Search results for: signal prediction
705 A Survey of Field Programmable Gate Array-Based Convolutional Neural Network Accelerators
Authors: Wei Zhang
Abstract:
With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.Keywords: deep learning, field programmable gate array, FPGA, hardware accelerator, convolutional neural networks, CNN
Procedia PDF Downloads 119704 Fatigue Crack Growth Rate Measurement by Means of Classic Method and Acoustic Emission
Authors: V. Mentl, V. Koula, P. Mazal, J. Volák
Abstract:
Nowadays, the acoustic emission is a widely recognized method of material damage investigation, mainly in cases of cracks initiation and growth observation and evaluation. This is highly important in structures, e.g. pressure vessels, large steam turbine rotors etc., applied both in classic and nuclear power plants. Nevertheless, the acoustic emission signals must be correlated with the real crack progress to be able to evaluate the cracks and their growth by this non-destructive technique alone in real situations and to reach reliable results when the assessment of the structures' safety and reliability is performed and also when the remaining lifetime should be evaluated. The main aim of this study was to propose a methodology for evaluation of the early manifestations of the fatigue cracks and their growth and thus to quantify the material damage by acoustic emission parameters. Specimens made of several steels used in the power producing industry were subjected to fatigue loading in the low- and high-cycle regimes. This study presents results of the crack growth rate measurement obtained by the classic compliance change method and the acoustic emission signal analysis. The experiments were realized in cooperation between laboratories of Brno University of Technology and West Bohemia University in Pilsen within the solution of the project of the Czech Ministry of Industry and Commerce: "A diagnostic complex for the detection of pressure media and material defects in pressure components of nuclear and classic power plants" and the project “New Technologies for Mechanical Engineering”.Keywords: fatigue, crack growth rate, acoustic emission, material damage
Procedia PDF Downloads 367703 Prognostic Implication of Nras Gene Mutations in Egyptian Adult Acute Myeloid Leukemia
Authors: Doaa M. Elghannam, Nashwa Khayrat Abousamra, Doaa A. Shahin, Enas F. Goda, Hanan Azzam, Emad Azmy, Manal Salah El-Din
Abstract:
Background: The pathogenesis of acute myeloid leukemia (AML) involves the cooperation of mutations promoting proliferation/survival and those impairing differentiation. Point mutations of the NRAS gene are the most frequent somatic mutations causing aberrant signal-transduction in acute myeloid leukemia (AML). Aim: The present work was conducted to study the frequency and prognostic significance of NRAS gene mutations (NRASmut) in de novo Egyptian adult AML. Material and methods: Bone marrow specimens from 150 patients with de novo acute myeloid leukemia and controls were analyzed by genomic PCR-SSCP at codons 12, 13 (exon 1), and 61 (exon 2) for NRAS mutations. Results: NRAS gene mutations was found in 19/150 (12.7%) AML cases, represented more frequently in the FAB subtype M4eo (P = 0.028), and at codon 12, 13 (14of 19; 73.7%). Patients with NRASmut had a significant lower peripheral marrow blasts (P = 0.004, P=0.03) and non significant improved clinical outcome than patients without the mutation. Complete remission rate was (63.2% vs 56.5%; p=0.46), resistant disease (15.8% vs 23.6%; p=0.51), three years overall survival (44% vs 42%; P = 0.85) and disease free survival (42.1% vs 38.9%, P = 0.74). Multivariate analysis showed that age was the strongest unfavorable factor for overall survival (relative risk [RR], 1.9; P = .002), followed by cytogenetics (P = .004). FAB types, NRAS mutation, and leukocytosis were less important. Conclusions: NRAS gene mutation frequency and spectrum differ between biologically distinct subtypes of AML but do not significantly influence prognosis and clinical outcome.Keywords: NRAS Gene, egyptian adult, acute myeloid leukemia, cytogenetics
Procedia PDF Downloads 89702 Feature Selection of Personal Authentication Based on EEG Signal for K-Means Cluster Analysis Using Silhouettes Score
Authors: Jianfeng Hu
Abstract:
Personal authentication based on electroencephalography (EEG) signals is one of the important field for the biometric technology. More and more researchers have used EEG signals as data source for biometric. However, there are some disadvantages for biometrics based on EEG signals. The proposed method employs entropy measures for feature extraction from EEG signals. Four type of entropies measures, sample entropy (SE), fuzzy entropy (FE), approximate entropy (AE) and spectral entropy (PE), were deployed as feature set. In a silhouettes calculation, the distance from each data point in a cluster to all another point within the same cluster and to all other data points in the closest cluster are determined. Thus silhouettes provide a measure of how well a data point was classified when it was assigned to a cluster and the separation between them. This feature renders silhouettes potentially well suited for assessing cluster quality in personal authentication methods. In this study, “silhouettes scores” was used for assessing the cluster quality of k-means clustering algorithm is well suited for comparing the performance of each EEG dataset. The main goals of this study are: (1) to represent each target as a tuple of multiple feature sets, (2) to assign a suitable measure to each feature set, (3) to combine different feature sets, (4) to determine the optimal feature weighting. Using precision/recall evaluations, the effectiveness of feature weighting in clustering was analyzed. EEG data from 22 subjects were collected. Results showed that: (1) It is possible to use fewer electrodes (3-4) for personal authentication. (2) There was the difference between each electrode for personal authentication (p<0.01). (3) There is no significant difference for authentication performance among feature sets (except feature PE). Conclusion: The combination of k-means clustering algorithm and silhouette approach proved to be an accurate method for personal authentication based on EEG signals.Keywords: personal authentication, K-mean clustering, electroencephalogram, EEG, silhouettes
Procedia PDF Downloads 277701 Chaotic Electronic System with Lambda Diode
Authors: George Mahalu
Abstract:
The Chua diode has been configured over time in various ways, using electronic structures like operational amplifiers (AOs) or devices with gas or semiconductors. When discussing the use of semiconductor devices, tunnel diodes (Esaki diodes) are most often considered, and more recently, transistorized configurations such as lambda diodes. The paperwork proposed here uses in the modeling a lambda diode type configuration consisting of two junction field effect transistors (JFET). The original scheme is created in the MULTISIM electronic simulation environment and is analyzed in order to identify the conditions for the appearance of evolutionary unpredictability specific to nonlinear dynamic systems with chaos-induced behavior. The chaotic deterministic oscillator is one autonomous type, a fact that places it in the class of Chua’s type oscillators, the only significant and most important difference being the presence of a nonlinear device like the one mentioned structure above. The chaotic behavior is identified both by means of strange attractor-type trajectories and visible during the simulation and by highlighting the hypersensitivity of the system to small variations of one of the input parameters. The results obtained through simulation and the conclusions drawn are useful in the further research of ways to implement such constructive electronic solutions in theoretical and practical applications related to modern small signal amplification structures, to systems for encoding and decoding messages through various modern ways of communication, as well as new structures that can be imagined both in modern neural networks and in those for the physical implementation of some requirements imposed by current research with the aim of obtaining practically usable solutions in quantum computing and quantum computers.Keywords: chua, diode, memristor, chaos
Procedia PDF Downloads 81700 Assessment of Predictive Confounders for the Prevalence of Breast Cancer among Iraqi Population: A Retrospective Study from Baghdad, Iraq
Authors: Nadia H. Mohammed, Anmar Al-Taie, Fadia H. Al-Sultany
Abstract:
Although breast cancer prevalence continues to increase, mortality has been decreasing as a result of early detection and improvement in adjuvant systemic therapy. Nevertheless, this disease required further efforts to understand and identify the associated potential risk factors that could play a role in the prevalence of this malignancy among Iraqi women. The objective of this study was to assess the perception of certain predictive risk factors on the prevalence of breast cancer types among a sample of Iraqi women diagnosed with breast cancer. This was a retrospective observational study carried out at National Cancer Research Center in College of Medicine, Baghdad University from November 2017 to January 2018. Data of 100 patients with breast cancer whose biopsies examined in the National Cancer Research Center were included in this study. Data were collected to structure a detailed assessment regarding the patients’ demographic, medical and cancer records. The majority of study participants (94%) suffered from ductal breast cancer with mean age 49.57 years. Among those women, 48.9% were obese with body mass index (BMI) 35 kg/m2. 68.1% of them had positive family history of breast cancer and 66% had low parity. 40.4% had stage II ductal breast cancer followed by 25.5% with stage III. It was found that 59.6% and 68.1% had positive oestrogen receptor sensitivity and positive human epidermal growth factor (HER2/neu) receptor sensitivity respectively. In regard to the impact of prediction of certain variables on the incidence of ductal breast cancer, positive family history of breast cancer (P < 0.0001), low parity (P< 0.0001), stage I and II breast cancer (P = 0.02) and positive HER2/neu status (P < 0.0001) were significant predictive factors among the study participants. The results from this study provide relevant evidence for a significant positive and potential association between certain risk factors and the prevalence of breast cancer among Iraqi women.Keywords: Ductal Breast Cancer, Hormone Sensitivity, Iraq, Risk Factors
Procedia PDF Downloads 124699 Analysis and Performance of European Geostationary Navigation Overlay Service System in North of Algeria for GPS Single Point Positioning
Authors: Tabti Lahouaria, Kahlouche Salem, Benadda Belkacem, Beldjilali Bilal
Abstract:
The European Geostationary Navigation Overlay Service (EGNOS) provides an augmentation signal to GPS (Global Positioning System) single point positioning. Presently EGNOS provides data correction and integrity information using the GPS L1 (1575.42 MHz) frequency band. The main objective of this system is to provide a better real-time positioning precision than using GPS only. They are expected to be used with single-frequency code observations. EGNOS offers navigation performance for an open service (OS), in terms of precision and availability this performance gradually degrades as moving away from the service area. For accurate system performance, the service will become less and less available as the user moves away from the EGNOS service. The improvement in position solution is investigated using the two collocated dual frequency GPS, where no EGNOS Ranging and Integrity Monitoring Station (RIMS) exists. One of the pseudo-range was kept as GPS stand-alone and the other was corrected by EGNOS to estimate the planimetric and altimetric precision for different dates. It is found that precision in position improved significantly in the second due to EGNOS correction. The performance of EGNOS system in the north of Algeria is also investigated in terms of integrity. The results show that the horizontal protection level (HPL) value is below 18.25 meters (95%) and the vertical protection level (VPL) is below 42.22 meters (95 %). These results represent good integrity information transmitted by EGNOS for APV I service. This service is thus compliant with the aviation requirements for Approaches with Vertical Guidance (APV-I), which is characterised by 40 m HAL (horizontal alarm limit) and 50 m VAL (vertical alarm limit).Keywords: EGNOS, GPS, positioning, integrity, protection level
Procedia PDF Downloads 218698 Rd-PLS Regression: From the Analysis of Two Blocks of Variables to Path Modeling
Authors: E. Tchandao Mangamana, V. Cariou, E. Vigneau, R. Glele Kakai, E. M. Qannari
Abstract:
A new definition of a latent variable associated with a dataset makes it possible to propose variants of the PLS2 regression and the multi-block PLS (MB-PLS). We shall refer to these variants as Rd-PLS regression and Rd-MB-PLS respectively because they are inspired by both Redundancy analysis and PLS regression. Usually, a latent variable t associated with a dataset Z is defined as a linear combination of the variables of Z with the constraint that the length of the loading weights vector equals 1. Formally, t=Zw with ‖w‖=1. Denoting by Z' the transpose of Z, we define herein, a latent variable by t=ZZ’q with the constraint that the auxiliary variable q has a norm equal to 1. This new definition of a latent variable entails that, as previously, t is a linear combination of the variables in Z and, in addition, the loading vector w=Z’q is constrained to be a linear combination of the rows of Z. More importantly, t could be interpreted as a kind of projection of the auxiliary variable q onto the space generated by the variables in Z, since it is collinear to the first PLS1 component of q onto Z. Consider the situation in which we aim to predict a dataset Y from another dataset X. These two datasets relate to the same individuals and are assumed to be centered. Let us consider a latent variable u=YY’q to which we associate the variable t= XX’YY’q. Rd-PLS consists in seeking q (and therefore u and t) so that the covariance between t and u is maximum. The solution to this problem is straightforward and consists in setting q to the eigenvector of YY’XX’YY’ associated with the largest eigenvalue. For the determination of higher order components, we deflate X and Y with respect to the latent variable t. Extending Rd-PLS to the context of multi-block data is relatively easy. Starting from a latent variable u=YY’q, we consider its ‘projection’ on the space generated by the variables of each block Xk (k=1, ..., K) namely, tk= XkXk'YY’q. Thereafter, Rd-MB-PLS seeks q in order to maximize the average of the covariances of u with tk (k=1, ..., K). The solution to this problem is given by q, eigenvector of YY’XX’YY’, where X is the dataset obtained by horizontally merging datasets Xk (k=1, ..., K). For the determination of latent variables of order higher than 1, we use a deflation of Y and Xk with respect to the variable t= XX’YY’q. In the same vein, extending Rd-MB-PLS to the path modeling setting is straightforward. Methods are illustrated on the basis of case studies and performance of Rd-PLS and Rd-MB-PLS in terms of prediction is compared to that of PLS2 and MB-PLS.Keywords: multiblock data analysis, partial least squares regression, path modeling, redundancy analysis
Procedia PDF Downloads 142697 Exploring the Interplay of Attention, Awareness, and Control: A Comprehensive Investigation
Authors: Venkateswar Pujari
Abstract:
This study tries to investigate the complex interplay between control, awareness, and attention in human cognitive processes. The fundamental elements of cognitive functioning that play a significant role in influencing perception, decision-making, and behavior are attention, awareness, and control. Understanding how they interact can help us better understand how our minds work and may even increase our understanding of cognitive science and its therapeutic applications. The study uses an empirical methodology to examine the relationships between attention, awareness, and control by integrating different experimental paradigms and neuropsychological tests. To ensure the generalizability of findings, a wide sample of participants is chosen, including people with various cognitive profiles and ages. The study is structured into four primary parts, each of which focuses on one component of how attention, awareness, and control interact: 1. Evaluation of Attentional Capacity and Selectivity: In this stage, participants complete established attention tests, including the Stroop task and visual search tasks. 2. Evaluation of Awareness Degrees: In the second stage, participants' degrees of conscious and unconscious awareness are assessed using perceptual awareness tasks such as masked priming and binocular rivalry tasks. 3. Investigation of Cognitive Control Mechanisms: In the third phase, reaction inhibition, cognitive flexibility, and working memory capacity are investigated using exercises like the Wisconsin Card Sorting Test and the Go/No-Go paradigm. 4. Results Integration and Analysis: Data from all phases are integrated and analyzed in the final phase. To investigate potential links and prediction correlations between attention, awareness, and control, correlational and regression analyses are carried out. The study's conclusions shed light on the intricate relationships that exist between control, awareness, and attention throughout cognitive function. The findings may have consequences for cognitive psychology, neuroscience, and clinical psychology by providing new understandings of cognitive dysfunctions linked to deficiencies in attention, awareness, and control systems.Keywords: attention, awareness, control, cognitive functioning, neuropsychological assessment
Procedia PDF Downloads 85696 Performance Comparison of Microcontroller-Based Optimum Controller for Fruit Drying System
Authors: Umar Salisu
Abstract:
This research presents the development of a hot air tomatoes drying system. To provide a more efficient and continuous temperature control, microcontroller-based optimal controller was developed. The system is based on a power control principle to achieve smooth power variations depending on a feedback temperature signal of the process. An LM35 temperature sensor and LM399 differential comparator were used to measure the temperature. The mathematical model of the system was developed and the optimal controller was designed and simulated and compared with the PID controller transient response. A controlled environment suitable for fruit drying is developed within a closed chamber and is a three step process. First, the infrared light is used internally to preheated the fruit to speedily remove the water content inside the fruit for fast drying. Second, hot air of a specified temperature is blown inside the chamber to maintain the humidity below a specified level and exhaust the humid air of the chamber. Third, the microcontroller disconnects the power to the chamber after the moisture content of the fruits is removed to minimal. Experiments were conducted with 1kg of fresh tomatoes at three different temperatures (40, 50 and 60 °C) at constant relative humidity of 30%RH. The results obtained indicate that the system is significantly reducing the drying time without affecting the quality of the fruits. In the context of temperature control, the results obtained showed that the response of the optimal controller has zero overshoot whereas the PID controller response overshoots to about 30% of the set-point. Another performance metric used is the rising time; the optimal controller rose without any delay while the PID controller delayed for more than 50s. It can be argued that the optimal controller performance is preferable than that of the PID controller since it does not overshoot and it starts in good time.Keywords: drying, microcontroller, optimum controller, PID controller
Procedia PDF Downloads 291695 Comparison and Improvement of the Existing Cone Penetration Test Results: Shear Wave Velocity Correlations for Hungarian Soils
Authors: Ákos Wolf, Richard P. Ray
Abstract:
Due to the introduction of Eurocode 8, the structural design for seismic and dynamic effects has become more significant in Hungary. This has emphasized the need for more effort to describe the behavior of structures under these conditions. Soil conditions have a significant effect on the response of structures by modifying the stiffness and damping of the soil-structural system and by modifying the seismic action as it reaches the ground surface. Shear modulus (G) and shear wave velocity (vs), which are often measured in the field, are the fundamental dynamic soil properties for foundation vibration problems, liquefaction potential and earthquake site response analysis. There are several laboratory and in-situ measurement techniques to evaluate dynamic soil properties, but unfortunately, they are often too expensive for general design practice. However, a significant number of correlations have been proposed to determine shear wave velocity or shear modulus from Cone Penetration Tests (CPT), which are used more and more in geotechnical design practice in Hungary. This allows the designer to analyze and compare CPT and seismic test result in order to select the best correlation equations for Hungarian soils and to improve the recommendations for the Hungarian geologic conditions. Based on a literature review, as well as research experience in Hungary, the influence of various parameters on the accuracy of results will be shown. This study can serve as a basis for selecting and modifying correlation equations for Hungarian soils. Test data are taken from seven locations in Hungary with similar geologic conditions. The shear wave velocity values were measured by seismic CPT. Several factors are analyzed including soil type, behavior index, measurement depth, geologic age etc. for their effect on the accuracy of predictions. The final results show an improved prediction method for Hungarian soilsKeywords: CPT correlation, dynamic soil properties, seismic CPT, shear wave velocity
Procedia PDF Downloads 243694 Analysis of Seismic Waves Generated by Blasting Operations and their Response on Buildings
Authors: S. Ziaran, M. Musil, M. Cekan, O. Chlebo
Abstract:
The paper analyzes the response of buildings and industrially structures on seismic waves (low frequency mechanical vibration) generated by blasting operations. The principles of seismic analysis can be applied for different kinds of excitation such as: earthquakes, wind, explosions, random excitation from local transportation, periodic excitation from large rotating and/or machines with reciprocating motion, metal forming processes such as forging, shearing and stamping, chemical reactions, construction and earth moving work, and other strong deterministic and random energy sources caused by human activities. The article deals with the response of seismic, low frequency, mechanical vibrations generated by nearby blasting operations on a residential home. The goal was to determine the fundamental natural frequencies of the measured structure; therefore it is important to determine the resonant frequencies to design a suitable modal damping. The article also analyzes the package of seismic waves generated by blasting (Primary waves – P-waves and Secondary waves S-waves) and investigated the transfer regions. For the detection of seismic waves resulting from an explosion, the Fast Fourier Transform (FFT) and modal analysis, in the frequency domain, is used and the signal was acquired and analyzed also in the time domain. In the conclusions the measured results of seismic waves caused by blasting in a nearby quarry and its effect on a nearby structure (house) is analyzed. The response on the house, including the fundamental natural frequency and possible fatigue damage is also assessed.Keywords: building structure, seismic waves, spectral analysis, structural response
Procedia PDF Downloads 395693 Experimental Pain Study Investigating the Distinction between Pain and Relief Reports
Authors: Abeer F. Almarzouki, Christopher A. Brown, Richard J. Brown, Anthony K. P. Jones
Abstract:
Although relief is commonly assumed to be a direct reflection of pain reduction, it seems to be driven by complex emotional interactions in which pain reduction is only one component. For example, termination of a painful/aversive event may be relieving and rewarding. Accordingly, in this study, whether terminating an aversive negative prediction of pain would be reflected in a greater relief experience was investigated, with a view to separating apart the effects of the manipulation on pain and relief. We use aversive conditioning paradigm to investigate the perception of relief in an aversive (threat) vs. positive context. Participants received positive predictors of a non-painful outcome which were presented within either a congruent positive (non-painful) context or an incongruent threat (painful) context that had been previously conditioned; trials followed by identical laser stimuli on both conditions. Participants were asked to rate the perceived intensity of pain as well as their perception of relief in response to the cue predicting the outcome. Results demonstrated that participants reported more pain in the aversive context compared to the positive context. Conversely, participants reported more relief in the aversive context compares to the neutral context. The rating of relief in the threat context was not correlated with pain reports. The results suggest that relief is not dependant on pain intensity. Consistent with this, relief in the threat context was greater than that in the positive expectancy condition, while the opposite pattern was obtained for the pain ratings. The value of relief in this study is better appreciated in the context of an impending negative threat, which is apparent in the higher pain ratings in the prior negative expectancy compared to the positive expectancy condition. Moreover, the more threatening the context (as manifested by higher unpleasantness/higher state anxiety scores), the more the relief is appreciated. The importance of the study highlights the importance of exploring relief and pain intensity in monitoring separately or evaluating pain-related suffering. The results also illustrate that the perception of painful input may largely be shaped by the context and not necessarily stimulus-related.Keywords: aversive context, pain, predictions, relief
Procedia PDF Downloads 134692 Estimation of Endogenous Brain Noise from Brain Response to Flickering Visual Stimulation Magnetoencephalography Visual Perception Speed
Authors: Alexander N. Pisarchik, Parth Chholak
Abstract:
Intrinsic brain noise was estimated via magneto-encephalograms (MEG) recorded during perception of flickering visual stimuli with frequencies of 6.67 and 8.57 Hz. First, we measured the mean phase difference between the flicker signal and steady-state event-related field (SSERF) in the occipital area where the brain response at the flicker frequencies and their harmonics appeared in the power spectrum. Then, we calculated the probability distribution of the phase fluctuations in the regions of frequency locking and computed its kurtosis. Since kurtosis is a measure of the distribution’s sharpness, we suppose that inverse kurtosis is related to intrinsic brain noise. In our experiments, the kurtosis value varied among subjects from K = 3 to K = 5 for 6.67 Hz and from 2.6 to 4 for 8.57 Hz. The majority of subjects demonstrated leptokurtic kurtosis (K < 3), i.e., the distribution tails approached zero more slowly than Gaussian. In addition, we found a strong correlation between kurtosis and brain complexity measured as the correlation dimension, so that the MEGs of subjects with higher kurtosis exhibited lower complexity. The obtained results are discussed in the framework of nonlinear dynamics and complex network theories. Specifically, in a network of coupled oscillators, phase synchronization is mainly determined by two antagonistic factors, noise, and the coupling strength. While noise worsens phase synchronization, the coupling improves it. If we assume that each neuron and each synapse contribute to brain noise, the larger neuronal network should have stronger noise, and therefore phase synchronization should be worse, that results in smaller kurtosis. The described method for brain noise estimation can be useful for diagnostics of some brain pathologies associated with abnormal brain noise.Keywords: brain, flickering, magnetoencephalography, MEG, visual perception, perception time
Procedia PDF Downloads 142691 Grid and Market Integration of Large Scale Wind Farms using Advanced Predictive Data Mining Techniques
Authors: Umit Cali
Abstract:
The integration of intermittent energy sources like wind farms into the electricity grid has become an important challenge for the utilization and control of electric power systems, because of the fluctuating behaviour of wind power generation. Wind power predictions improve the economic and technical integration of large amounts of wind energy into the existing electricity grid. Trading, balancing, grid operation, controllability and safety issues increase the importance of predicting power output from wind power operators. Therefore, wind power forecasting systems have to be integrated into the monitoring and control systems of the transmission system operator (TSO) and wind farm operators/traders. The wind forecasts are relatively precise for the time period of only a few hours, and, therefore, relevant with regard to Spot and Intraday markets. In this work predictive data mining techniques are applied to identify a statistical and neural network model or set of models that can be used to predict wind power output of large onshore and offshore wind farms. These advanced data analytic methods helps us to amalgamate the information in very large meteorological, oceanographic and SCADA data sets into useful information and manageable systems. Accurate wind power forecasts are beneficial for wind plant operators, utility operators, and utility customers. An accurate forecast allows grid operators to schedule economically efficient generation to meet the demand of electrical customers. This study is also dedicated to an in-depth consideration of issues such as the comparison of day ahead and the short-term wind power forecasting results, determination of the accuracy of the wind power prediction and the evaluation of the energy economic and technical benefits of wind power forecasting.Keywords: renewable energy sources, wind power, forecasting, data mining, big data, artificial intelligence, energy economics, power trading, power grids
Procedia PDF Downloads 510690 Numerical Investigation of Dynamic Stall over a Wind Turbine Pitching Airfoil by Using OpenFOAM
Authors: Mahbod Seyednia, Shidvash Vakilipour, Mehran Masdari
Abstract:
Computations for two-dimensional flow past a stationary and harmonically pitching wind turbine airfoil at a moderate value of Reynolds number (400000) are carried out by progressively increasing the angle of attack for stationary airfoil and at fixed pitching frequencies for rotary one. The incompressible Navier-Stokes equations in conjunction with Unsteady Reynolds Average Navier-Stokes (URANS) equations for turbulence modeling are solved by OpenFOAM package to investigate the aerodynamic phenomena occurred at stationary and pitching conditions on a NACA 6-series wind turbine airfoil. The aim of this study is to enhance the accuracy of numerical simulation in predicting the aerodynamic behavior of an oscillating airfoil in OpenFOAM. Hence, for turbulence modelling, k-ω-SST with low-Reynolds correction is employed to capture the unsteady phenomena occurred in stationary and oscillating motion of the airfoil. Using aerodynamic and pressure coefficients along with flow patterns, the unsteady aerodynamics at pre-, near-, and post-static stall regions are analyzed in harmonically pitching airfoil, and the results are validated with the corresponding experimental data possessed by the authors. The results indicate that implementing the mentioned turbulence model leads to accurate prediction of the angle of static stall for stationary airfoil and flow separation, dynamic stall phenomenon, and reattachment of the flow on the surface of airfoil for pitching one. Due to the geometry of the studied 6-series airfoil, the vortex on the upper surface of the airfoil during upstrokes is formed at the trailing edge. Therefore, the pattern flow obtained by our numerical simulations represents the formation and change of the trailing-edge vortex at near- and post-stall regions where this process determines the dynamic stall phenomenon.Keywords: CFD, moderate Reynolds number, OpenFOAM, pitching oscillation, unsteady aerodynamics, wind turbine
Procedia PDF Downloads 195689 Statistical Modeling and by Artificial Neural Networks of Suspended Sediment Mina River Watershed at Wadi El-Abtal Gauging Station (Northern Algeria)
Authors: Redhouane Ghernaout, Amira Fredj, Boualem Remini
Abstract:
Suspended sediment transport is a serious problem worldwide, but it is much more worrying in certain regions of the world, as is the case in the Maghreb and more particularly in Algeria. It continues to take disturbing proportions in Northern Algeria due to the variability of rains in time and in space and constant deterioration of vegetation. Its prediction is essential in order to identify its intensity and define the necessary actions for its reduction. The purpose of this study is to analyze the concentration data of suspended sediment measured at Wadi El-Abtal Hydrometric Station. It also aims to find and highlight regressive power relationships, which can explain the suspended solid flow by the measured liquid flow. The study strives to find models of artificial neural networks linking the flow, month and precipitation parameters with solid flow. The obtained results show that the power function of the solid transport rating curve and the models of artificial neural networks are appropriate methods for analysing and estimating suspended sediment transport in Wadi Mina at Wadi El-Abtal Hydrometric Station. They made it possible to identify in a fairly conclusive manner the model of neural networks with four input parameters: the liquid flow Q, the month and the daily precipitation measured at the representative stations (Frenda 013002 and Ain El-Hadid 013004 ) of the watershed. The model thus obtained makes it possible to estimate the daily solid flows (interpolate and extrapolate) even beyond the period of observation of solid flows (1985/86 to 1999/00), given the availability of the average daily liquid flows and daily precipitation since 1953/1954.Keywords: suspended sediment, concentration, regression, liquid flow, solid flow, artificial neural network, modeling, mina, algeria
Procedia PDF Downloads 94688 Frequency Selective Filters for Estimating the Equivalent Circuit Parameters of Li-Ion Battery
Authors: Arpita Mondal, Aurobinda Routray, Sreeraj Puravankara, Rajashree Biswas
Abstract:
The most difficult part of designing a battery management system (BMS) is battery modeling. A good battery model can capture the dynamics which helps in energy management, by accurate model-based state estimation algorithms. So far the most suitable and fruitful model is the equivalent circuit model (ECM). However, in real-time applications, the model parameters are time-varying, changes with current, temperature, state of charge (SOC), and aging of the battery and this make a great impact on the performance of the model. Therefore, to increase the equivalent circuit model performance, the parameter estimation has been carried out in the frequency domain. The battery is a very complex system, which is associated with various chemical reactions and heat generation. Therefore, it’s very difficult to select the optimal model structure. As we know, if the model order is increased, the model accuracy will be improved automatically. However, the higher order model will face the tendency of over-parameterization and unfavorable prediction capability, while the model complexity will increase enormously. In the time domain, it becomes difficult to solve higher order differential equations as the model order increases. This problem can be resolved by frequency domain analysis, where the overall computational problems due to ill-conditioning reduce. In the frequency domain, several dominating frequencies can be found in the input as well as output data. The selective frequency domain estimation has been carried out, first by estimating the frequencies of the input and output by subspace decomposition, then by choosing the specific bands from the most dominating to the least, while carrying out the least-square, recursive least square and Kalman Filter based parameter estimation. In this paper, a second order battery model consisting of three resistors, two capacitors, and one SOC controlled voltage source has been chosen. For model identification and validation hybrid pulse power characterization (HPPC) tests have been carried out on a 2.6 Ah LiFePO₄ battery.Keywords: equivalent circuit model, frequency estimation, parameter estimation, subspace decomposition
Procedia PDF Downloads 140687 Analysis of Network Connectivity for Ship-To-Ship Maritime Communication Using IEEE 802.11 on Maritime Environment of Tanjung Perak, Indonesia
Authors: Ahmad Fauzi Makarim, Okkie Puspitorini, Hani'ah Mahmudah, Nur Adi Siswandari, Ari Wijayanti
Abstract:
As a maritime country, Indonesia needs a solution in maritime connectivity which can assist the maritime communication system which including communication from harbor to the ship or ship to ship. The needs of many application services for maritime communication, whether for safety reasons until voyage service to help the process of voyage activity needs connection with a high bandwith. To support the government efforts in handling that kind of problem, a research is conducted in maritime communication issue by applying the new developed technology in Indonesia, namely IEEE 802.11. In this research, 3 outdoor WiFi devices are used in which have a frequency of 5.8 GHz. Maritime of Tanjung Perak harbor in Surabaya until Karang Jamuang Island are used as the location of the research with defining permission of ship node spreading by Navigation District Class 1. That maritime area formed by state 1 and state 2 areas which are the narrow area with average wave height of 0.7 meter based on the data from BMKG S urabaya. After that, wave height used as one of the parameters which are used in analyzing characteristic of signal propagation at sea surface, so it can be determined on the coverage area of transmitter system. In this research has been used three samples of outdoor wifi, there is the coverage of device A can be determined about 2256 meter, device B 4000 meter, and device C 1174 meter. Then to analyze of network connectivity for the ship to ship is used AODV routing algorithm system based on the value of the power transmit was smallest of all nodes within the transmitter coverage.Keywords: maritime of Indonesia, maritime communications, outdoor wifi, coverage, AODV
Procedia PDF Downloads 346686 The Extent of Land Use Externalities in the Fringe of Jakarta Metropolitan: An Application of Spatial Panel Dynamic Land Value Model
Authors: Rahma Fitriani, Eni Sumarminingsih, Suci Astutik
Abstract:
In a fast growing region, conversion of agricultural lands which are surrounded by some new development sites will occur sooner than expected. This phenomenon has been experienced by many regions in Indonesia, especially the fringe of Jakarta (BoDeTaBek). Being Indonesia’s capital city, rapid conversion of land in this area is an unavoidable process. The land conversion expands spatially into the fringe regions, which were initially dominated by agricultural land or conservation sites. Without proper control or growth management, this activity will invite greater costs than benefits. The current land use is the use which maximizes its value. In order to maintain land for agricultural activity or conservation, some efforts are needed to keep the land value of this activity as high as possible. In this case, the knowledge regarding the functional relationship between land value and its driving forces is necessary. In a fast growing region, development externalities are the assumed dominant driving force. Land value is the product of the past decision of its use leading to its value. It is also affected by the local characteristics and the observed surrounded land use (externalities) from the previous period. The effect of each factor on land value has dynamic and spatial virtues; an empirical spatial dynamic land value model will be more useful to capture them. The model will be useful to test and to estimate the extent of land use externalities on land value in the short run as well as in the long run. It serves as a basis to formulate an effective urban growth management’s policy. This study will apply the model to the case of land value in the fringe of Jakarta Metropolitan. The model will be used further to predict the effect of externalities on land value, in the form of prediction map. For the case of Jakarta’s fringe, there is some evidence about the significance of neighborhood urban activity – negative externalities, the previous land value and local accessibility on land value. The effects are accumulated dynamically over years, but they will fully affect the land value after six years.Keywords: growth management, land use externalities, land value, spatial panel dynamic
Procedia PDF Downloads 251685 Using the SMT Solver to Minimize the Latency and to Optimize the Number of Cores in an NoC-DSP Architectures
Authors: Imen Amari, Kaouther Gasmi, Asma Rebaya, Salem Hasnaoui
Abstract:
The problem of scheduling and mapping data flow applications on multi-core architectures is notoriously difficult. This difficulty is related to the rapid evaluation of Telecommunication and multimedia systems accompanied by a rapid increase of user requirements in terms of latency, execution time, consumption, energy, etc. Having an optimal scheduling on multi-cores DSP (Digital signal Processors) platforms is a challenging task. In this context, we present a novel technic and algorithm in order to find a valid schedule that optimizes the key performance metrics particularly the Latency. Our contribution is based on Satisfiability Modulo Theories (SMT) solving technologies which is strongly driven by the industrial applications and needs. This paper, describe a scheduling module integrated in our proposed Workflow which is advised to be a successful approach for programming the applications based on NoC-DSP platforms. This workflow transform automatically a Simulink model to a synchronous dataflow (SDF) model. The automatic transformation followed by SMT solver scheduling aim to minimize the final latency and other software/hardware metrics in terms of an optimal schedule. Also, finding the optimal numbers of cores to be used. In fact, our proposed workflow taking as entry point a Simulink file (.mdl or .slx) derived from embedded Matlab functions. We use an approach which is based on the synchronous and hierarchical behavior of both Simulink and SDF. Whence, results of running the scheduler which exist in the Workflow mentioned above using our proposed SMT solver algorithm refinements produce the best possible scheduling in terms of latency and numbers of cores.Keywords: multi-cores DSP, scheduling, SMT solver, workflow
Procedia PDF Downloads 280684 Evaluation of Compatibility between Produced and Injected Waters and Identification of the Causes of Well Plugging in a Southern Tunisian Oilfield
Authors: Sonia Barbouchi, Meriem Samcha
Abstract:
Scale deposition during water injection into aquifer of oil reservoirs is a serious problem experienced in the oil production industry. One of the primary causes of scale formation and injection well plugging is mixing two waters which are incompatible. Considered individually, the waters may be quite stable at system conditions and present no scale problems. However, once they are mixed, reactions between ions dissolved in the individual waters may form insoluble products. The purpose of this study is to identify the causes of well plugging in a southern Tunisian oilfield, where fresh water has been injected into the producing wells to counteract the salinity of the formation waters and inhibit the deposition of halite. X-ray diffraction (XRD) mineralogical analysis has been carried out on scale samples collected from the blocked well. Two samples collected from both formation water and injected water were analysed using inductively coupled plasma atomic emission spectroscopy, ion chromatography and other standard laboratory techniques. The results of complete waters analysis were the typical input parameters, to determine scaling tendency. Saturation indices values related to CaCO3, CaSO4, BaSO4 and SrSO4 scales were calculated for the water mixtures at different share, under various conditions of temperature, using a computerized scale prediction model. The compatibility study results showed that mixing the two waters tends to increase the probability of barite deposition. XRD analysis confirmed the compatibility study results, since it proved that the analysed deposits consisted predominantly of barite with minor galena. At the studied temperatures conditions, the tendency for barite scale is significantly increasing with the increase of fresh water share in the mixture. The future scale inhibition and removal strategies to be implemented in the concerned oilfield are being derived in a large part from the results of the present study.Keywords: compatibility study, produced water, scaling, water injection
Procedia PDF Downloads 160683 Improvement in Blast Furnace Performance Using Softening - Melting Zone Profile Prediction Model at G Blast Furnace, Tata Steel Jamshedpur
Authors: Shoumodip Roy, Ankit Singhania, K. R. K. Rao, Ravi Shankar, M. K. Agarwal, R. V. Ramna, Uttam Singh
Abstract:
The productivity of a blast furnace and the quality of the hot metal produced are significantly dependent on the smoothness and stability of furnace operation. The permeability of the furnace bed, as well as the gas flow pattern, influences the steady control of process parameters. The softening – melting zone that is formed inside the furnace contributes largely in distribution of the gas flow and the bed permeability. A better shape of softening-melting zone enhances the performance of blast furnace, thereby reducing the fuel rates and improving furnace life. Therefore, predictive model of the softening- melting zone profile can be utilized to control and improve the furnace operation. The shape of softening-melting zone depends upon the physical and chemical properties of the agglomerates and iron ore charged in the furnace. The variations in the agglomerate proportion in the burden at G Blast furnace disturbed the furnace stability. During such circumstances, it was analyzed that a w-shape softening-melting zone profile was formed inside the furnace. The formation of w-shape zone resulted in poor bed permeability and non-uniform gas flow. There was a significant increase in the heat loss at the lower zone of the furnace. The fuel demand increased, and the huge production loss was incurred. Therefore, visibility of softening-melting zone profile was necessary in order to pro-actively optimize the process parameters and thereby to operate the furnace smoothly. Using stave temperatures, a model was developed that predicted the shape of the softening-melting zone inside the furnace. It was observed that furnace operated smoothly during inverse V-shape of the zone and vice-versa during w-shape. This model helped to control the heat loss, optimize the burden distribution and lower the fuel rate at G Blast Furnace, TSL Jamshedpur. As a result of furnace stabilization productivity increased by 10% and fuel rate reduced by 80 kg/thm. Details of the process have been discussed in this paper.Keywords: agglomerate, blast furnace, permeability, softening-melting
Procedia PDF Downloads 245682 Role of P53, KI67 and Cyclin a Immunohistochemical Assay in Predicting Wilms’ Tumor Mortality
Authors: Ahmed Atwa, Ashraf Hafez, Mohamed Abdelhameed, Adel Nabeeh, Mohamed Dawaba, Tamer Helmy
Abstract:
Introduction and Objective: Tumour staging and grading do not usually reflect the future behavior of Wilms' tumor (WT) regarding mortality. Therefore, in this study, P53, Ki67 and cyclin A immunohistochemistry were used in a trial to predict WT cancer-specific survival (CSS). Methods: In this nonconcurrent cohort study, patients' archived data, including age at presentation, gender, history, clinical examination and radiological investigations, were retrieved then the patients were reviewed at the outpatient clinic of a tertiary care center by history-taking, clinical examination and radiological investigations to detect the oncological outcome. Cases that received preoperative chemotherapy or died due to causes other than WT were excluded. Formalin-fixed, paraffin-embedded specimens obtained from the previously preserved blocks at the pathology laboratory were taken on positively charged slides for IHC with p53, Ki67 and cyclin A. All specimens were examined by an experienced histopathologist devoted to the urological practice and blinded to the patient's clinical findings. P53 and cyclin A staining were scored as 0 (no nuclear staining),1 (<10% nuclear staining), 2 (10-50% nuclear staining) and 3 (>50% nuclear staining). Ki67 proliferation index (PI) was graded as low, borderline and high. Results: Of the 75 cases, 40 (53.3%) were males and 35 (46.7%) were females, and the median age was 36 months (2-216). With a mean follow-up of 78.6±31 months, cancer-specific mortality (CSM) occurred in 15 (20%) and 11 (14.7%) patients, respectively. Kaplan-Meier curve was used for survival analysis, and groups were compared using the Log-rank test. Multivariate logistic regression and Cox regression were not used because only one variable (cyclin A) had shown statistical significance (P=.02), whereas the other significant factor (residual tumor) had few cases. Conclusions: Cyclin A IHC should be considered as a marker for the prediction of WT CSS. Prospective studies with a larger sample size are needed.Keywords: wilms’ tumour, nephroblastoma, urology, survival
Procedia PDF Downloads 61681 Fuzzy Logic Classification Approach for Exponential Data Set in Health Care System for Predication of Future Data
Authors: Manish Pandey, Gurinderjit Kaur, Meenu Talwar, Sachin Chauhan, Jagbir Gill
Abstract:
Health-care management systems are a unit of nice connection as a result of the supply a straightforward and fast management of all aspects relating to a patient, not essentially medical. What is more, there are unit additional and additional cases of pathologies during which diagnosing and treatment may be solely allotted by victimization medical imaging techniques. With associate ever-increasing prevalence, medical pictures area unit directly acquired in or regenerate into digital type, for his or her storage additionally as sequent retrieval and process. Data Mining is the process of extracting information from large data sets through using algorithms and Techniques drawn from the field of Statistics, Machine Learning and Data Base Management Systems. Forecasting may be a prediction of what's going to occur within the future, associated it's an unsure method. Owing to the uncertainty, the accuracy of a forecast is as vital because the outcome foretold by foretelling the freelance variables. A forecast management should be wont to establish if the accuracy of the forecast is within satisfactory limits. Fuzzy regression strategies have normally been wont to develop shopper preferences models that correlate the engineering characteristics with shopper preferences relating to a replacement product; the patron preference models offer a platform, wherever by product developers will decide the engineering characteristics so as to satisfy shopper preferences before developing the merchandise. Recent analysis shows that these fuzzy regression strategies area units normally will not to model client preferences. We tend to propose a Testing the strength of Exponential Regression Model over regression toward the mean Model.Keywords: health-care management systems, fuzzy regression, data mining, forecasting, fuzzy membership function
Procedia PDF Downloads 273680 Simulation-Based Control Module for Offshore Single Point Mooring System
Authors: Daehyun Baek, Seungmin Lee, Minju Kim Jangik Park, Hyeong-Soon Moon
Abstract:
SPM (Single Point Mooring) is one of the mooring buoy facilities installed on a coast near oil and gas terminal which is not able to berth FPSO or large oil tankers under the condition of high draft due to geometrical limitation. Loading and unloading of crude oil and gas through a subsea pipeline can be carried out between the mooring buoy, ships and onshore facilities. SPM is an offshore-standalone system which has to withstand the harsh marine environment with harsh conditions such as high wind, current and so on. Therefore, SPM is required to have high stability, reliability and durability. Also, SPM is comprised to be integrated systems which consist of power management, high pressure valve control, sophisticated hardware/software and a long distance communication system. In order to secure required functions of SPM system, a simulation model for the integrated system of SPM using MATLAB Simulink and State flow tool has been developed. The developed model consists of configuration of hydraulic system for opening and closing of PLEM (Pipeline End Manifold) valves and control system logic. To verify functions of the model, an integrated simulation model for overall systems of SPM was also developed by considering handshaking variables between individual systems. In addition to the dynamic model, a self-diagnostic function to determine failure of the system was configured, which enables the SPM system itself to alert users about the failure once a failure signal comes to arise. Controlling and monitoring the SPM system is able to be done by a HMI system which is capable of managing the SPM system remotely, which was carried out by building a communication environment between the SPM system and the HMI system.Keywords: HMI system, mooring buoy, simulink simulation model, single point mooring, stateflow
Procedia PDF Downloads 414679 Thin Films of Glassy Carbon Prepared by Cluster Deposition
Authors: Hatem Diaf, Patrice Melinon, Antonio Pereira, Bernard Moine, Nicholas Blanchard, Florent Bourquard, Florence Garrelie, Christophe Donnet
Abstract:
Glassy carbon exhibits excellent biological compatibility with live tissues meaning it has high potential for applications in life science. Moreover, glassy carbon has interesting properties including 'high temperature resistance', hardness, low density, low electrical resistance, low friction, and low thermal resistance. The structure of glassy carbon has long been a subject of debate. It is now admitted that glassy carbon is 100% sp2. This term is a little bit confusing as long sp2 hybridization defined from quantum chemistry is related to both properties: threefold configuration and pi bonding (parallel pz orbitals). Using plasma laser deposition of carbon clusters combined with pulsed nano/femto laser annealing, we are able to synthesize thin films of glassy carbon of good quality (probed by G band/ D disorder band ratio in Raman spectroscopy) without thermal post annealing. A careful inspecting of Raman signal, plasmon losses and structure performed by HRTEM (High Resolution Transmission Electron Microscopy) reveals that both properties (threefold and pi orbitals) cannot coexist together. The structure of the films is compared to models including schwarzites based from negatively curved surfaces at the opposite of onions or fullerene-like structures with positively curved surfaces. This study shows that a huge collection of porous carbon named vitreous carbon with different structures can coexist.Keywords: glassy carbon, cluster deposition, coating, electronic structure
Procedia PDF Downloads 313678 Achieving Process Stability through Automation and Process Optimization at H Blast Furnace Tata Steel, Jamshedpur
Authors: Krishnendu Mukhopadhyay, Subhashis Kundu, Mayank Tiwari, Sameeran Pani, Padmapal, Uttam Singh
Abstract:
Blast Furnace is a counter current process where burden descends from top and hot gases ascend from bottom and chemically reduce iron oxides into liquid hot metal. One of the major problems of blast furnace operation is the erratic burden descent inside furnace. Sometimes this problem is so acute that burden descent stops resulting in Hanging and instability of the furnace. This problem is very frequent in blast furnaces worldwide and results in huge production losses. This situation becomes more adverse when blast furnaces are operated at low coke rate and high coal injection rate with adverse raw materials like high alumina ore and high coke ash. For last three years, H-Blast Furnace Tata Steel was able to reduce coke rate from 450 kg/thm to 350 kg/thm with an increase in coal injection to 200 kg/thm which are close to world benchmarks and expand profitability. To sustain this regime, elimination of irregularities of blast furnace like hanging, channeling, and scaffolding is very essential. In this paper, sustaining of zero hanging spell for consecutive three years with low coke rate operation by improvement in burden characteristics, burden distribution, changes in slag regime, casting practices and adequate automation of the furnace operation has been illustrated. Models have been created to comprehend and upgrade the blast furnace process understanding. A model has been developed to predict the process of maintaining slag viscosity in desired range to attain proper burden permeability. A channeling prediction model has also been developed to understand channeling symptoms so that early actions can be initiated. The models have helped to a great extent in standardizing the control decisions of operators at H-Blast Furnace of Tata Steel, Jamshedpur and thus achieving process stability for last three years.Keywords: hanging, channelling, blast furnace, coke
Procedia PDF Downloads 188677 Modelling the Impact of Installation of Heat Cost Allocators in District Heating Systems Using Machine Learning
Authors: Danica Maljkovic, Igor Balen, Bojana Dalbelo Basic
Abstract:
Following the regulation of EU Directive on Energy Efficiency, specifically Article 9, individual metering in district heating systems has to be introduced by the end of 2016. These directions have been implemented in member state’s legal framework, Croatia is one of these states. The directive allows installation of both heat metering devices and heat cost allocators. Mainly due to bad communication and PR, the general public false image was created that the heat cost allocators are devices that save energy. Although this notion is wrong, the aim of this work is to develop a model that would precisely express the influence of installation heat cost allocators on potential energy savings in each unit within multifamily buildings. At the same time, in recent years, a science of machine learning has gain larger application in various fields, as it is proven to give good results in cases where large amounts of data are to be processed with an aim to recognize a pattern and correlation of each of the relevant parameter as well as in the cases where the problem is too complex for a human intelligence to solve. A special method of machine learning, decision tree method, has proven an accuracy of over 92% in prediction general building consumption. In this paper, a machine learning algorithms will be used to isolate the sole impact of installation of heat cost allocators on a single building in multifamily houses connected to district heating systems. Special emphasises will be given regression analysis, logistic regression, support vector machines, decision trees and random forest method.Keywords: district heating, heat cost allocator, energy efficiency, machine learning, decision tree model, regression analysis, logistic regression, support vector machines, decision trees and random forest method
Procedia PDF Downloads 242676 Examining Predictive Coding in the Hierarchy of Visual Perception in the Autism Spectrum Using Fast Periodic Visual Stimulation
Authors: Min L. Stewart, Patrick Johnston
Abstract:
Predictive coding has been proposed as a general explanatory framework for understanding the neural mechanisms of perception. As such, an underweighting of perceptual priors has been hypothesised to underpin a range of differences in inferential and sensory processing in autism spectrum disorders. However, empirical evidence to support this has not been well established. The present study uses an electroencephalography paradigm involving changes of facial identity and person category (actors etc.) to explore how levels of autistic traits (AT) affect predictive coding at multiple stages in the visual processing hierarchy. The study uses a rapid serial presentation of faces, with hierarchically structured sequences involving both periodic and aperiodic repetitions of different stimulus attributes (i.e., person identity and person category) in order to induce contextual expectations relating to these attributes. It investigates two main predictions: (1) significantly larger and late neural responses to change of expected visual sequences in high-relative to low-AT, and (2) significantly reduced neural responses to violations of contextually induced expectation in high- relative to low-AT. Preliminary frequency analysis data comparing high and low-AT show greater and later event-related-potentials (ERPs) in occipitotemporal areas and prefrontal areas in high-AT than in low-AT for periodic changes of facial identity and person category but smaller ERPs over the same areas in response to aperiodic changes of identity and category. The research advances our understanding of how abnormalities in predictive coding might underpin aberrant perceptual experience in autism spectrum. This is the first stage of a research project that will inform clinical practitioners in developing better diagnostic tests and interventions for people with autism.Keywords: hierarchical visual processing, face processing, perceptual hierarchy, prediction error, predictive coding
Procedia PDF Downloads 104