Search results for: language learning

Authors: Praveen Boinee, Alessandro De Angelis, Gian Luca Foresti

Abstract:

Leo Breimans Random Forests (RF) is a recent development in tree based classifiers and quickly proven to be one of the most important algorithms in the machine learning literature. It has shown robust and improved results of classifications on standard data sets. Ensemble learning algorithms such as AdaBoost and Bagging have been in active research and shown improvements in classification results for several benchmarking data sets with mainly decision trees as their base classifiers. In this paper we experiment to apply these Meta learning techniques to the random forests. We experiment the working of the ensembles of random forests on the standard data sets available in UCI data sets. We compare the original random forest algorithm with their ensemble counterparts and discuss the results.

Keywords: Random Forests [RF], ensembles, UCI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2671

Authors: I. Oloyede

Abstract:

The study investigates the accuracy and loss of deep learning algorithms with the set of coronavirus (COVID-19) images dataset by comparing Bayesian convolutional neural network and traditional convolutional neural network in low dimensional dataset. 50 sets of X-ray images out of which 25 were COVID-19 and the remaining 20 were normal, twenty images were set as training while five were set as validation that were used to ascertained the accuracy of the model. The study found out that Bayesian convolution neural network outperformed conventional neural network at low dimensional dataset that could have exhibited under fitting. The study therefore recommended Bayesian Convolutional neural network (BCNN) for android apps in computer vision for image detection.

Keywords: BCNN, CNN, Images, COVID-19, Deep Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 831

Authors: A. K. Razilan, A. B. Amzari, B. Ap-azli, A. R. Safawi

Abstract:

Explosion in information management and information system technology has brought dramatic changes in learning and library system environments. The use of academic digital libraries does witness the spectacular impact on academic societies’ way of performing their study in Malaysia, a country with a multi-racial people. This paper highlights a research on examining the socio-demographic differences on the preference and use of academic digital libraries as compared to physical libraries at higher learning institutions. Findings indicate that preference towards digital libraries differed between ethnicity, gender and university. However none of the socio-demographic factors is statistically significant in terms of the use of digital libraries.

Keywords: Socio-demographic, academic digital library, preference, use.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1461

Authors: Reiko Yamamoto

Abstract:

This paper reports on a joint research project in which a researcher in applied linguistics and elementary school teachers in Japan explored new ways to realize emotional synchrony in a classroom in childhood education. The primary purpose of this project was to develop a cross-curriculum of the first language (L1) and second language (L2) based on the concept of plurilingualism. This concept is common in Europe, and can-do statements are used in forming the standard of linguistic proficiency in any language; these are attributed to the action-oriented approach in the Common European Framework of Reference for Languages (CEFR). CEFR has a basic tenet of language education: improving communicative competence. Can-do statements are classified into five categories based on the tenet: reading, writing, listening, speaking/ interaction, and speaking/ speech. The first approach of this research was to specify the linguistic proficiency of the children, who are still developing their L1. Elementary school teachers brainstormed and specified the linguistic proficiency of the children as the competency needed to synchronize with others – teachers or peers – physically and mentally. The teachers formed original can-do statements in language proficiency on the basis of the idea that emotional synchrony leads to understanding others in communication. The research objectives are to determine the effect of language education based on the newly developed curriculum and can-do statements. The participants of the experiment were 72 third-graders in Uji Elementary School, Japan. For the experiment, 17 items were developed from the can-do statements formed by the teachers and divided into the same five categories as those of CEFR. A can-do checklist consisting of the items was created. The experiment consisted of three steps: first, the students evaluated themselves using the can-do checklist at the beginning of the school year. Second, one year of instruction was given to the students in Japanese and English classes (six periods a week). Third, the students evaluated themselves using the same can-do checklist at the end of the school year. The results of statistical analysis showed an enhancement of linguistic proficiency of the students. The average results of the post-check exceeded that of the pre-check in 12 out of the 17 items. Moreover, significant differences were shown in four items, three of which belonged to the same category: speaking/ interaction. It is concluded that children can get to understand others’ minds through physical and emotional synchrony. In particular, emotional synchrony is what teachers should aim at in childhood education.

Keywords: Elementary school education, emotional synchrony, language proficiency, sympathy with others.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 602

Authors: Danielle Shackley, Yetunde Folajimi

Abstract:

As more people turn to the internet seeking health related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores of text, ranging from positive, neutral and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing, tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process, and substituting the Naive Bayes for a deep learning neural network model.

Keywords: Sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 422

Authors: Li Yu, Chenlu Jiao, Hongrun Xin, Yan Wang, Kaiyang Wang

Abstract:

In order to study the impact of various factors on the housing price, we propose to build different prediction models based on deep learning to determine the existing data of the real estate in order to more accurately predict the housing price or its changing trend in the future. Considering that the factors which affect the housing price vary widely, the proposed prediction models include two categories. The first one is based on multiple characteristic factors of the real estate. We built Convolution Neural Network (CNN) prediction model and Long Short-Term Memory (LSTM) neural network prediction model based on deep learning, and logical regression model was implemented to make a comparison between these three models. Another prediction model is time series model. Based on deep learning, we proposed an LSTM-1 model purely regard to time series, then implementing and comparing the LSTM model and the Auto-Regressive and Moving Average (ARMA) model. In this paper, comprehensive study of the second-hand housing price in Beijing has been conducted from three aspects: crawling and analyzing, housing price predicting, and the result comparing. Ultimately the best model program was produced, which is of great significance to evaluation and prediction of the housing price in the real estate industry.

Keywords: Deep learning, convolutional neural network, LSTM, housing prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4948

Authors: F. Havas Beigi, M. Vafaee Yeganeh, E. Mohammadi

Abstract:

Evaluation and survey of curriculum quality as one of the most important components of universities system is necessary for different levels in higher education. The main purpose of this study was to survey of the curriculum quality of Actuarial science field. Case: University of SHahid Beheshti and Higher education institute of Eco insurance (according to viewpoint of students, alumni, employers and faculty members). Descriptive statistics (mean, tables, percentage, and frequency distribution) and inferential statistics (CHI SQUARE) were used to analyze the data. Six criteria considered for the Quality of curriculum: objectives, content, teaching and learning methods, space and facilities, Time, assessment of learning. Content, teaching and learning methods, space and facilities, assessment of learning criteria were relatively desirable level, objectives and time criterions were desirable level. The quality of curriculum of Actuarial Science field was relatively desirable level.

Keywords: Quality, curriculum, Actuarial science, higher education

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1843

Authors: Sayed Hadi Sadeghi

Abstract:

This research study examines the current state of support services for e-network practice in an Australian and an American university. It identifies information that will be of assistance to Australian and American universities to improve their existing online programs. The study investigated the two universities using a quantitative methodological approach. Participants were students, lecturers and admins of universities engaged with online courses and learning management systems. The support services for e-network practice variables, namely academic support services, administrative support and technical support, were investigated for e-practice. Evaluations of e-network support service and its sub factors were above average and excellent in both countries, although the American admins and lecturers tended to evaluate this factor higher than others did. Support practice was evaluated higher by all participants of an American university than by Australians. One explanation for the results may be that most suppliers of the Australian university e-learning system were from eastern Asian cultural backgrounds with a western networking support perspective about e-learning.

Keywords: Support services, e-network practice, Australian universities, United States universities.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 965

Authors: Kaustubh Chakradeo, Michael Delves, Sofya Titarenko

Abstract:

Malaria is a serious disease which affects hundreds of millions of people around the world, each year. If not treated in time, it can be fatal. Despite recent developments in malaria diagnostics, the microscopy method to detect malaria remains the most common. Unfortunately, the accuracy of microscopic diagnostics is dependent on the skill of the microscopist and limits the throughput of malaria diagnosis. With the development of Artificial Intelligence tools and Deep Learning techniques in particular, it is possible to lower the cost, while achieving an overall higher accuracy. In this paper, we present a VGG-based model and compare it with previously developed models for identifying infected cells. Our model surpasses most previously developed models in a range of the accuracy metrics. The model has an advantage of being constructed from a relatively small number of layers. This reduces the computer resources and computational time. Moreover, we test our model on two types of datasets and argue that the currently developed deep-learning-based methods cannot efficiently distinguish between infected and contaminated cells. A more precise study of suspicious regions is required.

Keywords: Malaria, deep learning, DL, convolution neural network, CNN, thin blood smears.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 623

Authors: Vesna Vulić

Abstract:

Croatia has made large steps forward in the development of higher education over the past 10 years. Purposes and objectives of the tertiary education system are focused on the personal development of young people so that they obtain competences for employment on a flexible labour market. The most frequent tensions between the tertiary institutions and employers are complaints that the current tertiary education system still supplies students with an abundance of theoretical knowledge and not enough practical skills. Polytechnics and schools of professional higher education should deliver professional education and training that will satisfy the needs of their local communities. The 21^st century sets demand on undergraduates as well as their lecturers to strive for the highest standards. The skills students acquire during their studies should serve the needs of their future professional careers. In this context, teaching English for Specific Purposes (ESP) presents an enormous challenge for teachers. They have to cope with teaching the language in classes with a large number of students, limitations of time, inadequate equipment and teaching material; most frequently, this leads to focusing on specialist vocabulary neglecting the development of skills and competences required for future employment. Globalization has transformed the labour market and set new standards a perspective employee should meet. When knowledge of languages is considered, new generic skills and competences are required. Not only skillful written and oral communication is needed, but also information, media, and technology literacy, learning skills which include critical and creative thinking, collaborating and communicating, as well as social skills. The aim of this paper is to evaluate the needs of two groups of ESP first year Undergraduate Professional Administrative Study students taking ESP as a mandatory course: 47 first-year Undergraduate Professional Administrative Study students, 21 first-year employed part-time Undergraduate Professional Administrative Study students and 30 graduates with a degree in Undergraduate Professional Administrative Study with various amounts of work experience. The survey adopted a quantitative approach with the aim to determine the differences between the groups in their perception of the four language skills and different areas of law, as well as getting the insight into students' satisfaction with the current course and their motivation for studying ESP. Their perceptions will be compared to the results of the questionnaire conducted among sector professionals in order to examine how they perceive the same elements of the ESP course content and to what extent it fits into their working environment. The results of the survey indicated that there is a strong correlation between acquiring work experience and the level of importance given to particular areas of law studied in an ESP course which is in line with our initial hypothesis. In conclusion, the results of the survey should help lecturers in re-evaluating and updating their ESP course syllabi.

Keywords: English for Specific Purposes, ESP, language skills, motivation, needs analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1095

Authors: David C. White

Abstract:

This paper describes the architectural design considerations for building a new class of application, a Personal Knowledge Integrator and a particular example a Knowledge Theatre. It then supports this description by describing a scenario of a child acquiring knowledge and how this process could be augmented by the proposed architecture and design of a Knowledge Theatre. David Merrill-s first “principles of instruction" are kept in focus to provide a background to view the learning potential.

Keywords: Knowledge, personal, open data, visualization, learning, teaching

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1316

Authors: Yanwen Li, Shuguo Xie

Abstract:

In electromagnetic imaging, because of the diffraction limited system, the pixel values could change slowly near the edge of the image targets and they also change with the location in the same target. Using traditional digital image segmentation methods to segment electromagnetic gradient images could result in lots of errors because of this change in pixel values. To address this issue, this paper proposes a novel image segmentation and extraction algorithm based on Mean-Shift and dictionary learning. Firstly, the preliminary segmentation results from adaptive bandwidth Mean-Shift algorithm are expanded, merged and extracted. Then the overlap rate of the extracted image block is detected before determining a segmentation region with a single complete target. Last, the gradient edge of the extracted targets is recovered and reconstructed by using a dictionary-learning algorithm, while the final segmentation results are obtained which are very close to the gradient target in the original image. Both the experimental results and the simulated results show that the segmentation results are very accurate. The Dice coefficients are improved by 70% to 80% compared with the Mean-Shift only method.

Keywords: Gradient image, segmentation and extract, mean-shift algorithm, dictionary learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 948

Authors: Amiel Satvedi, Richard Pyne

Abstract:

Injuries in professional sports occur on a regular basis. Some may be minor while others can cause huge impact on a player’s career and earning potential. In soccer, there is a high risk of players picking up injuries during game time. This research work seeks to help soccer players reduce the risk of getting injured by predicting the likelihood of injury while playing in the near future and then providing recommendations for intervention. The injury prediction tool will use a soccer player’s number of minutes played on the field, number of appearances, distance covered and performance data for the current and previous seasons as variables to conduct statistical analysis and provide injury predictive results using a machine learning linear regression model.

Keywords: Injury predictor, soccer injury prevention, machine learning in soccer, big data in soccer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1691

Authors: Nazatul Aini Abd Majid, Faridah Yunus, Haslina Arshad, Mohammad Farhan Mohammad Johari

Abstract:

Mobile technology, augmented reality, and game-based learning are some of the key learning technologies that can be fully optimized to promote pre-literacy skills. The problem is how to design an effective pre-literacy kit that utilizes some of the learning technologies. This paper presents a framework based on mobile augmented reality for the development of pre-literacy kit. This pre-literacy kit incorporates three main components which are contents, design, and tools. A prototype of a mobile app based on the three main components was developed for promoting pre-literacy. The results show that the children and teachers gave positive feedbacks after using the mobile app for the pre-literacy.

Keywords: Framework, mobile technology, augmented reality, pre-literacy skills.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1893

Authors: Omnia Elkommos

Abstract:

Language is communication on several discourse levels. The target of teaching a language and the literature of a foreign language is to communicate a message. Reading, appreciating, analysing, and interpreting poetry as a sophisticated rhetorical expression of human thoughts, emotions, and philosophical messages is more feasible through the use of linguistic pragmatic tools from a communicative discourse perspective. The poet's intention, speech act, illocutionary act, and perlocutionary goal can be better understood when communicative situational context as well as linguistic discourse structure theories are employed. The use of linguistic theories in the teaching of poetry is, therefore, intrinsic to students' comprehension, interpretation, and appreciation of poetry of the different ages. It is the purpose of this study to show how both teachers as well as students can apply these linguistic theories and tools to dramatic poetic texts for an engaging, enlightening, and effective interpretation and appreciation of the language. Theories drawn from areas of pragmatics, discourse analysis, embedded discourse level, communicative situational context, and other linguistic approaches were applied to selected poetry texts from the different centuries. Further, in a simple statistical count of the number of poems with dialogic dramatic discourse with embedded two or three levels of discourse in different anthologies outweighs the number of descriptive poems with a one level of discourse, between the poet and the reader. Poetry is thus discourse on one, two, or three levels. It is, therefore, recommended that teachers and students in the area of ESL/EFL use the linguistics theories for a better understanding of poetry as communicative discourse. The practice of applying these linguistic theories in classrooms and in research will allow them to perceive the language and its linguistic, social, and cultural aspect. Texts will become live illocutionary acts with a perlocutionary acts goal rather than mere literary texts in anthologies.

Keywords: Coda, commissives, communicative situation, context of culture, context of reference, context of utterance, dialogue, directives, discourse analysis, dramatic discourse interaction, duologue, embedded discourse levels, language for communication, linguistic structures, literary texts, poetry, pragmatic theories, reader response, speech acts (macro/micro), stylistics, teaching literature, TEFL, terms of address, turn-taking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1690

Authors: Kathaleeya Chanda, Panupong Chanplin, Suppara Charoenpoom

Abstract:

This purposes of the development of creative instruction model through digital media are to: 1) enable learners to learn from instruction media application; 2) help learners implementing instruction media correctly and appropriately; and 3) facilitate learners to apply technology for searching information and practicing skills to implement technology creatively. The sample group consists of 130 cases of secondary students studying in Bo Kluea School, Bo Kluea Nuea Sub-district, Bo Kluea District, Nan Province. The probability sampling was selected through the simple random sampling and the statistics used in this research are percentage, mean, standard deviation and one group pretest – posttest design. The findings are summarized as follows: The congruence index of instruction media for occupation and technology subjects is appropriate. By comparing between learning achievements before implementing the instruction media and learning achievements after implementing the instruction media, it is found that the posttest achievements are higher than the pretest achievements with statistical significance at the level of .05. For the learning achievements from instruction media implementation, pretest mean is 16.24 while posttest mean is 26.28. Besides, pretest and posttest results are compared and differences of mean are tested, the test results show that the posttest achievements are higher than the pretest achievements with statistical significance at the level of .05. This can be interpreted that the learners achieve better learning progress.

Keywords: Teaching learning model, digital media, creative instruction model, facilitate learners.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 665

Authors: Nilubon Kurubanjerdjit, Nattakarn Iam-On, Ka-Lok Ng

Abstract:

MicroRNAs are small non-coding RNA found in many different species. They play crucial roles in cancer such as biological processes of apoptosis and proliferation. The identification of microRNA-target genes can be an essential first step towards to reveal the role of microRNA in various cancer types. In this paper, we predict miRNA-target genes for lung cancer by integrating prediction scores from miRanda and PITA algorithms used as a feature vector of miRNA-target interaction. Then, machine-learning algorithms were implemented for making a final prediction. The approach developed in this study should be of value for future studies into understanding the role of miRNAs in molecular mechanisms enabling lung cancer formation.

Keywords: MicroRNA, miRNAs, lung cancer, machine learning, Naïve Bayes, SVM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2365

Authors: Taylan Kabbani, Ekrem Duman

Abstract:

Deep Reinforcement Learning (DRL) algorithms can scale to previously intractable problems. The automation of profit generation in the stock market is possible using DRL, by combining  the financial assets price ”prediction” step and the ”allocation” step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with its environment to make optimal decisions through trial and error. This work represents a DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem as a Partially observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. We then solved the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm and achieved a 2.68 Sharpe ratio on the test dataset. From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of DRL in financial markets over other types of machine learning and proves its credibility and advantages of strategic decision-making.

Keywords: Autonomous agent, deep reinforcement learning, MDP, sentiment analysis, stock market, technical indicators, twin delayed deep deterministic policy gradient.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 484

Authors: Zhen Cheng, Xinyu Dai, Shujian Huang, Jiajun Chen

Abstract:

Recently, explanatory natural language inference has attracted much attention for the interpretability of logic relationship prediction, which is also known as explanation generation for Natural Language Inference (NLI). Existing explanation generators based on discriminative Encoder-Decoder architecture have achieved noticeable results. However, we find that these discriminative generators usually generate explanations with correct evidence but incorrect logic semantic. It is due to that logic information is implicitly encoded in the premise-hypothesis pairs and difficult to model. Actually, logic information identically exists between premise-hypothesis pair and explanation. And it is easy to extract logic information that is explicitly contained in the target explanation. Hence we assume that there exists a latent space of logic information while generating explanations. Specifically, we propose a generative model called Variational Explanation Generator (VariationalEG) with a latent variable to model this space. Training with the guide of explicit logic information in target explanations, latent variable in VariationalEG could capture the implicit logic information in premise-hypothesis pairs effectively. Additionally, to tackle the problem of posterior collapse while training VariaztionalEG, we propose a simple yet effective approach called Logic Supervision on the latent variable to force it to encode logic information. Experiments on explanation generation benchmark—explanation-Stanford Natural Language Inference (e-SNLI) demonstrate that the proposed VariationalEG achieves significant improvement compared to previous studies and yields a state-of-the-art result. Furthermore, we perform the analysis of generated explanations to demonstrate the effect of the latent variable.

Keywords: Natural Language Inference, explanation generation, variational auto-encoder, generative model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 653

Authors: Raquel P. F. Guiné, Daniela V. T. A. Costa, Paula M. R. Correia, Moisés Castro, Luis T. Guerra, Cristina A. Costa

Abstract:

The aim of this work was to characterize a potential target group of people interested in participating into a training program in organic farming in the context of mobile-learning. The information sought addressed in particular, but not exclusively, possible contents, formats and forms of evaluation that will contribute to define the course objectives and curriculum, as well as to ensure that the course meets the needs of the learners and their preferences. The sample was selected among different European countries. The questionnaires were delivered electronically for answering on-line and in the end 135 consented valid questionnaires were obtained. The results allowed characterizing the target group and identifying their training needs and preferences towards m-learning formats, giving valuable tools to design the training offer.

Keywords: Mobile-learning, organic farming, rural development, survey.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2050

Authors: Sanja Seljan, Ivan Dunđer

Abstract:

The paper presents combined automatic speech recognition (ASR) of English and machine translation (MT) for English and Croatian and Croatian-English language pairs in the domain of business correspondence. The first part presents results of training the ASR commercial system on English data sets, enriched by error analysis. The second part presents results of machine translation performed by free online tool for English and Croatian and Croatian-English language pairs. Human evaluation in terms of usability is conducted and internal consistency calculated by Cronbach's alpha coefficient, enriched by error analysis. Automatic evaluation is performed by WER (Word Error Rate) and PER (Position-independent word Error Rate) metrics, followed by investigation of Pearson’s correlation with human evaluation.

Keywords: Automatic machine translation, integrated language technologies, quality evaluation, speech recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2885

Authors: Abdolghani Ebrahimi, Diego Klabjan, Chenxi Ge, Daniela Ladner, Parker Stride

Abstract:

In this work, we use machine learning and data analysis techniques to predict the one-year mortality of cirrhotic patients. Data from 2,322 patients with liver cirrhosis are collected at a single medical center. Different machine learning models are applied to predict one-year mortality. A comprehensive feature space including demographic information, comorbidity, clinical procedure and laboratory tests is being analyzed. A temporal pattern mining technic called Frequent Subgraph Mining (FSM) is being used. Model for End-stage liver disease (MELD) prediction of mortality is used as a comparator. All of our models statistically significantly outperform the MELD-score model and show an average 10% improvement of the area under the curve (AUC). The FSM technic itself does not improve the model significantly, but FSM, together with a machine learning technique called an ensemble, further improves the model performance. With the abundance of data available in healthcare through electronic health records (EHR), existing predictive models can be refined to identify and treat patients at risk for higher mortality. However, due to the sparsity of the temporal information needed by FSM, the FSM model does not yield significant improvements. Our work applies modern machine learning algorithms and data analysis methods on predicting one-year mortality of cirrhotic patients and builds a model that predicts one-year mortality significantly more accurate than the MELD score. We have also tested the potential of FSM and provided a new perspective of the importance of clinical features.

Keywords: machine learning, liver cirrhosis, subgraph mining, supervised learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 410

Authors: Eunji Choi, Borang Park, Youngjae Choi, Jinwoo Moon

Abstract:

In this study, a predictive model for estimating the metabolism (MET) of human body was developed for the optimal control of indoor thermal environment. Human body images for indoor activities and human body joint coordinated values were collected as data sets, which are used in predictive model. A deep learning algorithm was used in an initial model, and its number of hidden layers and hidden neurons were optimized. Lastly, the model prediction performance was analyzed after the model being trained through collected data. In conclusion, the possibility of MET prediction was confirmed, and the direction of the future study was proposed as developing various data and the predictive model.

Keywords: Deep learning, indoor quality, metabolism, predictive model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1164

Authors: Ihuarulam Ambrose Ikenna

Abstract:

In the past few decades, the field of chemistry education has grown tremendously and researches indicated that after traditional chemistry instruction students often lacked deep conceptual understanding and failed to integrate their ideas into coherent conceptual framework. For several concepts in chemistry, students at all levels have demonstrated difficulty in changing their initial perceptions. Their perceptions are most often wrong and don't agree with correct scientific concepts. This study explored the effectiveness of intervention discussion sections for a college general chemistry course designed to apply research on students preconceptions, knowledge integration and student explanation. Three interventions discussions lasting three hours on bond energy and spontaneity were done tested and intervention (treatment) students’ performances were compared with that of control group which did not use the experimental pedagogy. Results indicated that this instruction which was capable of identifying students' misconceptions, initial conceptions and integrating those ideas into class discussion led to enhanced conceptual understanding and better achievement for the experimental group.

Keywords: Intervention Discussion Learning Model, Learning, Remedying, Students’ misconceptions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2516

Authors: Israa A. Qari

Abstract:

Learning to request in a foreign language is a key ability within pragmatics language teaching. This paper examines how requests are taught in English Unlimited Book 3 (Cambridge University Press), an EFL textbook series employed by King Abdulaziz University in Jeddah, Saudi Arabia to teach advanced foundation year students English. The focus of analysis is the evaluation of the request linguistic strategies present in the textbook, frequency of the use of these strategies, and the contextual information provided on the use of these linguistic forms. The researcher collected all the linguistic forms which consisted of the request speech act and divided them into levels employing the CCSARP request coding manual. Findings demonstrated that simple and commonly employed request strategies are introduced. Looking closely at the exercises throughout the chapters, it was noticeable that the book exclusively employed the most direct form of requesting (the imperative) when giving learners instructions: e.g. listen, write, ask, answer, read, look, complete, choose, talk, think, etc. The book also made use of some other request strategies such as ‘hedged performatives’ and ‘query preparatory’. However, it was also found that many strategies were not dealt with in the book, specifically strategies with combined functions (e.g. possibility, ability). On a sociopragmatic level, a strong focus was found to exist on standard situations in which relations between the requester and requestee are clear. In general, contextual information was communicated implicitly only. The textbook did not seem to differentiate between formal and informal request contexts (register) which might consequently impel students to overgeneralize. The paper closes with some recommendations for textbook and curriculum designers. Findings are also contrasted with previous results from similar body of research on EFL requests.

Keywords: EFL, Requests, Saudi, speech acts, textbook evaluation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 420

Authors: Lori L. Scarlatos, Ryan Courtney

Abstract:

This paper explores the impact that playing a casual game can have on a player's learning and subsequent behavior. A casual mobile game, Container Chaos, was created to teach undergraduate students about the carbon footprint of various disposable beverage containers. Learning was tested with a short quiz, and behavior was tested by observing which beverage containers players choose when offered a drink and a snack. The game was tested multiple times, under a variety of different circumstances. Findings of these tests indicate that, with extended play over time, players can learn new information and sometimes even change their behavior as a result. This has implications for how other casual games can be used to teach concepts and possibly modify behavior.

Keywords: Behavior, carbon footprint, casual games, environmental impact, material sciences.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 873

Authors: Khaled Abduesslam. M, Mohammed Ali, Basher H Alsdai, Muhammad Nizam, Inayati

Abstract:

This paper presents the voltage problem location classification using performance of Least Squares Support Vector Machine (LS-SVM) and Learning Vector Quantization (LVQ) in electrical power system for proper voltage problem location implemented by IEEE 39 bus New- England. The data was collected from the time domain simulation by using Power System Analysis Toolbox (PSAT). Outputs from simulation data such as voltage, phase angle, real power and reactive power were taken as input to estimate voltage stability at particular buses based on Power Transfer Stability Index (PTSI).The simulation data was carried out on the IEEE 39 bus test system by considering load bus increased on the system. To verify of the proposed LS-SVM its performance was compared to Learning Vector Quantization (LVQ). The results showed that LS-SVM is faster and better as compared to LVQ. The results also demonstrated that the LS-SVM was estimated by 0% misclassification whereas LVQ had 7.69% misclassification.

Keywords: IEEE 39 bus, Least Squares Support Vector Machine, Learning Vector Quantization, Voltage Collapse.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2387

Authors: Nabil El Kadhi, Minerva M. Bunagan

Abstract:

The dynamism in education, particularly in the area of teaching, learning and assessment has caused Higher Education Institutions (HEIs) worldwide to seek for ways to continuously improve their educational processes. HEIs use outcomes of institutional audits, assessments and accreditations, for improvement. In this study, the published institutional audit reports of HEIs in the Sultanate of Oman were analyzed to produce features of good practice; identify challenges along Teaching, Learning Assessment (TLA); and propose a framework that puts major emphasis in having a quality-assured TLA, including a set of principles that can be used as basis in succeeding an institutional visit. The TLA framework, which shows the TLA components, characteristics of the components, related expectation, including implementation tool/ strategy and pitfalls can be used by HEIs to have an adequate understanding of the scope of audit and be able to satisfy institutional audit requirements. The scope of this study can be widened by exploring the other requirements of the Institutional Audits in the Sultanate of Oman, particularly the area on Governance and Management and Student Support Services.

Keywords: Accreditation, audit, quality assurance, teaching, learning and assessment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1451

Authors: C.W. Kan

Abstract:

This paper investigates the use of atmospheric pressure plasma for improving the surface hydrophobicity of polyurethane synthetic leather with tetramethylsilane (TMS). The atmospheric pressure plasma treatment with TMS is a single-step process to enhance the hydrophobicity of polyurethane synthetic leather. The hydrophobicity of the treated surface was examined by contact angle measurement. The physical and chemical surface changes were evaluated by scanning electron microscopy (SEM) and infrared spectroscopy (FTIR). The purpose of this paper is to provide learning materials for understanding how to use atmospheric pressure plasma in the textile finishing process to transform a hydrophilic surface to hydrophobic.

Keywords: Learning materials, atmospheric pressure plasma treatment, hydrophobic, hydrophilic, surface.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1760

Authors: Patricia M. Boechler, Heather M. Gautreau

Abstract:

In this research study, postsecondary students completed an information learning task in an avatar-based 3D virtual learning environment. Three factors were of interest in relation to learning; 1) the influence of collaborative vs. independent conditions, 2) the influence of the spatial arrangement of the virtual environment (linear, random and clustered), and 3) the relationship of individual differences such as spatial skill, general computer experience and video game experience to learning. Students completed pretest measures of prior computer experience and prior spatial skill. Following the premeasure administration, students were given instruction to move through the virtual environment and study all the material within 10 information stations. In the collaborative condition, students proceeded in randomly assigned pairs, while in the independent condition they proceeded alone. After this learning phase, all students individually completed a multiple choice test to determine information retention. The overall results indicated that students in pairs did not perform any better or worse than independent students. As far as individual differences, only spatial ability predicted the performance of students. General computer experience and video game experience did not. Taking a closer look at the pairs and spatial ability, comparisons were made on pairs high/matched spatial ability, pairs low/matched spatial ability and pairs that were mismatched on spatial ability. The results showed that both high/matched pairs and mismatched pairs outperformed low/matched pairs. That is, if a pair had even one individual with strong spatial ability they would perform better than pairs with only low spatial ability individuals. This suggests that, in virtual environments, the specific individuals that are paired together are important for performance outcomes. The paper also includes a discussion of trends within the data that have implications for virtual environment education.

Keywords: Avatar-based, virtual environment, paired learning, individual differences.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 754