Search results for: deep plate loading test
Commenced in January 2007
Frequency: Monthly
Edition: International

Search results for: deep plate loading test

Synthesis and Characterization of TiO₂, N Doped TiO₂ and AG Doped TiO₂ for Photocatalytic Degradation of Methylene Blue in Adwa Almeda Textile Industry, Tigray, Ethiopia

Authors: Mulugeta Gurum Gerechal

Abstract:

Nowadays, the photocatalytic mechanism of water purification using nanoparticles has gained wider acceptance. For this purpose, the crystal form of N- TiO₂ and Ag-TiO₂ was prepared from TiCl₄, urea, NH₄OH, and AgNO₃ by sol-gel method and simple solid phase reaction followed by calcination at a temperature of 400°C for 4h at each. The synthesized photocatalysts were characterized using XRD, SEM, and UV-visible diffuse reflectance spectra. In the experiment, it was found that the absorption edge of N-TiO₂ was an efficient shift to visible light as compared to Ag-TiO₂. The XRD diffraction makes the particle size of N-TiO₂ smaller than Ag-TiO₂. The effect of catalyst loading and the effect of temperature on the photocatalytic efficiency of the prepared samples was tested using methylene blue as a target pollutant. The photocatalytic degradation efficiency of the catalysts for methylene blue was increased from 57.05 to 96.02% under solar radiation as the amount of the catalyst increased from 0.15 to 0.45 gram for N-TiO₂. Similarly, photocatalytic degradation of methylene blue was increased from 40.32 to 81.21% as the amount of Ag-TiO₂ increased from 0.05g to 0.1g. In addition, the photocatalytic degradation efficiency of the catalysts for the removal of methylene blue was increased from 58.00 to 98.00 and 47.00 to 81.21% under solar radiation as the calcination temperature of the catalyst increased from 300 to 500 for N-TiO₂ for Ag-TiO₂ 300 to 400⁰C. However, a further increase in catalyst loading and calcination temperature was found to decrease the degradation efficiency.

Keywords: photocatalysis, degradation, nanoparticles, catalyst loading, calcination, methylene blue

Procedia PDF Downloads 21
Chassis Level Control Using Proportional Integrated Derivative Control, Fuzzy Logic and Deep Learning

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 84
A Comparison of Methods for Neural Network Aggregation

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 167
Assessment of Metal and Nano-Metal Doped TiO₂ Nanoparticles for Photocatalytic Degradation of Methylene Blue in Almeda Textile Industry, Tigray, Ethiopia

Authors: Mulugeta Gurum Gerechal

Abstract:

Nowadays, the photocatalytic mechanism of water purification using nanoparticles has gained wider acceptance. For this purpose, the Crystal form of N- TiO₂ and Ag-TiO₂ was prepared from TiCl₄, Urea, NH₄OH and AgNO₃ by sol-gel method and simple solid phase reaction followed by calcination at a temperature of 400 °C for 4h at each. The synthesized photocatalysts were characterized using XRD, SEM and UV-visible diffuse reflectance spectra. In the experiment, it was found that the absorption edge of N-TiO₂ was a well efficient shift to visible light as compared to Ag-TiO₂. The XRD diffraction makes the particle size of N-TiO₂ smaller than Ag-TiO₂. The effect of catalyst loading and the effect of temperature on the photocatalytic efficiency of the prepared samples was tested using methylene blue as a target pollutant. The photocatalytic degradation efficiency of the catalysts for methylene blue was increased from 57.05 to 96.02% under solar radiation as the amount of the catalyst increased from 0.15 to 0.45 gram for N-TiO₂. Similarly, photocatalytic degradation of methylene blue was increased from 40.32 to 81.21% as the amount of Ag-TiO₂ increased from 0.05g to 0.1g. In addition, the photocatalytic degradation efficiency of the catalysts for the removal of methylene blue was increased from 58.00 to 98.00 and 47.00 to 81.21 % under solar radiation as the calcination temperature of the catalyst increased from 300 to 500 for N-TiO₂ for Ag-TiO₂ 300 to 4000C. However, a further increase in catalyst loading and calcination temperature was found to decrease the degradation efficiency.

Keywords: photocatalysis, degradation, nanoparticles, catalyst loading, calcination and methylene blue

Procedia PDF Downloads 68
3D Numerical Study of Tsunami Loading and Inundation in a Model Urban Area

Authors: A. Bahmanpour, I. Eames, C. Klettner, A. Dimakopoulos

Abstract:

We develop a new set of diagnostic tools to analyze inundation into a model district using three-dimensional CFD simulations, with a view to generating a database against which to test simpler models. A three-dimensional model of Oregon city with different-sized groups of building next to the coastline is used to run calculations of the movement of a long period wave on the shore. The initial and boundary conditions of the off-shore water are set using a nonlinear inverse method based on Eulerian spatial information matching experimental Eulerian time series measurements of water height. The water movement is followed in time, and this enables the pressure distribution on every surface of each building to be followed in a temporal manner. The three-dimensional numerical data set is validated against published experimental work. In the first instance, we use the dataset as a basis to understand the success of reduced models - including 2D shallow water model and reduced 1D models - to predict water heights, flow velocity and forces. This is because models based on the shallow water equations are known to underestimate drag forces after the initial surge of water. The second component is to identify critical flow features, such as hydraulic jumps and choked states, which are flow regions where dissipation occurs and drag forces are large. Finally, we describe how future tsunami inundation models should be modified to account for the complex effects of buildings through drag and blocking.Financial support from UCL and HR Wallingford is greatly appreciated. The authors would like to thank Professor Daniel Cox and Dr. Hyoungsu Park for providing the data on the Seaside Oregon experiment.

Keywords: computational fluid dynamics, extreme events, loading, tsunami

Procedia PDF Downloads 118
A Unified Deep Framework for Joint 3d Pose Estimation and Action Recognition from a Single Color Camera

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 149
Experimental Study on Depth Correction of Bearing Capacity of Medium-Weathered Silty Mudstone Foundation

Authors: Yang Xueying, Deng Wenni, Yang He

Abstract:

The bearing capacity of the foundation has always been a key point in the design and calculation of bridge foundations. The displacement-controlled Luzhou Lantian Yangtze River No. 5 Bridge is located in Jiangyang District, Luzhou City, Sichuan Province, with a main arch span of 570m, which is the largest arch bridge in China, and the bearing layer of the foundation on the north bank is moderately weathered silty mudstone. Based on the field deep load test, the measured values of load and settlement were corrected and analyzed, which confirmed that the bearing capacity of the soft rock foundation on the north bank meets the requirements and the depth correction can be carried out. Furthermore, the characteristic value of the bearing capacity of the foundation in the soft rock area can be obtained by using different depth correction coefficients k2'=2.5 or 8.0 according to the actual situation. This paper further substantiates that the bearing capacity of soft rock foundations can be significantly enhanced through in-depth modification, thereby offering meaningful reference and guidance for practical engineering applications.

Keywords: arch bridge foundation, field test, bearing capacity, displacement control

Procedia PDF Downloads 2
Experimental Modelling Gear Contact with TE77 Energy Pulse Setup

Authors: Zainab Mohammed Shukur, Najlaa Ali Alboshmina, Ali Safa Alsaegh

Abstract:

The project was investigated tribological behavior of polyether ether ketone (PEEK1000) against PEEK1000 rolling sliding (non-conformal) configuration with slip ratio 83.3%, were tested applications using a TE77 wear mechanisms and friction coefficient test rig. Under marginal lubrication conditions and the absence of film thick conditions, load 100 N was used to simulate the torque in gears 7 N.m. The friction coefficient and wear mechanisms of PEEK were studied under reciprocating roll/slide conditions with water, ethylene glycol, silicone, and base oil. Tribological tests were conducted on a TE77 high-frequency tribometer, with a disc-on-plate slide/roll (the energy pulse criterion) configuration. An Alicona G5 optical 3D micro-coordinate measurement microscope was used to investigate the surface topography and wear mechanisms. The surface roughness had been a significant effect on the friction coefficient for the PEEK/PEEK the rolling sliding contact test ethylene glycol and on the wear mechanisms. When silicone, ethylene glycol, and oil were used as a lubricant, the steady state of friction coefficient was reached faster than the other lubricant. Results describe the effect of the film thick with slip ratio of 83.3% on the tribological performance.

Keywords: polymer, rolling- sliding, energy pulse, gear contact

Procedia PDF Downloads 146
Deep Learning for Renewable Power Forecasting: An Approach Using LSTM Neural Networks

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 269
Modeling and Mapping of Soil Erosion Risk Using Geographic Information Systems, Remote Sensing, and Deep Learning Algorithms: Case of the Oued Mikkes Watershed, Morocco

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 27
Automated Weight Painting: Using Deep Neural Networks to Adjust 3D Mesh Skeletal Weights

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 278
Assessing Performance of Data Augmentation Techniques for a Convolutional Network Trained for Recognizing Humans in Drone Images

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 101
Correlation between the Undrained Shear Strength of Clay of the Champlain Sea as Determined by the Vane Test and the Swedish Cone

Authors: Tahar Ayadat

Abstract:

The undrained shear strength is an essential parameter for determining the consistency and the ultimate bearing capacity of a clay layer. The undrained shear strength can be determined by field tests such as the in situ vane test or in laboratory, including hand vane test, triaxial, simple compression test, and the consistency penetrometer (i.e. Swedish cone). However, the field vane test and the Swedish cone are the most commonly used tests by geotechnical experts. In this technical note, a comparison between the shear strength results obtained by the in situ vane test and the cone penetration test (Swedish cone) was conducted. A correlation between the results of these two tests, concerning the undrained shear strength of the Champlain sea clay, has been developed. Moreover, some applications of the proposed correlation on some geotechnical problems have been included, such as the determination of the consistency and the bearing capacity of a clay layer.

Keywords: correlation, shear strength, clay, vane test, Swedish cone

Procedia PDF Downloads 398
Integrated Geotechnical and Geophysical Investigation of a Proposed Construction Site at Mowe, Southwestern Nigeria

Authors: Kayode Festus Oyedele, Sunday Oladele, Adaora Chibundu Nduka

Abstract:

The subsurface of a proposed site for building development in Mowe, Nigeria, using Standard Penetration Test (SPT) and Cone Penetrometer Test (CPT) supplemented with Horizontal Electrical Profiling (HEP) was investigated with the aim of evaluating the suitability of the strata for foundation materials. Four SPT and CPT were implemented using 10 tonnes hammer. HEP utilizing Wenner array were performed with inter-electrode spacing of 10 – 60 m along four traverses coincident with each of the SPT and CPT. The HEP data were processed using DIPRO software and textural filtering of the resulting resistivity sections was implemented to enable delineation of hidden layers. Sandy lateritic clay, silty lateritic clay, clay, clayey sand and sand horizons were delineated. The SPT “N” value defined very soft to soft sandy lateritic (<4), stiff silty lateritic clay (7 – 12), very stiff silty clay (12 - 15), clayey sand (15- 20) and sand (27 – 37). Sandy lateritic clay (5-40 kg/cm2) and silty lateritic clay (25 - 65 kg/cm2) were defined from the CPT response. Sandy lateritic clay (220-750 Ωm), clay (< 50 Ωm) and sand (415-5359 Ωm) were delineated from the resistivity sections with two thin layers of silty lateritic clay and clayey sand defined in the texturally filtered resistivity sections. This study concluded that the presence of incompetent thick clayey materials (18 m) beneath the study area makes it unsuitable for shallow foundation. Deep foundation involving piling through the clayey layers to the competent sand at 20 m depth was recommended.

Keywords: cone penetrometer, foundation, lithologic texture, resistivity section, standard penetration test

Procedia PDF Downloads 268
Domain Adaptation Save Lives - Drowning Detection in Swimming Pool Scene Based on YOLOV8 Improved by Gaussian Poisson Generative Adversarial Network Augmentation

Authors: Simiao Ren, En Wei

Abstract:

Drowning is a significant safety issue worldwide, and a robust computer vision-based alert system can easily prevent such tragedies in swimming pools. However, due to domain shift caused by the visual gap (potentially due to lighting, indoor scene change, pool floor color etc.) between the training swimming pool and the test swimming pool, the robustness of such algorithms has been questionable. The annotation cost for labeling each new swimming pool is too expensive for mass adoption of such a technique. To address this issue, we propose a domain-aware data augmentation pipeline based on Gaussian Poisson Generative Adversarial Network (GP-GAN). Combined with YOLOv8, we demonstrate that such a domain adaptation technique can significantly improve the model performance (from 0.24 mAP to 0.82 mAP) on new test scenes. As the augmentation method only require background imagery from the new domain (no annotation needed), we believe this is a promising, practical route for preventing swimming pool drowning.

Keywords: computer vision, deep learning, YOLOv8, detection, swimming pool, drowning, domain adaptation, generative adversarial network, GAN, GP-GAN

Procedia PDF Downloads 104
Investigation on Dry Sliding Wear for Laser Cladding of Stellite 6 Produced on a P91 Steel Substrate

Authors: Alain Kusmoko, Druce Dunne, Huijun Li

Abstract:

Stellite 6 was deposited by laser cladding on a chromium bearing substrate (P91) with energy inputs of 1 kW (P91-1) and 1.8 kW (P91-1.8). The chemical compositions and microstructures of these coatings were characterized by atomic absorption spectroscopy, optical microscopy and scanning electron microscopy. The microhardness of the coatings was measured and the wear mechanism of the coatings was assessed using a pin-on-plate (reciprocating) wear testing machine. The results showed less cracking and pore development for Stellite 6 coatings applied to the P91 steel substrate with the lower heat input (P91-1). Further, the Stellite coating for P91-1 was significantly harder than that obtained for P91-1.8. The wear test results indicated that the weight loss for P91-1 was much lower than for P91-1.8. It is concluded that the lower hardness of the coating for P91-1.8, together with the softer underlying substrate structure, markedly reduced the wear resistance of the Stellite 6 coating.

Keywords: friction and wear, laser cladding, P91 steel, Stellite 6 coating

Procedia PDF Downloads 445
Effect of Type of Pile and Its Installation Method on Pile Bearing Capacity by Physical Modelling in Frustum Confining Vessel

Authors: Seyed Abolhasan Naeini, M. Mortezaee

Abstract:

Various factors such as the method of installation, the pile type, the pile material and the pile shape, can affect the final bearing capacity of a pile executed in the soil; among them, the method of installation is of special importance. The physical modeling is among the best options in the laboratory study of the piles behavior. Therefore, the current paper first presents and reviews the frustum confining vesel (FCV) as a suitable tool for physical modeling of deep foundations. Then, by describing the loading tests of two open-ended and closed-end steel piles, each of which has been performed in two methods, “with displacement" and "without displacement", the effect of end conditions and installation method on the final bearing capacity of the pile is investigated. The soil used in the current paper is silty sand of Firoozkooh. The results of the experiments show that in general the without displacement installation method has a larger bearing capacity in both piles, and in a specific method of installation the closed ended pile shows a slightly higher bearing capacity.

Keywords: physical modeling, frustum confining vessel, pile, bearing capacity, installation method

Procedia PDF Downloads 156
Development of an IoT System for Smart Crop Production

Authors: Oyenike M. Olanrewaju, Faith O. Echobu, Aderemi G. Adesoji, Emmy Danny Ajik, Joseph Nda Ndabula, Stephen Lucas

Abstract:

Nutrients are required for any soil with which plants thrive to improve efficient growth and productivity. Amongst these nutrients required for proper plant productivity are nitrogen, phosphorus and potassium (NPK). Due to factors like leaching, nutrients uptake by plants, soil erosion and evaporation, these elements tend to be in low quantity and the need to replenish them arises. But these replenishment of soil nutrients cannot be done without a timely soil test to enable farmers to know the amount of each element in short quantity and evaluate the amount required to be added. Though wet soil analysis is good but it comes with a lot of challenges ranging from soil test gargets availability to the technical knowledge of how to conduct such soil test by the common farmer. Internet of things test kit was developed to fill in the gaps created by wet soil analysis, as it can test for N, P, K, soil temperature and soil moisture in a given soil at the time of test. In this implementation, sample test was carried out within 0.2 hectares of land divided into smaller plots. The kits perform adequately well as the range of values obtained across the segments were within a very close range.

Keywords: Internet of Things, soil nutrients, test kit, soil temperature

Procedia PDF Downloads 83
The Current Practices of Analysis of Reinforced Concrete Panels Subjected to Blast Loading

Authors: Palak J. Shukla, Atul K. Desai, Chentankumar D. Modhera

Abstract:

For any country in the world, it has become a priority to protect the critical infrastructure from looming risks of terrorism. In any infrastructure system, the structural elements like lower floors, exterior columns, walls etc. are key elements which are the most susceptible to damage due to blast load. The present study revisits the state of art review of the design and analysis of reinforced concrete panels subjected to blast loading. Various aspects in association with blast loading on structure, i.e. estimation of blast load, experimental works carried out previously, the numerical simulation tools, various material models, etc. are considered for exploring the current practices adopted worldwide. Discussion on various parametric studies to investigate the effect of reinforcement ratios, thickness of slab, different charge weight and standoff distance is also made. It was observed that for the simulation of blast load, CONWEP blast function or equivalent numerical equations were successfully employed by many researchers. The study of literature indicates that the researches were carried out using experimental works and numerical simulation using well known generalized finite element methods, i.e. LS-DYNA, ABAQUS, AUTODYN. Many researchers recommended to use concrete damage model to represent concrete and plastic kinematic material model to represent steel under action of blast loads for most of the numerical simulations. Most of the studies reveal that the increase reinforcement ratio, thickness of slab, standoff distance was resulted in better blast resistance performance of reinforced concrete panel. The study summarizes the various research results and appends the present state of knowledge for the structures exposed to blast loading.

Keywords: blast phenomenon, experimental methods, material models, numerical methods

Procedia PDF Downloads 160
Hyperspectral Band Selection for Oil Spill Detection Using Deep Neural Network

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 121
Vertical Structure and Frequencies of Deep Convection during Active Periods of the West African Monsoon Season

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 157
Oxidative Stress Markers in Sports Related to Training

Authors: V. Antevska, B. Dejanova, L. Todorovska, J. Pluncevic, E. Sivevska, S. Petrovska, S. Mancevska, I. Karagjozova

Abstract:

Introduction: The aim of this study was to optimise the laboratory oxidative stress (OS) markers in soccer players. Material and methods: In a number of 37 soccer players (21±3 years old) and 25 control subjects (sedenters), plasma samples were taken for d-ROMs (reactive oxygen metabolites) and NO (nitric oxide) determination. The d-ROMs test was performed by measurement of hydroperoxide levels (Diacron, Italy). For NO determination the method of nitrate enzyme reduction with the Greiss reagent was used (OXIS, USA). The parameters were taken after the training of the soccer players and were compared with the control group. Training was considered as maximal exercise treadmill test. The criteria of maximum loading for each subject was established as >95% maximal heart rate. Results: The level of d-ROMs was found to be increased in the soccer players vs. control group but no significant difference was noticed. After the training d-ROMs in soccer players showed increased value of 299±44 UCarr (p<0.05). NO showed increased level in all soccer players vs. controls but significant difference was found after the training 102±29 μmol (p<0.05). Conclusion: Due to these results we may suggest that the measuring these OS markers in sport medicine may be useful for better estimation and evaluation of the training program. More oxidative stress should be used to clarify optimization of the training intensity program.

Keywords: oxidative stress markers, soccer players, training, sport

Procedia PDF Downloads 447
Deepnic, A Method to Transform Each Variable into Image for Deep Learning

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 95
Evaluation of Pollution in Underground Water from ODO-NLA and OGIJO Metropolis Industrial Areas in Ikorodu

Authors: Zaccheaus Olasupo Apotiola

Abstract:

This study evaluates the level of pollution in underground water from Ogijo and Odo-nla areas in lkorodu, Lagos State. Water sample were collected around various industries and transported in ice packs to the laboratory. Temperature and pH was determined on site, physicochemical parameters and total plate were determined using standard methods, while heavy metal concentration was determined using Atomic Absorption spectrophotometry method. The temperature was observed at a range of 20-28 oC, the pH was observed at a range of 5.64 to 6.91 mol/l and were significantly different (P < 0.05) from one another. The chloride content was observed at a range 70.92 to 163.10 mg/l there was no significant difference (P > 0.05) between sample 40 GAJ and ISUP, but there was significant difference (P < 0.05) between other samples. The acidity value varied from 11.0 – 34.5 (mg/l), the samples had no alkalinity. The Total plate count was found at 20-125 cfu/ml. Asernic, Lead, Cadmium, and Mercury concentration ranged between 0.03 - 0.09, 0.04 - 0.11, 0.00 -0.00, and 0.00 – 0.00(mg/l) respectively. However there was significant difference (p < 0.05) between all samples except for sample 4OGA, 5OGAJ, and 3SUTN that were not significantly different (P > 0.05). The results revealed all samples are not safe for human consumption as the levels of Asernic and Lead are above the maximum value of (0.01 mg/l) recommended by NIS 554 and WHO.

Keywords: arsenic, cadmium, lead mercury, WHO

Procedia PDF Downloads 523
Online Yoga Asana Trainer Using Deep Learning

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 248
Object-Scene: Deep Convolutional Representation for Scene Classification

Authors: Yanjun Chen, Chuanping Hu, Jie Shao, Lin Mei, Chongyang Zhang

Abstract:

Traditional image classification is based on encoding scheme (e.g. Fisher Vector, Vector of Locally Aggregated Descriptor) with low-level image features (e.g. SIFT, HoG). Compared to these low-level local features, deep convolutional features obtained at the mid-level layer of convolutional neural networks (CNN) have richer information but lack of geometric invariance. For scene classification, there are scattered objects with different size, category, layout, number and so on. It is crucial to find the distinctive objects in scene as well as their co-occurrence relationship. In this paper, we propose a method to take advantage of both deep convolutional features and the traditional encoding scheme while taking object-centric and scene-centric information into consideration. First, to exploit the object-centric and scene-centric information, two CNNs that trained on ImageNet and Places dataset separately are used as the pre-trained models to extract deep convolutional features at multiple scales. This produces dense local activations. By analyzing the performance of different CNNs at multiple scales, it is found that each CNN works better in different scale ranges. A scale-wise CNN adaption is reasonable since objects in scene are at its own specific scale. Second, a fisher kernel is applied to aggregate a global representation at each scale and then to merge into a single vector by using a post-processing method called scale-wise normalization. The essence of Fisher Vector lies on the accumulation of the first and second order differences. Hence, the scale-wise normalization followed by average pooling would balance the influence of each scale since different amount of features are extracted. Third, the Fisher vector representation based on the deep convolutional features is followed by a linear Supported Vector Machine, which is a simple yet efficient way to classify the scene categories. Experimental results show that the scale-specific feature extraction and normalization with CNNs trained on object-centric and scene-centric datasets can boost the results from 74.03% up to 79.43% on MIT Indoor67 when only two scales are used (compared to results at single scale). The result is comparable to state-of-art performance which proves that the representation can be applied to other visual recognition tasks.

Keywords: deep convolutional features, Fisher Vector, multiple scales, scale-specific normalization

Procedia PDF Downloads 335
Simulation of Low Cycle Fatigue Behaviour of Nickel-Based Alloy at Elevated Temperatures

Authors: Harish Ramesh Babu, Marco Böcker, Mario Raddatz, Sebastian Henkel, Horst Biermann, Uwe Gampe

Abstract:

Thermal power machines are subjected to cyclic loading conditions under elevated temperatures. At these extreme conditions, the durability of the components has a significant influence. The material mechanical behaviour has to be known in detail for a failsafe construction. For this study a nickel-based alloy is considered, the deformation and fatigue behaviour of the material is analysed under cyclic loading. A viscoplastic model is used for calculating the deformation behaviour as well as to simulate the rate-dependent and cyclic plasticity effects. Finally, the cyclic deformation results of the finite element simulations are compared with low cycle fatigue (LCF) experiments.

Keywords: complex low cycle fatigue, elevated temperature, fe-simulation, viscoplastic

Procedia PDF Downloads 240
Simplified Ultimate Strength Assessment of Ship Structures Based on Biro Klasifikasi Indonesia Rules for Hull

Authors: Sukron Makmun, Topan Firmandha, Siswanto

Abstract:

Ultimate Strength Assessment on ship cross section in accordance with Biro Klasifikasi Indonesia (BKI) Rules for Hull, follows step by step incremental iterative approach. In this approach, ship cross section is divided into plate-stiffener combinations and hard corners element. The average stress-strain relationship (σ-ε) for all structural elements will be defined, where the subscript k refers to the modes 0, 1, 2, 3 or 4. These results would be verified with a commercial software calculation in similar cases. The numerical calculations of buckling strength are in accordance with the commercial software (GL Rules ND). Then the comparison of failure behaviours of stiffened panels and hard corners are presented. Where failure modes 3 are likely to occur first follows the failure mode 4 and the last one is the failure mode 1.

Keywords: ultimate strength assessment, BKI rules, incremental, plate-stiffener combination and hard corner, commercial software

Procedia PDF Downloads 372
Seismotectonic Deformations along Strike-Slip Fault Systems of the Maghreb Region, Western Mediterranean

Authors: Abdelkader Soumaya, Noureddine Ben Ayed, Mojtaba Rajabi, Mustapha Meghraoui, Damien Delvaux, Ali Kadri, Moritz Ziegler, Said Maouche, Ahmed Braham, Aymen Arfaoui

Abstract:

The northern Maghreb region (Western Mediterranean) is a key area to study the seismotectonic deformations across the Africa-Eurasia convergent plate boundary. On the basis of young geologic fault slip data and stress inversion of focal mechanisms, we defined a first-order transpression-compatible stress field and a second-order spatial variation of tectonic regime across the Maghreb region, with a relatively stable SHmax orientation from east to west. Therefore, the present-day active contraction of the western Africa-Eurasia plate boundary is accommodated by (1) E-W strike-slip faulting with a reverse component along the Eastern Tell and Saharan-Tunisian Atlas, (2) a predominantly NE trending thrust faulting with strike-slip component in the Western Tell part, and (3) a conjugate strike-slip faulting regime with a normal component in the Alboran/Rif domain. This spatial variation of the active stress field and the tectonic regime is relatively in agreement with the inferred stress information from neotectonic features. According to newly suggested structural models, we highlight the role of main geometrically complex shear zones in the present-day stress pattern of the Maghreb region. Then, different geometries of these major preexisting strike-slip faults and related fractures (V-shaped conjugate fractures, horsetail splays faults, and Riedel fractures) impose their component on the second- and third-order stress regimes. Smoothed present-day and Neotectonic stress maps (mean SHmax orientation) reveal that plate boundary forces acting on the Africa-Eurasia collisional plates control the long wavelength of the stress field pattern in the Maghreb. The seismotectonic deformations and the upper crustal stress field in the study area are governed by the interplay of the oblique plate convergence (i.e., Africa-Eurasia), lithosphere-mantle interaction, and preexisting tectonic weakness zones.

Keywords: Maghreb, strike-slip fault, seismotectonic, focal mechanism, inversion

Procedia PDF Downloads 126
An Ensemble Deep Learning Architecture for Imbalanced Classification of Thoracic Surgery Patients

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: deep learning, ensemble models, imbalanced classification, lung cancer, TS patient selection

Procedia PDF Downloads 149