation. In this paper, by taking into account the behaviour of the early reflections, we extend the widely-used statistical model proposed by Polack. The squared room impulse response is modelled in each frequency band as the realisation of a...
This paper analyzes the basis of badminton special feature, energy supply characteristics, relationship between physical fitness and special quality, and evaluation theory to establish special quality evaluation index architecture, which can provide better distinction and reliability for badminton players. We adopt standard percentage method and deviation method to establish representative index score...
Modern process plants are becoming more and more complex with high demands placed on design, engineering and operation. Throughout the life cycle of process plants, there is always the typical conflict involving costs, time and quality. One way of resolving this conflict is to employ simulation technology as it can be used to answer questions relating to engineering and operation earlier and with...
The paper approaches the problem of modeling the microwave heating process using Neural Networks. The Neural Network was trained using Matlab and Comsol Multiphysics software. Numerical simulations were made in Comsol Multiphysics, obtaining the necessary input and output data to train the Neural Network. The training was made using Adaptive Neural Network tool from Matlab software.
This paper discusses the control strategies of a fleet of robots, especially the control by the virtual leader. The main contribution consists is to achieve the control of a group of vehicles while following a predefined mission carried out thanks to a virtual leader, and simultaneously avoiding the collisions between the different agents of the group. The approach proposed in this paper is based...
Increasing demands for high precision environmental protection measures regarding particulate matter (PM) emission from industrial productions and non-linear characteristics of spray tower system lead to the application of an intelligent control technique to adequately deal with these complexities. This includes the use of an artificial neural network (ANN) based predictive control strategy and differential...
OpenMP, with its extended parallelism features and support for radically changing HPC architectures, spurred to a surge in developing parallel applications among the HPC application developers community, leading to severe energy consumption issues. Consequently, a notion of addressing the energy consumption issue of HPC applications in an automated fashion increased among compiler developers although...
This paper presents a modeling technique of sequential batch reactor (SBR) for aerobic granular sludge (AGS) using artificial neural network (ANN). A SBR fed with synthetic wastewater was operated at high temperature of 50˚C to study the formation of AGS for simultaneous organics and nutrients removal in 60 days. The feed forward neural network (FFNN) was used to model the nutrients removal process...
Support Vector Regression (SVR) is a flexible regression method, which can be applied directly to NARMAX system identification models. SVR is a one-step convex optimisation process which attempts to maximise generalisation performance. This paper compares SVR performance with that of multi-layer perceptrons and radial basis function networks for varying numbers of time lags included in the model.
Model-based FDI systems are considered here. The problem of constructing the diagnosed system model as well as the automatic search for the best rule base of the residual analyzer is reduced to a set of global optimization tasks. Various optimization problems are considered depending on the chosen technology of the non-analytical model construction as well as that of the residual evaluation. Most...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.