Search results for: language learning model

Authors: Ming-Jen Huang, Chun-Fang Huang, Chiching Wei

Abstract:

With the recent advance of the deep neural network, we observe new applications of NLP (natural language processing) and CV (computer vision) powered by deep neural networks for processing business documents. However, creating a real-world document processing system needs to integrate several NLP and CV tasks, rather than treating them separately. There is a need to have a unified approach for processing documents containing textual and graphical elements with rich formats, diverse layout arrangement, and distinct semantics. In this paper, a framework that fulfills this unified approach is presented. The framework includes a representation model definition for holding the information generated by various tasks and specifications defining the coordination between these tasks. The framework is a blueprint for building a system that can process documents with rich formats, styles, and multiple types of elements. The flexible and lightweight design of the framework can help build a system for diverse business scenarios, such as contract monitoring and reviewing.

Keywords: document processing, framework, formal definition, machine learning

Procedia PDF Downloads 200

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Due to increasing cost pressure in global markets, artificial intelligence is becoming a technology that is decisive for competition. Predictive quality enables machinery and plant manufacturers to ensure product quality by using data-driven forecasts via machine learning models as a decision-making basis for test results. The use of cross-process Bosch production data along the value chain of hydraulic valves is a promising approach to classifying the quality characteristics of workpieces.

Keywords: predictive quality, hydraulics, machine learning, classification, supervised learning

Procedia PDF Downloads 218

Authors: Hong Lu, Xiong Xiao

Abstract:

Shaft parts are widely used in machinery industry, however, bending deformation often occurred when this kind of parts is being heat treated. This parts needs to be straightened to meet the requirement of straightness. As for the pressure straightening process, a good straightening stroke algorithm is related to the precision and efficiency of straightening process. In this paper, the relationship between straightening load and deflection during the straightening process is analyzed, and the mathematical model of the straightening process has been established. By the mathematical model, the iterative method is used to solve the straightening stroke. Compared to the traditional straightening stroke algorithm, straightening stroke calculated by this method is much more precise; because it can adapt to the change of material performance parameters. Considering that the straightening method is widely used in the mass production of the shaft parts, knowledge base is used to store the data of the straightening process, and a straightening stroke algorithm based on empirical data is set up. In this paper, the straightening process control model which combine the straightening stroke method based on iteration and straightening stroke algorithm based on empirical data has been set up. Finally, an experiment has been designed to verify the straightening process control model.

Keywords: straightness, straightening stroke, deflection, shaft parts

Procedia PDF Downloads 316

Authors: Atbin Mahabbati, Jason Beringer, Matthias Leopold

Abstract:

To address the global challenges of climate and environmental changes, there is a need for quantifying and reducing uncertainties in environmental data, including observations of carbon, water, and energy. Global eddy covariance flux tower networks (FLUXNET), and their regional counterparts (i.e., OzFlux, AmeriFlux, China Flux, etc.) were established in the late 1990s and early 2000s to address the demand. Despite the capability of eddy covariance in validating process modelling analyses, field surveys and remote sensing assessments, there are some serious concerns regarding the challenges associated with the technique, e.g. data gaps and uncertainties. To address these concerns, this research has developed an ensemble model to fill the data gaps of CO₂ flux to avoid the limitations of using a single algorithm, and therefore, provide less error and decline the uncertainties associated with the gap-filling process. In this study, the data of five towers in the OzFlux Network (Alice Springs Mulga, Calperum, Gingin, Howard Springs and Tumbarumba) during 2013 were used to develop an ensemble machine learning model, using five feedforward neural networks (FFNN) with different structures combined with an eXtreme Gradient Boosting (XGB) algorithm. The former methods, FFNN, provided the primary estimations in the first layer, while the later, XGB, used the outputs of the first layer as its input to provide the final estimations of CO₂ flux. The introduced model showed slight superiority over each single FFNN and the XGB, while each of these two methods was used individually, overall RMSE: 2.64, 2.91, and 3.54 g C m⁻² yr⁻¹ respectively (3.54 provided by the best FFNN). The most significant improvement happened to the estimation of the extreme diurnal values (during midday and sunrise), as well as nocturnal estimations, which is generally considered as one of the most challenging parts of CO₂ flux gap-filling. The towers, as well as seasonality, showed different levels of sensitivity to improvements provided by the ensemble model. For instance, Tumbarumba showed more sensitivity compared to Calperum, where the differences between the Ensemble model on the one hand and the FFNNs and XGB, on the other hand, were the least of all 5 sites. Besides, the performance difference between the ensemble model and its components individually were more significant during the warm season (Jan, Feb, Mar, Oct, Nov, and Dec) compared to the cold season (Apr, May, Jun, Jul, Aug, and Sep) due to the higher amount of photosynthesis of plants, which led to a larger range of CO₂ exchange. In conclusion, the introduced ensemble model slightly improved the accuracy of CO₂ flux gap-filling and robustness of the model. Therefore, using ensemble machine learning models is potentially capable of improving data estimation and regression outcome when it seems to be no more room for improvement while using a single algorithm.

Keywords: carbon flux, Eddy covariance, extreme gradient boosting, gap-filling comparison, hybrid model, OzFlux network

Procedia PDF Downloads 122

Authors: Gaya Tridinanti

Abstract:

Enhanching English vocabulary in early childhood is the main problem often faced by teachers. Thus, the purpose of this study was to determine the enhancement of children’s English vocabulary acquisition by using digital storytelling. This type of research was an action research. It consisted of a series of four activities done in repeated cycles: planning, implementation, observation, and reflection. The subject of the study consisted of 30 students of B group (5-6 years old) attending Happy Kids Kindergarten Palembang, Indonesia. This research was conducted in three cycles. The methods used for data collection were observation and documentation. Descriptive qualitative and quantitative methods were also used to analyse the data. The research showed that the digital storytelling learning activities could enhance the children’s English vocabulary acquisition. It is based on the data in which the enhancement in pre-cycle was 37% and 51% in Cycle I. In Cycle II it was 71% and in Cycle III it was 89.3%. The results showed an enhancement of about 14% from the pre-cycle to Cycle I, 20% from Cycle I to Cycle II, and enhancement of about 18.3% from Cycle II to Cycle III. The conclusion of this study suggests that digital storytelling learning method could enhance the English vocabulary acquisition of B group children at the Happy Kids Kindergarten Palembang. Therefore, digital storytelling can be considered as an alternative to improve English language learning in the classroom.

Keywords: acquisition, enhancing, digital storytelling, English vocabulary

Procedia PDF Downloads 247

Authors: Maria Tagarelli De Monte

Abstract:

In 2021, the passage of the law recognizing Italian Sign Language (LIS) as the language of the Italian deaf minority was the input for including this visual-gestural language in the curricula of interpreters and translators choosing the academic setting for their training. Yet, a gap remains concerning LIS education of teachers and communication assistants as referring figures for people who are deaf or hard of hearing in mainstream education. As well documented in the related scientific literature, deaf children often experience severe difficulties with the languages spoken in the country where they grow up, manifesting in all levels of literacy competence. In the research introduced here, the experience of deaf students (and their teachers) attending schools is explored in areas that are characterized by strong native bilingualism, such as Friuli-Venezia Giulia (FVG), facing Italian Northeast borders. This region is peculiar as the native population may be bilingual Italian and Friulian (50% of the local population), German, and/or Slovenian. The research involved all schools of all levels in Friuli to understand the relationship between the language skills expressed by teachers and those shown by deaf learners with a background in sign language. In addition to collecting specific information on the degree of preparation of teachers in deaf-related matters and LIS, the research has allowed to highlight the role, often poorly considered, covered by the communication assistants who work alongside deaf students. On several occasions, teachers and assistants were unanimous in affirming the importance of mutual collaboration and adequate consideration of the educational-rehabilitative history of the deaf child and her family. The research was based on a mixed method of structured questionnaires and semi-structured interviews with the referring teachers. As a result, a varied and complex framework emerged, showing an asymmetry in preparing personnel dedicated to the deaf learner. Considering how Italian education has long invested in creating an inclusive and accessible school system (i.e. with the "Ten Theses for Democratic Language Education"), a constructive analysis will complete the discussion in an attempt to understand how linguistic (and modal) differences can become levers of inclusion.

Keywords: FVG, LIS, linguistic needs, deafness, teacher education, bilingual bimodal children, communication assistants, inclusion model

Procedia PDF Downloads 27

Authors: Animish Jain

Abstract:

This study deals with using Multiplicative Weight Update within artificial intelligence and machine learning to create models that can diagnose skin cancer using microscopic images of cancer samples. In this study, the multiplicative weight update method is used to take the predictions of multiple models to try and acquire more accurate results. Logistic Regression, Convolutional Neural Network (CNN), and Support Vector Machine Classifier (SVMC) models are employed within the Multiplicative Weight Update system. These models are trained on pictures of skin cancer from the ISIC-Archive, to look for patterns to label unseen scans as either benign or malignant. These models are utilized in a multiplicative weight update algorithm which takes into account the precision and accuracy of each model through each successive guess to apply weights to their guess. These guesses and weights are then analyzed together to try and obtain the correct predictions. The research hypothesis for this study stated that there would be a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The SVMC model had an accuracy of 77.88%. The CNN model had an accuracy of 85.30%. The Logistic Regression model had an accuracy of 79.09%. Using Multiplicative Weight Update, the algorithm received an accuracy of 72.27%. The final conclusion that was drawn was that there was a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The conclusion was made that using a CNN model would be the best option for this problem rather than a Multiplicative Weight Update system. This is due to the possibility that Multiplicative Weight Update is not effective in a binary setting where there are only two possible classifications. In a categorical setting with multiple classes and groupings, a Multiplicative Weight Update system might become more proficient as it takes into account the strengths of multiple different models to classify images into multiple categories rather than only two categories, as shown in this study. This experimentation and computer science project can help to create better algorithms and models for the future of artificial intelligence in the medical imaging field.

Keywords: artificial intelligence, machine learning, multiplicative weight update, skin cancer

Procedia PDF Downloads 64

Authors: Aditya Karade, Sharada Falane, Dhananjay Deshmukh, Vijaykumar Mantri

Abstract:

Brain tumors pose a significant challenge in healthcare due to their complex nature and impact on patient outcomes. The application of deep learning (DL) algorithms in medical imaging have shown promise in accurate and efficient brain tumour detection. This paper explores the performance of various pre-trained DL models ResNet50, Xception, InceptionV3, EfficientNetB0, DenseNet121, NASNetMobile, VGG19, VGG16, and MobileNet on a brain tumour dataset sourced from Figshare. The dataset consists of MRI scans categorizing different types of brain tumours, including meningioma, pituitary, glioma, and no tumour. The study involves a comprehensive evaluation of these models’ accuracy and effectiveness in classifying brain tumour images. Data preprocessing, augmentation, and finetuning techniques are employed to optimize model performance. Among the evaluated deep learning models for brain tumour detection, ResNet50 emerges as the top performer with an accuracy of 98.86%. Following closely is Xception, exhibiting a strong accuracy of 97.33%. These models showcase robust capabilities in accurately classifying brain tumour images. On the other end of the spectrum, VGG16 trails with the lowest accuracy at 89.02%.

Keywords: brain tumour, MRI image, detecting and classifying tumour, pre-trained models, transfer learning, image segmentation, data augmentation

Procedia PDF Downloads 57

Authors: Misagh Faezipour

Abstract:

This paper explores the effects of screen time on children from a systems engineering perspective. We reviewed literature from several related works on the effects of screen time on children to explore all factors and interrelationships that would impact children that are subjected to using long screen times. Factors such as kids' age, parent attitudes, parent screen time influence, amount of time kids spend with technology, psychosocial and physical health outcomes, reduced mental imagery, problem-solving and adaptive thinking skills, obesity, unhealthy diet, depressive symptoms, health problems, disruption in sleep behavior, decrease in physical activities, problematic relationship with mothers, language, social, emotional delays, are examples of some factors that could be either a cause or effect of screen time. A systems engineering perspective is used to explore all the factors and factor relationships that were discovered through literature. A causal model is used to illustrate a graphical representation of these factors and their relationships. Through the causal model, the factors with the highest impacts can be realized. Future work would be to develop a system dynamics model to view the dynamic behavior of the relationships and observe the impact of changes in different factors in the model. The different changes on the input of the model, such as a healthier diet or obesity rate, would depict the effect of the screen time in the model and portray the effect on the children’s health and other factors that are important, which also works as a decision support tool.

Keywords: children, causal model, screen time, systems engineering, system dynamics

Procedia PDF Downloads 128

Authors: Maria Ahmad, Michael Page, Danë Goodsman

Abstract:

‘Educational’ debriefing – a construct distinct from clinical debriefing – is used following simulated scenarios and is central to learning and development in fields ranging from aviation to emergency medicine. However, little research into educational debriefing in prehospital medicine exists. This qualitative study explored the facilitation and effects of prehospital educational debriefing and identified obstacles to debriefing, using the London’s Air Ambulance Pre-Hospital Care Course (PHCC) as a model. Method: Ethnographic observations of moulages and debriefs were conducted over two consecutive days of the PHCC in October 2019. Detailed contemporaneous field notes were made and analysed thematically. Subsequently, seven one-to-one, semi-structured interviews were conducted with four PHCC debrief facilitators and three course participants to explore their experiences of prehospital educational debriefing. Interview data were manually transcribed and analysed thematically. Results: Four overarching themes were identified: the approach to the facilitation of debriefs, effects of debriefing, facilitator development, and obstacles to debriefing. The unpredictable debriefing environment was seen as both hindering and paradoxically benefitting educational debriefing. Despite using varied debriefing structures, facilitators emphasised similar key debriefing components, including exploring participants’ reasoning and sharing experiences to improve learning and prevent future errors. Debriefing was associated with three principal effects: releasing emotion; learning and improving, particularly participant compound learning as they progressed through scenarios; and the application of learning to clinical practice. Facilitator training and feedback were central to facilitator learning and development. Several obstacles to debriefing were identified, including mismatch of participant and facilitator agendas, performance pressure, and time. Interestingly, when used appropriately in the educational environment, these obstacles may paradoxically enhance learning. Conclusions: Educational debriefing in prehospital medicine is complex. It requires the establishment of a safe learning environment, an understanding of participant agendas, and facilitator experience to maximise participant learning. Aspects unique to prehospital educational debriefing were identified, notably the unpredictable debriefing environment, interdisciplinary working, and the paradoxical benefit of educational obstacles for learning. This research also highlights aspects of educational debriefing not extensively detailed in the literature, such as compound participant learning, display of ‘professional honesty’ by facilitators, and facilitator learning, which require further exploration. Future research should also explore educational debriefing in other prehospital services.

Keywords: debriefing, prehospital medicine, prehospital medical education, pre-hospital care course

Procedia PDF Downloads 202

Authors: Oladapo Tolulope Ibitoye

Abstract:

Neural networks have become prominent and widely engaged in algorithmic-based machine learning networks. They are perfect in solving day-to-day issues to a certain extent. Neural networks are computing systems with several interconnected nodes. One of the numerous areas of application of neural networks is object detection. This is a prominent area due to the coronavirus disease pandemic and the post-pandemic phases. Wearing a face mask in public slows the spread of the virus, according to experts’ submission. This calls for the development of a reliable and effective model for detecting face masks on people's faces during compliance checks. The existing neural network models for facemask detection are characterized by their black-box nature and large dataset requirement. The highlighted challenges have compromised the performance of the existing models. The proposed model utilized Faster R-CNN Model on Inception V3 backbone to reduce system complexity and dataset requirement. The model was trained and validated with very few datasets and evaluation results shows an overall accuracy of 96% regardless of skin tone.

Keywords: convolutional neural network, face detection, face mask, masked faces

Procedia PDF Downloads 53

Authors: Mumtaz Begum Mustafa, Siti Salwah Salim, Feizal Dani Rahman

Abstract:

Recently, Automatic Speech Recognition (ASR) systems were used to assist children in language acquisition as it has the ability to detect human speech signal. Despite the benefits offered by the ASR system, there is a lack of ASR systems for Malay-speaking children. One of the contributing factors for this is the lack of continuous speech database for the target users. Though cross-lingual adaptation is a common solution for developing ASR systems for under-resourced language, it is not viable for children as there are very limited speech databases as a source model. In this research, we propose a two-stage adaptation for the development of ASR system for Malay-speaking children using a very limited database. The two stage adaptation comprises the cross-lingual adaptation (first stage) and cross-age adaptation. For the first stage, a well-known speech database that is phonetically rich and balanced, is adapted to the medium-sized Malay adults using supervised MLLR. The second stage adaptation uses the speech acoustic model generated from the first adaptation, and the target database is a small-sized database of the target users. We have measured the performance of the proposed technique using word error rate, and then compare them with the conventional benchmark adaptation. The two stage adaptation proposed in this research has better recognition accuracy as compared to the benchmark adaptation in recognizing children’s speech.

Keywords: Automatic Speech Recognition System, children speech, adaptation, Malay

Procedia PDF Downloads 378

Authors: Aofan Liu, Qianqian Tan, Burra Venkata Durga Kumar

Abstract:

Data security is of the utmost importance in the healthcare area, as sensitive patient information is constantly sent around and analyzed by many different parties. The use of federated learning, which enables data to be evaluated locally on devices rather than being transferred to a central server, has emerged as a potential solution for protecting the privacy of user information. To protect against data breaches and unauthorized access, federated learning alone might not be adequate. In this context, the application of blockchain technology could provide the system extra protection. This study proposes a distributed federated learning system that is built on blockchain technology in order to enhance security in healthcare. This makes it possible for a wide variety of healthcare providers to work together on data analysis without raising concerns about the confidentiality of the data. The technical aspects of the system, including as the design and implementation of distributed learning algorithms, consensus mechanisms, and smart contracts, are also investigated as part of this process. The technique that was offered is a workable alternative that addresses concerns about the safety of healthcare while also fostering collaborative research and the interchange of data.

Keywords: data privacy, distributed system, federated learning, machine learning

Procedia PDF Downloads 104

Authors: Güzi̇n Ti̇rkeş, Özge Teki̇n, Kerem Kurtuluş, Y. Yekta Yurtseven, Murat Baran

Abstract:

A scanning electron microscope (SEM) is a type of electron microscope mainly used in nanoscience and nanotechnology areas. Automatic image recognition and classification are among the general areas of application concerning SEM. In line with these usages, the present paper proposes a deep learning algorithm that classifies SEM images into nine categories by means of an online application to simplify the process. The NFFA-EUROPE - 100% SEM data set, containing approximately 21,000 images, was used to train and test the algorithm at 80% and 20%, respectively. Validation was carried out using a separate data set obtained from the Middle East Technical University (METU) in Turkey. To increase the accuracy in the results, the Inception ResNet-V2 model was used in view of the Fine-Tuning approach. By using a confusion matrix, it was observed that the coated-surface category has a negative effect on the accuracy of the results since it contains other categories in the data set, thereby confusing the model when detecting category-specific patterns. For this reason, the coated-surface category was removed from the train data set, hence increasing accuracy by up to 96.5%.

Keywords: convolutional neural networks, deep learning, image classification, scanning electron microscope

Procedia PDF Downloads 107

Authors: Firas A. Al Laban, Mohamed Chabi, Sammani Danwawu Abdullahi

Abstract:

There are a real needs to integrate types of Open Educational Resources (OER) with an intelligent system to extract information and knowledge in the semantic searching level. Those needs raised because most of current learning standard adopted web based learning and the e-learning systems does not always serve all educational goals. Semantic Web systems provide educators, students, and researchers with intelligent queries based on a semantic knowledge management learning system. An ontology-based learning system is an advanced system, where ontology plays the core of the semantic web in a smart learning environment. The objective of this paper is to discuss the potentials of ontologies and mapping different kinds of ontologies; heterogeneous or homogenous to manage and control different types of Open Educational Resources. The important contribution of this research is to approach a methodology uses logical rules and conceptual relations to map between ontologies of different educational resources. We expect from this methodology to establish for an intelligent educational system supporting student tutoring, self and lifelong learning system.

Keywords: knowledge management systems, ontologies, semantic web, open educational resources

Procedia PDF Downloads 488

Authors: Eman Ayman, Gehan Nagy

Abstract:

The learning environment has four main parameters that affect its efficiency which they are: pedagogy, user, technology, and space. According to Morrone, enhancing these parameters to be adaptable for future developments is essential. The educational organization will be in need of developing its learning spaces. Flexibility of design an immersive technology could be used as tools for this development. when flexible design concepts are used, learning spaces that can accommodate a variety of teaching and learning activities are created. To accommodate the various needs and interests of students, these learning spaces are easily reconfigurable and customizable. The immersive learning opportunities offered by technologies like virtual reality, augmented reality, and interactive displays, on the other hand, transcend beyond the confines of the traditional classroom. These technological advancements could improve learning. This thesis highlights the problem of the lack of innovative, flexible learning spaces in educational institutions. It aims to develop guidelines for enhancing the learning environment by the integration of flexible design and immersive technology. This research uses a mixed method approach, both qualitative and quantitative: the qualitative section is related to the literature review theories and case studies analysis. On the other hand, the quantitative section will be identified by the results of the applied studies of the effectiveness of redesigning a learning space from its traditional current state to a flexible technological contemporary space that will be adaptable to many changes and educational needs. Research findings determine the importance of flexibility in learning spaces' internal design as it enhances the space optimization and capability to accommodate the changes and record the significant contribution of immersive technology that assists the process of designing. It will be summarized by the questionnaire results and comparative analysis, which will be the last step of finalizing the guidelines.

Keywords: flexibility, learning space, immersive technology, learning environment, interior design

Procedia PDF Downloads 72

Authors: Mohammad Shokoohi-Yekta, Hamid Mirebrahim

Abstract:

A body of research has been devoted to investigating the preferences of computer programmers. These researches used various questionnaires to find out what programming language is most popular among programmers. The problem with such research is that the programmers are usually familiar with only a few languages; therefore, disregarding a number of other languages which might have characteristics that match their preferences more closely. To overcome such a problem, we decided to investigate the preferences of programmers in regards to the characteristics of languages, which help us to discover the languages that include the most characteristics preferred by the users. We conducted a user study to measure the preferences of programmers on different characteristics of programming languages and then tried to compare existing languages in the areas of application, Web and system programming. Overall, the results of our study indicated that the Ruby programming language has the highest preference score in the two areas of application and Web, and C++ has the highest score in the system area. The results of our study can also help programming language designers know the characteristics they should consider when developing new programming languages in order to attract more programmers.

Keywords: object orientation, programming language design, programmers' preferences, characteristic

Procedia PDF Downloads 486

Authors: Chin-Wen Chien

Abstract:

Protocols are tools that help teachers inquire into the teaching and professional learning during the professional dialogue. This study focused on the integration of protocols into elementary school English teachers’ professional dialogue and discussed the influence of protocols on teachers’ teaching and learning. Based on the analysis of documents, observations, and interviews, this study concluded that with the introduction of protocols to elementary school English teachers, three major protocols were used during their professional dialogue. These protocols led the teachers to gain professional learning in content knowledge and pedagogical content knowledge. However, the facilitators’ lack of experience in using protocols led to interruptions during the professional dialogue. Suggestions for effective protocol-based professional dialogue are provided.

Keywords: protocols, professional learning, professional dialogue, classroom practice

Procedia PDF Downloads 371

Authors: Habtamu Ayenew Asegie

Abstract:

Wealth, as opposed to income or consumption, implies a more stable and permanent status. Due to natural and human-made difficulties, households' economies will be diminished, and their well-being will fall into trouble. Hence, governments and humanitarian agencies offer considerable resources for poverty and malnutrition reduction efforts. One key factor in the effectiveness of such efforts is the accuracy with which low-income or poor populations can be identified. As a result, this study aims to predict a household’s wealth status using ensemble Machine learning (ML) algorithms. In this study, design science research methodology (DSRM) is employed, and four ML algorithms, Random Forest (RF), Adaptive Boosting (AdaBoost), Light Gradient Boosted Machine (LightGBM), and Extreme Gradient Boosting (XGBoost), have been used to train models. The Ethiopian Demographic and Health Survey (EDHS) dataset is accessed for this purpose from the Central Statistical Agency (CSA)'s database. Various data pre-processing techniques were employed, and the model training has been conducted using the scikit learn Python library functions. Model evaluation is executed using various metrics like Accuracy, Precision, Recall, F1-score, area under curve-the receiver operating characteristics (AUC-ROC), and subjective evaluations of domain experts. An optimal subset of hyper-parameters for the algorithms was selected through the grid search function for the best prediction. The RF model has performed better than the rest of the algorithms by achieving an accuracy of 96.06% and is better suited as a solution model for our purpose. Following RF, LightGBM, XGBoost, and AdaBoost algorithms have an accuracy of 91.53%, 88.44%, and 58.55%, respectively. The findings suggest that some of the features like ‘Age of household head’, ‘Total children ever born’ in a family, ‘Main roof material’ of their house, ‘Region’ they lived in, whether a household uses ‘Electricity’ or not, and ‘Type of toilet facility’ of a household are determinant factors to be a focal point for economic policymakers. The determinant risk factors, extracted rules, and designed artifact achieved 82.28% of the domain expert’s evaluation. Overall, the study shows ML techniques are effective in predicting the wealth status of households.

Keywords: ensemble machine learning, households wealth status, predictive model, wealth status prediction

Procedia PDF Downloads 26

Authors: Rajan Ghimire

Abstract:

One of the diseases caused by the coronavirus shook the whole world. This situation challenged the education system across the world and compelled educators to shift to an online mode of teaching. Many academic institutions that were persistent to keep their traditional pedagogical approach were also forced to change their teaching methods. This study aims to assess science education students' experiences and perceptions of this global issue, especially on the science teaching and learning process. The study is based on qualitative research and through in-depth interviews with respondents and data is analyzed. Online distance teaching and learning processes meet the requirements of students who cannot or prefer not to participate in conventional classroom settings. But there are some challenges for the students and teachers in the science teaching learning process. This study recommends some points to all stakeholders.

Keywords: electronic devices, internet, online and distance learning, science education, educational policy

Procedia PDF Downloads 35

Authors: Kuo-Chun Chien, Chia-Hui Chang, Ren-Der Sun

Abstract:

Legal Judgment Prediction (LJP) is a subtask for legal AI. Its main purpose is to use the facts of a case to predict the judgment result. In Taiwan's criminal procedure, when prosecutors complete the investigation of the case, they will decide whether to prosecute the suspect and which article of criminal law should be used based on the facts and evidence of the case. In this study, we collected 305,240 indictments from the public inquiry system of the procuratorate of the Ministry of Justice, which included 169 charges and 317 articles from 21 laws. We take the crime facts in the indictments as the main input to jointly learn the prediction model for law source, article, and charge simultaneously based on the pre-trained Bert model. For single article cases where the frequency of the charge and article are greater than 50, the prediction performance of law sources, articles, and charges reach 97.66, 92.22, and 60.52 macro-f1, respectively. To understand the big performance gap between articles and charges, we used a bipartite graph to visualize the relationship between the articles and charges, and found that the reason for the poor prediction performance was actually due to the wording precision. Some charges use the simplest words, while others may include the perpetrator or the result to make the charges more specific. For example, Article 284 of the Criminal Law may be indicted as “negligent injury”, "negligent death”, "business injury", "driving business injury", or "non-driving business injury". As another example, Article 10 of the Drug Hazard Control Regulations can be charged as “Drug Control Regulations” or “Drug Hazard Control Regulations”. In order to solve the above problems and more accurately predict the article and charge, we plan to include the article content or charge names in the input, and use the sentence-pair classification method for question-answer problems in the BERT model to improve the performance. We will also consider a sequence-to-sequence approach to charge prediction.

Keywords: legal judgment prediction, deep learning, natural language processing, BERT, data visualization

Procedia PDF Downloads 108

Authors: Argaw T. Gurmu, Muhammad N. Mahmood

Abstract:

The objective of this research is to identify the architecture and construction management students’ learning challenges of the building measurement. This research used the survey data obtained collected from the students who completed the building measurement unit. NVivo qualitative data analysis software was used to identify relevant themes. The analysis of the qualitative data revealed the major learning difficulties such as inadequacy of practice questions for the examination, inability to work as a team, lack of detailed understanding of the prerequisite units, insufficiency of the time allocated for tutorials and incompatibility of lecture and tutorial schedules. The output of this research can be used as a basis for improving the teaching and learning activities in construction measurement units.

Keywords: building measurement, construction management, learning challenges, evaluate survey

Procedia PDF Downloads 127

Authors: Abhijeet Ostawal, Parmjit Lall

Abstract:

The run times for a large strategic model that we were managing had become too long leading to delays in project delivery, increased costs and loss in productivity. Software developers are continuously working towards developing more efficient tools by changing their algorithms and processes. The issue faced by our team was how do you apply the latest technologies on validated existing models which are based on much older versions of software that do not have the latest software capabilities. The multi-model transport model that we had could only be run in sequential assignment order. Recent upgrades to the software now allowed the assignment to be run in parallel, a concept called parallelization. Parallelization is a Python script working only within the latest version of the software. A full model transfer to the latest version was not possible due to time, budget and the potential changes in trip assignment. This article is to show the method to adapt and update the Python script in such a way that it can be used in older software versions by calling the latest version and then recalling the old version for assignment model without affecting the results. Through a process of trial-and-error run time savings of up to 30-40% have been achieved. Assignment results were maintained within the older version and through this learning process we’ve applied this methodology to other even older versions of the software resulting in huge time savings, more productivity and efficiency for both client and consultant.

Keywords: model run time, demand model, parallelisation, python scripting

Procedia PDF Downloads 102

Authors: F. S. Irwansyah, I. Farida, Y. Maulana

Abstract:

Studying chemistry requires the ability to understand three levels of understanding in the form of macroscopic, submicroscopic and symbolic, but the lack of emphasis on the submicroscopic level leads to the understanding of chemical concepts becoming incomplete, due to the limitations of the tools capable of providing visualization of submicroscopic concepts. The purpose of this study describes the stages of making augmented reality learning media on the concept of molecular geometry and analyze the feasibility test result of augmented reality learning media on the concept of molecular geometry. This research uses Research and Development (R & D) method which produces a product of AR learning media on molecular geometry concept and test the effectiveness of the product. Research stages include concept analysis and learning indicators, design development, validation, feasibility, and limited testing. The stages of validation and limited trial are aimed to get feedback in the form of assessment, suggestion and improvement on learning aspect, material substance aspect, visual communication aspect and software engineering aspects and media feasibility in terms of media creation purpose to be used in learning. The results of the overall feasibility test obtained r-calculation 0,7-0,9 with the interpretation of high feasibility value, whereas the result of limited trial got the percentage of eligibility with the average value equal to 70,83-92,5%. This percentage indicates that AR's learning media product on the concept of molecular geometry, deserves to be used as a learning resource.

Keywords: android, augmented reality, chemical learning, geometry

Procedia PDF Downloads 198

Authors: Jacqueline Mary Jepson

Abstract:

This article provides a case study centred on the development of 13 video episodes which have been created to enhance student engagement with a post graduate online course in Project Management. The student group was unique as their online course needed to provide for asynchronistic learning and an adult learning pedagogy. In addition, students had come from a wide range professional backgrounds, with some having no Project Management experience, while others had 20 years or more. Students had to gain an understanding of an advanced body of knowledge and the course needed to achieve the academic requirements to qualify individuals to apply their learning in a range of contexts for professional practice and scholarship. To achieve this, a 13 episode case study was developed along with supportive learning materials based on the relocation of a zoo. This unique project provided a learning environment where the project could evolve over each video episode demonstrating the application of Project Management methodology which was then tied into the learning outcomes for the course and the assessment tasks. Discussion forums provided a way for students to converse and demonstrate their own understanding of content and how Project Management methodology can be applied.

Keywords: project management, adult learning, video case study, asynchronistic education

Procedia PDF Downloads 325

Authors: Marie Alaghband, Niloofar Yousefi, Ivan Garibay

Abstract:

Facial expressions are important parts of both gesture and sign language recognition systems. Despite the recent advances in both fields, annotated facial expression datasets in the context of sign language are still scarce resources. In this manuscript, we introduce an annotated sequenced facial expression dataset in the context of sign language, comprising over 3000 facial images extracted from the daily news and weather forecast of the public tv-station PHOENIX. Unlike the majority of currently existing facial expression datasets, FePh provides sequenced semi-blurry facial images with different head poses, orientations, and movements. In addition, in the majority of images, identities are mouthing the words, which makes the data more challenging. To annotate this dataset we consider primary, secondary, and tertiary dyads of seven basic emotions of "sad", "surprise", "fear", "angry", "neutral", "disgust", and "happy". We also considered the "None" class if the image’s facial expression could not be described by any of the aforementioned emotions. Although we provide FePh as a facial expression dataset of signers in sign language, it has a wider application in gesture recognition and Human Computer Interaction (HCI) systems.

Keywords: annotated facial expression dataset, gesture recognition, sequenced facial expression dataset, sign language recognition

Procedia PDF Downloads 143

Authors: Tracey Bone

Abstract:

Deaf inmates, whose first or preferred language is a Signed Language, experience barriers to accessing the necessary two-way communication with correctional staff, and the educational and social programs that will enhance their eligibility for conditional release from the federal prison system in Canada. The development of visual content to enhance the knowledge and skill development of correctional staff is a contemporary strategy intended to significantly improve the correctional experience for deaf inmates. This presentation reports on the development of two distinct training videos created to enhance staff’s understanding of the needs of deaf inmates; one a two-part simulation of an interaction with a deaf inmate, the second an interview with a deaf academic. Part one of video one demonstrates the challenges and misunderstandings inherent in communicating across languages without a qualified sign language interpreter; the second part demonstrates the ease of communication when communication needs are met. Video two incorporates the experiences of a deaf academic to provide the cultural grounding necessary to educate staff in the unique experiences associated with being a visual language user. Lack of staff understanding or awareness of deaf culture and language must not be acceptable reasons for the inadequate treatment of deaf visual language users in federal prisons. This paper demonstrates a contemporary approach to meeting the human rights and needs of this unique and often ignored inmate subpopulation. The deaf community supports this visual approach to enhancing staff understanding of the unique needs of this population. A study of its effectiveness is currently underway.

Keywords: accommodations, American Sign Language (ASL), deaf inmates, sensory deprivation

Procedia PDF Downloads 137

Authors: S. J. Yune, S. Y. Lee, S. J. Im, B. S. Kam, S. Y. Baek

Abstract:

This study explored whether academic emotion, major satisfaction, and learning flow are associated with academic achievement in medical school. We know that emotion and affective factors are important factors in students' learning and performance. Emotion has taken the stage in much of contemporary educational psychology literature, no longer relegated to secondary status behind traditionally studied cognitive constructs. Medical school students (n=164) completed academic emotion, major satisfaction, and learning flow online survey. Academic performance was operationalized as students' average grade on two semester exams. For data analysis, correlation analysis, multiple regression analysis, hierarchical multiple regression analyses and ANOVA were conducted. The results largely confirmed the hypothesized relations among academic emotion, major satisfaction, learning flow and academic achievement. Positive academic emotion had a correlation with academic achievement (β=.191). Positive emotion had 8.5% explanatory power for academic achievement. Especially, sense of accomplishment had a significant impact on learning performance (β=.265). On the other hand, negative emotion, major satisfaction, and learning flow did not affect academic performance. Also, there were differences in sense of great (F=5.446, p=.001) and interest (F=2.78, p=.043) among positive emotion, boredom (F=3.55, p=.016), anger (F=4.346, p=.006), and petulance (F=3.779, p=.012) among negative emotion by grade. This study suggested that medical students' positive emotion was an important contributor to their academic achievement. At the same time, it is important to consider that some negative emotions can act to increase one’s motivation. Of particular importance is the notion that instructors can and should create learning environment that foster positive emotion for students. In doing so, instructors improve their chances of positively impacting students’ achievement emotions, as well as their subsequent motivation, learning, and performance. This result had an implication for medical educators striving to understand the personal emotional factors that influence learning and performance in medical training.

Keywords: academic achievement, learning emotion, learning flow, major satisfaction

Procedia PDF Downloads 252

Authors: Greg Turner, Bin Lu, Cheer-Sun Yang

Abstract:

As computing technology advances, smartphone applications can assist in student learning in a pervasive way. For example, the idea of using a mobile apps for the PA Common Trees, Pests, Pathogens, in the field as a reference tool allows middle school students to learn about trees and associated pests/pathogens without bringing a textbook. In the past, some researches study the mobile software Mobile Application Software Development Life Cycle (MADLC) including traditional models such as the waterfall model, or more recent Agile Methods. Others study the issues related to the software development process. Very little research is on the development of three heterogenous mobile systems simultaneously in a small university where the availability of developers is an issue. In this paper, we propose to use a hybride model of Waterfall Model and the Agile Model, known as the Relay Race Methodology (RRM) in practice, to reflect the concept of racing and relaying for scheduling. Based on the development project, we observe that the modeling of the transition between any two phases is manifested naturally. Thus, we claim that the RRM model can provide a de fecto rather than a de jure basis for the core concept in the MADLC. In this paper, the background of the project is introduced first. Then, the challenges are pointed out followed by our solutions. Finally, the experiences learned and the future work are presented.

Keywords: agile methods, mobile apps, software process model, waterfall model

Procedia PDF Downloads 395

Authors: Bikis Muhammed, Sehra Sedigh Sarvestani, Ali R. Hurson, Lasanthi Gamage

Abstract:

Vehicular traffic events have overly complex spatial correlations and temporal interdependencies and are also influenced by environmental events such as weather conditions. To capture these spatial and temporal interdependencies and make more realistic vehicular traffic predictions, graph neural networks (GNN) based traffic prediction models have been extensively utilized due to their capability of capturing non-Euclidean spatial correlation very effectively. However, most of the already existing GNN-based traffic prediction models have some limitations during learning complex and dynamic spatial and temporal patterns due to the following missing factors. First, most GNN-based traffic prediction models have used static distance or sometimes haversine distance mechanisms between spatially separated traffic observations to estimate spatial correlation. Secondly, most GNN-based traffic prediction models have not incorporated environmental events that have a major impact on the normal traffic states. Finally, most of the GNN-based models did not use an attention mechanism to focus on only important traffic observations. The objective of this paper is to study and make real-time vehicular traffic predictions while incorporating the effect of weather conditions. To fill the previously mentioned gaps, our prediction model uses a real-time driving distance between sensors to build a distance matrix or spatial adjacency matrix and capture spatial correlation. In addition, our prediction model considers the effect of six types of weather conditions and has an attention mechanism in both spatial and temporal data aggregation. Our prediction model efficiently captures the spatial and temporal correlation between traffic events, and it relies on the graph attention network (GAT) and Bidirectional bidirectional long short-term memory (Bi-LSTM) plus attention layers and is called GAT-BILSTMA.

Keywords: deep learning, real time prediction, GAT, Bi-LSTM, attention

Procedia PDF Downloads 58