Search results for: deep layer

Authors: Youji Miyake

Abstract:

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

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

Procedia PDF Downloads 194

Authors: Yilei Song, Linlin Tian, Ning Zhao

Abstract:

Turbulence energetics and structures in the wake of large-scale wind turbines under the stably-stratified atmospheric boundary layer (SABL) can be complicated due to the presence of low-level jets (LLJs), a region of higher wind speeds than the geostrophic wind speed. With a modified one-k-equation, eddy viscosity model specified for atmospheric flows as the sub-grid scale (SGS) model, a realistic atmospheric state of the stable ABL is well reproduced by large-eddy simulation (LES) techniques. Corresponding to the precursor stably stratification, the detailed wake properties of a standard 5-MW wind turbine represented as an actuator line model are provided. An engineering model is proposed for wake prediction based on the simulation statistics and gets validated. Results confirm that the proposed wake model can provide good predictions for wind turbines under the SABL.

Keywords: large-eddy simulation, stably-stratified atmospheric boundary layer, wake model, wind turbine wake

Procedia PDF Downloads 174

Authors: K. N. Seetharamu, Naveen Teggi, Kiranakumar Dhavalagi, Narayana Kamath

Abstract:

A method of temperature calculations is developed to study the conditions leading to hot spot occurrence on multicore chips. A physical model which has salient features of multicore chips is incorporated for the analysis. The model consists of active and background cell laid out in a checkered pattern, and this pattern repeats itself in each fine grain active cells. The die has three layers i) body ii) buried oxide layer iii) wiring layer, stacked one above the other with heat source placed at the interface between wiring and buried oxide layer. With this model we propose analytical method to calculate the target hotspot temperature, heat flow to top and bottom layers of the die and thermal resistance components at each granularity level, assuming appropriate values of die dimensions and parameters. Finally we attempt to find an easier method for the calculation of the target hotspot temperature using graph.

Keywords: checkered pattern, granularity level, heat conduction, multicore chips, target hotspot temperature

Procedia PDF Downloads 466

Authors: Donya Ashtiani Haghighi, Amirali Baniasadi

Abstract:

Coronavirus (COVID-19) disease has spread abruptly all over the world since the end of 2019. Computed tomography (CT) scans and X-ray images are used to detect this disease. Different Deep Neural Network (DNN)-based diagnosis solutions have been developed, mainly based on Convolutional Neural Networks (CNNs), to accelerate the identification of COVID-19 cases. However, CNNs lose important information in intermediate layers and require large datasets. In this paper, Capsule Network (CapsNet) is used. Capsule Network performs better than CNNs for small datasets. Accuracy of 0.9885, f1-score of 0.9883, precision of 0.9859, recall of 0.9908, and Area Under the Curve (AUC) of 0.9948 are achieved on the Capsule-based framework with hyperparameter tuning. Moreover, different dropout rates are investigated to decrease overfitting. Accordingly, a dropout rate of 0.1 shows the best results. Finally, we remove one convolution layer and decrease the number of trainable parameters to 146,752, which is a promising result.

Keywords: capsule network, dropout, hyperparameter tuning, classification

Procedia PDF Downloads 78

Authors: Atakan Aral Ormancı, Tuğçe Arslantaş, Murat Özcü

Abstract:

This study presents the design and implementation of an experimental chassis-level system for various control applications. Specifically, the height level of the chassis is controlled using proportional integrated derivative, fuzzy logic, and deep learning control methods. Real-time data obtained from height and pressure sensors installed in a 6x2 truck chassis, in combination with pulse-width modulation signal values, are utilized during the tests. A prototype pneumatic system of a 6x2 truck is added to the setup, which enables the Smart Pneumatic Actuators to function as if they were in a real-world setting. To obtain real-time signal data from height sensors, an Arduino Nano is utilized, while a Raspberry Pi processes the data using Matlab/Simulink and provides the correct output signals to control the Smart Pneumatic Actuator in the truck chassis. The objective of this research is to optimize the time it takes for the chassis to level down and up under various loads. To achieve this, proportional integrated derivative control, fuzzy logic control, and deep learning techniques are applied to the system. The results show that the deep learning method is superior in optimizing time for a non-linear system. Fuzzy logic control with a triangular membership function as the rule base achieves better outcomes than proportional integrated derivative control. Traditional proportional integrated derivative control improves the time it takes to level the chassis down and up compared to an uncontrolled system. The findings highlight the superiority of deep learning techniques in optimizing the time for a non-linear system, and the potential of fuzzy logic control. The proposed approach and the experimental results provide a valuable contribution to the field of control, automation, and systems engineering.

Keywords: automotive, chassis level control, control systems, pneumatic system control

Procedia PDF Downloads 81

Authors: John Pomerat, Aviv Segev

Abstract:

Recently, deep learning has had many theoretical breakthroughs. For deep learning to be successful in the industry, however, there need to be practical algorithms capable of handling many real-world hiccups preventing the immediate application of a learning algorithm. Although AI promises to revolutionize the healthcare industry, getting access to patient data in order to train learning algorithms has not been easy. One proposed solution to this is data- sharing. In this paper, we propose an alternative protocol, based on multi-party computation, to train deep learning models while maintaining both the privacy and security of training data. We examine three methods of training neural networks in this way: Transfer learning, average ensemble learning, and series network learning. We compare these methods to the equivalent model obtained through data-sharing across two different experiments. Additionally, we address the security concerns of this protocol. While the motivating example is healthcare, our findings regarding multi-party computation of neural network training are purely theoretical and have use-cases outside the domain of healthcare.

Keywords: neural network aggregation, multi-party computation, transfer learning, average ensemble learning

Procedia PDF Downloads 162

Authors: Xiping Guo, Jing Li

Abstract:

The microstructure of an Si-Al-Y co-deposition coating prepared on an Nb-Si based ultra high temperature alloy by pack cementation process at 1250°C for eight hours was studied. The results showed that the coating was composed of a (Nb,X)Si₂ (X represents Ti, Cr and Hf elements) outer layer, a (Ti,Nb)₅Si₄ middle layer and an Al, Cr-rich inner layer. For comparison, the oxidation behaviors of the coating at 800, 1050 and 1350°C were investigated respectively. Linear oxidation kinetics was found with the parabolic rate constants of 5.29×10⁻², 9×10⁻²and 5.81 mg² cm⁻⁴ h⁻¹, respectively. Catastrophic pesting oxidation has not been found at 800°C even for 100 h. The surface of the scale was covered by compact glassy SiO₂ film. The coating was able to effectively protect the Nb-Si based alloy from oxidation at 1350°C for at least 100 h. The formation process of the scale was testified following an epitaxial growth mechanism. The mechanism responsible for the oxidation behavior of the Si-Al-Y co-deposition coating at 800, 1050 and 1350°C was proposed.

Keywords: Nb-Si based ultra high temperature alloy, oxidation resistance, pack cementation, silicide coating, Al and Y modified

Procedia PDF Downloads 404

Authors: Roslinda Nazar, Ezad Hafidz Hafidzuddin, Norihan M. Arifin, Ioan Pop

Abstract:

In this paper, the problem of steady laminar boundary layer flow and heat transfer over a permeable exponentially stretching/shrinking sheet with generalized slip velocity is considered. The similarity transformations are used to transform the governing nonlinear partial differential equations to a system of nonlinear ordinary differential equations. The transformed equations are then solved numerically using the bvp4c function in MATLAB. Dual solutions are found for a certain range of the suction and stretching/shrinking parameters. The effects of the suction parameter, stretching/shrinking parameter, velocity slip parameter, critical shear rate, and Prandtl number on the skin friction and heat transfer coefficients as well as the velocity and temperature profiles are presented and discussed.

Keywords: boundary layer, exponentially stretching/shrinking sheet, generalized slip, heat transfer, numerical solutions

Procedia PDF Downloads 432

Authors: Behrooz Daneshmand

Abstract:

Software Defined Networking (SDN) is designed to meet the future needs of 5G mobile networks. The SDN architecture offers a new solution that involves separating the control plane from the data plane, which is usually paired together. Network functions traditionally performed on specific hardware can now be abstracted and virtualized on any device, and a centralized software-based administration approach is based on a central controller, facilitating the development of modern applications and services. These plan standards clear the way for a more adaptable, speedier, and more energetic network beneath computer program control compared with a conventional network. We accept SDN gives modern inquire about openings to security, and it can significantly affect network security research in numerous diverse ways. Subsequently, the SDN architecture engages systems to effectively screen activity and analyze threats to facilitate security approach modification and security benefit insertion. The segregation of the data planes and control and, be that as it may, opens security challenges, such as man-in-the-middle attacks (MIMA), denial of service (DoS) attacks, and immersion attacks. In this paper, we analyze security threats to each layer of SDN - application layer - southbound interfaces/northbound interfaces - controller layer and data layer. From a security point of see, the components that make up the SDN architecture have a few vulnerabilities, which may be abused by aggressors to perform noxious activities and hence influence the network and its administrations. Software-defined network assaults are shockingly a reality these days. In a nutshell, this paper highlights architectural weaknesses and develops attack vectors at each layer, which leads to conclusions about further progress in identifying the consequences of attacks and proposing mitigation strategies.

Keywords: software-defined networking, security, SDN, 5G/IMT-2020

Procedia PDF Downloads 100

Authors: Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio Velastin

Abstract:

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from color video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important key points of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the Spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, Microsoft Research Redmond (MSR) Action3D, and Stony Brook University (SBU) Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference.

Keywords: human action recognition, pose estimation, D-CNN, deep learning

Procedia PDF Downloads 146

Authors: Soufiene Ilahi, Noureddine Yacoubi

Abstract:

GaInAsSb grown on GaSb substrate is an interesting material employed as an active layer in vertical-cavity surface-emitting lasers (VCSELs) operating in mid-infrared emission. This material presents some advantages like highs optical absorption coefficient and good thermal conductivity, which is very desirable for VCSEL application. In this paper, we have investigated the effects of thermal annealing on optical properties and thermal conductivity of GaInAsSb/GaSb. The studies are carried out by means of the photo thermal deflection spectroscopy technique (PDS). In fact, optical absorption spectrum and thermal conductivity have been determined by a comparison between the experimental and theoretical phases of the PDS signal. We have found that thermal conductivity increased significantly to 13 W/m.K for GaInAsSb annealed during 60 min. In addition, we have found that bandgap energy is blue-shifted around 30 meV. The amplitudes signal of PDS reveals multiple reflections as a function of annealing time, which reflect the high crystalline quality of the layer.

Keywords: thermal conductivity, bandgap energy of GaInAsSb, GaInAsSb active layer, optical absorption

Procedia PDF Downloads 151

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 266

Authors: My Hachem Aouragh, Hind Ragragui, Abdellah El-Hmaidi, Ali Essahlaoui, Abdelhadi El Ouali

Abstract:

This study investigates soil erosion susceptibility in the Oued Mikkes watershed, located in the Meknes-Fez region of northern Morocco, utilizing advanced techniques such as deep learning algorithms and remote sensing integrated within Geographic Information Systems (GIS). Spanning approximately 1,920 km², the watershed is characterized by a semi-arid Mediterranean climate with irregular rainfall and limited water resources. The waterways within the watershed, especially the Oued Mikkes, are vital for agricultural irrigation and potable water supply. The research assesses the extent of erosion risk upstream of the Sidi Chahed dam while developing a spatial model of soil loss. Several important factors, including topography, land use/land cover, and climate, were analyzed, with data on slope, NDVI, and rainfall erosivity processed using deep learning models (DLNN, CNN, RNN). The results demonstrated excellent predictive performance, with AUC values of 0.92, 0.90, and 0.88 for DLNN, CNN, and RNN, respectively. The resulting susceptibility maps provide critical insights for soil management and conservation strategies, identifying regions at high risk for erosion across 24% of the study area. The most high-risk areas are concentrated on steep slopes, particularly near the Ifrane district and the surrounding mountains, while low-risk areas are located in flatter regions with less rugged topography. The combined use of remote sensing and deep learning offers a powerful tool for accurate erosion risk assessment and resource management in the Mikkes watershed, highlighting the implications of soil erosion on dam siltation and operational efficiency.

Keywords: soil erosion, GIS, remote sensing, deep learning, Mikkes Watershed, Morocco

Procedia PDF Downloads 19

Authors: John Gibbs, Benjamin Flanders, Dylan Pozorski, Weixuan Liu

Abstract:

Weight Painting–adjusting the influence a skeletal joint has on a given vertex in a character mesh–is an arduous and time con- suming part of the 3D animation pipeline. This process generally requires a trained technical animator and many hours of work to complete. Our skiNNer plug-in, which works within Autodesk’s Maya 3D animation software, uses Machine Learning and data pro- cessing techniques to create a deep neural network model that can accomplish the weight painting task in seconds rather than hours for bipedal quasi-humanoid character meshes. In order to create a properly trained network, a number of challenges were overcome, including curating an appropriately large data library, managing an arbitrary 3D mesh size, handling arbitrary skeletal architectures, accounting for extreme numeric values (most data points are near 0 or 1 for weight maps), and constructing an appropriate neural network model that can properly capture the high frequency alter- ation between high weight values (near 1.0) and low weight values (near 0.0). The arrived at neural network model is a cross between a traditional CNN, deep residual network, and fully dense network. The resultant network captures the unusually hard-edged features of a weight map matrix, and produces excellent results on many bipedal models.

Keywords: 3d animation, animation, character, rigging, skinning, weight painting, machine learning, artificial intelligence, neural network, deep neural network

Procedia PDF Downloads 273

Authors: Masood Varshosaz, Kamyar Hasanpour

Abstract:

In recent years, we have seen growing interest in recognizing humans in drone images for post-disaster search and rescue operations. Deep learning algorithms have shown great promise in this area, but they often require large amounts of labeled data to train the models. To keep the data acquisition cost low, augmentation techniques can be used to create additional data from existing images. There are many techniques of such that can help generate variations of an original image to improve the performance of deep learning algorithms. While data augmentation is potentially assumed to improve the accuracy and robustness of the models, it is important to ensure that the performance gains are not outweighed by the additional computational cost or complexity of implementing the techniques. To this end, it is important to evaluate the impact of data augmentation on the performance of the deep learning models. In this paper, we evaluated the most currently available 2D data augmentation techniques on a standard convolutional network which was trained for recognizing humans in drone images. The techniques include rotation, scaling, random cropping, flipping, shifting, and their combination. The results showed that the augmented models perform 1-3% better compared to a base network. However, as the augmented images only contain the human parts already visible in the original images, a new data augmentation approach is needed to include the invisible parts of the human body. Thus, we suggest a new method that employs simulated 3D human models to generate new data for training the network.

Keywords: human recognition, deep learning, drones, disaster mitigation

Procedia PDF Downloads 95

Authors: Yilei Xue, Yat-Hing Ham, Wenting Qiu, Wan Chan, Stefan Nagl

Abstract:

Polydopamine (PDA) is a popular material in biological and medical applications due to its excellent biocompatibility, outstanding physicochemical properties, and facile fabrication. In this project, a new sandwich-structured PDA and silver (Ag) hybrid material named PDA-Ag-PDA was synthesized and characterized layer-by-layer, where silver nanoparticles (Ag NPs) are wrapped in PDA coatings, using SEM, AFM, 3D surface metrology, and contact angle meter. The silver loading capacity is positively proportional to the roughness value of the initial PDA film. This designed film was subsequently integrated within a digital microfluidic (DMF) platform coupling with an oxygen sensor layer for on-chip antibacterial assay. The concentration of E. coli was quantified on DMF by real-time monitoring oxygen consumption during E. coli growth with the optical oxygen sensor layer. The PDA-Ag-PDA coating shows an 99.9% reduction in E. coli population under non-nutritive condition with 1-hour treatment and has a strong growth inhibition of E. coliin nutrient LB broth as well. Furthermore, PDA-Ag-PDA film maintaining a low cytotoxicity effect to human cells. After treating with PDA-Ag-PDA film for 24 hours, 82% HEK 293 and 86% HeLa cells were viable. The SERS enhancement factor of PDA-Ag-PDA is estimated to be 1.9 × 104 using Rhodamine 6G (R6G). Multifunctional PDA-Ag-PDA coating provides an alternative platform to conjugate biomolecules and perform biological applications on DMF, in particular, for the adhesive protein and cell study.

Keywords: polydopamine, silver nanoparticles, digital microfluidic, optical sensor, antimicrobial assay, SERS

Procedia PDF Downloads 93

Authors: Maymona Al-Husari, Craig Murdoch, Steven Webb

Abstract:

Some tumors are known to exhibit an extracellular pH that is more acidic than the intracellular, creating a 'reversed pH gradient' across the cell membrane and this has been shown to affect their invasive and metastatic potential. Tumour hypoxia also plays an important role in tumour development and has been directly linked to both tumour morphology and aggressiveness. In this paper, we present a hybrid mathematical model of intracellular pH regulation that examines the effect of oxygen and pH on tumour growth and morphology. In particular, we investigate the impact of pH regulatory mechanisms on the cellular pH gradient and tumour morphology. Analysis of the model shows that: low activity of the Na+/H+ exchanger or a high rate of anaerobic glycolysis can give rise to a 'fingering' tumour morphology; and a high activity of the lactate/H+ symporter can result in a reversed transmembrane pH gradient across a large portion of the tumour mass. Also, the reversed pH gradient is spatially heterogenous within the tumour, with a normal pH gradient observed within an intermediate growth layer, that is the layer between the proliferative inner and outermost layer of the tumour.

Keywords: acidic pH, cellular automaton, ebola, tumour growth

Procedia PDF Downloads 331

Authors: Marinelle El-Khoury, Lina Bouhaya, Nivine Abbas, Hassan Sleiman

Abstract:

The road network in the north of Lebanon is a prime example of the lack of pavement design and execution in Lebanon.  These roads show major distresses and hence, should be tested and evaluated. The aim of this research is to investigate and determine the deficiencies in road surface design in Lebanon, and to propose an environmentally friendly asphalt mix design. This paper consists of several parts: (i) evaluating pavement performance and structural behavior, (ii) identifying the distresses using visual examination followed by laboratory tests, (iii) deciding the optimal solution where rehabilitation or reconstruction is required and finally, (iv) identifying a sustainable method, which uses recycled material in the proposed mix. The asphalt formula contains Reclaimed Asphalt Pavement (RAP) in the base course layer and in the asphalt layer. Visual inspection of the roads in Tripoli shows that these roads face a high level of distress severity. Consequently, the pavement should be reconstructed rather than simply rehabilitated. Coring was done to determine the pavement layer thickness. The results were compared to the American Association of State Highway and Transportation Officials (AASHTO) design methodology and showed that the existing asphalt thickness is lower than the required asphalt thickness. Prior to the pavement reconstruction, the road materials were tested according to the American Society for Testing and Materials (ASTM) specification to identify whether the materials are suitable. Accordingly, the ASTM tests that were performed on the base course are Sieve analysis, Atterberg limits, modified proctor, Los Angeles, and California Bearing Ratio (CBR) tests. Results show a CBR value higher than 70%. Hence, these aggregates could be used as a base course layer. The asphalt layer was also tested and the results of the Marshall flow and stability tests meet the ASTM specifications. In the last section, an environmentally friendly mix was proposed. An optimal RAP percentage of 30%, which produced a well graded base course and asphalt mix, was determined through a series of trials.

Keywords: asphalt mix, reclaimed asphalt pavement, California bearing ratio, sustainability

Procedia PDF Downloads 130

Authors: Hye-Young Shin, Chan Kee Park

Abstract:

Background: To compare the thinning patterns of the ganglion cell-inner plexiform layer (GCIPL) and peripapillary retinal nerve fiber layer (pRNFL) as measured using Cirrus high-definition optical coherence tomography (HD-OCT) in patients with visual field (VF) defects that respect the vertical meridian. Methods: Twenty eyes of eleven patients with VF defects that respect the vertical meridian were enrolled retrospectively. The thicknesses of the macular GCIPL and pRNFL were measured using Cirrus HD-OCT. The 5% and 1% thinning area index (TAI) was calculated as the proportion of abnormally thin sectors at the 5% and 1% probability level within the area corresponding to the affected VF. The 5% and 1% TAI were compared between the GCIPL and pRNFL measurements. Results: The color-coded GCIPL deviation map showed a characteristic vertical thinning pattern of the GCIPL, which is also seen in the VF of patients with brain lesions. The 5% and 1% TAI were significantly higher in the GCIPL measurements than in the pRNFL measurements (all P < 0.01). Conclusions: Macular GCIPL analysis clearly visualized a characteristic topographic pattern of retinal ganglion cell (RGC) loss in patients with VF defects that respect the vertical meridian, unlike pRNFL measurements. Macular GCIPL measurements provide more valuable information than pRNFL measurements for detecting the loss of RGCs in patients with retrograde degeneration of the optic nerve fibers.

Keywords: brain lesion, macular ganglion cell, inner plexiform layer, spectral-domain optical coherence tomography

Procedia PDF Downloads 337

Authors: Asmau Mukhtar Ahmed, Olga Duran

Abstract:

Hydrocarbon (HC) spills constitute a significant problem that causes great concern to the environment. With the latest technology (hyperspectral images) and state of the earth techniques (image processing tools), hydrocarbon spills can easily be detected at an early stage to mitigate the effects caused by such menace. In this study; a controlled laboratory experiment was used, and clay soil was mixed and homogenized with different hydrocarbon types (diesel, bio-diesel, and petrol). The different mixtures were scanned with HYSPEX hyperspectral camera under constant illumination to generate the hypersectral datasets used for this experiment. So far, the Short Wave Infrared Region (SWIR) has been exploited in detecting HC spills with excellent accuracy. However, the Near-Infrared Region (NIR) is somewhat unexplored with regards to HC contamination and how it affects the spectrum of soils. In this study, Deep Neural Network (DNN) was applied to the controlled datasets to detect and quantify the amount of HC spills in soils in the Near-Infrared Region. The initial results are extremely encouraging because it indicates that the DNN was able to identify features of HC in the Near-Infrared Region with a good level of accuracy.

Keywords: hydrocarbon, Deep Neural Network, short wave infrared region, near-infrared region, hyperspectral image

Procedia PDF Downloads 114

Authors: Balogun R. Ayodeji, Adefisan E. Adesanya, Adeyewa Z. Debo, E. C. Okogbue

Abstract:

Deep convective systems during active periods of the West African monsoon season have not been properly investigated over better temporal and spatial resolution in West Africa. Deep convective systems are investigated over seven climatic zones of the West African sub-region, which are; west-coast rainforest, dry rainforest, Nigeria-Cameroon rainforest, Nigeria savannah, Central African and South Sudan (CASS) Savannah, Sudano-Sahel, and Sahel, using data from Tropical Rainfall Measurement Mission (TRMM) Precipitation Feature (PF) database. The vertical structure of the convective systems indicated by the presence of at least one 40 dBZ and reaching (attaining) at least 1km in the atmosphere showed strong core (highest frequency (%)) of reflectivity values around 2 km which is below the freezing level (4-5km) for all the zones. Echoes are detected above the 15km altitude much more frequently in the rainforest and Savannah zones than the Sudano and Sahel zones during active periods in March-May (MAM), whereas during active periods in June-September (JJAS) the savannahs, Sudano and Sahel zones convections tend to reach higher altitude more frequently than the rainforest zones. The percentage frequencies of deep convection indicated that the occurrences of the systems are within the range of 2.3-2.8% during both March-May (MAM) and June-September (JJAS) active periods in the rainforest and savannah zones. On the contrary, the percentage frequencies were found to be less than 2% in the Sudano and Sahel zones, except during the active-JJAS period in the Sudano zone.

Keywords: active periods, convective system, frequency, reflectivity

Procedia PDF Downloads 152

Authors: Ying Li, Yan Li

Abstract:

A new algorithm for single hidden layer feedforward neural networks (SLFN), Orthogonal Basis Extreme Learning (OBEL) algorithm, is proposed and the algorithm derivation is given in the paper. The algorithm can decide both the NNs parameters and the neuron number of hidden layer(s) during training while providing extreme fast learning speed. It will provide a practical way to develop NNs. The simulation results of function approximation showed that the algorithm is effective and feasible with good accuracy and adaptability.

Keywords: neural network, orthogonal basis extreme learning, function approximation

Procedia PDF Downloads 534

Authors: Seyedeh Mozhgan Seyed-Talebi, Javad Beheshtian

Abstract:

The toxicity of lead associated with the lifecycle of perovskite solar cells (PSCs( is a serious concern which may prove to be a major hurdle in the path toward their commercialization. The current proposed lead-free PSCs including Ag(I), Bi(III), Sb(III), Ti(IV), Ge(II), and Sn(II) low-toxicity cations are still plagued with the critical issues of poor stability and low efficiency. This is mainly because of their chemical stability. In the present research, utilization of all inorganic CsSnGeI₃ based materials offers the advantages to enhance resistance of device to degradation, reduce the cost of cells, and minimize the carrier recombination. The presence of inorganic halide perovskite improves the photovoltaic parameters of PCSs via improved surface coverage and stability. The inverted structure of simulated devices using a 1D simulator like solar cell capacitance simulator (SCAPS) version 3308 involves TCOHTL/Perovskite/ETL/Au contact layer. PEDOT:PSS, PCBM, and CsSnGeI₃ used as hole transporting layer (HTL), electron transporting layer (ETL), and perovskite absorber layer in the inverted structure for the first time. The holes are injected from highly stable and air tolerant Sn_0.5Ge_0.5I₃ perovskite composition to HTM and electrons from the perovskite to ETL. Simulation results revealed a great dependence of power conversion efficiency (PCE) on the thickness and defect density of perovskite layer. Here the effect of an increase in operating temperature from 300 K to 400 K on the performance of CsSnGeI₃ based perovskite devices is investigated. Comparison between simulated CsSnGeI₃ based PCSs and similar real testified devices with spiro-OMeTAD as HTL showed that the extraction of carriers at the interfaces of perovskite absorber depends on the energy level mismatches between perovskite and HTL/ETL. We believe that optimization results reported here represent a critical avenue for fabricating the stable, low-cost, efficient, and eco-friendly all-inorganic Cs-Sn-Ge based lead-free perovskite devices.

Keywords: hole transporting layer, lead-free, perovskite solar cell, SCAPS-1D, Sn-Ge based

Procedia PDF Downloads 155

Authors: Nguyen J. M., Lucas G., Brunner M., Ruan S., Antonioli D.

Abstract:

Deep learning based on convolutional neural networks (CNN) is a very powerful technique for classifying information from an image. We propose a new method, DeepNic, to transform each variable of a tabular dataset into an image where each pixel represents a set of conditions that allow the variable to make an error-free prediction. The contrast of each pixel is proportional to its prediction performance and the color of each pixel corresponds to a sub-family of NICs. NICs are probabilities that depend on the number of inputs to each neuron and the range of coefficients of the inputs. Each variable can therefore be expressed as a function of a matrix of 2 vectors corresponding to an image whose pixels express predictive capabilities. Our objective is to transform each variable of tabular data into images into an image that can be analysed by CNNs, unlike other methods which use all the variables to construct an image. We analyse the NIC information of each variable and express it as a function of the number of neurons and the range of coefficients used. The predictive value and the category of the NIC are expressed by the contrast and the color of the pixel. We have developed a pipeline to implement this technology and have successfully applied it to genomic expressions on an Affymetrix chip.

Keywords: tabular data, deep learning, perfect trees, NICS

Procedia PDF Downloads 90

Authors: Venkata Narayana Chejarla, Nafisa Parvez Shaik, Gopi Vara Prasad Marabathula, Deva Kumar Bejjam

Abstract:

Yoga is an advanced, well-recognized method with roots in Indian philosophy. Yoga benefits both the body and the psyche. Yoga is a regular exercise that helps people relax and sleep better while also enhancing their balance, endurance, and concentration. Yoga can be learned in a variety of settings, including at home with the aid of books and the internet as well as in yoga studios with the guidance of an instructor. Self-learning does not teach the proper yoga poses, and doing them without the right instruction could result in significant injuries. We developed "Online Yoga Asana Trainer using Deep Learning" so that people could practice yoga without a teacher. Our project is developed using Tensorflow, Movenet, and Keras models. The system makes use of data from Kaggle that includes 25 different yoga poses. The first part of the process involves applying the movement model for extracting the 17 key points of the body from the dataset, and the next part involves preprocessing, which includes building a pose classification model using neural networks. The system scores a 98.3% accuracy rate. The system is developed to work with live videos.

Keywords: yoga, deep learning, movenet, tensorflow, keras, CNN

Procedia PDF Downloads 240

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 290

Authors: Sharifullah Ahmed, Sarwar Jahan Md. Yasin

Abstract:

Shallow foundations on unimproved soft natural soils can undergo a high consolidation and secondary settlement. For low and medium rise building projects on such soil condition, pile foundation may not be cost effective. In such cases an alternative to pile foundations may be shallow strip footings placed on a double layered improved soil system soil. The upper layer of this system is untreated or cement treated compacted sand and underlying layer is natural soft clay. This system will reduce the settlement to an allowable limit. The current research has been conducted with the settlement of a rigid plane-strain strip footing of 2.5 m width placed on the surface of a soil consisting of an untreated or cement treated sand layer overlying a bed of homogeneous soft clay. The settlement of the mentioned shallow foundation has been studied considering both cases with the thicknesses of the sand layer are 0.3 to 0.9 times the width of footing. The response of the clay layer is assumed as undrained for plastic loading stages and drained during consolidation stages. The response of the sand layer is drained during all loading stages. FEM analysis was done using PLAXIS 2D Version 8.0. A natural clay deposit of 15 m thickness and 18 m width has been modeled using Hardening Soil Model, Soft Soil Model, Soft Soil Creep Model, and upper improvement layer has been modeled using only Hardening Soil Model. The groundwater level is at the top level of the clay deposit that made the system fully saturated. Parametric study has been conducted to determine the effect of thickness, density, cementation of the sand mat and density, shear strength of the soft clay layer on the settlement of strip foundation under the uniformly distributed vertical load of varying value. A set of the chart has been established for designing shallow strip footing on the sand mat over thick, soft clay deposit through obtaining the particular thickness of sand mat for particular subsoil parameter to ensure no punching shear failure and no settlement beyond allowable level. Design guideline in the form of non-dimensional charts has been developed for footing pressure equivalent to medium-rise residential or commercial building foundation with strip footing on soft inorganic Normally Consolidated (NC) soil of Bangladesh having void ratio from 1.0 to 1.45.

Keywords: design charts, ground improvement, PLAXIS 2D, primary and secondary settlement, sand mat, soft clay

Procedia PDF Downloads 123

Authors: Juree Hong, Sanggeun Lee, Jungmok Seo, Taeyoon Lee

Abstract:

We report a facile synthesis of metal nano particles (NPs) on graphene layer via galvanic displacement reaction between graphene-buffered copper (Cu) and metal ion-containing salts. Diverse metal NPs can be formed on graphene surface and their morphologies can be tailored by controlling the concentration of metal ion-containing salt and immersion time. The obtained metal NP-decorated single-layer graphene (SLG) has been used as hydrogen gas (H2) sensing material and exhibited highly sensitive response upon exposure to 2% of H2.

Keywords: metal nanoparticle, galvanic displacement reaction, graphene, hydrogen sensor

Procedia PDF Downloads 425

Authors: Joseph Gear, Yue Xu, Ernest Foo, Praveen Gauravaran, Zahra Jadidi, Leonie Simpson

Abstract:

Deep learning methods have been seeing an increasing application to the long-standing security research goal of automatic vulnerability detection for source code. Attention, however, must still be paid to the task of producing vector representations for source code (code embeddings) as input for these deep learning models. Graphical representations of code, most predominantly Abstract Syntax Trees and Code Property Graphs, have received some use in this task of late; however, for very large graphs representing very large code snip- pets, learning becomes prohibitively computationally expensive. This expense may be reduced by intelligently pruning this input to only vulnerability-relevant information; however, little research in this area has been performed. Additionally, most existing work comprehends code based solely on the structure of the graph at the expense of the information contained by the node in the graph. This paper proposes Semantic-enhanced Code Embedding for Vulnerability Discovery (SCEVD), a deep learning model which uses semantic-based feature selection for its vulnerability classification model. It uses information from the nodes as well as the structure of the code graph in order to select features which are most indicative of the presence or absence of vulnerabilities. This model is implemented and experimentally tested using the SARD Juliet vulnerability test suite to determine its efficacy. It is able to improve on existing code graph feature selection methods, as demonstrated by its improved ability to discover vulnerabilities.

Keywords: code representation, deep learning, source code semantics, vulnerability discovery

Procedia PDF Downloads 159

Authors: Huawei Bai, Jianguo Yao, Fellow, IEEE

Abstract:

Atrial fibrillation (AF) is the most common form of heart arrhythmia and is closely associated with mortality and morbidity in heart failure, stroke, and coronary artery disease. The development of single spot optical sensors enables widespread photoplethysmography (PPG) screening, especially for AF, since it represents a more convenient and noninvasive approach. To our knowledge, most existing studies based on public and unbalanced datasets can barely handle the multiple noises sources in the real world and, also, lack interpretability. In this paper, we construct a large- scale PPG dataset using measurements collected from PPG wrist- watch devices worn by volunteers and propose an attention-based two-stream heterogeneous neural network (TSHNN). The first stream is a hybrid neural network consisting of a three-layer one-dimensional convolutional neural network (1D-CNN) and two-layer attention- based bidirectional long short-term memory (Bi-LSTM) network to learn representations from temporally sampled signals. The second stream extracts latent representations from the PPG time-frequency spectrogram using a five-layer CNN. The outputs from both streams are fed into a fusion layer for the outcome. Visualization of the attention weights learned demonstrates the effectiveness of the attention mechanism against noise. The experimental results show that the TSHNN outperforms all the competitive baseline approaches and with 98.09% accuracy, achieves state-of-the-art performance.

Keywords: PPG wearables, atrial fibrillation, feature fusion, attention mechanism, hyber network

Procedia PDF Downloads 121