Search results for: backpropagation neural network

Authors: Zhihao Zheng, Zhilin Wang, Linxin Liu

Abstract:

In the research of automated knowledge question-answering systems, accuracy and efficiency are critical challenges. This paper proposes a knowledge graph-enhanced Retrieval-Augmented Generation (RAG) method, combined with a Graph Neural Network (GNN) structure, to automatically determine the correctness of knowledge competition questions. First, a domain-specific knowledge graph was constructed from a large corpus of academic journal literature, with key entities and relationships extracted using Natural Language Processing (NLP) techniques. Then, the RAG method's retrieval module was expanded to simultaneously query both text databases and the knowledge graph, leveraging the GNN to further extract structured information from the knowledge graph. During answer generation, contextual information provided by the knowledge graph and GNN is incorporated to improve the accuracy and consistency of the answers. Experimental results demonstrate that the knowledge graph and GNN-enhanced RAG method perform excellently in determining the correctness of questions, achieving an accuracy rate of 95%. Particularly in cases involving ambiguity or requiring contextual information, the structured knowledge provided by the knowledge graph and GNN significantly enhances the RAG method's performance. This approach not only demonstrates significant advantages in improving the accuracy and efficiency of automated knowledge question-answering systems but also offers new directions and ideas for future research and practical applications.

Keywords: knowledge graph, graph neural network, retrieval-augmented generation, NLP

Procedia PDF Downloads 39

Authors: Sofia Stoica

Abstract:

In this paper, we use historical data to predict the stock price of a tech company. To this end, we use a dataset consisting of the stock prices in the past five years of ten major tech companies – Adobe, Amazon, Apple, Facebook, Google, Microsoft, Netflix, Oracle, Salesforce, and Tesla. We experimented with a variety of models– a linear regressor model, K nearest Neighbors (KNN), a sequential neural network – and algorithms - Multiplicative Weight Update, and AdaBoost. We found that the sequential neural network performed the best, with a testing error of 0.18%. Interestingly, the linear model performed the second best with a testing error of 0.73%. These results show that using historical data is enough to obtain high accuracies, and a simple algorithm like linear regression has a performance similar to more sophisticated models while taking less time and resources to implement.

Keywords: finance, machine learning, opening price, stock market

Procedia PDF Downloads 189

Authors: Fengjuan Wang, Azilawati Jamaludin

Abstract:

Developmental Dyscalculia (DD) is defined as a particular learning difficulty with continuous challenges in learning requisite math skills that cannot be explained by intellectual disability or educational deprivation. Recent studies have increasingly recognized that DD is a heterogeneous, instead of monolithic, learning disorder with not only cognitive and behavioral deficits but so too neural dysfunction. In recent years, neuroimaging studies employed group comparison to explore the neural underpinnings of DD, which contradicted the heterogenous nature of DD and may obfuscate critical individual differences. This research aimed to investigate the neural heterogeneity of DD using case studies with functional near-infrared spectroscopy (fNIRS). A total of 54 aged 6-7 years old of children participated in this study, comprising two comprehensive cognitive assessments, an 8-minute resting state, and an 8-minute one-digit addition task. Nine children met the criteria of DD and scored at or below 85 (i.e., the 16th percentile) on the Mathematics or Math Fluency subtest of the Wechsler Individual Achievement Test, Third Edition (WIAT-III) (both subtest scores were 90 and below). The remaining 45 children formed the typically developing (TD) group. Resting-state data and brain activation in the inferior frontal gyrus (IFG), superior frontal gyrus (SFG), and intraparietal sulcus (IPS) were collected for comparison between each case and the TD group. Graph theory was used to analyze the brain network under the resting state. This theory represents the brain network as a set of nodes--brain regions—and edges—pairwise interactions across areas to reveal the architectural organizations of the nervous network. Next, a single-case methodology developed by Crawford et al. in 2010 was used to compare each case’s brain network indicators and brain activation against 45 TD children’s average data. Results showed that three out of the nine DD children displayed significant deviation from TD children’s brain indicators. Case 1 had inefficient nodal network properties. Case 2 showed inefficient brain network properties and weaker activation in the IFG and IPS areas. Case 3 displayed inefficient brain network properties with no differences in activation patterns. As a rise above, the present study was able to distill differences in architectural organizations and brain activation of DD vis-à-vis TD children using fNIRS and single-case methodology. Although DD is regarded as a heterogeneous learning difficulty, it is noted that all three cases showed lower nodal efficiency in the brain network, which may be one of the neural sources of DD. Importantly, although the current “brain norm” established for the 45 children is tentative, the results from this study provide insights not only for future work in “developmental brain norm” with reliable brain indicators but so too the viability of single-case methodology, which could be used to detect differential brain indicators of DD children for early detection and interventions.

Keywords: brain activation, brain network, case study, developmental dyscalculia, functional near-infrared spectroscopy, graph theory, neural heterogeneity

Procedia PDF Downloads 53

Authors: Aleksei Samarin, Artyom Nazarenko, Valentin Malykh

Abstract:

Image enhancement is becoming more and more popular, especially on mobile devices. Nowadays, it is a common approach to enhance an image using a convolutional neural network (CNN). Such a network should be of significant size; otherwise, a possibility for the artifacts to occur is overgrowing. The existing large CNNs are computationally expensive, which could be crucial for mobile devices. Another important flaw of such models is they are poorly interpretable. There is another approach to image enhancement, namely, the usage of predefined filters in combination with the prediction of their applicability. We present an approach following this paradigm, which outperforms both existing CNN-based and filter-based approaches in the image enhancement task. It is easily adaptable for mobile devices since it has only 47 thousand parameters. It shows the best SSIM 0.919 on RANDOM250 (MIT Adobe FiveK) among small models and is thrice faster than previous models.

Keywords: universal filter, image enhancement, neural networks, computer vision

Procedia PDF Downloads 101

Authors: Ajai Singh

Abstract:

Simulation of hydrological processes at the watershed outlet through modelling approach is essential for proper planning and implementation of appropriate soil conservation measures in Damodar Barakar catchment, Hazaribagh, India where soil erosion is a dominant problem. This study quantifies the parametric uncertainty involved in simulation of stream flow using Soil and Water Assessment Tool (SWAT), a watershed scale model and Radial Basis Neural Network (RBNN), an artificial neural network model. Both the models were calibrated and validated based on measured stream flow and quantification of the uncertainty in SWAT model output was assessed using ‘‘Sequential Uncertainty Fitting Algorithm’’ (SUFI-2). Though both the model predicted satisfactorily, but RBNN model performed better than SWAT with R2 and NSE values of 0.92 and 0.92 during training, and 0.71 and 0.70 during validation period, respectively. Comparison of the results of the two models also indicates a wider prediction interval for the results of the SWAT model. The values of P-factor related to each model shows that the percentage of observed stream flow values bracketed by the 95PPU in the RBNN model as 91% is higher than the P-factor in SWAT as 87%. In other words the RBNN model estimates the stream flow values more accurately and with less uncertainty. It could be stated that RBNN model based on simple input could be used for estimation of monthly stream flow, missing data, and testing the accuracy and performance of other models.

Keywords: SWAT, RBNN, SUFI 2, bootstrap technique, stream flow, simulation

Procedia PDF Downloads 370

Authors: Zekang Lan, Yan Xu, Yingkun Huang, Dian Huang, Shengzhong Feng

Abstract:

Jobs on high-performance computing (HPC) clusters can suffer significant performance degradation due to inter-job network interference. Topology-aware job allocation problem (TJAP) is such a problem that decides how to dedicate nodes to specific applications to mitigate inter-job network interference. In this paper, we study the window-based TJAP on a fat-tree network aiming at minimizing the cost of communication hop, a defined inter-job interference metric. The window-based approach for scheduling repeats periodically, taking the jobs in the queue and solving an assignment problem that maps jobs to the available nodes. Two special allocation strategies are considered, i.e., static continuity assignment strategy (SCAS) and dynamic continuity assignment strategy (DCAS). For the SCAS, a 0-1 integer programming is developed. For the DCAS, an approach called neural simulated algorithm (NSA), which is an extension to simulated algorithm (SA) that learns a repair operator and employs them in a guided heuristic search, is proposed. The efficacy of NSA is demonstrated with a computational study against SA and SCIP. The results of numerical experiments indicate that both the model and algorithm proposed in this paper are effective.

Keywords: high-performance computing, job allocation, neural simulated annealing, topology-aware

Procedia PDF Downloads 116

Authors: Aydin Azizi, Aburrahman Tanira

Abstract:

The main source of energy used in this modern age is fossil fuels. There is a myriad of problems that come with the use of fossil fuels, out of which the issues with the greatest impact are its scarcity and the cost it imposes on the planet. Fossil fuels are the only plausible option for many vital functions and processes; the most important of these is transportation. Thus, using this source of energy wisely and as efficiently as possible is a must. The aim of this work was to explore utilising mathematical modelling and artificial intelligence techniques to enhance fuel consumption in passenger cars by focusing on the speed at which cars are driven. An artificial neural network with an error less than 0.05 was developed to be applied practically as to predict the rate of fuel consumption in vehicles.

Keywords: mathematical modeling, neural networks, fuel consumption, fossil fuel

Procedia PDF Downloads 405

Authors: Ahmad Saadiq, Neeraj Sahu

Abstract:

Sediment, which comprises of solid particles of mineral and organic material are transported by water. In river systems, the amount of sediment transported is controlled by both the transport capacity of the flow and the supply of sediment. The transport of sediment in rivers is important with respect to pollution, channel navigability, reservoir ageing, hydroelectric equipment longevity, fish habitat, river aesthetics and scientific interests. The sediment load transported in a river is a very complex hydrological phenomenon. Hence, sediment transport has attracted the attention of engineers from various aspects, and different methods have been used for its estimation. So, several experimental equations have been submitted by experts. Though the results of these methods have considerable differences with each other and with experimental observations, because the sediment measures have some limits, these equations can be used in estimating sediment load. In this present study, two black box models namely, an SRC (Sediment Rating Curve) and ANN (Artificial Neural Network) are used in the simulation of the suspended sediment load. The study is carried out for Seonath subbasin. Seonath is the biggest tributary of Mahanadi river, and it carries a vast amount of sediment. The data is collected for Jondhra hydrological observation station from India-WRIS (Water Resources Information System) and IMD (Indian Meteorological Department). These data include the discharge, sediment concentration and rainfall for 10 years. In this study, sediment load is estimated from the input parameters (discharge, rainfall, and past sediment) in various combination of simulations. A sediment rating curve used the water discharge to estimate the sediment concentration. This estimated sediment concentration is converted to sediment load. Likewise, for the application of these data in ANN, they are normalised first and then fed in various combinations to yield the sediment load. RMSE (root mean square error) and R² (coefficient of determination) between the observed load and the estimated load are used as evaluating criteria. For an ideal model, RMSE is zero and R² is 1. However, as the models used in this study are black box models, they don’t carry the exact representation of the factors which causes sedimentation. Hence, a model which gives the lowest RMSE and highest R² is the best model in this study. The lowest values of RMSE (based on normalised data) for sediment rating curve, feed forward back propagation, cascade forward back propagation and neural network fitting are 0.043425, 0.00679781, 0.0050089 and 0.0043727 respectively. The corresponding values of R² are 0.8258, 0.9941, 0.9968 and 0.9976. This implies that a neural network fitting model is superior to the other models used in this study. However, a drawback of neural network fitting is that it produces few negative estimates, which is not at all tolerable in the field of estimation of sediment load, and hence this model can’t be crowned as the best model among others, based on this study. A cascade forward back propagation produces results much closer to a neural network model and hence this model is the best model based on the present study.

Keywords: artificial neural network, Root mean squared error, sediment, sediment rating curve

Procedia PDF Downloads 325

Authors: Brwa Abdulrahman Abubaker

Abstract:

Recently, there has been a lot of interest in the difficult task of applying reinforcement learning to autonomous mobile robots. Conventional reinforcement learning (TRL) techniques have many drawbacks, such as lengthy computation times, intricate control frameworks, a great deal of trial and error searching, and sluggish convergence. In this paper, a modified Spiking Neural Network (SNN) is used to offer a distinct method for autonomous mobile robot learning and control in unexpected surroundings. As a learning algorithm, the suggested model combines dopamine modulation with spike-timing-dependent plasticity (STDP). In order to create more computationally efficient, biologically inspired control systems that are adaptable to changing settings, this work uses the effective and physiologically credible Izhikevich neuron model. This study is primarily focused on creating an algorithm for target tracking in the presence of obstacles. Results show that the SNN trained with three obstacles yielded an impressive 96% success rate for our proposal, with collisions happening in about 4% of the 214 simulated seconds.

Keywords: spiking neural network, spike-timing-dependent plasticity, dopamine modulation, reinforcement learning

Procedia PDF Downloads 21

Authors: Jiangxia Han, Liang Xue, Keda Chen

Abstract:

Despite the significant progress over the last decades in reservoir simulation using numerical discretization, meshing is complex. Moreover, the high degree of freedom of the space-time flow field makes the solution process very time-consuming. Therefore, we present Physics-Informed Convolutional Neural Networks(PICNN) as a hybrid scientific theory and data method for reservoir modeling. Besides labeled data, the model is driven by the scientific theories of the underlying problem, such as governing equations, boundary conditions, and initial conditions. PICNN integrates governing equations and boundary conditions into the network architecture in the form of a customized convolution kernel. The loss function is composed of data matching, initial conditions, and other measurable prior knowledge. By customizing the convolution kernel and minimizing the loss function, the neural network parameters not only fit the data but also honor the governing equation. The PICNN provides a methodology to model and history-match flow and transport problems in porous media. Numerical results demonstrate that the proposed PICNN can provide an accurate physical solution from a limited dataset. We show how this method can be applied in the context of a forward simulation for continuous problems. Furthermore, several complex scenarios are tested, including the existence of data noise, different work schedules, and different good patterns.

Keywords: convolutional neural networks, deep learning, flow and transport in porous media, physics-informed neural networks, reservoir simulation

Procedia PDF Downloads 143

Authors: Abdelazziz Aouiche, El Moundher Aouiche, Mouhamed Salah Soudani

Abstract:

Renewable energy sources now significantly contribute to the replacement of traditional fossil fuel energy sources. One of the most potent types of renewable energy that has developed quickly in recent years is photovoltaic energy. We all know that solar energy, which is sustainable and non-depleting, is the best knowledge form of energy that we have at our disposal. Due to changing weather conditions, the primary drawback of conventional solar PV cells is their inability to track their maximum power point. In this study, we apply artificial neural networks (ANN) to automatically track and measure the maximum power point (MPP) of solar panels. In MATLAB, the complete system is simulated, and the results are adjusted for the external environment. The results are better performance than traditional MPPT methods and the results demonstrate the advantages of using neural networks in solar PV systems.

Keywords: modeling, photovoltaic panel, artificial neural networks, maximum power point tracking

Procedia PDF Downloads 88

Authors: Pengchao Wei, Xiangzhong Fang

Abstract:

Noise is ubiquitous in this world. Denoising is an essential technology, especially in image semantic segmentation, where noises are generally categorized into two main types i.e. feature noise and label noise. The main focus of this paper is aiming at modeling label noise, investigating the behaviors of different types of label noise on image semantic segmentation tasks using K-Nearest-Neighbor and Convolutional Neural Network classifier. The performance without label noise and with is evaluated and illustrated in this paper. In addition to that, the influence of feature noise on the image semantic segmentation task is researched as well and a feature noise reduction method is applied to mitigate its influence in the learning procedure.

Keywords: convolutional neural network, denoising, feature noise, image semantic segmentation, k-nearest-neighbor, label noise

Procedia PDF Downloads 220

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 194

Authors: Seyed Sadegh Naseralavi, Najmeh Bemani

Abstract:

In this paper, different concrete codes including America, New Zealand, Mexico, Italy, India, Canada, Hong Kong, Euro Code and Britain are compared with the Iranian concrete design code. First, by using Adaptive Neuro Fuzzy Inference System (ANFIS), the codes having the most correlation with the Iranian ninth issue of the national regulation are determined. Consequently, two anticipated methods are used for comparing the codes: Artificial Neural Network (ANN) and Multi-variable regression. The results show that ANN performs better. Predicting is done by using only tensile steel ratio and with ignoring the compression steel ratio.

Keywords: adaptive neuro fuzzy inference system, anticipate method, artificial neural network, concrete design code, multi-variable regression

Procedia PDF Downloads 284

Authors: M. Saiful Islam, M. Mohandes, S. Rehman, S. Badran

Abstract:

Increasing necessity of wind power is directing us to have precise knowledge on wind resources. Methodical investigation of potential locations is required for wind power deployment. High penetration of wind energy to the grid is leading multi megawatt installations with huge investment cost. This fact appeals to determine appropriate places for wind farm operation. For accurate assessment, detailed examination of wind speed profile, relative humidity, temperature and other geological or atmospheric parameters are required. Among all of these uncertainty factors influencing wind power estimation, vertical extrapolation of wind speed is perhaps the most difficult and critical one. Different approaches have been used for the extrapolation of wind speed to hub height which are mainly based on Log law, Power law and various modifications of the two. This paper proposes a Artificial Neural Network (ANN) and Genetic Algorithm (GA) based hybrid model, namely GA-NN for vertical extrapolation of wind speed. This model is very simple in a sense that it does not require any parametric estimations like wind shear coefficient, roughness length or atmospheric stability and also reliable compared to other methods. This model uses available measured wind speeds at 10m, 20m and 30m heights to estimate wind speeds up to 100m. A good comparison is found between measured and estimated wind speeds at 30m and 40m with approximately 3% mean absolute percentage error. Comparisons with ANN and power law, further prove the feasibility of the proposed method.

Keywords: wind profile, vertical extrapolation of wind, genetic algorithm, artificial neural network, hybrid machine learning

Procedia PDF Downloads 489

Authors: Zhi-Jun Lu, Qi Lu, Meng Wu, Qian Xiang, Jun Gu

Abstract:

The analysis of perforated steel members is a 3D problem in nature, therefore the traditional analytical expressions for the ultimate load of thin-walled steel sections cannot be used for the perforated steel member design. In this study, finite element method (FEM) and artificial neural network (ANN) were used to simulate the process of stub column tests based on specific codes. Results show that compared with those of the FEM model, the ultimate load predictions obtained from ANN technique were much closer to those obtained from the physical experiments. The ANN model for the solving the hard problem of complex steel perforated sections is very promising.

Keywords: artificial neural network (ANN), finite element method (FEM), perforated sections, thin-walled Steel, ultimate load

Procedia PDF Downloads 352

Authors: Saad Chahba, Rabia Sehab, Ahmad Akrad, Cristina Morel

Abstract:

Nowadays, the electric machines used in urban electric vehicles are, in most cases, three-phase electric machines with or without a magnet in the rotor. Permanent Magnet Synchronous Machine (PMSM) and Induction Machine (IM) are the main components of drive trains of electric and hybrid vehicles. These machines have very good performance in healthy operation mode, but they are not redundant to ensure safety in faulty operation mode. Faced with the continued growth in the demand for electric vehicles in the automotive market, improving the reliability of electric vehicles is necessary over the lifecycle of the electric vehicle. Multiphase electric machines respond well to this constraint because, on the one hand, they have better robustness in the event of a breakdown (opening of a phase, opening of an arm of the power stage, intern-turn short circuit) and, on the other hand, better power density. In this work, a diagnosis approach using a neural network for an open circuit fault or more of a five-phase induction machine is developed. Validation on the simulator of the vehicle drivetrain, at reduced power, is carried out, creating one and more open circuit stator phases showing the efficiency and the reliability of the new approach to detect and to locate on-line one or more open phases of a five-induction machine.

Keywords: electric vehicle drivetrain, multiphase drives, induction machine, control, open circuit (OC) fault diagnosis, artificial neural network

Procedia PDF Downloads 208

Authors: Afaf Alharbi, Qianni Zhang

Abstract:

The identification of malignant tissue in histopathological slides holds significant importance in both clinical settings and pathology research. This paper introduces a methodology aimed at automatically categorizing cancerous tissue through the utilization of a multiple-instance learning framework. This framework is specifically developed to acquire knowledge of the Bernoulli distribution of the bag label probability by employing neural networks. Furthermore, we put forward a neural network based permutation-invariant aggregation operator, equivalent to attention mechanisms, which is applied to the multi-instance learning network. Through empirical evaluation of an openly available colon cancer histopathology dataset, we provide evidence that our approach surpasses various conventional deep learning methods.

Keywords: attention multiple instance learning, MIL and transfer learning, histopathological slides, cancer tissue classification

Procedia PDF Downloads 110

Authors: Nassib Abdallah, Pierre Chauvet, Abd El Salam Hajjar, Bassam Daya

Abstract:

In this paper, we propose an optimized brain computer interface (BCI) system for unspoken speech recognition, based on the fact that the constructions of unspoken words rely strongly on the Wernicke area, situated in the temporal lobe. Our BCI system has four modules: (i) the EEG Acquisition module based on a non-invasive headset with 14 electrodes; (ii) the Preprocessing module to remove noise and artifacts, using the Common Average Reference method; (iii) the Features Extraction module, using Wavelet Packet Transform (WPT); (iv) the Classification module based on a one-hidden layer artificial neural network. The present study consists of comparing the recognition accuracy of 5 Arabic words, when using all the headset electrodes or only the 4 electrodes situated near the Wernicke area, as well as the selection effect of the subbands produced by the WPT module. After applying the articial neural network on the produced database, we obtain, on the test dataset, an accuracy of 83.4% with all the electrodes and all the subbands of 8 levels of the WPT decomposition. However, by using only the 4 electrodes near Wernicke Area and the 6 middle subbands of the WPT, we obtain a high reduction of the dataset size, equal to approximately 19% of the total dataset, with 67.5% of accuracy rate. This reduction appears particularly important to improve the design of a low cost and simple to use BCI, trained for several words.

Keywords: brain-computer interface, speech recognition, artificial neural network, electroencephalography, EEG, wernicke area

Procedia PDF Downloads 270

Authors: Marziyeh Khavari

Abstract:

In recent decades, climate change, global warming, and the growing population worldwide face some challenges, such as increasing food consumption and shortage of resources. Assessing how climate change could disturb crops, especially hazelnut production, seems crucial for sustainable agriculture production. For hazelnut cultivation in the mid-warm condition, such as in Iran, here we present an investigation of climate parameters and how much they are effective on fertility and nut production of hazelnut trees. Therefore, the climate change of the northern zones in Iran has investigated (1960-2017) and was reached an uptrend in temperature. Furthermore, the descriptive analysis performed on six cultivars during seven years shows how this small-scale survey could demonstrate the effects of climate change on hazelnut production and stability. Results showed that some climate parameters are more significant on nut production, such as solar radiation, soil temperature, relative humidity, and precipitation. Moreover, some cultivars have produced more stable production, for instance, Negret and Segorbe, while the Mervill de Boliver recorded the most variation during the study. Another aspect that needs to be met is training and predicting an actual model to simulate nut production through a neural network and linear regression simulation. The study developed and estimated the ANN model's generalization capability with different criteria such as RMSE, SSE, and accuracy factors for dependent and independent variables (environmental and yield traits). The models were trained and tested while the accuracy of the model is proper to predict hazelnut production under fluctuations in weather parameters.

Keywords: climate change, neural network, hazelnut, global warming

Procedia PDF Downloads 132

Authors: Rama Shanker, Anil Kumar Sachan

Abstract:

Basic ingredients of concrete are cement, fine aggregate, coarse aggregate and water. To produce a concrete of certain specific properties, optimum proportion of these ingredients are mixed. The important factors which govern the mix design are grade of concrete, type of cement and size, shape and grading of aggregates. Concrete mix design method is based on experimentally evolved empirical relationship between the factors in the choice of mix design. Basic draw backs of this method are that it does not produce desired strength, calculations are cumbersome and a number of tables are to be referred for arriving at trial mix proportion moreover, the variation in attainment of desired strength is uncertain below the target strength and may even fail. To solve this problem, a lot of cubes of standard grades were prepared and attained 28 days strength determined for different combination of cement, fine aggregate, coarse aggregate and water. An artificial neural network (ANN) was prepared using these data. The input of ANN were grade of concrete, type of cement, size, shape and grading of aggregates and output were proportions of various ingredients. With the help of these inputs and outputs, ANN was trained using feed forward back proportion model. Finally trained ANN was validated, it was seen that it gave the result with/ error of maximum 4 to 5%. Hence, specific type of concrete can be prepared from given material properties and proportions of these materials can be quickly evaluated using the proposed ANN.

Keywords: aggregate proportions, artificial neural network, concrete grade, concrete mix design

Procedia PDF Downloads 389

Authors: Zhaojun Wang, Zongdi Sun, Zhiyuan Liu

Abstract:

First of all, the carbon trading price and trading volume in Shanghai are transformed by Fourier transform, and the frequency response diagram is obtained. Then, the frequency response diagram is analyzed and the Blackman filter is designed. The Blackman filter is used to filter, and the carbon trading time domain and frequency response diagram are obtained. After wavelet analysis, the carbon trading data were processed; respectively, we got the average value for each 5 days, 10 days, 20 days, 30 days, and 60 days. Finally, the data are used as input of the Back Propagation Neural Network model for prediction.

Keywords: Shanghai carbon trading, carbon trading price, carbon trading volume, wavelet analysis, BP neural network model

Procedia PDF Downloads 391

Authors: Hervice Roméo Fogno Fotsoa, Germaine Djuidje Kenmoe, Claude Vidal Aloyem Kazé

Abstract:

One of the main applications of machine learning is the prediction of time series. But a more accurate prediction requires a more optimal model of machine learning. Several optimization techniques have been developed, but without considering the input variables disposition of the system. Thus, this work aims to present a new machine learning architecture optimization technique based on their optimal input variables disposition. The validations are done on the prediction of wind time series, using data collected in Cameroon. The number of possible dispositions with four input variables is determined, i.e., twenty-four. Each of the dispositions is used to perform the prediction, with the main criteria being the training and prediction performances. The results obtained from a static architecture and a dynamic architecture of neural networks have shown that these performances are a function of the input variable's disposition, and this is in a different way from the architectures. This analysis revealed that it is necessary to take into account the input variable's disposition for the development of a more optimal neural network model. Thus, a new neural network training algorithm is proposed by introducing the search for the optimal input variables disposition in the traditional back-propagation algorithm. The results of the application of this new optimization approach on the two single neural network architectures are compared with the previously obtained results step by step. Moreover, this proposed approach is validated in a collaborative optimization method with a single objective optimization technique, i.e., genetic algorithm back-propagation neural networks. From these comparisons, it is concluded that each proposed model outperforms its traditional model in terms of training and prediction performance of time series. Thus the proposed optimization approach can be useful in improving the accuracy of time series forecasts. This proves that the proposed optimization approach can be useful in improving the accuracy of time series prediction based on machine learning.

Keywords: input variable disposition, machine learning, optimization, performance, time series prediction

Procedia PDF Downloads 109

Authors: Mohammad Namazi, Mohammad Sadeghzadeh Maharluie

Abstract:

Predicting earnings management is vital for the capital market participants, financial analysts and managers. The aim of this research is attempting to respond to this query: Is there a significant difference between the regression model and neural networks’ models in predicting earnings management, and which one leads to a superior prediction of it? In approaching this question, a Linear Regression (LR) model was compared with two neural networks including Multi-Layer Perceptron (MLP), and Generalized Regression Neural Network (GRNN). The population of this study includes 94 listed companies in Tehran Stock Exchange (TSE) market from 2003 to 2011. After the results of all models were acquired, ANOVA was exerted to test the hypotheses. In general, the summary of statistical results showed that the precision of GRNN did not exhibit a significant difference in comparison with MLP. In addition, the mean square error of the MLP and GRNN showed a significant difference with the multi variable LR model. These findings support the notion of nonlinear behavior of the earnings management. Therefore, it is more appropriate for capital market participants to analyze earnings management based upon neural networks techniques, and not to adopt linear regression models.

Keywords: earnings management, generalized linear regression, neural networks multi-layer perceptron, Tehran stock exchange

Procedia PDF Downloads 421

Authors: Bryan Crompton, Daniel Giger, Tanay Mehta, Apurva Mody

Abstract:

The task of classifying radio frequency (RF) signals has seen recent success in employing deep neural network models. In this work, we present a combined signal processing and machine learning approach to signal classification for cochannel anomalous signals. The power spectral density and cyclostationary signal processing features of a captured signal are computed and fed into a neural net to produce a classification decision. Our combined signal preprocessing and machine learning approach allows for simpler neural networks with fast training times and small computational resource requirements for inference with longer preprocessing time.

Keywords: signal processing, machine learning, cyclostationary signal processing, signal classification

Procedia PDF Downloads 107

Authors: Raida Zouari, Iness Ahriz, Rafik Zayani, Ali Dziri, Ridha Bouallegue

Abstract:

This paper proposes a room level indoor localization algorithm based on the use Multi-Layer Neural Network (MLNN) classifiers and one versus one strategy. Seven parameters of the Channel Impulse Response (CIR) were used and Gram-Shmidt Orthogonalization was performed to study the relevance of the extracted parameters. Simulation results show that when relevant CIR parameters are used as position fingerprint and when optimal MLNN architecture is selected good room level localization score can be achieved. The current study showed also that some of the CIR parameters are not correlated to the location and can decrease the localization performance of the system.

Keywords: mobile indoor localization, multi-layer neural network (MLNN), channel impulse response (CIR), Gram-Shmidt orthogonalization

Procedia PDF Downloads 356

Authors: E. A. Mlybari, M. S. Elbisy, A. H. Alshahri, O. M. Albarakati

Abstract:

Sea level rise threatens to increase the impact of future storms and hurricanes on coastal communities. Accurate sea level change prediction and supplement is an important task in determining constructions and human activities in coastal and oceanic areas. In this study, support vector machines (SVM) is proposed to predict daily tidal levels along the Jeddah Coast, Saudi Arabia. The optimal parameter values of kernel function are determined using a genetic algorithm. The SVM results are compared with the field data and with back propagation (BP). Among the models, the SVM is superior to BPNN and has better generalization performance.

Keywords: tides, prediction, support vector machines, genetic algorithm, back-propagation neural network, risk, hazards

Procedia PDF Downloads 468

Authors: L. Rakesh, T. Y. Heblekar

Abstract:

This study entails the development and optimization of a mathematical model for a floating drum biogas reactor from first principles using thermal and empirical considerations. The model was derived on the basis of mass conservation, lumped mass heat transfer formulations and empirical biogas formation laws. The treatment leads to a system of coupled nonlinear ordinary differential equations whose solution mapped four-time independent controllable parameters to five output variables which adequately serve to describe the reactor performance. These equations were solved numerically using fourth order Runge-Kutta method for a range of input parameter values. Using the data so obtained an Artificial Neural Network with a single hidden layer was trained using Levenberg-Marquardt Damped Least Squares (DLS) algorithm. This network was then fine-tuned for optimal mapping by varying hidden layer size. This fast forward model was then employed as a health score generator in the Bacterial Foraging Optimization code. The optimal operating state of the simplified Biogas reactor was thus obtained.

Keywords: biogas, floating drum reactor, neural network model, optimization

Procedia PDF Downloads 143

Authors: Constanza A. Barriga, Rafael Bernardi, Amokrane Berdja, Christian D. Guzman

Abstract:

Most image restoration methods in astronomy rely upon probabilistic tools that infer the best solution for a deconvolution problem. They achieve good performances when the point spread function (PSF) is spatially invariable in the image plane. However, this latter condition is not always satisfied with real optical systems. PSF angular variations cannot be evaluated directly from the observations, neither be corrected at a pixel resolution. We have developed a method for the restoration of images affected by static and anisotropic aberrations using deep neural networks that can be directly applied to sky images. The network is trained using simulated sky images corresponding to the T-80 telescope optical system, an 80 cm survey imager at Cerro Tololo (Chile), which are synthesized using a Zernike polynomial representation of the optical system. Once trained, the network can be used directly on sky images, outputting a corrected version of the image, which has a constant and known PSF across its field-of-view. The method was tested with the T-80 telescope, achieving better results than with PSF deconvolution techniques. We present the method and results on this telescope.

Keywords: aberrations, deep neural networks, image restoration, variable point spread function, wide field images

Procedia PDF Downloads 134

Authors: Shahrzad Zolfagharnassab, Abdul Rashid Mohamed Shariff, Reza Ehsani, Hawa Ze Jaffar, Ishak Aris

Abstract:

Ripeness estimation of oil palm fresh fruit is important processes that affect the profitableness and salability of oil palm fruits. The adulthood or ripeness of the oil palm fruits influences the quality of oil palm. Conventional procedure includes physical grading of Fresh Fruit Bunches (FFB) maturity by calculating the number of loose fruits per bunch. This physical classification of oil palm FFB is costly, time consuming and the results may have human error. Hence, many researchers try to develop the methods for ascertaining the maturity of oil palm fruits and thereby, deviously the oil content of distinct palm fruits without the need for exhausting oil extraction and analysis. This research investigates the potential of infrared images (Thermal Images) as a predictor to classify the oil palm FFB ripeness. A total of 270 oil palm fresh fruit bunches from most common cultivar of oil palm bunches Nigresens according to three maturity categories: under ripe, ripe and over ripe were collected. Each sample was scanned by the thermal imaging cameras FLIR E60 and FLIR T440. The average temperature of each bunches were calculated by using image processing in FLIR Tools and FLIR ThermaCAM researcher pro 2.10 environment software. The results show that temperature content decreased from immature to over mature oil palm FFBs. An overall analysis-of-variance (ANOVA) test was proved that this predictor gave significant difference between underripe, ripe and overripe maturity categories. This shows that the temperature as predictors can be good indicators to classify oil palm FFB. Classification analysis was performed by using the temperature of the FFB as predictors through Linear Discriminant Analysis (LDA), Mahalanobis Discriminant Analysis (MDA), Artificial Neural Network (ANN) and K- Nearest Neighbor (KNN) methods. The highest overall classification accuracy was 88.2% by using Artificial Neural Network. This research proves that thermal imaging and neural network method can be used as predictors of oil palm maturity classification.

Keywords: artificial neural network, maturity classification, oil palm FFB, thermal imaging

Procedia PDF Downloads 360