Search results for: deep layer

Authors: Mohammad Reza Shahnazari, Reza Kazemi, Ali Saberi

Abstract:

Most of the engineering problems are in nonlinear forms. Nonlinear boundary layer problems defined in infinite intervals contain specific complexities, especially in boundary layer condition conformance. As an example of these nonlinear complex problems, the well-known Blasius equation can be mentioned, which itself is one of the classic boundary layer problems. No analytical solution has been proposed yet for the Blasius equation due to its complexity. In this paper, an analytical method, namely the Kourosh method, based on the singularity perturbation method and the Liao homotopy analysis is utilized to solve the Blasius problem. In this method, an inner solution is developed in the [0,1] interval to expedite the solution convergence. The magnitude of the f ˝(0), as an essential quantity for determining the physical parameters, is directly calculated from the solution of the boundary condition problem. The advantages of this solution are that it does not need any numerical solution, it has a closed form and that its validation is shown in the entire [0,∞] interval. Furthermore, all of the desirable parameters could be extracted through a series of simple analytical operations from the final solution. This solution also satisfies the continuity conditions, which is one of the main contributions of this paper in comparison with most of the other proposed analytical solutions available in the literature. Comparison with numerical solutions reveals that the proposed method is highly accurate and convenient for application.

Keywords: Blasius equation, boundary layer, Kourosh method, analytical solution

Procedia PDF Downloads 391

Authors: Hyun-Jong Choi, Minjun Kwak, Doo-Won Seo, Sang-Kuk Woo, Sun-Dong Kim

Abstract:

Solid Oxide Cell(SOC) systems can contribute to the transition to the hydrogen society by utilized as a power and hydrogen generator by the electrochemical reaction with high efficiency at high operation temperature (>750 ℃). La1-xSrxCo1-yFeyO3, which is an air electrode, is occurred stability degradations due to reaction and delamination with yittria stabilized zirconia(YSZ) electrolyte in a water electrolysis mode. To complement this phenomenon SOCs need gadolinium doped ceria(GDC) buffer layer between electrolyte and air electrode. However, GDC buffer layer requires a high sintering temperature and it causes a reaction with YSZ electrolyte. This study carried out low temperature sintering of GDC layer by applying Cu-oxide as a sintering aid. The effect of a copper additive as a sintering aid to lower the sintering temperature for the construction of solid oxide fuel cells (SOFCs) was investigated. GDC buffer layer with 0.25-10 mol% CuO sintering aid was prepared by reacting GDC power and copper nitrate solution followed by heating at 600 ℃. The sintering of CuO-added GDC powder was optimized by investigating linear shrinkage, microstructure, grain size, ionic conductivity, and activation energy of CuO-GDC electrolytes at temperatures ranging from 1100 to 1400 ℃. The sintering temperature of the CuO-GDC electrolyte decreases from 1400 ℃ to 1100 ℃ by adding the CuO sintering aid. The ionic conductivity of the CuO-GDC electrolyte shows a maximum value at 0.5 mol% of CuO. However, the addition of CuO has no significant effects on the activation energy of GDC electrolyte. GDC-LSCF layers were co-sintering at 1050 and 1100 ℃ and button cell tests were carried out at 750 ℃.

Keywords: Co-Sintering, GDC-LSCF, Sintering Aid, solid Oxide Cells

Procedia PDF Downloads 245

Authors: Lingzhi Li, Jiankun Zhang, Tiantian Gu

Abstract:

Hazard management that can prevent fatal accidents and property losses is a fundamental process during the buildings’ construction stage. However, due to lack of safety supervision resources and operational pressures, the conduction of hazard management is poor and ineffective in China. In order to improve the quality of construction safety management, it is critical to explore the use of information technologies to ensure that the process of hazard management is efficient and effective. After exploring the existing problems of construction hazard management in China, this paper develops the griddization management model for construction hazard management. First, following the knowledge grid infrastructure, the griddization computing infrastructure for construction hazards management is designed which includes five layers: resource entity layer, information management layer, task management layer, knowledge transformation layer and application layer. This infrastructure will be as the technical support for realizing grid management. Second, this study divides the construction hazards into grids through city level, district level and construction site level according to grid principles. Last, a griddization management process including hazard identification, assessment and control is developed. Meanwhile, all stakeholders of construction safety management, such as owners, contractors, supervision organizations and government departments, should take the corresponding responsibilities in this process. Finally, a case study based on actual construction hazard identification, assessment and control is used to validate the effectiveness and efficiency of the proposed griddization management model. The advantage of this designed model is to realize information sharing and cooperative management between various safety management departments.

Keywords: construction hazard, griddization computing, grid management, process

Procedia PDF Downloads 275

Authors: Ian Omung'a

Abstract:

Breast cancer remains to be one of the deadliest cancers for women worldwide, with the risk of developing tumors being as high as 50 percent in Sub-Saharan African countries like Kenya. With as many as 42 percent of these cases set to be diagnosed late when cancer has metastasized and or the prognosis has become terminal, Full Field Digital [FFD] Mammography remains an effective screening technique that leads to early detection where in most cases, successful interventions can be made to control or eliminate the tumors altogether. FFD Mammograms have been proven to multiply more effective when used together with Computer-Aided Detection and Diagnosis [CADe] systems, relying on algorithmic implementations of Deep Learning techniques in Computer Vision to carry out deep pattern recognition that is comparable to the level of a human radiologist and decipher whether specific areas of interest in the mammogram scan image portray abnormalities if any and whether these abnormalities are indicative of a benign or malignant tumor. Within this paper, we review emergent Deep Learning techniques that will prove relevant to the development of State-of-The-Art FFD Mammogram CADe systems. These techniques will span self-supervised learning for context-encoded occlusion, self-supervised learning for pre-processing and labeling automation, as well as the creation of a standardized large-scale mammography dataset as a benchmark for CADe systems' evaluation. Finally, comparisons are drawn between existing practices that pre-date these techniques and how the development of CADe systems that incorporate them will be different.

Keywords: breast cancer diagnosis, computer aided detection and diagnosis, deep learning, whole mammogram classfication, ultrasound classification, computer vision

Procedia PDF Downloads 93

Authors: Hui Zhang, Sherif Beskhyroun

Abstract:

Structural Health monitoring systems (SHM) are commonly used to identify and assess structural damage. In terms of damage detection, SHM needs to periodically collect data from sensors placed in the structure as damage-sensitive features. This includes abnormal changes caused by the strain field and abnormal symptoms of the structure, such as damage and deterioration. Currently, deploying sensors on a large scale in a building structure is a challenge. In this study, a highly stretchable strain sensors are used in this study to collect data sets of strain generated on the surface of full-size reinforced concrete (RC) frames under extreme cyclic load application. This sensing sheet can be switched freely between the test bending strain and the axial strain to achieve two different configurations. On this basis, the deep neural network prediction model of the frame beam and frame column is established. The training results show that the method can accurately predict the strain value and has good generalization ability. The two deep neural network prediction models will also be deployed in the SHM system in the future as part of the intelligent strain sensor system.

Keywords: strain sensing sheets, deep neural networks, strain measurement, SHM system, RC frames

Procedia PDF Downloads 99

Authors: Imine Zakaria, Meftah Sidi Mohamed El Amine

Abstract:

One of the most vital aerodynamic organs of a flying machine is the wing, which allows it to fly in the air efficiently. The flow around the wing is very sensitive to changes in the angle of attack. Beyond a value, there is a phenomenon of the boundary layer separation on the upper surface, which causes instability and total degradation of aerodynamic performance called a stall. However, controlling flow around an airfoil has become a researcher concern in the aeronautics field. There are two techniques for controlling flow around a wing to improve its aerodynamic performance: passive and active controls. Blowing and suction are among the active techniques that control the boundary layer separation around an airfoil. Their objective is to give energy to the air particles in the boundary layer separation zones and to create vortex structures that will homogenize the velocity near the wall and allow control. Blowing and suction have long been used as flow control actuators around obstacles. In 1904 Prandtl applied a permanent blowing to a cylinder to delay the boundary layer separation. In the present study, several numerical investigations have been developed to predict a turbulent flow around an aerodynamic profile. CFD code was used for several angles of attack in order to validate the present work with that of the literature in the case of a clean profile. The variation of the lift coefficient CL with the momentum coefficient

Keywords: CFD, control flow, lift, slot

Procedia PDF Downloads 197

Authors: Shaik Ayesha Fathima, Shaik Noor Jahan, Duvvada Rajeswara Rao

Abstract:

Earth's environment and its evolution can be seen through satellite images in near real-time. Through satellite imagery, remote sensing data provide crucial information that can be used for a variety of applications, including image fusion, change detection, land cover classification, agriculture, mining, disaster mitigation, and monitoring climate change. The objective of this project is to propose a method for classifying satellite images according to multiple predefined land cover classes. The proposed approach involves collecting data in image format. The data is then pre-processed using data pre-processing techniques. The processed data is fed into the proposed algorithm and the obtained result is analyzed. Some of the algorithms used in satellite imagery classification are U-Net, Random Forest, Deep Labv3, CNN, ANN, Resnet etc. In this project, we are using the DeepLabv3 (Atrous convolution) algorithm for land cover classification. The dataset used is the deep globe land cover classification dataset. DeepLabv3 is a semantic segmentation system that uses atrous convolution to capture multi-scale context by adopting multiple atrous rates in cascade or in parallel to determine the scale of segments.

Keywords: area calculation, atrous convolution, deep globe land cover classification, deepLabv3, land cover classification, resnet 50

Procedia PDF Downloads 140

Authors: Parvin Berenjkar, Qiuyan Yuan, Richard Sparling, Stan Lozecznik

Abstract:

Landfills highly contribute to anthropological global warming through CH₄ emissions. Landfills are usually capped by a conventional soil cover to control the migration of gases. Methane is consumed by CH₄-oxidizing microorganisms known as methanotrophs that naturally exist in the landfill soil cover. The growth of methanotrophs can be optimized in a bio-cover that typically consists of a gas distribution layer (GDL) to homogenize landfill gas fluxes and an overlying oxidation layer composed of suitable materials that support methanotrophic populations. Materials such as mature yard waste composts can provide an inexpensive and favourable porous support for the growth and activity of methanotrophs. In areas with seasonal cold climates, it is valuable to know if methanotrophs in a bio-cover can survive in winter until the next spring, and how deep they are active in the bio-cover to mitigate CH₄. In this study, a pilot bio-cover was constructed in a closed landfill cell in Winnipeg that has a very cold climate in Canada. The bio-cover has a surface area of 2.5 m x 3.5 m and 1.5 m of depth, filled with 50 cm of gravel as a GDL and 70 cm of biosolids compost amended with yard and leaf waste compost. The observed in situ potential of methanotrophs for CH₄ oxidation was investigated at a specific period of time from December 2016 to April 2017 as well as November 2017 to April 2018, when the transition to surface frost and thawing happens in the bio-cover. Compost samples taken from different depths of the bio-cover were incubated in the laboratory under standardized conditions; an optimal air: methane atmosphere, at 22ºC, but at in situ moisture content. Results showed that the methanotrophs were alive oxidizing methane without a lag, indicating that there was the potential for methanotrophic activity at some depths of the bio-cover.

Keywords: bio-cover, global warming, landfill, methanotrophic activity

Procedia PDF Downloads 121

Authors: Teja Sai Puligadda

Abstract:

Satellite images in detail can serve an important role in the geographic study. Quantitative and qualitative information provided by the satellite and remote sensing images minimizes the complexity of work and time. Data/images are captured at regular intervals by satellite remote sensing systems, and the amount of data collected is often enormous, and it expands rapidly as technology develops. Interpreting remote sensing images, geographic data mining, and researching distinct vegetation types such as agricultural and forests are all part of satellite image categorization. One of the biggest challenge data scientists faces while classifying satellite images is finding the best suitable classification algorithms based on the available that could able to classify images with utmost accuracy. In order to categorize satellite images, which is difficult due to the sheer volume of data, many academics are turning to deep learning machine algorithms. As, the CNN algorithm gives high accuracy in image recognition problems and automatically detects the important features without any human supervision and the ANN algorithm stores information on the entire network (Abhishek Gupta., 2020), these two deep learning algorithms have been used for satellite image classification. This project focuses on remote sensing through Deep Neural Networks i.e., ANN and CNN with Deep Sat (SAT-4) Airborne dataset for classifying images. Thus, in this project of classifying satellite images, the algorithms ANN and CNN are implemented, evaluated & compared and the performance is analyzed through evaluation metrics such as Accuracy and Loss. Additionally, the Neural Network algorithm which gives the lowest bias and lowest variance in solving multi-class satellite image classification is analyzed.

Keywords: artificial neural network, convolutional neural network, remote sensing, accuracy, loss

Procedia PDF Downloads 159

Authors: K. Bresilla, L. Manfrini, B. Morandi, A. Boini, G. Perulli, L. C. Grappadelli

Abstract:

Image/video processing for fruit in the tree using hard-coded feature extraction algorithms have shown high accuracy during recent years. While accurate, these approaches even with high-end hardware are computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks (CNNs), specifically an algorithm (YOLO - You Only Look Once) with 24+2 convolution layers. Using deep-learning techniques eliminated the need for hard-code specific features for specific fruit shapes, color and/or other attributes. This CNN is trained on more than 5000 images of apple and pear fruits on 960 cores GPU (Graphical Processing Unit). Testing set showed an accuracy of 90%. After this, trained data were transferred to an embedded device (Raspberry Pi gen.3) with camera for more portability. Based on correlation between number of visible fruits or detected fruits on one frame and the real number of fruits on one tree, a model was created to accommodate this error rate. Speed of processing and detection of the whole platform was higher than 40 frames per second. This speed is fast enough for any grasping/harvesting robotic arm or other real-time applications.

Keywords: artificial intelligence, computer vision, deep learning, fruit recognition, harvesting robot, precision agriculture

Procedia PDF Downloads 420

Authors: Motahare Aali, Fatemeh Tajik

Abstract:

Here, we investigate the sensitivity the Casimir force and consequently dynamical actuation of a three-layer microswitch to some ambient conditions. In fact, we have considered the effect of optical properties on the stable operation of the microswitch for both good (e.g. metals) and poor conductors via a three layer Casimir oscillator. Indeed, gold (Au) has been chosen as a good conductor which is widely used for Casimir force measurements, and highly doped conductive silicon carbide (SiC) has been considered as a poor conductor which is a promising material for device operating under harsh environments. Also, the intervening stratum is considered ethanol or water. It is also supposed that the microswitches are frictionless and autonomous. Using reduction factor diagrams and bifurcation curves, it has been shown how performance of the microswitches is sensitive to temperature and intervening stratum, moreover it is investigated how the conductivity of the components can affect this sensitivity.

Keywords: Casimir force, optical properties, Lifshitz theory, dielectric function

Procedia PDF Downloads 95

Authors: Kamal KC, Zhendong Yin, Dasen Li, Zhilu Wu

Abstract:

Intra-plant disease classification based on leaf images is a challenging computer vision task due to similarities in texture, color, and shape of leaves with a slight variation of leaf spot; and external environmental changes such as lighting and background noises. Deep convolutional neural network (DCNN) has proven to be an effective tool for binary classification. In this paper, two methods for binary classification of diseased plant leaves using DCNN are presented; model created from scratch and transfer learning. Our main contribution is a thorough evaluation of 4 networks created from scratch and transfer learning of 5 pre-trained models. Training and testing of these models were performed on a plant leaf images dataset belonging to 16 distinct classes, containing a total of 22,265 images from 8 different plants, consisting of a pair of healthy and diseased leaves. We introduce a deep CNN model, Optimized MobileNet. This model with depthwise separable CNN as a building block attained an average test accuracy of 99.77%. We also present a fine-tuning method by introducing the concept of a convolutional block, which is a collection of different deep neural layers. Fine-tuned models proved to be efficient in terms of accuracy and computational cost. Fine-tuned MobileNet achieved an average test accuracy of 99.89% on 8 pairs of [healthy, diseased] leaf ImageSet.

Keywords: deep convolution neural network, depthwise separable convolution, fine-grained classification, MobileNet, plant disease, transfer learning

Procedia PDF Downloads 186

Authors: Matan Cohen, Maxim Shoshany

Abstract:

Climatic, topographic and geological diversity, together with frequent disturbance and recovery cycles, produce highly complex spatial patterns of trees, shrubs, dwarf shrubs and bare ground patches. Assessment of spatial and temporal variations of these life-forms patterns under climate change is of high ecological priority. Here we report on one of the first attempts to discriminate between images of three Mediterranean life-forms patterns at three densities. The development of an extensive database of orthophoto images representing these 9 pattern categories was instrumental for training and testing pre-trained and newly-trained DL models utilizing DenseNet architecture. Both models demonstrated the advantages of using Deep Learning approaches over existing spectral and spatial (pattern or texture) algorithmic methods in differentiation 9 life-form spatial mixtures categories.

Keywords: texture classification, deep learning, desert fringe ecosystems, climate change

Procedia PDF Downloads 88

Authors: Evrim Colak, Andriy E. Serebryannikov, Thore Magath, Ekmel Ozbay

Abstract:

Single beam deflection and unidirectional transmission are examined for oblique incidence in a Photonic Crystal (PC) structure which employs defect layer instead of surface corrugations at the interfaces. In all of the studied cases, the defect layer is placed such that the symmetry is broken. Two types of deflection are observed depending on whether the zeroth order is coupled or not. These two scenarios can be distinguished from each other by considering the simulated field distribution in PC. In the first deflection type, Floquet-Bloch mode enables zeroth order coupling. The energy of the zeroth order is redistributed between the diffraction orders at the defect layer, providing deflection. In the second type, when zeroth order is not coupled, strong diffractions cause blazing and the evanescent waves deliver energy to higher order diffraction modes. Simulated isofrequency contours can be utilized to estimate the coupling behavior. The defect layer is placed at varying rows, preserving the asymmetry of PC while evancescent waves can still couple to higher order modes. Even for deeply buried defect layer, asymmetric transmission and beam deflection are still encountered when the zeroth order is not coupled. We assume ε=11.4 (refractive index close to that of GaAs and Si) for the PC rods. A possible operation wavelength can be within microwave and infrared range. Since the suggested material is low loss, the structure can be scaled down to operate higher frequencies. Thus, a sample operation wavelength is selected as 1.5μm. Although the structure employs no surface corrugations transmission value T≈0.97 can be achieved by means of diffraction order m=-1. Moreover, utilizing an extra line defect, T value can be increased upto 0.99, under oblique incidence even if the line defect layer is deeply embedded in the photonic crystal. The latter configuration can be used to obtain deflection in one frequency range and can also be utilized for the realization of another functionality like defect-mode wave guiding in another frequency range but still using the same structure.

Keywords: asymmetric transmission, beam deflection, blazing, bi-directional splitting, defect layer, dual beam splitting, Floquet-Bloch modes, isofrequency contours, line defect, oblique incidence, photonic crystal, unidirectionality

Procedia PDF Downloads 262

Authors: Javier Romera, Alberto Justo, Ignacio Fidalgo, Joshue Perez, Javier Araluce

Abstract:

Nowadays, individuals with mobility needs face a significant challenge when docking vehicles. In many cases, after parking, they encounter insufficient space to exit, leading to two undesired outcomes: either avoiding parking in that spot or settling for improperly placed vehicles. To address this issue, the following paper presents a parking control system employing gestural teleoperation. The system comprises three main phases: capturing body markers, interpreting gestures, and transmitting orders to the vehicle. The initial phase is centered around the MediaPipe framework, a versatile tool optimized for real-time gesture recognition. MediaPipe excels at detecting and tracing body markers, with a special emphasis on hand gestures. Hands detection is done by generating 21 reference points for each hand. Subsequently, after data capture, the project employs the MultiPerceptron Layer (MPL) for indepth gesture classification. This tandem of MediaPipe's extraction prowess and MPL's analytical capability ensures that human gestures are translated into actionable commands with high precision. Furthermore, the system has been trained and validated within a built-in dataset. To prove the domain adaptation, a framework based on the Robot Operating System (ROS), as a communication backbone, alongside CARLA Simulator, is used. Following successful simulations, the system is transitioned to a real-world platform, marking a significant milestone in the project. This real vehicle implementation verifies the practicality and efficiency of the system beyond theoretical constructs.

Keywords: gesture detection, mediapipe, multiperceptron layer, robot operating system

Procedia PDF Downloads 100

Authors: T. Praveenkumar, Kulpreet Singh, Divy Bhanpuriya, M. Saimurugan

Abstract:

This study analysed the classification accuracy for gearbox faults using Machine Learning Techniques. Gearboxes are widely used for mechanical power transmission in rotating machines. Its rotating components such as bearings, gears, and shafts tend to wear due to prolonged usage, causing fluctuating vibrations. Increasing the dependability of mechanical components like a gearbox is hampered by their sealed design, which makes visual inspection difficult. One way of detecting impending failure is to detect a change in the vibration signature. The current study proposes various machine learning algorithms, with aid of these vibration signals for obtaining the fault classification accuracy of an automotive 4-Speed synchromesh gearbox. Experimental data in the form of vibration signals were acquired from a 4-Speed synchromesh gearbox using Data Acquisition System (DAQs). Statistical features were extracted from the acquired vibration signal under various operating conditions. Then the extracted features were given as input to the algorithms for fault classification. Supervised Machine Learning algorithms such as Support Vector Machines (SVM) and unsupervised algorithms such as Deep Feed Forward Neural Network (DFFNN), Deep Belief Networks (DBN) algorithms are used for fault classification. The fusion of DBN & DFFNN classifiers were architected to further enhance the classification accuracy and to reduce the computational complexity. The fault classification accuracy for each algorithm was thoroughly studied, tabulated, and graphically analysed for fused and individual algorithms. In conclusion, the fusion of DBN and DFFNN algorithm yielded the better classification accuracy and was selected for fault detection due to its faster computational processing and greater efficiency.

Keywords: deep belief networks, DBN, deep feed forward neural network, DFFNN, fault diagnosis, fusion of algorithm, vibration signal

Procedia PDF Downloads 114

Authors: Belouadah Rabah, Guyomar Daneil, Guiffard Benoit

Abstract:

The magnetoelectric (ME) materials has dielectric polarization induced by the magnetic field or induced magnetization under an electric field. A strong ME effect requires the simultaneous presence of magnetic moments and electric dipoles. In the last decades, extensive research has been conducted on the ME effect in single phase and composite materials. This article reported the results obtained with two samples, the first is mono layer of PVDF bi-stretched and the second is the multi layer PVDF bi-stretched with the Polyurethane filled with micro particles magnetic Fe3O4 (PU+2% Fe3O4). Compare with non ME material like Alumine, a large ME polarization coefficient for the two samples was obtained. The piezoelectric properties of the PVDF and elastic proprieties of Pu+2% Fe3O4 give a big linear ME coefficient of the multi layer PVDF/(Pu+2% Fe3O4) than in the monolayer of PVDF.

Keywords: magnetoelectric effect, polymers, magnetic particles, composites, films

Procedia PDF Downloads 395

Authors: AnjalI A. Prasad

Abstract:

Nowadays, social media played an important role in spreading misinformation or fake news. This study analyzes the fake news related to the COVID-19 pandemic spread in social media. This paper aims at evaluating and comparing different approaches that are used to mitigate this issue, including popular deep learning approaches, such as CNN, RNN, LSTM, and BERT algorithm for classification. To evaluate models’ performance, we used accuracy, precision, recall, and F1-score as the evaluation metrics. And finally, compare which algorithm shows better result among the four algorithms.

Keywords: BERT, CNN, LSTM, RNN

Procedia PDF Downloads 206

Authors: P. S. Jagadeesh Kumar, Tracy Lin Huan, S. Meenakshi Sundaram

Abstract:

Alzheimer’s disease is one of the prevalent kind of ailment, expected for impudent reconciliation or an effectual therapy is to be accredited hitherto. Probable detonation of patients in the upcoming years, and consequently an enormous deal of apprehension in early discovery of the disorder, this will conceivably chaperon to enhanced healing outcomes. Complex impetuosity of the brain is an observant symbolic of the disease and a unique recognition of genetic sign of the disease. Machine learning alongside deep learning and decision tree reinforces the aptitude to absorb characteristics from multi-dimensional data’s and thus simplifies automatic classification of Alzheimer’s disease. Susceptible testing was prophesied and realized in training the prospect of Alzheimer’s disease classification built on machine learning advances. It was shrewd that the decision trees trained with deep neural network fashioned the excellent results parallel to related pattern classification.

Keywords: Alzheimer's diagnosis, decision trees, deep neural network, machine learning, pattern classification

Procedia PDF Downloads 297

Authors: Seyedeh Mozhgan Seyed Talebi, Chih -Hao Lee

Abstract:

With an abrupt rise in the power conservation efficiency (PCE) of perovskite solar cells (PSCs) within a short span of time, the toxicity of lead was raised as a major hurdle in the path toward their commercialization. In the present research, a systematic investigation of the electrical and optical characteristics of the all-inorganic CsSnI₃ perovskite absorber layer was performed with the Vienna Ab Initio Simulation Package (VASP) using the projector-augmented wave method. The presence of inorganic halide perovskite offers the advantages of enhancing the degradation resistance of the device, reducing the cost of cells, and minimizing the recombination of generated carriers. The simulated standard device using a 1D simulator like solar cell capacitance simulator (SCAPS) version 3308 involves FTO/n-TiO₂/CsSnI₃ Perovskite absorber/Spiro OmeTAD HTL/Au contact layer. The variation in the device design key parameters such as the thickness and defect density of perovskite absorber, hole transport layer and electron transport layer and interfacial defects are examined with their impact on the photovoltaic characteristic parameters. The effect of an increase in operating temperature from 300 K to 400 K on the performance of CsSnI3-based perovskite devices is also investigated. The optimized standard device at room temperature shows the highest PCE of 25.18 % with FF of 75.71 %, Voc of 0.96 V, and Jsc of 34.67 mA/cm². The outcomes and interpretation of different inorganic Cu-based HTLs presence, such as CuSCN, Cu₂O, CuO, CuI, SrCu₂O₂, and CuSbS₂, here represent a critical avenue for the possibility of fabricating high PCE perovskite devices made of stable, low-cost, efficient, safe, and eco-friendly all-inorganic materials like CsSnI₃ perovskite light absorber.

Keywords: CsSnI₃, hole transporting layer (HTL), lead-free perovskite solar cell, SCAPS-1D software

Procedia PDF Downloads 87

Authors: Benjamin Beltzung, Marie Pelé, Julien P. Renoult, Cédric Sueur

Abstract:

To this day, it is not known if drawing is specifically human behavior or if this behavior finds its origins in ancestor species. An interesting window to enlighten this question is to analyze the drawing behavior in genetically close to human species, such as non-human primate species. A good candidate for this approach is the orangutan, who shares 97% of our genes and exhibits multiple human-like behaviors. Focusing on figurative aspects may not be suitable for orangutans’ drawings, which may appear as scribbles but may have meaning. A manual feature selection would lead to an anthropocentric bias, as the features selected by humans may not match with those relevant for orangutans. In the present study, we used deep learning to analyze the drawings of a female orangutan named Molly († in 2011), who has produced 1,299 drawings in her last five years as part of a behavioral enrichment program at the Tama Zoo in Japan. We investigate multiple ways to decipher Molly’s drawings. First, we demonstrate the existence of differences between seasons by training a deep learning model to classify Molly’s drawings according to the seasons. Then, to understand and interpret these seasonal differences, we analyze how the information spreads within the network, from shallow to deep layers, where early layers encode simple local features and deep layers encode more complex and global information. More precisely, we investigate the impact of feature complexity on classification accuracy through features extraction fed to a Support Vector Machine. Last, we leverage style transfer to dissociate features associated with drawing style from those describing the representational content and analyze the relative importance of these two types of features in explaining seasonal variation. Content features were relevant for the classification, showing the presence of meaning in these non-figurative drawings and the ability of deep learning to decipher these differences. The style of the drawings was also relevant, as style features encoded enough information to have a classification better than random. The accuracy of style features was higher for deeper layers, demonstrating and highlighting the variation of style between seasons in Molly’s drawings. Through this study, we demonstrate how deep learning can help at finding meanings in non-figurative drawings and interpret these differences.

Keywords: cognition, deep learning, drawing behavior, interpretability

Procedia PDF Downloads 165

Authors: Chad Goldsworthy, B. Rajeswari Matam

Abstract:

The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.

Keywords: convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation

Procedia PDF Downloads 191

Authors: Pengfei Meng, Shuangcheng Jia, Qian Li

Abstract:

We proposed a real-time high-precision semantic segmentation network based on a multi-resolution feature fusion module, the auxiliary feature extracting module, upsampling module, and atrous spatial pyramid pooling (ASPP) module. We designed a feature fusion structure, which is integrated with sufficient features of different resolutions. We also studied the effect of side-branch structure on the network and made discoveries. Based on the discoveries about the side-branch of the network structure, we used a side-branch auxiliary feature extraction layer in the network to improve the effectiveness of the network. We also designed upsampling module, which has better results than the original upsampling module. In addition, we also re-considered the locations and number of atrous spatial pyramid pooling (ASPP) modules and modified the network structure according to the experimental results to further improve the effectiveness of the network. The network presented in this paper takes the backbone network of Bisenetv2 as a basic network, based on which we constructed a network structure on which we made improvements. We named this network deep multiple-resolution bilateral networks for real-time, referred to as DMBR-Net. After experimental testing, our proposed DMBR-Net network achieved 81.2% mIoU at 119FPS on the Cityscapes validation dataset, 80.7% mIoU at 109FPS on the CamVid test dataset, 29.9% mIoU at 78FPS on the COCOStuff test dataset. Compared with all lightweight real-time semantic segmentation networks, our network achieves the highest accuracy at an appropriate speed.

Keywords: multi-resolution feature fusion, atrous convolutional, bilateral networks, pyramid pooling

Procedia PDF Downloads 150

Authors: A. I. O. Zaid

Abstract:

Deep drawing is considered to be the most widely used sheet metal forming processes among the particularly in automobile and aircraft industries. It is widely used for manufacturing a large number of the body and spare parts. In its simplest form it may be defined as a secondary forming process by which a sheet metal is formed into a cylinder or alike by subjecting the sheet to compressive force through a punch with a flat end of the same geometry as the required shape of the cylinder end while it is held by a blank holder which hinders its movement but does not stop it. The punch and die profile radii play In this paper, the effects of punch and die profile radii on the autographic record, the minimum thickness strain location where the cracks normally start and cause the fracture, the maximum deep drawing force and the total consumed work in the drawing flat ended cylindrical brass cups are investigated. Five punches and five dies each having different profile radii were manufactured for this investigation. Furthermore, their effect on the quality of the drawn cups is also presented and discussed. It was found that the die profile radius has more effect on the maximum drawing force and the total consumed work than the punch profile radius.

Keywords: punch and die profile radii, deep drawing process, maximum drawing force, total consumed work, quality of produced parts, flat ended cylindrical brass cups

Procedia PDF Downloads 339

Authors: M. Mesrouk, A. Hadj Arab

Abstract:

This work allows highlight the effect of dust on the absorption of the optical spectrum on the photovoltaic module, the effect of the particles dust presence on the photovoltaic modules have been a microscopic scale studied with COMSOL Multi-physic software simulation. In this paper, we have supposed the dust layer as a diffraction network repetitive optical structure characterized by the spacing between particle which represented by 'd' and the simulated structure (air-dust particle-glass). In this study we can observe the relationship between the wavelength and the particle spacing, the simulation shows us that the maximum wavelength transmission value corresponding, λ0 = 400nm, which represent the spacing value between the particles dust, d = 400 nm. In fact, we can observe that while increase dust layer density the wavelength transmission value decrease, there is a relationship between the density and wavelength value which can be absorbed in a dusty photovoltaic panel.

Keywords: dust effect, photovoltaic module, spectral absorption, wavelength transmission

Procedia PDF Downloads 463

Authors: Eqqab Maree, Habil Jurgen Bast, Zana K. Shakir

Abstract:

Passive damping, once properly characterized and incorporated into the structure design is an autonomous mechanism. Passive damping can be achieved by applying layers of a polymeric material, called viscoelastic layers (VEM), to the base structure. This type of configuration is known as free or unconstrained layer damping treatment. A shear or constrained damping treatment uses the idea of adding a constraining layer, typically a metal, on top of the polymeric layer. Constrained treatment is a more efficient form of damping than the unconstrained damping treatment. In constrained damping treatment a sandwich is formed with the viscoelastic layer as the core. When the two outer layers experience bending, as they would if the structure was oscillating, they shear the viscoelastic layer and energy is dissipated in the form of heat. This form of energy dissipation allows the structural oscillations to attenuate much faster. The purpose behind this study is to predict damping effects by using two methods of passive viscoelastic constrained layer damping. First method is Euler-Bernoulli beam theory; it is commonly used for predicting the vibratory response of beams. Second method is Finite Element software packages provided in this research were obtained by using two-dimensional solid structural elements in ANSYS14 specifically eight nodded (SOLID183) and the output results from ANSYS 14 (SOLID183) its damped natural frequency values and mode shape for first five modes. This method of passive damping treatment is widely used for structural application in many industries like aerospace, automobile, etc. In this paper, take a steel cantilever sandwich beam with viscoelastic core type 3M-468 by using methods of passive viscoelastic constrained layer damping. Also can proved that, the percentage reduction of modal frequency between undamped and damped steel sandwich cantilever beam 8mm thickness for each mode is very high, this is due to the effect of viscoelastic layer on damped beams. Finally this types of damped sandwich steel cantilever beam with viscoelastic materials core type (3M468) is very appropriate to use in automotive industry and in many mechanical application, because has very high capability to reduce the modal vibration of structures.

Keywords: steel cantilever, sandwich beam, viscoelastic materials core type (3M468), ANSYS14, Euler-Bernoulli beam theory

Procedia PDF Downloads 318

Authors: Murad Almadani, Khalil Abu-Hantash, Xinyu Wang, Herbert Jelinek, Kinda Khalaf

Abstract:

Gait analysis is used by healthcare professionals as a tool to gain a better understanding of the movement impairment and track progress. In most circumstances, monitoring patients in their real-life environments with low-cost equipment such as cameras and wearable sensors is more important. Inertial sensors, on the other hand, cannot provide enough information on angular dynamics. This research offers a method for tracking 2D joint coordinates using cutting-edge vision algorithms and a single RGB camera. We provide an end-to-end comprehensive deep learning pipeline for marker-less gait parameter estimation, which, to our knowledge, has never been done before. To make our pipeline function in real-time for real-world applications, we leverage the AlphaPose human posture prediction model and a deep learning transformer. We tested our approach on the well-known GPJATK dataset, which produces promising results.

Keywords: gait analysis, human pose estimation, deep learning, real time gait estimation, AlphaPose, transformer

Procedia PDF Downloads 118

Authors: Manik Sharma, Ganapathy Krishnamurthi

Abstract:

The cost of some drugs and medical treatments has risen in recent years, that many patients are having to go without. A classification project could make researchers more efficient. One of the more surprising reasons behind the cost is how long it takes to bring new treatments to market. Despite improvements in technology and science, research and development continues to lag. In fact, finding new treatment takes, on average, more than 10 years and costs hundreds of millions of dollars. If successful, we could dramatically improve the industry's ability to model cellular images according to their relevant biology. In turn, greatly decreasing the cost of treatments and ensure these treatments get to patients faster. This work aims at solving a part of this problem by creating a cellular image classification model which can decipher the genetic perturbations in cell (occurring naturally or artificially). Another interesting question addressed is what makes the deep-learning model decide in a particular fashion, which can further help in demystifying the mechanism of action of certain perturbations and paves a way towards the explainability of the deep-learning model.

Keywords: cellular images, genetic perturbations, deep-learning, explainability

Procedia PDF Downloads 112

Authors: Revoti Prasad Bora, Nikita Katyal, Saurabh Yadav

Abstract:

Pre-processing plays an important role in various image processing applications. Most of the time due to the similar nature of images, a particular pre-processing or a set of pre-processing steps are sufficient to produce the desired results. However, in the education domain, there is a wide variety of images in various aspects like images with line-based diagrams, chemical formulas, mathematical equations, etc. Hence a single pre-processing or a set of pre-processing steps may not yield good results. Therefore, a Deep Learning based approach for dynamically selecting a relevant pre-processing technique for each image is proposed. The proposed method works as a classifier to detect hidden patterns in the images and predicts the relevant pre-processing technique needed for the image. This approach experimented for an image similarity matching problem but it can be adapted to other use cases too. Experimental results showed significant improvement in average similarity ranking with the proposed method as opposed to static pre-processing techniques.

Keywords: deep-learning, classification, pre-processing, computer vision, image processing, educational data mining

Procedia PDF Downloads 163

Authors: Amine Rezzoug, Said Abdi, Nadjet Bouhelal, Ismail Daoud

Abstract:

This paper investigates the application of metallic coatings on high fiber volume fraction carbon/epoxy polymer matrix composites. For the grip of the metallic layer, a method of modifying the surface of the composite by introducing a mixture of copper and steel powder (filler powders) which can reduce the impact of thermal spray particles. The powder was introduced to the surface at the time of the forming. Arc spray was used to project the zinc coating layer. The substrate was grit blasted to avoid poor adherence. The porosity, microstructure, and morphology of layers are characterized by optical microscopy, SEM and image analysis. The samples were studied also in terms of hardness and erosion resistance. This investigation did not reveal any visible evidence damage to the substrates. The hardness of zinc layer was about 25.94 MPa and the porosity was around (∼6.70%). The erosion test showed that the zinc coating improves the resistance to erosion. Based on the results obtained, we can conclude that thermal spraying allows the production of protective coating on PMC. Zinc coating has been identified as a compatible material with the substrate. The filler powders layer protects the substrate from the impact of hot particles and allows avoiding the rupture of brittle carbon fibers.

Keywords: arc spray, coating, composite, erosion

Procedia PDF Downloads 452