Search results for: neural tube defect

Authors: Tao Peng, Jing Zhao, Yanqing Xu, Jing Cai

Abstract:

Due to missing/ambiguous boundaries between the prostate and neighboring structures, the presence of shadow artifacts, as well as the large variability in prostate shapes, ultrasound prostate segmentation is challenging. To handle these issues, this paper develops a hybrid method for ultrasound prostate segmentation by combining an optimized closed principal curve-based method and the evolutionary neural network; the former can fit curves with great curvature and generate a contour composed of line segments connected by sorted vertices, and the latter is used to express an appropriate map function (represented by parameters of evolutionary neural network) for generating the smooth prostate contour to match the ground truth contour. Both qualitative and quantitative experimental results showed that our proposed method obtains accurate and robust performances.

Keywords: ultrasound prostate segmentation, optimized closed polygonal segment method, evolutionary neural network, smooth mathematical model, principal curve

Procedia PDF Downloads 204

Authors: Galal H. Senussi, Muamar Benisa, Sanja Vasin

Abstract:

In our business field today, one of the most important issues for any enterprises is cost minimization and profit maximization. Second issue is how to develop a strong and capable model that is able to give us desired forecasting of these two issues. Many researches deal with these issues using different methods. In this study, we developed a model for multi-criteria production program optimization, integrated with Artificial Neural Network. The prediction of the production cost and profit per unit of a product, dealing with two obverse functions at same time can be extremely difficult, especially if there is a great amount of conflict information about production parameters. Feed-Forward Neural Networks are suitable for generalization, which means that the network will generate a proper output as a result to input it has never seen. Therefore, with small set of examples the network will adjust its weight coefficients so the input will generate a proper output. This essential characteristic is of the most important abilities enabling this network to be used in variety of problems spreading from engineering to finance etc. From our results as we will see later, Feed-Forward Neural Networks has a strong ability and capability to map inputs into desired outputs.

Keywords: project profitability, multi-objective optimization, genetic algorithm, Pareto set, neural networks

Procedia PDF Downloads 446

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 547

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 138

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 191

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 90

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 94

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 125

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 164

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 109

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 599

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 406

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 516

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 362

Authors: M. A. Pawar, C. S. Patil

Abstract:

Investigations were carried out to evaluate the persistent toxicity of imidacloprid, thiamethoxam and dimethoate to Aphis gossypii and Amrasca biguttula biguttula under laboratory condition during 2012. The experiment was conducted in a completely randomized block design with three replications in the glass house of department of Entomology M. P. K. V. Rahuri. Okra plants were raised in glass house following all recommended agronomic practices. The 21 days old plants were used for assessing the effect of insecticides on aphids and jassids. The insecticides were diluted with distilled water to make desired concentrations and used for foliar application. The insecticides included in the study were imidacloprid 17.8 SL, imidacloprid 70 WG, thiamethoxam 25 WG and dimethoate 30 EC. Untreated check was maintained by spraying with distilled water. The mortality of aphids and jassids on treated leaf were recorded at 1, 3, 5, 7, 9, 11, 13, 15, 17, 21, and 25 days after spray till zero per cent mortality observed for each treatment. Treated leaves from the glasshouse were brought to laboratory and were put in tube with moist cotton swab at the bottom of leaf and sucking apparatus was fit to the tube. Ten jassids were sucked in each tube from the plants in the field. Evaluated insecticides differed in their persistence and index of persistence toxicity against both insects of different treatments. Recommended dose of imidacloprid (25 g a.i/ha) persisted for 21 days against both aphids and jassids. However dimethoate, a conventional insecticide persisted for 11 days.

Keywords: Amrasca biguttula biguttula, Aphis gossypii, imidacloprid, persistent toxicity

Procedia PDF Downloads 192

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 383

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 262

Authors: Bryce R. Jolley, Michael Uchic

Abstract:

This study presents initial results toward the correlative characterization of inherent defects of Ti-6Al-4V additive manufacture (AM). X-Ray Computed Tomography (CT) defect data are compared and correlated with microscopic photographs obtained via automated serial sectioning. The metal AM specimen was manufactured out of Ti-6Al-4V virgin powder to specified dimensions. A post-contour was applied during the fabrication process with a speed of 1050 mm/s, power of 260 W, and a width of 140 µm. The specimen was stress relief heat-treated at 16°F for 3 hours. Microfocus CT imaging was accomplished on the specimen within a predetermined region of the build. Microfocus CT imaging was conducted with parameters optimized for Ti-6Al-4V additive manufacture. After CT imaging, a modified RoboMet. 3D version 2 was employed for serial sectioning and optical microscopy characterization of the same predetermined region. Automated montage capture with sub-micron resolution, bright-field reflection, 12-bit monochrome optical images were performed in an automated fashion. These optical images were post-processed to produce 2D and 3D data sets. This processing included thresholding and segmentation to improve visualization of defect features. The defects observed from optical imaging were compared and correlated with the defects observed from CT imaging over the same predetermined region of the specimen. Quantitative results of area fraction and equivalent pore diameters obtained via each method are presented for this correlation. It is shown that Microfocus CT imaging does not capture all inherent defects within this Ti-6Al-4V AM sample. Best practices for this correlative effort are also presented as well as the future direction of research resultant from this current study.

Keywords: additive manufacture, automated serial sectioning, computed tomography, nondestructive evaluation

Procedia PDF Downloads 141

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 497

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 454

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 156

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 387

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 283

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 360

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 384

Authors: Matt Stichter

Abstract:

Moral development requires learning from one’s failures, but that turnsout to be especially challenging when dealing with moral failures. The distress prompted by moral failure can cause responses ofdefensiveness or disengagement rather than attempts to make amends and work on self-change. The most potentially distressing response to moral failure is a shame. However, there appears to be two different senses of “shame” that are conflated in the literature, depending on whether the failure is appraised as the result of a global and unalterable self-defect, or a local and alterable self-defect. One of these forms of shame does prompt self-improvement in response to moral failure. This occurs if one views the failure as indicating only a specific (local) defect in one’s identity, where that’s something repairable, rather than asanoverall(orglobal)defectinyouridentity that can’t be fixed. So, if the whole of one’s identity as a morally good person isn’t being called into question, but only a part, then that is something one could work on to improve. Shame, in this sense, provides motivation for self-improvement to fix this part oftheselfinthe long run, and this would be important for moral development. One factor that looks to affect these different self-attributions in the wake of moral failure can be found in mindset theory, as reactions to moral failure in these two forms of shame are similar to how those with a fixed or growth mindset of their own abilities, such as intelligence, react to failure. People fall along a continuum with respect to how they view abilities – it is more of a fixed entity that you cannot do much to change, or it is malleable such that you can train to improve it. These two mindsets, ‘fixed’ versus ‘growth’, have different consequences for how we react to failure – a fixed mindset leads to maladaptive responses because of feelings of helplessness to do better; whereas a growth mindset leads to adaptive responses where a person puts forth effort to learn how to act better the next time. Here we can see the parallels between a fixed mindset of one’s own (im)morality, as the way people respond to shame when viewed as indicating a global and unalterable self-defect parallels the reactions people have to failure when they have a fixed mindset. In addition, it looks like there may be a similar structure to pride. Pride is, like shame, a self-conscious emotion that arises from internal attributions about the self as being the cause of some event. There are also paradoxical results from research on pride, where pride was found to motivate pro-social behavior in some cases but aggression in other cases. Research suggests that there may be two forms of pride, authentic and hubristic, that are also connected to different self-attributions, depending on whether one is feeling proud about a particular (local) aspect of the self versus feeling proud about the whole of oneself (global).

Keywords: emotion, mindset, moral development, moral psychology, pride, shame, self-regulation

Procedia PDF Downloads 108

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 400

Authors: Sirilak Areerachakul, Nat Ployong, Supayothin Na Songkla

Abstract:

This research’s objective is to select the model with most accurate value by using Neural Network Technique as a way to filter potential students who enroll in IT course by electronic learning at Suan Suanadha Rajabhat University. It is designed to help students selecting the appropriate courses by themselves. The result showed that the most accurate model was 100 Folds Cross-validation which had 73.58% points of accuracy.

Keywords: artificial neural network, classification, students, e-learning

Procedia PDF Downloads 427

Authors: Pitchaporn Purngpiputtrakul, Suttasinee Petsakul, Sunisa Chatmongkolchart

Abstract:

Nasogastric tube (NGT) insertion in anaesthetized and intubated patients can be challenging even for experienced anesthesiologists. Various techniques have been proposed to facilitate NGT insertion in these patients. This study aimed to compare the success rate and time required for NGT insertion between the GlideScope visualization and neck flexion with lateral neck pressure techniques. This randomized clinical trial was performed at a teaching hospital on 86 adult patients undergoing abdominal surgery under relaxant general anaesthesia who required intraoperative NGT insertion. The patients were randomized into two groups, the GlideScope group (group G) and the neck flexion with lateral neck pressure group (group F). The success rate of first and second attempts, duration of insertion, and complications were recorded. The total success rate was 79.1% in Group G compared with 76.7% in Group F (P=1) The median time required for NGT insertion was significantly longer in Group G, for both first and second attempts (97 vs 42 seconds P<0.001) and (70 vs 48.5 seconds P=0.015), respectively. Complications were reported in 23 patients (53.5%) in group G and 13 patients (30.2%) in group F. Bleeding and kinking were the most common complications in both techniques. Using GlideScope visualization to facilitate NGT insertion was comparable to neck flexion with lateral neck pressure technique in degree of success rate of insertion, while neck flexion with lateral neck pressure technique had fewer complications and was less time-consuming.

Keywords: anaesthesia, nasogastric tube, GlideScope, intubation

Procedia PDF Downloads 165

Authors: Ashkan Zakaryazad, Ekrem Duman

Abstract:

A typical classification technique ranks the instances in a data set according to the likelihood of belonging to one (positive) class. A credit card (CC) fraud detection model ranks the transactions in terms of probability of being fraud. In fact, this approach is often criticized, because firms do not care about fraud probability but about the profitability or costliness of detecting a fraudulent transaction. The key contribution in this study is to focus on the profit maximization in the model building step. The artificial neural network proposed in this study works based on profit maximization instead of minimizing the error of prediction. Moreover, some studies have shown that the back propagation algorithm, similar to other gradient–based algorithms, usually gets trapped in local optima and swarm-based algorithms are more successful in this respect. In this study, we train our profit maximization ANN using the Migrating Birds optimization (MBO) which is introduced to literature recently.

Keywords: neural network, profit-based neural network, sum of squared errors (SSE), MBO, gradient descent

Procedia PDF Downloads 475