Neural network-based wind vector retrieval from satellite scatterometer data

Obtaining wind vectors over the ocean is important for weather forecasting and ocean modelling. Several satellite systems used operationally by meteorological agencies utilise scatterometers to infer wind vectors over the oceans. In this paper we present the results of using novel neural network based techniques to estimate wind vectors from such data. The problem is partitioned into estimating wind speed and wind direction. Wind speed is modelled using a multi-layer perceptron (MLP) and a sum of squares error function. Wind direction is a periodic variable and a multi-valued function for a given set of inputs; a conventional MLP fails at this task, and so we model the full periodic probability density of direction conditioned on the satellite derived inputs using a Mixture Density Network (MDN) with periodic kernel functions. A committee of the resulting MDNs is shown to improve the results.

Short-term electricity demand and gas price forecasts using wavelet transforms and adaptive models

This paper presents some forecasting techniques for energy demand and price prediction, one day ahead. These techniques combine wavelet transform (WT) with fixed and adaptive machine learning/time series models (multi-layer perceptron (MLP), radial basis functions, linear regression, or GARCH). To create an adaptive model, we use an extended Kalman filter or particle filter to update the parameters continuously on the test set. The adaptive GARCH model is a new contribution, broadening the applicability of GARCH methods. We empirically compared two approaches of combining the WT with prediction models: multicomponent forecasts and direct forecasts. These techniques are applied to large sets of real data (both stationary and non-stationary) from the UK energy markets, so as to provide comparative results that are statistically stronger than those previously reported. The results showed that the forecasting accuracy is significantly improved by using the WT and adaptive models. The best models on the electricity demand/gas price forecast are the adaptive MLP/GARCH with the multicomponent forecast; their MSEs are 0.02314 and 0.15384 respectively.

Macrophages and lymphocyte responiveness to mitogen

Purified B-cells fail to proliferate in response to the strong thymus-independent (TI) antigen Lipopolysaccharide (LPS) in the absence of macrophages (Corbel and Melchers, 1983). The fact that macrophages, or factors derived from them are required is supported by the inability of marginal zone B-cells in infants to respond to highly virulent strains of bacteria such as Neisseria meningitidis and Streptococcus pneumoniae (Timens, 1989). This may be due to the lack of CD21 expression on B-cells in infants which could associate with its co-receptor (C3d) on adjacent macrophages. It is not clear whether cell surface contacts and/or soluble products are involved in lymphocyte-macrophage interactions in response to certain antigens. This thesis describes the importance of the macrophage in lymphocyte responses to T-dependent (TD) and TI antigens. The major findings of this thesis were as follows: (1). Macrophages were essential for a full proliferative response to a range of T - and B-cell mitogens and TI-1 and TI-2 antigens, including Concanavalin A, LPS, Pokeweed mitogen (PWM), Dextran sulphate, Phytohaemagglutinin-P (PHA-P) and Poly[I][C]. (2). A ratio of 1 macrophage to 1000 lymphocytes was sufficient for the mitogens to exert their effects. (3). The optimal conditions were established for the activation of an oxidative burst in cells of the monocyte/macrophage lineage as measured by luminometry. The order of ability was OpZ >PMA/lonomycin >f-MLP >Con A >DS >PHA >Poly[I][C] >LPS >PWM. Responses were only substantial and protracted with OpZ and PMA. Peritoneal macrophages were the most responsive cells, whereas splenic and alveolar macrophages were significantly less active and no response could be elicited with Kupffer cells, thus demonstrating heterogeneity between macrophages. (4). Activated macrophages that were then fixed with paraformaldehyde were unable to restore mitogenic responsiveness, even with a ratio of 1 macrophage to 5 lymphocytes. (5). Although highly purified T- and B-cells could respond to mitogen provided live macrophages were present, maximum activation was only observed when all 3 cell types were present. (6). Supernatants from purified macrophage cultures treated with a range of activators were able to partially restore lymphocyte responses to mitogen in macrophage-depleted splenocyte cultures, and purified T - and B-cell cultures. In fact supernatants from macrophages treated with LPS for only 30 minutes could restore responsiveness. Supernatants from OpZ treated macrophages were without effect. (7). Macrophage supernatants could not induce proliferation in the absence of mitogen. They therefore provide a co-mitogenic signal required by lymphocytes in order to respond to mitogen. (8). Macrophage product profiles revealed that LPS and Con A-treated macrophage supernatants showed elevated levels of IL-1β, TNF -α L TB4 and TXB2. These products were therefore good candidates as the co-mitogenic factor. The possible inhibitory factors secreted by OpZ-treated macrophages were PGE2, IL-10 and NO. (9). The removal of cytokines, eicosanoids and TNF-α from LPS-treated macrophage supernatants using Cycloheximide, Dexamethasone and an MMPI respectively, resulted in the inability of these supernatants to restore macrophage-depleted lymphocyte responses to mitogen. (10). rIL-1β and rTNF-α are co-mitogenic factors, as macrophage-depleted lymphocytes incubated with rIL-1β and rTNF-α can respond to mitogen.

Solving a Direct Marketing Problem by Three Types of ARTMAP Neural Networks

An important task for a direct mailing company is to detect potential customers in order to avoid unnecessary and unwanted mailing. This paper describes a non-linear method to predict profiles of potential customers using dARTMAP, ARTMAP-IC, and Fuzzy ARTMAP neural networks. The paper discusses advantages of the proposed approaches over similar techniques based on MLP neural networks.

Fourier Neural Networks: An Approach with Sinusoidal Activation Functions

* Supported by INTAS 2000-626, INTAS YSF 03-55-1969, INTAS INNO 182, and TIC 2003-09319-c03-03.

AllerTOP v.2 - a server for in silico prediction of allergens

Allergy is an overreaction by the immune system to a previously encountered, ordinarily harmless substance - typically proteins - resulting in skin rash, swelling of mucous membranes, sneezing or wheezing, or other abnormal conditions. The use of modified proteins is increasingly widespread: their presence in food, commercial products, such as washing powder, and medical therapeutics and diagnostics, makes predicting and identifying potential allergens a crucial societal issue. The prediction of allergens has been explored widely using bioinformatics, with many tools being developed in the last decade; many of these are freely available online. Here, we report a set of novel models for allergen prediction utilizing amino acid E-descriptors, auto- and cross-covariance transformation, and several machine learning methods for classification, including logistic regression (LR), decision tree (DT), naïve Bayes (NB), random forest (RF), multilayer perceptron (MLP) and k nearest neighbours (kNN). The best performing method was kNN with 85.3% accuracy at 5-fold cross-validation. The resulting model has been implemented in a revised version of the AllerTOP server (http://www.ddg-pharmfac.net/AllerTOP). © Springer-Verlag 2014.

Influence of QT correction on temporal and amplitude features for human identification via ECG

Identification of humans via ECG is being increasingly studied because it can have several advantages over the traditional biometric identification techniques. However, difficulties arise because of the heartrate variability. In this study we analysed the influence of QT interval correction on the performance of an identification system based on temporal and amplitude features of ECG. In particular we tested MLP, Naive Bayes and 3-NN classifiers on the Fantasia database. Results indicate that QT correction can significantly improve the overall system performance. © 2013 IEEE.

CO2 emissions reduction of Chinese light manufacturing industries:a novel RAM-based global Malmquist-Luenberger productivity index

Climate change has become one of the most challenging issues facing the world. Chinese government has realized the importance of energy conservation and prevention of the climate changes for sustainable development of China's economy and set targets for CO2 emissions reduction in China. In China industry contributes 84.2% of the total CO2 emissions, especially manufacturing industries. Data envelopment analysis (DEA) and Malmquist productivity (MP) index are the widely used mathematical techniques to address the relative efficiency and productivity of a group of homogenous decision making units, e.g. industries or countries. However, in many real applications, especially those related to energy efficiency, there are often undesirable outputs, e.g. the pollutions, waste and CO2 emissions, which are produced inevitably with desirable outputs in the production. This paper introduces a novel Malmquist-Luenberger productivity (MLP) index based on directional distance function (DDF) to address the issue of productivity evolution of DMUs in the presence of undesirable outputs. The new RAM (Range-adjusted measure)-based global MLP index has been applied to evaluate CO2 emissions reduction in Chinese light manufacturing industries. Recommendations for policy makers have been discussed.

Freeway travel time estimation and prediction using dynamic neural networks

Providing transportation system operators and travelers with accurate travel time information allows them to make more informed decisions, yielding benefits for individual travelers and for the entire transportation system. Most existing advanced traveler information systems (ATIS) and advanced traffic management systems (ATMS) use instantaneous travel time values estimated based on the current measurements, assuming that traffic conditions remain constant in the near future. For more effective applications, it has been proposed that ATIS and ATMS should use travel times predicted for short-term future conditions rather than instantaneous travel times measured or estimated for current conditions. ^ This dissertation research investigates short-term freeway travel time prediction using Dynamic Neural Networks (DNN) based on traffic detector data collected by radar traffic detectors installed along a freeway corridor. DNN comprises a class of neural networks that are particularly suitable for predicting variables like travel time, but has not been adequately investigated for this purpose. Before this investigation, it was necessary to identifying methods for data imputation to account for missing data usually encountered when collecting data using traffic detectors. It was also necessary to identify a method to estimate the travel time on the freeway corridor based on data collected using point traffic detectors. A new travel time estimation method referred to as the Piecewise Constant Acceleration Based (PCAB) method was developed and compared with other methods reported in the literatures. The results show that one of the simple travel time estimation methods (the average speed method) can work as well as the PCAB method, and both of them out-perform other methods. This study also compared the travel time prediction performance of three different DNN topologies with different memory setups. The results show that one DNN topology (the time-delay neural networks) out-performs the other two DNN topologies for the investigated prediction problem. This topology also performs slightly better than the simple multilayer perceptron (MLP) neural network topology that has been used in a number of previous studies for travel time prediction.^

Freeway Travel Time Estimation and Prediction Using Dynamic Neural Networks

Providing transportation system operators and travelers with accurate travel time information allows them to make more informed decisions, yielding benefits for individual travelers and for the entire transportation system. Most existing advanced traveler information systems (ATIS) and advanced traffic management systems (ATMS) use instantaneous travel time values estimated based on the current measurements, assuming that traffic conditions remain constant in the near future. For more effective applications, it has been proposed that ATIS and ATMS should use travel times predicted for short-term future conditions rather than instantaneous travel times measured or estimated for current conditions. This dissertation research investigates short-term freeway travel time prediction using Dynamic Neural Networks (DNN) based on traffic detector data collected by radar traffic detectors installed along a freeway corridor. DNN comprises a class of neural networks that are particularly suitable for predicting variables like travel time, but has not been adequately investigated for this purpose. Before this investigation, it was necessary to identifying methods for data imputation to account for missing data usually encountered when collecting data using traffic detectors. It was also necessary to identify a method to estimate the travel time on the freeway corridor based on data collected using point traffic detectors. A new travel time estimation method referred to as the Piecewise Constant Acceleration Based (PCAB) method was developed and compared with other methods reported in the literatures. The results show that one of the simple travel time estimation methods (the average speed method) can work as well as the PCAB method, and both of them out-perform other methods. This study also compared the travel time prediction performance of three different DNN topologies with different memory setups. The results show that one DNN topology (the time-delay neural networks) out-performs the other two DNN topologies for the investigated prediction problem. This topology also performs slightly better than the simple multilayer perceptron (MLP) neural network topology that has been used in a number of previous studies for travel time prediction.

Protótipo de rastreador solar de um eixo baseado em microcontrolador

The increase in the efficiency of photo-voltaic systems has been the object of various studies the past few years. One possible way to increase the power extracted by a photovoltaic panel is the solar tracking, performing its movement in order to follow the sun’s path. One way to activate the tracking system is using an electric induction motor, which should have sufficient torque and low speed, ensuring tracking accuracy. With the use of voltage source inverters and logic devices that generate the appropriate switching is possible to obtain the torque and speed required for the system to operate. This paper proposes the implementation of a angular position sensor and a driver to be applied in solar tracker built at a Power Electronics and Renewable Energies Laboratory, located in UFRN. The speed variation of the motor is performed via a voltage source inverter whose PWM command to actuate their keys will be implemented in an FPGA (Field Programmable Gate Array) device and a TM4C microcontroller. A platform test with an AC induction machine of 1.5 CV was assembled for the comparative testing. The angular position sensor of the panel is implemented in a ATMega328 microcontroller coupled to an accelerometer, commanded by an Arduino prototyping board. The solar position is also calculated by the microcontroller from the geographic coordinates of the site where it was placed, and the local time and date obtained from an RTC (Real-Time Clock) device. A prototype of a solar tracker polar axis moved by a DC motor was assembled to certify the operation of the sensor and to check the tracking efficiency.

Implementação de uma matriz de neurônios dinamicamente reconfigurável para descrição de topologias de redes neurais artificiais multilayer perceptrons

The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Implementação de uma matriz de neurônios dinamicamente reconfigurável para descrição de topologias de redes neurais artificiais multilayer perceptrons

The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Functionals for TDDFT description of electron transport in nanostructures

La Teoria di Densità Funzionale (DFT) e la sua versione dipendente dal tempo (TDDFT) sono strumenti largamente usati per simulare e calcolare le proprietà statiche e dinamiche di sistemi con elettroni interagenti. La precisione del metodo si basa su una serie di approssimazioni degli effetti di exchange correlation fra gli elettroni, descritti da un funzionale della sola densità di carica. Nella presente tesi viene testata l'affidabilità del funzionale Mixed Localization Potential (MLP), una media pesata fra Single Orbital Approximation (SOA) e un potenziale di riferimento, ad esempio Local Density Approximation (LDA). I risultati mostrano capacità simulative superiori a LDA per i sistemi statici (curando anche un limite di LDA noto in letteratura come fractional dissociation) e dei progressi per sistemi dinamici quando si sviluppano correnti di carica. Il livello di localizzazione del sistema, inteso come la capacità di un elettrone di tenere lontani da sé altri elettroni, è descritto dalla funzione Electron Localization Function (ELF). Viene studiato il suo ruolo come guida nella costruzione e ottimizzazione del funzionale MLP.

Estudo comparativo de dois conversores Boost quadrático com comutação suave monochaveados para aplicação de rastreamento de máxima potência em sistemas fotovoltaicos

This paper makes a comparative study of two Soft Single Switched Quadratic Boost Converters (SSS1 and SSS2) focused on Maximum Power Point Tracking (MPPT) of a PV array using Perturb and Observe (P&O) algorithm. The proposed converters maintain the static gain characteristics and dynamics of the original converter with the advantage of considerably reducing the switching losses and Electromagnetic Interference (EMI). It is displayed the input voltage Quadratic Boost converter modeling; qualitative and quantitative analysis of soft switching converters, defining the operation principles, main waveforms, time intervals and the state variables in each operation steps, phase planes of resonant elements, static voltage gain expressions, analysis of voltage and current efforts in semiconductors and the operational curves at 200 W to 800 W. There are presented project of PI, PID and PID + Notch compensators for MPPT closed-loop system and resonant elements design. In order to analyze the operation of a complete photovoltaic system connected to the grid, it was chosen to simulate a three-phase inverter using the P-Q control theory of three-phase instantaneous power. Finally, the simulation results and experimental with the necessary comparative analysis of the proposed converters will be presented.