Search results for: language learning model

Authors: Talal Alshammari, Nasser Alshammari, Mohamed Sedky, Chris Howard

Abstract:

With the widespread adoption of the Internet-connected devices, and with the prevalence of the Internet of Things (IoT) applications, there is an increased interest in machine learning techniques that can provide useful and interesting services in the smart home domain. The areas that machine learning techniques can help advance are varied and ever-evolving. Classifying smart home inhabitants’ Activities of Daily Living (ADLs), is one prominent example. The ability of machine learning technique to find meaningful spatio-temporal relations of high-dimensional data is an important requirement as well. This paper presents a comparative evaluation of state-of-the-art machine learning techniques to classify ADLs in the smart home domain. Forty-two synthetic datasets and two real-world datasets with multiple inhabitants are used to evaluate and compare the performance of the identified machine learning techniques. Our results show significant performance differences between the evaluated techniques. Such as AdaBoost, Cortical Learning Algorithm (CLA), Decision Trees, Hidden Markov Model (HMM), Multi-layer Perceptron (MLP), Structured Perceptron and Support Vector Machines (SVM). Overall, neural network based techniques have shown superiority over the other tested techniques.

Keywords: activities of daily living, classification, internet of things, machine learning, prediction, smart home

Procedia PDF Downloads 340

Authors: Hervice Roméo Fogno Fotsoa, Germaine Djuidje Kenmoe, Claude Vidal Aloyem Kazé

Abstract:

One of the main applications of machine learning is the prediction of time series. But a more accurate prediction requires a more optimal model of machine learning. Several optimization techniques have been developed, but without considering the input variables disposition of the system. Thus, this work aims to present a new machine learning architecture optimization technique based on their optimal input variables disposition. The validations are done on the prediction of wind time series, using data collected in Cameroon. The number of possible dispositions with four input variables is determined, i.e., twenty-four. Each of the dispositions is used to perform the prediction, with the main criteria being the training and prediction performances. The results obtained from a static architecture and a dynamic architecture of neural networks have shown that these performances are a function of the input variable's disposition, and this is in a different way from the architectures. This analysis revealed that it is necessary to take into account the input variable's disposition for the development of a more optimal neural network model. Thus, a new neural network training algorithm is proposed by introducing the search for the optimal input variables disposition in the traditional back-propagation algorithm. The results of the application of this new optimization approach on the two single neural network architectures are compared with the previously obtained results step by step. Moreover, this proposed approach is validated in a collaborative optimization method with a single objective optimization technique, i.e., genetic algorithm back-propagation neural networks. From these comparisons, it is concluded that each proposed model outperforms its traditional model in terms of training and prediction performance of time series. Thus the proposed optimization approach can be useful in improving the accuracy of time series forecasts. This proves that the proposed optimization approach can be useful in improving the accuracy of time series prediction based on machine learning.

Keywords: input variable disposition, machine learning, optimization, performance, time series prediction

Procedia PDF Downloads 88

Authors: Faiza Abdul Latip

Abstract:

One of the ultimate goals of any nation is to produce competitive manpower and this includes Philippines. Inclination in the field of Mathematics has a significant role in achieving this goal. However, Mathematics, as considered by most people, is the most difficult subject matter along with its topics to learn. This could be manifested from the low performance of students in national and international assessments. Educators have been widely using learning style models in identifying the way students learn. Moreover, it could be the frontline in knowing the difficulties held by each learner in a particular topic specifically concepts pertaining to fractions. However, as what many educators observed, students show difficulties in doing mathematical tasks and in great degree in dealing with fractions most specifically in the district of Datu Odin Sinsuat, Maguindanao. This study focused on the Datu Odin Sinsuat district grade six pupils’ learning styles along with their achievements and difficulties in learning concepts on fractions. Five hundred thirty-two pupils from ten different public elementary schools of the Datu Odin Sinsuat districts were purposively used as the respondents of the study. A descriptive research using the survey method was employed in this study. Quantitative analysis on the pupils’ learning styles on the Kolb’s Learning Style Inventory (KLSI) and scores on the mathematics diagnostic test on fraction concepts were made using this method. The simple frequency and percentage counts were used to analyze the pupils’ learning styles and their achievements on fractions. To determine the pupils’ difficulties in fractions, the index of difficulty on every item was determined. Lastly, the Kruskal-Wallis Test was used in determining the significant difference in the pupils’ achievements on fractions classified by their learning styles. This test was set at 0.05 level of significance. The minimum H-Value of 7.82 was used to determine the significance of the test. The results revealed that the pupils of Datu Odin Sinsuat districts learn fractions in varied ways as they are of different learning styles. However, their achievements in fractions are low regardless of their learning styles. Difficulties in learning fractions were found most in the area of Estimation, Comparing/Ordering, and Division Interpretation of Fractions. Most of the pupils find it very difficult to use fraction as a measure, compare or arrange series of fractions and use the concept of fraction as a quotient.

Keywords: difficulties in fraction, fraction, Kolb's model, learning styles

Procedia PDF Downloads 199

Authors: Karlygash Adamova

Abstract:

This article is focused on the KazTest as one of the most important high-stakes tests and the key tool in Kazakh language assessment. The research will also include the brief introduction to the language policy in Kazakhstan. Particularly, it is going to be changed significantly and turn from bilingualism (Kazakh, Russian) to multilingual policy (three languages - Kazakh, Russian, English). Therefore, the current status of the abovementioned languages will be described. Due to the various educational reforms in the country, the language evaluation system should also be improved and moderated. The research will present the most significant test of Kazakhstan – the KazTest, which is aimed to evaluate the Kazakh language proficiency. Assessment is an ongoing process that encompasses a wide area of knowledge upon the productive performance of the learners. Test is widely defined as a standardized or standard method of research, testing, diagnostics, verification, etc. The two most important characteristics of any test, as the main element of the assessment - validity and reliability - will also be described in this paper. Therefore, the preparation and design of the test, which is assumed to be an indicator of knowledge, and it is highly important to take into account all these properties.

Keywords: multilingualism, language assessment, testing, language policy

Procedia PDF Downloads 122

Authors: Jiwan Kumar, Pooja, Sandeep Negi, Anjum Rouf, Amit Kumar, Naveen Lakra

Abstract:

In modern times where, health issues are increasing day by day, breast cancer is also one of them, which is very crucial and really important to find in the early stages. Doctors can use this model in order to tell their patients whether a cancer is not harmful (benign) or harmful (malignant). We have used the knowledge of machine learning in order to produce the model. we have used algorithms like Logistic Regression, Random forest, support Vector Classifier, Bayesian Network and Radial Basis Function. We tried to use the data of crucial parts and show them the results in pictures in order to make it easier for doctors. By doing this, we're making ML better at finding breast cancer, which can lead to saving more lives and better health care.

Keywords: Bayesian network, radial basis function, ensemble learning, understandable, data making better, random forest, logistic regression, breast cancer

Procedia PDF Downloads 33

Authors: L. Cruz-Lopes, M. Sell, P. Escudeiro, B. Esteves

Abstract:

It might be difficult for deaf people to communicate since spoken and written languages are different from sign language. When it comes to getting information, going to places of cultural heritage, or using services and infrastructure, there is a clear lack of inclusiveness. By creating assistive technology that enables deaf individuals to get around communication hurdles and encourage inclusive tourism, the ICHT- Inclusive Cultural Heritage Tourism initiative hopes to increase knowledge of sign language. The purpose of the Inclusive Cultural Heritage Tourism (ICHT) project is to develop online and on-site sign language tools and material for usage at popular tourist destinations in the northern region of Portugal, including Torre dos Clérigos, the Lello bookstore, Maia Zoo, Porto wine cellars, and São Pedro do Sul (Viseu) thermae. The ICHT system consists of an application using holography, a mobile game, an online platform for collaboration with deaf and hearing users, and a collection of International Sign training courses. The project also offers a prospect for a more inclusive society by introducing a method of teaching sign languages to tourism industry professionals. As a result, the teaching and learning of sign language along with the assistive technology tools created by the project sets up an inclusive environment for the deaf community, producing results in the area of automatic sign language translation and aiding in the global recognition of the Portuguese tourism industry.

Keywords: inclusive tourism, games, international sign training, deaf community

Procedia PDF Downloads 104

Authors: Ravija Gunawardana, Banuka Athuraliya

Abstract:

Machine learning has emerged as a powerful tool for disease diagnosis and prediction. The use of machine learning algorithms has the potential to improve the accuracy of disease prediction, thereby enabling medical professionals to provide more effective and personalized treatments. This study focuses on developing a machine-learning model for disease prediction using symptoms and X-ray images. The importance of this study lies in its potential to assist medical professionals in accurately diagnosing diseases, thereby improving patient outcomes. Respiratory diseases are a significant cause of morbidity and mortality worldwide, and chest X-rays are commonly used in the diagnosis of these diseases. However, accurately interpreting X-ray images requires significant expertise and can be time-consuming, making it difficult to diagnose respiratory diseases in a timely manner. By incorporating machine learning algorithms, we can significantly enhance disease prediction accuracy, ultimately leading to better patient care. The study utilized the Mask R-CNN algorithm, which is a state-of-the-art method for object detection and segmentation in images, to process chest X-ray images. The model was trained and tested on a large dataset of patient information, which included both symptom data and X-ray images. The performance of the model was evaluated using a range of metrics, including accuracy, precision, recall, and F1-score. The results showed that the model achieved an accuracy rate of over 90%, indicating that it was able to accurately detect and segment regions of interest in the X-ray images. In addition to X-ray images, the study also incorporated symptoms as input data for disease prediction. The study used three different classifiers, namely Random Forest, K-Nearest Neighbor and Support Vector Machine, to predict diseases based on symptoms. These classifiers were trained and tested using the same dataset of patient information as the X-ray model. The results showed promising accuracy rates for predicting diseases using symptoms, with the ensemble learning techniques significantly improving the accuracy of disease prediction. The study's findings indicate that the use of machine learning algorithms can significantly enhance disease prediction accuracy, ultimately leading to better patient care. The model developed in this study has the potential to assist medical professionals in diagnosing respiratory diseases more accurately and efficiently. However, it is important to note that the accuracy of the model can be affected by several factors, including the quality of the X-ray images, the size of the dataset used for training, and the complexity of the disease being diagnosed. In conclusion, the study demonstrated the potential of machine learning algorithms for disease prediction using symptoms and X-ray images. The use of these algorithms can improve the accuracy of disease diagnosis, ultimately leading to better patient care. Further research is needed to validate the model's accuracy and effectiveness in a clinical setting and to expand its application to other diseases.

Keywords: K-nearest neighbor, mask R-CNN, random forest, support vector machine

Procedia PDF Downloads 126

Authors: Jian Li

Abstract:

The uncertainty quantification and inversion problems of subsurface oil-water phase flow usually require extensive repeated forward calculations for new runs with changed conditions. To reduce the computational time, various forms of surrogate models have been built. Related research shows that deep learning has emerged as an effective surrogate model, while most surrogate models with deep learning are purely data-driven, which always leads to poor robustness and abnormal results. To guarantee the model more consistent with the physical laws, a coupled theory-guided convolutional neural network (TgCNN) based surrogate model is built to facilitate computation efficiency under the premise of satisfactory accuracy. The model is a convolutional neural network based on multi-well reservoir simulation. The core notion of this proposed method is to bridge two separate blocks on top of an overall network. They underlie the TgCNN model in a coupled form, which reflects the coupling nature of pressure and water saturation in the two-phase flow equation. The model is driven by not only labeled data but also scientific theories, including governing equations, stochastic parameterization, boundary, and initial conditions, well conditions, and expert knowledge. The results show that the TgCNN-based surrogate model exhibits satisfactory accuracy and efficiency in subsurface oil-water phase flow under multi-well conditions.

Keywords: coupled theory-guided convolutional neural network, multi-well conditions, surrogate model, subsurface oil-water phase

Procedia PDF Downloads 72

Authors: Rossella Resi

Abstract:

This paper describes a project carried out in an Italian school with English learning pupils combining three didactic tools which are attested to be relevant for the success of young learner’s language curriculum: the use of technology, the intralingual and interlingual mediation (according to CEFR) and the cultural dimension. Aim of this project was to test a technological hands-on translation activity like subtitling in a formal teaching context and to exploit its potential as motivational tool for developing listening and writing, translation and cross-cultural skills among language learners. The activities proposed involved the use of professional subtitling software called Aegisub and culture-specific films. The workshop was optional so motivation was entirely based on the pleasure of engaging in the use of a realistic subtitling program and on the challenge of meeting the constraints that a real life/work situation might involve. Twelve pupils in the age between 16 and 18 have attended the afternoon workshop. The workshop was organized in three parts: (i) An introduction where the learners were opened up to the concept and constraints of subtitling and provided with few basic rules on spotting and segmentation. During this session learners had also the time to familiarize with the main software features. (ii) The second part involved three subtitling activities in plenum or in groups. In the first activity the learners experienced the technical dimensions of subtitling. They were provided with a short video segment together with its transcription to be segmented and time-spotted. The second activity involved also oral comprehension. Learners had to understand and transcribe a video segment before subtitling it. The third activity embedded a translation activity of a provided transcription including segmentation and spotting of subtitles. (iii) The workshop ended with a small final project. At this point learners were able to master a short subtitling assignment (transcription, translation, segmenting and spotting) on their own with a similar video interview. The results of these assignments were above expectations since the learners were highly motivated by the authentic and original nature of the assignment. The subtitled videos were evaluated and watched in the regular classroom together with other students who did not take part to the workshop.

Keywords: ICT, L2, language learning, language mediation, subtitling

Procedia PDF Downloads 401

Authors: Mohammad Hosein Panahi, Naser Yazdani

Abstract:

we present a technical trading strategy that leverages the FinBERT language model and financial news analysis with a focus on news related to a subset of Nasdaq 100 stocks. Our approach surpasses the baseline Range Break-out strategy in the Bitcoin market, yielding a remarkable 24.8% increase in the win ratio for all Friday trades and an impressive 48.9% surge in short trades specifically on Fridays. Moreover, we conduct rigorous hypothesis testing to establish the statistical significance of these improvements. Our findings underscore considerable potential of our NLP-driven approach in enhancing trading strategies and achieving greater profitability within financial markets.

Keywords: quantitative finance, technical analysis, bitcoin market, NLP, language models, FinBERT, technical trading

Procedia PDF Downloads 53

Authors: Farhad Shafiepour Motlagh, Narges Salehi

Abstract:

Purpose: The purpose of this study was to support student strategies for virtual learning in the learning management system. Methodology: The research method was based on grounded theory. The statistical population included all the articles of the ten years 2022-2010, and the sampling method was purposeful to the extent of theoretical saturation (n=31 ). Data collection was done by referring to the authoritative scientific databases of Emerald, Springer, Elsevier, Google Scholar, Sage Publication, and Science Direct. For data analysis, open coding, axial coding, and selective coding were used. Results: The results showed that causal conditions include cognitive empowerment (comprehension, analysis, composition), emotional empowerment (learning motivation, involvement in the learning system, enthusiasm for learning), psychomotor empowerment (learning to master, internalizing learning skills, creativity in learning). Conclusion: Supporting students requires their empowerment in three dimensions: cognitive, emotional empowerment, and psychomotor empowerment. In such a way that by introducing them to enter the learning management system, the capacities of the system, the toolkit of learning in the system, improve the motivation to learn in them, and in such a case, by learning more in the learning management system, they will reach mastery learning.

Keywords: student support, virtual education, learning management system, electronic

Procedia PDF Downloads 285

Authors: Chris Landorf, Stephen Ward

Abstract:

This paper addresses a virtual environment approach to work integrated learning for students in construction-related disciplines. The virtual approach provides a safe and pedagogically rigorous environment where students can apply theoretical knowledge in a simulated real-world context. The paper describes the development of a 4-dimensional digital construction environment and associated learning activities funded by the Australian Office for Learning and Teaching. The environment was trialled with over 1,300 students and evaluated through questionnaires, observational studies and coursework analysis. Results demonstrate a positive impact on students’ technical learning and collaboration skills, but there is need for further research in relation to critical thinking skills and work-readiness.

Keywords: architectural education, construction industry, digital learning environments, immersive learning

Procedia PDF Downloads 390

Authors: Ulil Afidah, Muhamad Fathan Mubin, Firdha Aulia

Abstract:

Code riverbanks Yogyakarta is a settlement area with middle to lower social classes. Socio-economic situation is affecting the behavior of society. This research aimed to find and explain the implementation and the assessment of character education which were done in elementary schools in Code riverside, Yogyakarta region of Indonesia. This research is a qualitative research which the subjects were the kids of Code riverbanks, Yogyakarta. The data were collected through interviews and document studies and analyzed qualitatively using the technique of interactive analysis model of Miles and Huberman. The results show that: (1) The learning process of character education was done by integrating all aspects such as democratic and interactive learning session also introducing role model to the students. 2) The assessment of character education was done by teacher based on teaching and learning process and an activity in outside the classroom that was the criterion on three aspects: Cognitive, affective and psychomotor.

Keywords: character, Code riverbanks, education, Yogyakarta

Procedia PDF Downloads 237

Authors: Yi-Hsiang Pan, Chen-Hui Huang, Wei-Ting Hsu

Abstract:

The purposes of the study were to understand these topics as follows: 1. To explore the effect of merging teaching personal and social responsibility (TPSR) with sports education model on students' game performance and responsibility. 2. To explore the effect of sports education model on students' game performance and responsibility. 3. To compare the difference between "merging TPSR with sports education model" and "sports education model" on students' game performance and responsibility. The participants include three high school physical education teachers and six physical education classes. Every teacher teaches an experimental group and a control group. The participants had 121 students, including 65 students in the experimental group and 56 students in the control group. The research methods had game performance assessment, questionnaire investigation, interview, focus group meeting. The research instruments include personal and social responsibility questionnaire and game performance assessment instrument. Paired t-test test and MANCOVA were used to test the difference between "merging TPSR with sports education model" and "sports education model" on students' learning performance. 1) "Merging TPSR with sports education model" showed significant improvements in students' game performance, and responsibilities with self-direction, helping others, cooperation. 2) "Sports education model" also had significant improvements in students' game performance, and responsibilities with effort, self-direction, helping others. 3.) There was no significant difference in game performance and responsibilities between "merging TPSR with sports education model" and "sports education model". 4)."Merging TPSR with sports education model" significantly improve learning atmosphere and peer relationships, it may be developed in the physical education curriculum. The conclusions were as follows: Both "Merging TPSR with sports education model" and "sports education model" can help improve students' responsibility and game performance. However, "Merging TPSR with sports education model" can reduce the competitive atmosphere in highly intensive games between students. The curricular projects of hybrid TPSR-Sport Education model is a good approach for moral character education.

Keywords: curriculum and teaching model, sports self-efficacy, sport enthusiastic, character education

Procedia PDF Downloads 305

Authors: Mei-Hui Liu

Abstract:

This paper reports 20 preservice EFL teachers’ learning-to-teach experience when they were engaged in an online project-based practicum implemented on a Cloud Platform. This 10-month study filled in the literature gap by documenting the impact of online project-based instruction on preservice EFL teachers’ professional development. Data analysis showed that the online practicum was regarded as a flexible mechanism offering chances of teaching practices without geographical barriers. Additionally, this project-based practice helped the participants integrate the theories they had learned and further foster them how to create a self-directed online learning environment. Furthermore, these preservice teachers with experiences of technology-enabled practicum showed their motivation to apply technology and online platforms into future instructional practices. Yet, this study uncovered several concerns encountered by these participants during this online field experience. The findings of this study rendered meaning and lessons for teacher educators intending to integrate online practicum into preservice training courses.

Keywords: online teaching practicum, project-based learning, teacher preparation, English language education

Procedia PDF Downloads 356

Authors: Tanmay Bisen, Aastha Shayla, Susham Biswas

Abstract:

Oil spills from tankers can cause significant harm to the environment and local communities, as well as have economic consequences. Early predictions of oil spills can help to minimize these impacts. Our proposed system uses machine learning and neural networks to predict potential oil spills by monitoring data from ship Automatic Identification Systems (AIS). The model analyzes ship movements, speeds, and changes in direction to identify patterns that deviate from the norm and could indicate a potential spill. Our approach not only identifies anomalies but also predicts spills before they occur, providing early detection and mitigation measures. This can prevent or minimize damage to the reputation of the company responsible and the country where the spill takes place. The model's performance on the MV Wakashio oil spill provides insight into its ability to detect and respond to real-world oil spills, highlighting areas for improvement and further research.

Keywords: Anomaly Detection, Oil Spill Prediction, Machine Learning, Image Processing, Graph Neural Network (GNN)

Procedia PDF Downloads 54

Authors: Ayşe Yurdakul, Eckehard Schnieder

Abstract:

Nowadays, there are multilingual and multidisciplinary communication problems because of the increasing technical progress. Each technical field has its own specific terminology and in each particular language, there are differences in relation to definitions of terms. Besides, there could be several translations in the certain target language for one term of the source language. First of all, these problems of semantic relations between terms include the synonymy, antonymy, hypernymy/hyponymy, ambiguity, risk of confusion and translation problems. Therefore, the iglos terminology management system of the Institute for Traffic Safety and Automation Engineering of the Technische Universität Braunschweig has the goal to avoid these problems by a methodological standardisation of term definitions on the basis of the iglos sign model and iglos relation types. The focus of this paper should be on standardisation of navigation terminology as an example.

Keywords: iglos, localisation, methodological approaches, navigation, positioning, definition problems, terminology

Procedia PDF Downloads 355

Authors: Ahmed Shuhaiber

Abstract:

The explosion of the World Wide Web and the electronic trend of university teaching have transformed the learning style to become more learner-centred, Which has popularized the digital delivery of mediated lectures as an alternative or an adjunct to traditional lectures. Despite its potential and popularity, virtual lectures have not been adopted yet in Jordanian universities. This research aimed to fill this gap by studying the factors that influence student’s willingness to accept virtual lectures in one Jordanian University. A quantitative approach was followed by obtaining 216 survey responses and statistically applying the UTAUT model with some modifications. Results revealed that performance expectancy, effort expectancy, social influences and self-efficacy could significantly influence student’s attitudes towards virtual lectures. Additionally, facilitating conditions and attitudes towards virtual lectures were found with significant influence on student’s intention to take virtual lectures. Research implications and future work were specified afterwards.

Keywords: E-learning, student willingness, UTAUT, virtual Lectures, web-based learning systems

Procedia PDF Downloads 278

Authors: Hoi Yan Lau

Abstract:

In Hong Kong, most families have working parents, and the primary caregivers of young children are helpers. This leads to a lack of interaction and language expression in children’s home environment, which affects their language development. This study aims to explore the effectiveness of parent-child reading in improving young children’s language skills. A 4-year-old girl and her mother are recruited to a 3 months’ parent-child reading program. There is a total of 26 reading sessions which target to enhance the parent’s skill of parent-child reading and to assess the child’s language ability. At the same time, the child’s use of language in normal classroom settings is analyzed by anecdotal records. It is shown that the parent is able to use more and better guiding questions during parent-child reading after this program, which in turn leads to more and longer response of the child during the reading sessions. The child also has an increase in Mean Length of Utterance and has a higher frequency of using complete sentences when interacting with other classmates in the classroom. It is worthwhile to further investigate the inclusion of promoting parent-child reading to enhance children’s language development in preschool curriculum planning.

Keywords: Hong Kong, language skills, parent-child reading, preschoolers

Procedia PDF Downloads 146

Authors: Beatriz Lafuente Alcázar, Yash Wani, Amit J. Nimunkar

Abstract:

Cardiovascular Diseases (CVDs) are the leading cause of death globally, and around 80% of sudden cardiac deaths are due to arrhythmias or irregular heartbeats. The majority of these pathologies are revealed by either short-term or long-term alterations in the electrocardiogram (ECG) morphology. The ECG is the main diagnostic tool in cardiology. It is a non-invasive, pain free procedure that measures the heart’s electrical activity and that allows the detecting of abnormal rhythms and underlying conditions. A cardiologist can diagnose a wide range of pathologies based on ECG’s form alterations, but the human interpretation is subjective and it is contingent to error. Moreover, ECG records can be quite prolonged in time, which can further complicate visual diagnosis, and deeply retard disease detection. In this context, deep learning methods have risen as a promising strategy to extract relevant features and eliminate individual subjectivity in ECG analysis. They facilitate the computation of large sets of data and can provide early and precise diagnoses. Therefore, the cardiology field is one of the areas that can most benefit from the implementation of deep learning algorithms. In the present study, a deep learning algorithm is trained following a novel approach, using a combination of different databases as the training set. The goal of the algorithm is to achieve the detection of R-peaks in ECG signals. Its performance is further evaluated in ECG signals with different origins and features to test the model’s ability to generalize its outcomes. Performance of the model for detection of R-peaks for clean and noisy ECGs is presented. The model is able to detect R-peaks in the presence of various types of noise, and when presented with data, it has not been trained. It is expected that this approach will increase the effectiveness and capacity of cardiologists to detect divergences in the normal cardiac activity of their patients.

Keywords: arrhythmia, deep learning, electrocardiogram, machine learning, R-peaks

Procedia PDF Downloads 160

Authors: Yufen Qin

Abstract:

Text sentiment transfer is an important branch of text style transfer. The goal is to generate text with another sentiment attribute based on a text with a specific sentiment attribute while maintaining the content and semantic information unrelated to sentiment unchanged in the process. There are currently two main challenges in this field: no parallel corpus and text attribute entanglement. In response to the above problems, this paper proposed a novel solution: Mask-Prompt-Rerank. Use the method of masking the sentiment words and then using prompt regeneration to transfer the sentence sentiment. Experiments on two sentiment benchmark datasets and one formality transfer benchmark dataset show that this approach makes the performance of small pre-trained language models comparable to that of the most advanced large models, while consuming two orders of magnitude less computing and memory.

Keywords: language model, natural language processing, prompt, text sentiment transfer

Procedia PDF Downloads 62

Authors: Sara T. K. Li, Belinda H. J. Chung, Jeffery C. N. Yip, Janet H. Hsiao

Abstract:

Music notation and text reading both involve statistical learning of music or linguistic structures. However, it remains unclear how music reading expertise influences text reading behavior. The present study examined this issue through an eye-tracking study. Chinese-English bilingual musicians and non-musicians read English sentences, Chinese sentences, musical phrases, and sentences in Tibetan, a language novel to the participants, with their eye movement recorded. Each set of stimuli consisted of two conditions in terms of structural regularity: syntactically correct and syntactically incorrect musical phrases/sentences. They then completed a sentence comprehension (for syntactically correct sentences) or a musical segment/word recognition task afterwards to test their comprehension/recognition abilities. The results showed that in reading musical phrases, as compared with non-musicians, musicians had a higher accuracy in the recognition task, and had shorter reading time, fewer fixations, and shorter fixation duration when reading syntactically correct (i.e., in diatonic key) than incorrect (i.e., in non-diatonic key/atonal) musical phrases. This result reflects their expertise in music reading. Interestingly, in reading Tibetan sentences, which was novel to both participant groups, while non-musicians did not show any behavior differences between reading syntactically correct or incorrect Tibetan sentences, musicians showed a shorter reading time and had marginally fewer fixations when reading syntactically correct sentences than syntactically incorrect ones. However, none of the musicians reported discovering any structural regularities in the Tibetan stimuli after the experiment when being asked explicitly, suggesting that they may have implicitly acquired the structural regularities in Tibetan sentences. This group difference was not observed when they read English or Chinese sentences. This result suggests that music reading expertise facilities reading texts in a novel language (i.e., Tibetan), but not in languages that the readers are already familiar with (i.e., English and Chinese). This phenomenon may be due to the similarities between reading music notations and reading texts in a novel language, as in both cases the stimuli follow particular statistical structures but do not involve semantic or lexical processing. Thus, musicians may transfer their statistical learning skills stemmed from music notation reading experience to implicitly discover structures of sentences in a novel language. This speculation is consistent with a recent finding showing that music reading expertise modulates the processing of English nonwords (i.e., words that do not follow morphological or orthographic rules) but not pseudo- or real words. These results suggest that the modulation of music reading expertise on language processing depends on the similarities in the cognitive processes involved. It also has important implications for the benefits of music education on language and cognitive development.

Keywords: eye movement behavior, eye-tracking, music reading expertise, sentence reading, structural regularity, visual processing

Procedia PDF Downloads 367

Authors: Argyro Maria Skourmalla

Abstract:

The present paper draws on the example of the University of Luxembourg as a multilingual and international setting. The University of Luxembourg, which is located between France, Germany, and Belgium, has adopted a new multilingualism policy in 2020, establishing English, French, German, and Luxembourgish as the official languages of the Institution. With around 7.000 students, more than half of which are international students, the University is a meeting point for languages and cultures. This paper includes data from an online survey that with undergraduate students from different disciplines at the University of Luxembourg. Students shared their personal experience and opinions regarding language use in this higher education context, as well as practices they use in learning in this multilingual context. Findings show the role of technology in assisting students in different aspects of learning this multilingual context. At the same time, more needs to be done to avoid an exclusively monolingual paradigm in higher education. Findings also show that some languages remain ‘unseen’ in this context. Overall, even though linguistic diversity in this University is seen as an asset, a lot needs to be done towards the recognition of staff and students’ linguistic repertoires for inclusion and education equity.

Keywords: higher education, learning, linguistic diversity, multilingual practices

Procedia PDF Downloads 52

Authors: Ji-Seok Koo, Hee‑Yong Kwon, Hui-Young Yun, Kyung-Hui Wang, Youn-Seo Koo

Abstract:

This paper presents a forecasting system for PM2.5 levels in Seoul, South Korea, leveraging a combination of chemical transport modeling and ConvLSTM-DNN machine learning technology. Exposure to PM2.5 has known detrimental impacts on public health, making its prediction crucial for establishing preventive measures. Existing forecasting models, like the Community Multiscale Air Quality (CMAQ) and Weather Research and Forecasting (WRF), are hindered by their reliance on uncertain input data, such as anthropogenic emissions and meteorological patterns, as well as certain intrinsic model limitations. The system we've developed specifically addresses these issues by integrating machine learning and using carefully selected input features that account for local and distant sources of PM2.5. In South Korea, the PM2.5 concentration is greatly influenced by both local emissions and long-range transport from China, and our model effectively captures these spatial and temporal dynamics. Our PM2.5 prediction system combines the strengths of advanced hybrid machine learning algorithms, convLSTM and DNN, to improve upon the limitations of the traditional CMAQ model. Data used in the system include forecasted information from CMAQ and WRF models, along with actual PM2.5 concentration and weather variable data from monitoring stations in China and South Korea. The system was implemented specifically for Seoul's PM2.5 forecasting.

Keywords: PM2.5 forecast, machine learning, convLSTM, DNN

Procedia PDF Downloads 43

Authors: Ioanna Taouki, Marie Lallier, David Soto

Abstract:

Metacognition refers to the capacity to reflect upon our own cognitive processes. Although there is an ongoing discussion in the literature on the role of metacognition in learning and academic achievement, little is known about its neurodevelopmental trajectories in early childhood, when children begin to receive formal education in reading. Here, we evaluate the metacognitive ability, estimated under a recently developed Signal Detection Theory model, of a cohort of children aged between 6 and 7 (N=60), who performed three two-alternative-forced-choice tasks (two linguistic: lexical decision task, visual attention span task, and one non-linguistic: emotion recognition task) including trial-by-trial confidence judgements. Our study has three aims. First, we investigated how metacognitive ability (i.e., how confidence ratings track accuracy in the task) relates to performance in general standardized tasks related to students' reading and general cognitive abilities using Spearman's and Bayesian correlation analysis. Second, we assessed whether or not young children recruit common mechanisms supporting metacognition across the different task domains or whether there is evidence for domain-specific metacognition at this early stage of development. This was done by examining correlations in metacognitive measures across different task domains and evaluating cross-task covariance by applying a hierarchical Bayesian model. Third, using robust linear regression and Bayesian regression models, we assessed whether metacognitive ability in this early stage is related to the longitudinal learning of children in a linguistic and a non-linguistic task. Notably, we did not observe any association between students’ reading skills and metacognitive processing in this early stage of reading acquisition. Some evidence consistent with domain-general metacognition was found, with significant positive correlations between metacognitive efficiency between lexical and emotion recognition tasks and substantial covariance indicated by the Bayesian model. However, no reliable correlations were found between metacognitive performance in the visual attention span and the remaining tasks. Remarkably, metacognitive ability significantly predicted children's learning in linguistic and non-linguistic domains a year later. These results suggest that metacognitive skill may be dissociated to some extent from general (i.e., language and attention) abilities and further stress the importance of creating educational programs that foster students’ metacognitive ability as a tool for long term learning. More research is crucial to understand whether these programs can enhance metacognitive ability as a transferable skill across distinct domains or whether unique domains should be targeted separately.

Keywords: confidence ratings, development, metacognitive efficiency, reading acquisition

Procedia PDF Downloads 136

Authors: Prasanna Ramachandran, Kareem Graham, Helena Kiefel, Sunit Jain, Todd DeSantis

Abstract:

Microbes that reside inside the mammalian GI tract, commonly referred to as the gut microbiome, have been shown to have therapeutic effects in animal models of disease. We hypothesize that specific proteins produced by these microbes are responsible for this activity and may be used directly as therapeutics. To speed up the discovery of these key proteins from the big-data metagenomics, we have applied machine learning techniques. Using amino acid sequences of known epitopes and their corresponding binding partners, protein interaction descriptors (PID) were calculated, making a positive interaction set. A negative interaction dataset was calculated using sequences of proteins known not to interact with these same binding partners. Using Random Forest and positive and negative PID, a machine learning model was trained and used to predict interacting versus non-interacting proteins. Furthermore, the continuous variable, cosine similarity in the interaction descriptors was used to rank bacterial therapeutic candidates. Laboratory binding assays were conducted to test the candidates for their potential as therapeutics. Results from binding assays reveal the accuracy of the machine learning prediction and are subsequently used to further improve the model.

Keywords: protein-interactions, machine-learning, metagenomics, microbiome

Procedia PDF Downloads 359

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

Abstract:

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

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

Procedia PDF Downloads 126

Authors: Ulas Vural, M. Ergun Okay, E. Mesut Yildiz

Abstract:

Telecommunication service providers demand accurate and precise prediction of customer churn probabilities to increase the effectiveness of their customer relation services. The large amount of customer data owned by the service providers is suitable for analysis by machine learning methods. In this study, expenditure data of customers are analyzed by using an artificial neural network (ANN). The ANN model is applied to the data of customers with different billing duration. The proposed model successfully predicts the churn probabilities at 83% accuracy for only three months expenditure data and the prediction accuracy increases up to 89% when the nine month data is used. The experiments also show that the accuracy of ANN model increases on an extended feature set with information of the changes on the bill amounts.

Keywords: customer relationship management, churn prediction, telecom industry, deep learning, artificial neural networks

Procedia PDF Downloads 131

Authors: Gholam Reza Parvizi, Hossein Azad, Ali Reza Kargar

Abstract:

This article investigated the impact of task-based language teaching (TBLT) on writing performance of the Iranian intermediate EFL learners. There were two groups of forty students of the intermediate female learners studying English in Jahad-e-Daneshgahi language institute, ranging in age from thirteen to nineteen. They participated in their regular classes in the institute and were assigned to two groups including an experimental group of task-based language teaching and a control group for the purpose of homogeneity, all students in two groups took an achievement test before the treatment. As a pre-test; students were assigned to write a task at the beginning of the course. One of the classes was conducted through talking a TBLT approach on their writing, while the other class followed regular patterns of teaching, namely traditional approach for TBLT group. There were some tasks chosen from learners’ textbook. The task selection was in accordance with learning standards for ESL and TOFEL writing sections. At the end of the treatment, a post-test was administered to both experimental group and the control group. Scoring was done on the basis of scoring scale of “expository writing quality scale”. The researcher used paired samples t-test to analyze the effect of TBLT teaching approach on the writing performance of the learners. The data analysis revealed that the subjects in TBLT group performed better on the writing performance post-test than the subjects in control group. The findings of the study also demonstrated that TBLT would enhance writing performance in the group of learners. Moreover, it was indicated that TBLT has been effective in teaching writing performance to Iranian EFL learners

Keywords: task-based language teaching, task, language teaching approach, writing proficiency, EFL learners

Procedia PDF Downloads 409

Authors: Schnell Zsuzsanna

Abstract:

Background: The interpretation of written texts, language processing in the visual domain, in other words, atypical reading abilities, also known as dyslexia, is an ever-growing phenomenon in today’s societies and educational communities. The much-researched problem affects cognitive abilities and, coupled with normal intelligence normally manifests difficulties in the differentiation of sounds and orthography and in the holistic processing of written words. The factors of susceptibility are varied: social, cognitive psychological, and linguistic factors interact with each other. Methods: The research will explain the psycholinguistics of dyslexia on the basis of several empirical experiments and demonstrate how domain-general abilities of inhibition, retrieval from the mental lexicon, priming, phonological processing, and visual modality transfer affect successful language processing and interpretation. Interpretation of visual stimuli is hindered, and the problem seems to be embedded in a sociocultural, psycholinguistic, and cognitive background. This makes the picture even more complex, suggesting that the understanding and resolving of the issues of dyslexia has to be interdisciplinary, aided by several disciplines in the field of humanities and social sciences, and should be researched from an empirical approach, where the practical, educational corollaries can be analyzed on an applied basis. Aim and applicability: The lecture sheds light on the applied, cognitive aspects of interpretation, social cognitive traits of language processing, the mental underpinnings of cognitive interpretation strategies in different languages (namely, Hungarian and English), offering solutions with a few applied techniques for success in foreign language learning that can be useful advice for the developers of testing methodologies and measures across ESL teaching and testing platforms.

Keywords: dyslexia, social cognition, transparency, modalities

Procedia PDF Downloads 71