Search results for: deep layer

Authors: Ahmed Negm, George Aggidis, Xiandong Ma

Abstract:

With the diverse nature of urban cities, customer demand patterns, landscape topologies or even seasonal weather trends; managing our water distribution networks (WDNs) has proved a complex task. These unpredictable circumstances manifest as pipe failures, intermittent supply and burst events thus adding to water loss, energy waste and increased carbon emissions. Whilst these events are unavoidable, advanced pressure management has proved an effective tool to control and mitigate them. Henceforth, water utilities have struggled with developing a real-time control method that is resilient when confronting the challenges of water distribution. In this paper we use deep reinforcement learning (DRL) algorithms as a novel pressure control strategy to minimise pressure violations and leakage under both burst and background leakage conditions. Agents based on asynchronous actor critic (A2C) and recurrent proximal policy optimisation (Recurrent PPO) were trained and compared to benchmarked optimisation algorithms (differential evolution, particle swarm optimisation. A2C manages to minimise leakage by 32.48% under burst conditions and 67.17% under background conditions which was the highest performance in the DRL algorithms. A2C and Recurrent PPO performed well in comparison to the benchmarks with higher processing speed and lower computational effort.

Keywords: deep reinforcement learning, pressure management, water distribution networks, leakage management

Procedia PDF Downloads 92

Authors: M. K. Bin Subhan, P. Cullen, C. Howard

Abstract:

A recent study by the World Corrosion Organization estimated that corrosion related damage causes $2.5tr worth of damage every year. As such, a low cost easily scalable solution is required to the corrosion problem which is economically viable. Graphene is an ideal anti-corrosion barrier layer material due to its excellent barrier properties and chemical stability, which makes it impermeable to all molecules. However, attempts to employ graphene as a barrier layer has been hampered by the fact that defect sites in graphene accelerate corrosion due to the inert nature of graphene which promotes galvanic corrosion at the expense of the metal. The recent discovery of spontaneous dissolution of charged graphite intercalation compounds in aprotic solvents enables defect free graphene platelets to be employed for anti-corrosion applications. These ‘inks’ of defect-free charged graphene platelets in solution can be coated onto a metallic surfaces via electroplating to form a homogeneous barrier layer. In this paper, initial data showing homogeneous coatings of graphene barrier layers on steel coupons via electroplating will be presented. This easily scalable technique also provides a controllable method for applying different barrier thicknesses from ultra thin layers to thick opaque coatings making it useful for a wide range of applications.

Keywords: anti-corrosion, defect-free, electroplating, graphene

Procedia PDF Downloads 131

Authors: Olga S. Volodko, Lidiya A. Kompaniets, Ludmila V. Gavrilova

Abstract:

The method of empirical orthogonal functions is the method of data analysis with a complex spatial-temporal structure. This method allows us to decompose the data into a finite number of modes determined by empirically finding the eigenfunctions of data correlation matrix. The modes have different scales and can be associated with various physical processes. The empirical orthogonal function method has been widely used for the analysis of hydrophysical characteristics, for example, the analysis of sea surface temperatures in the Western North Atlantic, ocean surface currents in the North Carolina, the study of tropical wave disturbances etc. The method used in this study has been applied to the analysis of temperature and velocity measurements in saline Lake Shira (Southern Siberia, Russia). Shira is a shallow lake with the maximum depth of 25 m. The lake Shira can be considered as a closed water site because of it has one small river providing inflow and but it has no outflows. The main factor that causes the motion of fluid is variable wind flows. In summer the lake is strongly stratified by temperature and saline. Long-term measurements of the temperatures and currents were conducted at several points during summer 2014-2015. The temperature has been measured with an accuracy of 0.1 ºC. The data were analyzed using the empirical orthogonal function method in the real version. The first empirical eigenmode accounts for 70-80 % of the energy and can be interpreted as temperature distribution with a thermocline. A thermocline is a thermal layer where the temperature decreases rapidly from the mixed upper layer of the lake to much colder deep water. The higher order modes can be interpreted as oscillations induced by internal waves. The currents measurements were recorded using Acoustic Doppler Current Profilers 600 kHz and 1200 kHz. The data were analyzed using the empirical orthogonal function method in the complex version. The first empirical eigenmode accounts for about 40 % of the energy and corresponds to the Ekman spiral occurring in the case of a stationary homogeneous fluid. Other modes describe the effects associated with the stratification of fluids. The second and next empirical eigenmodes were associated with dynamical modes. These modes were obtained for a simplified model of inhomogeneous three-level fluid at a water site with a flat bottom.

Keywords: Ekman spiral, empirical orthogonal functions, data analysis, stratified fluid, thermocline

Procedia PDF Downloads 136

Authors: R. Alias, A. Kasa, M. R. Taha

Abstract:

The effect of particle size on shear strength of granular materials are investigated using direct shear tests. Small direct shear test (60 mm by 60 mm by 24 mm deep) were conducted for particles passing the sieves with opening size of 2.36 mm. Meanwhile, particles passing the standard 20 mm sieves were tested using large direct shear test (300 mm by 300 mm by 200 mm deep). The large direct shear tests and the small direct shear tests carried out using the same shearing rate of 0.09 mm/min and similar normal stresses of 100, 200, and 300 kPa. The results show that the peak and residual shear strength decreases as particle size increases.

Keywords: particle size, shear strength, granular material, direct shear test

Procedia PDF Downloads 489

Authors: Ali Ahmed Ali Al-Juboori, H. Zhu, D. Wexler, H. Li, C. Lu, J. McLeod, S. Pannila, J. Barnes

Abstract:

A number of studies have focused on the formation mechanics of white etching layer and its origin in the railway operation. Until recently, the following hypotheses consider the precise mechanics of WELs formation: (i) WELs are the result of thermal process caused by wheel slip; (ii) WELs are mechanically induced by severe plastic deformation; (iii) WELs are caused by a combination of thermo-mechanical process. The mechanisms discussed above lead to occurrence of white etching layers on the area of wheel and rail contact. This is because the contact patch which is the active point of the wheel on the rail is exposed to highest shear stresses which result in localised severe plastic deformation; and highest rate of heat caused by wheel slipe during excessive traction or braking effort. However, if the WELs are not on the running band area, it would suggest that there is another cause of WELs formation. In railway system, particularly electrified railway, arcing phenomenon has been occurring more often and regularly on the rails. In electrified railway, the current is delivered to the train traction motor via contact wires and then returned to the station via the contact between the wheel and the rail. If the contact between the wheel and the rail is temporarily losing, due to dynamic vibration, entrapped dirt or water, lubricant effect or oxidation occurrences, high current can jump through the gap and results in arcing. The other resources of arcing also include the wheel passage the insulated joint and lightning on a train during bad weather. During the arcing, an extensive heat is generated and speared over a large area of top surface of rail. Thus, arcing is considered another heat source in the rail head (rather than wheel slipe) that results in microstructural changes and white etching layer formation. A head hardened (HH) rail steel, cut from a curved rail truck was used for the investigation. Samples were sectioned from a depth of 10 mm below the rail surface, where the material is considered to be still within the hardened layer but away from any microstructural changes on the top surface layer caused by train passage. These samples were subjected to electrical discharges by using Gas Tungsten Arc Welding (GTAW) machine. The arc current was controlled and moved along the samples surface in the direction of travel, as indicated by an arrow. Five different conditions were applied on the surface of the samples. Samples containing pre-existed WELs, taken from ex-service rail surface, were also considered in this study for comparison. Both simulated and ex-serviced WELs were characterised by advanced methods including SEM, TEM, TKD, EDS, XRD. Samples for TEM and TKFD were prepared by Focused Ion Beam (FIB) milling. The results showed that both simulated WELs by electrical arcing and ex-service WEL comprise similar microstructure. Brown etching layer was found with WELs and likely induced by a concurrent tempering process. This study provided a clear understanding of new formation mechanics of WELs which contributes to track maintenance procedure.

Keywords: white etching layer, arcing, brown etching layer, material characterisation

Procedia PDF Downloads 121

Authors: Malihe Moeinin, Robert Hill, Ferranti Wong

Abstract:

Background: A white spot lesion (WSL) is defined as subsurface enamel porosity from carious demineralisation on the smooth surfaces of the tooth. It appears as a milky white opacity. Lesions shown an apparently intact surface layer, followed underneath by the more porous lesion body. The small pores within the body of the lesion act as diffusion pathway for both acids and minerals, so allowing the demineralisation of enamel to occur at the advancing front of the lesion. Objectives: The objective is to mapthe porosity and its size on WSL with Focused Ion Bean- Scanning Electron Microscopy (FIB-SEM) Method: The basic method used for FIB-SEM consisted of depositing a one micron thick layer of platinum over 25μmx 25μm of the interest region of enamel. Then, making a rough cut (25μmx 5μmx 20μm) with 3nA current and 30Kv was applied with the help of drift suppression (DS), using a standard “cross-sectional” cutting pattern, which ended at the front of the deposited platinum layer. Two adjacent areas (25μmx 5μmx 20μm) on the both sides of the platinum layer were milled under the same conditions. Subsequent, cleaning cross-sections were applied to polish the sub-surface edge of interest running perpendicular to the surface. The "slice and view" was carried out overnight for milling almost 700 slices with 2Kv and 4nA and taking backscattered (BS) images. Then, images were imported into imageJ and analysed. Results: The prism structure is clearly apparent on FIB-SEM slices of WSL with the dissolution of prism boundaries as well as internal porosity within the prism itself. Porosity scales roughly 100-400nm, which is comparable to the light wavelength (500nm). Conclusion: FIB-SEM is useful to characterize the porosity of WSL and it clearly shows the difference between WSL and normal enamel.

Keywords: white spot lesion, FIB-SEM, enamel porosity, porosity

Procedia PDF Downloads 94

Authors: Sharifullah Ahmed

Abstract:

Residual settlement of cohesionless or non-plastic soil of different strength underlying highway embankment overlain by stronger soil layer highway embankment is studied. A parametric study is carried out for different height of embankment and for different ESAL factor. The sum of elastic settlements of cohesionless subsoil due to axle induced stress and due to self-weight of pavement layers is termed as the residual settlement. The values of residual settlement (Sr) for different heights of road embankment (He) are obtained and presented as design charts for different SPT Value (N60) and ESAL factor. For rigid pavement and flexible pavement in approach to bridge or culvert, the tolerable residual settlement is 0.100m. This limit is taken as 0.200m for flexible pavement in general sections of highway without approach to bridge or culvert. A simplified guideline is developed for design of highway embankment underlain by very loose to loose cohesionless subsoil overlain by a stronger soil layer for limiting value of the residual settlement. In the current research study range of ESAL factor is 1-10 and range of SPT value (N60) is 1-10. That is found that, ground improvement is not required if the overlying stronger layer is minimum 1.5m and 4.0m for general road section of flexible pavement except bridge or culvert approach and for rigid pavement or flexible pavement in bridge or culvert approach. Tables and charts are included in the prepared guideline to obtain minimum allowable height of highway embankment to limit the residual settlement with in mentioned tolerable limit. Allowable values of the embankment height (He) are obtained corresponding to tolerable or limiting level of the residual settlement of loose subsoil for different SPT value, thickness of stronger layer (d) and ESAL factor. The developed guideline is may be issued to be used in assessment of the necessity of ground improvement in case of cohesionless subsoil underlying highway embankment overlain by stronger subsoil layer for limiting residual settlement. The ground improvement is only to be required if the residual settlement of subsoil is more than tolerable limit.

Keywords: axle pressure, equivalent single axle load, ground improvement, highway embankment, tolerable residual settlement

Procedia PDF Downloads 127

Authors: Endrick Barnacin, Jean-Luc Henry, Jimmy Nagau, Jack Molinie

Abstract:

Palynology is a field of interest in many disciplines due to its multiple applications: chronological dating, climatology, allergy treatment, and honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time consuming task that requires the intervention of experts in the field, which are becoming increasingly rare due to economic and social conditions. That is why the need for automation of this task is urgent. A lot of studies have investigated the subject using different standard image processing descriptors and sometimes hand-crafted ones.In this work, we make a comparative study between classical feature extraction methods (Shape, GLCM, LBP, and others) and Deep Learning (CNN, Autoencoders, Transfer Learning) to perform a recognition task over 80 regional pollen species. It has been found that the use of Transfer Learning seems to be more precise than the other approaches

Keywords: pollens identification, features extraction, pollens classification, automated palynology

Procedia PDF Downloads 137

Authors: Anshika Kankane, Dongshik Kang

Abstract:

Marine debris has a significant influence on coastal environments, damaging biodiversity, and causing loss and damage to marine and ocean sector. A functional cost-effective and automatic approach has been used to look up at this problem. Computer vision combined with a deep learning-based model is being proposed to identify and categorize marine debris of seven kinds on different beach locations of Japan. This research compares state-of-the-art deep learning models with a suggested model architecture that is utilized as a feature extractor for debris categorization. The model is being proposed to detect seven categories of litter using a manually constructed debris dataset, with the help of Mask R-CNN for instance segmentation and a shape matching network called HOGShape, which can then be cleaned on time by clean-up organizations using warning notifications of the system. The manually constructed dataset for this system is created by annotating the images taken by fixed KaKaXi camera using CVAT annotation tool with seven kinds of category labels. A pre-trained HOG feature extractor on LIBSVM is being used along with multiple templates matching on HOG maps of images and HOG maps of templates to improve the predicted masked images obtained via Mask R-CNN training. This system intends to timely alert the cleanup organizations with the warning notifications using live recorded beach debris data. The suggested network results in the improvement of misclassified debris masks of debris objects with different illuminations, shapes, viewpoints and litter with occlusions which have vague visibility.

Keywords: computer vision, debris, deep learning, fixed live camera images, histogram of gradients feature extractor, instance segmentation, manually annotated dataset, multiple template matching

Procedia PDF Downloads 107

Authors: Milagros Jaén-Vargas, Javier García Martínez, Karla Miriam Reyes Leiva, María Fernanda Trujillo-Guerrero, Francisco Fernandes, Sérgio Barroso Gonçalves, Miguel Tavares Silva, Daniel Simões Lopes, José Javier Serrano Olmedo

Abstract:

Human Activity Recognition (HAR) is having a growing impact in creating new applications and is responsible for emerging new technologies. Also, the use of wearable sensors is an important key to exploring the human body's behavior when performing activities. Hence, the use of these dispositive is less invasive and the person is more comfortable. In this study, a database that includes three activities is used. The activities were acquired from inertial measurement unit sensors (IMU) and motion capture systems (MOCAP). The main objective is differentiating the performance from four Deep Learning (DL) models: Deep Neural Network (DNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and hybrid model Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), when considering acceleration, velocity and position and evaluate if integrating the IMU acceleration to obtain velocity and position represent an increment in performance when it works as input to the DL models. Moreover, compared with the same type of data provided by the MOCAP system. Despite the acceleration data is cleaned when integrating, results show a minimal increase in accuracy for the integrated signals.

Keywords: HAR, IMU, MOCAP, acceleration, velocity, position, feature maps

Procedia PDF Downloads 98

Authors: Mohammad A. Sazzad, Md M. Alam

Abstract:

Wind energy is one of the cleanest form of renewable energy. Despite wind industry is growing faster than ever there are some roadblocks towards the improvement. One of the difficulties the industry facing is insufficient knowledge about wake within the wind farms. As we know energy is generated in the lowest layer of the atmospheric boundary layer (ABL). This interaction between the wind turbine (WT) blades and wind introduces a low speed wind region which is defined as wake. This wake region shows different characteristics under each stability condition of the ABL. So, it is fundamental to know this wake region well which is defined mainly by turbulence transport and wake shear. Defining the wake recovery length and width are very crucial for wind farm to optimize the generation and reduce the waste of power to the grid. Therefore, in order to obtain the turbulent coefficients of velocity and length, this research focused on the large eddy simulation (LES) data for neutral ABL (NABL). According to turbulent theory, if we can present velocity defect and Reynolds stress in the form of local length and velocity scales, they become invariant. In our study velocity and length coefficients are 0.4867 and 0.4794 respectively which is close to the theoretical value of 0.5 for NABL. There are some invariant profiles because of the presence of thermal and wind shear power coefficients varied a little from the ideal condition.

Keywords: atmospheric boundary layer, renewable energy, turbulent coefficient, wind turbine, wake

Procedia PDF Downloads 132

Authors: Apolinar Picado, Steve Alfaro, Rafael Gamero

Abstract:

Energy and exergy analyses of thin-layer drying of pineapple slices (Ananas comosus L.) were conducted in a laboratory tunnel dryer. Drying experiments were carried out at three temperatures (100, 115 and 130 °C) and an air velocity of 1.45 m/s. The effects of drying variables on energy utilisation, energy utilisation ratio, exergy loss and exergy efficiency were studied. The enthalpy difference of the gas increased as the inlet gas temperature increase. It is observed that at the 75 minutes of the drying process the outlet gas enthalpy achieves a maximum value that is very close to the inlet value and remains constant until the end of the drying process. This behaviour is due to the reduction of the total enthalpy within the system, or in other words, the reduction of the effective heat transfer from the hot gas flow to the vegetable being dried. Further, the outlet entropy exhibits a significant increase that is not only due to the temperature variation, but also to the increase of water vapour phase contained in the hot gas flow. The maximum value of the exergy efficiency curve corresponds to the maximum value observed within the drying rate curves. This maximum value represents the stage when the available energy is efficiently used in the removal of the moisture within the solid. As the drying rate decreases, the available energy is started to be less employed. The exergetic efficiency was directly dependent on the evaporation flux and since the convective drying is less efficient that other types of dryer, it is likely that the exergetic efficiency has relatively low values.

Keywords: efficiency, energy, exergy, thin-layer drying

Procedia PDF Downloads 255

Authors: Wen Cai Ng, Saman Ilankoon, Meng Nan Chong

Abstract:

The vast increase in global energy demand, coupled with the growing concerns on environmental issues, has triggered the search for cleaner alternative energy sources. In view of this, the photoelectrochemical (PEC) water splitting offers a sustainable hydrogen (H2) production route that only requires solar energy, water, and PEC system operating in an ambient environment. However, the current advancement of PEC water splitting technologies is still far from the commercialization benchmark indicated by the solar-to-H2 (STH) efficiency of at least 10 %. This is largely due to the shortcomings of photoelectrodes used in the PEC system, such as the rapid recombination of photogenerated charge carriers and limited photo-responsiveness in the visible-light spectrum. Silver orthophosphate (Ag3PO4) possesses many desirable intrinsic properties for the fabrication into photoanode used in PEC systems, such as narrow bandgap of 2.4 eV and low valence band (VB) position. Hence, in this study, a highly efficient Ag3PO4-based photoanode was synthesized and characterized. The surface of the Ag foil substrate was directly oxidized to fabricate a top layer composed of {111}-bound Ag3PO4 tetrahedrons layer with a porous structure, forming the dual-layer Ag/Ag3PO4 photoanode. Furthermore, the key synthesis parameters were systematically investigated by varying the concentration ratio of capping agent-to-precursor (R), the volume ratio of hydrogen peroxide (H2O2)-to-water, and reaction period. Results showed that the optimized dual-layer Ag/Ag3PO4 photoanode achieved a photocurrent density as high as 4.19 mA/cm2 at 1 V vs. Ag/AgCl for the R-value of 4, the volume ratio of H2O2-to-water of 3:5 and 20 h reaction period. The current work provides a solid foundation for further nanoarchitecture modification strategies on Ag3PO4-based photoanodes for more efficient PEC water splitting applications. This piece of information needs to be backed up by evidence; therefore, you need to provide a reference. As the abstract should be self-contained, all information requiring a reference should be removed. This is a fact known to the area of research, and not necessarily required a reference to support.

Keywords: solar-to-hydrogen fuel, photoelectrochemical water splitting, photoelectrode, silver orthophosphate

Procedia PDF Downloads 121

Authors: Shady Adib, Vladimir Vinogradov, Peter Gosling

Abstract:

Digital Twin (DT) technology is a new technology that appeared in the early 21st century. The DT is defined as the digital representation of living and non-living physical assets. By connecting the physical and virtual assets, data are transmitted smoothly, allowing the virtual asset to fully represent the physical asset. Although there are lots of studies conducted on the DT concept, there is still limited information about the ability of the DT models for monitoring and detecting unexpected changes in structural behaviour in real time. This is due to the large computational efforts required for the analysis and an excessively large amount of data transferred from sensors. This paper aims to develop the DT concept to be able to detect the abnormal changes in structural behaviour in real time using advanced modelling techniques, deep learning algorithms, and data acquisition systems, taking into consideration model uncertainties. finite element (FE) models were first developed offline to be used with a reduced basis (RB) model order reduction technique for the construction of low-dimensional space to speed the analysis during the online stage. The RB model was validated against experimental test results for the establishment of a DT model of a two-dimensional truss. The established DT model and deep learning algorithms were used to identify the location of damage once it has appeared during the online stage. Finally, the RB model was used again to identify the damage severity. It was found that using the RB model, constructed offline, speeds the FE analysis during the online stage. The constructed RB model showed higher accuracy for predicting the damage severity, while deep learning algorithms were found to be useful for estimating the location of damage with small severity.

Keywords: data acquisition system, deep learning, digital twin, model uncertainties, reduced basis, reduced order model

Procedia PDF Downloads 99

Authors: Ibnorachid Zakaria, El Bikri Khalid, Benamar Rhali, Farah Abdoun

Abstract:

The aim of the present work is to study the linear free symmetric vibration of three-layer sandwich beam using the energy method. The zigzag model is used to describe the displacement field. The theoretical model is based on the top and bottom layers behave like Euler-Bernoulli beams while the core layer like a Timoshenko beam. Based on Hamilton’s principle, the governing equation of motion sandwich beam is obtained in order to calculate the linear frequency parameters for a clamped-clamped and simple supported-simple-supported beams. The effects of material properties and geometric parameters on the natural frequencies are also investigated.

Keywords: linear vibration, sandwich, shear deformation, Timoshenko zig-zag model

Procedia PDF Downloads 474

Authors: Rahma Abed, Sahbi Bahroun, Ezzeddine Zagrouba

Abstract:

Due to the huge amount of data in videos, extracting the relevant frames became a necessity and an essential step prior to performing face recognition. In this context, we propose a method for extracting keyframes from videos based on face quality and deep learning for a face recognition task. This method has two steps. We start by generating face quality scores for each face image based on the use of three face feature extractors, including Gabor, LBP, and HOG. The second step consists in training a Deep Convolutional Neural Network in a supervised manner in order to select the frames that have the best face quality. The obtained results show the effectiveness of the proposed method compared to the methods of the state of the art.

Keywords: keyframe extraction, face quality assessment, face in video recognition, convolution neural network

Procedia PDF Downloads 234

Authors: Ehsan Heidaryan

Abstract:

Gas hydrate sediments are ice like permafrost in deep see and oceans. Methane production in sequestration process and reducing atmospheric carbon dioxide, a main source of greenhouse gas, has been accentuated recently. One focus is capture, separation, and sequestration of industrial carbon dioxide. As a hydrate former, carbon dioxide forms hydrates at moderate temperatures and pressures. This phenomenon could be utilized to capture and separate carbon dioxide from flue gases, and also has the potential to sequester carbon dioxide in the deep seabeds. This research investigated the effect of synthetic surfactants on carbon dioxide hydrate formation, catalysis and consequently, methane production from hydrate permafrosts in sediments. It investigated the sequestration potential of carbon dioxide hydrates in ocean sediments. Also, the catalytic effect of biosurfactants in these processes was investigated.

Keywords: carbon dioxide, hydrate, sequestration, surfactant

Procedia PDF Downloads 437

Authors: M. O. Ezegbogu, H. B. Osadolor

Abstract:

Lipsticks constitute a significant source of transfer evidence, and can, therefore, provide corroborative or inclusionary evidence in criminal investigation. This study aimed to determine the uniqueness and persistence of different lipstick smears using Thin Layer Chromatography (TLC), and Gas Chromatography with a Flame Ionisation Detector (GC-FID). In this study, we analysed lipstick smears retrieved from tea cups exposed to the environment for up to four weeks. The n-alkane content of each sample was determined using GC-FID, while TLC was used to determine the number of bands, and retention factor of each band per smear. This study shows that TLC gives more consistent results over a 4-week period than GC-FID. It also proposes a maximum exposure time of two weeks for the analysis of lipsticks left in the open using GC-FID. Finally, we conclude that neither TLC nor GC-FID can distinguish lipstick evidence recovered from hypothetical crime scenes.

Keywords: forensic science, chromatography, identification, lipstick

Procedia PDF Downloads 187

Authors: Martin K. Steiger, Lukas Heisler, Hans-Georg Brachtendorf

Abstract:

Deep neural networks and their variants form the backbone of many AI applications. Based on the so-called residual networks, a continuous formulation of such models as ordinary differential equations (ODEs) has proven advantageous since different techniques may be applied that significantly increase the learning speed and enable controlled trade-offs with the resulting error at the same time. For the evaluation of such models, high-performance numerical differential equation solvers are used, which also provide the gradients required for training. However, whether classical gradient-based methods are even applicable or which one yields the best results has not been discussed yet. This paper aims to redeem this situation by providing empirical results for different applications.

Keywords: deep neural networks, gradient-based learning, image processing, ordinary differential equation networks

Procedia PDF Downloads 168

Authors: Simone Leonardi, Luca Ardito

Abstract:

Micro-influencers are effective elements in the marketing strategies of companies and institutions because of their capability to create an hyper-engaged audience around a specific topic of interest. In recent years, many scientific approaches and commercial tools have handled the task of detecting this type of social media users. These strategies adopt solutions ranging from rule based machine learning models to deep neural networks and graph analysis on text, images, and account information. This work compares the existing solutions and proposes an ensemble method to generalize them with different input data and social media platforms. The deployed solution combines deep learning models on unstructured data with statistical machine learning models on structured data. We retrieve both social media accounts information and multimedia posts on Twitter and Instagram. These data are mapped into feature vectors for an eXtreme Gradient Boosting (XGBoost) classifier. Sixty different topics have been analyzed to build a rule based gold standard dataset and to compare the performances of our approach against baseline classifiers. We prove the effectiveness of our work by comparing the accuracy, precision, recall, and f1 score of our model with different configurations and architectures. We obtained an accuracy of 0.91 with our best performing model.

Keywords: deep learning, gradient boosting, image processing, micro-influencers, NLP, social media

Procedia PDF Downloads 183

Authors: Anwar Ul Haque, Waqar Asrar, Erwin Sulaeman, Jaffar S. M. Ali

Abstract:

Pressure distribution data of the standard airfoils is usually used for the calibration purposes in subsonic wind tunnels. Results of such experiments are quite old and obtained by using the model in the spanwise direction. In this manuscript, pressure distribution over NACA 4412 airfoil model was presented by placing the 3D model in the lateral direction. The model is made of metal with pressure ports distributed longitudinally as well as in the lateral direction. The pressure model was attached to the floor of the tunnel with the help of the base plate to give the specified angle of attack to the model. Before the start of the experiments, the pressure tubes of the respective ports of the 128 ports pressure scanner are checked for leakage, and the losses due to the length of the pipes were also incorporated in the results for the specified pressure range. Growth rate maps of the boundary layer thickness were also plotted. It was found that with the increase in the velocity, the dynamic pressure distribution was also increased for the alpha seep. Plots of pressure distribution so obtained were overlapped with those obtained by using XFLR software, a low fidelity tool. It was found that at moderate and high angles of attack, the distribution of the pressure coefficients obtained from the experiments is high when compared with the XFLR ® results obtained along with the span of the wing. This under-prediction by XFLR ® is more obvious on the windward than on the leeward side.

Keywords: subsonic flow, boundary layer, wind tunnel, pressure testing

Procedia PDF Downloads 320

Authors: Fayssal Ynineb, Toufik Hadjersi, Fatsah Moulai, Wafa Achour

Abstract:

Currently, tremendous attention has been paid to the rational design and synthesis of core/shell heterostructures for high-performance supercapacitors. In this study, the hierarchical NiO/ZnCo₂O₄ Core-Shell Nanorods Arrays were successfully deposited onto ITO substrate via a two-step hydrothermal and electrodeposition methods. The effect of the thin carbon layer between NiO and ZnCo₂O₄ in this multi-scale hierarchical structure was investigated. The selection of this structure was based on: (i) a high specific area of pseudo-capacitive NiO to maximize specific capacitance; (ii) an effective NiO-electrolyte interface to facilitate fast charging/discharging; and (iii) conducting carbon layer between ZnCo₂O₄ and NiO enhance the electric conductivity which reduces energy loss, and the corrosion protection of ZnCo₂O₄ in alkaline electrolyte. The obtained results indicate that hierarchical NiO/ZnCo₂O₄ present a high specific capacitance of 63 mF.cm⁻² at a current density of 0.05 mA.cm⁻² higher than that of pristine NiO and ZnCo₂O₄ of 6 and 3 mF.cm⁻², respectively. The carbon layer improves the electrical conductivity among NiO and ZnCo₂O₄ in the hierarchical NiO/C/ZnCo₂O₄ electrode. As well, the specific capacitance drastically increased to reach 125 mF.cm⁻². Moreover, this multi-scale hierarchical structure exhibits superior cycling stability with ~ 95.7 % capacitance retention after 65k cycles. These results indicate that the NiO/C/ZnCo₂O₄ nanocomposite material is an outstanding electrode material for supercapacitors.

Keywords: NiO/C/ZnCo₂O₄, specific capacitance, hydrothermal, supercapacitors

Procedia PDF Downloads 99

Authors: A. Giniatoulline

Abstract:

A model of the mathematical fluid dynamics which describes the motion of a three-dimensional viscous rotating fluid in a homogeneous gravitational field with the consideration of the salinity and heat transfer is considered in a vertical finite layer. The model is a generalization of the linearized Navier-Stokes system with the addition of the Coriolis parameter and the equations for changeable density, salinity, and heat transfer. An explicit solution is constructed and the proof of the existence and uniqueness theorems is given. The localization and the structure of the spectrum of inner waves is also investigated. The results may be used, in particular, for constructing stable numerical algorithms for solutions of the considered models of fluid dynamics of the Atmosphere and the Ocean.

Keywords: Fourier transform, generalized solutions, Navier-Stokes equations, stratified fluid

Procedia PDF Downloads 255

Authors: Dmytro Symak

Abstract:

Drying is a complex technologic, thermal and energy process. Energy cost of drying processes in many cases is the most costly stage of production, and can be over 50% of total costs. As we know, in Ukraine over 85% of Portland cement is produced moist, and the finished product energy costs make up to almost 60%. During the wet cement production, energy costs make up over 5500 kJ / kg of clinker, while during the dry only 3100 kJ / kg, that is, switching to a dry Portland cement will allow result into double cutting energy costs. Therefore, to study raw materials drying process in the manufacture of Portland cement is very actual task. The fine ferrous materials drying (small pyrites, red mud, clay Kyoko) is recommended to do by filtration method, that is one of the most intense. The essence of filtration method drying lies in heat agent filtering through a stationary layer of wet material, which is located on the perforated partition, in the "layer-dispersed material - perforated partition." For the optimum drying purposes, it is necessary to establish the dependence of pressure loss in the layer of dispersed material, and the values of heat and mass transfer, depending on the speed of the gas flow filtering. In our research, the experimentally determined pressure loss in the layer of dispersed material was generalized based on dimensionless complexes in the form and coefficients of heat exchange. We also determined the relation between the coefficients of mass and heat transfer. As a result of theoretic and experimental investigations, it was possible to develop a methodology for calculating the optimal parameters for the thermal agent and the main parameters for the filtration drying installation. The comparison of calculated by known operating expenses methods for the process of small pyrites drying in a rotating drum and filtration method shows to save up to 618 kWh per 1,000 kg of dry material and 700 kWh during filtration drying clay.

Keywords: drying, cement, heat and mass transfer, filtration method

Procedia PDF Downloads 262

Authors: S. Mohamed, D. Gonzalez, C. Sayada, P. Halfon

Abstract:

Drug resistance mutations are routinely detected using standard Sanger sequencing, which does not detect minor variants with a frequency below 20%. The impact of detecting minor variants generated by ultra-deep sequencing (UDS) on HIV drug-resistance (DR) interpretations has not yet been studied. Fifty HIV-1 patients who experienced virological failure were included in this retrospective study. The HIV-1 UDS protocol allowed the detection and quantification of HIV-1 protease and reverse transcriptase variants related to genotypes A, B, C, E, F, and G. DeepChek®-HIV simplified DR interpretation software was used to compare Sanger sequencing and UDS. The total time required for the UDS protocol was found to be approximately three times longer than Sanger sequencing with equivalent reagent costs. UDS detected all of the mutations found by population sequencing and identified additional resistance variants in all patients. An analysis of DR revealed a total of 643 and 224 clinically relevant mutations by UDS and Sanger sequencing, respectively. Three resistance mutations with > 20% prevalence were detected solely by UDS: A98S (23%), E138A (21%) and V179I (25%). A significant difference in the DR interpretations for 19 antiretroviral drugs was observed between the UDS and Sanger sequencing methods. Y181C and T215Y were the most frequent mutations associated with interpretation differences. A combination of UDS and DeepChek® software for the interpretation of DR results would help clinicians provide suitable treatments. A cut-off of 1% allowed a better characterisation of the viral population by identifying additional resistance mutations and improving the DR interpretation.

Keywords: HIV-1, ultra-deep sequencing, Sanger sequencing, drug resistance

Procedia PDF Downloads 336

Authors: Ratnakar Mahajan, Matteo Lelli, Kinjal Parmar

Abstract:

Ground improvement is a very important aspect of infrastructure development, especially when it comes to deep-ground improvement. The use of various geosynthetic applications is very common these days for ground improvement. This paper presents a case study where the combination of two geosynthetic applications was used in order to optimize the design as well as to control the settlements through uniform load distribution. The Agartala-Akaura rail project was made to help increase railway connectivity between India and Bangladesh. Both countries have started the construction of the same. The project requires high railway embankments to be built for the rail link. However, the challenge was to design a proper ground improvement solution as the entire area comprises very soft soil for an average depth of 15m. After due diligence, a combination of two methods was worked out by Maccaferri. PVDs were provided for the consolidation, and on top of that, a layer of high-strength geogrids (Paralink) was proposed as a basal reinforcement. The design approach was followed as described in Indian standards as well as British standards. By introducing a basal reinforcement, the spacing of PVDs could be increased, which allowed quick installation and less material consumption while keeping the consolidation time within the project duration.

Keywords: ground improvement, basal reinforcement, PVDs, high strength geogrids, Paralink

Procedia PDF Downloads 75

Authors: Ibnorachid Zakaria, El Bikri Khalid, Benamar Rhali, Farah Abdoun

Abstract:

The aim of the present work is to study the linear free symmetric vibration of three-layer sandwich beam using the energy method. The zigzag model is used to describe the displacement field. The theoretical model is based on the top and bottom layers behave like Euler-Bernoulli beams while the core layer like a Timoshenko beam. Based on Hamilton’s principle, the governing equation of motion sandwich beam is obtained in order to calculate the linear frequency parameters for a clamped-clamped and simple supported-simple-supported beams. The effects of material properties and geometric parameters on the natural frequencies are also investigated.

Keywords: linear vibration, sandwich, shear deformation, Timoshenko zig-zag model

Procedia PDF Downloads 472

Authors: Jiaxin Shi, Kaifeng Hao, Qingfan An, Zeng Peng

Abstract:

Due to a lack of data sources and data processing techniques, it has always been difficult to quantify public space quality, which includes urban construction quality and how it is perceived by people, especially in large urban areas. This study proposes a quantitative research method based on the consideration of emotional health and physical health of the built environment. It highlights the low quality of public areas in Tianjin, China, where there are many negative elements. Deep learning technology is then used to measure how effectively people perceive urban areas. First, this work suggests a deep learning model that might simulate how people can perceive the quality of urban construction. Second, we perform semantic segmentation on street images to identify visual elements influencing scene perception. Finally, this study correlated the scene perception score with the proportion of visual elements to determine the surrounding environmental elements that influence scene perception. Using a small-scale labeled Tianjin street view data set based on transfer learning, this study trains five negative spatial discriminant models in order to explore the negative space distribution and quality improvement of urban streets. Then it uses all Tianjin street-level imagery to make predictions and calculate the proportion of negative space. Visualizing the spatial distribution of negative space along the Tianjin Inner Ring Road reveals that the negative elements are mainly found close to the five key districts. The map of Tianjin was combined with the experimental data to perform the visual analysis. Based on the emotional assessment, the distribution of negative materials, and the direction of street guidelines, we suggest guidance content and design strategy points of the negative phenomena in Tianjin street space in the two dimensions of perception and substance. This work demonstrates the utilization of deep learning techniques to understand how people appreciate high-quality urban construction, and it complements both theory and practice in urban planning. It illustrates the connection between human perception and the actual physical public space environment, allowing researchers to make urban interventions.

Keywords: human perception, public space quality, deep learning, negative elements, street images

Procedia PDF Downloads 115

Authors: A. Shoiynbek, K. Kozhakhmet, P. Menezes, D. Kuanyshbay, D. Bayazitov

Abstract:

Speech emotion recognition has received increasing research interest all through current years. There was used emotional speech that was collected under controlled conditions in most research work. Actors imitating and artificially producing emotions in front of a microphone noted those records. There are four issues related to that approach, namely, (1) emotions are not natural, and it means that machines are learning to recognize fake emotions. (2) Emotions are very limited by quantity and poor in their variety of speaking. (3) There is language dependency on SER. (4) Consequently, each time when researchers want to start work with SER, they need to find a good emotional database on their language. In this paper, we propose the approach to create an automatic tool for speech emotion extraction based on facial emotion recognition and describe the sequence of actions of the proposed approach. One of the first objectives of the sequence of actions is a speech detection issue. The paper gives a detailed description of the speech detection model based on a fully connected deep neural network for Kazakh and Russian languages. Despite the high results in speech detection for Kazakh and Russian, the described process is suitable for any language. To illustrate the working capacity of the developed model, we have performed an analysis of speech detection and extraction from real tasks.

Keywords: deep neural networks, speech detection, speech emotion recognition, Mel-frequency cepstrum coefficients, collecting speech emotion corpus, collecting speech emotion dataset, Kazakh speech dataset

Procedia PDF Downloads 101

Authors: Bharat Kumar, Deepak Kumar, Vijay Chaudhry

Abstract:

Zirconium alloys are used as core components of nuclear reactors due to their high wear resistance, good corrosion properties, and good mechanical stability at high temperatures. Water flows inside the pressure tube through fuel claddings, which produces vibration of these core components and results in the wear of some components. Some components are subjected to the environment of coolant water containing LiOH which results in the corrosion of these components. The present work simulates some of these conditions to determine the failure mechanisms under these conditions and the effect of various parameters on them. Friction and wear experiments were performed varying the surrounding environment (room temperature, high temperature, and water submerged), duration, frequency, and displacement amplitude. Electrochemical corrosion experiments were performed by varying the concentration of LiOH in water. The worn and corroded surfaces were analyzed using scanning electron microscopy (SEM) to analyze the wear and corrosion mechanism and energy dispersive x-ray spectroscopy (EDS) and Raman spectroscopy to analyze the tribo-oxide layer formed during the wear and oxide layer formed during the corrosion. Wear increases with frequency and amplitude, and corrosion increases with LiOH concentration in water.

Keywords: zirconium alloys, wear, oxide layer, corrosion, EIS, linear polarization

Procedia PDF Downloads 68