Search results for: bullet train

Authors: Qin Long, Li Xiaoge

Abstract:

The Knowledge Graphs have now become a new form of knowledge representation. However, there is no consensus in regard to a plausible and definition of entities and relationships in the domain-specific knowledge graph. Further, in conjunction with several limitations and deficiencies, various domain-specific entities and relationships recognition approaches are far from perfect. Specifically, named entity recognition in Chinese domain is a critical task for the natural language process applications. However, a bottleneck problem with Chinese named entity recognition in new domains is the lack of annotated data. To address this challenge, a domain distant supervised named entity recognition framework is proposed. The framework is divided into two stages: first, the distant supervised corpus is generated based on the entity linking model of graph attention neural network; secondly, the generated corpus is trained as the input of the distant supervised named entity recognition model to train to obtain named entities. The link model is verified in the ccks2019 entity link corpus, and the F1 value is 2% higher than that of the benchmark method. The re-pre-trained BERT language model is added to the benchmark method, and the results show that it is more suitable for distant supervised named entity recognition tasks. Finally, it is applied in the computer field, and the results show that this framework can obtain domain named entities.

Keywords: distant named entity recognition, entity linking, knowledge graph, graph attention neural network

Procedia PDF Downloads 68

Authors: Amah Nnachi Lofty, Oyefeso Olufemi, Ibiam Udu Ama

Abstract:

New and more powerful communications technologies continue to emerge at a rapid pace and their uses in education are widespread and the impact remarkable in the developing societies. This study investigates Mobile Collaboration Learning Technique (MCLT) on learners’ outcome among students in tertiary institutions of developing nations (a case of Nigeria students). It examines the significance of retention achievement scores of students taught using mobile collaboration and conventional method. The sample consisted of 120 students using Stratified random sampling method. Three research questions and hypotheses were formulated, and tested at a 0.05 level of significance. A student achievement test (SAT) was made of 40 items of multiple-choice objective type, developed and validated for data collection by professionals. The SAT was administered to students as pre-test and post-test. The data were analyzed using t-test statistic to test the hypotheses. The result indicated that students taught using MCLT performed significantly better than their counterparts using the conventional method of instruction. Also, there was no significant difference in the post-test performance scores of male and female students taught using MCLT. Based on the findings, the following recommendations was made that: Mobile collaboration system be encouraged in the institutions to boost knowledge sharing among learners, workshop and trainings should be organized to train teachers on the use of this technique and that schools and government should formulate policies and procedures towards responsible use of MCLT.

Keywords: education, communication, learning, mobile collaboration, technology

Procedia PDF Downloads 192

Authors: Chandra Gupt Porwal, Preeti C. Porwal

Abstract:

Transient data reveals much about the machine's condition that steady-state data cannot. New technologies make this information much more available for evaluating the mechanical integrity of a machine train. Recent surveys at various stations indicate that simplicity is preferred over completeness in machine audits throughout the power generation industry. This is most clearly shown by the number of rotating machinery predictive maintenance programs in which only steady-state vibration amplitude is trended while important transient vibration data is not even acquired. Efforts have been made to explain what transient data is, its importance, the types of plots used for its display, and its effective utilization for analysis. In order to demonstrate the value of measuring transient data and its practical application in rotating machinery for resolving complex and persistent issues with turbine generators, the author presents a few case studies that highlight the presence of rotor instabilities due to the shaft moving towards the bearing centre in a 100 MM LMZ unit located in the Northern Capital Region (NCR), heavy misalignment noticed—especially after 2993 rpm—caused by loose coupling bolts, which prevented the machine from being synchronized for more than four months in a 250 MW KWU unit in the Western Region (WR), and heavy preload noticed at Intermediate pressure turbine (IPT) bearing near HP- IP coupling, caused by high points on coupling faces at a 500 MW KWU unit in the Northern region (NR), experienced at Indian power plants.

Keywords: transient data, steady-state-data, intermediate -pressure-turbine, high-points

Procedia PDF Downloads 29

Authors: James Jr. Mashiyane, Risuna Nkolele, Stephanie J. Müller, Gciniwe S. Dlamini, Rebone L. Meraba, Darlington S. Mapiye

Abstract:

When performing language tasks in natural language processing (NLP), the dimensionality of word embeddings is chosen either ad-hoc or is calculated by optimizing the Pairwise Inner Product (PIP) loss. The PIP loss is a metric that measures the dissimilarity between word embeddings, and it is obtained through matrix perturbation theory by utilizing the unitary invariance of word embeddings. Unlike in natural language, in genomics, especially in genome sequence processing, unlike in natural language processing, there is no notion of a “word,” but rather, there are sequence substrings of length k called k-mers. K-mers sizes matter, and they vary depending on the goal of the task at hand. The dimensionality of word embeddings in NLP has been studied using the matrix perturbation theory and the PIP loss. In this paper, the sufficiency and reliability of applying word-embedding algorithms to various genomic sequence datasets are investigated to understand the relationship between the k-mer size and their embedding dimension. This is completed by studying the scaling capability of three embedding algorithms, namely Latent Semantic analysis (LSA), Word2Vec, and Global Vectors (GloVe), with respect to the k-mer size. Utilising the PIP loss as a metric to train embeddings on different datasets, we also show that Word2Vec outperforms LSA and GloVe in accurate computing embeddings as both the k-mer size and vocabulary increase. Finally, the shortcomings of natural language processing embedding algorithms in performing genomic tasks are discussed.

Keywords: word embeddings, k-mer embedding, dimensionality reduction

Procedia PDF Downloads 98

Authors: Nader Khalafian, Mohsen Ghaderi

Abstract:

Field observations have revealed many examples of structures which were damaged due to ground surface deformation caused by the faulting phenomena. In this paper some efforts were made in order to estimate the length and location of the ground surface where large displacements were created due to the reverse faulting. This research has conducted in two steps; (1) in the first step, a 2D explicit finite element model were developed using ABAQUS software. A subroutine for Mohr-Coulomb failure criterion with strain softening model was developed by the authors in order to properly model the stress strain behavior of the soil in the fault rapture zone. The results of the numerical analysis were verified with the results of available centrifuge experiments. Reasonable coincidence was found between the numerical and experimental data. (2) In the second step, the effects of the fault dip angle (δ), depth of soil layer (H), dilation and friction angle of sand (ψ and φ) and the amount of fault offset (d) on the soil surface displacement and fault rupture path were investigated. An artificial neural network-based model (ANN), as a powerful prediction tool, was developed to generate a general model for predicting faulting characteristics. A properly sized database was created to train and test network. It was found that the length and location of the zone of displaced ground surface can be accurately estimated using the proposed model.

Keywords: reverse faulting, surface deformation, numerical, neural network

Procedia PDF Downloads 400

Authors: Rattana Sangchan, Pattaraporn Thampradit

Abstract:

Teaching students to use a variety of reading methods in developing reading is essential for Thai university students. However, there haven’t been a lot of studies concerned about developing reading methods that are used by Thai students in the industrial education field. Therefore, this study was carried out not only to investigate the developing reading methods of Industrial Education students at King Mongkut’s Institute of Technology Ladkrabang, but also to determine if the developing reading strategies differ among the students’ reading abilities and differ gender: male and female. The research instrument used in collecting the data consisted of fourteen statements which include either metacognitive strategies, cognitive strategies or social / affective strategies. Results of this study revealed that students could develop their reading methods in moderate level (mean=3.13). Furthermore, high reading ability students had different levels of using reading methods to develop their reading from those of mid reading ability students. In addition, high reading ability students could use either metacognitive reading methods or cognitive reading methods to develop their reading much better than mid reading ability students. Interestingly, male students could develop their reading methods in great levels while female students could develop their reading methods only in moderate level. Last but not least, male students could use either metacognitive reading methods or cognitive reading methods to develop their reading much better than female students. Thus, the results of this study could indicate that most students need to apply much more reading strategies to develop their reading. At the same time, suggestions on how to motivate and train their students to apply much more appropriate effective reading strategies to better comprehend their reading were also provided.

Keywords: developing reading methods, industrial education, reading abilities, reading method classification

Procedia PDF Downloads 258

Authors: Masica Jordan Alston, Angela N. Bullock, Angela S. Henderson, Stephanie Strianse, Sade Dunn, Joseph Hackett, Alaysia Black Hackett, Marcus Mason

Abstract:

The Energy Model of Cumulative Grief was created in 2018. The Energy Model of Cumulative Grief utilizes historic models of grief stage theories. The innovative model is additionally unique due to its focus on cultural responsiveness. The Energy Model of Cumulative Grief helps to train practitioners who work with clients dealing with grief and loss. This paper assists in introducing the world to this innovative model and exploring how this model positively impacted a convenience sample of 140 practitioners and individuals experiencing grief and loss. Respondents participated in Webinars provided by the National Grief and Loss Center of America (NGLCA). Participants in this cross-sectional research design study completed one of three Grief and Loss Surveys created by the Grief and Loss Centers of America. Data analysis for this study was conducted via SPSS and Survey Hero to examine survey results for respondents. Results indicate that the Energy Model of Cumulative Grief was an effective resource for participants in addressing grief and loss. The majority of participants found the Webinars to be helpful and a conduit to providing them with higher levels of hope. The findings suggest that using The Energy Model of Cumulative Grief is effective in providing culturally responsive grief and loss resources to practitioners and clients. There are far reaching implications with the use of technology to provide hope to those suffering from grief and loss worldwide through The Energy Model of Cumulative Grief.

Keywords: grief, loss, grief energy, grieving brain

Procedia PDF Downloads 56

Authors: Zasha Romero, Joe Paschall

Abstract:

This poster will detail the importance of physical activity for the Visually Impaired students and how to promote inclusion in fitness through way of social gatherings and jogging. Furthermore, it will demonstrate how a Health & Kinesiology University Club cooperated in the journey of visually impaired students from participating in physical activity to completing their first 10K fun run. Purpose: The poster will detail how a university’s Health & Kinesiology Club developed a program to promote participation in fitness activities for visually impaired individuals. Also, it will detail their journey from participation in physical activity to completing a 10K fun run. Methods: In an effort to promote inclusion of all into physical activity, a university’s Health & Kinesiology Club developed a non-profit program to challenge visually impaired students to train and complete a 10 kilometer fun run in a South Texas town. The idea was to promote physical fitness through way of social interaction. In order to maintain runners interested, Club students developed training plans and strategies to be able to navigate in a race that was attended by over 18,000 runners. The idea was to promote interaction and life-long fitness amongst participants. Implications: This strategy was done in collaboration with different non-profit institutions to create awareness and provide opportunities for physical fitness, social interaction and life-long fitness skills associated with the jogging. The workshop provided collaboration amongst different entities and novel ideas to create opportunities for a typically underserved population.

Keywords: inclusion, participation, management, disability, fitness

Procedia PDF Downloads 366

Authors: Hyang Lim, Sungwon Choi

Abstract:

Many previous studies in area of adolescents' depression have used a longitudinal design. The previous studies have found that the developmental trajectory of them is only one. But it needs to be examined whether the trajectory is applied to all adolescents. Some factors in their home and/or school have an effect on adolescents' depression and more likely to be specific groups. The present study was a longitudinal study aimed to identify the trajectories and to explore the predictors of adolescents' depression. The study used Korean Children and Youth Panel Survey (KCYPS) data. In this study, 2,351 second and third-year of middle school and first of high school students' data was analyzed by using semi-parametric group modeling (SGM). There were 5 trajectory groups for adolescents; low depressed stables, low depressed risers, moderately depressed decreases, moderately depressed stables, severe depressed decreases. The predictors of adolescents' depression were parental abuse, parental neglect, annual family income, parental academic background, friendship at school, and teacher-student relationship at school. All predictors had the significant difference across trajectory group profile for adolescents. The findings of the present study recommend to promote the socioeconomic status and to train social skill for the interpersonal relationship at the home and school. And the results suggest that the proper prevention programs for each group in the middle adolescents that target selected factors may be helpful in reducing the level of depression.

Keywords: adolescent, depression, KCYPS, school life, semi-parametric group-based modeling

Procedia PDF Downloads 422

Authors: Saeid Eshghi, Neeraj Saxena, Abdulmajeed Alsultan

Abstract:

Carbon dioxide (CO₂) alongside other gas emissions in the atmosphere cause a greenhouse effect, resulting in an increase of the average temperature of the planet. Transportation vehicles are among the main contributors of CO₂ emission. Stationary vehicles with initiated motors produce more emissions than mobile ones. Intersections with traffic lights that force the vehicles to become stationary for a period of time produce more CO₂ pollution than other parts of the road. This paper focuses on analyzing the CO₂ produced by the traffic flow at Anzac Parade Road - Barker Street intersection in Sydney, Australia, before and after the implementation of Light rail transport (LRT). The data are gathered during the construction phase of the LRT by collecting the number of vehicles on each path of the intersection for 15 minutes during the evening rush hour of 1 week (6-7 pm, July 04-31, 2018) and then multiplied by 4 to calculate the flow of vehicles in 1 hour. For analyzing the data, the microscopic simulation software “VISSIM” has been used. Through the analysis, the traffic flow was processed in three stages: before and after implementation of light rail train, and one during the construction phase. Finally, the traffic results were input into another software called “EnViVer”, to calculate the amount of CO₂ during 1 h. The results showed that after the implementation of the light rail, CO₂ will drop by a minimum of 13%. This finding provides an evidence that light rail is a sustainable mode of transport.

Keywords: carbon dioxide, emission modeling, light rail, microscopic model, traffic flow

Procedia PDF Downloads 112

Authors: Ainur Bulasheva

Abstract:

During the last decade, the dual learning system (DLS) has been actively introduced in various industries in Kazakhstan, including both vocational, post-secondary, and higher education levels. It is a relatively new practice-oriented approach to training qualified personnel in Kazakhstan, officially introduced in 2012. Dual learning was integrated from the German vocational education and training system, combining practical training with part-time work in production and training in an educational institution. The policy of DLS has increasingly focused on decreasing youth unemployment and the shortage of mid-level professionals by providing incentives for employers to involve in this system. By participating directly in the educational process, the enterprise strives to train its future personnel to meet fast-changing market demands. This study examines the effectiveness of DLS from the perspective of employers to understand the motivations of businesses to participate (invest) in this program. The human capital theory of Backer, which predicts that employers will invest in training their workers (in our case, dual students) when they expect that the return on investment will be greater than the cost - acts as a starting point. Further extensionists of this theory will be considered to understand investing intentions of businesses. By comparing perceptions of DLS employers and non-dual practices, this study determines the efficiency of promoted training approach for enterprises in the Kazakhstan agri-food industry.

Keywords: vocational and technical education, dualeducation, human capital theory, argi-food industry

Procedia PDF Downloads 49

Authors: Lei Zhu, Nan Li

Abstract:

Cold stamping has been widely applied in the automotive industry for the mass production of a great range of automotive panels. Predicting the springback to ensure the dimensional accuracy of the cold-stamped components is a critical step. The main approaches for the prediction and compensation of springback in cold stamping include running Finite Element (FE) simulations and conducting experiments, which require forming process expertise and can be time-consuming and expensive for the design of cold stamping tools. Machine learning technologies have been proven and successfully applied in learning complex system behaviours using presentative samples. These technologies exhibit the promising potential to be used as supporting design tools for metal forming technologies. This study, for the first time, presents a novel application of a Convolutional Neural Network (CNN) based surrogate model to predict the springback fields for variable U-shape cold bending geometries. A dataset is created based on the U-shape cold bending geometries and the corresponding FE simulations results. The dataset is then applied to train the CNN surrogate model. The result shows that the surrogate model can achieve near indistinguishable full-field predictions in real-time when compared with the FE simulation results. The application of CNN in efficient springback prediction can be adopted in industrial settings to aid both conceptual and final component designs for designers without having manufacturing knowledge.

Keywords: springback, cold stamping, convolutional neural networks, machine learning

Procedia PDF Downloads 121

Authors: Wasim Ahmad, Bir Singh Chavan, Nazli Ahmad

Abstract:

Objectives: The present investigation is an attempt to find out the efficacy of training the special educators on promoting self-determination among individuals with intellectual disability. Methods: The study equipped the special educators with necessary skills and knowledge to train individuals with the intellectual disability for practicing self-determination. Subjects: Special educators (N=25) were selected for training on self-determination among individuals with intellectual disability. After receiving the training, (N=50) individuals with an intellectual disability were selected and intervened by the trained special educators. Tool: Self-Determination Scale for Adults with Mild Mental Retardation (SDSAMR) developed by Keshwal and Thressiakutty (2010) has been used. It’s a reliable and valid tool used by many researchers. It has 36 items distributed in five domains namely: personal management, community participation, recreation and leisure time, choice making and problem solving. Analysis: The collected data was analyzed using the statistical techniques such as t-test, ANCOVA, and Posthoc Tuckey test. Results: The findings of the study reveal that there is a significant difference at 1% level in the pre and post tests mean scores (t-15.56) of self-determination concepts among the special educators. This indicates that the training enhanced the performance of special educators on the concept of self-determination among individuals with intellectual disability. The study also reveals that the training received on transition planning by the special educators found to be effective because they were able to practice the concept by imparting and training the individuals with intellectual disability to if determined. The results show that there was a significant difference at 1% level in the pre and post tests mean scores (t-16.61) of self-determination among individuals with intellectual disability. Conclusion: To conclude it can be said that the training has a remarkable impact on the performance of the individuals with intellectual disability on self-determination.

Keywords: experiment, individuals with intellectual disability, self-determination, special educators

Procedia PDF Downloads 305

Authors: Derjew Ayele Ejigu, Houde Song, Xiaojing Liu

Abstract:

This work presents the particle swarm optimization trained neural network (PSO-NN) supervisory proportional integral derivative (PID) control method to monitor the pressurized water reactor (PWR) core power for safe operation. The proposed control approach is implemented on the transfer function of the PWR core, which is computed from the state-space model. The PWR core state-space model is designed from the neutronics, thermal-hydraulics, and reactivity models using perturbation around the equilibrium value. The proposed control approach computes the control rod speed to maneuver the core power to track the reference in a closed-loop scheme. The particle swarm optimization (PSO) algorithm is used to train the neural network (NN) and to tune the PID simultaneously. The controller performance is examined using integral absolute error, integral time absolute error, integral square error, and integral time square error functions, and the stability of the system is analyzed by using the Bode diagram. The simulation results indicated that the controller shows satisfactory performance to control and track the load power effectively and smoothly as compared to the PSO-PID control technique. This study will give benefit to design a supervisory controller for nuclear engineering research fields for control application.

Keywords: machine learning, neural network, pressurized water reactor, supervisory controller

Procedia PDF Downloads 127

Authors: Soumya Sajjan

Abstract:

Liver cancer is the most common cancer disease worldwide in men and women, and is one of the few cancers still on the rise. Liver disease is the 4th leading cause of death. According to new NHS (National Health Service) figures, deaths from liver diseases have reached record levels, rising by 25% in less than a decade; heavy drinking, obesity, and hepatitis are believed to be behind the rise. In this study, we focus on Development of Diagnostic Classifier for Ultrasound liver lesion. Ultrasound (US) Sonography is an easy-to-use and widely popular imaging modality because of its ability to visualize many human soft tissues/organs without any harmful effect. This paper will provide an overview of underlying concepts, along with algorithms for processing of liver ultrasound images Naturaly, Ultrasound liver lesion images are having more spackle noise. Developing classifier for ultrasound liver lesion image is a challenging task. We approach fully automatic machine learning system for developing this classifier. First, we segment the liver image by calculating the textural features from co-occurrence matrix and run length method. For classification, Support Vector Machine is used based on the risk bounds of statistical learning theory. The textural features for different features methods are given as input to the SVM individually. Performance analysis train and test datasets carried out separately using SVM Model. Whenever an ultrasonic liver lesion image is given to the SVM classifier system, the features are calculated, classified, as normal and diseased liver lesion. We hope the result will be helpful to the physician to identify the liver cancer in non-invasive method.

Keywords: segmentation, Support Vector Machine, ultrasound liver lesion, co-occurance Matrix

Procedia PDF Downloads 382

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 84

Authors: Michael C. Barbecho, Romeo B. Morcilla

Abstract:

This study focused on the development of a solar powered front wheel drive electric trike for personal use and short distance travel, utilizing solar power and a variable speed transmission to adapt in places where varying road grades and unavailability of plug-in charging stations are of great problems. The actual performance of the vehicle was measured in terms of duration of charging using solar power, distance travel and battery power duration, top speed developed at full power, and load capacity. This project followed the research and development process which involved planning, designing, construction, and testing. Solar charging tests revealed that the vehicle requires 6 to 8 hours sunlight exposure to fully charge the batteries. At full charge, the vehicle can travel 35 km utilizing battery power down to 42%. Vehicle showed top speed of 25 kph at 0 to 3% road grade carrying a maximum load of 122 kg. The maximum climbing grade was 23% with the vehicle carrying a maximum load of 122 kg. Technically the project was feasible and can be a potential model for possible conversion of traditional Philippine made “pedicabs” and gasoline engine powered tricycle into modern electric vehicles. Moreover, it has several technical features and advantages over a commercialized electric vehicle such as the use solar charging system and variable speed power transmission and front drive power train for adaptability in any road gradient.

Keywords: electric vehicle, solar vehicles, front drive, solar, solar power

Procedia PDF Downloads 545

Authors: Huazhen Lin, Ruihua Xu, Zhibin Jiang

Abstract:

In this real-world case, timetabling the LRT network as a whole is rather challenging for the operator: they are supposed to create a timetable to avoid various route conflicts manually while satisfying a given interval and the number of rolling stocks, but the outcome is not satisfying. Therefore, the operator adopts a computerised timetabling tool, the Train Plan Maker (TPM), to cope with this problem. However, with various constraints in the dual-line network, it is still difficult to find an adequate pairing of turnback time, interval and rolling stocks’ number, which requires extra manual intervention. Aiming at current problems, a one-off model for timetabling is presented in this paper to simplify the procedure of timetabling. Before the timetabling procedure starts, this paper presents how the dual-line system with a ring and several branches is turned into a simpler structure. Then, a non-linear programming model is presented in two stages. In the first stage, the model sets a series of constraints aiming to calculate a proper timing for coordinating two lines by adjusting the turnback time at termini. Then, based on the result of the first stage, the model introduces a series of inequality constraints to avoid various route conflicts. With this model, an analysis is conducted to reveal the relation between the ratio of trains in different directions and the possible minimum interval, observing that the more imbalance the ratio is, the less possible to provide frequent service under such strict constraints.

Keywords: light rail transit (LRT), non-linear programming, railway timetabling, timetable coordination

Procedia PDF Downloads 37

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 65

Authors: Evridiki Zachopoulou, Vasilis Grammatikopoulos, Michail Vitoulis, Athanasios Gregoriadis

Abstract:

In the last ten years, the recent economic crisis in Greece has decreased the financial ability and strength of several families when it comes to supporting their children’s studies. As a result, the number of students who are significantly delaying or even dropping out of their university studies is constantly increasing. The students who are at greater risk for academic failure are those who are facing various problems and social disadvantages, like health problems, special needs, family poverty or unemployment, single-parent students, immigrant students, etc. The ‘Umbrella’ project is a volunteer-based initiative to tackle this problem at International Hellenic University. The main purpose of the project is to provide support to disadvantaged students at a socio-emotional, academic, and practical level in order to help them complete their undergraduate studies. More specifically, the ‘Umbrella’ project has the following goals: (a) to develop a consulting-supporting network based on volunteering senior students, called ‘i-mentors’. (b) to train the volunteering i-mentors and create a systematic and consistent support procedure for students at-risk, (c), to develop a service that, parallel to the i-mentor network will be ensuring opportunities for at-risk students to find a job, (d) to support students who are coping with accessibility difficulties, (e) to secure the sustainability of the ‘Umbrella’ project after the completion of the funding of the project. The innovation of the Umbrella project is in its holistic-person-centered approach that will be providing individualized support -via the i-mentors network- to any disadvantaged student that will come ‘under the Umbrella.’

Keywords: peer mentoring, student support, socially disadvantaged students, volunteerism in higher education

Procedia PDF Downloads 209

Authors: Qasim Munye, Juned Islam, Haseeb Qureshi, Syed Jung

Abstract:

Lung nodules are commonly identified in computed tomography (CT) scans by experienced radiologists at a relatively late stage. Early diagnosis can greatly increase survival. We propose using a pix2pix conditional generative adversarial network to generate realistic images simulating early-stage lung nodule growth. We have applied deep images prior to 2341 slices from 895 computed tomography (CT) scans from the Lung Image Database Consortium (LIDC) dataset to generate pseudo-healthy medical images. From these images, 819 were chosen to train a pix2pix network. We observed that for most of the images, the pix2pix network was able to generate images where the nodule increased in size and intensity across epochs. To evaluate the images, 400 generated images were chosen at random and shown to a medical student beside their corresponding original image. Of these 400 generated images, 384 were defined as satisfactory - meaning they resembled a nodule and were visually similar to the corresponding image. We believe that this generated dataset could be used as training data for neural networks to detect lung nodules at an early stage or to improve the accuracy of such networks. This is particularly significant as datasets containing the growth of early-stage nodules are scarce. This project shows that the combination of deep image prior and generative models could potentially open the door to creating larger datasets than currently possible and has the potential to increase the accuracy of medical classification tasks.

Keywords: medical technology, artificial intelligence, radiology, lung cancer

Procedia PDF Downloads 39

Authors: Yash Jain

Abstract:

The US Center for Disease Control has recommended wearing masks to slow the spread of the virus. The research uses a video feed from a camera to conduct real-time classifications of whether or not a human is correctly wearing a mask, incorrectly wearing a mask, or not wearing a mask at all. Utilizing two distinct datasets from the open-source website Kaggle, a mask detection network had been trained. The first dataset that was used to train the model was titled 'Face Mask Detection' on Kaggle, where the dataset was retrieved from and the second dataset was titled 'Face Mask Dataset, which provided the data in a (YOLO Format)' so that the TinyYoloV3 model could be trained. Based on the data from Kaggle, two machine learning models were implemented and trained: a Tiny YoloV3 Real-time model and a two-stage neural network classifier. The two-stage neural network classifier had a first step of identifying distinct faces within the image, and the second step was a classifier to detect the state of the mask on the face and whether it was worn correctly, incorrectly, or no mask at all. The TinyYoloV3 was used for the live feed as well as for a comparison standpoint against the previous two-stage classifier and was trained using the darknet neural network framework. The two-stage classifier attained a mean average precision (MAP) of 80%, while the model trained using TinyYoloV3 real-time detection had a mean average precision (MAP) of 59%. Overall, both models were able to correctly classify stages/scenarios of no mask, mask, and incorrectly worn masks.

Keywords: datasets, classifier, mask-detection, real-time, TinyYoloV3, two-stage neural network classifier

Procedia PDF Downloads 128

Authors: Maria Pavlova

Abstract:

In our days, it is possible to put the camera on different vehicles like quadcopter, train, airplane and etc. The camera also can be the input sensor in many different systems. That means the object recognition like non separate part of monitoring control can be key part of the most intelligent systems. The aim of this paper is to focus of the object recognition process during vehicles movement. During the vehicle’s movement the camera takes pictures from the environment without storage in Data Base. In case the camera detects a special object (for example human or animal), the system saves the picture and sends it to the work station in real time. This functionality will be very useful in emergency or security situations where is necessary to find a specific object. In another application, the camera can be mounted on crossroad where do not have many people and if one or more persons come on the road, the traffic lights became the green and they can cross the road. In this papers is presented the system has solved the aforementioned problems. It is presented architecture of the object recognition system includes the camera, Raspberry platform, GPS system, neural network, software and Data Base. The camera in the system takes the pictures. The object recognition is done in real time using the OpenCV library and Raspberry microcontroller. An additional feature of this library is the ability to display the GPS coordinates of the captured objects position. The results from this processes will be sent to remote station. So, in this case, we can know the location of the specific object. By neural network, we can learn the module to solve the problems using incoming data and to be part in bigger intelligent system. The present paper focuses on the design and integration of the image recognition like a part of smart systems.

Keywords: camera, object recognition, OpenCV, Raspberry

Procedia PDF Downloads 196

Authors: K. S. Kan

Abstract:

The main purpose of this paper is to deepen the current understanding of how a Teaching English as a Second Language (TESL) teacher trainee self is constructed. The present aim of Malaysian TESL teacher education is to train teacher trainees with established English Language Teaching methodologies of the four main language skills (listening, reading, writing and speaking) apart from building them up holistically. Therefore, it is crucial to learn more of the ways on how these teacher trainees construct their professional selves during their undergraduate years. The participants come from a class of 17 Semester 6 TESL students who had undergone a 3-month’s practicum practice during their fifth semester and going for their final 3 month’s practicum period from July 2018 onwards. Findings from a survey, interviews with the participants and lecturers, documentations such as the participants’ practicum record-books would be consolidated with the supervisory notes and comments. The findings suggest that these teacher trainees negotiate their identities and emotions that react with the socio-cultural factors. Periodical reflections on the teacher trainees’ practicum practices influence transformation.The findings will be further aligned to the courses that these teacher trainees have to take in order to equip them as future second language practitioners. It is hoped that the findings will be able to fill the gap from the teacher trainees’ perspectives on identity construction dealing. This study is much more significant now, in view of the new English Language Curriculum for Primary School (widely known as KSSR, its Malay acronym) which had been introduced and implemented in Malaysian primary schools recently. This research will benefit second language practitioners who is in the language education field, as well as, TESL undergraduates, on the knowledge of how teacher trainees respond to and negotiate their professional teaching identities as future second language educators.

Keywords: construction of selves, professional identities, second language, TEST teacher trainees

Procedia PDF Downloads 203

Authors: Yahya Almurtadha, Mukhtar Ghaleb, Ahmed M. Shamsan Saleh

Abstract:

The world witnessed a fierce attack from the Covid-19 virus, which affected public life socially, economically, healthily and psychologically. The world's governments tried to confront the pandemic by imposing a number of precautionary measures such as general closure, curfews and social distancing. Scientists have also made strenuous efforts to develop an effective vaccine to train the immune system to develop antibodies to combat the virus, thus reducing its symptoms and limiting its spread. Artificial intelligence, along with researchers and medical authorities, has accelerated the vaccine development process through big data processing and simulation. On the other hand, one of the most important negatives of the impact of Covid 19 was the state of anxiety and fear due to the blowout of rumors through social media, which prompted governments to try to reassure the public with the available means. This study aims to proposed using Sentiment Analysis (AKA Opinion Mining) and deep learning as efficient artificial intelligence techniques to work on retrieving the tweets of the public from Twitter and then analyze it automatically to extract their opinions, expression and feelings, negatively or positively, about the symptoms they may feel after vaccination. Sentiment analysis is characterized by its ability to access what the public post in social media within a record time and at a lower cost than traditional means such as questionnaires and interviews, not to mention the accuracy of the information as it comes from what the public expresses voluntarily.

Keywords: deep learning, opinion mining, natural language processing, sentiment analysis

Procedia PDF Downloads 144

Authors: Jiyeon Kang, Yeon Jin Jeong, Hoon Heo

Abstract:

Purpose: Bullying in nursing workplace has been a serious problem that increases the turnover of nurses. Few studies have examined the effects of communication training on workplace bullying for nurses, and all used a single-group design and a small sample size. Thus, more rigorous research has been needed to evaluate the effects properly. This research was aimed to identify the effects of the mobile type communication training of responses on bullying behaviors among nurses. Methods: A randomized controlled trial was performed. Subjects were 62 critical care nurses working in university hospitals in Busan, South Korea. We developed a mobile phone application to train nurses to deal with bullying situation. This application includes 6 common bullying situations and appropriate empathetic communication (non-violent communication) samples in the form of webtoons. The experimental group used this application for 4 weeks, and we measured interpersonal relationship, workplace bullying, symptom experience, and intention to leave before, post, and 8 weeks after the intervention from both experimental and control groups. The effect of the intervention was analyzed using repeated measures ANOVA. Results: The mobile type communication training developed in this study was effective for decreasing nurses’ intention to leave workplace (F = 5.11, p = .027). However, it had no effect on interpersonal relationship (F = 2.54, p = .116), workplace bullying (F = 2.99, p = .089) or symptom experience (F = 2.81, p = .099). The beneficial effects on intention to leave lasted at least up to 4 weeks after the training. Conclusion: The mobile type communication training can be utilized as an effective personal coping strategy for workplace bullying among nurses. Further studies on the long-term effects of the communication training are necessary.

Keywords: bullying, communication, mobile applications, nurses, training, workplace

Procedia PDF Downloads 305

Authors: Shariful Islam, Sharun Akter Khushbu, S. M. Shaqib, Shahriar Sultan Ramit

Abstract:

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwear. The suggested method precisely locates these safety items by using the YOLO v7 (You Only Look Once) object detection algorithm. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a [email protected] score of 87.7%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research contributes to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry.

Keywords: deep learning, safety equipment detection, YOLOv7, computer vision, workplace safety

Procedia PDF Downloads 40

Authors: Manoj Sarda, Abhishek Agarwal, Juhi Kaushik, Vatsal Sanjay, Arup Kumar Das

Abstract:

Railways in India remain primary mode of transport having one of the largest networks in the world and catering to billions of transits yearly. Catastrophic economic damage and loss to life is encountered over the past few decades due to fire to locomotives. Study of fire dynamics and fire propagation plays an important role in evacuation planning and reducing losses. Simulation based study of propagation of fire and soot inside an air conditioned coach of Indian locomotive is done in this paper. Finite difference based solver, Fire Dynamic Simulator (FDS) version 6 has been used for analysis. A single air conditioned 3 tier coupe closed to ambient surroundings by glass windows having occupancy for 8 people is the basic unit of the domain. A system of three such coupes combined is taken to be fundamental unit for the entire study to resemble effect to an entire coach. Analysis of flame and soot contours and concentrations is done corresponding to variations in heat release rate per unit volume (HRRPUA) of fire source, variations in conditioned air velocity being circulated inside coupes by vents and an alternate fire initiation and propagation mechanism via ducts. Quantitative results of fractional area in top and front view of the three coupes under fire and smoke are obtained using MATLAB (IMT). Present simulations and its findings will be useful for organizations like Commission of Railway Safety and others in designing and implementing safety and evacuation measures.

Keywords: air conditioned coaches, fire propagation, flame contour, soot flow, train fire

Procedia PDF Downloads 255

Authors: Zohreh Soleimani, Sally Salome Shahzad, Stamatis Zoras

Abstract:

As a result of current energy and environmental issues, the human body is known as one of the promising candidate for converting wasted heat to electricity (Seebeck effect). Thermoelectric generator (TEG) is one of the most prevalent means of harvesting body heat and converting that to eco-friendly electrical power. However, the uneven distribution of the body heat and its curvature geometry restrict harvesting adequate amount of energy. To perfectly transform the heat radiated by the body into power, the most direct solution is conforming the thermoelectric generators (TEG) with the arbitrary surface of the body and increase the temperature difference across the thermoelectric legs. Due to this, a computational survey through COMSOL Multiphysics is presented in this paper with the main focus on the impact of integrating a flexible wearable TEG with a corrugated shaped heat sink on the module power output. To eliminate external parameters (temperature, air flow, humidity), the simulations are conducted within indoor thermal level and when the wearer is stationary. The full thermoelectric characterization of the proposed TEG fabricated by a wavy shape heat sink has been computed leading to a maximum power output of 25µW/cm2 at a temperature gradient nearly 13°C. It is noteworthy that for the flexibility of the proposed TEG and heat sink, the applicability and efficiency of the module stay high even on the curved surfaces of the body. As a consequence, the results demonstrate the superiority of such a TEG to the most state of the art counterparts fabricated with no heat sink and offer a new train of thought for the development of self-sustained and unobtrusive wearable power suppliers which generate energy from low grade dissipated heat from the body.

Keywords: device simulation, flexible thermoelectric module, heat sink, human body heat

Procedia PDF Downloads 132

Authors: Parisa Mansour

Abstract:

Cystic fibrosis (CF) is one of the most common autosomal recessive diseases among whites. It mostly affects the lungs, causing infections and inflammation that account for 90% of deaths in CF patients. Because of this high variability in clinical presentation and organ involvement, investigating treatment responses and evaluating lung changes over time is critical to preventing CF progression. High-resolution computed tomography (HRCT) greatly facilitates the assessment of lung disease progression in CF patients. Recently, artificial intelligence was used to analyze chest CT scans of CF patients. In this paper, we propose a convolutional neural network (CNN) approach to classify CF lung patterns in HRCT images. The proposed network consists of two convolutional layers with 3 × 3 kernels and maximally connected in each layer, followed by two dense layers with 1024 and 10 neurons, respectively. The softmax layer prepares a predicted output probability distribution between classes. This layer has three exits corresponding to the categories of normal (healthy), bronchitis and inflammation. To train and evaluate the network, we constructed a patch-based dataset extracted from more than 1100 lung HRCT slices obtained from 45 CF patients. Comparative evaluation showed the effectiveness of the proposed CNN compared to its close peers. Classification accuracy, average sensitivity and specificity of 93.64%, 93.47% and 96.61% were achieved, indicating the potential of CNNs in analyzing lung CF patterns and monitoring lung health. In addition, the visual features extracted by our proposed method can be useful for automatic measurement and finally evaluation of the severity of CF patterns in lung HRCT images.

Keywords: HRCT, CF, cystic fibrosis, chest CT, artificial intelligence

Procedia PDF Downloads 37