Search results for: convolution neural network- long short term memory network (CNN-LSTM)

Authors: Joseph Uzuazomaro Oju

Abstract:

The ease at which manipulated media can be created, and the increasing difficulty in identifying fake media makes it a great threat. Most of the applications used for the creation of these high-quality fake videos and images are built with deep learning. Hence, the use of deep learning in creating a detection mechanism cannot be overemphasized. Any successful fake media that is being detected before it reached the populace will save people from the self-doubt of either a content is genuine or fake and will ensure the credibility of videos and images. The methodology introduced in this paper approaches the manipulated media detection challenge using a combo of VGG-19 and a deep capsule network. In the case of videos, they are converted into frames, which, in turn, are resized and cropped to the face region. These preprocessed images/videos are fed to the VGG-19 network to extract the latent features. The extracted latent features are inputted into a deep capsule network enhanced with a 3D -convolution dynamic routing agreement. The 3D –convolution dynamic routing agreement algorithm helps to reduce the linkages between capsules networks. Thereby limiting the poor learning shortcoming of multiple capsule network layers. The resultant output from the deep capsule network will indicate a media to be either genuine or fake.

Keywords: deep capsule network, dynamic routing, fake media detection, manipulated media

Procedia PDF Downloads 99

Authors: Bowei Yuan, Shi Li, Liuyang Song, Huaqing Wang, Lingli Cui

Abstract:

Convolutional neural networks (CNN) have received extensive attention in the field of fault diagnosis. Many fault diagnosis methods use CNN for fault type identification. However, when the amount of raw data collected by sensors is massive, the neural network needs to perform a time-consuming classification task. In this paper, a mechanical fault diagnosis method based on vibration signal down-sampling and the improved one-dimensional convolutional neural network is proposed. Through the robust principal component analysis, the low-rank feature matrix of a large amount of raw data can be separated, and then down-sampling is realized to reduce the subsequent calculation amount. In the improved one-dimensional CNN, a smaller convolution kernel is used to reduce the number of parameters and computational complexity, and regularization is introduced before the fully connected layer to prevent overfitting. In addition, the multi-connected layers can better generalize classification results without cumbersome parameter adjustments. The effectiveness of the method is verified by monitoring the signal of the centrifugal pump test bench, and the average test accuracy is above 98%. When compared with the traditional deep belief network (DBN) and support vector machine (SVM) methods, this method has better performance.

Keywords: fault diagnosis, vibration signal down-sampling, 1D-CNN

Procedia PDF Downloads 102

Authors: Shibo Wei, Ting Jiang

Abstract:

Convolutional-recurrent neural networks (CRN) have achieved much success recently in the speech enhancement field. The common processing method is to use the convolution layer to compress the feature space by multiple upsampling and then model the compressed features with the LSTM layer. At last, the enhanced speech is obtained by deconvolution operation to integrate the global information of the speech sequence. However, the feature space compression process may cause the loss of information, so we propose to model the upsampling result of each step with the residual LSTM layer, then join it with the output of the deconvolution layer and input them to the next deconvolution layer, by this way, we want to integrate the global information of speech sequence better. The experimental results show the network model (RES-CRN) we introduce can achieve better performance than LSTM without residual and overlaying LSTM simply in the original CRN in terms of scale-invariant signal-to-distortion ratio (SI-SNR), speech quality (PESQ), and intelligibility (STOI).

Keywords: convolutional-recurrent neural networks, speech enhancement, residual LSTM, SI-SNR

Procedia PDF Downloads 169

Authors: Faezeh Aghazadeh, Mohammad Javad Sharifi

Abstract:

The application of neural networks to model a full-scale industrial acetylene hydrogenation in olefin plant has been studied. The operating variables studied are the, input-temperature of the reactor, output-temperature of the reactor, hydrogen ratio of the reactor, [C₂H₂]input, and [C₂H₆]input. The studied operating variables were used as the input to the constructed neural network to predict the [C₂H₆]output at any time as the output or the target. The constructed neural network was found to be highly precise in predicting the quantity of [C₂H₆]output for the new input data, which are kept unaware of the trained neural network showing its applicability to determine the [C₂H₆]output for any operating conditions. The enhancement of [C₂H₆]output as compared with [C₂H₆]input was a consequence of low selective acetylene hydrogenation to ethylene.

Keywords: acetylene hydrogenation, Pd-Ag/Al₂O₃, artificial neural network, modeling, optimal design

Procedia PDF Downloads 236

Authors: Majid Arvan, Peyman Beygi, Sina Rokhsati

Abstract:

In-time detection of fire in buildings is of great importance. Employing intelligent methods in data processing in fire detection systems leads to a significant reduction of fire damage at lowest cost. In this paper, the raw data obtained from the fire detection sensor networks in buildings is processed by using intelligent methods based on neural networks and the likelihood of fire happening is predicted. In order to enhance the quality of system, the noise in the sensor data is reduced by analyzing wavelets and applying SVD technique. Meanwhile, the proposed neural network is trained using particle swarm optimization (PSO). In the simulation work, the data is collected from sensor network inside the room and applied to the proposed network. Then the outputs are compared with conventional MLP network. The simulation results represent the superiority of the proposed method over the conventional one.

Keywords: intelligent fire detection, neural network, particle swarm optimization, fire sensor network

Procedia PDF Downloads 351

Authors: Kostas Kouvaris, Anastasia Eleftheriou, Georgios A. Sarantitis, Apostolos Chondronasios

Abstract:

To achieve the objective of almost zero carbon energy solutions by 2050, the EU needs to accelerate the development of integrated, highly efficient and environmentally friendly solutions. In this direction, district heating and cooling (DHC) emerges as a viable and more efficient alternative to conventional, decentralized heating and cooling systems, enabling a combination of more efficient renewable and competitive energy supplies. In this paper, we develop a forecasting tool for near real-time local weather and thermal energy demand predictions for an entire DHC network. In this fashion, we are able to extend the functionality and to improve the energy efficiency of the DHC network by predicting and adjusting the heat load that is distributed from the heat generation plant to the connected buildings by the heat pipe network. Two case-studies are considered; one for Vransko, Slovenia and one for Montpellier, France. The data consists of i) local weather data, such as humidity, temperature, and precipitation, ii) weather forecast data, such as the outdoor temperature and iii) DHC operational parameters, such as the mass flow rate, supply and return temperature. The external temperature is found to be the most important energy-related variable for space conditioning, and thus it is used as an external parameter for the energy demand models. For the development of the forecasting tool, we use state-of-the-art deep neural networks and more specifically, recurrent networks with long-short-term memory cells, which are able to capture complex non-linear relations among temporal variables. Firstly, we develop models to forecast outdoor temperatures for the next 24 hours using local weather data for each case-study. Subsequently, we develop models to forecast thermal demand for the same period, taking under consideration past energy demand values as well as the predicted temperature values from the weather forecasting models. The contributions to the scientific and industrial community are three-fold, and the empirical results are highly encouraging. First, we are able to predict future thermal demand levels for the two locations under consideration with minimal errors. Second, we examine the impact of the outdoor temperature on the predictive ability of the models and how the accuracy of the energy demand forecasts decreases with the forecast horizon. Third, we extend the relevant literature with a new dataset of thermal demand and examine the performance and applicability of machine learning techniques to solve real-world problems. Overall, the solution proposed in this paper is in accordance with EU targets, providing an automated smart energy management system, decreasing human errors and reducing excessive energy production.

Keywords: machine learning, LSTMs, district heating and cooling system, thermal demand

Procedia PDF Downloads 112

Authors: Han Bing, Yin Zhenjie

Abstract:

In order to analyze the status of a diesel engine, as well as conduct fault prediction, a new prediction model based on a gray system is proposed in this paper, which takes advantage of the neural network and the genetic algorithm. The proposed GBPGA prediction model builds on the GM (1.5) model and uses a neural network, which is optimized by a genetic algorithm to construct the error compensator. We verify our proposed model on the diesel faulty simulation data and the experimental results show that GBPGA has the potential to employ fault prediction on diesel.

Keywords: fault prediction, neural network, GM(1, 5) genetic algorithm, GBPGA

Procedia PDF Downloads 272

Authors: Adel Khorramrouz, Monireh Ahmadi Bani, Ehsan Norouzi, Morvarid Lalenoor

Abstract:

Background: Plantar pressure distribution measurement has been used for a long time to assess foot disorders. Plantar pressure is an important component affecting the foot and ankle function and Changes in plantar pressure distribution could indicate various foot and ankle disorders. Morphologic and mechanical properties of the foot may be important factors affecting the plantar pressure distribution. Accurate and early measurement may help to reduce the prevalence of pes planus. With recent developments in technology, new techniques such as machine learning have been used to assist clinicians in predicting patients with foot disorders. Significance of the study: This study proposes a neural network learning-based flat foot classification methodology using static foot pressure distribution. Methodologies: Data were collected from 895 patients who were referred to a foot clinic due to foot disorders. Patients with pes planus were labeled by an experienced physician based on clinical examination. Then all subjects (with and without pes planus) were evaluated for static plantar pressures distribution. Patients who were diagnosed with the flat foot in both feet were included in the study. In the next step, the leg length was normalized and the network was trained for plantar pressure mapping images. Findings: From a total of 895 image data, 581 were labeled as pes planus. A computational neural network (CNN) ran to evaluate the performance of the proposed model. The prediction accuracy of the basic CNN-based model was performed and the prediction model was derived through the proposed methodology. In the basic CNN model, the training accuracy was 79.14%, and the test accuracy was 72.09%. Conclusion: This model can be easily and simply used by patients with pes planus and doctors to predict the classification of pes planus and prescreen for possible musculoskeletal disorders related to this condition. However, more models need to be considered and compared for higher accuracy.

Keywords: foot disorder, machine learning, neural network, pes planus

Procedia PDF Downloads 326

Authors: Osama Elsarrar, Marjorie Darrah, Richard Devin

Abstract:

This paper discusses the idea of capturing an expert’s knowledge in the form of human understandable rules and then inserting these rules into a dynamic cell structure (DCS) neural network. The DCS is a form of self-organizing map that can be used for many purposes, including classification and prediction. This particular neural network is considered to be a topology preserving network that starts with no pre-structure, but assumes a structure once trained. The DCS has been used in mission and safety-critical applications, including adaptive flight control and health-monitoring in aerial vehicles. The approach is to insert expert knowledge into the DCS before training. Rules are translated into a pre-structure and then training data are presented. This idea has been demonstrated using the well-known Iris data set and it has been shown that inserting the pre-structure results in better accuracy with the same training.

Keywords: neural network, self-organizing map, rule extraction, rule insertion

Procedia PDF Downloads 140

Authors: Rosdyana Mangir Irawan Kusuma, Wei-Chun Kao, Ho-Thi Trang, Yu-Yen Ou, Kai-Lung Hua

Abstract:

Stock market prediction is still a challenging problem because there are many factors that affect the stock market price such as company news and performance, industry performance, investor sentiment, social media sentiment, and economic factors. This work explores the predictability in the stock market using deep convolutional network and candlestick charts. The outcome is utilized to design a decision support framework that can be used by traders to provide suggested indications of future stock price direction. We perform this work using various types of neural networks like convolutional neural network, residual network and visual geometry group network. From stock market historical data, we converted it to candlestick charts. Finally, these candlestick charts will be feed as input for training a convolutional neural network model. This convolutional neural network model will help us to analyze the patterns inside the candlestick chart and predict the future movements of the stock market. The effectiveness of our method is evaluated in stock market prediction with promising results; 92.2% and 92.1 % accuracy for Taiwan and Indonesian stock market dataset respectively.

Keywords: candlestick chart, deep learning, neural network, stock market prediction

Procedia PDF Downloads 402

Authors: Oluwaponmile David Alao

Abstract:

Misdiagnosis has been the major problem in health sector. Heart attack has been one of diseases that have high level of misdiagnosis recorded on the part of physicians. In this paper, an intelligent system has been developed for diagnosis of heart attack in the health sector. Dataset of heart attack obtained from UCI repository has been used. This dataset is made up of thirteen attributes which are very vital in diagnosis of heart disease. The system is developed on the multilayer perceptron trained with back propagation neural network then simulated with feed forward neural network and a recognition rate of 87% was obtained which is a good result for diagnosis of heart attack in medical field.

Keywords: heart attack, artificial neural network, diagnosis, intelligent system

Procedia PDF Downloads 620

Authors: Aisulu Tileukulova, Zhexebay Dauren

Abstract:

Radar plays an important role because it is widely used in civil and military fields. Target detection is one of the most important radar applications. The accuracy of detecting inconspicuous aerial objects in radar facilities is lower against the background of noise. Convolutional neural networks can be used to improve the recognition of this type of aerial object. The purpose of this work is to develop an algorithm for recognizing aerial objects using convolutional neural networks, as well as training a neural network. In this paper, the structure of a convolutional neural network (CNN) consists of different types of layers: 8 convolutional layers and 3 layers of a fully connected perceptron. ReLU is used as an activation function in convolutional layers, while the last layer uses softmax. It is necessary to form a data set for training a neural network in order to detect a target. We built a Confusion Matrix of the CNN model to measure the effectiveness of our model. The results showed that the accuracy when testing the model was 95.7%. Classification of echo signals using CNN shows high accuracy and significantly speeds up the process of predicting the target.

Keywords: radar, neural network, convolutional neural network, echo signals

Procedia PDF Downloads 314

Authors: Shelby Simpson, William Stanley, Namir Naba, Xiaodi Wang

Abstract:

Both t-SNE and UMAP are brand new state of art tools to predominantly preserve the local structure that is to group neighboring data points together, which indeed provides a very informative visualization of heterogeneity in our data. In this research, we develop a t-SNE and UMAP base neural network image classification algorithm to embed the original dataset to a corresponding low dimensional dataset as a preprocessing step, then use this embedded database as input to our specially designed neural network classifier for image classification. We use the fashion MNIST data set, which is a labeled data set of images of clothing objects in our experiments. t-SNE and UMAP are used for dimensionality reduction of the data set and thus produce low dimensional embeddings. Furthermore, we use the embeddings from t-SNE and UMAP to feed into two neural networks. The accuracy of the models from the two neural networks is then compared to a dense neural network that does not use embedding as an input to show which model can classify the images of clothing objects more accurately.

Keywords: t-SNE, UMAP, fashion MNIST, neural networks

Procedia PDF Downloads 164

Authors: Mohammed Affanuddin H. Siddique, Jayesh S. Shukla, Chetan B. Meshram

Abstract:

The neural networks are one of the power tools of machine learning. After the invention of perceptron in early 1980's, the neural networks and its application have grown rapidly. Neural networks are a technique originally developed for pattern investigation. The structure of a neural network consists of neurons connected through synapse. Here, we have investigated the different algorithms and cost function reduction techniques for optimization of vertical axis wind turbine (VAWT) rotor blades. The aerodynamic force coefficients corresponding to the airfoils are stored in a database along with the airfoil coordinates. A forward propagation neural network is created with the input as aerodynamic coefficients and output as the airfoil co-ordinates. In the proposed algorithm, the hidden layer is incorporated into cost function having linear and non-linear error terms. In this article, it is observed that the ANNs (Artificial Neural Network) can be used for the VAWT’s optimization.

Keywords: VAWT, ANN, optimization, inverse design

Procedia PDF Downloads 284

Authors: Xiaohan Bookman, Xiaoyan Zhu

Abstract:

The outputs of non-linear feed-forward neural network are positive, which could be treated as probability when they are normalized to one. If we take Entropy-Based Principle into consideration, the outputs for each sample could be represented as the distribution of this sample for different clusters. Entropy-Based Principle is the principle with which we could estimate the unknown distribution under some limited conditions. As this paper defines two processes in Feed-Forward Neural Network, our limited condition is the abstracted features of samples which are worked out in the abstraction process. And the final outputs are the probability distribution for different clusters in the clustering process. As Entropy-Based Principle is considered into the feed-forward neural network, a clustering method is born. We have conducted some experiments on six open UCI data sets, comparing with a few baselines and applied purity as the measurement. The results illustrate that our method outperforms all the other baselines that are most popular clustering methods.

Keywords: feed-forward neural network, clustering, max-entropy principle, probabilistic models

Procedia PDF Downloads 407

Authors: Amartya Hatua, Trung Nguyen, Andrew Sung

Abstract:

In this paper, we study the information diffusion process on Twitter as a multivariate time series problem. Our model concerns three measures (volume, network influence, and sentiment of tweets) based on 10 features, and we collected 27 million tweets to build our information diffusion time series dataset for analysis. Then, different time series clustering techniques with Dynamic Time Warping (DTW) distance were used to identify different patterns of information diffusion. Finally, we built the information diffusion prediction models for new hashtags which comprise two phrases: The first phrase is recognizing the pattern using k-NN with DTW distance; the second phrase is building the forecasting model using the traditional Autoregressive Integrated Moving Average (ARIMA) model and the non-linear recurrent neural network of Long Short-Term Memory (LSTM). Preliminary results of performance evaluation between different forecasting models show that LSTM with clustering information notably outperforms other models. Therefore, our approach can be applied in real-world applications to analyze and predict the information diffusion characteristics of selected topics or memes (hashtags) in Twitter.

Keywords: ARIMA, DTW, information diffusion, LSTM, RNN, time series clustering, time series forecasting, Twitter

Procedia PDF Downloads 361

Authors: Sumit Sen, Sohan Khedekar, Umang Shinde, Shivam Bhargava

Abstract:

This study has been undertaken to investigate whether the deep learning models are able to predict the future stock prices by training the model with the historical stock price data. Since this work required time series analysis, various models are present today to perform time series analysis such as Recurrent Neural Network LSTM, ARIMA and Facebook Prophet. Applying these models the movement of stock price of stocks are predicted and also tried to provide the future prediction of the stock price of a stock. Final product will be a stock price prediction web application that is developed for providing the user the ease of analysis of the stocks and will also provide the predicted stock price for the next seven days.

Keywords: Autoregressive Integrated Moving Average, Deep Learning, Long Short Term Memory, Time-series

Procedia PDF Downloads 111

Authors: Oluwaponmile David Alao

Abstract:

Due to an increase in the death rate as a result of heart attack. There is need to develop a system that can be useful in the diagnosis of the disease at the medical centre. This system will help in preventing misdiagnosis that may occur from the medical practitioner or the physicians. In this research work, heart disease dataset obtained from UCI repository has been used to develop an intelligent prediction diagnosis system. The system is modeled on a feedforwad neural network and trained with back propagation neural network. A recognition rate of 86% is obtained from the testing of the network.

Keywords: heart disease, artificial neural network, diagnosis, prediction system

Procedia PDF Downloads 421

Authors: Rehab Abdulmajed, Amr Hamada, Ahmed Elsaid, Hisashi Hayakawa, Ayman Mahrous

Abstract:

Solar emissions have a high impact on the Earth’s magnetic field, and the prediction of solar events is of high interest. Various techniques have been used in the prediction of solar wind using mathematical models, MHD models, and neural network (NN) models. This study investigates the coronal hole (CH) derived high-speed streams (HSSs) and their correlation to the CH area and create a neural network model to predict the HSSs. Two different algorithms were used to compare different models to find a model that best simulates the HSSs. A dataset of CH synoptic maps through Carrington rotations 1601 to 2185 along with Omni-data set solar wind speed averaged over the Carrington rotations is used, which covers Solar cycles (sc) 21, 22, 23, and most of 24.

Keywords: artificial neural network, coronal hole area, feed-forward neural network models, solar high speed streams

Procedia PDF Downloads 56

Authors: Kevin D. Manalo, Jumelyn L. Torres, Noel B. Linsangan

Abstract:

This paper focuses on a wireless myoelectric prosthesis of the upper-limb that uses a Multilayer Perceptron Neural network with back propagation. The algorithm is widely used in pattern recognition. The network can be used to train signals and be able to use it in performing a function on their own based on sample inputs. The paper makes use of the Neural Network in classifying the electromyography signal that is produced by the muscle in the amputee’s skin surface. The gathered data will be passed on through the Classification Stage wirelessly through Zigbee Technology. The signal will be classified and trained to be used in performing the arm positions in the prosthesis. Through programming using Verilog and using a Field Programmable Gate Array (FPGA) with Zigbee, the EMG signals will be acquired and will be used for classification. The classified signal is used to produce the corresponding Hand Movements (Open, Pick, Hold, and Grip) through the Zigbee controller. The data will then be processed through the MLP Neural Network using MATLAB which then be used for the surface myoelectric prosthesis. Z-test will be used to display the output acquired from using the neural network.

Keywords: field programmable gate array, multilayer perceptron neural network, verilog, zigbee

Procedia PDF Downloads 361

Authors: Reza Dinarvand, Mahdi Sadeghian, Somaye Sadeghian

Abstract:

Prediction of the ultimate bearing capacity of piles (Qu) is one of the basic issues in geotechnical engineering. So far, several methods have been used to estimate Qu, including the recently developed artificial intelligence methods. In recent years, optimization algorithms have been used to minimize artificial network errors, such as colony algorithms, genetic algorithms, imperialist competitive algorithms, and so on. In the present research, artificial neural networks based on colonial competition algorithm (ANN-ICA) were used, and their results were compared with other methods. The results of laboratory tests of short piles in clayey soils with parameters such as pile diameter, pile buried length, eccentricity of load and undrained shear resistance of soil were used for modeling and evaluation. The results showed that ICA-based artificial neural networks predicted lateral bearing capacity of short piles with a correlation coefficient of 0.9865 for training data and 0.975 for test data. Furthermore, the results of the model indicated the superiority of ICA-based artificial neural networks compared to back-propagation artificial neural networks as well as the Broms and Hansen methods.

Keywords: artificial neural network, clayey soil, imperialist competition algorithm, lateral bearing capacity, short pile

Procedia PDF Downloads 116

Authors: Christina Adly, Meena Abdelmeseeh, Tamer Basha

Abstract:

This paper proposes a system for hand movement recognition using multichannel surface EMG(sEMG) signals obtained from 40 subjects using 40 different exercises, which are available on the Ninapro(Non-Invasive Adaptive Prosthetics) database. First, we applied processing methods to the raw sEMG signals to convert them to their amplitudes. Second, we used deep learning methods to solve our problem by passing the preprocessed signals to Fully connected neural networks(FCNN) and recurrent neural networks(RNN) with Long Short Term Memory(LSTM). Using intrasubject evaluation, The accuracy using the FCNN is 72%, with a processing time for training around 76 minutes, and for RNN's accuracy is 79.9%, with 8 minutes and 22 seconds processing time. Third, we applied some postprocessing methods to improve the accuracy, like majority voting(MV) and Movement Error Rate(MER). The accuracy after applying MV is 75% and 86% for FCNN and RNN, respectively. The MER value has an inverse relationship with the prediction delay while varying the window length for measuring the MV. The different part uses the RNN with the intersubject evaluation. The experimental results showed that to get a good accuracy for testing with reasonable processing time, we should use around 20 subjects.

Keywords: hand movement recognition, recurrent neural network, movement error rate, intrasubject evaluation, intersubject evaluation

Procedia PDF Downloads 105

Authors: Hussam Elias, Ninovic Perez, Holger Hirsch

Abstract:

The completion of the EMC regulations worldwide is growing steadily as the usage of electronics in our daily lives is increasing more than ever. In this paper, we introduce a novel method to perform the final phase of Electromagnetic compatibility (EMC) measurement and to reduce the required test time according to the norm EN 55032 by using a developed tool and the conventional neural network(CNN). The neural network was trained using real EMC measurements, which were performed in the Semi Anechoic Chamber (SAC) by CETECOM GmbH in Essen, Germany. To implement our proposed method, we wrote software to perform the radiated electromagnetic interference (EMI) measurements and use the CNN to predict and determine the position of the turntable that meets the maximum radiation value.

Keywords: conventional neural network, electromagnetic compatibility measurement, mean absolute error, position error

Procedia PDF Downloads 169

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 260

Authors: Thomas E. Portegys

Abstract:

An animal behavior problem is presented in the form of a nest-building task that involves two cooperating virtual birds, a male and female. The female builds a nest into which she lays an egg. The male's job is to forage in a forest for food for both himself and the female. In addition, the male must fetch stones from a nearby desert for the female to use as nesting material. The task is completed when the nest is built, and an egg is laid in it. A goal-seeking neural network and a recurrent neural network were trained and tested with little success. The goal-seeking network was then enhanced with “place cells”, allowing the birds to spatially navigate the world, building the nest while keeping themselves fed. Place cells are neurons in the hippocampus that map space.

Keywords: artificial animal intelligence, artificial life, goal-seeking neural network, nest-building, place cells, spatial navigation

Procedia PDF Downloads 27

Authors: Muhammad Azam, Micheal Olaolu Arowolo, Fei He, Mihail Popescu, Dong Xu

Abstract:

The number of biological papers is growing quickly, which means that the number of biological pathway figures in those papers is also increasing quickly. Each pathway figure shows extensive biological information, like the names of genes and how the genes are related. However, manually annotating pathway figures takes a lot of time and work. Even though using advanced image understanding models could speed up the process of curation, these models still need to be made more accurate. To improve gene name recognition from pathway figures, we applied a Siamese network to map image segments to a library of pictures containing known genes in a similar way to person recognition from photos in many photo applications. We used a triple loss function and a triplet spatial pyramid pooling network by combining the triplet convolution neural network and the spatial pyramid pooling (TSPP-Net). We compared VGG19 and VGG16 as the Siamese network model. VGG16 achieved better performance with an accuracy of 93%, which is much higher than OCR results.

Keywords: biological pathway, image understanding, gene name recognition, object detection, Siamese network, VGG

Procedia PDF Downloads 243

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 456

Authors: R. Marhenke, M. Martini

Abstract:

The distraction of attentional resources after learning hinders long-term memory consolidation compared to several minutes of post-encoding inactivity in form of wakeful resting. We tested whether an 8-minute period of wakeful resting, compared to performing an adapted version of the d2 test of attention after learning, supports memory retention. Participants encoded and immediately recalled a word list followed by either an 8 minute period of wakeful resting (eyes closed, relaxed) or by performing an adapted version of the d2 test of attention (scanning and selecting specific characters while ignoring others). At the end of the experimental session (after 12-24 min) and again after 7 days, participants were required to complete a surprise free recall test of both word lists. Our results showed no significant difference in memory retention between the experimental conditions. However, we found that participants who completed the first lines of the d2 test in less than the given time limit of 20 seconds and thus had short unfilled intervals before switching to the next test line, remembered more words over the 12-24 minute and over the 7 days retention interval than participants who did not complete the first lines. This interaction occurred only for the first test lines, with the highest temporal proximity to the encoding task and not for later test lines. Differences in retention scores between groups (completed first line vs. did not complete) seem to be widely independent of the general performance in the d2 test. Implications and limitations of these exploratory findings are discussed.

Keywords: long-term memory, retroactive interference, attention, forgetting

Procedia PDF Downloads 104

Authors: Chico Horacio Jose Sambo

Abstract:

Recently neural network has gained popularity when come to solve complex nonlinear problems. Permeability is one of fundamental reservoir characteristics system that are anisotropic distributed and non-linear manner. For this reason, permeability prediction from well log data is well suited by using neural networks and other computer-based techniques. The main goal of this paper is to predict reservoir permeability from well logs data by using neural network approach. A multi-layered perceptron trained by back propagation algorithm was used to build the predictive model. The performance of the model on net results was measured by correlation coefficient. The correlation coefficient from testing, training, validation and all data sets was evaluated. The results show that neural network was capable of reproducing permeability with accuracy in all cases, so that the calculated correlation coefficients for training, testing and validation permeability were 0.96273, 0.89991 and 0.87858, respectively. The generalization of the results to other field can be made after examining new data, and a regional study might be possible to study reservoir properties with cheap and very fast constructed models.

Keywords: neural network, permeability, multilayer perceptron, well log

Procedia PDF Downloads 365

Authors: Mathew Wakefield, Matthew Mitchell, Lisa Wise, Christopher McCarthy

Abstract:

The properties of memory representations in artificial neural networks have cognitive implications. Distributed representations that encode instances as a pattern of activity across layers of nodes afford memory compression and enforce the selection of a single point in instance space. These encoding schemes also appear to distort the representational space, as well as trading off the ability to validate that input information is within the bounds of past experience. In contrast, a localist representation which encodes some meaningful information into individual nodes in a network layer affords less memory compression while retaining the integrity of the representational space. This allows the validity of an input to be determined. The validity (or familiarity) of input along with the capacity of localist representation for multiple instance selections affords a memory sampling approach that dynamically balances the bias-variance trade-off. When the input is familiar, bias may be high by referring only to the most similar instances in memory. When the input is less familiar, variance can be increased by referring to more instances that capture a broader range of features. Using this approach in a localist instance memory network, an experiment demonstrates a relationship between representational conflict, generalization performance, and memorization demand. Relatively small sampling ranges produce the best performance on a classic machine learning dataset of visual objects. Combining memory validity with conflict detection produces a reliable confidence judgement that can separate responses with high and low error rates. Confidence can also be used to signal the need for supervisory input. Using this judgement, the need for supervised learning as well as memory encoding can be substantially reduced with only a trivial detriment to classification performance.

Keywords: artificial neural networks, representation, memory, conflict monitoring, confidence

Procedia PDF Downloads 99