Search results for: deep mixing method

Authors: Joseph Zernik

Abstract:

The mechanics of rip currents are complex, involving interactions between waves, currents, water levels and the bathymetry, that present particular challenges for numerical models. Here, the effects of a grid-spacing dependent horizontal mixing on the wave-current interactions are studied. Near the shore, wave rays diverge from channels towards bar crests because of refraction by topography and currents, in a way that depends on the rip current intensity which is itself modulated by the horizontal mixing. At low resolution with the grid-spacing dependent horizontal mixing, the wave motion is the same for both coupling modes because the wave deviation by the currents is weak. In high-resolution case, however, classical results are found with the stabilizing effect of the flow by feedback of waves on currents. Lastly, wave-current interactions and the horizontal mixing strongly affect the intensity of the three-dimensional rip velocity.

Keywords: e-justice, federal courts, human rights, banking regulation, United States

Procedia PDF Downloads 350

Authors: A. C. Bennis, F. Dumas, F. Ardhuin, B. Blanke

Abstract:

The mechanics of rip currents are complex, involving interactions between waves, currents, water levels and the bathymetry, that present particular challenges for numerical models. Here, the effects of a grid-spacing dependent horizontal mixing on the wave-current interactions are studied. Near the shore, wave rays diverge from channels towards bar crests because of refraction by topography and currents, in a way that depends on the rip current intensity which is itself modulated by the horizontal mixing. At low resolution with the grid-spacing dependent horizontal mixing, the wave motion is the same for both coupling modes because the wave deviation by the currents is weak. In high-resolution case, however, classical results are found with the stabilizing effect of the flow by feedback of waves on currents. Lastly, wave-current interactions and the horizontal mixing strongly affect the intensity of the three-dimensional rip velocity.

Keywords: numerical modeling, wave-current interactions, turbulence modeling, rip currents

Procedia PDF Downloads 434

Authors: Abe D. Desta

Abstract:

This study suggests a deep learning-based method for identifying and following moving objects in surveillance video. The proposed method uses a fast regional convolution neural network (F-RCNN) trained on a substantial dataset of vehicle images to first detect vehicles. A Kalman filter and a data association technique based on a Hungarian algorithm are then used to monitor the observed vehicles throughout time. However, in general, F-RCNN algorithms have been shown to be effective in achieving high detection accuracy and robustness in this research study. For example, in one study The study has shown that the vehicle detection and tracking, the system was able to achieve an accuracy of 97.4%. In this study, the F-RCNN algorithm was compared to other popular object detection algorithms and was found to outperform them in terms of both detection accuracy and speed. The presented system, which has application potential in actual surveillance systems, shows the usefulness of deep learning approaches in vehicle detection and tracking.

Keywords: artificial intelligence, computer vision, deep learning, fast-regional convolutional neural networks, feature extraction, vehicle tracking

Procedia PDF Downloads 75

Authors: Siham Mezher Yousif, Intisar Yahiya Mohammed, Salma Nagem Mouhy

Abstract:

Low Density Polyethylene is a thermoplastic resin extracted from petroleum based, whereas the wax is an oily organic component that is contains of alkanes, ester, polyester, and hydroxyl ester. The purpose of this research is to find out the optimum conditions of the wax produced by inducing with LDPE. The experiments were carried out by mixing different percentages of wax and LDPE to produce different polymer/wax compositions, in which lower values of the penetration, thickness, and electrical conductivity are obtained with increasing of mixing ratio of LDPE/wax which showed results of 19 mm penetration, 692 micron thickness and 5.9 mA electrical conductivity for 90 wt % of LDPE/wax) maximum mixing ratio (. It’s found that the optimum results regarding penetration, enamel thickness, and electrical conductivity “according to the enamel hardness, insulation properties, and economic aspects” are 20 mm, 276 micron, and 6.2 mA respectively.

Keywords: paraffin wax, low density polyethylene, blending, mixing ratio, bleaching

Procedia PDF Downloads 80

Authors: Sana Eid, Ahmad S. Darwish, Tarek Lemaoui, Maguy Abi Jaoude, Fawzi Banat, Shadi W. Hasan, Inas M. AlNashef

Abstract:

Addressing the growing challenge of per- and polyfluoroalkyl substances (PFAS) pollution in water bodies, this study introduces natural deep eutectic solvents (NADESs) as a pioneering solution for the efficient extraction of perfluorooctanoic acid (PFOA), one of the most persistent and concerning PFAS pollutants. Among the tested NADESs, trioctylphosphine oxide: lauric acid (TOPO:LauA) in a 1:1 molar ratio was distinguished as the most effective, achieving an extraction efficiency of approximately 99.52% at a solvent-to-feed (S:F) ratio of 1:2, room temperature, and neutral pH. This efficiency is achieved within a notably short mixing time of only one min, which is significantly less than the time required by conventional methods, underscoring the potential of TOPO:LauA for rapid and effective PFAS remediation. TOPO:LauA maintained consistent performance across various operational parameters, including a range of initial PFOA concentrations (0.1 ppm to 1000 ppm), temperatures (15 °C to 100 °C), pH values (3 to 9), and S:F ratios (2:3 to 1:7), demonstrating its versatility and robustness. Furthermore, its effectiveness was consistently high over seven consecutive extraction cycles, highlighting TOPO:LauA as a sustainable, environmentally friendly alternative to hazardous organic solvents, with promising applications for reliable, repeatable use in combating persistent water pollutants such as PFOA.

Keywords: deep eutectic solvents, natural deep eutectic solvents, perfluorooctanoic acid, water remediation

Procedia PDF Downloads 31

Authors: Mohammadjavad Yaghoubi, Arul Arulrajah, Mahdi M. Disfani, Suksun Horpibulsuk, Myint W. Bo, Stephen P. Darmawan

Abstract:

Utilising waste materials, such as fly ash (FA) and slag (S) stockpiled in landfills, has drawn the attention of researchers and engineers in the recent years. There is a great potential for usage of these wastes in ground improvement projects, especially where deep deposits of soft compressible soils exist. This paper investigates the changes in the strength development of a high water content soft soil stabilised with alkaline activated FA and S, termed as geopolymer binder, to use in deep soil mixing technology. The strength improvement and the changes in the microstructure of the mixtures have been studied. The results show that using FA and S-based geopolymers can increases the strength significantly. Furthermore, utilising FA and S in ground improvement projects, where large amounts of binders are required, can be a solution to the disposal of these wastes.

Keywords: alkaline activation, fly ash, geopolymer, slag, strength development

Procedia PDF Downloads 233

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: visual search, deep learning, convolutional neural network, machine learning

Procedia PDF Downloads 188

Authors: Lei Li, Ming M. Chai, Xiao X. Lu, Jia W. Wang

Abstract:

The mixing process of two liquid layers in a cylindrical container includes the upper liquid with higher density rushing into the lower liquid with lighter density, the lower liquid rising into the upper liquid, meanwhile the two liquid layers having interactions with each other, forming vortices, spreading or dispersing in others, entraining or mixing with others. It is a complex process constituted of flow instability, turbulent mixing and other multiscale physical phenomena and having a fast evolution velocity. In order to explore the mechanism of the process and make further investigations, some experiments about the interfacial instability and mixing behavior between two liquid layers bounded in different volumes are carried out, applying the planar laser induced fluorescence (PLIF) and the high speed camera (HSC) techniques. According to the results, the evolution of interfacial instability between immiscible liquid develops faster than theoretical rate given by the Rayleigh-Taylor Instability (RTI) theory. It is reasonable to conjecture that some mechanisms except the RTI play key roles in the mixture process of two liquid layers. From the results, it is shown that the invading velocity of the upper liquid into the lower liquid does not depend on the upper liquid's volume (height). Comparing to the cases that the upper and lower containers are of identical diameter, in the case that the lower liquid volume increases to larger geometric space, the upper liquid spreads and expands into the lower liquid more quickly during the evolution of interfacial instability, indicating that the container wall has important influence on the mixing process. In the experiments of miscible liquid layers’ mixing, the diffusion time and pattern of the liquid interfacial mixing also does not depend on the upper liquid's volumes, and when the lower liquid volume increases to larger geometric space, the action of the bounded wall on the liquid falling and rising flow will decrease, and the liquid interfacial mixing effects will also attenuate. Therefore, it is also concluded that the volume weight of upper heavier liquid is not the reason of the fast interfacial instability evolution between the two liquid layers and the bounded wall action is limited to the unstable and mixing flow. The numerical simulations of the immiscible liquid layers’ interfacial instability flow using the VOF method show the typical flow pattern agree with the experiments. However the calculated instability development is much slower than the experimental measurement. The numerical simulation of the miscible liquids’ mixing, which applying Fick’s diffusion law to the components’ transport equation, shows a much faster mixing rate than the experiments on the liquids’ interface at the initial stage. It can be presumed that the interfacial tension plays an important role in the interfacial instability between the two liquid layers bounded in finite volume.

Keywords: interfacial instability and mixing, two liquid layers, Planar Laser Induced Fluorescence (PLIF), High Speed Camera (HSC), interfacial energy and tension, Cahn-Hilliard Navier-Stokes (CHNS) equations

Procedia PDF Downloads 215

Authors: Weiwei Xie, Yichao Li

Abstract:

The initial installation of the umbilical can affect the subsequent installation process and final installation. Meanwhile, the design of both ends of the ultra-deep water dynamic umbilical (UDWDU), as well as the design of the surface unit and the subsea production system connected by UDWDU,], varies in different oil and gas fields. To optimize the installation process of UDWDU, on the basis of the summary and analysis of the surface-end and the subsea-end design of UDWDU and the mainstream construction resources, the method of initial installation from the surface unit side or the subsea production system side of UDWDU is studied, and each initiation installation method is pointed out if some difficulties that may be encountered.

Keywords: dynamic umbilical, ultra-deep-water, initial installation, installation process

Procedia PDF Downloads 114

Authors: Zhong Ma, Zhuping Wang, Congxin Liu, Xiangzeng Liu

Abstract:

Satellite imagery classification is a challenging problem with many practical applications. In this paper, we designed a deep convolution neural network (DCNN) to classify the satellite imagery. The contributions of this paper are twofold — First, to cope with the large-scale variance in the satellite image, we introduced the inception module, which has multiple filters with different size at the same level, as the building block to build our DCNN model. Second, we proposed a genetic algorithm based method to efficiently search the best hyper-parameters of the DCNN in a large search space. The proposed method is evaluated on the benchmark database. The results of the proposed hyper-parameters search method show it will guide the search towards better regions of the parameter space. Based on the found hyper-parameters, we built our DCNN models, and evaluated its performance on satellite imagery classification, the results show the classification accuracy of proposed models outperform the state of the art method.

Keywords: satellite imagery classification, deep convolution network, genetic algorithm, hyper-parameter optimization

Procedia PDF Downloads 270

Authors: Saif Akram, E. Rathakrishnan

Abstract:

The mixing promoting efficiency of two identical sharp and truncated vertex triangular tabs offering geometrical blockage of 2.5% each, placed at the exit of a Mach 1.5 elliptic nozzle was studied experimentally. The effectiveness of both the tabs in enhancing the mixing of jets with the ambient air are determined by measuring the Pitot pressure along the jet axis and the jet spread in both the minor and major axes of the elliptic nozzle, covering marginally overexpanded to moderately underexpanded levels at the nozzle exit. The results reveal that both the tabs enhance mixing characteristics of the uncontrolled elliptic jet when placed at minor axis. A core length reduction of 67% is achieved at NPR 3 which is the overexpanded state. Similarly, the core length is reduced by about 67%, 50% and 57% at NPRs of 4, 5 and 6 (underexpanded states) respectively. However, unlike the considerable increment in mixing promoting efficiency by the use of truncated vertex tabs for axisymmetric jets, the effect is not much pronounced for the case of supersonic elliptic jets. The CPD plots for both the cases almost overlap, especially when tabs are placed at minor axis, at all the pressure conditions. While, when the tabs are used at major axis, in the case of overexpanded condition, the sharp vertex triangular tabs act as a better mixing enhancer for the supersonic elliptic jets. For the jet controlled with truncated vertex triangular tabs, the core length reductions are of the same order as those for the sharp vertex triangular tabs. The jet mixing is hardly influenced by the tip effect in case of supersonic elliptic jet.

Keywords: elliptic jet, tabs, truncated, triangular

Procedia PDF Downloads 357

Authors: Cheng-Jui Li, Chien-Chou Tseng

Abstract:

This study adopts Computational Fluid Dynamics (CFD) technique to build the multiphase flow numerical model where the interface between the flue gas and desulfurization liquid can be traced by Eulerian-Eulerian model. Inside the tower, the contact of the desulfurization liquid flow from the spray nozzles and flue gas flow can trigger chemical reactions to remove the sulfur dioxide from the exhaust gas. From experimental observations of the industrial scale plant, the desulfurization mechanism depends on the mixing level between the flue gas and the desulfurization liquid. In order to significantly improve the desulfurization efficiency, the mixing efficiency and the residence time can be increased by perforated sieve trays. Hence, the purpose of this research is to investigate the flow structure of sieve trays for the flue gas desulfurization by numerical simulation. In this study, there is an outlet at the top of FGD tower to discharge the clean gas and the FGD tower has a deep tank at the bottom, which is used to collect the slurry liquid. In the major desulfurization zone, the desulfurization liquid and flue gas have a complex mixing flow. Because there are four perforated plates in the major desulfurization zone, which spaced 0.4m from each other, and the spray array is placed above the top sieve tray, which includes 33 nozzles. Each nozzle injects desulfurization liquid that consists of the Mg(OH)2 solution. On each sieve tray, the outside diameter, the hole diameter, and the porosity are 0.6m, 20 mm and 34.3%. The flue gas flows into the FGD tower from the space between the major desulfurization zone and the deep tank can finally become clean. The desulfurization liquid and the liquid slurry goes to the bottom tank and is discharged as waste. When the desulfurization solution flow impacts the sieve tray, the downward momentum will be converted to the upper surface of the sieve tray. As a result, a thin liquid layer can be developed above the sieve tray, which is the so-called the slurry layer. And the volume fraction value within the slurry layer is around 0.3~0.7. Therefore, the liquid phase can't be considered as a discrete phase under the Eulerian-Lagrangian framework. Besides, there is a liquid column through the sieve trays. The downward liquid column becomes narrow as it interacts with the upward gas flow. After the flue gas flows into the major desulfurization zone, the flow direction of the flue gas is upward (+y) in the tube between the liquid column and the solid boundary of the FGD tower. As a result, the flue gas near the liquid column may be rolled down to slurry layer, which developed a vortex or a circulation zone between any two sieve trays. The vortex structure between two sieve trays results in a sufficient large two-phase contact area. It also increases the number of times that the flue gas interacts with the desulfurization liquid. On the other hand, the sieve trays improve the two-phase mixing, which may improve the SO2 removal efficiency.

Keywords: Computational Fluid Dynamics (CFD), Eulerian-Eulerian Model, Flue Gas Desulfurization (FGD), perforated sieve tray

Procedia PDF Downloads 259

Authors: Yitao Lei, Xingxiang Zhai, Burra Venkata Durga Kumar

Abstract:

As the quantity and complexity of computing in large-scale software systems increase, distributed system computing becomes increasingly important. The distributed system realizes high-performance computing by collaboration between different computing resources. If there are no efficient resource scheduling resources, the abuse of distributed computing may cause resource waste and high costs. However, resource scheduling is usually an NP-hard problem, so we cannot find a general solution. However, some optimization algorithms exist like genetic algorithm, ant colony optimization, etc. The large scale of distributed systems makes this traditional optimization algorithm challenging to work with. Heuristic and machine learning algorithms are usually applied in this situation to ease the computing load. As a result, we do a review of traditional resource scheduling optimization algorithms and try to introduce a deep reinforcement learning method that utilizes the perceptual ability of neural networks and the decision-making ability of reinforcement learning. Using the machine learning method, we try to find important factors that influence the performance of distributed system computing and help the distributed system do an efficient computing resource scheduling. This paper surveys the application of deep reinforcement learning on distributed system computing resource scheduling proposes a deep reinforcement learning method that uses a recurrent neural network to optimize the resource scheduling, and proposes the challenges and improvement directions for DRL-based resource scheduling algorithms.

Keywords: resource scheduling, deep reinforcement learning, distributed system, artificial intelligence

Procedia PDF Downloads 82

Authors: Shiyin He, Zheng Huang

Abstract:

In this paper, deep learning methods are applied in bio-medical field to detect and count different types of cells in an automatic way instead of manual work in medical practice, specifically in bone marrow examination. The process is mainly composed of two steps, detection and recognition. Mask-Region-Convolutional Neural Networks (Mask-RCNN) was used for detection and image segmentation to extract cells and then Convolutional Neural Networks (CNN), as well as Deep Residual Network (ResNet) was used to classify. Result of cell detection network shows high efficiency to meet application requirements. For the cell recognition network, two networks are compared and the final system is fully applicable.

Keywords: cell detection, cell recognition, deep learning, Mask-RCNN, ResNet

Procedia PDF Downloads 156

Authors: A. Ersan, A. S. Kipcak, M. Yildirim, A. M. Erayvaz, E. M. Derun, S. Piskin, N. Tugrul

Abstract:

Zinc borates are used as a multi-functional flame retardant additive for its high dehydration temperature. In this study, a new method of ultrasonic mixing was used in the synthesis of zinc borates. The reactants of zinc oxide (ZnO) and boric acid (H3BO3) were used at the constant reaction parameters of 90°C reaction temperature and 55 min of reaction time. Several molar ratios of ZnO:H3BO3 (1:1, 1:2, 1:3, 1:4, and 1:5) were conducted for the determination of the optimum reaction ratio. Prior to the synthesis, the characterization of the synthesized zinc borates were made by X-Ray Diffraction (XRD) and Fourier Transform Infrared Spectroscopy (FT-IR). From the results Zinc Oxide Borate Hydrate [Zn3B6O12.3.5H2O], were synthesized optimum at the molar ratio of 1:3, with a reaction efficiency of 95.2%.

Keywords: zinc borates, ultrasonic mixing, XRD, FT-IR, reaction efficiency

Procedia PDF Downloads 319

Authors: Nuntaporn Aukkanit

Abstract:

The aim of this study was to determine the effect of oils on chemical, physical, and sensory properties of deep-fried dough stick. Five kinds of vegetable oil which were used for addition and frying consist of: palm oil, soybean oil, sunflower oil, rice bran oil, and canola oil. The results of this study showed that using different kinds of oil made significant difference in the quality of deep-fried dough stick. Deep-fried dough stick fried with the rice bran oil had the lowest moisture loss and oil absorption (p≤0.05), but it had some unsatisfactory physical properties (color, specific volume, density, and texture) and sensory characteristics. Nonetheless, deep-fried dough stick fried with the sunflower oil had moisture loss and oil absorption slightly more than the rice bran oil, but it had almost higher physical and sensory properties. Deep-fried dough sticks together with the sunflower oil did not have different sensory score from the palm oil, commonly used for production of deep-fried dough stick. These results indicated that addition and frying with the sunflower oil are appropriate for the production of deep-fried dough stick.

Keywords: deep-fried dough stick, palm oil, sunflower oil, rice bran oil

Procedia PDF Downloads 256

Authors: Sajeeha Ansar, Asad Ali Safi, Sheikh Ziauddin, Ahmad R. Shahid, Faraz Ahsan

Abstract:

Gliomas are most challenging and aggressive type of tumors which appear in different sizes, locations, and scattered boundaries. CNN is most efficient deep learning approach with outstanding capability of solving image analysis problems. A fully automatic deep learning based 2D-CNN model for brain tumor segmentation is presented in this paper. We used small convolution filters (3 x 3) to make architecture deeper. We increased convolutional layers for efficient learning of complex features from large dataset. We achieved better results by pushing convolutional layers up to 16 layers for HGG model. We achieved reliable and accurate results through fine-tuning among dataset and hyper-parameters. Pre-processing of this model includes generation of brain pipeline, intensity normalization, bias correction and data augmentation. We used the BRATS-2015, and Dice Similarity Coefficient (DSC) is used as performance measure for the evaluation of the proposed method. Our method achieved DSC score of 0.81 for complete, 0.79 for core, 0.80 for enhanced tumor regions. However, these results are comparable with methods already implemented 2D CNN architecture.

Keywords: brain tumor segmentation, convolutional neural networks, deep learning, HGG

Procedia PDF Downloads 221

Authors: Youji Miyake

Abstract:

In aircraft assembly, a large number of preparatory holes are required for screw and rivet joints. Currently, many holes are drilled manually because it is difficult to machine the holes using conventional computerized numerical control(CNC) machines. The application of industrial robots to drill the hole has been considered as an alternative to the CNC machines. However, the rigidity of robot arms is so low that vibration is likely to occur during drilling. In this study, it is proposed constant-load feed machining as a method to perform high-precision drilling while minimizing the thrust force, which is considered to be the cause of vibration. In this method, the drill feed is realized by a constant load applied onto the tool so that the thrust force is theoretically kept below the applied load. The performance of the proposed method was experimentally examined through the deep hole drilling of plastic and simultaneous drilling of metal/plastic stack plates. It was confirmed that the deep hole drilling and simultaneous drilling could be performed without generating vibration by controlling the tool feed rate in the appropriate range.

Keywords: constant load feed machining, robotic drilling, deep hole, simultaneous drilling

Procedia PDF Downloads 165

Authors: Khamael M. Abualnaja, Lidija Šiller, Benjamin R. Horrocks

Abstract:

Alkylated silicon nanocrystals (C11-SiNCs) were prepared successfully by galvanostatic etching of p-Si(100) wafers followed by a thermal hydrosilation reaction of 1-undecene in refluxing toluene in order to extract C11-SiNCs from porous silicon. Erbium trichloride was added to alkylated SiNCs using a simple mixing chemical route. To the best of our knowledge, this is the first investigation on mixing SiNCs with erbium ions (III) by this chemical method. The chemical characterization of C11-SiNCs and their mixtures with Er3+ (Er/C11-SiNCs) were carried out using X-ray photoemission spectroscopy (XPS). The optical properties of C11-SiNCs and their mixtures with Er3+ were investigated using Raman spectroscopy and photoluminescence (PL). The erbium-mixed alkylated SiNCs shows an orange PL emission peak at around 595 nm that originates from radiative recombination of Si. Er/C11-SiNCs mixture also exhibits a weak PL emission peak at 1536 nm that originates from the intra-4f transition in erbium ions (Er3+). The PL peak of Si in Er/C11-SiNCs mixture is increased in the intensity up to three times as compared to pure C11-SiNCs. The collected data suggest that this chemical mixing route leads instead to a transfer of energy from erbium ions to alkylated SiNCs.

Keywords: photoluminescence, silicon nanocrystals, erbium, Raman spectroscopy

Procedia PDF Downloads 337

Authors: Ashutosh Mishra, Nikhil Goyal

Abstract:

A 3D facial emotion recognition model based on deep learning is proposed in this paper. Two convolution layers and a pooling layer are employed in the deep learning architecture. After the convolution process, the pooling is finished. The probabilities for various classes of human faces are calculated using the sigmoid activation function. To verify the efficiency of deep learning-based systems, a set of faces. The Kaggle dataset is used to verify the accuracy of a deep learning-based face recognition model. The model's accuracy is about 65 percent, which is lower than that of other facial expression recognition techniques. Despite significant gains in representation precision due to the nonlinearity of profound image representations.

Keywords: facial recognition, computational intelligence, convolutional neural network, depth map

Procedia PDF Downloads 196

Authors: Pawan Kumar Mishra, Ganesh Singh Bisht

Abstract:

Super-resolution is the technique that is being used in computer vision to construct high-resolution images from a single low-resolution image. It is used to increase the frequency component, recover the lost details and removing the down sampling and noises that caused by camera during image acquisition process. High-resolution images or videos are desired part of all image processing tasks and its analysis in most of digital imaging application. The target behind super-resolution is to combine non-repetition information inside single or multiple low-resolution frames to generate a high-resolution image. Many methods have been proposed where multiple images are used as low-resolution images of same scene with different variation in transformation. This is called multi-image super resolution. And another family of methods is single image super-resolution that tries to learn redundancy that presents in image and reconstruction the lost information from a single low-resolution image. Use of deep learning is one of state of art method at present for solving reconstruction high-resolution image. In this research, we proposed Deep Denoising Super Resolution (DDSR) that is a deep neural network for effectively reconstruct the high-resolution image from low-resolution image.

Keywords: resolution, deep-learning, neural network, de-blurring

Procedia PDF Downloads 484

Authors: Shashi Kant Verma, S. L. Sinha, D. K. Chandraker

Abstract:

Numerical simulations of selected subchannel tracer (Potassium Nitrate) based experiments have been performed to study the capabilities of state-of-the-art of Computational Fluid Dynamics (CFD) codes. The Computational Fluid Dynamics (CFD) methodology can be useful for investigating the spacer effect on turbulent mixing to predict turbulent flow behavior such as Dimensionless mixing scalar distributions, radial velocity and vortices in the nuclear fuel assembly. A Gibson and Launder (GL) Reynolds stress model (RSM) has been selected as the primary turbulence model to be applied for the simulation case as it has been previously found reasonably accurate to predict flows inside rod bundles. As a comparison, the case is also simulated using a standard k-ε turbulence model that is widely used in industry. Despite being an isotropic turbulence model, it has also been used in the modeling of flow in rod bundles and to produce lateral velocities after thorough mixing of coolant fairly. Both these models have been solved numerically to find out fully developed isothermal turbulent flow in a 30º segment of a 54-rod bundle. Numerical simulation has been carried out for the study of natural mixing of a Tracer (Passive scalar) to characterize the growth of turbulent diffusion in an injected sub-channel and, afterwards on, cross-mixing between adjacent sub-channels. The mixing with water has been numerically studied by means of steady state CFD simulations with the commercial code STAR-CCM+. Flow enters into the computational domain through the mass inflow at the three subchannel faces. Turbulence intensity and hydraulic diameter of 1% and 5.9 mm respectively were used for the inlet. A passive scalar (Potassium nitrate) is injected through the mass fraction of 5.536 PPM at subchannel 2 (Upstream of the mixing section). Flow exited the domain through the pressure outlet boundary (0 Pa), and the reference pressure was 1 atm. Simulation results have been extracted at different locations of the mixing zone and downstream zone. The local mass fraction shows uniform mixing. The effect of the applied turbulence model is nearly negligible just before the outlet plane because the distributions look like almost identical and the flow is fully developed. On the other hand, quantitatively the dimensionless mixing scalar distributions change noticeably, which is visible in the different scale of the colour bars.

Keywords: single-phase flow, turbulent mixing, tracer, sub channel analysis

Procedia PDF Downloads 184

Authors: Shimaa Holail, Tamer Saleh, Xiongwu Xiao

Abstract:

Building change detection (BCD) from satellite imagery is an essential topic in urbanization monitoring, agricultural land management, and updating geospatial databases. Recently, methods for detecting changes based on deep learning have made significant progress and impressive results. However, it has the problem of being insensitive to changes in buildings with complex spectral differences, and the features being extracted are not discriminatory enough, resulting in incomplete buildings and irregular boundaries. To overcome these problems, we propose a dual Siamese network based on the Unet model with the addition of a deep supervision strategy (DS) in this paper. This network consists of a backbone (encoder) based on ImageNet pre-training, a fusion block, and feature pyramid networks (FPN) to enhance the step-by-step information of the changing regions and obtain a more accurate BCD map. To train the proposed method, we created a new dataset (EGY-BCD) of high-resolution and multi-temporal aerial images captured over New Cairo in Egypt to detect building changes for this purpose. The experimental results showed that the proposed method is effective and performs well with the EGY-BCD dataset regarding the overall accuracy, F1-score, and mIoU, which were 91.6 %, 80.1 %, and 73.5 %, respectively.

Keywords: building change detection, deep supervision, semantic segmentation, EGY-BCD dataset

Procedia PDF Downloads 72

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 32

Authors: Suriya

Abstract:

Rapid socio-economic development and urbanization have led to an increasingly serious air pollution problem in Ulaanbaatar (UB), the capital of Mongolia. PM₂.₅ pollution has become the most pressing aspect of UB air pollution. Therefore, monitoring and predicting PM₂.₅ concentration in UB is of great significance for the health of the local people and environmental management. As of yet, very few studies have used models to predict PM₂.₅ concentrations in UB. Using data from 0:00 on June 1, 2018, to 23:00 on April 30, 2020, we proposed two deep learning models based on Bayesian-optimized LSTM (Bayes-LSTM) and CNN-LSTM. We utilized hourly observed data, including Himawari8 (H8) aerosol optical depth (AOD), meteorology, and PM₂.₅ concentration, as input for the prediction of PM₂.₅ concentrations. The correlation strengths between meteorology, AOD, and PM₂.₅ were analyzed using the gray correlation analysis method; the comparison of the performance improvement of the model by using the AOD input value was tested, and the performance of these models was evaluated using mean absolute error (MAE) and root mean square error (RMSE). The prediction accuracies of Bayes-LSTM and CNN-LSTM deep learning models were both improved when AOD was included as an input parameter. Improvement of the prediction accuracy of the CNN-LSTM model was particularly enhanced in the non-heating season; in the heating season, the prediction accuracy of the Bayes-LSTM model slightly improved, while the prediction accuracy of the CNN-LSTM model slightly decreased. We propose two novel deep learning models for PM₂.₅ concentration prediction in UB, Bayes-LSTM, and CNN-LSTM deep learning models. Pioneering the use of AOD data from H8 and demonstrating the inclusion of AOD input data improves the performance of our two proposed deep learning models.

Keywords: deep learning, AOD, PM2.5, prediction, Ulaanbaatar

Procedia PDF Downloads 13

Authors: Arefeh Arabaninezhad, Ali Fakher

Abstract:

Since the deterministic analysis methods fail to take system uncertainties into account, probabilistic and non-probabilistic methods are suggested. Geotechnical analyses are used to determine the stress and deformation caused by construction; accordingly, many input variables which depend on ground behavior are required for geotechnical analyses. The Random Set approach is an applicable reliability analysis method when comprehensive sources of information are not available. Using Random Set method, with relatively small number of simulations compared to fully probabilistic methods, smooth extremes on system responses are obtained. Therefore random set approach has been proposed for reliability analysis in geotechnical problems. In the present study, the application of random set method in reliability analysis of deep excavations is investigated through three deep excavation projects which were monitored during the excavating process. A finite element code is utilized for numerical modeling. Two expected ranges, from different sources of information, are established for each input variable, and a specific probability assignment is defined for each range. To determine the most influential input variables and subsequently reducing the number of required finite element calculations, sensitivity analysis is carried out. Input data for finite element model are obtained by combining the upper and lower bounds of the input variables. The relevant probability share of each finite element calculation is determined considering the probability assigned to input variables present in these combinations. Horizontal displacement of the top point of excavation is considered as the main response of the system. The result of reliability analysis for each intended deep excavation is presented by constructing the Belief and Plausibility distribution function (i.e. lower and upper bounds) of system response obtained from deterministic finite element calculations. To evaluate the quality of input variables as well as applied reliability analysis method, the range of displacements extracted from models has been compared to the in situ measurements and good agreement is observed. The comparison also showed that Random Set Finite Element Method applies to estimate the horizontal displacement of the top point of deep excavation. Finally, the probability of failure or unsatisfactory performance of the system is evaluated by comparing the threshold displacement with reliability analysis results.

Keywords: deep excavation, random set finite element method, reliability analysis, uncertainty

Procedia PDF Downloads 243

Authors: Debneil Saha Roy

Abstract:

Weather forecasting is a complex topic and is well suited for analysis by deep learning approaches. With the wide availability of weather observation data nowadays, these approaches can be utilized to identify immediate comparisons between historical weather forecasts and current observations. This work explores the application of deep learning techniques to weather forecasting in order to accurately predict the weather over a given forecast hori­zon. Three deep neural networks are used in this study, namely, Multi-Layer Perceptron (MLP), Long Short Tunn Memory Network (LSTM) and a combination of Convolutional Neural Network (CNN) and LSTM. The predictive performance of these models is compared using two evaluation metrics. The results show that forecasting accuracy increases with an increase in the complexity of deep neural networks.

Keywords: convolutional neural network, deep learning, long short term memory, multi-layer perceptron

Procedia PDF Downloads 137

Authors: Prima Khairunisa, Febriana Tri Kusumawati, Endah Luthfiana

Abstract:

Background: Hypertension in elderly, caused by cardiovascular system cannot work normally, because the valves thickened and inelastic blood vessels. It causes vasoconstriction of the blood vessels. Hypertension exercise, increase cardiovascular function and the elasticity of the blood vessels. While slow deep breathing helps the body and mind feel relax. Combination both of them will decrease the blood pressure. Objective: To know the effect of hypertension exercise and slow deep breathing combination to blood pressure in elderly. Method: The study conducted with one group pre-post test experimental design. The samples were 10 elderly both male and female in a Village in Semarang, Central Java, Indonesia. The tool was manual sphygmomanometer to measure blood pressure. Result: Based on paired t-test between hypertension exercise and slow deep breathing with systole blood pressure showed sig (2-tailed) was 0.045, while paired t-test between hypertension exercise hypertension exercise and slow deep breathing with diastole blood pressure showed sig (2-tailed) was 0,343. The changes of systole blood pressure were 127.5 mmHg, and diastole blood pressure was 80 mmHg. Systole blood pressure decreases significantly because the average of systole blood pressure before implementation was 135-160 mmHg. While diastole blood pressure was not decreased significantly. It was influenced by the average of diastole blood pressure before implementation of hypertension exercise was not too high. It was between 80- 90 mmHg. Conclusion: There was an effect of hypertension exercise and slow deep breathing combination to the blood pressure in elderly after 6 times implementations.

Keywords: hypertension exercise, slow deep breathing, elderly, blood pressure

Procedia PDF Downloads 315

Authors: Binod Duwadi

Abstract:

This article examines the language and literacy practices of English Code-mixing in Nepalese Classroom. Situating the study within an ecological framework, a systematic functional linguistic (SFL) approach was used to analyze students writing in two Neplease schools. Data collection included interviews with teachers, classroom observations, instructional materials, and focal students’ writing samples. Data analyses revealed vastly different language ecologies between the schools owing to sharp socioeconomic stratification, the structural organization of schools, and the pervasiveness of standard language ideology, with stigmatizes English code mixing (ECM) and privileges Standard English in schools. Functional analysis of students’ writing showed that the nature of the writing tasks at the schools created different affordances for exploiting lexicogrammatically choices for meaning making-enhancing them in the case of one school but severely restricting them in the case of another- perpetuating the academic disadvantage for code mixing speakers. Recommendations for structural and attitudinal changes through teacher training and implementation of approaches that engage students’ bidialectal competence for learning are made as important first steps towards addressing educational inequities in Nepalese schools.

Keywords: code-mixing, ecological perspective, systematic functional approach, language and identity

Procedia PDF Downloads 102

Authors: Basiliyos Tilahun Betru, Charles Awono Onana, Bernabe Batchakui

Abstract:

Recommender systems have become increasingly popular in recent years, and are utilized in numerous areas. Nowadays many web services provide several information for users and recommender systems have been developed as critical element of these web applications to predict choice of preference and provide significant recommendations. With the help of the advantage of deep learning in modeling different types of data and due to the dynamic change of user preference, building a deep model can better understand users demand and further improve quality of recommendation. In this paper, deep neural network models for recommender system are evaluated. Most of deep neural network models in recommender system focus on the classical collaborative filtering user-item setting. Deep learning models demonstrated high level features of complex data can be learned instead of using metadata which can significantly improve accuracy of recommendation. Even though deep learning poses a great impact in various areas, applying the model to a recommender system have not been fully exploited and still a lot of improvements can be done both in collaborative and content-based approach while considering different contextual factors.

Keywords: big data, decision making, deep learning, recommender system

Procedia PDF Downloads 440