Search results for: empathic accuracy

Authors: David Chao, John Lai, Alvin Wu, Carl Wang

Abstract:

For lithium-ion batteries with multiple cell configurations, some use scenarios can cause uneven aging effects to each cell within the battery because of uneven current distribution. Hence the focus of the study is to explore the aging effect(s) on batteries with different construction designs. In order to systematically study the influence of various factors in some key battery configurations, a detailed analysis of three key battery construction factors is conducted. And those key factors are (1) terminal position; (2) cell alignment matrix; and (3) interconnect resistance between cells. In this study, the 2S2P circuitry has been set as a model multi-cell battery to set up different battery samples, and the aging behavior is studied by a cycling test to analyze the current distribution and recoverable capacity. According to the outcome of aging tests, some key findings are: (I) different cells alignment matrices can have an impact on the cycle life of the battery; (II) symmetrical structure has been identified as a critical factor that can influence the battery cycle life, and unbalanced resistance can lead to inconsistent cell aging status; (III) the terminal position has been found to contribute to the uneven current distribution, that can cause an accelerated battery aging effect; and (IV) the internal connection resistance increase can actually result in cycle life increase; however, it is noteworthy that such increase in cycle life is accompanied by a decline in battery performance. In summary, the key findings from the study can help to identify the key aging factor of multi-cell batteries, and it can be useful to effectively improve the accuracy of battery capacity predictions.

Keywords: multiple cells battery, current distribution, battery aging, cell connection

Procedia PDF Downloads 80

Authors: Siwei Chang, Heng Li, Haitao Wu, Xin Fang

Abstract:

Construction robots are receiving more and more attention as a promising solution to the manpower shortage issue in the construction industry. The development of intelligent control techniques that assist in controlling the robots to avoid transparency and reflected building obstacles is crucial for guaranteeing the adaptability and flexibility of mobile construction robots in complex construction environments. With the boom of computer vision techniques, a number of studies have proposed vision-based methods for transparent obstacle avoidance to improve operation accuracy. However, vision-based methods are also associated with disadvantages such as high computational costs. To provide better perception and value evaluation, this study aims to analyze the performance of vision-based techniques for avoiding transparent building obstacles. To achieve this, commonly used sensors, including a lidar, an ultrasonic sensor, and a USB camera, are equipped on the robotic platform to detect obstacles. A Raspberry Pi 3 computer board is employed to compute data collecting and control algorithms. The turtlebot3 burger is employed to test the programs. On-site experiments are carried out to observe the performance in terms of success rate and detection distance. Control variables include obstacle shapes and environmental conditions. The findings contribute to demonstrating how effectively vision-based obstacle avoidance strategies for transparent building obstacle avoidance and provide insights and informed knowledge when introducing computer vision techniques in the aforementioned domain.

Keywords: construction robot, obstacle avoidance, computer vision, transparent obstacle

Procedia PDF Downloads 80

Authors: Xiyang Li, Qi Yu, Lun Zhang

Abstract:

In the face of natural disasters and other emergency situations, determining the optimal location of rescue centers is crucial for improving rescue efficiency and minimizing impact on affected populations. This paper proposes a method that integrates genetic algorithms (GA) and backpropagation neural networks (BPNN) to address the site selection optimization problem for emergency rescue centers. We utilize BPNN to accurately estimate the cost of delivering supplies from rescue centers to each temporary camp. Moreover, a genetic algorithm with a special partially matched crossover (PMX) strategy is employed to ensure that the number of temporary camps assigned to each rescue center adheres to predetermined limits. Using the population distribution data during the 2022 epidemic in Jiading District, Shanghai, as an experimental case, this paper verifies the effectiveness of the proposed method. The experimental results demonstrate that the BPNN-GA method proposed in this study outperforms existing algorithms in terms of computational efficiency and optimization performance. Especially considering the requirements for computational resources and response time in emergency situations, the proposed method shows its ability to achieve rapid convergence and optimal performance in the early and mid-stages. Future research could explore incorporating more real-world conditions and variables into the model to further improve its accuracy and applicability.

Keywords: emergency rescue centers, genetic algorithms, back-propagation neural networks, site selection optimization

Procedia PDF Downloads 85

Authors: Alireza Rasekh, Peter Sergeant, Jan Vierendeels

Abstract:

This paper copes with the numerical simulation for convective heat transfer in the stator disk of an axial flux permanent magnet (AFPM) electrical machine. Overheating is one of the main issues in the design of AFMPs, which mainly occurs in the stator disk, so that it needs to be prevented. A rotor-stator configuration with 16 magnets at the periphery of the rotor is considered. Air is allowed to flow through openings in the rotor disk and channels being formed between the magnets and in the gap region between the magnets and the stator surface. The rotating channels between the magnets act as a driving force for the air flow. The significant non-dimensional parameters are the rotational Reynolds number, the gap size ratio, the magnet thickness ratio, and the magnet angle ratio. The goal is to find correlations for the Nusselt number on the stator disk according to these non-dimensional numbers. Therefore, CFD simulations have been performed with the multiple reference frame (MRF) technique to model the rotary motion of the rotor and the flow around and inside the machine. A minimization method is introduced by a pattern-search algorithm to find the appropriate values of the reference temperature. It is found that the correlations are fast, robust and is capable of predicting the stator heat transfer with a good accuracy. The results reveal that the magnet angle ratio diminishes the stator heat transfer, whereas the rotational Reynolds number and the magnet thickness ratio improve the convective heat transfer. On the other hand, there a certain gap size ratio at which the stator heat transfer reaches a maximum.

Keywords: AFPM, CFD, magnet parameters, stator heat transfer

Procedia PDF Downloads 250

Authors: Erin Curtis, Avraham Schwiger

Abstract:

Neuropsychological testing and evaluation is a crucial step in providing patients with effective diagnoses and treatment while in clinical care. The variety of batteries used in these evaluations can help clinicians better understand the nuanced declivities in a patient’s cognitive, behavioral, or emotional functioning, consequently equipping clinicians with the insights to make intentional choices about a patient’s care. Despite the knowledge these batteries can yield, some aspects of neuropsychological testing remain largely inaccessible to certain patient groups as a result of fundamental cultural, educational, or social differences. One such battery includes the Dot Counting Test (DCT), during which patients are required to count a series of dots on a page as rapidly and accurately as possible. As the battery progresses, the dots appear in clusters that are designed to be easily multiplied. This task evaluates a patient’s cognitive functioning, attention, and level of effort exerted on the evaluation as a whole. However, there is evidence to suggest that certain social groups, particularly Latinx groups, may perform worse on this task as a result of cultural or educational differences, not reduced cognitive functioning or effort. As such, this battery fails to account for baseline differences among patient groups, thus creating questions surrounding the accuracy, generalizability, and value of its results. Accessibility and cultural sensitivity are critical considerations in the testing and treatment of marginalized groups, yet have been largely ignored in the literature and in clinical settings to date. Implications and improvements to applications are discussed.

Keywords: culture, latino, neuropsychological assessment, neuropsychology, accessibility

Procedia PDF Downloads 113

Authors: Sun-Jin Han, Deuck Hang Lee, Hyo-Eun Joo, Hyun Kang, Kang Su Kim

Abstract:

In pretensioned concrete members, the transfer length region is existed, in which the stress in prestressing strand is developed due to the bond mechanism with surrounding concrete. The stress of strands in the transfer length zone is smaller than that in the strain plateau zone, so-called effective prestress, therefore the web-shear strength in transfer length region is smaller than that in the strain plateau zone. Although the transfer length is main key factor in the shear design, a few analytical researches have been conducted to investigate the transfer length. Therefore, in this study, a theoretical approach was used to estimate the transfer length. The bond stress developed between the strands and the surrounding concrete was quantitatively calculated by using the Thick-Walled Cylinder Model (TWCM), based on this, the transfer length of strands was calculated. To verify the proposed model, a total of 209 test results were collected from the previous studies. Consequently, the analysis results showed that the main influencing factors on the transfer length are the compressive strength of concrete, the cover thickness of concrete, the diameter of prestressing strand, and the magnitude of initial prestress. In addition, the proposed model predicted the transfer length of collected test specimens with high accuracy. Acknowledgement: This research was supported by a grant(17TBIP-C125047-01) from Technology Business Innovation Program funded by Ministry of Land, Infrastructure and Transport of Korean government.

Keywords: bond, Hoyer effect, prestressed concrete, prestressing strand, transfer length

Procedia PDF Downloads 295

Authors: Yu-ding Du, Qi-lian Bao, Nassim Bessaad, Lin Liu

Abstract:

The Global Navigation Satellite System (GNSS) is regarded as an effective approach for the purpose of replacing the large amount used track-side balises in modern train localization systems. This paper describes a method based on the data fusion of a GNSS receiver sensor and an odometer sensor that can significantly improve the positioning accuracy. A digital track map is needed as another sensor to project two-dimensional GNSS position to one-dimensional along-track distance due to the fact that the train’s position can only be constrained on the track. A model trained by BP neural network is used to estimate the trend positioning error which is related to the specific location and proximate processing of the digital track map. Considering that in some conditions the satellite signal failure will lead to the increase of GNSS positioning error, a detection step for GNSS signal is applied. An adaptive weighted fusion algorithm is presented to reduce the standard deviation of train speed measurement. Finally an Extended Kalman Filter (EKF) is used for the fusion of the projected 1-D GNSS positioning data and the 1-D train speed data to get the estimate position. Experimental results suggest that the proposed method performs well, which can reduce positioning error notably.

Keywords: multi-sensor data fusion, train positioning, GNSS, odometer, digital track map, map matching, BP neural network, adaptive weighted fusion, Kalman filter

Procedia PDF Downloads 252

Authors: Joselito Medina-Marin, Maria G. Serna-Diaz, Juan C. Seck-Tuoh-Mora, Norberto Hernandez-Romero, Irving Barragán-Vite

Abstract:

Wind speed forecasting is an important issue for planning wind power generation facilities. The accuracy in the wind speed prediction allows a good performance of wind turbines for electricity generation. A model based on artificial neural networks is presented in this work. A dataset with atmospheric information about air temperature, atmospheric pressure, wind direction, and wind speed in Pachuca, Hidalgo, México, was used to train the artificial neural network. The data was downloaded from the web page of the National Meteorological Service of the Mexican government. The records were gathered for three months, with time intervals of ten minutes. This dataset was used to develop an iterative algorithm to create 1,110 ANNs, with different configurations, starting from one to three hidden layers and every hidden layer with a number of neurons from 1 to 10. Each ANN was trained with the Levenberg-Marquardt backpropagation algorithm, which is used to learn the relationship between input and output values. The model with the best performance contains three hidden layers and 9, 6, and 5 neurons, respectively; and the coefficient of determination obtained was r²=0.9414, and the Root Mean Squared Error is 1.0559. In summary, the ANN approach is suitable to predict the wind speed in Pachuca City because the r² value denotes a good fitting of gathered records, and the obtained ANN model can be used in the planning of wind power generation grids.

Keywords: wind power generation, artificial neural networks, wind speed, coefficient of determination

Procedia PDF Downloads 124

Authors: Lal Hussain, Wajid Aziz, Imtiaz Ahmed Awan, Sharjeel Saeed

Abstract:

Multiscale entropy analysis (MSE) is a useful technique recently developed to quantify the dynamics of physiological signals at different time scales. This study is aimed at investigating the electroencephalogram (EEG) signals to analyze the background activity of alcoholic and control subjects by inspecting various coarse-grained sequences formed at different time scales. EEG recordings of alcoholic and control subjects were taken from the publically available machine learning repository of University of California (UCI) acquired using 64 electrodes. The MSE analysis was performed on the EEG data acquired from all the electrodes of alcoholic and control subjects. Mann-Whitney rank test was used to find significant differences between the groups and result were considered statistically significant for p-values<0.05. The area under receiver operator curve was computed to find the degree separation between the groups. The mean ranks of MSE values at all the times scales for all electrodes were higher control subject as compared to alcoholic subjects. Higher mean ranks represent higher complexity and vice versa. The finding indicated that EEG signals acquired through electrodes C3, C4, F3, F7, F8, O1, O2, P3, T7 showed significant differences between alcoholic and control subjects at time scales 1 to 5. Moreover, all electrodes exhibit significance level at different time scales. Likewise, the highest accuracy and separation was obtained at the central region (C3 and C4), front polar regions (P3, O1, F3, F7, F8 and T8) while other electrodes such asFp1, Fp2, P4 and F4 shows no significant results.

Keywords: electroencephalogram (EEG), multiscale sample entropy (MSE), Mann-Whitney test (MMT), Receiver Operator Curve (ROC), complexity analysis

Procedia PDF Downloads 376

Authors: Fujia Yang

Abstract:

Alongside technological innovation, the current “double reduction” policy and English Curriculum Standards for Compulsory Education in China both emphasise and encourage appropriately integrating educational technologies into the classroom. Therefore, schools are increasingly using digital means to engage students in English reading, but the impact of such technologies on Chinese pupils’ reading achievement remains unclear. To serve as a reference for reforming English reading education in primary schools under the double reduction policy, this study investigates the effects and primary influencing factors of a specific reading programme, Accelerated Reader (AR), on Chinese primary school students’ reading achievement. A quantitative online survey was used to collect 37 valid questionnaires from teachers, and the results demonstrate that, from teachers’ perspectives, the AR program seemed to positively affect students’ reading achievement by recommending material at the appropriate reading levels and developing students’ reading habits. Although the reading enjoyment derived from the AR program does not directly influence students’ reading achievement, these factors are strongly correlated. This can be explained by the self-paced, independent learning AR format, its high accuracy in predicting reading level, the quiz format and external motivation, and the importance of examinations and resource limitations in China. The results of this study may support reforming English reading education in Chinese primary schools.

Keywords: educational technology, reading programme, primary students, accelerated reader, reading effects

Procedia PDF Downloads 84

Authors: Junbeom Lee, Jaehyuck Cho, Wookyeong Jeong, Jonghan Won, Jungmin Hwang, Youngseok Song, Taikyeong Jeong

Abstract:

This paper investigates and analyzes meta-learning technologies that use multiple-cameras to monitor and check abnormal behavior in people in real-time in the area of healthcare fields. Advances in artificial intelligence and computer vision technologies have confirmed that cameras can be useful for individual health monitoring and abnormal behavior detection. Through this, it is possible to establish a system that can respond early by automatically detecting abnormal behavior of the elderly, such as patients and the elderly. In this paper, we use a technique called meta-learning to analyze image data collected from cameras and develop a commercial product to determine abnormal behavior. Meta-learning applies machine learning algorithms to help systems learn and adapt quickly to new real data. Through this, the accuracy and reliability of the abnormal behavior discrimination system can be improved. In addition, this study proposes a meta-learning-based abnormal behavior detection system that includes steps such as data collection and preprocessing, feature extraction and selection, and classification model development. Various healthcare scenarios and experiments analyze the performance of the proposed system and demonstrate excellence compared to other existing methods. Through this study, we present the possibility that camera-based meta-learning technology can be useful for monitoring and testing abnormal behavior in the healthcare area.

Keywords: artificial intelligence, abnormal behavior, early detection, health monitoring

Procedia PDF Downloads 86

Authors: Hamed Yousefi, Farnaz Mohammadi, Niloufar Mirian, Navid Amini

Abstract:

Investigating possible capacities of visual functions where adapted mechanisms can enhance the capability of sports trainees is a promising area of research, not only from the cognitive viewpoint but also in terms of unlimited applications in sports training. In this paper, the visual evoked potential (VEP) and event-related potential (ERP) signals of amateur and trained volleyball players in a pilot study were processed. Two groups of amateur and trained subjects are asked to imagine themselves in the state of receiving a ball while they are shown a simulated volleyball field. The proposed method is based on a set of time-frequency features using algorithms such as Gabor filter, continuous wavelet transform, and a multi-stage wavelet decomposition that are extracted from VEP signals that can be indicative of being amateur or trained. The linear discriminant classifier achieves the accuracy, sensitivity, and specificity of 100% when the average of the repetitions of the signal corresponding to the task is used. The main purpose of this study is to investigate the feasibility of a fast, robust, and reliable feature/model determination as a neurofeedback parameter to be utilized for improving the volleyball players’ performance. The proposed measure has potential applications in brain-computer interface technology where a real-time biomarker is needed.

Keywords: visual evoked potential, time-frequency feature extraction, short-time Fourier transform, event-related spectrum potential classification, linear discriminant analysis

Procedia PDF Downloads 138

Authors: Abdulkader Helwan

Abstract:

Iris cancer, so called intraocular melanoma is a cancer that starts in the iris; the colored part of the eye that surrounds the pupil. There is a need for an accurate and cost-effective iris cancer detection system since the available techniques used currently are still not efficient. The combination of the image processing and artificial neural networks has a great efficiency for the diagnosis and detection of the iris cancer. Image processing techniques improve the diagnosis of the cancer by enhancing the quality of the images, so the physicians diagnose properly. However, neural networks can help in making decision; whether the eye is cancerous or not. This paper aims to develop an intelligent system that stimulates a human visual detection of the intraocular melanoma, so called iris cancer. The suggested system combines both image processing techniques and neural networks. The images are first converted to grayscale, filtered, and then segmented using prewitt edge detection algorithm to detect the iris, sclera circles and the cancer. The principal component analysis is used to reduce the image size and for extracting features. Those features are considered then as inputs for a neural network which is capable of deciding if the eye is cancerous or not, throughout its experience adopted by many training iterations of different normal and abnormal eye images during the training phase. Normal images are obtained from a public database available on the internet, “Mile Research”, while the abnormal ones are obtained from another database which is the “eyecancer”. The experimental results for the proposed system show high accuracy 100% for detecting cancer and making the right decision.

Keywords: iris cancer, intraocular melanoma, cancerous, prewitt edge detection algorithm, sclera

Procedia PDF Downloads 503

Authors: Wendy Flory, Kazi Czarnecki, Matthijs Mercy, Mark Joswiak, Mary Beth Seasholtz

Abstract:

Polyurethane Materials are present in a wide range of industrial segments such as Furniture, Building and Construction, Composites, Automotive, Electronics, and more. Dow is one of the leaders for the manufacture of the two main raw materials, Isocyanates and Polyols used to produce polyurethane products. Dow is also a key player for the manufacture of Polyurethane Systems/Formulations designed for targeted applications. In 1990, the first analytical chemometric models were developed and deployed for use in the Dow QC labs of the polyols business for the quantification of OH, water, cloud point, and viscosity. Over the years many models have been added; there are now over 140 models for quantification and hundreds for product identification, too many to be reasonable for support. There are 29 global models alone for the quantification of OH across > 70 products at many sites. An attempt was made to consolidate these into a single model. While the consolidated model proved good statistics across the entire range of OH, several products had a bias by ASTM E1655 with individual product validation. This project summary will show the strategy for global model updates for OH, to reduce the number of models for quantification from over 140 to 5 or less using chemometric methods. In order to gain an understanding of the best product groupings, we identify clusters by reducing spectra to a few dimensions via Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP). Results from these cluster analyses and a separate validation set allowed dow to reduce the number of models for predicting OH from 29 to 3 without loss of accuracy.

Keywords: hydroxyl, global model, model maintenance, near infrared, polyol

Procedia PDF Downloads 135

Authors: Daudi S. Simbeye, Mbazingwa E. Mkiramweni

Abstract:

Plant diseases have the potential to drastically diminish the quantity and quality of agricultural products. Guava (Psidium guajava), sometimes known as the apple of the tropics, is one of the most widely cultivated fruits in tropical regions. Monitoring plant health and diagnosing illnesses is an essential matter for sustainable agriculture, requiring the inspection of visually evident patterns on plant leaves and fruits. Due to minor variations in the symptoms of various guava illnesses, a professional opinion is required for disease diagnosis. Due to improper pesticide application by farmers, erroneous diagnoses may result in economic losses. This study proposes a method that uses artificial intelligence (AI) to detect and classify the most widespread guava plant by comparing images of its leaves and fruits to datasets. ESP32 CAM is responsible for data collection, which includes images of guava leaves and fruits. By comparing the datasets, these image formats are used as datasets to help in the diagnosis of plant diseases through the leaves and fruits, which is vital for the development of an effective automated agricultural system. The system test yielded the most accurate identification findings (99 percent accuracy in differentiating four guava fruit diseases (Canker, Mummification, Dot, and Rust) from healthy fruit). The proposed model has been interfaced with a mobile application to be used by smartphones to make a quick and responsible judgment, which can help the farmers instantly detect and prevent future production losses by enabling them to take precautions beforehand.

Keywords: early identification, guava plants, fruit diseases, deep learning

Procedia PDF Downloads 76

Authors: Shanshan Zhu, Mohammad Nasim

Abstract:

Financial fraud continues to be a major threat to financial institutions across the world, causing colossal money losses and undermining public trust. Fraud prevention techniques, based on hard rules, have become ineffective due to evolving patterns of fraud in recent times. Against such a background, the present study probes into distinct methodologies that exploit emergent AI-driven techniques to further strengthen fraud detection. We would like to compare the performance of generative adversarial networks and graph neural networks with other popular techniques, like gradient boosting, random forests, and neural networks. To this end, we would recommend integrating all these state-of-the-art models into one robust, flexible, and smart system for real-time anomaly and fraud detection. To overcome the challenge, we designed synthetic data and then conducted pattern recognition and unsupervised and supervised learning analyses on the transaction data to identify which activities were fishy. With the use of actual financial statistics, we compare the performance of our model in accuracy, speed, and adaptability versus conventional models. The results of this study illustrate a strong signal and need to integrate state-of-the-art, AI-driven fraud detection solutions into frameworks that are highly relevant to the financial domain. It alerts one to the great urgency that banks and related financial institutions must rapidly implement these most advanced technologies to continue to have a high level of security.

Keywords: AI-driven fraud detection, financial security, machine learning, anomaly detection, real-time fraud detection

Procedia PDF Downloads 42

Authors: Timir Baran Roy, Luis Guerreiro, Ashutosh Bagchi

Abstract:

Dynamic study is important in order to design, repair and rehabilitation of structures. It has played an important role in the behavior characterization of structures; such as bridges, dams, high-rise buildings etc. There had been a substantial development in this area over the last few decades, especially in the field of dynamic identification techniques of structural systems. Frequency Domain Decomposition (FDD) and Time Domain Decomposition are most commonly used methods to identify modal parameters; such as natural frequency, modal damping, and mode shape. The focus of the present research is to study the dynamic characteristics of typical timber masonry walls commonly used in Portugal. For that purpose, a multi-storey structural prototypes of such walls have been tested on a seismic shake table at the National Laboratory for Civil Engineering, Portugal (LNEC). Signal processing has been performed of the output response, which is collected from the shaking table experiment of the prototype using accelerometers. In the present work signal processing of the output response, based on the input response has been done in two ways: FDD and Stochastic Subspace Identification (SSI). In order to estimate the values of the modal parameters, algorithms for FDD are formulated, and parametric functions for the SSI are computed. Finally, estimated values from both the methods are compared to measure the accuracy of both the techniques.

Keywords: frequency domain decomposition (fdd), modal parameters, signal processing, stochastic subspace identification (ssi), time domain decomposition

Procedia PDF Downloads 264

Authors: Jikhil Joseph, S. R. Satish Kumar

Abstract:

Steel Structures are commonly used for rapid erections and multistory constructions due to its inherent advantages. However, the high accuracy required in detailing and heavier sections, make it difficult to erect in place and transport. Cold Formed steel which are specially made by reducing carbon and other alloys are used nowadays to make thin-walled structures. Various types of connections are being reported as well as practiced for the thin-walled members such as bolting, riveting, welding and other mechanical connections. Commonly self-drilling screw connections are used for cold-formed purlin sheeting connection. In this paper an attempt is made to develop a moment resting frame which can be rapidly and remotely constructed with thin walled sections and self-drilling screws. Semi-rigid Moment connections are developed with Rectangular thin-walled tubes and the screws. The Finite Element Analysis programme ABAQUS is used for modelling the screwed connections. The various modelling procedures for simulating the connection behavior such as tie-constraint model, oriented spring model and solid interaction modelling are compared and are critically reviewed. From the experimental validations the solid-interaction modelling identified to be the most accurate one and are used for predicting the connection behaviors. From the finite element analysis, hysteresis curves and the modes of failure were identified. Parametric studies were done on the connection model to optimize the connection configurations to get desired connection characteristics.

Keywords: buckling, cold formed steel, finite element analysis, screwed connections

Procedia PDF Downloads 187

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 94

Authors: Goudjil kamel, Boukhatem Ghania, Jlailia Djihene

Abstract:

This paper delves into the development of a sophisticated desktop application designed to calculate soil bearing capacity and predict limit pressure. Drawing from an extensive review of existing methodologies, the study meticulously examines various approaches employed in soil bearing capacity calculations, elucidating their theoretical foundations and practical applications. Furthermore, the study explores the burgeoning intersection of artificial intelligence (AI) and geotechnical engineering, underscoring the transformative potential of AI- driven solutions in enhancing predictive accuracy and efficiency.Central to the research is the utilization of cutting-edge machine learning techniques, including Artificial Neural Networks (ANN), XGBoost, and Random Forest, for predictive modeling. Through comprehensive experimentation and rigorous analysis, the efficacy and performance of each method are rigorously evaluated, with XGBoost emerging as the preeminent algorithm, showcasing superior predictive capabilities compared to its counterparts. The study culminates in a nuanced understanding of the intricate dynamics at play in geotechnical analysis, offering valuable insights into optimizing soil bearing capacity calculations and limit pressure predictions. By harnessing the power of advanced computational techniques and AI-driven algorithms, the paper presents a paradigm shift in the realm of geotechnical engineering, promising enhanced precision and reliability in civil engineering projects.

Keywords: limit pressure of soil, xgboost, random forest, bearing capacity

Procedia PDF Downloads 22

Authors: Abdelkader Hachemi & Boualem Remini

Abstract:

Seawater intrusion is a significant challenge faced by coastal aquifers in the Mediterranean basin. This study aims to determine the position of the sharp interface between seawater and freshwater in the aquifer of Wadi Nador, located in the Wilaya of Tipaza, Algeria. A numerical areal sharp interface model using the finite element method is developed to investigate the spatial and temporal behavior of seawater intrusion. The aquifer is assumed to be homogeneous and isotropic. The simulation results are compared with geophysical prospection data obtained through electrical methods in 2011 to validate the model. The simulation results demonstrate a good agreement with the geophysical prospection data, confirming the accuracy of the sharp interface model. The position of the sharp interface in the aquifer is found to be approximately 1617 meters from the sea. Two scenarios are proposed to predict the interface position for the year 2024: one without pumping and the other with pumping. The results indicate a noticeable retreat of the sharp interface position in the first scenario, while a slight decline is observed in the second scenario. The findings of this study provide valuable insights into the dynamics of seawater intrusion in the Wadi Nador aquifer. The predicted changes in the sharp interface position highlight the potential impact of pumping activities on the aquifer's vulnerability to seawater intrusion. This study emphasizes the importance of implementing measures to manage and mitigate seawater intrusion in coastal aquifers. The sharp interface model developed in this research can serve as a valuable tool for assessing and monitoring the vulnerability of aquifers to seawater intrusion.

Keywords: seawater, intrusion, sharp interface, Algeria

Procedia PDF Downloads 74

Authors: Majid Haghshenas, James Wilson, Ranganathan Kumar

Abstract:

In this study, an Algebraic Coupled Level Set-Volume of Fluid (A-CLSVOF) method with capillary pressure treatment is proposed for the modeling of two-phase capillary flows. The Volume of Fluid (VOF) method is utilized to incorporate one-way coupling with the Level Set (LS) function in order to further improve the accuracy of the interface curvature calculation and resulting surface tension force. The capillary pressure is determined and treated independently of the hydrodynamic pressure in the momentum balance in order to maintain consistency between cell centered and interpolated values, resulting in a reduction in parasitic currents. In this method, both VOF and LS functions are transported where the new volume fraction determines the interface seed position used to reinitialize the LS field. The Hamilton-Godunov function is used with a second order (in space and time) discretization scheme to produce a signed distance function. The performance of the current methodology has been tested against some common test cases in order to assess the reduction in non-physical velocities and improvements in the interfacial pressure jump. The cases of a static drop, non-linear Rayleigh-Taylor instability and finally a droplets impact on a liquid pool were simulated to compare the performance of the present method to other well-known methods in the area of parasitic current reduction, interface location evolution and overall agreement with experimental results.

Keywords: two-phase flow, capillary flow, surface tension force, coupled LS with VOF

Procedia PDF Downloads 358

Authors: Kuen Ming Shu, Ren Kai Ho

Abstract:

Ultrasonic horn has the functions of amplifying amplitude and reducing resonant impedance in ultrasonic system. Its primary function is to amplify deformation or velocity during vibration and focus ultrasonic energy on the small area. It is a crucial component in design of ultrasonic vibration system. There are five common design methods for ultrasonic horns: analytical method, equivalent circuit method, equal mechanical impedance, transfer matrix method, finite element method. In addition, the general optimization design process is to change the geometric parameters to improve a single performance. Therefore, in the general optimization design process, we couldn't find the relation of parameter and objective. However, a good optimization design must be able to establish the relationship between input parameters and output parameters so that the designer can choose between parameters according to different performance objectives and obtain the results of the optimization design. In this study, an ultrasonic horn provided by Maxwide Ultrasonic co., Ltd. was used as the contrast of optimized ultrasonic horn. The ANSYS finite element analysis (FEA) software was used to simulate the distribution of the horn amplitudes and the natural frequency value. The results showed that the frequency for the simulation values and actual measurement values were similar, verifying the accuracy of the simulation values. The ANSYS DesignXplorer was used to perform Response Surface optimization, which could shows the relation of parameter and objective. Therefore, this method can be used to substitute the traditional experience method or the trial-and-error method for design to reduce material costs and design cycles.

Keywords: horn, natural frequency, response surface optimization, ultrasonic vibration

Procedia PDF Downloads 116

Authors: Korosh Khorshidi, Mohammad Khodadadi

Abstract:

In this paper, exact close form solution for out of plate free flexural vibration of moderately thick rectangular nanoplates are presented based on nonlocal modified trigonometric shear deformation theory, with assumptions of the Levy's type boundary conditions, for the first time. The aim of this study is to evaluate the effect of small-scale parameters on the frequency parameters of the moderately thick rectangular nano-plates. To describe the effects of small-scale parameters on vibrations of rectangular nanoplates, the Eringen theory is used. The Levy's type boundary conditions are combination of six different boundary conditions; specifically, two opposite edges are simply supported and any of the other two edges can be simply supported, clamped or free. Governing equations of motion and boundary conditions of the plate are derived by using the Hamilton’s principle. The present analytical solution can be obtained with any required accuracy and can be used as benchmark. Numerical results are presented to illustrate the effectiveness of the proposed method compared to other methods reported in the literature. Finally, the effect of boundary conditions, aspect ratios, small scale parameter and thickness ratios on nondimensional natural frequency parameters and frequency ratios are examined and discussed in detail.

Keywords: exact solution, nonlocal modified sinusoidal shear deformation theory, out of plane vibration, moderately thick rectangular plate

Procedia PDF Downloads 387

Authors: Maryam Ziaei, Saeedeh Rafiei, Leila Mivehi, Akbar Khodaparast Haghi

Abstract:

Carbon nanofibers possess properties that are rarely present in any other types of carbon adsorbents, including a small cross-sectional area, combined with a multitude of slit shaped nanopores that are suitable for adsorption of certain types of molecules. Because of their unique properties these materials can be used for the selective adsorption of organic molecules. On the other hand, activated carbon fiber (ACF) has been widely applied as an effective adsorbent for micro-pollutants in recent years. ACF effectively adsorbs and removes a full spectrum of harmful substances. Although there are various methods of fabricating carbon nanofibres, electrospinning is perhaps the most versatile procedure. This technique has been given great attention in current decades because of the nearly simple, comfortable and low cost. Spinning process control and achieve optimal conditions is important in order to effect on its physical properties, absorbency and versatility with different industrial purposes. Modeling and simulation are suitable methods to obtain this approach. In this paper, activated carbon nanofibers were produced during electrospinning of polyacrylonitrile solution. Stabilization, carbonization and activation of electrospun nanofibers in optimized conditions were achieved, and mathematical modelling of electrosinning process done by focusing on governing equations of electrified fluid jet motion (using FeniCS software). Experimental and theoretical results will be compared with each other in order to estimate the accuracy of the model. The simulation can provide the possibility of predicting essential parameters, which affect the electrospinning process.

Keywords: carbon nanofibers, electrospinning, electrospinning modeling, simulation

Procedia PDF Downloads 287

Authors: Jefri Draup, Antoine Ambard, Chi-Toan Nguyen

Abstract:

Zirconium alloys exhibit solid-state phase transformations under thermal loading. These can lead to a significant evolution of the microstructure and associated mechanical properties of materials used in nuclear fuel cladding structures. Therefore, the ability to capture effects of phase transformation on the material constitutive behavior is of interest during conditions of severe transient thermal loading. Whilst typical Avrami, or Johnson-Mehl-Avrami-Kolmogorov (JMAK), type models for phase transformations have been shown to have a good correlation with the behavior of Zircaloy-4 under constant heating rates, the effects of variable and fast heating rates are not fully explored. The present study utilises the results of in-situ high energy synchrotron X-ray diffraction (SXRD) measurements in order to validate the phase transformation models for Zircaloy-4 under fast variable heating rates. These models are used to assess the performance of fuel cladding structures under loss of coolant accident (LOCA) scenarios. The results indicate that simple Avrami type models can provide a reasonable indication of the phase distribution in experimental test specimens under variable fast thermal loading. However, the accuracy of these models deteriorates under the faster heating regimes, i.e., 100Cs⁻¹. The studies highlight areas for improvement of simple Avrami type models, such as the inclusion of temperature rate dependence of the JMAK n-exponent.

Keywords: accident, fuel, modelling, zirconium

Procedia PDF Downloads 142

Authors: Yendo Hu, Xu-Yu Wu, Dylan Oh

Abstract:

GPS-Denied drones open the possibility of indoor applications, including dynamic arial surveillance, inspection, safety enforcement, and discovery. Indoor swarming further enhances these applications in accuracy, robustness, operational time, and coverage. For micro-drones, power management becomes a critical issue, given the battery payload restriction. This paper proposes an application enabling battery replacement solution that extends the micro-drone active phase without human intervention. First, a framework to quantify the effectiveness of a power management solution for a drone fleet is proposed. The operation-to-non-operation ratio, ONR, gives one a quantitative benchmark to measure the effectiveness of a power management solution. Second, a survey was carried out to evaluate the ONR performance for the various solutions. Third, through analysis, this paper proposes a solution tailored to the indoor micro-drone, suitable for swarming applications. The proposed automated battery replacement solution, along with a modified micro-drone architecture, was implemented along with the associated micro-drone. Fourth, the system was tested and compared with the various solutions within the industry. Results show that the proposed solution achieves an ONR value of 31, which is a 1-fold improvement of the best alternative option. The cost analysis shows a manufacturing cost of $25, which makes this approach viable for cost-sensitive markets (e.g., consumer). Further challenges remain in the area of drone design for automated battery replacement, landing pad/drone production, high-precision landing control, and ONR improvements.

Keywords: micro-drone, battery swap, battery replacement, battery recharge, landing pad, power management

Procedia PDF Downloads 119

Authors: Mohsen Farhadloo, Majid Farhadloo

Abstract:

Aspect-level opinion mining that aims at discovering aspects (aspect identification) and their corresponding ratings (sentiment identification) from customer reviews have increasingly attracted attention of researchers and practitioners as it provides valuable insights about products/services from customer's points of view. Instead of addressing aspect identification and sentiment identification in two separate steps, it is possible to simultaneously identify both aspects and sentiments. In recent years many graphical models based on Latent Dirichlet Allocation (LDA) have been proposed to solve both aspect and sentiment identifications in a single step. Although LDA models have been effective tools for the statistical analysis of document collections, they also have shortcomings in addressing some unique characteristics of opinion mining. Our goal in this paper is to address one of the limitations of topic models to date; that is, they fail to directly model the associations among topics. Indeed in many text corpora, it is natural to expect that subsets of the latent topics have higher probabilities. We propose a probabilistic graphical model called focus-LDA, to better capture the associations among topics when applied to aspect-level opinion mining. Our experiments on real-life data sets demonstrate the improved effectiveness of the focus-LDA model in terms of the accuracy of the predictive distributions over held out documents. Furthermore, we demonstrate qualitatively that the focus-LDA topic model provides a natural way of visualizing and exploring unstructured collection of textual data.

Keywords: aspect-level opinion mining, document modeling, Latent Dirichlet Allocation, LDA, sentiment analysis

Procedia PDF Downloads 94

Authors: Azher Jameel, Ghulam Ashraf Harmain

Abstract:

In the recent years, the enriched techniques like the extended finite element method, the element free Galerkin method, and the Coupled finite element-element free Galerkin method have found wide application in modeling different types of discontinuities produced by cracks, contact surfaces, and bi-material interfaces. The extended finite element method faces severe mesh distortion issues while modeling large deformation problems. The element free Galerkin method does not have mesh distortion issues, but it is computationally more demanding than the finite element method. The coupled FE-EFGM proves to be an efficient numerical tool for modeling large deformation problems as it exploits the advantages of both FEM and EFGM. The present paper employs the coupled FE-EFGM to model large elastoplastic deformations in bi-material engineering components. The large deformation occurring in the domain has been modeled by using the total Lagrangian approach. The non-linear elastoplastic behavior of the material has been represented by the Ramberg-Osgood model. The elastic predictor-plastic corrector algorithms are used for the evaluation stresses during large deformation. Finally, several numerical problems are solved by the coupled FE-EFGM to illustrate its applicability, efficiency and accuracy in modeling large elastoplastic deformations in bi-material samples. The results obtained by the proposed technique are compared with the results obtained by XFEM and EFGM. A remarkable agreement was observed between the results obtained by the three techniques.

Keywords: XFEM, EFGM, coupled FE-EFGM, level sets, large deformation

Procedia PDF Downloads 447

Authors: Haneen Alrawashdeh, Naciye Kunt

Abstract:

Intercultural communicative competence or (ICC), is an extension of communicative competence that takes into account the intercultural aspect of learning a foreign language. Accordingly, this study aimed at investigating the intercultural interaction impact on English as a foreign language learners' academic achievement of language as a scholastic subject and their motivation towards learning it. To achieve the aim of the study, a qualitative research approach was implemented by means of semi-structured interviews. Interview sessions were conducted with eight teachers of English as well as ten English language learners who work in the tourism industry in a variety of career paths, such as selling antiques and traditional costumes. An analysis of learners' grades of English subjects from 2014 to 2019 academic years was performed by using the Open Education Management Information System Database in Jordan to support the findings of the study. The results illustrated that due to the fact that they work in the tourism sector, students gain skills and knowledge that assist them in better academic achievement in the subject of English by practicing intercultural communication with different nationalities on a daily basis; intercultural communication enhances students speaking skills, lexicon, and fluency; however, despite that their grades showed increasing, from teachers perspectives, intercultural communicative competence reduces their linguistic accuracy and ability to perform English academic writing in academic contexts such as exams.

Keywords: intercultural communicative competence, Jordan, language learning motivation, language academic achievement

Procedia PDF Downloads 206