Search results for: neural simulated annealing

Authors: R. Ghasemi, M. R. Rahimi Khoygani

Abstract:

This paper proposes the designing direct adaptive neural controller to apply for a class of a nonlinear pendulum dynamic system. The radial basis function (RBF) neural adaptive controller is robust in presence of external and internal uncertainties. Both the effectiveness of the controller and robustness against disturbances are importance of this paper. The simulation results show the promising performance of the proposed controller.

Keywords: adaptive neural controller, nonlinear dynamical, neural network, RBF, driven pendulum, position control

Procedia PDF Downloads 453

Authors: Zhongyang Sun, Shu Zhang, Manjiang Xie

Abstract:

Emerging evidence indicates that microRNAs (miRNAs) play important roles in modulating osteoblast function and bone formation. However, the influence of miRNA on osteoblast proliferation and the possible mechanisms underlying remain to be defined. In this study, we aimed to investigate whether miR-103 regulates osteoblast proliferation under simulated microgravity condition through regulating Cav1.2, the primary subunit of L-type voltage sensitive calcium channels (LTCCs). We first investigated the effect of simulated microgravity on osteoblast proliferation and the outcomes clearly demonstrated that the mechanical unloading inhibits MC3T3-E1 osteoblast-like cells proliferation. Using quantitative Real-Time PCR (qRT-PCR), we provided data showing that miR-103 was up-regulated in response to simulated microgravity. In addition, we observed that up-regulation of miR-103 inhibited and down-regulation of miR-103 promoted osteoblast proliferation under simulated microgravity condition. Furthermore, knocking-down or over-expressing miR-103, respectively, up- or down-regulated the level of Cav1.2 expression and LTCCs currents, suggesting that miR-103 acts as an endogenous attenuator of Cav1.2 in osteoblasts under the condition of simulated microgravity. More importantly, we showed that the effect of miR-103 on osteoblast proliferation was diminished in simulated microgravity, when co-transfecting miR-103 mimic or inhibitor with Cav1.2 siRNA. Taken together, our data suggest that miR-103 inhibits osteoblast proliferation mainly through suppression of Cav1.2 expression under simulated microgravity condition. This work may provide a novel mechanism of microgravity-induced detrimental effects on osteoblast, identifying miR-103 as a novel possible therapeutic target in bone remodeling disorders in this mechanical unloading.

Keywords: microRNA, osteoblasts, cell proliferation, Cav1.2, simulated microgravity

Procedia PDF Downloads 341

Authors: Yasser F. Hassan

Abstract:

Deep learning structure is a branch of machine learning science and greet achievement in research and applications. Cellular neural networks are regarded as array of nonlinear analog processors called cells connected in a way allowing parallel computations. The paper discusses how to use deep learning structure for representing neural cellular automata model. The proposed learning technique in cellular automata model will be examined from structure of deep learning. A deep automata neural cellular system modifies each neuron based on the behavior of the individual and its decision as a result of multi-level deep structure learning. The paper will present the architecture of the model and the results of simulation of approach are given. Results from the implementation enrich deep neural cellular automata system and shed a light on concept formulation of the model and the learning in it.

Keywords: cellular automata, neural cellular automata, deep learning, classification

Procedia PDF Downloads 160

Authors: Almagul Assainova , Dariya Abykenova, Liudmila Goncharenko, Sergey Sybachin, Saule Rakhimova, Abay Aman

Abstract:

The recognition of a handwritten Kazakh text is a relevant objective today for the digitization of materials. The study presents a model of a hybrid neural network for handwriting recognition, which includes a convolutional neural network and a multi-layer perceptron. Each network includes 1024 input neurons and 42 output neurons. The model is implemented in the program, written in the Python programming language using the EMNIST database, NumPy, Keras, and Tensorflow modules. The neural network training of such specific letters of the Kazakh alphabet as ә, ғ, қ, ң, ө, ұ, ү, h, і was conducted. The neural network model and the program created on its basis can be used in electronic document management systems to digitize the Kazakh text.

Keywords: handwriting recognition system, image recognition, Kazakh font, machine learning, neural networks

Procedia PDF Downloads 226

Authors: S. Adjiri-Bailiche, S. M. Boudia, H. Daaou, S. Hadouche, A. Benzaoui

Abstract:

In this work the study of changes in the wind speed depending on the altitude is calculated and described by the model of the neural networks, the use of measured data, the speed and direction of wind, temperature and the humidity at 10 m are used as input data and as data targets at 50m above sea level. Comparing predict wind speeds and extrapolated at 50 m above sea level is performed. The results show that the prediction by the method of artificial neural networks is very accurate.

Keywords: MATLAB, neural network, power low, vertical extrapolation, wind energy, wind speed

Procedia PDF Downloads 651

Authors: Mustafa Alhamdi

Abstract:

Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.

Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification

Procedia PDF Downloads 121

Authors: Alireza Lavaei, Alireza Lohrasbi, Mohammadali M. Shahlaei

Abstract:

To reduce the overall time of structural optimization for earthquake loads two strategies are adopted. In the first strategy, a neural system consisting self-organizing map and radial basis function neural networks, is utilized to predict the time history responses. In this case, the input space is classified by employing a self-organizing map neural network. Then a distinct RBF neural network is trained in each class. In the second strategy, an improved genetic algorithm is employed to find the optimum design. A 72-bar space truss is designed for optimal weight using exact and approximate analysis for the El Centro (S-E 1940) earthquake loading. The numerical results demonstrate the computational advantages and effectiveness of the proposed method.

Keywords: optimization, genetic algorithm, neural networks, self-organizing map

Procedia PDF Downloads 273

Authors: Sang-Hoon Park, Yeji Ho, Gwang-Moon Eom

Abstract:

Fast and accurate detection of Freezing of Gait (FOG) is desirable for appropriate application of cueing which has been shown to ameliorate FOG. Utilization of frequency spectrum of leg acceleration to derive the freeze index requires much calculation and it would lead to delayed cueing. We hypothesized that FOG can be reasonably detected from the time domain amplitude of foot acceleration. A time instant was recognized as FOG if the mean amplitude of the acceleration in the time window surrounding the time instant was in the specific FOG range. Parameters required in the FOG detection was optimized by simulated annealing. The suggested time domain methods showed performances comparable to those of frequency domain methods.

Keywords: freezing of gait, detection, Parkinson's disease, time-domain method

Procedia PDF Downloads 415

Authors: R. Loukil, M. Chtourou, T. Damak

Abstract:

This paper investigates the training of multilayer neural network using the classic approach. Then, for estimation purposes, we suggest the use of a specific neural observer that we study its training algorithm which is the back-propagation one in the case of the disponibility of the state and in the case of an unmeasurable state. A MATLAB simulation example will be studied to highlight the usefulness of this kind of observer.

Keywords: training, estimation purposes, neural observer, back-propagation, unmeasurable state

Procedia PDF Downloads 539

Authors: Shreyash Hadke, Manendra Singh Parihar, Rajesh Khatirkar

Abstract:

In the present investigation, the variation in the microstructure with the changes in the heat treatment conditions i.e. temperature and time was observed. Ti-6Al-4V alloy was subject to solution annealing treatments in β (1066C) and α+β phase (930C and 850C) followed by quenching, air cooling and furnace cooling to room temperature respectively. The effect of solution annealing and cooling on the microstructure was studied by using optical microscopy (OM), scanning electron microscopy (SEM), electron backscattered diffraction (EBSD) and x-ray diffraction (XRD). The chemical composition of the β phase for different conditions was determined with the help of energy dispersive spectrometer (EDS) attached to SEM. Furnace cooling resulted in the development of coarser structure (α+β), while air cooling resulted in much finer structure with widmanstatten morphology of α at the grain boundaries. Quenching from solution annealing temperature formed α’ martensite, their proportion being dependent on the temperature in β phase field. It is well known that the transformation of β to α follows Burger orientation relationship (OR). In order to reconstruct the microstructure of parent β phase, a MATLAB code was written using neighbor-to-neighbor, triplet method and Tari’s method. The code was tested on the annealed samples (1066C solution annealing temperature followed by furnace cooling to room temperature). The parent phase data thus generated was then plotted using the TSL-OIM software. The reconstruction results of the above methods were compared and analyzed. The Tari’s approach (clustering approach) gave better results compared to neighbor-to-neighbor and triplet method but the time taken by the triplet method was least compared to the other two methods.

Keywords: Ti-6Al-4V alloy, microstructure, electron backscattered diffraction, parent phase reconstruction

Procedia PDF Downloads 419

Authors: Pavlo Selyshchev

Abstract:

A theoretical approach to describe kinetic of heat transfer between an irradiated sample and environment is developed via formalism of the Complex systems and kinetic equations. The irradiated material is a metastable system with non-linear feedbacks, which can give rise to different regimes of buildup and annealing of radiation-induced defects, heating and heat transfer with environment. Irradiation with energetic particles heats the sample and produces defects of the crystal lattice of the sample. The crystal with defects accumulates extra (non-thermal) energy, which is transformed into heat during the defect annealing. Any increase of temperature leads to acceleration of defect annealing, to additional transformation of non-thermal energy into heat and to further growth of the temperature. Thus a non-linear feedback is formed. It is shown that at certain conditions of irradiation this non-linear feedback leads to self-oscillations of the defect density, the temperature of the irradiated sample and the heat transfer between the sample and environment. Simulation and analysis of these phenomena is performed. The frequency of the self-oscillations is obtained. It is determined that the period of the self-oscillations is varied from minutes to several hours depending on conditions of irradiation and properties of the sample. Obtaining results are compared with experimental ones.

Keywords: irradiation, heat transfer, non-linear feed-back, self-oscillations

Procedia PDF Downloads 201

Authors: Koray U. Erbas

Abstract:

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

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

Procedia PDF Downloads 230

Authors: Shaik Jilani Basha, Inavolu Avinash, Alla Venu Sai Reddy, Bitragunta Taraka Ramu

Abstract:

We can use the neural style transfer technique to build a picture with the same "content" as the beginning image but the "style" of the picture we've chosen. Neural style transfer is a technique for merging the style of one image into another while retaining its original information. The only change is how the image is formatted to give it an additional artistic sense. The content image depicts the plan or drawing, as well as the colors of the drawing or paintings used to portray the style. It is a computer vision programme that learns and processes images through deep convolutional neural networks. To implement software, we used to train deep learning models with the train data, and whenever a user takes an image and a styled image, the output will be as the style gets transferred to the original image, and it will be shown as the output.

Keywords: neural networks, computer vision, deep learning, convolutional neural networks

Procedia PDF Downloads 53

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

Abstract:

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

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

Procedia PDF Downloads 106

Authors: Ning Xue, Srinivas Merugu, Ignacio Delgado Martinez, Tao Sun, John Tsang, Shih-Cheng Yen

Abstract:

We have developed a polyimide based neural interface electrode to record nerve signals from the sciatic nerve of a rat. The neural interface electrode has a split-ring shape, with four protruding gold electrodes for recording, and two reference gold electrodes around the split-ring. The split-ring electrode can be opened up to encircle the sciatic nerve. The four electrodes can be bent to sit on top of the nerve and hold the device in position, while the split-ring frame remains flat. In comparison, while traditional cuff electrodes can only fit certain sizes of the nerve, the developed device can fit a variety of rat sciatic nerve dimensions from 0.6 mm to 1.0 mm, and adapt to the chronic changes in the nerve as the electrode tips are bendable. The electrochemical impedance spectroscopy measurement was conducted. The gold electrode impedance is on the order of 10 kΩ, showing excellent charge injection capacity to record neural signals.

Keywords: impedance, neural interface, split-ring electrode, neural signal recording

Procedia PDF Downloads 342

Authors: Tianle Yang

Abstract:

As a common mental disorder, depression is a leading cause of various diseases worldwide. Early detection and treatment of depression can dramatically promote remission and prevent relapse. However, conventional ways of depression diagnosis require considerable human effort and cause economic burden, while still being prone to misdiagnosis. On the other hand, recent studies report that physical characteristics are major contributors to the diagnosis of depression, which inspires us to mine the internal relationship by neural networks instead of relying on clinical experiences. In this paper, neural networks are constructed to predict depression from physical characteristics. Two initialization methods are examined - Xaiver and Kaiming initialization. Experimental results show that a 3-layers neural network with Kaiming initialization achieves 83% accuracy.

Keywords: depression, neural network, Xavier initialization, Kaiming initialization

Procedia PDF Downloads 96

Authors: N. Berrouachedi, M. Bouslama, S. Rioual, B. Lescop, J. Langlois

Abstract:

Using first-principles calculations within the LSDA (Local Spin Density Approximation) method based on density functional theory (DFT), the electronic structure and magnetic properties of zinc blende Fe/In0.5Ga0.5As/InPsuperlattice are investigated. This compound are found to be half -metallic ferromagnets with a total magnetic moment of 2.25μB per Fe. In addition to this, we reported the DRX measurements of the thick iron sample before and after annealing. One should note, after the annealing treatment at a higher temperature, the disappearance of the peak associated to the Fe(001) plane. In contrast to this report, we observed after the annealing at low temperature the additional peaks attributed to the presence of indium and Fe2As. This suggests a subsequent process consisting in a strong migration of atoms followed with crystallization at the higher temperature.To investigate the origin of magnetism and electronic structure in these zb compounds, we calculated the total and partial DOS of FeInP.One can see that µtotal=4.24µBand µFe=3.27µB in contrast µIn=0.021µB and µP=0.049µB.These results predicted that FeInP compound do belong to the class of zb half metallic HM ferromagnetswith a pseudo gap= 0.93 eVare more promising materials for spintronics devices.

Keywords: zincblend structure, half metallic ferromagnet, spin moments, total and partial DOS, DRX, Wien2k

Procedia PDF Downloads 245

Authors: A. L. R. Rangel, J. A. M. Chaves, A. P. R. Alves Claro

Abstract:

Surface modification of titanium and its alloys using TiO2 nanotube growth has been widely studied for biomedical field due to excellent interaction between implant and biological environment. The success of this treatment is directly related to anatase phase formation (TiO2 phase) which affects the cells growth. The aim of this study was to evaluate the phases formed in the nanotubes growth on the Ti-15Mo surface. Nanotubes were grown by electrochemical anodization of the alloy in ammonium fluoride based glycerol electrolyte for 24 hours at 20V. Then, the samples were annealed at 200°,400°, 450°, 500°, 600°, and 800° C for 1 hour. Contact angles measurements, scanning electron microscopy images and X rays diffraction analysis (XRD) were carried out for all samples. Raman Spectroscopy was used to evaluate TiO2 phases transformation in nanotubes samples as well. The results of XRD showed anatase formation for lower temperatures, while at 800 ° C the rutile phase was observed all over the surface. Raman spectra indicate that this phase transition occurs between 500 and 600 °C. The different phases formed have influenced the nanotubes morphologies, since higher annealing temperatures induced agglutination of the TiO2 layer, disrupting the tubular structure. On the other hand, the nanotubes drastically reduced the contact angle, regardless the annealing temperature.

Keywords: nanotubes, TiO2, titanium alloys, Ti-15Mo

Procedia PDF Downloads 361

Authors: Yahia. Kourd, N. Guersi D. Lefebvre

Abstract:

In this paper we propose to study the faults diagnosis in squirrel-cage induction motor using MLP neural networks. We use neural healthy and faulty models of the behavior in order to detect and isolate some faults in machine. In the first part of this work, we have created a neural model for the healthy state using Matlab and a motor located in LGEB by acquirins data inputs and outputs of this engine. Then we detected the faults in the machine by residual generation. These residuals are not sufficient to isolate the existing faults. For this reason, we proposed additive neural networks to represent the faulty behaviors. From the analysis of these residuals and the choice of a threshold we propose a method capable of performing the detection and diagnosis of some faults in asynchronous machines with squirrel cage rotor.

Keywords: faults diagnosis, neural networks, multi-models, squirrel-cage induction motor

Procedia PDF Downloads 602

Authors: Ahmad Alwosheel, Ahmed Alqaraawi

Abstract:

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

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

Procedia PDF Downloads 468

Authors: Wasi Khan, Suboohi Shervani, Swaleha Naseem, Mohd. Shoeb, J. A. Khan, B. R. Singh, A. H. Naqvi

Abstract:

We have successfully synthesized ZnO/TiO2 nanocomposite using a two-step solochemical synthesis method. The influence of annealing temperature on microstructural, optical, anticandidal, photocatalytic activities and dielectric properties were investigated. X-ray diffraction (XRD) and scanning electron microscopy (SEM) show the formation of nanocomposite and uniform surface morphology of all samples. The UV-Vis spectra indicate decrease in band gap energy with increase in annealing temperature. The anticandidal activity of ZnO/TiO2 nanocomposite was evaluated against MDR C. albicans 077. The in-vitro killing assay revealed that the ZnO/TiO2 nanocomposite efficiently inhibit the growth of the C. albicans 077. The nanocomposite also exhibited the photocatalytic activity for the degradation of methyl orange as a function of time at 465 nm wavelength. The electrical behaviour of composite has been studied over a wide range of frequencies at room temperature using complex impedance spectroscopy. The dielectric constants, dielectric loss and ac conductivity (σac) were studied as the function of frequency, which have been explained by ‘Maxwell Wagner Model’. The data reveals that the dielectric constant and loss (tanδ) exhibit the normal dielectric behavior and decreases with the increase in frequency.

Keywords: ZnO/TiO2 nanocomposites, SEM, photocatalytic activity, dielectric properties

Procedia PDF Downloads 376

Authors: T. A. Prikhna, A. V. Shaternik, V. E. Moshchil, M. Eisterer, V. E. Shaternik

Abstract:

The paper presents the results of studying the structure, phase composition, relief, and superconducting characteristics of oxygen-containing thin films of magnesium diboride (MgB₂) deposited on a dielectric substrate by magnetron sputtering of diboride-magnesium targets. The possibility of forming films of varying degrees of crystalline perfection and phase composition in the process of precipitation and annealing is shown, depending on the conditions of deposition and annealing. In the films, it is possible to realize various combinations of the Abrikosov vortex pinning centers (in the places of fluctuations of the critical temperature of the superconducting transition (T

Keywords: critical current density, diboride, superconducting thin films, upper critical field

Procedia PDF Downloads 87

Authors: Natalia Espinosa, Arthur Amorim, Rudolf Huebner

Abstract:

Epilepsy is a chronic neural disease and around 50 million people in the world suffer from this disease, however, in many cases, the individual acquires resistance to the medication, which is known as drug-resistant epilepsy, where a detection system is necessary. This paper showed the development of an automatic system for seizure detection based on artificial neural networks (ANN), which are common techniques of machine learning. Discrete Wavelet Transform (DWT) is used for decomposing electroencephalogram (EEG) signal into main brain waves, with these frequency bands is extracted features for training a feedforward neural network with backpropagation, finally made a pattern classification, seizure or non-seizure. Obtaining 95% accuracy in epileptic EEG and 100% in normal EEG.

Keywords: Artificial Neural Network (ANN), Discrete Wavelet Transform (DWT), Epilepsy Detection , Seizure.

Procedia PDF Downloads 177

Authors: Mehdi Ghatus

Abstract:

Two simple apparatus based on the hammer and anvil principle have been constructed and used to study the microstructure and micro-hardness characteristics of some AL-base alloys. Foils with thicknesses arranging from 20 µm up to 600 µm have been obtained. The cooling rate was estimated to be in the range 10^4 - 10^5 K/sec. Microstructure study of rapidly quenched Al-30% Si foils indicated that with decreasing the foil thickness the size of primary Si crystallites decreases in the whole investigated range (0.64-0.15 mm). However, the volume fraction of the primary Si crystals in the structure remained constant down to thickness the primary Si volume fraction started to decrease. Rapid quenching of Al- 14-16% Cu showed single phase cell structure. In foils up to 0.55 mm with decreasing the foil thickness the cell size decreases and micro-hardness increases particularly in foils below 0.3 mm in thickness. Isochronal annealing of theses foils show that the highly supersaturated Al-14-16% Cu solid solution decomposes readily at relatively low temperature and short time intervals. The maximum hardness is obtained after annealing at 100 °C for 30 minutes. However with decreasing the Cu content of the foils the precipitation process is largely delayed. Eight hours of annealing at 100 °C was not enough to achieve the maximum hardness in Al-4% Cu thin foils. The achieved hardness value was more than twice of the maximum hardness obtained in articles of similar composition but conventionally aged.

Keywords: aluminum, hardness, alloys, quenched aluminum

Procedia PDF Downloads 397

Authors: Ali Isapour, Ramin Nateghi

Abstract:

— Markov parameters are unique parameters of the system and remain unchanged under similarity transformations. Markov parameters from a power series that is convergent only if the system matrix’s eigenvalues are inside the unity circle. Therefore, Markov parameters of a stable discrete-time system are convergent. In this study, we aim to realize the system based on Markov parameters by using Artificial Neural Networks (ANN), and this end, we use Flexible Neural Networks. Realization means determining the elements of matrices A, B, C, and D.

Keywords: Markov parameters, realization, activation function, flexible neural network

Procedia PDF Downloads 160

Authors: Wen-Shyong Tzou, Chih-Ching Huang, Chin-Hwa Hu, Ying-Tsang Lo, Tun-Wen Pai, Chia-Yin Chiang, Chung-Hao Li, Hong-Jyuan Jian

Abstract:

Plasmin plays an important role in the human circulatory system owing to its catalytic ability of fibrinolysis. The immediate injection of plasmin in patients of strokes has intrigued many scientists to design vectors that can transport plasmin to the desired location in human body. Here we predict the structure of human plasmin and investigate the interaction of plasmin with the gold-nanoparticle. Because the crystal structure of plasminogen has been solved, we deleted N-terminal domain (Pan-apple domain) of plasminogen and generate a mimic of the active form of this enzyme (plasmin). We conducted a simulated annealing process on plasmin and discovered a very large conformation occurs. Kringle domains 1, 4 and 5 had been observed to leave its original location relative to the main body of the enzyme and the original doughnut shape of this enzyme has been transformed to a V-shaped by opening its two arms. This observation of conformational change is consistent with the experimental results of neutron scattering and centrifugation. We subsequently docked the plasmin on the simulated gold surface to predict their interaction. The V-shaped plasmin could utilize its Kringle domain and catalytic domain to contact the gold surface. Our findings not only reveal the flexibility of plasmin structure but also provide a guide for the design of a plasmin-gold nanoparticle.

Keywords: docking, gold nanoparticle, molecular simulation, plasmin

Procedia PDF Downloads 451

Authors: Hassan Masoumi, Ahad Salimi, Nazanin Barhemmat, Babak Gholami

Abstract:

Artificial neural networks have gained a lot of interest as empirical models for their powerful representational capacity, multi input and output mapping characteristics. In fact, most feed-forward networks with nonlinear nodal functions have been proved to be universal approximates. In this paper, we propose a new supervised method for color image classification based on self organizing feature maps (SOFM). This algorithm is based on competitive learning. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods. Our image classification system entered into RGB image. Experiments with simulated data showed that separability of classes increased when increasing training time. In additional, the result shows proposed algorithms are effective for color image classification.

Keywords: classification, SOFM algorithm, neural network, neighborhood, RGB image

Procedia PDF Downloads 445

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: Mohd Khairul Bazli Mohd Aziz, Fadhilah Yusof, Zulkifli Yusop, Zalina Mohd Daud, Mohammad Afif Kasno

Abstract:

Recent developed rainfall network design techniques have been discussed and compared by many researchers worldwide due to the demand of acquiring higher levels of accuracy from collected data. In many studies, rain-gauge networks are designed to provide good estimation for areal rainfall and for flood modelling and prediction. In a certain study, even using lumped models for flood forecasting, a proper gauge network can significantly improve the results. Therefore existing rainfall network in Johor must be optimized and redesigned in order to meet the required level of accuracy preset by rainfall data users. The well-known geostatistics method (variance-reduction method) that is combined with simulated annealing was used as an algorithm of optimization in this study to obtain the optimal number and locations of the rain gauges. Rain gauge network structure is not only dependent on the station density; station location also plays an important role in determining whether information is acquired accurately. The existing network of 84 rain gauges in Johor is optimized and redesigned by using rainfall, humidity, solar radiation, temperature and wind speed data during monsoon season (November – February) for the period of 1975 – 2008. Three different semivariogram models which are Spherical, Gaussian and Exponential were used and their performances were also compared in this study. Cross validation technique was applied to compute the errors and the result showed that exponential model is the best semivariogram. It was found that the proposed method was satisfied by a network of 64 rain gauges with the minimum estimated variance and 20 of the existing ones were removed and relocated. An existing network may consist of redundant stations that may make little or no contribution to the network performance for providing quality data. Therefore, two different cases were considered in this study. The first case considered the removed stations that were optimally relocated into new locations to investigate their influence in the calculated estimated variance and the second case explored the possibility to relocate all 84 existing stations into new locations to determine the optimal position. The relocations of the stations in both cases have shown that the new optimal locations have managed to reduce the estimated variance and it has proven that locations played an important role in determining the optimal network.

Keywords: geostatistics, simulated annealing, semivariogram, optimization

Procedia PDF Downloads 273

Authors: Suk-Hyun Yu, Heeyong Kwon

Abstract:

Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.

Keywords: artificial intelligence, air quality prediction, neural networks, pattern recognition, PM-10

Procedia PDF Downloads 205