Search results for: BP neural network model

Authors: A. Shoiynbek, K. Kozhakhmet, P. Menezes, D. Kuanyshbay, D. Bayazitov

Abstract:

Speech emotion recognition has received increasing research interest all through current years. There was used emotional speech that was collected under controlled conditions in most research work. Actors imitating and artificially producing emotions in front of a microphone noted those records. There are four issues related to that approach, namely, (1) emotions are not natural, and it means that machines are learning to recognize fake emotions. (2) Emotions are very limited by quantity and poor in their variety of speaking. (3) There is language dependency on SER. (4) Consequently, each time when researchers want to start work with SER, they need to find a good emotional database on their language. In this paper, we propose the approach to create an automatic tool for speech emotion extraction based on facial emotion recognition and describe the sequence of actions of the proposed approach. One of the first objectives of the sequence of actions is a speech detection issue. The paper gives a detailed description of the speech detection model based on a fully connected deep neural network for Kazakh and Russian languages. Despite the high results in speech detection for Kazakh and Russian, the described process is suitable for any language. To illustrate the working capacity of the developed model, we have performed an analysis of speech detection and extraction from real tasks.

Keywords: deep neural networks, speech detection, speech emotion recognition, Mel-frequency cepstrum coefficients, collecting speech emotion corpus, collecting speech emotion dataset, Kazakh speech dataset

Procedia PDF Downloads 101

Authors: Gajaanuja Megalathan, Banuka Athuraliya

Abstract:

Crime is one of our society's most intimidating and threatening challenges. With the majority of the population residing in cities, many experts and data provided by local authorities suggest a rapid increase in the number of crimes committed in these cities in recent years. There has been an increasing graph in the crime rates. People living in Sri Lanka have the right to know the exact crime rates and the crime rates in the future of the place they are living in. Due to the current economic crisis, crime rates have spiked. There have been so many thefts and murders recorded within the last 6-10 months. Although there are many sources to find out, there is no solid way of searching and finding out the safety of the place. Due to all these reasons, there is a need for the public to feel safe when they are introduced to new places. Through this research, the author aims to develop a mobile application that will be a solution to this problem. It is mainly targeted at tourists, and people who recently relocated will gain advantage of this application. Moreover, the Arima Model combined with ANN is to be used to predict crime rates. From the past researchers' works, it is evidently clear that they haven’t used the Arima model combined with Artificial Neural Networks to forecast crimes.

Keywords: arima model, ANN, crime prediction, data analysis

Procedia PDF Downloads 131

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 211

Authors: Naci Büyükkaracığan

Abstract:

Artificial neural networks (ANN) is an electrical model based on the human brain nervous system and working principle. Artificial neural networks have been the subject of an active field of research that has matured greatly over the past 55 years. ANN now is used in many fields. But, it has been viewed that artificial neural networks give better results in particular optimization and control systems. There are requirements of optimization and control system in many of the area forming the subject of civil engineering applications. In this study, the first artificial intelligence systems are widely used in the solution of civil engineering systems were examined with the basic principles and technical aspects. Finally, the literature reviews for applications in the field of civil engineering were conducted and also artificial intelligence techniques were informed about the study and its results.

Keywords: artificial neural networks, civil engineering, Fuzzy logic, statistics

Procedia PDF Downloads 412

Authors: Neveen AlQasas, Daniel Johnson

Abstract:

Membranes for water treatment are an established technology that attracts great attention due to its simplicity and cost effectiveness. However, membranes in operation suffer from the adverse effect of membrane fouling. Bio-fouling is a phenomenon that occurs at the water-membrane interface, and is a dynamic process that is initiated by the adsorption of dissolved organic material, including biomacromolecules, on the membrane surface. After initiation, attachment of microorganisms occurs, followed by biofilm growth. The biofilm blocks the pores of the membrane and consequently results in reducing the water flux. Moreover, the presence of a fouling layer can have a substantial impact on the membrane separation properties. Understanding the mechanism of the initiation phase of biofouling is a key point in eliminating the biofouling on membrane surfaces. The adhesion and attachment of different fouling materials is affected by the surface properties of the membrane materials. Therefore, surface properties of different polymeric materials had been studied in terms of their surface energies and Hansen solubility parameters (HSP). The difference between the combined HSP parameters (HSP distance) allows prediction of the affinity of two materials to each other. The possibilities of measuring the HSP of different polymer films via surface measurements, such as contact angle has been thoroughly investigated. Knowing the HSP of a membrane material and the HSP of a specific foulant, facilitate the estimation of the HSP distance between the two, and therefore the strength of attachment to the surface. Contact angle measurements using fourteen different solvents on five different polymeric films were carried out using the sessile drop method. Solvents were ranked as good or bad solvents using different ranking method and ranking was used to calculate the HSP of each polymeric film. Results clearly indicate the absence of a direct relation between contact angle values of each film and the HSP distance between each polymer film and the solvents used. Therefore, estimating HSP via contact angle alone is not sufficient. However, it was found if the surface tensions and viscosities of the used solvents are taken in to the account in the analysis of the contact angle values, a prediction of the HSP from contact angle measurements is possible. This was carried out via training of a neural network model. The trained neural network model has three inputs, contact angle value, surface tension and viscosity of solvent used. The model is able to predict the HSP distance between the used solvent and the tested polymer (material). The HSP distance prediction is further used to estimate the total and individual HSP parameters of each tested material. The results showed an accuracy of about 90% for all the five studied films

Keywords: surface characterization, hansen solubility parameter estimation, contact angle measurements, artificial neural network model, surface measurements

Procedia PDF Downloads 94

Authors: Lin Cheng, Zijiang Yang

Abstract:

Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specification. In order doing so, we propose a deep neural network called GRCNN that recognizes graph structure from its image. GRCNN is trained end-to-end, which can predict edge and node information of the flow chart simultaneously. Experiments show that the accuracy rate to synthesize a program is 66.4%, and the accuracy rates to recognize edge and node are 94.1% and 67.9%, respectively. On average, it takes about 60 milliseconds to synthesize a program.

Keywords: program synthesis, flow chart, specification, graph recognition, CNN

Procedia PDF Downloads 119

Authors: Lee Jeong Min, Lee Mi Hee, Eo Yang Dam

Abstract:

Geospatial feature extraction is a very important issue in the remote sensing research. In the meantime, the image classification based on statistical techniques, but, in recent years, data mining and machine learning techniques for automated image processing technology is being applied to remote sensing it has focused on improved results generated possibility. In this study, artificial neural network and decision tree technique is applied to classify the high-resolution satellite images, as compared to the MLC processing result is a statistical technique and an analysis of the pros and cons between each of the techniques.

Keywords: remote sensing, artificial neural network, decision tree, maximum likelihood classification

Procedia PDF Downloads 347

Authors: Somayeh Komeylian

Abstract:

The direction of arrival (DoA) estimation is the crucial aspect of the radar technologies for detecting and dividing several signal sources. In this scenario, the antenna array output modeling involves numerous parameters including noise samples, signal waveform, signal directions, signal number, and signal to noise ratio (SNR), and thereby the methods of the DoA estimation rely heavily on the generalization characteristic for establishing a large number of the training data sets. Hence, we have analogously represented the two different optimization models of the DoA estimation; (1) the implementation of the decision directed acyclic graph (DDAG) for the multiclass least-squares support vector machine (LS-SVM), and (2) the optimization method of the deep neural network (DNN) radial basis function (RBF). We have rigorously verified that the LS-SVM DDAG algorithm is capable of accurately classifying DoAs for the three classes. However, the accuracy and robustness of the DoA estimation are still highly sensitive to technological imperfections of the antenna arrays such as non-ideal array design and manufacture, array implementation, mutual coupling effect, and background radiation and thereby the method may fail in representing high precision for the DoA estimation. Therefore, this work has a further contribution on developing the DNN-RBF model for the DoA estimation for overcoming the limitations of the non-parametric and data-driven methods in terms of array imperfection and generalization. The numerical results of implementing the DNN-RBF model have confirmed the better performance of the DoA estimation compared with the LS-SVM algorithm. Consequently, we have analogously evaluated the performance of utilizing the two aforementioned optimization methods for the DoA estimation using the concept of the mean squared error (MSE).

Keywords: DoA estimation, Adaptive antenna array, Deep Neural Network, LS-SVM optimization model, Radial basis function, and MSE

Procedia PDF Downloads 100

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 132

Authors: Jing Zhao, Dayong Liu, Shihao Wang, Xinghua Zhu, Delong Li

Abstract:

Uhumanned Underwater Vehicles generally operate in the deep sea, which has its own unique working conditions. Lithium-ion power batteries should have the necessary stability and endurance for use as an underwater vehicle’s power source. Therefore, it is essential to accurately forecast how long lithium-ion batteries will last in order to maintain the system’s reliability and safety. In order to model and forecast lithium battery Remaining Useful Life (RUL), this research suggests a model based on Complete Ensemble Empirical Mode Decomposition with Adaptive noise-Temporal Convolutional Net (CEEMDAN-TCN). In this study, two datasets, NASA and CALCE, which have a specific gap in capacity data fluctuation, are used to verify the model and examine the experimental results in order to demonstrate the generalizability of the concept. The experiments demonstrate the network structure’s strong universality and ability to achieve good fitting outcomes on the test set for various battery dataset types. The evaluation metrics reveal that the CEEMDAN-TCN prediction performance of TCN is 25% to 35% better than that of a single neural network, proving that feature expansion and modal decomposition can both enhance the model’s generalizability and be extremely useful in industrial settings.

Keywords: lithium-ion battery, remaining useful life, complete EEMD with adaptive noise, temporal convolutional net

Procedia PDF Downloads 152

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

The purpose of this work is to develop a method for classifying hand signals and using the output in a drone control algorithm. To achieve this, methods based on Convolutional Neural Networks (CNN) were applied. CNN's are a subset of deep learning, which allows grid-like inputs to be processed and passed through a neural network to be trained for classification. This type of neural network allows for classification via imaging, which is less intrusive than previous methods using biosensors, such as EMG sensors. Classification CNN's operate purely from the pixel values in an image; therefore they can be used without additional exteroceptive sensors. A development bench was constructed using a desktop computer connected to a high-definition webcam mounted on a scissor arm. This allowed the camera to be pointed downwards at the desk to provide a constant solid background for the dataset and a clear detection area for the user. A MATLAB script was created to automate dataset image capture at the development bench and save the images to the desktop. This allowed the user to create their own dataset of 12,000 images within three hours. These images were evenly distributed among seven classes. The defined classes include forward, backward, left, right, idle, and land. The drone has a popular flip function which was also included as an additional class. To simplify control, the corresponding hand signals chosen were the numerical hand signs for one through five for movements, a fist for land, and the universal “ok” sign for the flip command. Transfer learning with PyTorch (Python) was performed using a pre-trained 18-layer residual learning network (ResNet-18) to retrain the network for custom classification. An algorithm was created to interpret the classification and send encoded messages to a Ryze Tello drone over its 2.4 GHz Wi-Fi connection. The drone’s movements were performed in half-meter distance increments at a constant speed. When combined with the drone control algorithm, the classification performed as desired with negligible latency when compared to the delay in the drone’s movement commands.

Keywords: classification, computer vision, convolutional neural networks, drone control

Procedia PDF Downloads 210

Authors: Sandeep Mehmi, Harsh Verma, A. L. Sangal

Abstract:

Ever since the idea of using computing services as commodity that can be delivered like other utilities e.g. electric and telephone has been floated, the scientific fraternity has diverted their research towards a new area called utility computing. New paradigms like cluster computing and grid computing came into existence while edging closer to utility computing. With the advent of internet the demand of anytime, anywhere access of the resources that could be provisioned dynamically as a service, gave rise to the next generation computing paradigm known as cloud computing. Today, cloud computing has become one of the most aggressively growing computer paradigm, resulting in growing rate of applications in area of IT outsourcing. Besides catering the computational and storage demands, cloud computing has economically benefitted almost all the fields, education, research, entertainment, medical, banking, military operations, weather forecasting, business and finance to name a few. Smart grid is another discipline that direly needs to be benefitted from the cloud computing advantages. Smart grid system is a new technology that has revolutionized the power sector by automating the transmission and distribution system and integration of smart devices. Cloud based smart grid can fulfill the storage requirement of unstructured and uncorrelated data generated by smart sensors as well as computational needs for self-healing, load balancing and demand response features. But, security issues such as confidentiality, integrity, availability, accountability and privacy need to be resolved for the development of smart grid cloud. In recent years, a number of intrusion prevention techniques have been proposed in the cloud, but hackers/intruders still manage to bypass the security of the cloud. Therefore, precise intrusion detection systems need to be developed in order to secure the critical information infrastructure like smart grid cloud. Considering the success of artificial neural networks in building robust intrusion detection, this research proposes an artificial neural network based model for detecting attacks in smart grid cloud.

Keywords: artificial neural networks, cloud computing, intrusion detection systems, security issues, smart grid

Procedia PDF Downloads 318

Authors: Nurul Bin Ibrahim

Abstract:

Advancements in neural networks have offered valuable insights into Fluid Dynamics, notably in addressing turbulence-related challenges. In this research, we introduce multiple applications of models of neural networks, namely Feed-Forward and Recurrent Neural Networks, to explore the relationship between jet formations and stratified turbulence within stochastically excited Boussinesq systems. Using machine learning tools like TensorFlow and PyTorch, the study has created models that effectively mimic and show the underlying features of the complex patterns of jet formation and stratified turbulence. These models do more than just help us understand these patterns; they also offer a faster way to solve problems in stochastic systems, improving upon traditional numerical techniques to solve stochastic differential equations such as the Euler-Maruyama method. In addition, the research includes a thorough comparison with the Statistical State Dynamics (SSD) approach, which is a well-established method for studying chaotic systems. This comparison helps evaluate how well neural networks can help us understand the complex relationship between jet formations and stratified turbulence. The results of this study underscore the potential of neural networks in computational physics and fluid dynamics, opening up new possibilities for more efficient and accurate simulations in these fields.

Keywords: neural networks, machine learning, computational fluid dynamics, stochastic systems, simulation, stratified turbulence

Procedia PDF Downloads 70

Authors: Tayo P. Ogundunmade, Adedayo A. Adepoju

Abstract:

Terrorist attacks in liberal democracies bring about a few pessimistic results, for example, sabotaged public support in the governments they target, disturbing the peace of a protected environment underwritten by the state, and a limitation of individuals from adding to the advancement of the country, among others. Hence, seeking for techniques to understand the different factors involved in terrorism and how to deal with those factors in order to completely stop or reduce terrorist activities is the topmost priority of the government in every country. This research aim is to develop an efficient deep learning-based predictive model for the prediction of future terrorist activities in Nigeria, addressing low-quality prediction accuracy problems associated with the existing solution methods. The proposed predictive AI-based model as a counterterrorism tool will be useful by governments and law enforcement agencies to protect the lives of individuals in society and to improve the quality of life in general. A Heterogeneous Bayesian Neural Network (HETBNN) model was derived with Gaussian error normal distribution. Three primary transfer functions (HOTTFs), as well as two derived transfer functions (HETTFs) arising from the convolution of the HOTTFs, are namely; Symmetric Saturated Linear transfer function (SATLINS ), Hyperbolic Tangent transfer function (TANH), Hyperbolic Tangent sigmoid transfer function (TANSIG), Symmetric Saturated Linear and Hyperbolic Tangent transfer function (SATLINS-TANH) and Symmetric Saturated Linear and Hyperbolic Tangent Sigmoid transfer function (SATLINS-TANSIG). Data on the Terrorist activities in Nigeria gathered through questionnaires for the purpose of this study were used. Mean Square Error (MSE), Mean Absolute Error (MAE) and Test Error are the forecast prediction criteria. The results showed that the HETFs performed better in terms of prediction and factors associated with terrorist activities in Nigeria were determined. The proposed predictive deep learning-based model will be useful to governments and law enforcement agencies as an effective counterterrorism mechanism to understand the parameters of terrorism and to design strategies to deal with terrorism before an incident actually happens and potentially causes the loss of precious lives. The proposed predictive AI-based model will reduce the chances of terrorist activities and is particularly helpful for security agencies to predict future terrorist activities.

Keywords: activation functions, Bayesian neural network, mean square error, test error, terrorism

Procedia PDF Downloads 165

Authors: L. Parisi

Abstract:

In this research work, neural networks were applied to classify two types of hip joint implants based on the relative hip joint implant side speed and three components of each ground reaction force. The condition of walking gait at normal velocity was used and carried out with each of the two hip joint implants assessed. Ground reaction forces’ kinetic temporal changes were considered in the first approach followed but discarded in the second one. Ground reaction force components were obtained from eighteen patients under such gait condition, half of which had a hip implant type I-II, whilst the other half had the hip implant, defined as type III by Orthoload®. After pre-processing raw gait kinetic data and selecting the time frames needed for the analysis, the ground reaction force components were used to train a MLP neural network, which learnt to distinguish the two hip joint implants in the abovementioned condition. Further to training, unknown hip implant side and ground reaction force components were presented to the neural networks, which assigned those features into the right class with a reasonably high accuracy for the hip implant type I-II and the type III. The results suggest that neural networks could be successfully applied in the performance assessment of hip joint implants.

Keywords: kinemic gait data, neural networks, hip joint implant, hip arthroplasty, rehabilitation engineering

Procedia PDF Downloads 354

Authors: Sabri Arik

Abstract:

In this paper, we study the global asymptotic robust stability of delayed neural networks with norm-bounded uncertainties. By employing the Lyapunov stability theory and Homeomorphic mapping theorem, we derive some new types of sufficient conditions ensuring the existence, uniqueness and global asymptotic stability of the equilibrium point for the class of neural networks with discrete time delays under parameter uncertainties and with respect to continuous and slopebounded activation functions. An important aspect of our results is their low computational complexity as the reported results can be verified by checking some properties symmetric matrices associated with the uncertainty sets of network parameters. The obtained results are shown to be generalization of some of the previously published corresponding results. Some comparative numerical examples are also constructed to compare our results with some closely related existing literature results.

Keywords: neural networks, delayed systems, lyapunov functionals, stability analysis

Procedia PDF Downloads 527

Authors: Wullapa Wongsinlatam

Abstract:

Back propagation algorithm (BP) is a widely used technique in artificial neural network and has been used as a tool for solving the time series problems, such as decreasing training time, maximizing the ability to fall into local minima, and optimizing sensitivity of the initial weights and bias. This paper proposes an improvement of a BP technique which is called IM-COH algorithm (IM-COH). By combining IM-COH algorithm with cuckoo search algorithm (CS), the result is cuckoo search improved control output hidden layer algorithm (CS-IM-COH). This new algorithm has a better ability in optimizing sensitivity of the initial weights and bias than the original BP algorithm. In this research, the algorithm of CS-IM-COH is compared with the original BP, the IM-COH, and the original BP with CS (CS-BP). Furthermore, the selected benchmarks, four time series samples, are shown in this research for illustration. The research shows that the CS-IM-COH algorithm give the best forecasting results compared with the selected samples.

Keywords: artificial neural networks, back propagation algorithm, time series, local minima problem, metaheuristic optimization

Procedia PDF Downloads 152

Authors: Yao-Hong Tsai

Abstract:

Due to the sensor technology, video surveillance has become the main way for security control in every big city in the world. Surveillance is usually used by governments for intelligence gathering, the prevention of crime, the protection of a process, person, group or object, or the investigation of crime. Many surveillance systems based on computer vision technology have been developed in recent years. Moving target tracking is the most common task for Unmanned Aerial Vehicle (UAV) to find and track objects of interest in mobile aerial surveillance for civilian applications. The paper is focused on vision-based collision avoidance for UAVs by recurrent neural networks. First, images from cameras on UAV were fused based on deep convolutional neural network. Then, a recurrent neural network was constructed to obtain high-level image features for object tracking and extracting low-level image features for noise reducing. The system distributed the calculation of the whole system to local and cloud platform to efficiently perform object detection, tracking and collision avoidance based on multiple UAVs. The experiments on several challenging datasets showed that the proposed algorithm outperforms the state-of-the-art methods.

Keywords: unmanned aerial vehicle, object tracking, deep learning, collision avoidance

Procedia PDF Downloads 160

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

One of the most important challenges in the field of software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a largescale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of opensource functions that point to potential exploits. We developed an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. The source code is first converted into a minimal intermediate representation to remove the pointless components and shorten the dependency. Moreover, we keep the semantic and syntactic information using state-of-the-art word embedding algorithms such as glove and fastText. The embedded vectors are subsequently fed into deep learning networks such as LSTM, BilSTM, LSTM-Autoencoder, word2vec, BERT, and GPT-2 to classify the possible vulnerabilities. Furthermore, we proposed a neural network model which can overcome issues associated with traditional neural networks. Evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time have been used to measure the performance. We made a comparative analysis between results derived from features containing a minimal text representation and semantic and syntactic information. We found that all of the deep learning models provide comparatively higher accuracy when we use semantic and syntactic information as the features but require higher execution time as the word embedding the algorithm puts on a bit of complexity to the overall system.

Keywords: cyber security, vulnerability detection, neural networks, feature extraction

Procedia PDF Downloads 89

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 289

Authors: Mohamed Othmani, Yassine Khlifi

Abstract:

This paper presents a technique for compact three dimensional (3D) object model reconstruction using wavelet networks. It consists to transform an input surface vertices into signals,and uses wavelet network parameters for signal approximations. To prove this, we use a wavelet network architecture founded on several mother wavelet families. POLYnomials WindOwed with Gaussians (POLYWOG) wavelet families are used to maximize the probability to select the best wavelets which ensure the good generalization of the network. To achieve a better reconstruction, the network is trained several iterations to optimize the wavelet network parameters until the error criterion is small enough. Experimental results will shown that our proposed technique can effectively reconstruct an irregular 3D object models when using the optimized wavelet network parameters. We will prove that an accurateness reconstruction depends on the best choice of the mother wavelets.

Keywords: 3d object, optimization, parametrization, polywog wavelets, reconstruction, wavelet networks

Procedia PDF Downloads 284

Authors: Skiker Kaoutar, Mounir Maouene

Abstract:

Neuroimaging studies have shown that animal and tool concepts rely on distinct networks of brain areas. Animal concepts depend predominantly on temporal areas while tool concepts rely on fronto-temporo-parietal areas. However, the origin of this neurofunctional distinction for processing animal and tool concepts remains still unclear. Here, we address this question from a network perspective suggesting that the neural distinction between animals and tools might reflect the differences in their structural semantic networks. We build semantic networks for animal and tool concepts derived from McRae and colleagues’s behavioral study conducted on a large number of participants. These two networks are thus analyzed through a large number of graph theoretical measures for small-worldness: centrality, clustering coefficient, average shortest path length, as well as resistance to random and targeted attacks. The results indicate that both animal and tool networks have small-world properties. More importantly, the animal network is more vulnerable to targeted attacks compared to the tool network a result that correlates with brain lesions studies.

Keywords: animals, tools, network, semantics, small-worls, resilience to damage

Procedia PDF Downloads 543

Authors: Lei Zhu, Nan Li

Abstract:

Cold stamping has been widely applied in the automotive industry for the mass production of a great range of automotive panels. Predicting the springback to ensure the dimensional accuracy of the cold-stamped components is a critical step. The main approaches for the prediction and compensation of springback in cold stamping include running Finite Element (FE) simulations and conducting experiments, which require forming process expertise and can be time-consuming and expensive for the design of cold stamping tools. Machine learning technologies have been proven and successfully applied in learning complex system behaviours using presentative samples. These technologies exhibit the promising potential to be used as supporting design tools for metal forming technologies. This study, for the first time, presents a novel application of a Convolutional Neural Network (CNN) based surrogate model to predict the springback fields for variable U-shape cold bending geometries. A dataset is created based on the U-shape cold bending geometries and the corresponding FE simulations results. The dataset is then applied to train the CNN surrogate model. The result shows that the surrogate model can achieve near indistinguishable full-field predictions in real-time when compared with the FE simulation results. The application of CNN in efficient springback prediction can be adopted in industrial settings to aid both conceptual and final component designs for designers without having manufacturing knowledge.

Keywords: springback, cold stamping, convolutional neural networks, machine learning

Procedia PDF Downloads 149

Authors: Xiang-Yao Zheng, Jen-Cheng Wang, Joe-Air Jiang

Abstract:

Improving the line ampacity while using existing power grids is an important issue that electricity dispatchers are now facing. Using the information provided by the dynamic thermal rating (DTR) of transmission lines, an overhead power grid can operate safely. However, dispatchers usually lack real-time DTR information. Thus, this study proposes a long-short-term memory (LSTM)-based method, which is one of the neural network models. The LSTM-based method predicts the DTR of lines using the weather data provided by Central Weather Bureau (CWB) of Taiwan. The possible thermal bottlenecks at different locations along the line and the margin of line ampacity can be real-time determined by the proposed LSTM-based prediction method. A case study that targets the 345 kV power grid of TaiPower in Taiwan is utilized to examine the performance of the proposed method. The simulation results show that the proposed method is useful to provide the information for the smart grid application in the future.

Keywords: electricity dispatch, line ampacity prediction, dynamic thermal rating, long-short-term memory neural network, smart grid

Procedia PDF Downloads 282

Authors: Dung V. H. Pham, Kathryn Cullen

Abstract:

Introduction: 40% of adolescents with major depression (MDD) are unresponsive to 1st line antidepressant treatment. The neural mechanism underlying treatment-responsive and treatment-resistant depression in adolescent are unclear. Amygdala is important for emotion processing and has been implicated in mood disorders. Past research has shown abnormal amygdala connectivity in adolescents with MDD. This research study changes in amygdala resting-state functional connectivity to find neural correlates of successful antidepressant treatment. Methods: Thirteen adolescents aged 12-19 underwent rfMRI before and after 8-week antidepressant treatment and completed BDI-II at each scan. A whole-brain approach, using anatomically defined amygdala ROIs (1) identified brain regions that are highly synchronous with the amygdala, (2) correlated neural changes with changes in overall depression and specific symptom clusters within depression. Results: Some neural correlates were common across domains: (1) decreased amygdala RSFC with the default mode network (posterior cingulate, precuneus) is associated with improvement in overall depression and many symptom clusters, (2) increased amygdala RSFC with fusiform gyrus is associated with symptom improvement across many symptom clusters. We also found unique neural changes associated with symptom improvement in each symptom cluster. Conclusion: This is the first preliminary study that looks at neural correlates of antidepressant treatment response to overall depression as well as different clusters of symptoms of depression. The finding suggests both overlapping and distinct neural mechanisms underlying improvement in each symptom clusters within depression. Some brain regions found are also implicated in MDD among adults in previous literature.

Keywords: depression, adolescents, fMRI, antidepressants

Procedia PDF Downloads 252

Authors: Ajoy Kumar Das, Prasenjit Dey

Abstract:

Heat transfer due to forced convection of copper water based nanofluid has been predicted by Artificial Neural network (ANN). The present nanofluid is formed by mixing copper nano particles in water and the volume fractions are considered here are 0% to 15% and the Reynolds number are kept constant at 100. The back propagation algorithm is used to train the network. The present ANN is trained by the input and output data which has been obtained from the numerical simulation, performed in finite volume based Computational Fluid Dynamics (CFD) commercial software Ansys Fluent. The numerical simulation based results are compared with the back propagation based ANN results. It is found that the forced convection heat transfer of water based nanofluid can be predicted correctly by ANN. It is also observed that the back propagation ANN can predict the heat transfer characteristics of nanofluid very quickly compared to standard CFD method.

Keywords: forced convection, square cylinder, nanofluid, neural network

Procedia PDF Downloads 320

Authors: Lassaad Smirani

Abstract:

In this paper we propose a Neurosymbolic Learning System (NLS) as a channel estimator for Long Term Evolution Advanced (LTE-A) uplink. The proposed system main idea based on Neural Network has modules capable of performing bidirectional information transfer between symbolic module and connectionist module. We demonstrate various strengths of the NLS especially the ability to integrate theoretical knowledge (rules) and experiential knowledge (examples), and to make an initial knowledge base (rules) converted into a connectionist network. Also to use empirical knowledge witch by learning will have the ability to revise the theoretical knowledge and acquire new one and explain it, and finally the ability to improve the performance of symbolic or connectionist systems. Compared with conventional SC-FDMA channel estimation systems, The performance of NLS in terms of complexity and quality is confirmed by theoretical analysis and simulation and shows that this system can make the channel estimation accuracy improved and bit error rate decreased.

Keywords: channel estimation, SC-FDMA, neural network, hybrid system, BER, LTE-A

Procedia PDF Downloads 394

Authors: Xuewen Yu, Danhui Dan

Abstract:

The identification of impact load and some hard-to-obtain system parameters is crucial for the activities of analysis, validation, and evaluation in the engineering field. This paper proposes a method that utilizes neural networks based on 1D-CNN to identify the impact load and partial system parameters from measured responses. To this end, forward computations are conducted to provide datasets consisting of the triples (parameter θ, input u, output y). Then neural networks are trained to learn the mapping from input to output, fu|{θ} : y → u, as well as from input and output to parameter, fθ : (u, y) → θ. Afterward, feeding the trained neural networks the measured output response, the input impact load and system parameter can be calculated, respectively. The method is tested on two simulated examples and shows sound accuracy in estimating the impact load (waveform and location) and system parameters.

Keywords: convolutional neural network, impact load identification, system parameter identification, inverse problem

Procedia PDF Downloads 123

Authors: Seyed Sobhan Alvani, Mohammad Gohari

Abstract:

By developing cities and increasing the population, traffic congestion has become a vital problem. Due to this crisis, urban designers try to present solutions to decrease this difficulty. On the other hand, predicting the model with perfect accuracy is essential for solution-providing. The current study presents a model based on artificial intelligence which can predict traffic index based on city population, growth rate, and area. The accuracy of the model was evaluated, which is acceptable and it is around 90%. Thus, urban designers and planners can employ it for predicting traffic index in the future to provide strategies.

Keywords: traffic index, population growth rate, cities wideness, artificial neural network

Procedia PDF Downloads 40

Authors: Abbas Ahmadi, Bijan Raie, Mohammad Reza Neyshabouri, Mohammad Ali Ghorbani, Farrokh Asadzadeh

Abstract:

In recent years, vast areas of Urmia Lake in Dasht-e-Tabriz has dried up leading to saline sediments exposure on the surface lake coastal areas being highly susceptible to wind erosion. This study was conducted to investigate wind erosion and its relevance to soil physicochemical properties and also modeling of wind erodibility (WE) using artificial intelligence techniques. For this purpose, 96 soil samples were collected from 0-5 cm depth in 414000 hectares using stratified random sampling method. To measure the WE, all samples (<8 mm) were exposed to 5 different wind velocities (9.5, 11, 12.5, 14.1 and 15 m s-1 at the height of 20 cm) in wind tunnel and its relationship with soil physicochemical properties was evaluated. According to the results, WE varied within the range of 76.69-9.98 (g m-2 min-1)/(m s-1) with a mean of 10.21 and coefficient of variation of 94.5% showing a relatively high variation in the studied area. WE was significantly (P<0.01) affected by soil physical properties, including mean weight diameter, erodible fraction (secondary particles smaller than 0.85 mm) and percentage of the secondary particle size classes 2-4.75, 1.7-2 and 0.1-0.25 mm. Results showed that the mean weight diameter, erodible fraction and percentage of size class 0.1-0.25 mm demonstrated stronger relationship with WE (coefficients of determination were 0.69, 0.67 and 0.68, respectively). This study also compared efficiency of multiple linear regression (MLR), gene expression programming (GEP), artificial neural network (MLP), artificial neural network based on genetic algorithm (MLP-GA) and artificial neural network based on whale optimization algorithm (MLP-WOA) in predicting of soil wind erodibility in Dasht-e-Tabriz. Among 32 measured soil variable, percentages of fine sand, size classes of 1.7-2.0 and 0.1-0.25 mm (secondary particles) and organic carbon were selected as the model inputs by step-wise regression. Findings showed MLP-WOA as the most powerful artificial intelligence techniques (R2=0.87, NSE=0.87, ME=0.11 and RMSE=2.9) to predict soil wind erodibility in the study area; followed by MLP-GA, MLP, GEP and MLR and the difference between these methods were significant according to the MGN test. Based on the above finding MLP-WOA may be used as a promising method to predict soil wind erodibility in the study area.

Keywords: wind erosion, erodible fraction, gene expression programming, artificial neural network

Procedia PDF Downloads 71