Search results for: boundary layer noise denoising

Authors: Shashank N. Mathur, Anil K. Ahlawat, Virendra P. Vishwakarma

Abstract:

In this paper, a comparative study of application of supervised and unsupervised learning algorithms on illumination invariant face recognition has been carried out. The supervised learning has been carried out with the help of using a bi-layered artificial neural network having one input, two hidden and one output layer. The gradient descent with momentum and adaptive learning rate back propagation learning algorithm has been used to implement the supervised learning in a way that both the inputs and corresponding outputs are provided at the time of training the network, thus here is an inherent clustering and optimized learning of weights which provide us with efficient results.. The unsupervised learning has been implemented with the help of a modified Counterpropagation network. The Counterpropagation network involves the process of clustering followed by application of Outstar rule to obtain the recognized face. The face recognition system has been developed for recognizing faces which have varying illumination intensities, where the database images vary in lighting with respect to angle of illumination with horizontal and vertical planes. The supervised and unsupervised learning algorithms have been implemented and have been tested exhaustively, with and without application of histogram equalization to get efficient results.

Keywords: Artificial Neural Networks, back propagation, Counterpropagation networks, face recognition, learning algorithms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1686

Authors: Kutubuddin Ansari, Malay Mukul, Sridevi Jade

Abstract:

We used high-precision Global Positioning System (GPS) to geodetically constrain the motion of stations in the Darjiling-Sikkim Himalayan (DSH) wedge and examine the deformation at the Indian-Tibetan plate boundary using IGS (International GPS Service) fiducial stations. High-precision GPS based displacement and velocity field was measured in the DSH between 1997 and 2009. To obtain additional insight north of the Indo-Tibetan border and in the Darjiling-Sikkim-Tibet (DaSiT) wedge, published velocities from four stations J037, XIGA, J029 and YADO were also included in the analysis. India-fixed velocities or the back-slip was computed relative to the pole of rotation of the Indian Plate (Latitude 52.97 ± 0.22º, Longitude - 0.30 ± 3.76º, and Angular Velocity 0.500 ± 0.008º/ Myr) in the DaSiT wedge. Dislocation modelling was carried out with the back-slip to model the best possible solution of a finite rectangular dislocation or the causative fault based on dislocation theory that produced the observed back-slip using a forward modelling approach. To find the best possible solution, three different models were attempted. First, slip along a single thrust fault, then two thrust faults and in finally, three thrust faults were modelled to simulate the back-slip in the DaSiT wedge. The three-fault case bests the measured displacements and is taken as the best possible solution.

Keywords: Global Positioning System, Darjiling-Sikkim Himalaya, Dislocation modelling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2104

Authors: Megha Rao, Søren H. Jensen, Xiufu Sun, Anke Hagen, Mogens B. Mogensen

Abstract:

Solid oxide electrolysis cells have an immense potential in converting CO₂ and H₂O into syngas during co-electrolysis operation. The produced syngas can be further converted into hydrocarbons. This kind of technology is called power-to-gas or power-to-liquid. To produce hydrocarbons via this route, durability of the cells is still a challenge, which needs to be further investigated in order to improve the cells. In this work, various nickel-yttria stabilized zirconia (Ni-YSZ) fuel electrode supported or YSZ electrolyte supported cells, cerium gadolinium oxide (CGO) barrier layer, and an oxygen electrode are investigated for durability under co-electrolysis conditions in both galvanostatic and potentiostatic conditions. While changing the gas on the oxygen electrode, keeping the fuel electrode gas composition constant, a change in the gas concentration arc was observed by impedance spectroscopy. Measurements of open circuit potential revealed the presence of leaks in the setup. It is speculated that the change in concentration impedance may be related to the leaks. Furthermore, the cells were also tested under pressurized conditions to find an inter-play between the leak rate and the pressure. A mathematical modeling together with electrochemical and microscopy analysis is presented.

Keywords: Co-electrolysis, solid oxide electrolysis cells, leaks, durability, gas concentration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 897

Authors: Shahana T. K., Babita R. Jose, K. Poulose Jacob, Sreela Sasi

Abstract:

The modern telecommunication industry demands higher capacity networks with high data rate. Orthogonal frequency division multiplexing (OFDM) is a promising technique for high data rate wireless communications at reasonable complexity in wireless channels. OFDM has been adopted for many types of wireless systems like wireless local area networks such as IEEE 802.11a, and digital audio/video broadcasting (DAB/DVB). The proposed research focuses on a concatenated coding scheme that improve the performance of OFDM based wireless communications. It uses a Redundant Residue Number System (RRNS) code as the outer code and a convolutional code as the inner code. Here, a direct conversion of analog signal to residue domain is done to reduce the conversion complexity using sigma-delta based parallel analog-to-residue converter. The bit error rate (BER) performances of the proposed system under different channel conditions are investigated. These include the effect of additive white Gaussian noise (AWGN), multipath delay spread, peak power clipping and frame start synchronization error. The simulation results show that the proposed RRNS-Convolutional concatenated coding (RCCC) scheme provides significant improvement in the system performance by exploiting the inherent properties of RRNS.

Keywords: Analog-to-residue converter, Concatenated codes, OFDM, Redundant Residue Number System, Sigma-delta modulator, Wireless communication

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1944

Authors: M. Miladi, T. Ezzedine, R. Bouallegue

Abstract:

In the current decade, wireless sensor networks are emerging as a peculiar multi-disciplinary research area. By this way, energy efficiency is one of the fundamental research themes in the design of Medium Access Control (MAC) protocols for wireless sensor networks. Thus, in order to optimize the energy consumption in these networks, a variety of MAC protocols are available in the literature. These schemes were commonly evaluated under simple network density and a few results are published on their robustness in realistic network-s size. We, in this paper, provide an analytical study aiming to highlight the energy waste sources in wireless sensor networks. Then, we experiment three energy efficient hybrid CSMA/CA based MAC protocols optimized for wireless sensor networks: Sensor-MAC (SMAC), Time-out MAC (TMAC) and Traffic aware Energy Efficient MAC (TEEM). We investigate these protocols with different network densities in order to discuss the end-to-end performances of these schemes (i.e. in terms of energy efficiency, delay and throughput). Through Network Simulator (NS- 2) implementations, we explore the behaviors of these protocols with respect to the network density. In fact, this study may help the multihops sensor networks designers to design or select the MAC layer which matches better their applications aims.

Keywords: Energy efficiency, medium access control, network density, wireless sensor networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1627

Authors: P. Parthiban, J. Karthikeyan

Abstract:

This paper deals with the performance of semi-light weight concrete, prepared by using wood ash pellets as coarse aggregates which were improved by partial replacement of cement with alccofine. Alccofine is a mineral admixture which contains high glass content obtained through the process of controlled granulation. This is finer than cement which carries its own pozzolanic property. Therefore, cement could be replaced by alccofine as 0%, 5%, 10%, 15%, 20%, 25%, 30%, 35%, 40%, 45%, 50%, 55%, 60%, 65%, and 70% to enhance the strength and durability properties of concrete. High range water reducing admixtures (HRWA) were used in these mixes which were dosed up to 1.5% weight of the total cementitious content (alccofine & cement). It also develops the weaker transition zone into more impermeable layer. Specimens were subjected in both the accelerated curing method as well as conventional curing method. Experimental results were compared and reported, in that the maximum compressive strength of 32.6 MPa was achieved on 28^th day with 30% replacement level in a density of 2200 kg/m³ to a conventional curing, while in the accelerated curing, maximum compressive strength was achieved at 40% replacement level. Rapid chloride penetration test (RCPT) output results for the conventional curing method at 0% and 70% give 3296.7 and 545.6 coulombs.

Keywords: Alccofine, compressive strength, RCPT, wood ash pellets.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 667

Authors: Yanju Zhang, Joost M. Woltering, Fons J. Verbeek

Abstract:

It has been established that microRNAs (miRNAs) play an important role in gene expression by post-transcriptional regulation of messengerRNAs (mRNAs). However, the precise relationships between microRNAs and their target genes in sense of numbers, types and biological relevance remain largely unclear. Dissecting the miRNA-target relationships will render more insights for miRNA targets identification and validation therefore promote the understanding of miRNA function. In miRBase, miRanda is the key algorithm used for target prediction for Zebrafish. This algorithm is high-throughput but brings lots of false positives (noise). Since validation of a large scale of targets through laboratory experiments is very time consuming, several computational methods for miRNA targets validation should be developed. In this paper, we present an integrative method to investigate several aspects of the relationships between miRNAs and their targets with the final purpose of extracting high confident targets from miRanda predicted targets pool. This is achieved by using the techniques ranging from statistical tests to clustering and association rules. Our research focuses on Zebrafish. It was found that validated targets do not necessarily associate with the highest sequence matching. Besides, for some miRNA families, the frequency of their predicted targets is significantly higher in the genomic region nearby their own physical location. Finally, in a case study of dre-miR-10 and dre-miR-196, it was found that the predicted target genes hoxd13a, hoxd11a, hoxd10a and hoxc4a of dre-miR- 10 while hoxa9a, hoxc8a and hoxa13a of dre-miR-196 have similar characteristics as validated target genes and therefore represent high confidence target candidates.

Keywords: MicroRNA targets validation, microRNA-target relationships, dre-miR-10, dre-miR-196.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1991

Authors: Nasim Abuali Galehdari, Venkat Mani, Ajit D. Kelkar

Abstract:

Space Radiation has become one of the major factors in successful long duration space exploration. Exposure to space radiation not only can affect the health of astronauts but also can disrupt or damage materials and electronics. Hazards to materials include degradation of properties, such as, modulus, strength, or glass transition temperature. Electronics may experience single event effects, gate rupture, burnout of field effect transistors and noise. Presently aluminum is the major component in most of the space structures due to its lightweight and good structural properties. However, aluminum is ineffective at blocking space radiation. Therefore, most of the past research involved studying at polymers which contain large amounts of hydrogen. Again, these materials are not structural materials and would require large amounts of material to achieve the structural properties needed. One of the materials to alleviate this problem is polymeric composite materials, which has good structural properties and use polymers that contained large amounts of hydrogen. This paper presents steps involved in fabrication of multi-functional hybrid sandwich panels that can provide beneficial radiation shielding as well as structural strength. Multifunctional hybrid sandwich panels were manufactured using vacuum assisted resin transfer molding process and were subjected to radiation treatment. Study indicates that various nanoparticles including Boron Nano powder, Boron Carbide and Gadolinium nanoparticles can be successfully used to block the space radiation without sacrificing the structural integrity.

Keywords: Multi-functional, polymer composites, radiation shielding, sandwich composites.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1816

Authors: Jaya Mahar Maligan, Teti Estiasih, Joni Kusnadi

Abstract:

Structured phospholipids from commercial soybean lecithin with oil enriched omega-3 fatty acid form by product of tuna canning is alternative procedure to provides the stability of omega-3 fatty acid structure and increase these bioactive function in metabolism. Best treatment condition was obtain in 18 hours acidolysis reaction with 30% enzyme concentration, which EPADHA incorporation level was 127,47 mg/g and incorporation percentage of EPA-DHA was 51,04% at phospholipids structure. This structured phospolipids could reduce atherosclerosis risk in male Sprague dawley rat. Provision of structured phospholipids has significant effect (α = 0.05) on changes in lipid profile, intima-media thickness of aorta rats (male Sprague dawley) fed atherogenic diet. Structured phospholipids intake can lower total cholesterol 78.36 mg/dL, total triglycerides 94,57 mg/dL, LDL levels 87.08 mg/dL and increased HDL level as much as 12,64 mg/dL in 10 weeks cares. Structured phospholipids intake also can prevent the thickening of the intima-media layer of the aorta.

Keywords: Structured phospholipids, commercial soybean lecithin, omega-3 fatty acid, atherosclerosis risk.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2562

Authors: MohammadReza EffatParvar, Akbar Bemana, Mehdi EffatParvar

Abstract:

Scheduling algorithms are used in operating systems to optimize the usage of processors. One of the most efficient algorithms for scheduling is Multi-Layer Feedback Queue (MLFQ) algorithm which uses several queues with different quanta. The most important weakness of this method is the inability to define the optimized the number of the queues and quantum of each queue. This weakness has been improved in IMLFQ scheduling algorithm. Number of the queues and quantum of each queue affect the response time directly. In this paper, we review the IMLFQ algorithm for solving these problems and minimizing the response time. In this algorithm Recurrent Neural Network has been utilized to find both the number of queues and the optimized quantum of each queue. Also in order to prevent any probable faults in processes' response time computation, a new fault tolerant approach has been presented. In this approach we use combinational software redundancy to prevent the any probable faults. The experimental results show that using the IMLFQ algorithm results in better response time in comparison with other scheduling algorithms also by using fault tolerant mechanism we improve IMLFQ performance.

Keywords: IMLFQ, Fault Tolerant, Scheduling, Queue, Recurrent Neural Network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1536

Authors: Iman A. Saad, Loay E. George

Abstract:

Iris pattern is an important biological feature of human body; it becomes very hot topic in both research and practical applications. In this paper, an algorithm is proposed for iris recognition and a simple, efficient and fast method is introduced to extract a set of discriminatory features using first order gradient operator applied on grayscale images. The gradient based features are robust, up to certain extents, against the variations may occur in contrast or brightness of iris image samples; the variations are mostly occur due lightening differences and camera changes. At first, the iris region is located, after that it is remapped to a rectangular area of size 360x60 pixels. Also, a new method is proposed for detecting eyelash and eyelid points; it depends on making image statistical analysis, to mark the eyelash and eyelid as a noise points. In order to cover the features localization (variation), the rectangular iris image is partitioned into N overlapped sub-images (blocks); then from each block a set of different average directional gradient densities values is calculated to be used as texture features vector. The applied gradient operators are taken along the horizontal, vertical and diagonal directions. The low order norms of gradient components were used to establish the feature vector. Euclidean distance based classifier was used as a matching metric for determining the degree of similarity between the features vector extracted from the tested iris image and template features vectors stored in the database. Experimental tests were performed using 2639 iris images from CASIA V4-Interival database, the attained recognition accuracy has reached up to 99.92%.

Keywords: Iris recognition, contrast stretching, gradient features, texture features, Euclidean metric.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1965

Authors: Andhe Dharani, P. S. Satyanarayana, Andhe Pallavi

Abstract:

Considering payload, reliability, security and operational lifetime as major constraints in transmission of images we put forward in this paper a steganographic technique implemented at the physical layer. We suggest transmission of Halftoned images (payload constraint) in wireless sensor networks to reduce the amount of transmitted data. For low power and interference limited applications Turbo codes provide suitable reliability. Ensuring security is one of the highest priorities in many sensor networks. The Turbo Code structure apart from providing forward error correction can be utilized to provide for encryption. We first consider the Halftoned image and then the method of embedding a block of data (called secret) in this Halftoned image during the turbo encoding process is presented. The small modifications required at the turbo decoder end to extract the embedded data are presented next. The implementation complexity and the degradation of the BER (bit error rate) in the Turbo based stego system are analyzed. Using some of the entropy based crypt analytic techniques we show that the strength of our Turbo based stego system approaches that found in the OTPs (one time pad).

Keywords: Halftoning, Turbo codes, security, operationallifetime, Turbo based stego system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1508

Authors: Y. Bai, M. Bodlak, V. Frolov, S. Huber, V. Jary, I. Konorov, D. Levit, J. Novy, D. Steffen, O. Subrt, M. Virius

Abstract:

Modern experiments in high energy physics impose great demands on the reliability, the efficiency, and the data rate of Data Acquisition Systems (DAQ). This contribution focuses on the development and deployment of the new communication library DIALOG for the intelligent, FPGA-based Data Acquisition System (iFDAQ) of the COMPASS experiment at CERN. The iFDAQ utilizing a hardware event builder is designed to be able to readout data at the maximum rate of the experiment. The DIALOG library is a communication system both for distributed and mixed environments, it provides a network transparent inter-process communication layer. Using the high-performance and modern C++ framework Qt and its Qt Network API, the DIALOG library presents an alternative to the previously used DIM library. The DIALOG library was fully incorporated to all processes in the iFDAQ during the run 2016. From the software point of view, it might be considered as a significant improvement of iFDAQ in comparison with the previous run. To extend the possibilities of debugging, the online monitoring of communication among processes via DIALOG GUI is a desirable feature. In the paper, we present the DIALOG library from several insights and discuss it in a detailed way. Moreover, the efficiency measurement and comparison with the DIM library with respect to the iFDAQ requirements is provided.

Keywords: Data acquisition system, DIALOG library, DIM library, FPGA, Qt framework, TCP/IP.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1125

Authors: S.P.Gautam, P.S.Bundela, R.K. Jain, V. N. Tripathi

Abstract:

The manufacturing transmission line tower parts has being generated hazardous waste which is required proper disposal of waste for protection of land pollution. Manufacturing Process in the manufacturing of steel angle, plates, pipes, channels are passes through conventional, semi automatic and CNC machines for cutting, marking, punching, drilling, notching, bending operations. All fabricated material Coated with thin layer of Zinc in Galvanizing plant where molten zinc is used for coating. Prior to Galvanizing, chemical like 33% concentrated HCl Acid, ammonium chloride and d-oil being used for pretreatment of iron. The bath of water with sodium dichromate is used for cooling and protection of the galvanized steel. For the heating purpose the furnace oil burners are used. These above process the Zinc dross, Zinc ash, ETP sludge and waste pickled acid generated as hazardous waste. The RPG has made captive secured land fill site, since 1997 since then it was using for disposal of hazardous waste after completion of SLF (Secured land fill) site. The RPG has raised height from ground level then now it is being used for disposal of waste as he designed the SLF after in creasing height of from GL it is functional without leach ate or adverse impacts in the environment.

Keywords: Disposal, Drilling, Fabricated. Hazardous waste, Punching.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1647

Authors: Sabina Baraković, Dragan Jevtić, Jasmina Baraković Husić

Abstract:

Wireless mobile communications have experienced the phenomenal growth through last decades. The advances in wireless mobile technologies have brought about a demand for high quality multimedia applications and services. For such applications and services to work, signaling protocol is required for establishing, maintaining and tearing down multimedia sessions. The Session Initiation Protocol (SIP) is an application layer signaling protocols, based on request/response transaction model. This paper considers SIP INVITE transaction over an unreliable medium, since it has been recently modified in Request for Comments (RFC) 6026. In order to help in assuring that the functional correctness of this modification is achieved, the SIP INVITE transaction is modeled and analyzed using Colored Petri Nets (CPNs). Based on the model analysis, it is concluded that the SIP INVITE transaction is free of livelocks and dead codes, and in the same time it has both desirable and undesirable deadlocks. Therefore, SIP INVITE transaction should be subjected for additional updates in order to eliminate undesirable deadlocks. In order to reduce the cost of implementation and maintenance of SIP, additional remodeling of the SIP INVITE transaction is recommended.

Keywords: Colored Petri Nets, SIP INVITE, state space, dead marking

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2917

Authors: B. L. Ho, L. Shi, D. F. Wang, V. C. T. Mok

Abstract:

The brain’s functional connectivity while temporally non-stationary does express consistency at a macro spatial level. The study of stable resting state connectivity patterns hence provides opportunities for identification of diseases if such stability is severely perturbed. A mathematical model replicating the brain’s spatial connections will be useful for understanding brain’s representative geometry and complements the empirical model where it falls short. Empirical computations tend to involve large matrices and become infeasible with fine parcellation. However, the proposed analytical model has no such computational problems. To improve replicability, 92 subject data are obtained from two open sources. The proposed methodology, inspired by financial theory, uses multivariate regression to find relationships of every cortical region of interest (ROI) with some pre-identified hubs. These hubs acted as representatives for the entire cortical surface. A variance-covariance framework of all ROIs is then built based on these relationships to link up all the ROIs. The result is a high level of match between model and empirical correlations in the range of 0.59 to 0.66 after adjusting for sample size; an increase of almost forty percent. More significantly, the model framework provides an intuitive way to delineate between systemic drivers and idiosyncratic noise while reducing dimensions by more than 30 folds, hence, providing a way to conduct attribution analysis. Due to its analytical nature and simple structure, the model is useful as a standalone toolkit for network dependency analysis or as a module for other mathematical models.

Keywords: Functional magnetic resonance imaging, multivariate regression, network hubs, resting state functional connectivity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 807

Authors: Julieta D. Chelaru, Maria Gorea

Abstract:

The massive demolition of old buildings in recent years has generated tons of waste, especially brick waste. Thus, a concern of recent research is the use of this waste for the production of environmentally friendly concrete. At the same time, corrosion of the reinforcement steel rebar in classical concrete is a current problem. In this context, in the present paper a study was carried out on the corrosion of metal reinforcement in cement mortars with added brick waste. The corrosion process was analyzed on four compositions of mortars without and with 15%, 25% and 35% brick waste replacing the sand. The brick waste has majority content in SiO2, Al2O3, FeO3 and CaO. The grain size distribution of brick waste was close to that of the sand (dmax = 2 mm). The preparation method of the samples was similar to ordinary mortars. The corrosion action on the rebar in concrete, at different brick waste concentrations, was investigated by electrochemical measurements (polarization curves and electrochemical impedance spectroscopy (EIS)) at 1 month and 26 months. The results obtained at 26 months revealed that the addition of the brick waste in mortar improved the anticorrosion properties in the case of all samples compared with the etalon mortar. The best results were obtained in the case of the sample with 15% brick waste (the efficiency was ≈ 90%). The corrosion intermediary layer formed on the rebar surface was evidenced by SEM-EDX.

Keywords: EIS, steel corrosion, steel reinforced concrete, waste materials.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 679

Authors: Machimontorn Promtong, Sherman C. P. Cheung, Guan H. Yeoh, Sara Vahaji, Jiyuan Tu

Abstract:

The wide range of industrial applications involved with boiling flows promotes the necessity of establishing fundamental knowledge in boiling flow phenomena. For this purpose, a number of experimental and numerical researches have been performed to elucidate the underlying physics of this flow. In this paper, the improved wall boiling models, implemented on ANSYS CFX 14.5, were introduced to study subcooled boiling flow at elevated pressure. At the heated wall boundary, the Fractal model, Force balance approach and Mechanistic frequency model are given for predicting the nucleation site density, bubble departure diameter, and bubble departure frequency. The presented wall heat flux partitioning closures were modified to consider the influence of bubble sliding along the wall before the lift-off, which usually happens in the flow boiling. The simulation was performed based on the Two-fluid model, where the standard k-ω SST model was selected for turbulence modelling. Existing experimental data at around 5 bars were chosen to evaluate the accuracy of the presented mechanistic approach. The void fraction and Interfacial Area Concentration (IAC) are in good agreement with the experimental data. However, the predicted bubble velocity and Sauter Mean Diameter (SMD) are over-predicted. This over-prediction may be caused by consideration of only dispersed and spherical bubbles in the simulations. In the future work, the important physical mechanisms of bubbles, such as merging and shrinking during sliding on the heated wall will be incorporated into this mechanistic model to enhance its capability for a wider range of flow prediction.

Keywords: CFD, mechanistic model, subcooled boiling flow, two-fluid model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1270

Authors: Apoorva Vinod, Archana Mathur, Snehanshu Saha

Abstract:

Though there exists a plethora of Activation Functions (AFs) used in single and multiple hidden layer Neural Networks (NN), their behavior always raised curiosity, whether used in combination or singly. The popular AFs – Sigmoid, ReLU, and Tanh – have performed prominently well for shallow and deep architectures. Most of the time, AFs are used singly in multi-layered NN, and, to the best of our knowledge, their performance is never studied and analyzed deeply when used in combination. In this manuscript, we experiment on multi-layered NN architecture (both on shallow and deep architectures; Convolutional NN and VGG16) and investigate how well the network responds to using two different AFs (Sigmoid-Tanh, Tanh-ReLU, ReLU-Sigmoid) used alternately against a traditional, single (Sigmoid-Sigmoid, Tanh-Tanh, ReLU-ReLU) combination. Our results show that on using two different AFs, the network achieves better accuracy, substantially lower loss, and faster convergence on 4 computer vision (CV) and 15 Non-CV (NCV) datasets. When using different AFs, not only was the accuracy greater by 6-7%, but we also accomplished convergence twice as fast. We present a case study to investigate the probability of networks suffering vanishing and exploding gradients when using two different AFs. Additionally, we theoretically showed that a composition of two or more AFs satisfies Universal Approximation Theorem (UAT).

Keywords: Activation Function, Universal Approximation function, Neural Networks, convergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 154

Authors: Samit Ari, Goutam Saha

Abstract:

Artificial Neural Network (ANN) has been extensively used for classification of heart sounds for its discriminative training ability and easy implementation. However, it suffers from overparameterization if the number of nodes is not chosen properly. In such cases, when the dataset has redundancy within it, ANN is trained along with this redundant information that results in poor validation. Also a larger network means more computational expense resulting more hardware and time related cost. Therefore, an optimum design of neural network is needed towards real-time detection of pathological patterns, if any from heart sound signal. The aims of this work are to (i) select a set of input features that are effective for identification of heart sound signals and (ii) make certain optimum selection of nodes in the hidden layer for a more effective ANN structure. Here, we present an optimization technique that involves Singular Value Decomposition (SVD) and QR factorization with column pivoting (QRcp) methodology to optimize empirically chosen over-parameterized ANN structure. Input nodes present in ANN structure is optimized by SVD followed by QRcp while only SVD is required to prune undesirable hidden nodes. The result is presented for classifying 12 common pathological cases and normal heart sound.

Keywords: ANN, Classification of heart diseases, murmurs, optimization, Phonocardiogram, QRcp, SVD.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2071

Authors: Yan Yu, Wang Yu, Chen Xintong, Liu Yi, Zhang Yanzhong, Wang Yanji, Chen Xingyu, Zhang Miaocheng, Tong Yi

Abstract:

Neuromorphic computing based on spiking neural networks (SNNs) has emerged as a promising avenue for building the next generation of intelligent computing systems. Owing to their high-density integration, low power, and outstanding nonlinearity, memristors have attracted emerging attention on achieving SNNs. However, fabricating a low-power and robust memristor-based spiking neuron without extra electrical components is still a challenge for brain-inspired systems. In this work, we demonstrate a TiO2-based threshold switching (TS) memristor to emulate a leaky integrate-and-fire (LIF) neuron without auxiliary circuits, used to realize single layer fully connected (FC) SNNs. Moreover, our TiO2-based resistive switching (RS) memristors realize spiking-time-dependent-plasticity (STDP), originating from the Ag diffusion-based filamentary mechanism. This work demonstrates that TiO2-based memristors may provide an efficient method to construct hardware neuromorphic computing systems.

Keywords: Leaky integrate-and-fire, memristor, spiking neural networks, spiking-time-dependent-plasticity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 691

Authors: S. S. Ghodsi, M. H. Mehrabi, Zainah Ibrahim, Meldi Suhatril

Abstract:

This research examines the performance of a hybrid passive control device for enhancing the seismic response of steel frame structures. The device design comprises a damper which employs a viscoelastic material to control both shear and axial strain. In the design, energy is dissipated through the shear strain of a two-layer system of viscoelastic pads which are located between steel plates. In addition, viscoelastic blocks have been included on either side of the main shear damper which obtains compressive strains in the viscoelastic blocks. These dampers not only dissipate energy but also increase the stiffness of the steel frame structure, and the degree to which they increase the stiffness may be controlled by the size and shape. In this research, the cyclical behavior of the damper was examined both experimentally and numerically with finite element modeling. Cyclic loading results of the finite element modeling reveal fundamental characteristics of this hybrid viscoelastic damper. The results indicate that incorporating a damper of the design can significantly improve the seismic performance of steel frame structures.

Keywords: Cyclic loading, energy dissipation, hybrid damper, passive control system, viscoelastic damper.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 848

Authors: Luis Fonseca, Filipe Cabral Pinto, Susana Sargento

Abstract:

The increase of the world population, especially in large urban centers, has resulted in new challenges particularly with the control and optimization of public safety. Thus, in the present work, a solution is proposed for the prediction of criminal occurrences in a city based on historical data of incidents and demographic information. The entire research and implementation will be presented start with the data collection from its original source, the treatment and transformations applied to them, choice and the evaluation and implementation of the Machine Learning model up to the application layer. Classification models will be implemented to predict criminal risk for a given time interval and location. Machine Learning algorithms such as Random Forest, Neural Networks, K-Nearest Neighbors and Logistic Regression will be used to predict occurrences, and their performance will be compared according to the data processing and transformation used. The results show that the use of Machine Learning techniques helps to anticipate criminal occurrences, which contributed to the reinforcement of public security. Finally, the models were implemented on a platform that will provide an API to enable other entities to make requests for predictions in real-time. An application will also be presented where it is possible to show criminal predictions visually.

Keywords: Crime prediction, machine learning, public safety, smart city.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1326

Authors: K. Sandjak, B. Tiliouine

Abstract:

Structural analysis of flexible pavements has been and still is currently performed using multi-layer elastic theory. However, for thinly surfaced pavements subjected to low to medium volumes of traffics, the importance of non-linear stress-strain behavior of unbound granular materials (UGM) requires the use of more sophisticated numerical models for structural design and performance of such pavements. In the present work, nonlinear unbound aggregates constitutive model is implemented within an axisymmetric finite element code developed to simulate the nonlinear behavior of pavement structures including two local aggregates of different mineralogical nature, typically used in Algerian pavements. The performance of the mechanical model is examined about its capability of representing adequately, under various conditions, the granular material non-linearity in pavement analysis. In addition, deflection data collected by Falling Weight Deflectometer (FWD) are incorporated into the analysis in order to assess the sensitivity of critical pavement design criteria and pavement design life to the constitutive model. Finally, conclusions of engineering significance are formulated. 

Keywords: Nonlinear resilient behavior, unbound granular materials, RLT test results, FWD backcalculations, finite element simulations, pavement response and performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2294

Authors: Ming-Hsun Tsai, Ming-Chyuan Lin, Fu-Tsai Chung, Ling-Jhen Chen, Yu-Hang Lin, Meng-Shu Yeh, Lee-Long Han

Abstract:

Since 2005, an SRF module of CESR type serves as the accelerating cavity at the Taiwan Light Source in the National Synchrotron Radiation Research Center. A 500-MHz niobium cavity is immersed in liquid helium inside this SRF module. To reduce heat load, the liquid helium vessel is thermally shielded by liquid-nitrogen-cooled copper layer, and the beam chambers are also anchored with pipes of the liquid nitrogen flow in middle of the liquid helium vessel and the vacuum vessel. A strong correlation of the movement of the cavity-s frequency tuner with the temperature variation of parts cooled with liquid nitrogen was observed. A previous study on a spare SRF module with the niobium cavity cooled by liquid nitrogen instead of liquid helium, satisfactory suppression of the thermal oscillation was achieved by attaching a temporary buffer tank for the vented shielding nitrogen flow from the SRF module. In this study, a home-made buffer tank is designed and integrated to the spare SRF module with cavity cooled by liquid helium. Design, construction, integration, and preliminary test results of this buffer tank are presented.

Keywords: Cryogenics, flow control, oscillation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1945

Authors: Sheam-Chyun Lin, Wei-Kai Chen, Hung-Cheng Yen, Yung-Jen Cheng, Yu-Cheng Chen

Abstract:

Result from the constant dwindle in natural resources, the alternative way to reduce the costs in our daily life would be urgent to be found in the near future. As the ancient technique based on the theory of solar chimney since roman times, the double-skin façade are simply composed of two large glass panels in purpose of daylighting and also natural ventilation in the daytime. Double-skin façade is generally installed on the exterior side of buildings as function as the window, so there is always a huge amount of passive solar energy the façade would receive to induce the airflow every sunny day. Therefore, this article imposes a domestic double-skin window for residential usage and attempts to improve the volume flow rate inside the cavity between the panels by the frame geometry design, the installation of outlet guide plate and the solar energy collection system. Note that the numerical analyses are applied to investigate the characteristics of flow field, and the boundary conditions in the simulation are totally based on the practical experiment of the original prototype. Then we redesign the prototype from the knowledge of the numerical results and fluid dynamic theory, and later the experiments of modified prototype will be conducted to verify the simulation results. The velocities at the inlet of each case are increase by 5%, 45% and 15% from the experimental data, and also the numerical simulation results reported 20% improvement in volume flow rate both for the frame geometry design and installation of outlet guide plate.

Keywords: Solar energy, Double-skin façades, Thermal buoyancy, Fluid machinery.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1521

Authors: H. Shayeghi, H. A. Shayanfar, G. Azimi

Abstract:

Short-Term Load Forecasting (STLF) plays an important role for the economic and secure operation of power systems. In this paper, Continuous Genetic Algorithm (CGA) is employed to evolve the optimum large neural networks structure and connecting weights for one-day ahead electric load forecasting problem. This study describes the process of developing three layer feed-forward large neural networks for load forecasting and then presents a heuristic search algorithm for performing an important task of this process, i.e. optimal networks structure design. The proposed method is applied to STLF of the local utility. Data are clustered due to the differences in their characteristics. Special days are extracted from the normal training sets and handled separately. In this way, a solution is provided for all load types, including working days and weekends and special days. We find good performance for the large neural networks. The proposed methodology gives lower percent errors all the time. Thus, it can be applied to automatically design an optimal load forecaster based on historical data.

Keywords: Feed-forward Large Neural Network, Short-TermLoad Forecasting, Continuous Genetic Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1830

Authors: Adel Belal, Sameh Aboelsoud, Mohy Elmashad, Mohammed Abdelmonem

Abstract:

The two main criteria that control the design and performance of footings are bearing capacity and settlement of soil. In soft soils, the construction of buildings, storage tanks, warehouse, etc. on weak soils usually involves excessive settlement problems. To solve bearing capacity or reduce settlement problems, soil improvement may be considered by using different techniques, including encased cement dust–lime columns. The proposed research studies the effect of adding floating encased cement dust and lime mix columns to soft clay on the clay-bearing capacity. Four experimental tests were carried out. Columns diameters of 3.0 cm, 4.0 cm, and 5.0 cm and columns length of 60% of the clay layer thickness were used. Numerical model was constructed and verified using commercial finite element package (PLAXIS 2D, V8.5). The verified model was used to study the effect of distributing columns around the footing at different distances. The study showed that the floating cement dust lime columns enhanced the clay-bearing capacity with 262%. The numerical model showed that the columns around the footing have a limit effect on the clay improvement.

Keywords: Bearing capacity, cement dust – lime columns, ground improvement, soft clay.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1116

Authors: M. H. Sedaghat, A. Zamani, S. Morshedi, R. Janamiri, M. Safdari, I. Mahdavi, A. Hosseini, A. Hatampour

Abstract:

Although lots of experiments have been done in enhanced oil recovery, the number of experiments which consider the effects of local and global heterogeneity on efficiency of enhanced oil recovery based on the polymer-surfactant flooding is low and rarely done. In this research, we have done numerous experiments of water flooding and polymer-surfactant flooding on a five spot glass micromodel in different conditions such as different positions of layers. In these experiments, five different micromodels with three different pore structures are designed. Three models with different layer orientation, one homogenous model and one heterogeneous model are designed. In order to import the effect of heterogeneity of porous media, three types of pore structures are distributed accidentally and with equal ratio throughout heterogeneous micromodel network according to random normal distribution. The results show that maximum EOR recovery factor will happen in a situation where the layers are orthogonal to the path of mainstream and the minimum EOR recovery factor will happen in a situation where the model is heterogeneous. This experiments show that in polymer-surfactant flooding, with increase of angles of layers the EOR recovery factor will increase and this recovery factor is strongly affected by local heterogeneity around the injection zone.

Keywords: Layered Reservoir, Micromodel, Local Heterogeneity, Polymer-Surfactant Flooding, Enhanced Oil Recovery.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2219

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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 686