Search results for: neural tube defects

Authors: Devendra Gupta, S. P. Ambesh, P. K Singh

Abstract:

Introduction: Minimally invasive coronary artery bypass grafting (MICABG) is a less invasive method of performing surgical revascularization. Minimally invasive direct coronary artery bypass (MIDCAB) provides many anesthetic challenges including one lung ventilation (OLV), managing myocardial ischemia, and pain. We present an early and midterm result of the use of this technique with OLV. Method: We enrolled 62 patients for analysis operated between 2008 and 2012. Patients were anesthetized and left endobronchial tube was placed. During the procedure left lung was isolated and one lung ventilation was maintained through right lung. Operation was performed utilizing off pump technique of coronary artery bypass grafting through a minimal invasive incision. Left internal mammary artery graft was done for single vessel disease and radial artery was utilized for other grafts if required. Postoperative ventilation was done with single lumen endotracheal tube. Median follow-up is 2.5 years (6 months to 4 years). Results: Median age was 58.5 years (41-77) and all were male. Single vessel disease was present in 36, double vessel in 24 and triple vessel disease in 2 patients. All the patients had normal left ventricular size and function. In 2 cases difficulty were encounter in placement of endobronchial tube. In 1 case cuff of endobronchial tube was ruptured during intubation. High airway pressure was developed on OLV in 1 case and surgery was accomplished with two lung anesthesia with low tidal volume. Mean postoperative ventilation time was 14.4 hour (11-22). There was no perioperative and 30 day mortality. Conversion to median sternotomy to complete the operation was done in 3.23% (2 out of 62 patients). One patient had acute myocardial infarction postoperatively and there were no deaths during follow-up. Conclusion: MICABG is a safe and effective method of revascularization with OLV in low risk candidates for coronary artery bypass grafting.

Keywords: MIDCABG, one lung ventilation, coronary artery bypass grafting, endobronchial tube

Procedia PDF Downloads 425

Authors: A. N. Dagang, E. I. Ismail, Z. Zakaria

Abstract:

This paper presents the analysis on the performance of monopole antenna with fluorescent tubes. In this research, the simulation and experimental approach is conducted. The fluorescent tube with different length and size is designed using Computer Simulation Technology (CST) software and the characteristics of antenna parameter are simulated throughout the software. CST was used to simulate antenna parameters such as return loss, resonant frequency, gain and directivity. Vector Network Analyzer (VNA) was used to measure the return loss of plasma antenna in order to validate the simulation results. In the simulation and experiment, the supply frequency is set starting from 1 GHz to 10 GHz. The results show that the return loss of plasma antenna changes when size of fluorescent tubes is varied, correspond to the different plasma properties. It shows that different values of plasma properties such as plasma frequency and collision frequency gives difference result of return loss, gain and directivity. For the gain, the values range from 2.14 dB to 2.36 dB. The return loss of plasma antenna offers higher value range from -22.187 dB to -32.903 dB. The higher the values of plasma frequency and collision frequency, the higher return loss can be obtained. The values obtained are comparative to the conventional type of metal antenna.

Keywords: plasma antenna, fluorescent tube, CST, plasma parameters

Procedia PDF Downloads 387

Authors: Frank Kuebler, Rolf Steinhilper

Abstract:

Artificial neural networks (ANN) as well as Design of Experiments (DOE) based regression analysis (RA) are mainly used for modeling of complex systems. Both methodologies are commonly applied in process and quality control of manufacturing processes. Due to the fact that resource efficiency has become a critical concern for manufacturing companies, these models needs to be extended to predict resource-consumption of manufacturing processes. This paper describes an approach to use neural networks as well as DOE based regression analysis for predicting resource consumption of manufacturing processes and gives a comparison of the achievable results based on an industrial case study of a turning process.

Keywords: artificial neural network, design of experiments, regression analysis, resource efficiency, manufacturing process

Procedia PDF Downloads 524

Authors: Nasrin Bakhshizadeh, Ashkan Forootan

Abstract:

A major problem that affects the quality control of polymer in the industrial polymerization is the lack of suitable on-line measurement tools to evaluate the properties of the polymer such as melt and density indices. Controlling the polymerization in ordinary method is performed manually by taking samples, measuring the quality of polymer in the lab and registry of results. This method is highly time consuming and leads to producing large number of incompatible products. An online application for estimating melt index and density proposed in this study is a neural network based on the input-output data of the polyethylene production plant. Temperature, the level of reactors' bed, the intensity of ethylene mass flow, hydrogen and butene-1, the molar concentration of ethylene, hydrogen and butene-1 are used for the process to establish the neural model. The neural network is taught based on the actual operational data and back-propagation and Levenberg-Marquart techniques. The simulated results indicate that the neural network process model established with three layers (one hidden layer) for forecasting the density and the four layers for the melt index is able to successfully predict those quality properties.

Keywords: polyethylene, polymerization, density, melt index, neural network

Procedia PDF Downloads 144

Authors: K. R. Guna, Aldin Justin Sundararaj, B. C. Pillai, A. N. Subash

Abstract:

A systematic study has been made for ignition delay times measurement behind a reflected shock wave for the low molecular weight hydrocarbon fuel in argon simulated gas mixtures. The low molecular hydrocarbon fuel–oxygen was diluted with argon for desired concentration is taken for the study. The suitability of the shock tube for measuring the ignition delay time is demonstrated by measuring the ignition delay for the liquefied petroleum gas for equivalence ratios (ф=0.5 & 1) in the temperature range 1150-1650 K. The pressure range was fixed from 5-15 bar. The ignition delay was measured by recording the ignition-induced pressure jump and emission from CH radical simultaneously. From conducting experiments, it was found that the ignition delay time for liquefied petroleum gas reduces with increase in temperature. The shock tube was calibrated for ethane-oxygen gas mixture and the results obtained from this study is compared with the earlier reported values and found to be comparably well suited for the measurement of ignition delay times. The above work was carried out using the shock tube facility at propulsion and high enthalpy laboratory, Karunya University.

Keywords: ignition delay, LPG, reflected shock, shock wave

Procedia PDF Downloads 252

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 231

Authors: Z. Zerdoumi, D. Benatia, , D. Chicouche

Abstract:

This paper investigates the application of artificial neural network to the problem of nonlinear channel equalization. The difficulties caused by channel distortions such as inter symbol interference (ISI) and nonlinearity can overcome by nonlinear equalizers employing neural networks. It has been shown that multilayer perceptron based equalizer outperform significantly linear equalizers. We present a multilayer perceptron based equalizer with decision feedback (MLP-DFE) trained with the back propagation algorithm. The capacity of the MLP-DFE to deal with nonlinear channels is evaluated. From simulation results it can be noted that the MLP based DFE improves significantly the restored signal quality, the steady state mean square error (MSE), and minimum Bit Error Rate (BER), when comparing with its conventional counterpart.

Keywords: Artificial Neural Network, signal restoration, Nonlinear Channel equalization, equalization

Procedia PDF Downloads 496

Authors: Sello Mokwena, Monyepao Thabang

Abstract:

In this study, we propose a comprehensive approach to address the challenges in person re-identification models. By combining a centroid tracking algorithm with a Siamese convolutional neural network model, our method excels in detecting, tracking, and capturing robust person features across non-overlapping camera views. The algorithm efficiently identifies individuals in the camera network, while the neural network extracts fine-grained global features for precise cross-image comparisons. The approach's effectiveness is further accentuated by leveraging the camera network topology for guidance. Our empirical analysis on benchmark datasets highlights its competitive performance, particularly evident when background subtraction techniques are selectively applied, underscoring its potential in advancing person re-identification techniques.

Keywords: camera network, convolutional neural network topology, person tracking, person re-identification, siamese

Procedia PDF Downloads 72

Authors: Bhrugesh Radadiya, Jaydeep Shah

Abstract:

In Indian foundry industry, there is a need of defect free casting with minimum production cost in short lead time. Casting defect is a very large issue in foundry shop which increases the rejection rate of casting and wastage of materials. The various parameters influences on casting process such as mold machine related parameters, green sand related parameters, cast metal related parameters, mold related parameters and shake out related parameters. The mold related parameters are most influences on casting defects in sand casting process. This paper review the casting produced by foundry with shrinkage and blow holes as a major defects was analyzed and identified that mold related parameters such as mold temperature, pouring temperature and runner size were not properly set in sand casting process. These parameters were optimized using different optimization techniques such as Taguchi method, Response surface methodology, Genetic algorithm and Teaching-learning based optimization algorithm. Finally, concluded that a Teaching-learning based optimization algorithm give better result than other optimization techniques.

Keywords: casting defects, genetic algorithm, parametric optimization, Taguchi method, TLBO algorithm

Procedia PDF Downloads 728

Authors: S. M. Anowarul Haque, Md. Asiful Islam

Abstract:

Electrical load forecasting is considered to be one of the most indispensable parts of a modern-day electrical power system. To ensure a reliable and efficient supply of electric energy, special emphasis should have been put on the predictive feature of electricity supply. Artificial Neural Network-based approaches have emerged to be a significant area of interest for electric load forecasting research. This paper proposed an Artificial Neural Network model based on the particle swarm optimization algorithm for improved electric load forecasting for Mymensingh, Bangladesh. The forecasting model is developed and simulated on the MATLAB environment with a large number of training datasets. The model is trained based on eight input parameters including historical load and weather data. The predicted load data are then compared with an available dataset for validation. The proposed neural network model is proved to be more reliable in terms of day-wise load forecasting for Mymensingh, Bangladesh.

Keywords: load forecasting, artificial neural network, particle swarm optimization

Procedia PDF Downloads 171

Authors: P. D. Pastuszak

Abstract:

The present work is devoted to thermographic studies of curved composite panels (unidirectional GFRP) with subsurface defects. Various artificial defects, created by inserting PTFE stripe between individual layers of a laminate during manufacturing stage are studied. The analysis is conducted both with the use finite element method and experiments. To simulate transient heat transfer in 3D model with embedded various defect sizes, the ANSYS package is used. Pulsed Thermography combined with optical excitation source provides good results for flat surfaces. Composite structures are mostly used in complex components, e.g., pipes, corners and stiffeners. Local decrease of mechanical properties in these regions can have significant influence on strength decrease of the entire structure. Application of active procedures of thermography to defect detection and evaluation in this type of elements seems to be more appropriate that other NDT techniques. Nevertheless, there are various uncertainties connected with correct interpretation of acquired data. In this paper, important factors concerning Infrared Thermography measurements of curved surfaces in the form of cylindrical panels are considered. In addition, temperature effects on the surface resulting from complex geometry and embedded and real defect are also presented.

Keywords: active thermography, composite, curved structures, defects

Procedia PDF Downloads 319

Authors: Lu-Chen Yeh‚ Jui-Ming Yeh

Abstract:

In this manuscript, we produced neat electrospun poly(o-methoxyaniline) (POMA) fibers and utilized it for applying the growth of neural stem cells. The transparency and morphology of as-prepared POMA fibers were characterized by UV-visible spectroscopy and scanning electron microscopy, respectively. It was found to have no adverse effects on the long-term proliferation of the neural stem cells (NSCs), retained the ability to self-renew, and exhibit multi-potentiality. Results of immunofluorescence staining studies confirmed that POMA electrospun fibers could provide a great environment for NSCs and enhance its differentiation.

Keywords: electrospun, polyaniline, neural stem cell, differentiation

Procedia PDF Downloads 410

Authors: Osama Elsarrar, Marjorie Darrah, Richard Devin

Abstract:

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

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

Procedia PDF Downloads 172

Authors: Tatiana A. Dolenko, Sergey A. Burikov, Alexander O. Efitorov, Sergey A. Dolenko

Abstract:

In this study, a comparative analysis of the approaches associated with the use of neural network algorithms for effective solution of a complex inverse problem – the problem of identifying and determining the individual concentrations of inorganic salts in multicomponent aqueous solutions by the spectra of Raman scattering of light – is performed. It is shown that application of artificial neural networks provides the average accuracy of determination of concentration of each salt no worse than 0.025 M. The results of comparative analysis of input data compression methods are presented. It is demonstrated that use of uniform aggregation of input features allows decreasing the error of determination of individual concentrations of components by 16-18% on the average.

Keywords: inverse problems, multi-component solutions, neural networks, Raman spectroscopy

Procedia PDF Downloads 528

Authors: Qianying Sun, Abdelhadi Kassiba, Guorong Li

Abstract:

ZnO with wurtzite structure is a well-known semiconducting oxide (SCO), being applied in thermoelectric devices, varistors, gas sensors, transparent electrodes, solar cells, liquid crystal displays, piezoelectric and electro-optical devices. Intrinsically, ZnO is weakly n-type SCO due to native defects (Znⱼ, Vₒ). However, the substitutional doping by metallic elements as (Al, Ti) gives rise to a high n-type conductivity ensured by donor centers. Under CO+N₂ sintering atmosphere, Schottky barriers of ZnO ceramics will be suppressed by lowering the concentration of acceptors at grain boundaries and then inducing a large increase in the Hall mobility, thereby increasing the conductivity. The presented work concerns ZnO based ceramics, which are fabricated with doping by TiO₂ (0.50mol%), Al₂O₃ (0.25mol%) and MgO (1.00mol%) and sintering in different atmospheres (Air (A), N₂ (N), CO+N₂(C)). We obtained uniform, dense ceramics with ZnO as the main phase and Zn₂TiO₄ spinel as a secondary and minor phase. An important increase of the conductivity was shown for the samples A, N, and C which were sintered under different atmospheres. The highest conductivity (σ = 1.52×10⁵ S·m⁻¹) was obtained under the reducing atmosphere (CO). The role of doping was investigated with the aim to identify the local environment and valence states of the doping elements. Thus, Electron paramagnetic spectroscopy (EPR) determines the concentration of defects and the effects of charge carriers in ZnO ceramics as a function of the sintering atmospheres. The relation between conductivity and defects concentration shows the opposite behavior between these parameters suggesting that defects act as traps for charge carriers. For Al ions, nuclear magnetic resonance (NMR) technique was used to identify the involved local coordination of these ions. Beyond the six and forth coordinated Al, an additional NMR signature of ZnO based TCO requires analysis taking into account the grain boundaries and the conductivity through the Knight shift effects. From the thermal evolution of the conductivity as a function of the sintering atmosphere, we succeed in defining the conditions to realize ZnO based TCO ceramics with an important thermal coefficient of resistance (TCR) which is promising for electrical safety of devices.

Keywords: ceramics, conductivity, defects, TCO, ZnO

Procedia PDF Downloads 196

Authors: Subodh N. Patel, Abhijit Pusty, Manashi Adhikary, Sandip Bhattacharyya

Abstract:

The steam superheater (SH) is a coil type heat exchanger which is used to produce superheated steam or to convert the wet steam to dry steam (69.6 kg/cm² and 495°C), generated by a boiler. There were two superheaters in the system, SH I and SH II. SH II is a set of tubes that faces the initial interaction with flue gas at high temperature followed by SH I tubes. After a service life of 2100 hours, a tube in the SH II found to be punctured. Dye penetrant test revealed that out of 50 such tubes, 14 more tubes had severe cracks at a similar location. The failure was investigated in detail. The materials and scale were characterized by optical microscope and advance characterization technique. Scale, observed on fracture surface, was characterized under scanning electron microscope and Raman spectroscopy. Stresses acting on the tubes in working condition were analyzed by finite element method software, ANSYS. Cyclic stresses were observed in the simulation at the same prone location due to restriction in expansion of tubes. Based on scale characterization and stress analysis, it was concluded that the tube failed in thermo-mechanical fatigue. Finally, prevention and control measures were taken to avoid such failure in the future.

Keywords: finite element analysis, oxide scale, superheater tube, thermomechanical fatigue

Procedia PDF Downloads 117

Authors: Po-Jen Chen, Jian-Jiun Ding, Hung-Wei Hsu, Chien-Yao Wang, Jia-Ching Wang

Abstract:

A more accurate scene classification algorithm using label relations and the hierarchy neural network was developed in this work. In many classification algorithms, it is assumed that the labels are mutually exclusive. This assumption is true in some specific problems, however, for scene classification, the assumption is not reasonable. Because there are a variety of objects with a photo image, it is more practical to assign multiple labels for an image. In this paper, two label relations, which are exclusive relation and hierarchical relation, were adopted in the classification process to achieve more accurate multiple label classification results. Moreover, the hierarchy neural network (hierarchy NN) is applied to classify the image and the directed acyclic graph structure is used for predicting a more reasonable result which obey exclusive and hierarchical relations. Simulations show that, with these techniques, a much more accurate scene classification result can be achieved.

Keywords: convolutional neural network, label relation, hierarchy neural network, scene classification

Procedia PDF Downloads 458

Authors: O. Afshar

Abstract:

A solar receiver is designed for operation under extremely uneven heat flux distribution, cyclic weather, and cloud transient cycle conditions, which can include large thermal stress and even receiver failure. In this study, the effect of different oil velocity on convection coefficient factor and impact of wind velocity on local Nusselt number by Finite Volume Method will be analyzed. This study is organized to give an overview of the numerical modeling using a MATLAB software, as an accurate, time efficient and economical way of analyzing the heat transfer trends over stationary receiver tube for different Reynolds number. The results reveal when oil velocity is below 0.33m/s, the value of convection coefficient is negligible at low temperature. The numerical graphs indicate that when oil velocity increases up to 1.2 m/s, heat convection coefficient increases significantly. In fact, a reduction in oil velocity causes a reduction in heat conduction through the glass envelope. In addition, the different local Nusselt number is reduced when the wind blows toward the concave side of the collector and it has a significant effect on heat losses reduction through the glass envelope.

Keywords: receiver tube, heat convection, heat conduction, Nusselt number

Procedia PDF Downloads 356

Authors: Emad Amar, Tawfik Khattab, Fatma Zada

Abstract:

Predicting earthquakes is an important issue in the study of geography. Accurate prediction of earthquakes can help people to take effective measures to minimize the loss of personal and economic damage, such as large casualties, destruction of buildings and broken of traffic, occurred within a few seconds. United States Geological Survey (USGS) science organization provides reliable scientific information of Earthquake Existed throughout history & Preliminary database from the National Center Earthquake Information (NEIC) show some useful factors to predict an earthquake in a seismic area like Aleutian Arc in the U.S. state of Alaska. The main advantage of this prediction method that it does not require any assumption, it makes prediction according to the future evolution of object's time series. The article compares between simulation data result from trained BP and RBF neural network versus actual output result from the system calculations. Therefore, this article focuses on analysis of data relating to real earthquakes. Evaluation results show better accuracy and higher speed by using radial basis functions (RBF) neural network.

Keywords: BP neural network, prediction, RBF neural network, earthquake

Procedia PDF Downloads 496

Authors: Mohamed Aymen Slim, Afef Abdelkrim, Mohamed Benrejeb

Abstract:

The handwriting is a physical demonstration of a complex cognitive process learnt by man since his childhood. People with disabilities or suffering from various neurological diseases are facing so many difficulties resulting from problems located at the muscle stimuli (EMG) or signals from the brain (EEG) and which arise at the stage of writing. The handwriting velocity of the same writer or different writers varies according to different criteria: age, attitude, mood, writing surface, etc. Therefore, it is interesting to reconstruct an experimental basis records taking, as primary reference, the writing speed for different writers which would allow studying the global system during handwriting process. This paper deals with a new approach of the handwriting system modeling based on the velocity criterion through the concepts of artificial neural networks, precisely the Radial Basis Functions (RBF) neural networks. The obtained simulation results show a satisfactory agreement between responses of the developed neural model and the experimental data for various letters and forms then the efficiency of the proposed approaches.

Keywords: Electro Myo Graphic (EMG) signals, experimental approach, handwriting process, Radial Basis Functions (RBF) neural networks, velocity modeling

Procedia PDF Downloads 440

Authors: Svitov David, Alyamkin Sergey

Abstract:

The usage of convolutional neural networks (CNNs) in conjunction with the margin-based softmax approach demonstrates the state-of-the-art performance for the face recognition problem. Recently, lightweight neural network models trained with the margin-based softmax have been introduced for the face identification task for edge devices. In this paper, we propose a distillation method for lightweight neural network architectures that outperforms other known methods for the face recognition task on LFW, AgeDB-30 and Megaface datasets. The idea of the proposed method is to use class centers from the teacher network for the student network. Then the student network is trained to get the same angles between the class centers and face embeddings predicted by the teacher network.

Keywords: ArcFace, distillation, face recognition, margin-based softmax

Procedia PDF Downloads 146

Authors: S. Mousavian, D. Ashouri, F. Mousavian, V. Nikkhah Rashidabad, N. Ghazinia

Abstract:

PH, temperature, and time of extraction of each stage, agitation speed, and delay time between stages effect on efficiency of zinc extraction from concentrate. In this research, efficiency of zinc extraction was predicted as a function of mentioned variable by artificial neural networks (ANN). ANN with different layer was employed and the result show that the networks with 8 neurons in hidden layer has good agreement with experimental data.

Keywords: zinc extraction, efficiency, neural networks, operating condition

Procedia PDF Downloads 545

Authors: Frankie Burgos, Emely Munar, Conrado Basa

Abstract:

This paper aimed at developing an artificial neural network (ANN) model specifically for the Philippine Stock Exchange index closing value. The inputs to the ANN are US Dollar and Philippine Peso(USD-PHP) exchange rate, GDP growth of the country, quarterly inflation rate, 10-year bond yield, credit rating of the country, previous open, high, low, close values and volume of trade of the Philippine Stock Exchange Index (PSEi), gold price of the previous day, National Association of Securities Dealers Automated Quotations (NASDAQ), Standard and Poor’s 500 (S & P 500) and the iShares MSCI Philippines ETF (EPHE) previous closing value. The target is composed of the closing value of the PSEi during the 627 trading days from November 3, 2011, to May 30, 2014. MATLAB’s Neural Network toolbox was employed to create, train and simulate the network using multi-layer feed forward neural network with back-propagation algorithm. The results satisfactorily show that the neural network developed has the ability to model the PSEi, which is affected by both internal and external economic factors. It was found out that the inputs used are the main factors that influence the movement of the PSEi closing value.

Keywords: artificial neural networks, artificial intelligence, philippine stocks exchange index, stocks trading

Procedia PDF Downloads 297

Authors: Ghofrane Rehaiem, Hamza Gharsellaoui, Samir Benahmed

Abstract:

In this study, Artificial Neural Networks (ANNs) were used for modeling the parameters that allow the real-time scheduling of embedded systems under resources constraints designed for real-time applications running. The objective of this work is to implement a neural networks based approach for real-time scheduling of embedded systems in order to handle real-time constraints in execution scenarios. In our proposed approach, many techniques have been proposed for both the planning of tasks and reducing energy consumption. In fact, a combination of Dynamic Voltage Scaling (DVS) and time feedback can be used to scale the frequency dynamically adjusting the operating voltage. Indeed, we present in this paper a hybrid contribution that handles the real-time scheduling of embedded systems, low power consumption depending on the combination of DVS and Neural Feedback Scheduling (NFS) with the energy Priority Earlier Deadline First (PEDF) algorithm. Experimental results illustrate the efficiency of our original proposed approach.

Keywords: optimization, neural networks, real-time scheduling, low-power consumption

Procedia PDF Downloads 371

Authors: Cathal Merz, Gareth O’Donnell

Abstract:

Coil reinforced thin-walled (CRTW) tubes are used in medicine to treat problems affecting blood vessels within the body through minimally invasive procedures. The CRTW tube considered in this research makes up part of such a device and is inserted into the patient via their femoral or brachial arteries and manually navigated to the site in need of treatment. This procedure replaces the requirement to perform open surgery but is limited by reduction of blood vessel lumen diameter and increase in tortuosity of blood vessels deep in the brain. In order to maximize the capability of these procedures, CRTW tube devices are being manufactured with decreasing wall thicknesses in order to deliver treatment deeper into the body and to allow passage of other devices through its inner diameter. This introduces significant stresses to the device materials which have resulted in an observed increase in the breaking of the proximal segment of the device into two separate pieces after it has failed by buckling. As there is currently no international standard for measuring the mechanical properties of these CRTW tube devices, it is difficult to accurately analyze this problem. The aim of the current work is to address this discrepancy in the biomedical device industry by developing a measurement system that can be used to quantify the effect of process and design changes on CRTW tube performance, aiding in the development of better performing, next generation devices. Using materials testing frames, micro-computed tomography (micro-CT) imaging, experiment planning, analysis of variance (ANOVA), T-tests and regression analysis, test methods have been developed for assessing the impact of process and design changes on the device. The major findings of this study have been an insight into the suitability of buckle and three-point bend tests for the measurement of the effect of varying processing factors on the device’s performance, and guidelines for interpreting the output data from the test methods. The findings of this study are of significant interest with respect to verifying and validating key process and design changes associated with the device structure and material condition. Test method integrity evaluation is explored throughout.

Keywords: neurovascular catheter, coil reinforced tube, buckling, three-point bend, tensile

Procedia PDF Downloads 117

Authors: Abdelhadi Lotfi, Abdelkader Benyettou

Abstract:

In this work, a training algorithm for probabilistic neural networks (PNN) is presented. The algorithm addresses one of the major drawbacks of PNN, which is the size of the hidden layer in the network. By using a cross-validation training algorithm, the number of hidden neurons is shrunk to a smaller number consisting of the most representative samples of the training set. This is done without affecting the overall architecture of the network. Performance of the network is compared against performance of standard PNN for different databases from the UCI database repository. Results show an important gain in network size and performance.

Keywords: classification, probabilistic neural networks, network optimization, pattern recognition

Procedia PDF Downloads 262

Authors: Chia-Chen Wei, Pack Hsieh, Jeffrey Chen

Abstract:

Surface Mount Technology (SMT) is widely used in the area of the electronic assembly in which the electronic components are mounted to the surface of the printed circuit board (PCB). Most of the defects in the SMT process are mainly related to the quality of solder paste printing. These defects lead to considerable manufacturing costs in the electronics assembly industry. Therefore, the solder paste inspection (SPI) machine for controlling and monitoring the amount of solder paste printing has become an important part of the production process. So far, the setting of the SPI threshold is based on statistical analysis and experts’ experiences to determine the appropriate threshold settings. Because the production data are not normal distribution and there are various variations in the production processes, defects related to solder paste printing still occur. In order to solve this problem, this paper proposes an online machine learning algorithm, called the automatic threshold adjustment (ATA) algorithm, and closed-loop architecture in the SMT process to determine the best threshold settings. Simulation experiments prove that our proposed threshold settings improve the accuracy from 99.85% to 100%.

Keywords: big data analytics, Industry 4.0, SPI threshold setting, surface mount technology

Procedia PDF Downloads 116

Authors: Hannachi Med Tahar, H. Djebaili, B. Daheche

Abstract:

In this approach, we have tried to describe the flattening of welded tubes, and its experimental application. The test is carried out at the (National product processing company dishes and tubes production). Usually, the final products (tubes) undergo a series of non-destructive inspection online and offline welding, and obviously destructive mechanical testing (bending, flattening, flaring, etc.). For this and for the purpose of implementing the flattening test, which applies to the processing of round tubes in other forms, it took four sections of welded tubes draft (before stretching hot) and welded tubes finished (after drawing hot and annealing), it was also noted the report 'health' flattened tubes must not show or crack or tear. The test is considered poor if it reveals a lack of ductility of the metal.

Keywords: flattening, destructive testing, tube drafts, finished tube, Castem 2001

Procedia PDF Downloads 446

Authors: Venkatesh Pulletikurthi, Karthik B. Ariyur, Luciano Castillo

Abstract:

The system identification from the turbulence wakes will lead to the tactical advantage to prepare and also, to predict the trajectory of the opponents’ movements. A low-order modeling technique, POD, is used to predict the object based on the wake pattern and compared with pre-trained image recognition neural network (NN) to classify the wake patterns into objects. It is demonstrated that low-order modeling, POD, is able to predict the objects better compared to pretrained NN by ~30%.

Keywords: the bluff body wakes, low-order modeling, neural network, system identification

Procedia PDF Downloads 180

Authors: Debajyoti Mukherjee, Arathy B. S., Arpita Sahu, Saranga P. Pogula

Abstract:

A Functional Model to mimic the functional correctness of a Neural Network Compute Accelerator IP is very crucial for design validation. Neural network workloads are based on a Brain Floating Point (BF-16) data type. The major challenge we were facing was the incompatibility of gcc compilers to BF-16 datatype, which we addressed with a native BF-16 generator integrated to our functional model. Moreover, working with big GEMM (General Matrix Multiplication) or SpMM (Sparse Matrix Multiplication) Work Loads (Dense or Sparse) and debugging the failures related to data integrity is highly painstaking. In this paper, we are addressing the quality challenge of such a complex Neural Network Accelerator design by proposing a Functional Model-based scoreboard or Software model using SystemC. The proposed Functional Model executes the assembly code based on the ISA of the processor IP, decodes all instructions, and executes as expected to be done by the DUT. The said model would give a lot of visibility and debug capability in the DUT bringing up micro-steps of execution.

Keywords: ISA (instruction set architecture), NN (neural network), TLM (transaction-level modeling), GEMM (general matrix multiplication)

Procedia PDF Downloads 86