Search results for: neural network training

Authors: S. M. Anowarul Haque, Md. Asiful Islam

Abstract:

Electrical load forecasting is considered to be one of the most indispensable parts of a modern-day electrical power system. To ensure a reliable and efficient supply of electric energy, special emphasis should have been put on the predictive feature of electricity supply. Artificial Neural Network-based approaches have emerged to be a significant area of interest for electric load forecasting research. This paper proposed an Artificial Neural Network model based on the particle swarm optimization algorithm for improved electric load forecasting for Mymensingh, Bangladesh. The forecasting model is developed and simulated on the MATLAB environment with a large number of training datasets. The model is trained based on eight input parameters including historical load and weather data. The predicted load data are then compared with an available dataset for validation. The proposed neural network model is proved to be more reliable in terms of day-wise load forecasting for Mymensingh, Bangladesh.

Keywords: load forecasting, artificial neural network, particle swarm optimization

Procedia PDF Downloads 148

Authors: Guanghua Zhang, Fubao Wang, Weijun Duan

Abstract:

Convolution neural network (CNN) has attracted more and more attention on recent years. Especially in the field of computer vision and image classification. However, unsupervised learning with CNN has received less attention than supervised learning. In this work, we use a new powerful tool which is deep convolutional generative adversarial networks (DCGANs) to generate images from Sloan Digital Sky Survey. Training by various star and galaxy images, it shows that both the generator and the discriminator are good for unsupervised learning. In this paper, we also took several experiments to choose the best value for hyper-parameters and which could help to stabilize the training process and promise a good quality of the output.

Keywords: convolution neural network, discriminator, generator, unsupervised learning

Procedia PDF Downloads 240

Authors: Zan Azma Nasruddin, Irwan Mazlin, Nor Aziah Daud, Fauziah Redzuan, Fariza Hanis Abdul Razak

Abstract:

This paper focuses on a machine learning that learn the correct pronunciation of Makhraj Huroofs. Usually, people need to find an expert to pronounce the Huroof accurately. In this study, the researchers have developed a system that is able to learn the selected Huroofs which are ha, tsa, zho, and dza using the Convolutional Neural Network. The researchers present the chosen type of the CNN architecture to make the system that is able to learn the data (Huroofs) as quick as possible and produces high accuracy during the prediction. The researchers have experimented the system to measure the accuracy and the cross entropy in the training process.

Keywords: convolutional neural network, Makhraj recognition, speech recognition, signal processing, tensorflow

Procedia PDF Downloads 307

Authors: Mohammad Heidari

Abstract:

In this paper a method for high strength steel is proposed of residual stresses in autofrettaged tubes by combination of artificial neural networks is presented. Many different thick walled cylinders that were subjected to different conditions were studied. At first, the residual stress is calculated by analytical solution. Then by changing of the parameters that influenced in residual stresses such as percentage of autofrettage, internal pressure, wall ratio of cylinder, material property of cylinder, bauschinger and hardening effect factor, a neural network is created. These parameters are the input of network. The output of network is residual stress. Numerical data, employed for training the network and capabilities of the model in predicting the residual stress has been verified. The output obtained from neural network model is compared with numerical results, and the amount of relative error has been calculated. Based on this verification error, it is shown that the radial basis function of neural network has the average error of 2.75% in predicting residual stress of thick wall cylinder. Further analysis of residual stress of thick wall cylinder under different input conditions has been investigated and comparison results of modeling with numerical considerations shows a good agreement, which also proves the feasibility and effectiveness of the adopted approach.

Keywords: thick walled cylinder, residual stress, radial basis, artificial neural network

Procedia PDF Downloads 389

Authors: Strahinja Kovačević, Jelena Vladić, Senka Vidović, Zoran Zeković, Lidija Jevrić, Sanja Podunavac Kuzmanović

Abstract:

Supercritical extracts of highly valuated medicinal plant Satureja montana were prepared by application of supercritical carbon dioxide extraction in the carbon dioxide pressure range from 125 to 350 bar and temperature range from 40 to 60°C. Using GC/MS method of analysis chemical profiles (aromatic constituents) of S. montana extracts were obtained. Self-training artificial neural networks were applied to predict the retention time of the analyzed terpenes in GC/MS system. The best ANN model obtained was multilayer perceptron (MLP 11-11-1). Hidden activation was tanh and output activation was identity with Broyden–Fletcher–Goldfarb–Shanno training algorithm. Correlation measures of the obtained network were the following: R(training) = 0.9975, R(test) = 0.9971 and R(validation) = 0.9999. The comparison of the experimental and predicted retention times of the analyzed compounds showed very high correlation (R = 0.9913) and significant predictive power of the established neural network.

Keywords: ANN regression, GC/MS, Satureja montana, terpenes

Procedia PDF Downloads 428

Authors: Jui-Chen Huang, Shou-Hsiung Cheng

Abstract:

This study examined their willingness to use telecare for people who have had experience falling in the last three months in Taiwan. This study adopted convenience sampling and a structural questionnaire to collect data. It was based on the definition and the constructs related to the Health Belief Model (HBM). HBM is comprised of seven constructs: perceived benefits (PBs), perceived disease threat (PDT), perceived barriers of taking action (PBTA), external cues to action (ECUE), internal cues to action (ICUE), attitude toward using (ATT), and behavioral intention to use (BI). This study adopted Fuzzy Neural Network (FNN) to put forward an effective method. It shows the dependence of ATT on PB, PDT, PBTA, ECUE, and ICUE. The training and testing data RMSE (root mean square error) are 0.028 and 0.166 in the FNN, respectively. The training and testing data RMSE are 0.828 and 0.578 in the regression model, respectively. On the other hand, as to the dependence of ATT on BI, as presented in the FNN, the training and testing data RMSE are 0.050 and 0.109, respectively. The training and testing data RMSE are 0.529 and 0.571 in the regression model, respectively. The results show that the FNN method is better than the regression analysis. It is an effective and viable good way.

Keywords: fall, fuzzy neural network, health belief model, telecare, willingness

Procedia PDF Downloads 162

Authors: Jiahao Cui

Abstract:

In the past centuries, due to climate change and intense whaling, the global whale population has dramatically declined. Among the various whale species, the fin whale experienced the most drastic drop in number due to its popularity in whaling. Under this background, identifying fin whale calls could be immensely beneficial to the preservation of the species. This paper uses feature extraction to process the input audio signal, then a network based on AlexNet and three networks based on the ResNet model was constructed to classify fin whale calls. A mixture of the DOSITS database and the Watkins database was used during training. The results demonstrate that a modified ResNet network has the best performance considering precision and network complexity.

Keywords: convolutional neural network, ResNet, AlexNet, fin whale preservation, feature extraction

Procedia PDF Downloads 94

Authors: Zachary Pan

Abstract:

Our general mission is to solve the problem of classifying images into different body part types and deciding if each of them is healthy or not. However, for now, we will determine healthiness for only one-sixth of the body parts, specifically the chest. We will detect pneumonia in X-ray scans of those chest images. With this type of AI, doctors can use it as a second opinion when they are taking CT or X-ray scans of their patients. Another ad-vantage of using this machine learning classifier is that it has no human weaknesses like fatigue. The overall ap-proach to this problem is to split the problem into two parts: first, classify the image, then determine if it is healthy. In order to classify the image into a specific body part class, the body parts dataset must be split into test and training sets. We can then use many models, like neural networks or logistic regression models, and fit them using the training set. Now, using the test set, we can obtain a realistic accuracy the models will have on images in the real world since these testing images have never been seen by the models before. In order to increase this testing accuracy, we can also apply many complex algorithms to the models, like multiplicative weight update. For the second part of the problem, to determine if the body part is healthy, we can have another dataset consisting of healthy and non-healthy images of the specific body part and once again split that into the test and training sets. We then use another neural network to train on those training set images and use the testing set to figure out its accuracy. We will do this process only for the chest images. A major conclusion reached is that convolutional neural networks are the most reliable and accurate at image classification. In classifying the images, the logistic regression model, the neural network, neural networks with multiplicative weight update, neural networks with the black box algorithm, and the convolutional neural network achieved 96.83 percent accuracy, 97.33 percent accuracy, 97.83 percent accuracy, 96.67 percent accuracy, and 98.83 percent accuracy, respectively. On the other hand, the overall accuracy of the model that de-termines if the images are healthy or not is around 78.37 percent accuracy.

Keywords: body part, healthcare, machine learning, neural networks

Procedia PDF Downloads 72

Authors: İkbal Eski

Abstract:

This investigation is researched on design of robust neural network predictors for analyzing vibration effects on moving parts of a drilling machine. Moreover, the research is divided two parts; first part is experimental investigation, second part is simulation analysis with neural networks. Therefore, a real time the drilling machine is used to vibrations during working conditions. The measured real vibration parameters are analyzed with proposed neural network. As results: Simulation approaches show that Radial Basis Neural Network has good performance to adapt real time parameters of the drilling machine.

Keywords: artificial neural network, vibration analyses, drilling machine, robust

Procedia PDF Downloads 360

Authors: Malgorzata Schwab, Ashis Kumer Biswas

Abstract:

In this concept paper, we explore the topic of Reversibility in Neural Networks leveraged for Network Integrity Verification and crafted the term ''Trusted Neural Network'' (TNN), paired with the API abstraction around it, to embrace the idea formally. This newly proposed high-level generalizable TNN model builds upon the Invertible Neural Network architecture, trained simultaneously in both forward and reverse directions. This allows for the original system inputs to be compared with the ones reconstructed from the outputs in the reversed flow to assess the integrity of the end-to-end inference flow. The outcome of that assessment is captured as an Integrity Score. Concrete implementation reflecting the needs of specific problem domains can be derived from this general approach and is demonstrated in the experiments. The model aspires to become a useful practice in drafting high-level systems architectures which incorporate AI capabilities.

Keywords: trusted, neural, invertible, API

Procedia PDF Downloads 122

Authors: O. P. Oladipo, O. A. Falode

Abstract:

The determination of Recovery Factor is of great importance to the reservoir engineer since it relates reserves to the initial oil in place. Reserves are the producible portion of reservoirs and give an indication of the profitability of a field Development. The core objective of this project is to develop an artificial neural network model using selected reservoir data to predict Recovery Factors (RF) of hydrocarbon reservoirs and compare the model with a couple of the existing correlations. The type of Artificial Neural Network model developed was the Single Layer Feed Forward Network. MATLAB was used as the network simulator and the network was trained using the supervised learning method, Afterwards, the network was tested with input data never seen by the network. The results of the predicted values of the recovery factors of the Artificial Neural Network Model, API Correlation for water drive reservoirs (Sands and Sandstones) and Guthrie and Greenberger Correlation Equation were obtained and compared. It was noted that the coefficient of correlation of the Artificial Neural Network Model was higher than the coefficient of correlations of the other two correlation equations, thus making it a more accurate prediction tool. The Artificial Neural Network, because of its accurate prediction ability is helpful in the correct prediction of hydrocarbon reservoir factors. Artificial Neural Network could be applied in the prediction of other Petroleum Engineering parameters because it is able to recognise complex patterns of data set and establish a relationship between them.

Keywords: recovery factor, reservoir, reserves, artificial neural network, hydrocarbon, MATLAB, API, Guthrie, Greenberger

Procedia PDF Downloads 410

Authors: Azadeh Bashiri

Abstract:

Introduction: Lack of proper diagnosis and inadequate treatment of asthma leads to physical and financial complications. This study aimed to use data mining techniques and creating a neural network intelligent system for diagnosis of asthma. Methods: The study population is the patients who had visited one of the Lung Clinics in Tehran. Data were analyzed using the SPSS statistical tool and the chi-square Pearson's coefficient was the basis of decision making for data ranking. The considered neural network is trained using back propagation learning technique. Results: According to the analysis performed by means of SPSS to select the top factors, 13 effective factors were selected, in different performances, data was mixed in various forms, so the different models were made for training the data and testing networks and in all different modes, the network was able to predict correctly 100% of all cases. Conclusion: Using data mining methods before the design structure of system, aimed to reduce the data dimension and the optimum choice of the data, will lead to a more accurate system. Therefore, considering the data mining approaches due to the nature of medical data is necessary.

Keywords: asthma, data mining, Artificial Neural Network, intelligent system

Procedia PDF Downloads 246

Authors: Ahmad Alwosheel, Ahmed Alqaraawi

Abstract:

This work proposes a new speaker segmentation approach for two speakers. It is an online approach that does not require a prior information about speaker models. It has two phases, a conventional approach such as unsupervised BIC-based is utilized in the first phase to detect speaker changes and train a Neural Network, while in the second phase, the output trained parameters from the Neural Network are used to predict next incoming audio stream. Using this approach, a comparable accuracy to similar BIC-based approaches is achieved with a significant improvement in terms of computation time.

Keywords: artificial neural network, diarization, speaker indexing, speaker segmentation

Procedia PDF Downloads 470

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 135

Authors: Khader S. Al-Aidmat, Venus W. Samawi

Abstract:

Blurred vision in the misty atmosphere is essential problem which needs to be resolved. To solve this problem, we developed a technique to restore foggy degraded image from its original version using Back-propagation neural network (BP-NN). The suggested technique is based on mapping between foggy scene and its corresponding original scene. Seven different approaches are suggested based on type of features used in image restoration. Features are extracted from spatial and spatial-frequency domain (using DCT). Each of these approaches comes with its own BP-NN architecture depending on type and number of used features. The weight matrix resulted from training each BP-NN represents a fog filter. The performance of these filters are evaluated empirically (using PSNR), and perceptually. By comparing the performance of these filters, the effective features that suits BP-NN technique for restoring foggy images is recognized. This system proved its effectiveness and success in restoring moderate foggy images.

Keywords: artificial neural network, discrete cosine transform, feed forward neural network, foggy image restoration

Procedia PDF Downloads 364

Authors: José Luis Carrillo-Medina, Roberto Latorre

Abstract:

Experimental evidence has revealed that different living neural systems can sign their output signals with some specific neural signature. Although experimental and modeling results suggest that neural signatures can have an important role in the activity of neural networks in order to identify the source of the information or to contextualize a message, the functional meaning of these neural fingerprints is still unclear. The existence of cellular mechanisms to identify the origin of individual neural signals can be a powerful information processing strategy for the nervous system. We have recently built different models to study the ability of a neural network to process information based on the emission and recognition of specific neural fingerprints. In this paper we further analyze the features that can influence on the information processing ability of this kind of networks. In particular, we focus on the role that the duration of a refractory period in each neuron after emitting a signed message can play in the network collective dynamics.

Keywords: neural signature, neural fingerprint, processing based on signal identification, self-organizing neural network

Procedia PDF Downloads 463

Authors: Martins Y. Otache, John J. Musa, Abayomi I. Kuti, Mustapha Mohammed

Abstract:

The performance of an artificial neural network (ANN) is contingent on a host of factors, for instance, the network optimisation scheme. In view of this, the study examined the general implications of the ANN training optimisation algorithm on its forecast performance. To this end, the Bayesian regularisation (Br), Levenberg-Marquardt (LM), and the adaptive learning gradient descent: GDM (with momentum) algorithms were employed under different ANN structural configurations: (1) single-hidden layer, and (2) double-hidden layer feedforward back propagation network. Results obtained revealed generally that the gradient descent with momentum (GDM) optimisation algorithm, with its adaptive learning capability, used a relatively shorter time in both training and validation phases as compared to the Levenberg- Marquardt (LM) and Bayesian Regularisation (Br) algorithms though learning may not be consummated; i.e., in all instances considering also the prediction of extreme flow conditions for 1-day and 5-day ahead, respectively especially using the ANN model. In specific statistical terms on the average, model performance efficiency using the coefficient of efficiency (CE) statistic were Br: 98%, 94%; LM: 98 %, 95 %, and GDM: 96 %, 96% respectively for training and validation phases. However, on the basis of relative error distribution statistics (MAE, MAPE, and MSRE), GDM performed better than the others overall. Based on the findings, it is imperative to state that the adoption of ANN for real-time forecasting should employ training algorithms that do not have computational overhead like the case of LM that requires the computation of the Hessian matrix, protracted time, and sensitivity to initial conditions; to this end, Br and other forms of the gradient descent with momentum should be adopted considering overall time expenditure and quality of the forecast as well as mitigation of network overfitting. On the whole, it is recommended that evaluation should consider implications of (i) data quality and quantity and (ii) transfer functions on the overall network forecast performance.

Keywords: streamflow, neural network, optimisation, algorithm

Procedia PDF Downloads 126

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 162

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

Neural network approaches are machine learning methods used in many domains, such as healthcare and cyber security. Neural networks are mostly known for dealing with image datasets. While training with the images, several fundamental mathematical operations are carried out in the Neural Network. The operation includes a number of algebraic and mathematical functions, including derivative, convolution, and matrix inversion and transposition. Such operations require higher processing power than is typically needed for computer usage. Central Processing Unit (CPU) is not appropriate for a large image size of the dataset as it is built with serial processing. While Graphics Processing Unit (GPU) has parallel processing capabilities and, therefore, has higher speed. This paper uses advanced Neural Network techniques such as VGG16, Resnet50, Densenet, Inceptionv3, Xception, Mobilenet, XGBOOST-VGG16, and our proposed models to compare CPU and GPU resources. A system for classifying autism disease using face images of an autistic and non-autistic child was used to compare performance during testing. We used evaluation matrices such as Accuracy, F1 score, Precision, Recall, and Execution time. It has been observed that GPU runs faster than the CPU in all tests performed. Moreover, the performance of the Neural Network models in terms of accuracy increases on GPU compared to CPU.

Keywords: autism disease, neural network, CPU, GPU, transfer learning

Procedia PDF Downloads 88

Authors: V. Nikkhah Rashidabad, M. Manteghian, M. Masoumi, S. Mousavian, D. Ashouri

Abstract:

In this research, the capability of neural networks in modeling and learning complicated and nonlinear relations has been used to develop a model for the prediction of changes in the diameter of bubbles in pool boiling distilled water. The input parameters used in the development of this network include element temperature, heat flux, and retention time of bubbles. The test data obtained from the experiment of the pool boiling of distilled water, and the measurement of the bubbles form on the cylindrical element. The model was developed based on training algorithm, which is typologically of back-propagation type. Considering the correlation coefficient obtained from this model is 0.9633. This shows that this model can be trusted for the simulation and modeling of the size of bubble and thermal transfer of boiling.

Keywords: bubble diameter, heat flux, neural network, training algorithm

Procedia PDF Downloads 422

Authors: Lamyaa Gamal El-Deen Taha, Ashraf Sharawi

Abstract:

China launched satellite GF-2 in 2014. This study deals with comparing nearest neighbor object-based classification and neural network classification methods for classification of the fused GF-2 image. Firstly, rectification of GF-2 image was performed. Secondly, a comparison between nearest neighbor object-based classification and neural network classification for classification of fused GF-2 was performed. Thirdly, the overall accuracy of classification and kappa index were calculated. Results indicate that nearest neighbor object-based classification is better than neural network classification for urban mapping.

Keywords: GF-2 images, feature extraction-rectification, nearest neighbour object based classification, segmentation algorithms, neural network classification, multilayer perceptron

Procedia PDF Downloads 358

Authors: A. Clementking, C. Jothi Venkateswaran

Abstract:

Mathematical and computational functionalities such as descriptive mining, optimization, and predictions are espoused to resolve natural resource planning. The water quality prediction and its attributes influence determinations are adopted optimization techniques. The water properties are tainted while merging water resource one with another. This work aimed to predict influencing water resource distribution connectivity in accordance to water quality and sediment using an innovative proposed master-slave neural network back-propagation model. The experiment results are arrived through collecting water quality attributes, computation of water quality index, design and development of neural network model to determine water quality and sediment, master–slave back propagation neural network back-propagation model to determine variations on water quality and sediment attributes between the water resources and the recommendation for connectivity. The homogeneous and parallel biochemical reactions are influences water quality and sediment while distributing water from one location to another. Therefore, an innovative master-slave neural network model [M (9:9:2)::S(9:9:2)] designed and developed to predict the attribute variations. The result of training dataset given as an input to master model and its maximum weights are assigned as an input to the slave model to predict the water quality. The developed master-slave model is predicted physicochemical attributes weight variations for 85 % to 90% of water quality as a target values.The sediment level variations also predicated from 0.01 to 0.05% of each water quality percentage. The model produced the significant variations on physiochemical attribute weights. According to the predicated experimental weight variation on training data set, effective recommendations are made to connect different resources.

Keywords: master-slave back propagation neural network model(MSBPNNM), water quality analysis, multivariate analysis, environmental mining

Procedia PDF Downloads 447

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: convolutional neural network, deep learning, deep learning based FER, facial emotion recognition

Procedia PDF Downloads 234

Authors: Danladi Ali

Abstract:

In this paper, we measured GSM signal strength in the Dnepropetrovsk city in order to predict path loss in study area using nonlinear autoregressive neural network prediction and we also, used neural network clustering to determine average GSM signal strength receive at the study area. The nonlinear auto-regressive neural network predicted that the GSM signal is attenuated with the mean square error (MSE) of 2.6748dB, this attenuation value is used to modify the COST 231 Hata and the Okumura-Hata models. The neural network clustering revealed that -75dB to -95dB is received more frequently. This means that the signal strength received at the study is mostly weak signal

Keywords: one-dimensional multilevel wavelets, path loss, GSM signal strength, propagation, urban environment and model

Procedia PDF Downloads 357

Authors: Abhisek Dash

Abstract:

This study had three neural networks, one for number segmentation, one for number detection and one for number recognition all of which are coupled to one another. All networks were trained on the MNIST dataset and were convolutional. It was assumed that the images had lighter background and darker foreground. The segmentation network took 28x28 images as input and had sixteen outputs. Segmentation training starts when a dark pixel is encountered. Taking a window(7x7) over that pixel as focus, the eight neighborhood of the focus was checked for further dark pixels. The segmentation network was then trained to move in those directions which had dark pixels. To this end the segmentation network had 16 outputs. They were arranged as “go east”, ”don’t go east ”, “go south east”, “don’t go south east”, “go south”, “don’t go south” and so on w.r.t focus window. The focus window was resized into a 28x28 image and the network was trained to consider those neighborhoods which had dark pixels. The neighborhoods which had dark pixels were pushed into a queue in a particular order. The neighborhoods were then popped one at a time stitched to the existing partial image of the number one at a time and trained on which neighborhoods to consider when the new partial image was presented. The above process was repeated until the image was fully covered by the 7x7 neighborhoods and there were no more uncovered black pixels. During testing the network scans and looks for the first dark pixel. From here on the network predicts which neighborhoods to consider and segments the image. After this step the group of neighborhoods are passed into the detection network. The detection network took 28x28 images as input and had two outputs denoting whether a number was detected or not. Since the ground truth of the bounds of a number was known during training the detection network outputted in favor of number not found until the bounds were not met and vice versa. The recognition network was a standard CNN that also took 28x28 images and had 10 outputs for recognition of numbers from 0 to 9. This network was activated only when the detection network votes in favor of number detected. The above methodology could segment connected and overlapping numbers. Additionally the recognition unit was only invoked when a number was detected which minimized false positives. It also eliminated the need for rules of thumb as segmentation is learned. The strategy can also be extended to other characters as well.

Keywords: convolutional neural networks, OCR, text detection, text segmentation

Procedia PDF Downloads 133

Authors: Aydin Teymourifar, Gurkan Ozturk

Abstract:

In this paper, a new hybrid Hopfield neural network is proposed for the dynamic, flexible job shop scheduling problem. A new heuristic based and easy to implement energy function is designed for the Hopfield neural network, which penalizes the constraints violation and decreases makespan. Moreover, for enhancing the performance, several heuristics are integrated to it that achieve active, and non-delay schedules also, prevent early convergence of the neural network. The suggested algorithm that is designed as a generalization of the previous studies for the flexible and dynamic scheduling problems can be used for solving real scheduling problems. Comparison of the presented hybrid method results with the previous studies results proves its efficiency.

Keywords: dynamic flexible job shop scheduling, neural network, heuristics, constrained optimization

Procedia PDF Downloads 395

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, convolutional neural network, capsule network, capacity optimization, character recognition, data augmentation, semantic segmentation

Procedia PDF Downloads 125

Authors: Li Kewen, Su Zhaoxin, Wang Xingmou, Zhu Jian Bing

Abstract:

Conventional reservoir prediction methods ar not sufficient to explore the implicit relation between seismic attributes, and thus data utilization is low. In order to improve the predictive classification accuracy of reservoir lithology, this paper proposes a deep learning lithology prediction method based on ResNet (Residual Neural Network) and SENet (Squeeze-and-Excitation Neural Network). The neural network model is built and trained by using seismic attribute data and lithology data of Shengli oilfield, and the nonlinear mapping relationship between seismic attribute and lithology marker is established. The experimental results show that this method can significantly improve the classification effect of reservoir lithology, and the classification accuracy is close to 70%. This study can effectively predict the lithology of undrilled area and provide support for exploration and development.

Keywords: convolutional neural network, lithology, prediction of reservoir, seismic attributes

Procedia PDF Downloads 150

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: artificial intelligence, machine learning, deep learning, convolutional neural networks

Procedia PDF Downloads 178

Authors: Ahmed Kayad Abdourazak, Abderafi Souad, Zejli Driss, Idriss Abdoulkader Ibrahim

Abstract:

In this paper Artificial Neural Network (ANN) is used to predict the solar irradiation in Djibouti for the first Time that is useful to the integration of Concentrating Solar Power (CSP) and sites selections for new or future solar plants as part of solar energy development. An ANN algorithm was developed to establish a forward/reverse correspondence between the latitude, longitude, altitude and monthly solar irradiation. For this purpose the German Aerospace Centre (DLR) data of eight Djibouti sites were used as training and testing in a standard three layers network with the back propagation algorithm of Lavenber-Marquardt. Results have shown a very good agreement for the solar irradiation prediction in Djibouti and proves that the proposed approach can be well used as an efficient tool for prediction of solar irradiation by providing so helpful information concerning sites selection, design and planning of solar plants.

Keywords: artificial neural network, solar irradiation, concentrated solar power, Lavenberg-Marquardt

Procedia PDF Downloads 335