Search results for: neural tube defects
2505 Instant Fire Risk Assessment Using Artifical Neural Networks
Authors: Tolga Barisik, Ali Fuat Guneri, K. Dastan
Abstract:
Major industrial facilities have a high potential for fire risk. In particular, the indices used for the detection of hidden fire are used very effectively in order to prevent the fire from becoming dangerous in the initial stage. These indices provide the opportunity to prevent or intervene early by determining the stage of the fire, the potential for hazard, and the type of the combustion agent with the percentage values of the ambient air components. In this system, artificial neural network will be modeled with the input data determined using the Levenberg-Marquardt algorithm, which is a multi-layer sensor (CAA) (teacher-learning) type, before modeling the modeling methods in the literature. The actual values produced by the indices will be compared with the outputs produced by the network. Using the neural network and the curves to be created from the resulting values, the feasibility of performance determination will be investigated.Keywords: artifical neural networks, fire, Graham Index, levenberg-marquardt algoritm, oxygen decrease percentage index, risk assessment, Trickett Index
Procedia PDF Downloads 1312504 Exergy Analysis of Poultry Litter-to-Energy Production by the Advanced Combustion System
Authors: Samuel Oludayo Alamu, Seong Lee
Abstract:
The need for generating energy from biomass in an efficient way as well as maximizing the yield of total energy from the thermal conversion process has been a major concern for researchers. A holistic approach which involves the combination of First law of thermodynamics (FLT) and the second law of thermodynamics (SLT) is required for conducting an effective assessment of an energy plant since FLT analysis alone fails to identify the quality of the dissipated energy and how much work potential is available. The overall purpose of this study is to investigate the exergy analysis of direct combustion of poultry waste being converted to energy with a handful of environmental assessment of the conversion processes in order to maximize thermal efficiency. The exergy analysis around the shell and tube heat exchanger (STHE) was investigated primarily by varying the operating parameters for different tube shapes and flow direction, and an exergy model was obtained from estimations of the higher heating value and standard entropy of poultry waste from the elemental compositions. The STHE was designed and fabricated by Lee Research Group at Morgan State University. The analysis conducted on theSTHE using the flue gas temperature entering and exiting show that only about one-third of the energy input to the STHE was available to do work with an overall efficiency of 13.8%, while a huge amount was lost to the surrounding. By recirculating the flue gas, the exergy efficiency of the combustion system can be maximized with a greater reduction in the amount of exergy loss.Keywords: exergy analysis, shell and tube heat exchanger, thermodynamics, combustion system, thermal efficiency
Procedia PDF Downloads 1012503 Large Neural Networks Learning From Scratch With Very Few Data and Without Explicit Regularization
Authors: Christoph Linse, Thomas Martinetz
Abstract:
Recent findings have shown that Neural Networks generalize also in over-parametrized regimes with zero training error. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining. We train the architectures ResNet018, ResNet101 and VGG19 on subsets of the difficult benchmark datasets Caltech101, CUB_200_2011, FGVCAircraft, Flowers102 and StanfordCars with 100 classes and more, perform a comprehensive comparative study and draw implications for the practical application of CNNs. Finally, we show that VGG19 with 140 million weights learns to distinguish airplanes and motorbikes with up to 95% accuracy using only 20 training samples per class.Keywords: convolutional neural networks, fine-grained image classification, generalization, image recognition, over-parameterized, small data sets
Procedia PDF Downloads 822502 Broadband Ultrasonic and Rheological Characterization of Liquids Using Longitudinal Waves
Authors: M. Abderrahmane Mograne, Didier Laux, Jean-Yves Ferrandis
Abstract:
Rheological characterizations of complex liquids like polymer solutions present an important scientific interest for a lot of researchers in many fields as biology, food industry, chemistry. In order to establish master curves (elastic moduli vs frequency) which can give information about microstructure, classical rheometers or viscometers (such as Couette systems) are used. For broadband characterization of the sample, temperature is modified in a very large range leading to equivalent frequency modifications applying the Time Temperature Superposition principle. For many liquids undergoing phase transitions, this approach is not applicable. That is the reason, why the development of broadband spectroscopic methods around room temperature becomes a major concern. In literature many solutions have been proposed but, to our knowledge, there is no experimental bench giving the whole rheological characterization for frequencies about a few Hz (Hertz) to many MHz (Mega Hertz). Consequently, our goal is to investigate in a nondestructive way in very broadband frequency (A few Hz – Hundreds of MHz) rheological properties using longitudinal ultrasonic waves (L waves), a unique experimental bench and a specific container for the liquid: a test tube. More specifically, we aim to estimate the three viscosities (longitudinal, shear and bulk) and the complex elastic moduli (M*, G* and K*) respectively longitudinal, shear and bulk moduli. We have decided to use only L waves conditioned in two ways: bulk L wave in the liquid or guided L waves in the tube test walls. In this paper, we will present first results for very low frequencies using the ultrasonic tracking of a falling ball in the test tube. This will lead to the estimation of shear viscosity from a few mPa.s to a few Pa.s (Pascal second). Corrections due to the small dimensions of the tube will be applied and discussed regarding the size of the falling ball. Then the use of bulk L wave’s propagation in the liquid and the development of a specific signal processing in order to assess longitudinal velocity and attenuation will conduct to the longitudinal viscosity evaluation in the MHz frequency range. At last, the first results concerning the propagation, the generation and the processing of guided compressional waves in the test tube walls will be discussed. All these approaches and results will be compared to standard methods available and already validated in our lab.Keywords: nondestructive measurement for liquid, piezoelectric transducer, ultrasonic longitudinal waves, viscosities
Procedia PDF Downloads 2622501 Single Pole-To-Earth Fault Detection and Location on the Tehran Railway System Using ICA and PSO Trained Neural Network
Authors: Masoud Safarishaal
Abstract:
Detecting the location of pole-to-earth faults is essential for the safe operation of the electrical system of the railroad. This paper aims to use a combination of evolutionary algorithms and neural networks to increase the accuracy of single pole-to-earth fault detection and location on the Tehran railroad power supply system. As a result, the Imperialist Competitive Algorithm (ICA) and Particle Swarm Optimization (PSO) are used to train the neural network to improve the accuracy and convergence of the learning process. Due to the system's nonlinearity, fault detection is an ideal application for the proposed method, where the 600 Hz harmonic ripple method is used in this paper for fault detection. The substations were simulated by considering various situations in feeding the circuit, the transformer, and typical Tehran metro parameters that have developed the silicon rectifier. Required data for the network learning process has been gathered from simulation results. The 600Hz component value will change with the change of the location of a single pole to the earth's fault. Therefore, 600Hz components are used as inputs of the neural network when fault location is the output of the network system. The simulation results show that the proposed methods can accurately predict the fault location.Keywords: single pole-to-pole fault, Tehran railway, ICA, PSO, artificial neural network
Procedia PDF Downloads 1132500 An Approach to Building a Recommendation Engine for Travel Applications Using Genetic Algorithms and Neural Networks
Authors: Adrian Ionita, Ana-Maria Ghimes
Abstract:
The lack of features, design and the lack of promoting an integrated booking application are some of the reasons why most online travel platforms only offer automation of old booking processes, being limited to the integration of a smaller number of services without addressing the user experience. This paper represents a practical study on how to improve travel applications creating user-profiles through data-mining based on neural networks and genetic algorithms. Choices made by users and their ‘friends’ in the ‘social’ network context can be considered input data for a recommendation engine. The purpose of using these algorithms and this design is to improve user experience and to deliver more features to the users. The paper aims to highlight a broader range of improvements that could be applied to travel applications in terms of design and service integration, while the main scientific approach remains the technical implementation of the neural network solution. The motivation of the technologies used is also related to the initiative of some online booking providers that have made the fact that they use some ‘neural network’ related designs public. These companies use similar Big-Data technologies to provide recommendations for hotels, restaurants, and cinemas with a neural network based recommendation engine for building a user ‘DNA profile’. This implementation of the ‘profile’ a collection of neural networks trained from previous user choices, can improve the usability and design of any type of application.Keywords: artificial intelligence, big data, cloud computing, DNA profile, genetic algorithms, machine learning, neural networks, optimization, recommendation system, user profiling
Procedia PDF Downloads 1582499 Production of Chromium Matrix Composite Reinforced by WC by Powder Metallurgy
Authors: Ahmet Yonetken, Ayhan Erol
Abstract:
Intermetallic materials advanced technology materials that have outstanding mechanical and physical properties for high temperature applications. Especially creep resistance, low density and high hardness properties stand out in such intermetallics. The microstructure, mechanical properties of %80Cr-%10Ti and %10WC powders were investigated using specimens produced by tube furnace sintering at 1000-1400°C temperature. A composite consisting of ternary additions, a metallic phase, Ti,Cr and WC have been prepared under Ar shroud and then tube furnace sintered. XRD, SEM (Scanning Electron Microscope), were investigated to characterize the properties of the specimens. Experimental results carried out for composition %80Cr-%10Ti and %10WC at 1400°C suggest that the best properties as 292HV and 5,34g/cm3 density were obtained at 1400°C.Keywords: ceramic-metal, composites, powder metallurgy, sintering
Procedia PDF Downloads 4602498 Using Machine Learning to Classify Different Body Parts and Determine Healthiness
Authors: Zachary Pan
Abstract:
Our general mission is to solve the problem of classifying images into different body part types and deciding if each of them is healthy or not. However, for now, we will determine healthiness for only one-sixth of the body parts, specifically the chest. We will detect pneumonia in X-ray scans of those chest images. With this type of AI, doctors can use it as a second opinion when they are taking CT or X-ray scans of their patients. Another ad-vantage of using this machine learning classifier is that it has no human weaknesses like fatigue. The overall ap-proach to this problem is to split the problem into two parts: first, classify the image, then determine if it is healthy. In order to classify the image into a specific body part class, the body parts dataset must be split into test and training sets. We can then use many models, like neural networks or logistic regression models, and fit them using the training set. Now, using the test set, we can obtain a realistic accuracy the models will have on images in the real world since these testing images have never been seen by the models before. In order to increase this testing accuracy, we can also apply many complex algorithms to the models, like multiplicative weight update. For the second part of the problem, to determine if the body part is healthy, we can have another dataset consisting of healthy and non-healthy images of the specific body part and once again split that into the test and training sets. We then use another neural network to train on those training set images and use the testing set to figure out its accuracy. We will do this process only for the chest images. A major conclusion reached is that convolutional neural networks are the most reliable and accurate at image classification. In classifying the images, the logistic regression model, the neural network, neural networks with multiplicative weight update, neural networks with the black box algorithm, and the convolutional neural network achieved 96.83 percent accuracy, 97.33 percent accuracy, 97.83 percent accuracy, 96.67 percent accuracy, and 98.83 percent accuracy, respectively. On the other hand, the overall accuracy of the model that de-termines if the images are healthy or not is around 78.37 percent accuracy.Keywords: body part, healthcare, machine learning, neural networks
Procedia PDF Downloads 932497 Comparative Study of Bending Angle in Laser Forming Process Using Artificial Neural Network and Fuzzy Logic System
Authors: M. Hassani, Y. Hassani, N. Ajudanioskooei, N. N. Benvid
Abstract:
Laser Forming process as a non-contact thermal forming process is widely used to forming and bending of metallic and non-metallic sheets. In this process, according to laser irradiation along a specific path, sheet is bent. One of the most important output parameters in laser forming is bending angle that depends on process parameters such as physical and mechanical properties of materials, laser power, laser travel speed and the number of scan passes. In this paper, Artificial Neural Network and Fuzzy Logic System were used to predict of bending angle in laser forming process. Inputs to these models were laser travel speed and laser power. The comparison between artificial neural network and fuzzy logic models with experimental results has been shown both of these models have high ability to prediction of bending angles with minimum errors.Keywords: artificial neural network, bending angle, fuzzy logic, laser forming
Procedia PDF Downloads 5862496 The Impact of Space Charges on the Electromechanical Constraints in HVDC Power Cable Containing Defects
Authors: H. Medoukali, B. Zegnini
Abstract:
Insulation techniques in high-voltage cables rely heavily on chemically synapsed polyethylene. The latter may contain manufacturing defects such as small cavities, for example. The presence of the cavity affects the distribution of the electric field at the level of the insulating layer; this change in the electric field is affected by the presence of different space charge densities within the insulating material. This study is carried out by performing simulations to determine the distribution of the electric field inside the insulator. The simulations are based on the creation of a two-dimensional model of a high-voltage cable of 154 kV using the COMSOL Multiphysics software. Each time we study the effect of changing the space charge density of on the electromechanical Constraints.Keywords: COMSOL multiphysics, electric field, HVDC, microcavities, space charges, XLPE
Procedia PDF Downloads 1232495 Macular Ganglion Cell Inner Plexiform Layer Thinning
Authors: Hye-Young Shin, Chan Kee Park
Abstract:
Background: To compare the thinning patterns of the ganglion cell-inner plexiform layer (GCIPL) and peripapillary retinal nerve fiber layer (pRNFL) as measured using Cirrus high-definition optical coherence tomography (HD-OCT) in patients with visual field (VF) defects that respect the vertical meridian. Methods: Twenty eyes of eleven patients with VF defects that respect the vertical meridian were enrolled retrospectively. The thicknesses of the macular GCIPL and pRNFL were measured using Cirrus HD-OCT. The 5% and 1% thinning area index (TAI) was calculated as the proportion of abnormally thin sectors at the 5% and 1% probability level within the area corresponding to the affected VF. The 5% and 1% TAI were compared between the GCIPL and pRNFL measurements. Results: The color-coded GCIPL deviation map showed a characteristic vertical thinning pattern of the GCIPL, which is also seen in the VF of patients with brain lesions. The 5% and 1% TAI were significantly higher in the GCIPL measurements than in the pRNFL measurements (all P < 0.01). Conclusions: Macular GCIPL analysis clearly visualized a characteristic topographic pattern of retinal ganglion cell (RGC) loss in patients with VF defects that respect the vertical meridian, unlike pRNFL measurements. Macular GCIPL measurements provide more valuable information than pRNFL measurements for detecting the loss of RGCs in patients with retrograde degeneration of the optic nerve fibers.Keywords: brain lesion, macular ganglion cell, inner plexiform layer, spectral-domain optical coherence tomography
Procedia PDF Downloads 3322494 Urinary Volatile Organic Compound Testing in Fast-Track Patients with Suspected Colorectal Cancer
Authors: Godwin Dennison, C. E. Boulind, O. Gould, B. de Lacy Costello, J. Allison, P. White, P. Ewings, A. Wicaksono, N. J. Curtis, A. Pullyblank, D. Jayne, J. A. Covington, N. Ratcliffe, N. K. Francis
Abstract:
Background: Colorectal symptoms are common but only infrequently represent serious pathology, including colorectal cancer (CRC). A large number of invasive tests are presently performed for reassurance. We investigated the feasibility of urinary volatile organic compound (VOC) testing as a potential triage tool in patients fast-tracked for assessment for possible CRC. Methods: A prospective, multi-centre, observational feasibility study was performed across three sites. Patients referred on NHS fast-track pathways for potential CRC provided a urine sample which underwent Gas Chromatography Mass Spectrometry (GC-MS), Field Asymmetric Ion Mobility Spectrometry (FAIMS) and Selected Ion Flow Tube Mass Spectrometry (SIFT-MS) analysis. Patients underwent colonoscopy and/or CT colonography and were grouped as either CRC, adenomatous polyp(s), or controls to explore the diagnostic accuracy of VOC output data supported by an artificial neural network (ANN) model. Results: 558 patients participated with 23 (4.1%) CRC diagnosed. 59% of colonoscopies and 86% of CT colonographies showed no abnormalities. Urinary VOC testing was feasible, acceptable to patients, and applicable within the clinical fast track pathway. GC-MS showed the highest clinical utility for CRC and polyp detection vs. controls (sensitivity=0.878, specificity=0.882, AUROC=0.884). Conclusion: Urinary VOC testing and analysis are feasible within NHS fast-track CRC pathways. Clinically meaningful differences between patients with cancer, polyps, or no pathology were identified therefore suggesting VOC analysis may have future utility as a triage tool. Acknowledgment: Funding: NIHR Research for Patient Benefit grant (ref: PB-PG-0416-20022).Keywords: colorectal cancer, volatile organic compound, gas chromatography mass spectrometry, field asymmetric ion mobility spectrometry, selected ion flow tube mass spectrometry
Procedia PDF Downloads 872493 Modelling Vehicle Fuel Consumption Utilising Artificial Neural Networks
Authors: Aydin Azizi, Aburrahman Tanira
Abstract:
The main source of energy used in this modern age is fossil fuels. There is a myriad of problems that come with the use of fossil fuels, out of which the issues with the greatest impact are its scarcity and the cost it imposes on the planet. Fossil fuels are the only plausible option for many vital functions and processes; the most important of these is transportation. Thus, using this source of energy wisely and as efficiently as possible is a must. The aim of this work was to explore utilising mathematical modelling and artificial intelligence techniques to enhance fuel consumption in passenger cars by focusing on the speed at which cars are driven. An artificial neural network with an error less than 0.05 was developed to be applied practically as to predict the rate of fuel consumption in vehicles.Keywords: mathematical modeling, neural networks, fuel consumption, fossil fuel
Procedia PDF Downloads 3972492 Effect of Number of Baffles on Pressure Drop and Heat Transfer in a Shell and Tube Heat Exchanger
Authors: A. Falavand Jozaei, A. Ghafouri, M. Mosavi Navaei
Abstract:
In this paper for a given heat duty, study of number of baffles on pressure drop and heat transfer is considered in a STHX (Shell and Tube Heat Exchanger) with single segmental baffles. The effect of number of baffles from 9 to 52 baffles (baffle spacing variations from 4 to 24 inches) over OHTC (Overall Heat Hransfer Coefficient) to pressure drop ratio (U/Δp ratio). The results show that U/Δp ratio is low when baffle spacing is minimum (4 inches) because pressure drop is high; however, heat transfer coefficient is very significant. Then, with the increase of baffle spacing, pressure drop rapidly decreases and OHTC also decreases, but the decrease of OHTC is lower than pressure drop, so (U/Δp) ratio increases. After increasing baffles more than 12 inches, variation in pressure drop is gradual and approximately constant and OHTC decreases; Consequently, U/Δp ratio decreases again. If baffle spacing reaches to 24 inches, STHX will have minimum pressure drop, but OHTC decreases, so required heat transfer surface increases and U/Δp ratio decreases. After baffle spacing more than 12 inches, variation of shell side pressure drop is negligible. So optimum baffle spacing is suggested between 8 to 12 inches (43 to 63 percent of inside shell diameter) for a sufficient heat duty and low pressure drop.Keywords: shell and tube heat exchanger, single segmental baffle, overall heat transfer coefficient, pressure drop
Procedia PDF Downloads 5342491 Design an Intelligent Fire Detection System Based on Neural Network and Particle Swarm Optimization
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 3752490 Hard Sludge Formation and Consolidation in Pressurized Water Reactor Steam Generators: An Experimental Study
Authors: R. Fernandez-Saavedra, M. B. Gomez-Mancebo, D. Gomez-Briceno
Abstract:
The gradual corrosion of PWR (Pressurized Water Reactor) feedwater, condensate and drain systems results in the inevitable liberation of corrosion products, principally metallic oxides, to the secondary circuit. In addition, other contaminants and impurities are introduced into the makeup water, auxiliary feedwater and by condenser leaks. All these compounds circulating in the secondary flow can eventually be transported to steam generators and be transformed into deposits on their surfaces. Deposits that accumulate on the tube sheet are known as sludge piles and when they consolidate and harden become into hard sludge. Hard sludge is especially detrimental because it favors tube deformation or denting at the top of tube sheet and further stress corrosion cracking (SCC). These failures affect the efficiency of nuclear power plants. In a recent work, a model for the formation and consolidation of hard sludge has been formulated, highlighting the influence of aluminum and silicon compounds in the initial formation of hard sludge. In this work, an experimental study has been performed in order to get a deeper understanding of the behavior of Al and Si species in hard sludge formation and consolidation. For this purpose, the key components of hard sludge (magnetite, aluminum and/or silicon sources) have been isothermally autoclaved in representative secondary circuit conditions during one week, and the resulting products have been chemically and structurally characterized by XRF and XRD techniques, respectively.Keywords: consolidation, hard sludge, secondary circuit, steam generator
Procedia PDF Downloads 1862489 Ontology-Based Backpropagation Neural Network Classification and Reasoning Strategy for NoSQL and SQL Databases
Authors: Hao-Hsiang Ku, Ching-Ho Chi
Abstract:
Big data applications have become an imperative for many fields. Many researchers have been devoted into increasing correct rates and reducing time complexities. Hence, the study designs and proposes an Ontology-based backpropagation neural network classification and reasoning strategy for NoSQL big data applications, which is called ON4NoSQL. ON4NoSQL is responsible for enhancing the performances of classifications in NoSQL and SQL databases to build up mass behavior models. Mass behavior models are made by MapReduce techniques and Hadoop distributed file system based on Hadoop service platform. The reference engine of ON4NoSQL is the ontology-based backpropagation neural network classification and reasoning strategy. Simulation results indicate that ON4NoSQL can efficiently achieve to construct a high performance environment for data storing, searching, and retrieving.Keywords: Hadoop, NoSQL, ontology, back propagation neural network, high distributed file system
Procedia PDF Downloads 2592488 Effect of Interference and Form Defect on the Cohesion of the Shrink-Fit Assembly
Authors: Allal Bedlaoui, Hamid Boutoutaou
Abstract:
Due to its superior economics, shrink-fit assembly is one of the best mechanical assembly methods. There are simply two components, the axis and hub. It is used in many different industries, including the production of trains, cars, and airplanes. The outer radius of the inner cylinder must be greater than the inner radius of the outer cylinder for this operation; this difference is referred to as the "interference" between the two cylinders. There are three ways to accomplish this: heating the outer cylinder to cause it to expand; cooling the cylinder's inside to cause it to contract; and third, finishing the fitting under a press. At the intersection of the two matched parts, a contact pressure and friction force are generated. We consider interference and form defects in this article because they prevent the connection between the axis and the hub from having a perfect form surface and because we will be looking at how they affect the assembly. Numerical simulation is used to ascertain if interference and form defects have a beneficial or negative influence in the distribution of stresses, assembly resistance, and plasticity.Keywords: shrink-fit, interference, form defect, plasticity, extraction force
Procedia PDF Downloads 732487 Neuroplasticity: A Fresh Begining for Life
Authors: Leila Maleki, Ezatollah Ahmadi
Abstract:
Neuroplasticity or the flexibility of the neural system is the ability of the brain to adapt to the lack or deterioration of sense and the capability of the neural system to modify itself through changing shape and function. Not only have studies revealed that neuroplasticity does not end in childhood, but also they have proven that it continues till the end of life and is not limited to the neural system and covers the cognitive system as well. In the field of cognition, neuroplasticity is defined as the ability to change old thoughts according to new conditions and the individuals' differences in using various styles of cognitive regulation inducing several social, emotional and cognitive outcomes. On the other hand, complexities of daily life necessitates cognitive neuroplasticity in order to adapt to different circumstances. The present paper attempts to discuss and define major theories and principles of neuroplasticity and elaborate on nature or nurture.Keywords: neuroplasticity, cognitive plasticity, plasticity theories, plasticity mechanisms
Procedia PDF Downloads 4882486 Neuroplasticity: A Fresh Beginning for Life
Authors: Leila Maleki, Ezatollah Ahmadi
Abstract:
Neuroplasticity or the flexibility of the neural system is the ability of the brain to adapt to the lack or deterioration of sense and the capability of the neural system to modify itself through changing shape and function. Not only have studies revealed that neuroplasticity does not end in childhood, but also they have proven that it continues till the end of life and is not limited to the neural system and covers the cognitive system as well. In the field of cognition, neuroplasticity is defined as the ability to change old thoughts according to new conditions and the individuals' differences in using various styles of cognitive regulation inducing several social, emotional and cognitive outcomes. On the other hand, complexities of daily life necessitates cognitive neuroplasticity in order to adapt to different circumstances. The. present paper attempts to discuss and define major theories and principles of neuroplasticity and elaborate on nature or nurture.Keywords: neuroplasticity, cognitive plasticity, plasticity theories, plasticity mechanisms
Procedia PDF Downloads 4472485 Two Concurrent Convolution Neural Networks TC*CNN Model for Face Recognition Using Edge
Authors: T. Alghamdi, G. Alaghband
Abstract:
In this paper we develop a model that couples Two Concurrent Convolution Neural Network with different filters (TC*CNN) for face recognition and compare its performance to an existing sequential CNN (base model). We also test and compare the quality and performance of the models on three datasets with various levels of complexity (easy, moderate, and difficult) and show that for the most complex datasets, edges will produce the most accurate and efficient results. We further show that in such cases while Support Vector Machine (SVM) models are fast, they do not produce accurate results.Keywords: Convolution Neural Network, Edges, Face Recognition , Support Vector Machine.
Procedia PDF Downloads 1462484 Artificial Neural Networks Face to Sudden Load Change for Shunt Active Power Filter
Authors: Dehini Rachid, Ferdi Brahim
Abstract:
The shunt active power filter (SAPF) is not destined only to improve the power factor, but also to compensate the unwanted harmonic currents produced by nonlinear loads. This paper presents a SAPF with identification and control method based on artificial neural network (ANN). To identify harmonics, many techniques are used, among them the conventional p-q theory and the relatively recent one the artificial neural network method. It is difficult to get satisfied identification and control characteristics by using a normal (ANN) due to the nonlinearity of the system (SAPF + fast nonlinear load variations). This work is an attempt to undertake a systematic study of the problem to equip the (SAPF) with the harmonics identification and DC link voltage control method based on (ANN). The latter has been applied to the (SAPF) with fast nonlinear load variations. The results of computer simulations and experiments are given, which can confirm the feasibility of the proposed active power filter.Keywords: artificial neural networks (ANN), p-q theory, harmonics, total harmonic distortion
Procedia PDF Downloads 3812483 Laser Ultrasonic Imaging Based on Synthetic Aperture Focusing Technique Algorithm
Authors: Sundara Subramanian Karuppasamy, Che Hua Yang
Abstract:
In this work, the laser ultrasound technique has been used for analyzing and imaging the inner defects in metal blocks. To detect the defects in blocks, traditionally the researchers used piezoelectric transducers for the generation and reception of ultrasonic signals. These transducers can be configured into the sparse and phased array. But these two configurations have their drawbacks including the requirement of many transducers, time-consuming calculations, limited bandwidth, and provide confined image resolution. Here, we focus on the non-contact method for generating and receiving the ultrasound to examine the inner defects in aluminum blocks. A Q-switched pulsed laser has been used for the generation and the reception is done by using Laser Doppler Vibrometer (LDV). Based on the Doppler effect, LDV provides a rapid and high spatial resolution way for sensing ultrasonic waves. From the LDV, a series of scanning points are selected which serves as the phased array elements. The side-drilled hole of 10 mm diameter with a depth of 25 mm has been introduced and the defect is interrogated by the linear array of scanning points obtained from the LDV. With the aid of the Synthetic Aperture Focusing Technique (SAFT) algorithm, based on the time-shifting principle the inspected images are generated from the A-scan data acquired from the 1-D linear phased array elements. Thus the defect can be precisely detected with good resolution.Keywords: laser ultrasonics, linear phased array, nondestructive testing, synthetic aperture focusing technique, ultrasonic imaging
Procedia PDF Downloads 1242482 Continuous Functions Modeling with Artificial Neural Network: An Improvement Technique to Feed the Input-Output Mapping
Authors: A. Belayadi, A. Mougari, L. Ait-Gougam, F. Mekideche-Chafa
Abstract:
The artificial neural network is one of the interesting techniques that have been advantageously used to deal with modeling problems. In this study, the computing with artificial neural network (CANN) is proposed. The model is applied to modulate the information processing of one-dimensional task. We aim to integrate a new method which is based on a new coding approach of generating the input-output mapping. The latter is based on increasing the neuron unit in the last layer. Accordingly, to show the efficiency of the approach under study, a comparison is made between the proposed method of generating the input-output set and the conventional method. The results illustrated that the increasing of the neuron units, in the last layer, allows to find the optimal network’s parameters that fit with the mapping data. Moreover, it permits to decrease the training time, during the computation process, which avoids the use of computers with high memory usage.Keywords: neural network computing, continuous functions generating the input-output mapping, decreasing the training time, machines with big memories
Procedia PDF Downloads 2742481 Effect of Locally Injected Mesenchymal Stem Cells on Bone Regeneration of Rat Calvaria Defects
Authors: Gileade P. Freitas, Helena B. Lopes, Alann T. P. Souza, Paula G. F. P. Oliveira, Adriana L. G. Almeida, Paulo G. Coelho, Marcio M. Beloti, Adalberto L. Rosa
Abstract:
Bone tissue presents great capacity to regenerate when injured by trauma, infectious processes, or neoplasia. However, the extent of injury may exceed the inherent tissue regeneration capability demanding some kind of additional intervention. In this scenario, cell therapy has emerged as a promising alternative to treat challenging bone defects. This study aimed at evaluating the effect of local injection of bone marrow-derived mesenchymal stem cells (BM-MSCs) and adipose tissue-derived mesenchymal stem cells (AT-MSCs) on bone regeneration of rat calvaria defects. BM-MSCs and AT-MSCs were isolated and characterized by expression of surface markers; cell viability was evaluated after injection through a 21G needle. Defects of 5 mm in diameter were created in calvaria and after two weeks a single injection of BM-MSCs, AT-MSCs or vehicle-PBS without cells (Control) was carried out. Cells were tracked by bioluminescence and at 4 weeks post-injection bone formation was evaluated by micro-computed tomography (μCT) and histology, nanoindentation, and through gene expression of bone remodeling markers. The data were evaluated by one-way analysis of variance (p≤0.05). BM-MSCs and AT-MSCs presented characteristics of mesenchymal stem cells, kept viability after passing through a 21G needle and remained in the defects until day 14. In general, injection of both BM-MSCs and AT-MSCs resulted in higher bone formation compared to Control. Additionally, this bone tissue displayed elastic modulus and hardness similar to the pristine calvaria bone. The expression of all evaluated genes involved in bone formation was upregulated in bone tissue formed by BM-MSCs compared to AT-MSCs while genes involved in bone resorption were upregulated in AT-MSCs-formed bone. We show that cell therapy based on the local injection of BM-MSCs or AT-MSCs is effective in delivering viable cells that displayed local engraftment and induced a significant improvement in bone healing. Despite differences in the molecular cues observed between BM-MSCs and AT-MSCs, both cells were capable of forming bone tissue at comparable amounts and properties. These findings may drive cell therapy approaches toward the complete bone regeneration of challenging sites.Keywords: cell therapy, mesenchymal stem cells, bone repair, cell culture
Procedia PDF Downloads 1762480 Neural Network Based Approach of Software Maintenance Prediction for Laboratory Information System
Authors: Vuk M. Popovic, Dunja D. Popovic
Abstract:
Software maintenance phase is started once a software project has been developed and delivered. After that, any modification to it corresponds to maintenance. Software maintenance involves modifications to keep a software project usable in a changed or a changing environment, to correct discovered faults, and modifications, and to improve performance or maintainability. Software maintenance and management of software maintenance are recognized as two most important and most expensive processes in a life of a software product. This research is basing the prediction of maintenance, on risks and time evaluation, and using them as data sets for working with neural networks. The aim of this paper is to provide support to project maintenance managers. They will be able to pass the issues planned for the next software-service-patch to the experts, for risk and working time evaluation, and afterward to put all data to neural networks in order to get software maintenance prediction. This process will lead to the more accurate prediction of the working hours needed for the software-service-patch, which will eventually lead to better planning of budget for the software maintenance projects.Keywords: laboratory information system, maintenance engineering, neural networks, software maintenance, software maintenance costs
Procedia PDF Downloads 3472479 A Genetic-Neural-Network Modeling Approach for Self-Heating in GaN High Electron Mobility Transistors
Authors: Anwar Jarndal
Abstract:
In this paper, a genetic-neural-network (GNN) based large-signal model for GaN HEMTs is presented along with its parameters extraction procedure. The model is easy to construct and implement in CAD software and requires only DC and S-parameter measurements. An improved decomposition technique is used to model self-heating effect. Two GNN models are constructed to simulate isothermal drain current and power dissipation, respectively. The two model are then composed to simulate the drain current. The modeling procedure was applied to a packaged GaN-on-Si HEMT and the developed model is validated by comparing its large-signal simulation with measured data. A very good agreement between the simulation and measurement is obtained.Keywords: GaN HEMT, computer-aided design and modeling, neural networks, genetic optimization
Procedia PDF Downloads 3752478 Blood Flow in Stenosed Arteries: Analytical and Numerical Study
Authors: Shashi Sharma, Uaday Singh, V. K. Katiyar
Abstract:
Blood flow through a stenosed tube, which is of great interest to mechanical engineers as well as medical researchers. If stenosis exists in an artery, normal blood flow is disturbed. The deposition of fatty substances, cholesterol, cellular waste products in the inner lining of an artery results to plaque formation .The present study deals with a mathematical model for blood flow in constricted arteries. Blood is considered as a Newtonian, incompressible, unsteady and laminar fluid flowing in a cylindrical rigid tube along the axial direction. A time varying pressure gradient is applied in the axial direction. An analytical solution is obtained using the numerical inversion method for Laplace Transform for calculating the velocity profile of fluid as well as particles.Keywords: blood flow, stenosis, Newtonian fluid, medical biology and genetics
Procedia PDF Downloads 5112477 Experimental Study and Analysis of Parabolic Trough Collector with Various Reflectors
Authors: Avadhesh Yadav, Balram Manoj Kumar
Abstract:
A solar powered air heating system using parabolic trough collector was experimentally investigated. In this experimental setup, the reflected solar radiations were focused on absorber tube which was placed at focal length of the parabolic trough. In this setup, air was used as working fluid which collects the heat from absorber tube. To enhance the performance of parabolic trough, collector with different type of reflectors were used. It was observed for aluminum sheet maximum temperature is 52.3ºC, which 24.22% more than steel sheet as reflector and 8.5% more than aluminum foil as reflector, also efficiency by using Aluminum sheet as reflector compared to steel sheet as reflector is 61.18% more. Efficiency by using aluminum sheet as reflector compared to aluminum foil as reflector is 18.98% more.Keywords: parabolic trough collector, reflectors, air flow rates, solar power, aluminum sheet
Procedia PDF Downloads 3542476 New Neuroplasmonic Sensor Based on Soft Nanolithography
Authors: Seyedeh Mehri Hamidi, Nasrin Asgari, Foozieh Sohrabi, Mohammad Ali Ansari
Abstract:
New neuro plasmonic sensor based on one dimensional plasmonic nano-grating has been prepared. To record neural activity, the sample has been exposed under different infrared laser and then has been calculated by ellipsometry parameters. Our results show that we have efficient sensitivity to different laser excitation.Keywords: neural activity, Plasmonic sensor, Nanograting, Gold thin film
Procedia PDF Downloads 391