Repository logo
 
Loading...
Profile Picture
Person

Khosravani, Hamid Reza

Search Results

Now showing 1 - 10 of 10
  • Artificial neural network models: data selection and online adaptation
    Publication . Khosravani, Hamid Reza; Ruano, A. E.; Ferreira, Pedro Miguel Frazão F.
    Energy consumption has been increasing steadily due to globalization and industrialization. Studies have shown that buildings have the biggest proportion in energy consumption; for example in European Union countries, energy consumption in buildings represents around 40% of the total energy consumption. Hence this PhD was intended towards managing the energy consumed by Heating, Ventilating and Air Conditioning (HVAC) systems in buildings benefiting from Model Predictive Control (MPC) technique. To achieve this goal, artificial intelligence models such as neural networks and Support Vector Machines (SVM) have been proposed because of their high potential capabilities of performing accurate nonlinear mappings between inputs and outputs in real environments which are not noise-free. In this PhD, Radial Basis Function Neural Networks (RBFNN) as a promising class of Artificial Neural Networks (ANN) were considered to model a sequence of time series processes where the RBFNN models were built using Multi Objective Genetic Algorithm (MOGA) as a design platform. Regarding the design of such models, two main challenges were tackled; data selection and model adaptation. Since RBFNNs are data driven models, the performance of such models relies, to a good extent, on selecting proper data throughout the design phase, covering the whole input-output range in which they will be employed. The convex hull algorithms can be applied as methods for data selection; however the use of conventional implementations of these methods in high dimensions, due to their high complexity, is not feasible. As the first phase of this PhD, a new randomized approximation convex hull algorithm called ApproxHull was proposed for high dimensions so that it can be used in an acceptable execution time, and with low memory requirements. Simulation results showed that applying ApproxHull as a filter data selection method (i.e., unsupervised data selection method) could improve the performance of the classification and regression models, in comparison with random data selection method. In addition, ApproxHull was employed in real applications in terms of three case studies. The first two were in association with applying predictive models for energy saving. The last case study was related to segmentation of lesion areas in brain Computed Tomography (CT) images. The evaluation results showed that applying ApproxHull in MOGA could result in models with an acceptable level of accuracy. Specifically, the results obtained from the third case study demonstrated that ApproxHull is capable of being applied on large size data sets in high dimensions. Besides the random selection method, it was also compared with an entropy based unsupervised data selection method and a hybrid method involving ApproxHull and the entropy based method. Based on the simulation results, for most cases, ApproxHull and the hybrid method achieved a better performance than the others. In the second phase of this PhD, a new convex-hull-based sliding window online adaptation method was proposed. The goal was to update the offline predictive RBFNN models used in HVAC MPC technique, where these models are applied to processes in which the data input-output range changes over time. The idea behind the proposed method is capturing a new arriving point at each time instant which reflects a new range of data by comparing the point with current convex hull presented via ApproxHull. In this situation the underlying model’s parameters are updated based on the new point and a sliding window of some past points. The simulation results showed that not only the proposed method could efficiently update the model while a good level of accuracy is kept but also it was comparable with other methods.
  • A support vector machine seismic detector for early-warning applications
    Publication . Ruano, Antonio; Madureira, G.; Barros, O.; Khosravani, Hamid Reza; Ruano, M. Graça; Ferreira, P. M.
    This paper extends a Support Vector Machine (SVM) approach for the detection of seismic events, at the level of a seismic station. In previous works, it was shown that this approach produced excellent results, in terms of the Recall and Specificity measures, whether applied off-line or in a continuous scheme. The drawback was the time taken for achieving the detection, too large to be applied in a Early-Warning System (EWS). This paper shows that, by using alternative input features, a similar performance can be obtained, with a significant reduction in detection time. Additionally, it is experimentally proved that, whether off-line or in continuous operation, the best results are obtained when the SVM detector is trained with data originated from the respective seismic station.
  • PVM-based intelligent predictive control of HVAC systems
    Publication . Ruano, Antonio; Pesteh, S.; Silva, S.; Duarte, H.; Mestre, G.; Ferreira, P. M.; Khosravani, Hamid Reza; Horta, R.
    This paper describes the application of a complete MBPC solution for existing HVAC systems, with a focus on the implementation of the objective function employed. Real-time results obtained with this solution, in terms of economical savings and thermal comfort, are compared with standard, temperature regulated control.(1) (C) 2016, IFAC (International Federation of Antomatic Control) Hosting by Elsevier Ltd. All rights reserved.
  • Seismic detection using support vector machines
    Publication . Ruano, Antonio; Madureira, G.; Barros, O.; Khosravani, Hamid Reza; Ruano, M. Graça; Ferreira, P. M.
    This study describes research to design a seismic detection system to act at the level of a seismic station, providing a similar role to that of STA/LTA ratio-based detection algorithms. In a first step, Multi-Layer Perceptrons (MLPs) and Support Vector Machines (SVMs), trained in supervised mode, were tested. The sample data consisted of 2903 patterns extracted from records of the PVAQ station, one of the seismographic network’s stations of the Institute of Meteorology of Portugal (IM). Records’ spectral variations in time and characteristics were reflected in the input ANN patterns, as a set of values of power spectral density at selected frequencies. To ensure that all patterns of the sample data were within the range of variation of the training set, we used an algorithm to separate the universe of data by hyper-convex polyhedrons, determining in this manner a set of patterns that have a mandatory part of the training set. Additionally, an active learning strategy was conducted, by iteratively incorporating poorly classified cases in the training set. The proposed system best results, in terms of sensitivity and selectivity in the whole data ranged between 98% and 100%. These results compare very favourably with the ones obtained by the existing detection system, 50%, and with other approaches found in the literature. Subsequently, the system was tested in continuous operation for unseen (out of sample) data, and the SVM detector obtained 97.7% and 98.7% of sensitivity and selectivity, respectively. The classifier presented 88.4% and 99.4% of sensitivity and selectivity when applied to data of a different seismic station of IM. Due to the input features used, the average time taken for detection with this approach is in the order of 100 s. This is too long to be used in an early-warning system. In order to decrease this time, an alternative set of input features was tested. A similar performance was obtained, with a significant reduction in the average detection time (around 1.3 s). Additionally, it was experimentally proved that, whether off-line or in continuous operation, the best results are obtained when the SVM detector is trained with data originated from the respective seismic station.
  • A simple algorithm for convex hull determination in high dimensions
    Publication . Khosravani, Hamid Reza; Ruano, Antonio; Ferreira, P. M.
    Selecting suitable data for neural network training, out of a larger set, is an important task. For approximation problems, as the role of the model is a nonlinear interpolator, the training data should cover the whole range where the model must be used, i.e., the samples belonging to the convex hull of the data should belong to the training set. Convex hull is also widely applied in reducing training data for SVM classification. The determination of the samples in the convex-hull of a set of high dimensions, however, is a time-complex task. In this paper, a simple algorithm for this problem is proposed.
  • The IMBPC HVAC system: a complete MBPC solution for existing HVAC systems
    Publication . Ruano, Antonio; Pesteh, Shabnam; Silva, Sergio; Duarte, Helder; Mestre, Gonçalo; Ferreira, Pedro M.; Khosravani, Hamid Reza; Horta, Ricardo
    This paper introduces the Intelligent MBPC (IMBPC) HVAC system, a complete solution to enable Model Based Predictive Control (MBPC) of existing HVAC installations in a building. The IMPBC HVAC minimizes the economic cost needed to maintain controlled rooms in thermal comfort during the periods of occupation. The hardware and software components of the IMBPC system are described, with a focus on the MBPC algorithm employed.The installation of IMBPC HVAC solution in a University building is described, and the results obtained in terms of economical savings and thermal comfort obtained are compared with standard, temperature regulated control. (C) 2016 Elsevier B.V. All rights reserved.
  • A comparison of energy consumption prediction models based on neural networks of a bioclimatic building
    Publication . Khosravani, Hamid Reza; Del Mar Castilla, Maria; Berenguel, Manuel; Ruano, Antonio; Ferreira, Pedro M.
    Energy consumption has been increasing steadily due to globalization and industrialization. Studies have shown that buildings are responsible for the biggest proportion of energy consumption; for example in European Union countries, energy consumption in buildings represents around 40% of the total energy consumption. In order to control energy consumption in buildings, different policies have been proposed, from utilizing bioclimatic architectures to the use of predictive models within control approaches. There are mainly three groups of predictive models including engineering, statistical and artificial intelligence models. Nowadays, artificial intelligence models such as neural networks and support vector machines have also been proposed because of their high potential capabilities of performing accurate nonlinear mappings between inputs and outputs in real environments which are not free of noise. The main objective of this paper is to compare a neural network model which was designed utilizing statistical and analytical methods, with a group of neural network models designed benefiting from a multi objective genetic algorithm. Moreover, the neural network models were compared to a naive autoregressive baseline model. The models are intended to predict electric power demand at the Solar Energy Research Center (Centro de Investigacion en Energia SOLar or CIESOL in Spanish) bioclimatic building located at the University of Almeria, Spain. Experimental results show that the models obtained from the multi objective genetic algorithm (MOGA) perform comparably to the model obtained through a statistical and analytical approach, but they use only 0.8% of data samples and have lower model complexity.
  • A convex hull-based data selection method for data driven models
    Publication . Khosravani, Hamid Reza; Ruano, Antonio; Ferreira, P. M.
    The accuracy of classification and regression tasks based on data driven models, such as Neural Networks or Support Vector Machines, relies to a good extent on selecting proper data for designing these models, covering the whole input range in which they will be employed. The convex hull algorithm can be applied as a method for data selection; however the use of conventional implementations of this method in high dimensions, due to its high complexity, is not feasible. In this paper, we propose a randomized approximation convex hull algorithm which can be used for high dimensions in an acceptable execution time, and with low memory requirements. Simulation results show that data selection by the proposed algorithm (coined as ApproxHull) can improve the performance of classification and regression models, in comparison with random data selection. (C) 2016 Elsevier B.V. All rights reserved.
  • A comparison of four data selection methods for artificial neural networks and support vector machines
    Publication . Khosravani, Hamid Reza; Ruano, Antonio; Ferreira, P. M.
    The performance of data-driven models such as Artificial Neural Networks and Support Vector Machines relies to a good extent on selecting proper data throughout the design phase. This paper addresses a comparison of four unsupervised data selection methods including random, convex hull based, entropy based and a hybrid data selection method. These methods were evaluated on eight benchmarks in classification and regression problems. For classification, Support Vector Machines were used, while for the regression problems, Multi-Layer Perceptrons were employed. Additionally, for each problem type, a non-dominated set of Radial Basis Functions Neural Networks were designed, benefiting from a Multi Objective Genetic Algorithm. The simulation results showed that the convex hull based method and the hybrid method involving convex hull and entropy, obtain better performance than the other methods, and that MOGA designed RBFNNs always perform better than the other models. (C) 2017, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.
  • An Intelligent Weather Station
    Publication . Mestre, Goncalo; Ruano, Antonio; Duarte, Helder; Silva, Sergio; Khosravani, Hamid Reza; Pesteh, Shabnam; Ferreira, Pedro M.; Horta, Ricardo
    Accurate measurements of global solar radiation, atmospheric temperature and relative humidity, as well as the availability of the predictions of their evolution over time, are important for different areas of applications, such as agriculture, renewable energy and energy management, or thermal comfort in buildings. For this reason, an intelligent, light-weight, self-powered and portable sensor was developed, using a nearest-neighbors (NEN) algorithm and artificial neural network (ANN) models as the time-series predictor mechanisms. The hardware and software design of the implemented prototype are described, as well as the forecasting performance related to the three atmospheric variables, using both approaches, over a prediction horizon of 48-steps-ahead.