Search results for: deep soil mixing column

Authors: Mathieu Imbert, Sebastien Comas-Cardona, Emmanuelle Abisset-Chavanne, David Prono

Abstract:

Short cycle time Resin Transfer Molding (RTM) applications appear to be of great interest for the mass production of automotive or aeronautical lightweight structural parts. During the RTM process, the two components of a resin are mixed on-line and injected into the cavity of a mold where a fibrous preform has been placed. Injection and polymerization occur simultaneously in the preform inducing evolutions of temperature, degree of cure and viscosity that furthermore affect flow and curing. In order to adjust the processing conditions to reduce the cycle time, it is, therefore, essential to understand and quantify the physical mechanisms occurring in the part during injection. In a previous study, a dual-scale simulation tool has been developed to help determining the optimum injection parameters. This tool allows tracking finely the repartition of the resin and the evolution of its properties during reactive injections with on-line mixing. Tows and channels of the fibrous material are considered separately to deal with the consequences of the dual-scale morphology of the continuous fiber textiles. The simulation tool reproduces the unsaturated area at the flow front, generated by the tow/channel difference of permeability. Resin “storage” in the tows after saturation is also taken into account as it may significantly affect the repartition and evolution of the temperature, degree of cure and viscosity in the part during reactive injections. The aim of the current study is, thanks to experiments, to understand and quantify the “storage” evolution in the tows to adjust and validate the numerical tool. The presented study is based on four experimental repeats conducted on three different types of textiles: a unidirectional Non Crimp Fabric (NCF), a triaxial NCF and a satin weave. Model fluids, dyes and image analysis, are used to study quantitatively, the resin flow in the saturated area of the samples. Also, textiles characteristics affecting the resin “storage” evolution in the tows are analyzed. Finally, fully coupled on-line mixing reactive injections are conducted to validate the numerical model.

Keywords: experimental, on-line mixing, high-speed RTM process, dual-scale flow

Procedia PDF Downloads 167

Authors: Samuel Akinlabi Ola, Emeka Segun Nnochiri, Stephen Kayode Aderomose, Paul Ayesemhe Edoh

Abstract:

Fadama soils of Northern Nigeria are generally a problem soil for highway and geotechnical engineers. There has been no consistent conclusion on the effect of the strain rate on the shear strength of soils, thus necessitating the need to clarify this issue with various types of soil. Consolidated undrained tests with pore pressure measurements were conducted at optimum moisture content and maximum dry density using standard proctor compaction. Back pressures were applied to saturate the soil. The shear strength parameters were determined. Analyzing the results and model studies using the Rate Process Theory, functional relationships between the deviator stress and strain rate were determined and expressed mathematically as deviator stress = β0+ β1 log(strain rate) at each cell pressure where β0 and β1 are constants. Also, functional relationships between the pore pressure coefficient Āf and the time to failure were determined and expressed mathematically as pore pressure coefficient, Āf = ψ0+ѱ1log (time to failure) where ψ0 and ѱ1 are constants. For cell pressure between 69 – 310 kN/m2 (10 - 45psi) the constants found for Fadama soil in this study are ψ0=0.17 and ѱ1=0.18. The study also shows the dependence of the angle of friction (ø’) on the rate of strain as it increases from 22o to 25o for an increase in the rate of strain from 0.08%/min to 1.0%/min. Conclusively, the study also shows that within the strain rate utilized in the research, the deviator strength increased with the strain rate while the excess pore water pressure decreased with an increase in the rate of strain.

Keywords: deviator stress, Fadama soils, pore pressure coefficient, rate process

Procedia PDF Downloads 78

Authors: Shiuh-Jer Huang, Chen-Zon Yan, C. K. Huang, Chun-Chien Ting

Abstract:

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Keywords: deep learning, image processing, convolution neural network, YOLOv2, 7A6 series manipulator

Procedia PDF Downloads 251

Authors: Parisa Mansour

Abstract:

The coronavirus disease 2019 (COVID-19) was discovered and rapidly spread to various countries around the world since the end of 2019. Computed tomography (CT) images have been used as an important alternative to the time-consuming RT. PCR test. However, manual segmentation of CT images alone is a major challenge as the number of suspected cases increases. Thus, accurate and automatic segmentation of COVID-19 infections is urgently needed. Because the imaging features of the COVID-19 infection are different and similar to the background, existing medical image segmentation methods cannot achieve satisfactory performance. In this work, we try to build a deep convolutional neural network adapted for the segmentation of chest CT images with COVID-19 infections. First, we maintain a large and novel chest CT image database containing 165,667 annotated chest CT images from 861 patients with confirmed COVID-19. Inspired by the observation that the boundary of an infected lung can be improved by global intensity adjustment, we introduce a feature variable block into the proposed deep CNN, which adjusts the global features of features to segment the COVID-19 infection. The proposed PV array can effectively and adaptively improve the performance of functions in different cases. We combine features of different scales by proposing a progressive atrocious space pyramid fusion scheme to deal with advanced infection regions with various aspects and shapes. We conducted experiments on data collected in China and Germany and showed that the proposed deep CNN can effectively produce impressive performance.

Keywords: chest, COVID-19, chest Image, coronavirus, CT image, chest CT

Procedia PDF Downloads 59

Authors: Wei Li, Tuo Yang

Abstract:

In order to satisfy the real-time and accurate requirements of cigarette smoke detection in complex scenes, a cigarette smoke detection technology based on the combination of deep learning and color features was proposed. Firstly, based on the color features of cigarette smoke, the suspicious cigarette smoke area in the image is extracted. Secondly, combined with the efficiency of cigarette smoke detection and the problem of network overfitting, a network model for cigarette smoke detection was designed according to YOLOV3 algorithm to reduce the false detection rate. The experimental results show that the method is feasible and effective, and the accuracy of cigarette smoke detection is up to 99.13%, which satisfies the requirements of real-time cigarette smoke detection in complex scenes.

Keywords: deep learning, computer vision, cigarette smoke detection, YOLOV3, color feature extraction

Procedia PDF Downloads 89

Authors: Sumit Sen, Sohan Khedekar, Umang Shinde, Shivam Bhargava

Abstract:

This study has been undertaken to investigate whether the deep learning models are able to predict the future stock prices by training the model with the historical stock price data. Since this work required time series analysis, various models are present today to perform time series analysis such as Recurrent Neural Network LSTM, ARIMA and Facebook Prophet. Applying these models the movement of stock price of stocks are predicted and also tried to provide the future prediction of the stock price of a stock. Final product will be a stock price prediction web application that is developed for providing the user the ease of analysis of the stocks and will also provide the predicted stock price for the next seven days.

Keywords: Autoregressive Integrated Moving Average, Deep Learning, Long Short Term Memory, Time-series

Procedia PDF Downloads 144

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 196

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 115

Authors: Wahhaj Ahmed Farooqi, Bilal Ahmad, Sandra Maritza Zambrano Bernal

Abstract:

In view of structural engineering, monitoring of structural responses over time is of great importance with respect to recent developments of construction technologies. Recently, developments of advanced computing tools have enabled researcher’s better execution of structural health monitoring (SHM) and control systems. In the last decade, building information modeling (BIM) has substantially enhanced the workflow of planning and operating engineering structures. Typically, building information can be stored and exchanged via model files that are based on the Industry Foundation Classes (IFC) standard. In this study a modeling approach for semantic modeling of SHM and control systems is integrated into the BIM methodology using the IFC standard. For validation of the modeling approach, a laboratory test structure, a four-story shear frame structure, is modeled using a conventional BIM software tool. An IFC schema extension is applied to describe information related to monitoring and control of a prototype SHM and control system installed on the laboratory test structure. The SHM and control system is described by a semantic model applying Unified Modeling Language (UML). Subsequently, the semantic model is mapped into the IFC schema. The test structure is composed of four aluminum slabs and plate-to-column connections are fully fixed. In the center of the top story, semi-active tuned liquid column damper (TLCD) is installed. The TLCD is used to reduce effects of structural responses in context of dynamic vibration and displacement. The wireless prototype SHM and control system is composed of wireless sensor nodes. For testing the SHM and control system, acceleration response is automatically recorded by the sensor nodes equipped with accelerometers and analyzed using embedded computing. As a result, SHM and control systems can be described within open BIM, dynamic responses and information of damages can be stored, documented, and exchanged on the formal basis of the IFC standard.

Keywords: structural health monitoring, open building information modeling, industry foundation classes, unified modeling language, semi-active tuned liquid column damper, nondestructive testing

Procedia PDF Downloads 154

Authors: Rusnardi Rahmat Putra, Junji Kiyono, Aiko Furukawa

Abstract:

Several powerful earthquakes have struck Padang during recent years, one of the largest of which was an M 7.6 event that occurred on September 30, 2009 and caused more than 1000 casualties. Following the event, we conducted a 12-site microtremor array investigation to gain a representative determination of the soil condition of subsurface structures in Padang. From the dispersion curve of array observations, the central business district of Padang corresponds to relatively soft soil condition with Vs30 less than 400 m/s. because only one accelerometer existed, we simulated the 2009 Padang earthquake to obtain peak ground acceleration for all sites in Padang city. By considering the damage data of the 2009 Padang earthquake, we produced seismic risk vulnerability estimation of non-engineered houses for rock, medium and soft soil condition. We estimated the loss ratio based on the ground response, seismic hazard of Padang and the existing damaged to non-engineered structure houses due to Padang earthquake in 2009 data for several return periods of earthquake events.

Keywords: profile, Padang earthquake, microtremor array, seismic vulnerability

Procedia PDF Downloads 412

Authors: Swapnil A. Padvi, Dipak S. Dalal

Abstract:

The chemistry of tetrazoles has been grown tremendously in the past few years because tetrazoles are important and useful class of heterocyclic compounds which have a widespread application such as anticancer, antimicrobial, analgesics, antibacterial, antifungal, antihypertensive, and anti-allergic drugs in medicinal chemistry. Furthermore, tetrazoles have application in material sciences as explosives, rocket propellants, and in information recording systems. In addition to this, they have a wide range of application in coordination chemistry as a ligand. Deep eutectic solvents (DES) have emerged over the current decade as a novel class of green reaction media and applied in various fields of sciences because of their unique physical and chemical properties similar to the ionic liquids such as low vapor pressure, non-volatility, high thermal stability and recyclability. In addition, the reactants of DES are cheaply available, low-toxic, and biodegradable, which makes them predominantly required for large-scale applications effectively in industrial production. Herein we report the [2+3] cycloaddition reaction of organic nitriles with sodium azide affords the corresponding 5-substituted 1H-tetrazoles in six different types of choline chloride based deep eutectic solvents under mild reaction condition. Choline chloride: ZnCl2 (1:2) showed the best results for the synthesis of 5-substituted 1 H-tetrazoles. This method reduces the disadvantages such as: the use of toxic metals and expensive reagents, drastic reaction conditions and the presence of dangerous hydrazoic acid. The approach provides environment-friendly, short reaction times, good to excellent yields; safe process and simple workup make this method an attractive and useful contribution to present green organic synthesis of 5-substituted-1H-tetrazoles. All synthesized compounds were characterized by IR, 1H NMR, 13C NMR and Mass spectroscopy. DES can be recovered and reused three times with very little loss in activity.

Keywords: click chemistry, choline chloride, green chemistry, deep eutectic solvent, tetrazoles

Procedia PDF Downloads 232

Authors: Yeganeh Attari, Gudmund Reidar Eiksund, Hans Peter Jostad

Abstract:

In Geotechnical practice, there is no standard method recognized by the industry to account for the reduction of safety factor of a slope as an effect of soil displacement and pore pressure build-up during pile installation. Pile driving disturbs causes large strains and generates excess pore pressures in a zone that can extend many diameters from the installed pile, resulting in a decrease of the shear strength of the surrounding soil. This phenomenon may cause slope failure. Moreover, dissipation of excess pore pressure set-up may cause weakening of areas outside the volume of soil remoulded during installation. Because of complex interactions between changes in mean stress and shearing, it is challenging to predict installation induced pore pressure response. Furthermore, it is a complex task to follow the rate and path of pore pressure dissipation in order to analyze slope stability. In cohesive soils it is necessary to implement soil models that account for strain softening in the analysis. In the literature, several cases of slope failure due to pile driving activities have been reported, for instance, a landslide in Gothenburg that resulted in a slope failure destroying more than thirty houses and Rigaud landslide in Quebec which resulted in loss of life. Up to now, several methods have been suggested to predict the effect of pile driving on total and effective stress, pore pressure changes and their effect on soil strength. However, this is still not well understood or agreed upon. In Norway, general approaches applied by geotechnical engineers for this problem are based on old empirical methods with little accurate theoretical background. While the limitations of such methods are discussed, this paper attempts to capture the reduction in the factor of safety of a slope during pile driving, using coupled Finite Element analysis and cavity expansion method. This is demonstrated by analyzing a case of slope failure due to pile driving in Norway.

Keywords: cavity expansion method, excess pore pressure, pile driving, slope failure

Procedia PDF Downloads 151

Authors: R. Nandhini, Gaurab Mudbhari

Abstract:

Ranging from the field of health care to self-driving cars, machine learning and deep learning algorithms have revolutionized the field with the proper utilization of images and visual-oriented data. Segmentation, regression, classification, clustering, dimensionality reduction, etc., are some of the Machine Learning tasks that helped Machine Learning and Deep Learning models to become state-of-the-art models for the field where images are key datasets. Among these tasks, classification and clustering are essential but difficult because of the intricate and high-dimensional characteristics of image data. This finding examines and assesses advanced techniques in supervised classification and unsupervised clustering for image datasets, emphasizing the relative efficiency of Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), Deep Embedded Clustering (DEC), and self-supervised learning approaches. Due to the distinctive structural attributes present in images, conventional methods often fail to effectively capture spatial patterns, resulting in the development of models that utilize more advanced architectures and attention mechanisms. In image classification, we investigated both CNNs and ViTs. One of the most promising models, which is very much known for its ability to detect spatial hierarchies, is CNN, and it serves as a core model in our study. On the other hand, ViT is another model that also serves as a core model, reflecting a modern classification method that uses a self-attention mechanism which makes them more robust as this self-attention mechanism allows them to lean global dependencies in images without relying on convolutional layers. This paper evaluates the performance of these two architectures based on accuracy, precision, recall, and F1-score across different image datasets, analyzing their appropriateness for various categories of images. In the domain of clustering, we assess DEC, Variational Autoencoders (VAEs), and conventional clustering techniques like k-means, which are used on embeddings derived from CNN models. DEC, a prominent model in the field of clustering, has gained the attention of many ML engineers because of its ability to combine feature learning and clustering into a single framework and its main goal is to improve clustering quality through better feature representation. VAEs, on the other hand, are pretty well known for using latent embeddings for grouping similar images without requiring for prior label by utilizing the probabilistic clustering method.

Keywords: machine learning, deep learning, image classification, image clustering

Procedia PDF Downloads 17

Authors: C. C. Egwuonwu, N. A. A. Okereke, K. O. Chilakpu, S. O. Ohanyere

Abstract:

In this study, initial soil strength indices (qu) and stress-strain characteristics, namely failure strain (ϵf), area under the stress-strain curve up to failure (Is) and stress-strain modulus between no load and failure (Es) were investigated as potential indicators for characterizing the erosion resistance of two compacted soils, namely sandy clay loam (SCL) and clay loam (CL) in some selected sites in Enugu State, Nigeria. The unconfined compressive strength (used in obtaining strength indices) and stress-strain measurements were obtained as a function of moisture content in percentage (mc %) and dry density (γd). Test were conducted over a range of 8% to 30% moisture content and 1.0 g/cm3 to 2.0 g/cm3 dry density at applied loads of 20, 40, 80, 160 and 320 kPa. Based on the results, it was found out that initial soil strength alone was not a good indicator of erosion resistance. For instance, in the comparison of exponents of mc% and γd for jet index or erosion resistance index (Ji) and the strength measurements, qu and Es agree in signs for mc%, but are opposite in signs for γd. Therefore, there is an inconsistency in exponents making it difficult to develop a relationship between the strength parameters and Ji for this data set. In contrast, the exponents of mc% and γd for Ji and ϵf and Is are opposite in signs, there is potential for an inverse relationship. The measured stress-strain characteristics, however, appeared to have potential in providing useful information on erosion resistance. The models developed for the prediction of the extent or the susceptibility of soils to erosion and subjected to sensitivity test on some selected sites achieved over 90% efficiency in their functions.

Keywords: characterization of erodibility, selected sites in Enugu state, soil strength, stress-strain indices

Procedia PDF Downloads 415

Authors: Sonia Machraoui, Salam Labidi, Karunakara Naregundi

Abstract:

Environmental radiation measurements are useful to identify areas of potential natural radiation hazard particularly in areas of phosphate industries where enhanced radiation levels are expected to be present. Measurements of primordial radionuclides concentrations have been carried out in samples collected from Sfax City around the SIAPE phosphate industry of Tunis. The samples analysed include fish, beef meat, egg, and vegetables as well as in soil and grass. Measurements were performed by gamma spectrometry method using a 42% relative efficiency N-type HPGe detector. The activity concentrations of radionuclides were measured by gamma ray spectrometry. As expected, the concentrations of radionuclides belonging to uranium and thorium series were low in food materials. In all the samples analysed, the 137Cs concentration was below detection level, except meat samples which showed the activity concentration of 2.4 Bq kg-1 (dry wt.) The soil to grass transfer factor was found to be similar to those reported in literature. The effective dose to the population due to intake of food products were also estimated and are presented in this paper.

Keywords: effective doses, phosphate industry, transfer coefficients, Tunisia

Procedia PDF Downloads 221

Authors: Maria Trimintziou, Michael Sakellariou, Prodromos Psarropoulos

Abstract:

Nowadays, the exploitation of hydrocarbons reserves in deep seas and oceans, in combination with the need to transport hydrocarbons among countries, has made the design, construction and operation of offshore pipelines very significant. Under this perspective, it is evident that many more offshore pipelines are expected to be constructed in the near future. Since offshore pipelines are usually crossing extended areas, they may face a variety of geohazards that impose substantial permanent ground deformations (PGDs) to the pipeline and potentially threaten its integrity. In case of a geohazard area, there exist three options to proceed. The first option is to avoid the problematic area through rerouting, which is usually regarded as an unfavorable solution due to its high cost. The second is to apply (if possible) mitigation/protection measures in order to eliminate the geohazard itself. Finally, the last appealing option is to allow the pipeline crossing through the geohazard area, provided that the pipeline will have been verified against the expected PGDs. In areas with moderate or high seismicity the design of an offshore pipeline is more demanding due to the earthquake-related geohazards, such as landslides, soil liquefaction phenomena, and active faults. It is worthy to mention that although worldwide there is a great experience in offshore geotechnics and pipeline design, the experience in seismic design of offshore pipelines is rather limited due to the fact that most of the pipelines have been constructed in non-seismic regions (e.g. North Sea, West Australia, Gulf of Mexico, etc.). The current study focuses on the seismic design of offshore pipelines against active faults. After an extensive literature review of the provisions of the seismic norms worldwide and of the available analytical methods, the study simulates numerically (through finite-element modeling and strain-based criteria) the distress of offshore pipelines subjected to PGDs induced by active seismic faults at the seabed. Factors, such as the geometrical properties of the fault, the mechanical properties of the ruptured soil formations, and the pipeline characteristics, are examined. After some interesting conclusions regarding the seismic vulnerability of offshore pipelines, potential cost-effective mitigation measures are proposed taking into account constructability issues.

Keywords: offhore pipelines, seismic design, active faults, permanent ground deformations (PGDs)

Procedia PDF Downloads 591

Authors: Richard O’Riordan, Saritha Unnikrishnan

Abstract:

Autonomous Vehicles (AVs) are incorporating an increasing number of ADAS features, including automated lane-keeping systems. In recent years, many research papers into lane detection algorithms have been published, varying from computer vision techniques to deep learning methods. The transition from lower levels of autonomy defined in the SAE framework and the progression to higher autonomy levels requires increasingly complex models and algorithms that must be highly reliable in their operation and functionality capacities. Furthermore, these algorithms have no room for error when operating at high levels of autonomy. Although the current research details existing computer vision and deep learning algorithms and their methodologies and individual results, the research also details challenges faced by the algorithms and the resources needed to operate, along with shortcomings experienced during their detection of lanes in certain weather and lighting conditions. This paper will explore these shortcomings and attempt to implement a lane detection algorithm that could be used to achieve improvements in AV lane detection systems. This paper uses a pre-trained LaneNet model to detect lane or non-lane pixels using binary segmentation as the base detection method using an existing dataset BDD100k followed by a custom dataset generated locally. The selected roads will be modern well-laid roads with up-to-date infrastructure and lane markings, while the second road network will be an older road with infrastructure and lane markings reflecting the road network's age. The performance of the proposed method will be evaluated on the custom dataset to compare its performance to the BDD100k dataset. In summary, this paper will use Transfer Learning to provide a fast and robust lane detection algorithm that can handle various road conditions and provide accurate lane detection.

Keywords: ADAS, autonomous vehicles, deep learning, LaneNet, lane detection

Procedia PDF Downloads 107

Authors: Khairani Binti Supyan, Fatimah Khalid, Mas Rina Mustaffa, Azreen Bin Azman, Amirul Azuani Romle

Abstract:

Perennial plant classification plays a significant role in various agricultural and environmental applications, assisting in plant identification, disease detection, and biodiversity monitoring. Nevertheless, attaining high accuracy in perennial plant image classification remains challenging due to the complex variations in plant appearance, the diverse range of environmental conditions under which images are captured, and the inherent variability in image quality stemming from various factors such as lighting conditions, camera settings, and focus. This paper proposes an adaptation approach to optimize perennial plant image classification by fine-tuning the pre-trained DNNs model. This paper explores the efficacy of fine-tuning prevalent architectures, namely VGG16, ResNet50, and InceptionV3, leveraging transfer learning to tailor the models to the specific characteristics of perennial plant datasets. A subset of the MYLPHerbs dataset consisted of 6 perennial plant species of 13481 images under various environmental conditions that were used in the experiments. Different strategies for fine-tuning, including adjusting learning rates, training set sizes, data augmentation, and architectural modifications, were investigated. The experimental outcomes underscore the effectiveness of fine-tuning deep neural networks for perennial plant image classification, with ResNet50 showcasing the highest accuracy of 99.78%. Despite ResNet50's superior performance, both VGG16 and InceptionV3 achieved commendable accuracy of 99.67% and 99.37%, respectively. The overall outcomes reaffirm the robustness of the fine-tuning approach across different deep neural network architectures, offering insights into strategies for optimizing model performance in the domain of perennial plant image classification.

Keywords: perennial plants, image classification, deep neural networks, fine-tuning, transfer learning, VGG16, ResNet50, InceptionV3

Procedia PDF Downloads 67

Authors: Muhammad Alif Bin Razali, Cheng-Gang Xie, Wai Lam Loh

Abstract:

A venturi device is commonly used as an integral part of a multiphase flowmeter (MPFM) in real-time oil-gas production monitoring. For an accurate determination of individual phase fraction and flowrate, a gas-liquid flow ideally needs to be well mixed in the venturi measurement section. Partial flow mixing is achieved by installing a venturi vertically downstream of the blind-tee pipework that ‘homogenizes’ the incoming horizontal gas-liquid flow. In order to study in-depth the flow-mixing effect of the blind-tee, gas-liquid flows are captured at blind-tee and venturi sections by using a high-speed video camera and a purpose-built transparent test rig, over a wide range of superficial liquid velocities (0.3 to 2.4m/s) and gas volume fractions (10 to 95%). Electrical capacitance sensors are built to measure the instantaneous holdup (of oil-gas flows) at the venturi inlet and throat. Flow regimes and flow (a)symmetry are investigated based on analyzing the statistical features of capacitance sensors’ holdup time-series data and of the high-speed video time-stacked images. The perceived homogenization effect of the blind-tee on the incoming intermittent horizontal flow regimes is found to be relatively small across the tested flow conditions. A horizontal (blind-tee) to vertical (venturi) flow-pattern transition map is proposed based on gas and liquid mass fluxes (weighted by the Baker parameters).

Keywords: blind-tee, flow visualization, gas-liquid two-phase flow, MPFM

Procedia PDF Downloads 130

Authors: Zhifeng Xu, Zhongfan Chen

Abstract:

A series of tests on cold-formed steel foamed concrete (CSFC) composite walls subjected to axial load were proposed. The primary purpose of the experiments was to study the mechanical behavior and identify the failure modes of CSFC composite walls. Two main factors were considered in this study: 1) specimen with pouring foamed concrete or without and 2) different foamed concrete density ranks (corresponding to different foamed concrete strength). The interior space between two pieces of straw board of the specimen W-2 and W-3 were poured foamed concrete, and the specimen W-1 does not have foamed concrete core. The foamed concrete density rank of the specimen W-2 was A05 grade, and that of the specimen W-3 was A07 grade. Results showed that the failure mode of CSFC composite wall without foamed concrete was distortional buckling of cold-formed steel (CFS) column, and that poured foamed concrete includes the local crushing of foamed concrete and local buckling of CFS column, but the former prior to the later. Compared with CSFC composite wall without foamed concrete, the ultimate bearing capacity of spec imens poured A05 grade and A07 grade foamed concrete increased 1.6 times and 2.2 times respectively, and specimen poured foamed concrete had a low vertical deformation. According to these results, the simplified calculation formula for the CSFC wall subjected to axial load was proposed, and the calculated results from this formula are in very good agreement with the test results.

Keywords: cold-formed steel, composite wall, foamed concrete, axial behavior test

Procedia PDF Downloads 337

Authors: Yong Chen

Abstract:

To understand the detailed molecular mechanisms of memory formation in engram cells is one of the most fundamental questions in neuroscience. Recent single-cell RNA-seq (scRNA-seq) and single-nucleus RNA-seq (snRNA-seq) techniques have allowed us to explore the sparsely activated engram ensembles, enabling access to the molecular mechanisms that underlie experience-dependent memory formation and consolidation. However, the absence of specific and powerful computational methods to detect memory-related genes (modules) and their regulatory relationships in the sc/snRNA-seq datasets has strictly limited the analysis of underlying mechanisms and memory coding principles in mammalian brains. Here, we present a deep-learning method named SCENTBOX, to detect memory-related gene modules and causal regulatory relationships among themfromsc/snRNA-seq datasets. SCENTBOX first constructs codifferential expression gene network (CEGN) from case versus control sc/snRNA-seq datasets. It then detects the highly correlated modules of differential expression genes (DEGs) in CEGN. The deep network embedding and attention-based convolutional neural network strategies are employed to precisely detect regulatory relationships among DEG genes in a module. We applied them on scRNA-seq datasets of TRAP; Ai14 mouse neurons with fear memory and detected not only known memory-related genes, but also the modules and potential causal regulations. Our results provided novel regulations within an interesting module, including Arc, Bdnf, Creb, Dusp1, Rgs4, and Btg2. Overall, our methods provide a general computational tool for processing sc/snRNA-seq data from case versus control studie and a systematic investigation of fear-memory-related gene modules.

Keywords: sc/snRNA-seq, memory formation, deep learning, gene module, causal inference

Procedia PDF Downloads 121

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 171

Authors: A. Degale Desta, Cheng Jian

Abstract:

Deep learning application in computer vision is rapidly advancing, giving it the ability to monitor the public and quickly identify potentially anomalous behaviour from crowd scenes. Therefore, the purpose of the current work is to improve the performance of safety of people in crowd events from panic behaviour through introducing the innovative idea of Aggregation of Ensembles (AOE), which makes use of the pre-trained ConvNets and a pool of classifiers to find anomalies in video data with packed scenes. According to the theory of algorithms that applied K-means, KNN, CNN, SVD, and Faster-CNN, YOLOv5 architectures learn different levels of semantic representation from crowd videos; the proposed approach leverages an ensemble of various fine-tuned convolutional neural networks (CNN), allowing for the extraction of enriched feature sets. In addition to the above algorithms, a long short-term memory neural network to forecast future feature values and a handmade feature that takes into consideration the peculiarities of the crowd to understand human behavior. On well-known datasets of panic situations, experiments are run to assess the effectiveness and precision of the suggested method. Results reveal that, compared to state-of-the-art methodologies, the system produces better and more promising results in terms of accuracy and processing speed.

Keywords: action recognition, computer vision, crowd detecting and tracking, deep learning

Procedia PDF Downloads 165

Authors: Ayorinde B. Ogunremi, Kehinde A. Adewoyin, Adebamwo Adebayo

Abstract:

Record of radionuclide concentration in an environment is essential to ensure human safety due to exposure to ionizing radiation. This study aimed at assessing the radionuclide concentration and doses from soil samples in the study area. Twenty soil samples were collected and dried in the oven at 110°C to remove the moisture, pulverized, and sieved. 200 g of each of the samples were sealed in cylindrical sample holders; they were left for four weeks to attain secular equilibrium between ²²⁶Ra and its decay daughters, after which the sample was analyzed using gamma-ray spectrometry. After the well-guided procedure for the calibrations, the analysis of the samples was carried out using a well-calibrated NaI (TI) and well-shielded detector coupled to a computer resident quantum MCA2100 R Multichannel analyzer for 36,000 s. The mean activity concentrations of ⁴⁰K, ²²⁶Ra, and ²³²Th obtained were calculated to be 272.37 ± 33.58, 10.97 ± 3.24, 9.39 ± 2.27 Bqkg-1 respectively. The average absorbed dose obtained was 22.10 nGy/h. The radium equivalent activity (Raeq) was estimated to be 43.27 Bq/kg. The activity concentrations (Bq/kg) were below the recommended values, which are 420, 33, and 45 for ⁴⁰K, ²²⁶Ra, and ²³²Th, respectively. Considering the results, we conclude thus, the radiation level within the estate poses no significant health risk on dwellers and workers.

Keywords: absorbed, effective, multichannel, radionuclide

Procedia PDF Downloads 217

Authors: Genevieve D. Fernandes, Nisha P. Naik

Abstract:

All through the ages in all human civilizations, men have been engaged in construction activity, not only to build their dwellings and house their activities, but also roads, bridges to facilitate means of transport, and communication etc. The main concern in this activity was to ensure safety and reduce the collapse of the buildings and other structures. But even after taking all precautions, it is impossible to guarantee safety and collapse because of several unforeseen reasons like faulty constructions, design errors, overloading, soil liquefaction, gas explosion, material degradation, terrorist attacks and economic factors also contributing to the collapse. It is also uneconomical to design the structure for unforeseen events unless they have a reasonable chance of occurrence. In order to ensure safety and prevent collapse, many guidelines have been framed by local bodies and government authorities in many countries like the United States Department of Defence (DOD), United States General Service Administration (GSA) and Euro-Codes in European Nations. Some other practices are followed to incorporate redundancies in the structure like detailing, ductile designs, tying of elements at particular locations, and provision of hinges and interconnections. It is also to be admitted that a full-proof safe design structure for accidental events cannot be prepared and implemented as it is uneconomical and the chances of such occurrences are less. This paper reviews past case studies of the collapse of structures with the aim of developing an understanding of the collapse mechanism. This study will definitely help to bring about a detailed improvement in the design to maximise the quality of the construction at a minimal cost.

Keywords: unforeseen factors, progressive collapse, collapse resisting mechanisms, column removal scenario

Procedia PDF Downloads 138

Authors: Warda L. Panondi, Norihiro Izumi

Abstract:

Sedimentation is a significant threat to the sustainability of reservoirs and their watershed. In the Philippines, the Pulangi watershed experienced a high sediment loss mainly due to land conversions and plantations that showed critical erosion rates beyond the tolerable limit of -10 ton/ha/yr in all of its sub-basin. From this event, the prediction of runoff volume and sediment yield is essential to examine using the country's soil conservation techniques realistically. In this research, the Pulangi watershed was modeled using the soil water assessment tool (SWAT) to predict its watershed basin's annual runoff and sediment yield. For the calibration and validation of the model, the SWAT-CUP was utilized. The model was calibrated with monthly discharge data for 1990-1993 and validated for 1994-1997. Simultaneously, the sediment yield was calibrated in 2014 and validated in 2015 because of limited observed datasets. Uncertainty analysis and calculation of efficiency indexes were accomplished through the SUFI-2 algorithm. According to the coefficient of determination (R2), Nash Sutcliffe efficiency (NSE), King-Gupta efficiency (KGE), and PBIAS, the calculation of streamflow indicates a good performance for both calibration and validation periods while the sediment yield resulted in a satisfactory performance for both calibration and validation. Therefore, this study was able to identify the most critical sub-basin and severe needs of soil conservation. Furthermore, this study will provide baseline information to prevent floods and landslides and serve as a useful reference for land-use policies and watershed management and sustainability in the Pulangi watershed.

Keywords: Pulangi watershed, sediment yield, streamflow, SWAT model

Procedia PDF Downloads 210

Authors: Judith Mwakalonge, Geophrey Mbatta, Saidi Siuhi, Gurcan Comert, Cuthbert Ruseruka

Abstract:

Transportation agencies worldwide continuously monitor their roads' conditions to minimize road maintenance costs and maintain public safety and rideability quality. Existing methods for carrying out road condition surveys involve manual observations of roads using standard survey forms done by qualified road condition surveyors or engineers either on foot or by vehicle. Automated road condition survey vehicles exist; however, they are very expensive since they require special vehicles equipped with sensors for data collection together with data processing and computing devices. The manual methods are expensive, time-consuming, infrequent, and can hardly provide real-time information for road conditions. This study contributes to this arena by utilizing built-in vehicle technologies, drones, and deep learning to automate road condition surveys while using low-cost technology. A single model is trained to capture flexible pavement distresses (Potholes, Rutting, Cracking, and raveling), thereby providing a more cost-effective and efficient road condition monitoring approach that can also provide real-time road conditions. Additionally, data fusion is employed to enhance the road condition assessment with data from vehicles and drones.

Keywords: road conditions, built-in vehicle technology, deep learning, drones

Procedia PDF Downloads 127

Authors: Hongmei Wang, Ziyun Xiang, Ying liu, Li Yu, Dongsheng Yue

Abstract:

Intro: The COVID-19 (Corona Virus Disease 2019) has greatly changed the global economic, political and financial ecology. The mutation of the coronavirus in the UK in December 2020 has brought new panic to the world. Deep learning was performed on Chest Computed tomography (CT) of COVID-19 and Influenza and describes their characteristics. The predominant features of COVID-19 pneumonia was ground-glass opacification, followed by consolidation. Lesion density: most lesions appear as ground-glass shadows, and some lesions coexist with solid lesions. Lesion distribution: the focus is mainly on the dorsal side of the periphery of the lung, with the lower lobe of the lungs as the focus, and it is often close to the pleura. Other features it has are grid-like shadows in ground glass lesions, thickening signs of diseased vessels, air bronchi signs and halo signs. The severe disease involves whole bilateral lungs, showing white lung signs, air bronchograms can be seen, and there can be a small amount of pleural effusion in the bilateral chest cavity. At the same time, this year's flu season could be near its peak after surging throughout the United States for months. Chest CT for Influenza infection is characterized by focal ground glass shadows in the lungs, with or without patchy consolidation, and bronchiole air bronchograms are visible in the concentration. There are patchy ground-glass shadows, consolidation, air bronchus signs, mosaic lung perfusion, etc. The lesions are mostly fused, which is prominent near the hilar and two lungs. Grid-like shadows and small patchy ground-glass shadows are visible. Deep neural networks have great potential in image analysis and diagnosis that traditional machine learning algorithms do not. Method: Aiming at the two major infectious diseases COVID-19 and influenza, which are currently circulating in the world, the chest CT of patients with two infectious diseases is classified and diagnosed using deep learning algorithms. The residual network is proposed to solve the problem of network degradation when there are too many hidden layers in a deep neural network (DNN). The proposed deep residual system (ResNet) is a milestone in the history of the Convolutional neural network (CNN) images, which solves the problem of difficult training of deep CNN models. Many visual tasks can get excellent results through fine-tuning ResNet. The pre-trained convolutional neural network ResNet is introduced as a feature extractor, eliminating the need to design complex models and time-consuming training. Fastai is based on Pytorch, packaging best practices for in-depth learning strategies, and finding the best way to handle diagnoses issues. Based on the one-cycle approach of the Fastai algorithm, the classification diagnosis of lung CT for two infectious diseases is realized, and a higher recognition rate is obtained. Results: A deep learning model was developed to efficiently identify the differences between COVID-19 and influenza using chest CT.

Keywords: COVID-19, Fastai, influenza, transfer network

Procedia PDF Downloads 144

Authors: A. Bayoumi, M. Abdallah, F. Hage Chehade

Abstract:

Structures on the ground surface bear impact from the tunneling-induced settlement, especially when twin tunnels are constructed. The tunneling influence on the structure is considered as a critical issue based on the construction procedure and relative position of tunnels. Lebanon is suffering from a traffic phenomenon caused by the lack of transportation systems. After several traffic counts and geotechnical investigations in Beirut city, efforts aim for the construction of tunneling systems. In this paper, we present a non-linear numerical modeling of the effect of the twin tunnels constructions on the structures located at soil surface for a particular site in Beirut. A parametric study, which concerns the geometric configuration of tunnels, the distance between their centers, the construction order, and the position of the structure, is performed. The tunnel-soil-structure interaction is analyzed by using the non-linear finite element modeling software PLAXIS 2D. The results of the surface settlement and the bending moment of the structure reveal significant influence when the structure is moved away, especially in vertical aligned tunnels.

Keywords: bending moment, elastic modulus, horizontal twin tunnels, soil, structure location, surface settlement, vertical twin tunnels

Procedia PDF Downloads 298

Authors: Mohammad R. Jafari, Francois G. Bernardeau

Abstract:

With its arid climate, Qatar experiences low annual rainfall, intense storms, and high evaporation rates. However, the fast-paced rate of infrastructure development in the capital city of Doha has led to recurring instances of surface water flooding as well as rising groundwater levels. Public Work Authority (PWA/ASHGHAL) has implemented an approach to collect and discharge the flood water into a) positive gravity systems; b) Emergency Flooding Area (EFA) – Evaporation, Infiltration or Storage off-site using tankers; and c) Discharge to deep injection wells. As part of the flood prevention scheme, 21 deep injection wells have been constructed to discharge the collected surface and groundwater table in Doha city. These injection wells function as an alternative in localities that do not possess either positive gravity systems or downstream networks that can accommodate additional loads. These injection wells are 400-m deep and are constructed in a complex karstic subsurface condition with large cavities. The injection well system will discharge collected groundwater and storm surface runoff into the permeable Umm Er Radhuma Formation, which is an aquifer present throughout the Persian Gulf Region. The Umm Er Radhuma formation contains saline water that is not being used for water supply. The injection zone is separated by an impervious gypsum formation which acts as a barrier between upper and lower aquifer. State of the art drilling, grouting, and geophysical techniques have been implemented in construction of the wells to assure that the shallow aquifer would not be contaminated and impacted by injected water. Injection and pumping tests were performed to evaluate injection well functionality (injectability). The results of these tests indicated that majority of the wells can accept injection rate of 200 to 300 m³ /h (56 to 83 l/s) under gravity with average value of 250 m³ /h (70 l/s) compared to design value of 50 l/s. This paper presents design and construction process and issues associated with these injection wells, performing injection/pumping tests to determine capacity and effectiveness of the injection wells, the detailed design of collection system and conveying system into the injection wells, and the operation and maintenance process. This system is completed now and is under operation, and therefore, construction of injection wells is an effective option for flood control.

Keywords: deep injection well, flood prevention scheme, geophysical tests, pumping and injection tests, wellhead assembly

Procedia PDF Downloads 120