Search results for: students with learning disabilities

Authors: Musbah Abdussayed

Abstract:

The washback effect refers to the influence of assessment on teaching and learning, and this washback effect can either be positive or negative. This study implemented, sequentially, self-assessment (SA) and peer assessment (PA) and examined the washback effect of self and peer assessment (SPA) activities on the writing growth during the revision phase in the writing process. Twenty advanced Arabic as a second language learners from a private school in the USA participated in the study. The participants composed and then revised a short Arabic story as a part of a midterm grade. Qualitative data was collected, analyzed, and synthesized from ten interviews with the learners and from the twenty learners’ post-reflective journals. The findings indicate positive washback effects on the learners’ writing growth. The PA activity enhanced descriptions and meaning, promoted creativity, and improved textual coherence, whereas the SA activity led to detecting editing issues. Furthermore, both SPA activities had washback effects in common, including helping the learners meet the writing genre conventions and developing metacognitive awareness. However, the findings also demonstrate negative washback effects on the learners’ attitudes during the revision phase in the writing process, including bias toward self-evaluation during the SA activity and reluctance to rate peers’ writing performance during the PA activity. The findings suggest that self-and peer assessment activities are essential teaching and learning tools that can be utilized sequentially to help learners tackle multiple writing areas during the revision phase in the writing process.

Keywords: self assessment, peer assessment, washback effect, second language writing, writing process

Procedia PDF Downloads 75

Authors: B. Padmaja, V. V. Rama Prasad, K. V. N. Sunitha, E. Krishna Rao Patro

Abstract:

Stress is a psychological condition that reduces the quality of sleep and affects every facet of life. Constant exposure to stress is detrimental not only for mind but also body. Nevertheless, to cope with stress, one should first identify it. This paper provides an effective method for the cognitive stress level detection by using data provided from a physical activity tracker device Fitbit. This device gathers people’s daily activities of food, weight, sleep, heart rate, and physical activities. In this paper, four major stressors like physical activities, sleep patterns, working hours and change in heart rate are used to assess the stress levels of individuals. The main motive of this system is to use machine learning approach in stress detection with the help of Smartphone sensor technology. Individually, the effect of each stressor is evaluated using logistic regression and then combined model is built and assessed using variants of ordinal logistic regression models like logit, probit and complementary log-log. Then the quality of each model is evaluated using Akaike Information Criterion (AIC) and probit is assessed as the more suitable model for our dataset. This system is experimented and evaluated in a real time environment by taking data from adults working in IT and other sectors in India. The novelty of this work lies in the fact that stress detection system should be less invasive as possible for the users.

Keywords: physical activity tracker, sleep pattern, working hours, heart rate, smartphone sensor

Procedia PDF Downloads 259

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 89

Authors: Asima Ranjan Parhi

Abstract:

English language teaching-learning in higher education departments in Indian and Asian contexts needs to be one of innovation and experimentation rather than rigid prescription. The communicative language teaching has been proposing the context to be of primary importance in this process. Today, English print and electronic media have flooded the market with plenty of material suitable to the classroom context. The entries are poetic, catchy and contain a deliberate method in them which could be utilized to teach not only English language but literature, literary terms and the theory of literature. The Bollywood movies, especially through their songs have been propagating a package which may be useful to teach language and even theory in the sub-continent. While investigating, one may be fascinated to see how such material in the body of media (print and electronic), movies and popular songs generate a data for our classroom in our context, thereby developing a mass language with huge pedagogical implications. Harping on the four skills of teaching and learning of a language in general and English language in particular appears stale and mechanical in a decontextualised, matter of fact classroom. So this discussion visualizes a model beyond these skills as well as the conventional theory, literature, language classroom practices in order to build up a systematic pattern stressing the factors responsible in the particular context, that of specific language, society and culture in tune with language-literature teaching. This study intends to examine certain catchy use of the language entries in mass media which could be in the direction of inviting more such investigations in the Asian context in order to develop a common platform of decolonized pedagogy.

Keywords: pedagogy, electronic media, Bollywood, decolonized, mass media

Procedia PDF Downloads 278

Authors: Michael Campbell, Malaz Elsaddig, Kevin Jones

Abstract:

Background: Despite encouraging progress, global maternal mortality has remained stubbornly high since the declaration of the Millennium development goals. Sub-Saharan Africa accounts for well over half of maternal deaths with Post-Partum Haemorrhage (PPH) being the lead cause. ‘In house’ simulation training delivered by local doctors may be a sustainable approach for improving emergency obstetric care. The aim of this study was to evaluate the use of a Train-the-Trainer (TtT) model in a rural Ugandan hospital to ascertain whether it can feasibly improve practitioners’ management of PPH. Methods: Three Ugandan doctors underwent a training course to enable them to design and deliver simulation training. These doctors used MamaNatalie® models to simulate PPH scenarios for midwives, nurses and medical students. The main outcome was improvement in participants’ knowledge and confidence, assessed using self-reported scores on a 10-point scale. Results: The TtT model produced significant improvements in the confidence and knowledge scores of the ten participants. The mean confidence score rose significantly (p=0.0005) from 6.4 to 8.6 following the simulation training. There was also a significant increase in the mean knowledge score from 7.2 to 9.0 (p=0.04). Medical students demonstrated the greatest overall increase in confidence scores whilst increases in knowledge scores were largest amongst nurses. Conclusions: This study demonstrates that a TtT model can be used in a low resource setting to improve healthcare professionals’ confidence and knowledge in managing obstetric emergencies. This Train-the-Trainer model represents a sustainable approach to addressing skill deficits in low resource settings. We believe that its expansion across healthcare institutions in Sub-Saharan Africa will help to reduce the region’s high maternal mortality rate and step closer to achieving the ambitions of the Millennium development goals.

Keywords: low resource setting, post-partum haemorrhage, simulation training, train the trainer

Procedia PDF Downloads 181

Authors: Nanche Billa Robert

Abstract:

More and more youth are doubtful of making a satisfactory labour market transition because of the present global economic instability and this is more so in Africa of the Sahara and metropolis like Douala. We use the explanatory sequential mixed method: in the first phase we randomly administered 610 questionnaires in the Douala metropolis respecting the population size of each division and its gender composition. We constructed the questionnaire using the desired values for living a comfortable life in Douala. In the second phase, we purposefully selected and interviewed 50 poor youth in order to explain in detail the initial quantitative results. We obtain the following result: The modal income class is 24,000-74,000 frs Central Africa Franc (CFA) and about 67% of the youth of the Douala metropolis earn below 75,000 frs CFA. They earn only 31.02% of the total income. About 85.7% earn below 126,000 frs CFA and about 92.14% earn below 177,000 frs CFA. The poverty-line is estimated at 177,000 frs CFA per month based on the desired predominant values in Douala and only about 9% of youth earn this sum, therefore, 91% of the youth are poor. We discovered that the salary a youth earns influences his level of poverty. Low income earners eat once or twice per day, rent low-standard houses of below 20,000 frs, are dependent and possess very limited durable goods, consult traditional doctors when they are sick, sleep and gamble during their leisure time. Intermediate income earners feed themselves either twice or thrice per day, eat healthy meals weekly, possess more durable goods, are independent, gamble and drink during their leisure time. High income earners feed themselves at least thrice per day, eat healthy food daily, inhabit high quality and expensive houses, are more stable by living longer in their neighbourhoods, like travelling and drinking during their leisure time. Unsalaried youth, are students, housewives or unemployed youth, they eat four times per day, take healthy meals daily, weekly, fortnightly or occasionally, are dependent or homeless depending on whether they are students or unemployed youth. The situation of the youth can be ameliorated through investing in the productive sector and promoting entrepreneurship as well as formalizing the informal sector.

Keywords: income, inequality, poverty, metropolis

Procedia PDF Downloads 101

Authors: Shakila N. Senarath, Dinesh Asanka, Janaka Wijayanayake

Abstract:

The necessity of cosmetic products is arising to fulfill consumer needs of personality appearance and hygiene. A cosmetic product consists of various chemical ingredients which may help to keep the skin healthy or may lead to damages. Every chemical ingredient in a cosmetic product does not perform on every human. The most appropriate way to select a healthy cosmetic product is to identify the texture of the body first and select the most suitable product with safe ingredients. Therefore, the selection process of cosmetic products is complicated. Consumer surveys have shown most of the time, the selection process of cosmetic products is done in an improper way by consumers. From this study, a content-based system is suggested that recommends cosmetic products for the human factors. To such an extent, the skin type, gender and price range will be considered as human factors. The proposed system will be implemented by using Machine Learning. Consumer skin type, gender and price range will be taken as inputs to the system. The skin type of consumer will be derived by using the Baumann Skin Type Questionnaire, which is a value-based approach that includes several numbers of questions to derive the user’s skin type to one of the 16 skin types according to the Bauman Skin Type indicator (BSTI). Two datasets are collected for further research proceedings. The user data set was collected using a questionnaire given to the public. Those are the user dataset and the cosmetic dataset. Product details are included in the cosmetic dataset, which belongs to 5 different kinds of product categories (Moisturizer, Cleanser, Sun protector, Face Mask, Eye Cream). An alternate approach of TF-IDF (Term Frequency – Inverse Document Frequency) is applied to vectorize cosmetic ingredients in the generic cosmetic products dataset and user-preferred dataset. Using the IF-IPF vectors, each user-preferred products dataset and generic cosmetic products dataset can be represented as sparse vectors. The similarity between each user-preferred product and generic cosmetic product will be calculated using the cosine similarity method. For the recommendation process, a similarity matrix can be used. Higher the similarity, higher the match for consumer. Sorting a user column from similarity matrix in a descending order, the recommended products can be retrieved in ascending order. Even though results return a list of similar products, and since the user information has been gathered, such as gender and the price ranges for product purchasing, further optimization can be done by considering and giving weights for those parameters once after a set of recommended products for a user has been retrieved.

Keywords: content-based filtering, cosmetics, machine learning, recommendation system

Procedia PDF Downloads 138

Authors: Feiying Wu

Abstract:

Chatbots are computer programs that attempt to engage a human in a dialogue, which originated in the 1960s with MIT's Eliza. However, they have become widespread more recently as advances in language technology have produced chatbots with increasing linguistic quality and sophistication, leading to their potential to serve as a tool for Computer-Assisted Language Learning(CALL). The aim of this article is to assess the feasibility of using two chatbots, Mitsuku and CleverBot, as pedagogical tools for learning English as a second language by stimulating L2 learners with distinct English proficiencies. Speaking of the input of stimulated learners, they are measured by AntWordProfiler to match the user's expected vocabulary proficiency. Totally, there are four chat sessions as each chatbot will converse with both beginners and advanced learners. For evaluation, it focuses on chatbots' responses from a linguistic standpoint, encompassing vocabulary and sentence levels. The vocabulary level is determined by the vocabulary range and the reaction to misspelled words. Grammatical accuracy and responsiveness to poorly formed sentences are assessed for the sentence level. In addition, the assessment of this essay sets 25% lexical and grammatical incorrect input to determine chatbots' corrective ability towards different linguistic forms. Based on statistical evidence and illustration of examples, despite the small sample size, neither Mitsuku nor CleverBot is ideal as educational tools based on their performance through word range, grammatical accuracy, topic range, and corrective feedback for incorrect words and sentences, but rather as a conversational tool for beginners of L2 English.

Keywords: chatbots, CALL, L2, corrective feedback

Procedia PDF Downloads 82

Authors: Nathaniel Carpenter

Abstract:

Web-enabled systems for supporting youth mental health management in Australia are pioneering in their field; however, with their success, these systems are experiencing exponential growth in demand which is straining an already stretched service. Supporting youth mental is critical as the lack of support is associated with significant and lasting negative consequences. To meet this growing demand, and provide critical support, investigations are needed on evaluating and improving existing online support services. Improvements should focus on developing frameworks capable of augmenting and scaling service provisions. There are few investigations informing best-practice frameworks when implementing e-mental health support systems for youth mental health; there are fewer which implement machine learning or artificially intelligent systems to facilitate the delivering of services. This investigation will use a case study methodology to highlight the design features which are important for systems to enable young people to self-manage their mental health. The investigation will also highlight the current information system challenges, to include challenges associated with service quality, provisioning, and scaling. This work will propose methods of meeting these challenges through improved design, service augmentation and automation, service quality, and through artificially intelligent inspired solutions. The results of this study will inform a framework for supporting youth mental health with intelligent and scalable web-enabled technologies to support an ever-growing user base.

Keywords: artificial intelligence, information systems, machine learning, youth mental health

Procedia PDF Downloads 119

Authors: Yibeltal Chanie Manie, Zebider Asire Munyelet

Abstract:

5G and 6G technology offers enhanced quality of service with high data transmission rates, which necessitates the implementation of the Internet of Things (IoT) in 5G/6G architecture. In this paper, we proposed the integration of free space optical communication (FSO) with fiber sensor networks for IoT applications. Recently, free-space optical communications (FSO) are gaining popularity as an effective alternative technology to the limited availability of radio frequency (RF) spectrum. FSO is gaining popularity due to flexibility, high achievable optical bandwidth, and low power consumption in several applications of communications, such as disaster recovery, last-mile connectivity, drones, surveillance, backhaul, and satellite communications. Hence, high-speed FSO is an optimal choice for wireless networks to satisfy the full potential of 5G/6G technology, offering 100 Gbit/s or more speed in IoT applications. Moreover, machine learning must be integrated into the design, planning, and optimization of future optical wireless communication networks in order to actualize this vision of intelligent processing and operation. In addition, fiber sensors are important to achieve real-time, accurate, and smart monitoring in IoT applications. Moreover, we proposed deep learning techniques to estimate the strain changes and peak wavelength of multiple Fiber Bragg grating (FBG) sensors using only the spectrum of FBGs obtained from the real experiment.

Keywords: optical sensor, artificial Intelligence, Internet of Things, free-space optics

Procedia PDF Downloads 69

Authors: Maria Antonietta Marongiu

Abstract:

Propositional information in discourse is made coherent, intelligible, and persuasive through metadiscourse. The linguistic and rhetorical choices that writers/speakers make to organize and negotiate content matter are intended to help relate a text to its context. Besides, they help the audience to connect to and interpret a text according to the values of a specific discourse community. Based on these assumptions, this work aims to analyse the use of metadiscourse in the spoken performance of teachers in online EFL, ESP, and subject-teacher courses taught in English to non-native learners in higher education. In point of fact, the global spread of Covid 19 has forced universities to transition their in-class courses to online delivery. This has inevitably placed on the instructor a heavier interactional responsibility compared to in-class courses. Accordingly, online delivery needs greater structuring as regards establishing the reader/listener’s resources for text understanding and negotiating. Indeed, in online as well as in in-class courses, lessons are social acts which take place in contexts where interlocutors, as members of a community, affect the ways ideas are presented and understood. Following Hyland’s Interactional Model of Metadiscourse (2005), this study intends to investigate Teacher Talk in online academic courses during the Covid 19 lock-down in Italy. The selected corpus includes the transcripts of online EFL and ESP courses and subject-teachers online courses taught in English. The objective of the investigation is, firstly, to ascertain the presence of metadiscourse in the form of interactive devices (to guide the listener through the text) and interactional features (to involve the listener in the subject). Previous research on metadiscourse in academic discourse, in college students' presentations in EAP (English for Academic Purposes) lessons, as well as in online teaching methodology courses and MOOC (Massive Open Online Courses) has shown that instructors use a vast array of metadiscoursal features intended to express the speakers’ intentions and standing with respect to discourse. Besides, they tend to use directions to orient their listeners and logical connectors referring to the structure of the text. Accordingly, the purpose of the investigation is also to find out whether metadiscourse is used as a rhetorical strategy by instructors to control, evaluate and negotiate the impact of the ongoing talk, and eventually to signal their attitudes towards the content and the audience. Thus, the use of metadiscourse can contribute to the informative and persuasive impact of discourse, and to the effectiveness of online communication, especially in learning contexts.

Keywords: discourse analysis, metadiscourse, online EFL and ESP teaching, rhetoric

Procedia PDF Downloads 131

Authors: Shanshan Zhu, Mohammad Nasim

Abstract:

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

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

Procedia PDF Downloads 51

Authors: Zehra Gencel Efe, Fatma Susam Ozsayın, Satı Tas

Abstract:

Background and Aim: It is not possible to teach all the knowledge related to operating room nursing in the nursing education process. Certified courses are organized by the Ministry of Health to compensate the lack of postgraduate training and the theoretical and practical training needs of working nurses. In this study; It is aimed to investigate the participants’ opinions and recommendations attending the certified course of operating room nursing that organized in İKCU AtaturkTraining and Research Hospital. Method: Two operating room nursing courses were organized in 2016. The 1st Operating Room Nursing Certified Course Program was organized between March 07, 2016 and April 6, 2016and the 2nd Operating Room Nursing Certified Course Program was organized between 07 November 2016 - 06 December 2016 at the İKCU Ataturk Training and Research Hospital. The first program was accepted for 29 participants, the second program was accepted for 30 participants. In the collection of the data, the 'Operating Room Nursing Certified Training Program Evaluation Form', 'Operating Room Nursing Certified Training Program Theoretical Training Evaluation Form' were used. Three point Likert-type scale is used for responses in the 'Operating Room Nursing Certified Training Program Evaluation Form’ (1=verygood, 2=good, 3=poor). Data is collected in five areas related to training program, operation room practice, communication, responsibility, experiences of learning. Four point Likert-type scale is used for responses in the 'Operating Room Nursing Certified Training Program Theoretical Training Evaluation Form' (1=verysatisfied, 2=quitesatisfied, 3=satisfied, 4=dissatisfied). Data is collected in two areas include presentation and content. Data were analyzed with SPSS 16 program. Findings and Conclusion: It was found that 93,22% of participants were female in addition, 62,7% had bachelor degree. It was seen that 33,87% of the work group had 1-5 years of experience in their field. It was found that; 88% of trainees participating in the first group to the operating room nursing-certified course program stated the training program was very good, 12% of them stated the training program was good. Nobody was signed the ‘poor’ choice. 81% of the trainees who participated in the 2nd group to the operating room nursing-certified course program stated the training program was very good, 19% of them stated the training program was good. Nobody was signed the ‘poor’ choice. It was found that there was no meaningful difference between the achievement ratios of the trainees and the learning status of the trainees when compared with the t test in the groups with success level of the operating room nursing certified course program according to the learning status of the participants (p ˃ 0,05). The trainees noted that the course was satisfied with theoretical and practical steps but the support services (lunch, coffee breaks etc.) were in adequate.

Keywords: certified courses, nursing certified courses, operating room nursing, training program

Procedia PDF Downloads 219

Authors: Yuwaratu Syafira, Wahyu K. Y. Putra, Kusharisupeni Djokosujono

Abstract:

Background/Objective: Body Mass Index (BMI) serves various purposes, including measuring the prevalence of obesity in a population, and also in formulating a patient’s diet at a hospital, and can be calculated with the equation = body weight (kg)/body height (m)². However, the BMI of an individual with difficulties in carrying their weight or standing up straight can not necessarily be measured. The aim of this study was to form a prediction model for the BMI of young adult students of Public Health Faculty of University of Indonesia. Subject/Method: This study used a cross sectional design, with a total sample of 132 respondents, consisted of 58 males and 74 females aged 21- 30. The dependent variable of this study was BMI, and the independent variables consisted of sex and anthropometric measurements, which included ulna length, arm length, tibia length, knee height, mid-upper arm circumference, and calf circumference. Anthropometric information was measured and recorded in a single sitting. Simple and multiple linear regression analysis were used to create the prediction equation for BMI. Results: The male respondents had an average BMI of 24.63 kg/m² and the female respondents had an average of 22.52 kg/m². A total of 17 variables were analysed for its correlation with BMI. Bivariate analysis showed the variable with the strongest correlation with BMI was Mid-Upper Arm Circumference/√Ulna Length (MUAC/√UL) (r = 0.926 for males and r = 0.886 for females). Furthermore, MUAC alone also has a very strong correlation with BMI (r = 0,913 for males and r = 0,877 for females). Prediction models formed from either MUAC/√UL or MUAC alone both produce highly accurate predictions of BMI. However, measuring MUAC/√UL is considered inconvenient, which may cause difficulties when applied on the field. Conclusion: The prediction model considered most ideal to estimate BMI is: Male BMI (kg/m²) = 1.109(MUAC (cm)) – 9.202 and Female BMI (kg/m²) = 0.236 + 0.825(MUAC (cm)), based on its high accuracy levels and the convenience of measuring MUAC on the field.

Keywords: body mass index, mid-upper arm circumference, prediction model, ulna length

Procedia PDF Downloads 218

Authors: J. Knight, E. Barberà

Abstract:

Language learning strategies have been defined as thoughts and actions, consciously chosen and operationalized by language learners, to help them in carrying out a multiplicity of tasks from the very outset of learning to the most advanced levels of target language performance. While research in the field of Second Language Acquisition has focused on ‘good’ language learners, the effectiveness of strategy-use and orchestration by effective learners in face-to-face classrooms much less research has attended to learner strategies in online contexts, particular strategies in relation to technological tool use which can be part of a task design. In addition, much research on learner strategies and strategy use has been explored focusing on cognitive, attitudinal and metacognitive behaviour with less research focusing on the social aspect of strategies. This study focuses on how learners mediate with a technological tool designed to support synchronous spoken interaction and how this shape their spoken interaction in the opening of their talk. A case study approach is used incorporating notions from communities of practice theory to analyse and understand learner strategies of dyads carrying out a role play task. The study employs analysis of transcripts of spoken interaction in the openings of the talk along with log files of tool use. The study draws on results of previous studies pertaining to the same tool as a form of triangulation. Findings show how learners gain pre-task planning time through technological tool control. The strategies involving learners’ choices to enter and exit the tool shape their spoken interaction qualitatively, with some cases demonstrating long silences whilst others appearing to start the pedagogical task immediately. Who/what learners orientate to in the openings of the talk: an audience (i.e. the teacher), each other and/or screen-based signifiers in the opening moments of the talk also becomes a focus. The study highlights how tool use as a social practice should be considered a learning strategy in online contexts whereby different usages may be understood in the light of the more usual asynchronous social practices of the online community. The teachers’ role in the community is also problematised as the evaluator of the practices of that community. Results are pertinent for task design for synchronous speaking tasks. The use of community of practice theory supports an understanding of strategy use that involves both metacognition alongside social context revealing how tool-use strategies may need to be orally (socially) negotiated by learners and may also differ from an online language community.

Keywords: learner strategy, tool use, community of practice, speaking task

Procedia PDF Downloads 345

Authors: John Gibbs, Benjamin Flanders, Dylan Pozorski, Weixuan Liu

Abstract:

Weight Painting–adjusting the influence a skeletal joint has on a given vertex in a character mesh–is an arduous and time con- suming part of the 3D animation pipeline. This process generally requires a trained technical animator and many hours of work to complete. Our skiNNer plug-in, which works within Autodesk’s Maya 3D animation software, uses Machine Learning and data pro- cessing techniques to create a deep neural network model that can accomplish the weight painting task in seconds rather than hours for bipedal quasi-humanoid character meshes. In order to create a properly trained network, a number of challenges were overcome, including curating an appropriately large data library, managing an arbitrary 3D mesh size, handling arbitrary skeletal architectures, accounting for extreme numeric values (most data points are near 0 or 1 for weight maps), and constructing an appropriate neural network model that can properly capture the high frequency alter- ation between high weight values (near 1.0) and low weight values (near 0.0). The arrived at neural network model is a cross between a traditional CNN, deep residual network, and fully dense network. The resultant network captures the unusually hard-edged features of a weight map matrix, and produces excellent results on many bipedal models.

Keywords: 3d animation, animation, character, rigging, skinning, weight painting, machine learning, artificial intelligence, neural network, deep neural network

Procedia PDF Downloads 278

Authors: Farhad Shafiepour Motlagh, Narges Salehi

Abstract:

Purpose: The aim of the present study was a paradigm model of educational policy review strategies for the development of Professional schools in Iran. Research Methodology: The research method was based on Grounded theory. The statistical population included all articles of the ten years 2022-2010 and the method of sampling in a purposeful manner to the extent of theoretical saturation to 31 articles. For data analysis, open coding, axial coding and selective coding were used. Results: The results showed that causal conditions include social requirements (social expectations, educational justice, social justice); technology requirements (use of information and communication technology, use of new learning methods), educational requirements (development of educational territory, Development of educational tools and development of learning methods), contextual conditions including dual dimensions (motivational-psychological context, context of participation and cooperation), strategic conditions including (decentralization, delegation, organizational restructuring), intervention conditions (poor knowledge) Human resources, centralized system governance) and outcomes (school productivity, school professionalism, graduate entry into the labor market) were obtained. Conclusion: A review of educational policy is necessary to develop Iran's Professional schools, and this depends on decentralization, delegation, and, of course, empowerment of school principals.

Keywords: school productivity, professional schools, educational policy, paradigm

Procedia PDF Downloads 212

Authors: Goudjil kamel, Boukhatem Ghania, Jlailia Djihene

Abstract:

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

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

Procedia PDF Downloads 29

Authors: Oluwaseun Ijiwade, Chris Davison, Kelvin Gregory

Abstract:

In Australia, like other parts of the world, the debate on how to enhance teachers using assessment data to inform teaching and learning of English as an Additional Language (EAL, Australia) or English as a Foreign Language (EFL, United States) have occupied the centre of academic scholarship. Traditionally, this approach was conceptualised as ‘Formative Assessment’ and, in recent times, ‘Assessment for Learning (AfL)’. The central problem is that teacher-made tests are limited in providing data that can inform teaching and learning due to variability of classroom assessments, which are hindered by teachers’ characteristics and assessment literacy. To address this concern, scholars in language education and testing have proposed a uniformed large-scale computer-based assessment program to meet the needs of teachers and promote AfL in language education. In Australia, for instance, the Victoria state government commissioned a large-scale project called 'Tools to Enhance Assessment Literacy (TEAL) for Teachers of English as an additional language'. As part of the TEAL project, a tool called ‘Reading and Vocabulary assessment for English as an Additional Language (RVEAL)’, as a diagnostic language assessment (DLA), was developed by language experts at the University of New South Wales for teachers in Victorian schools to guide EAL pedagogy in the classroom. Therefore, this study aims to provide qualitative evidence for understanding beliefs about the diagnostic language assessment (DLA) among EAL teachers in primary and secondary schools in Victoria, Australia. To realize this goal, this study raises the following questions: (a) How do teachers use large-scale assessment data for diagnostic purposes? (b) What skills do language teachers think are necessary for using assessment data for instruction in the classroom? and (c) What factors, if any, contribute to teachers’ beliefs about diagnostic assessment in a large-scale assessment? Semi-structured interview method was used to collect data from at least 15 professional teachers who were selected through a purposeful sampling. The findings from the resulting data analysis (thematic analysis) provide an understanding of teachers’ beliefs about DLA in a classroom context and identify how these beliefs are crystallised in language teachers. The discussion shows how the findings can be used to inform professional development processes for language teachers as well as informing important factor of teacher cognition in the pedagogic processes of language assessment. This, hopefully, will help test developers and testing organisations to align the outcome of this study with their test development processes to design assessment that can enhance AfL in language education.

Keywords: beliefs, diagnostic language assessment, English as an additional language, teacher cognition

Procedia PDF Downloads 201

Authors: Bathmajaa Muralisankar

Abstract:

As much as railway station infrastructure designs and ticket-booking norms have been changed to facilitate use by differently abled persons, the railway train compartments themselves have not been made user-friendly for differently abled persons. Owing to safety concerns, dependency on others for their travel, and fear of isolation, differently abled people do not prefer travelling by train. Rather than including a dedicated compartment open only to the differently abled, including the latter with others in the normal compartment (with the proposed modifications discussed here) will make them feel secure and make for an enhanced travel experience for them. This approach also represents the most practical way to include a particular category of people in the mainstream society. Lowering the height of the compartment doors and providing a wider entrance with a ramp will provide easy entry for those using wheelchairs. As well, removing the first two alternate rows and the first two side seats will not only widen the passage and increase seating space but also improve wheelchair turning radius. This will help them travel without having to depend on others. Seating arrangements may be done to accommodate their family members near them instead of isolating the differently abled in a separate compartment. According to present ticket-booking regulations of the Indian Railways, three to four disabled persons may travel without their family or one to two along with their family, and the numbers may be added or reduced. To help visually challenged and hearing-impaired persons, in addition to the provision of special instruments, railings, and textured footpaths and flooring, the seat numbers above the seats may be set in metal or plastic as an outward projection so the visually impaired can touch and feel the numbers. Braille boards may be included at the entrance to the compartment along with seat numbers in the aforementioned projected manner. These seat numbers may be designed as buttons, which when pressed results in an announcement of the seat number in the applicable local language as well as English. Emergency buttons, rather than emergency chains, within the easy reach of disabled passengers will also help them.

Keywords: dependency, differently abled, inclusion, mainstream society

Procedia PDF Downloads 258

Authors: Kanika Gupta, Ashok Kumar

Abstract:

Biofilms are dense, highly hydrated cell clusters that are irreversibly attached to a substratum, to an interface or to each other, and are embedded in a self-produced gelatinous matrix composed of extracellular polymeric substances. Research in biofilm field has become very significant, as biofilm has shown high mechanical resilience and resistance to antibiotic treatment and constituted as a significant problem in both healthcare and other industry related to microorganisms. The massive information both stated and hidden in the biofilm literature are growing exponentially therefore it is not possible for researchers and practitioners to automatically extract and relate information from different written resources. So, the current work proposes and discusses the use of text mining techniques for the extraction of information from biofilm literature corpora containing 34306 documents. It is very difficult and expensive to obtain annotated material for biomedical literature as the literature is unstructured i.e. free-text. Therefore, we considered unsupervised approach, where no annotated training is necessary and using this approach we developed a system that will classify the text on the basis of growth and development, drug effects, radiation effects, classification and physiology of biofilms. For this, a two-step structure was used where the first step is to extract keywords from the biofilm literature using a metathesaurus and standard natural language processing tools like Rapid Miner_v5.3 and the second step is to discover relations between the genes extracted from the whole set of biofilm literature using pubmed.mineR_v1.0.11. We used unsupervised approach, which is the machine learning task of inferring a function to describe hidden structure from 'unlabeled' data, in the above-extracted datasets to develop classifiers using WinPython-64 bit_v3.5.4.0Qt5 and R studio_v0.99.467 packages which will automatically classify the text by using the mentioned sets. The developed classifiers were tested on a large data set of biofilm literature which showed that the unsupervised approach proposed is promising as well as suited for a semi-automatic labeling of the extracted relations. The entire information was stored in the relational database which was hosted locally on the server. The generated biofilm vocabulary and genes relations will be significant for researchers dealing with biofilm research, making their search easy and efficient as the keywords and genes could be directly mapped with the documents used for database development.

Keywords: biofilms literature, classifiers development, text mining, unsupervised learning approach, unstructured data, relational database

Procedia PDF Downloads 174

Authors: Mateusz Jeżowski, Jadwiga Fila, Paweł Poszytek

Abstract:

This abstract summarizes the combined findings of several analyses carried out by the authors on the barriers to accessing international education mobility programs by people with fewer opportunities, especially those with a low level of cultural and social capital. Two flagship educational mobility initiatives of the European Union – the Erasmus+ Program and the European Solidarity Corps are aimed at equipping young people and participants of all ages with the qualifications and skills needed for their meaningful participation in a democratic society intercultural understanding and successful transition in the labour market. The heart of these programs is to come closer to people with fewer opportunities, including people with disabilities, migrants, as well as those facing socio-economic difficulties and displaying a low level of social and cultural capital. Still, people who participate in such initiatives usually demonstrate higher than average cultural and social capital, as understood by Pierre Bourdieu. First of all, the educational attainment of their parents is higher than the average. Secondly, they mostly live in large agglomerations, with good access to education and culture, which affects their foreign language skills as well as social and cultural competencies. Finally, participation in Erasmus+ Program or European Solidarity Corps is not their first educational mobility experience. It is therefore justified to state that their social and cultural capital, already high before taking part in Erasmus+ and European Solidarity Corps, becomes even higher once their international mobility activities have been over, at the expense of those people with fewer opportunities, who, in theory, could participate in those initiatives, nonetheless did not, for the following reasons: lack of sufficient information on such programs, financial obstacles or unappreciation of the value of international mobility. In their work, the authors will discuss what are, in the light of Bourdieu’s perception of social and cultural capital, the main obstacles for young people to participate in international mobility programs of the European Union and will offer comprehensive solutions rooted in their vast experience in management and implementation of Erasmus+ Program and European Solidarity Corps.

Keywords: cultural capital, educational mobility, Erasmus+, European solidarity corps, inclusion, social capital

Procedia PDF Downloads 125

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Electricity prices have sophisticated features such as high volatility, nonlinearity and high frequency that make forecasting quite difficult. Electricity price has a volatile and non-random character so that, it is possible to identify the patterns based on the historical data. Intelligent decision-making requires accurate price forecasting for market traders, retailers, and generation companies. So far, many shallow-ANN (artificial neural networks) models have been published in the literature and showed adequate forecasting results. During the last years, neural networks with many hidden layers, which are referred to as DNN (deep neural networks) have been using in the machine learning community. The goal of this study is to investigate electricity price forecasting performance of the shallow-ANN and DNN models for the Turkish day-ahead electricity market. The forecasting accuracy of the models has been evaluated with publicly available data from the Turkish day-ahead electricity market. Both shallow-ANN and DNN approach would give successful result in forecasting problems. Historical load, price and weather temperature data are used as the input variables for the models. The data set includes power consumption measurements gathered between January 2016 and December 2017 with one-hour resolution. In this regard, forecasting studies have been carried out comparatively with shallow-ANN and DNN models for Turkish electricity markets in the related time period. The main contribution of this study is the investigation of different shallow-ANN and DNN models in the field of electricity price forecast. All models are compared regarding their MAE (Mean Absolute Error) and MSE (Mean Square) results. DNN models give better forecasting performance compare to shallow-ANN. Best five MAE results for DNN models are 0.346, 0.372, 0.392, 0,402 and 0.409.

Keywords: deep learning, artificial neural networks, energy price forecasting, turkey

Procedia PDF Downloads 299

Authors: Ghassan Kbar, Shady Aly, Ibrahim Alsharawy, Akshay Bhatia, Nur Alhasan, Ronaldo Enriquez

Abstract:

The Smart Help for persons with disability (PWD) is a part of the project SMARTDISABLE which aims to develop relevant solution for PWD that target to provide an adequate workplace environment for them. It would support PWD needs smartly through smart help to allow them access to relevant information and communicate with other effectively and flexibly, and smart editor that assist them in their daily work. It will assist PWD in knowledge processing and creation as well as being able to be productive at the work place. The technical work of the project involves design of a technological scenario for the Ambient Intelligence (AmI) - based assistive technologies at the workplace consisting of an integrated universal smart solution that suits many different impairment conditions and will be designed to empower the Physically disabled persons (PDP) with the capability to access and effectively utilize the ICTs in order to execute knowledge rich working tasks with minimum efforts and with sufficient comfort level. The proposed technology solution for PWD will support voice recognition along with normal keyboard and mouse to control the smart help and smart editor with dynamic auto display interface that satisfies the requirements for different PWD group. In addition, a smart help will provide intelligent intervention based on the behavior of PWD to guide them and warn them about possible misbehavior. PWD can communicate with others using Voice over IP controlled by voice recognition. Moreover, Auto Emergency Help Response would be supported to assist PWD in case of emergency. This proposed technology solution intended to make PWD very effective at the work environment and flexible using voice to conduct their tasks at the work environment. The proposed solution aims to provide favorable outcomes that assist PWD at the work place, with the opportunity to participate in PWD assistive technology innovation market which is still small and rapidly growing as well as upgrading their quality of life to become similar to the normal people at the workplace. Finally, the proposed smart help solution is applicable in all workplace setting, including offices, manufacturing, hospital, etc.

Keywords: ambient intelligence, ICT, persons with disability PWD, smart application, SHW

Procedia PDF Downloads 423

Authors: M. Kharrat, G. Moreau, Z. Aboura

Abstract:

The latest advances in the weaving industry, combined with increasingly sophisticated means of materials processing, have made it possible to produce complex 3D composite structures. Mainly used in aeronautics, composite materials with 3D architecture offer better mechanical properties than 2D reinforced composites. Nevertheless, these materials require a good understanding of their behavior. Because of the complexity of such materials, the damage mechanisms are multiple, and the scenario of their appearance and evolution depends on the nature of the exerted solicitations. The AE technique is a well-established tool for discriminating between the damage mechanisms. Suitable sensors are used during the mechanical test to monitor the structural health of the material. Relevant AE-features are then extracted from the recorded signals, followed by a data analysis using pattern recognition techniques. In order to better understand the damage scenarios of interlock composite materials, a multi-instrumentation was set-up in this work for tracking damage initiation and development, especially in the vicinity of the first significant damage, called macro-damage. The deployed instrumentation includes video-microscopy, Digital Image Correlation, Acoustic Emission (AE) and micro-tomography. In this study, a multi-variable AE data analysis approach was developed for the discrimination between the different signal classes representing the different emission sources during testing. An unsupervised classification technique was adopted to perform AE data clustering without a priori knowledge. The multi-instrumentation and the clustered data served to label the different signal families and to build a learning database. This latter is useful to construct a supervised classifier that can be used for automatic recognition of the AE signals. Several materials with different ingredients were tested under various solicitations in order to feed and enrich the learning database. The methodology presented in this work was useful to refine the damage threshold for the new generation materials. The damage mechanisms around this threshold were highlighted. The obtained signal classes were assigned to the different mechanisms. The isolation of a 'noise' class makes it possible to discriminate between the signals emitted by damages without resorting to spatial filtering or increasing the AE detection threshold. The approach was validated on different material configurations. For the same material and the same type of solicitation, the identified classes are reproducible and little disturbed. The supervised classifier constructed based on the learning database was able to predict the labels of the classified signals.

Keywords: acoustic emission, classifier, damage mechanisms, first damage threshold, interlock composite materials, pattern recognition

Procedia PDF Downloads 160

Authors: Martin Lauzier, Benjamin Lafreniere-Carrier, Nathalie Delobbe

Abstract:

Supervisor support is one of the main levers to foster transfer of training. Although past and current studies voice its effects, few have sought to identify the factors that may explain why supervisors offer support to their subordinates when they return from training. Based on Goal Orientation Theory and following the principles of supportive supervision, this study aims to improve our understanding of the factors that influence supervisors’ involvement in the transfer process. More specifically, this research seeks to verify the influence of supervisors’ goal orientation on the adoption of post-training support behaviors. This study also assesses the mediating role of the supervisors’ interest in subordinates’ development on this first relationship. Conducted in two organizations (Canadian: N₁ = 292; Belgian: N₂ = 80), the results of this study revealed three main findings. First, supervisors’ who adopt learning mastery goal orientation also tend to adopt more post-training supportive behaviors. Secondly, regression analyses (using the bootstrap method) show that supervisors' interest in developing their subordinates’ skills mediate the relationship between supervisors’ goal orientation and post-training supportive behaviors. Thirdly, the observed mediation effects are consistent in both samples, regardless of supervisors’ gender or age. Overall, this research is part of the limited number of studies that have focused on the determining factors supervisors’ involvement in the learning transfer process.

Keywords: supervisor support, transfer of training, goal orientation, interest in the development of subordinates’ skills

Procedia PDF Downloads 191

Authors: Gaurav Kumar Sinha

Abstract:

The oil refining industry, significant in its energy consumption and carbon emissions, faces increasing pressure to reduce its environmental footprint. This article explores the application of energy efficiency and sustainability analytics as crucial tools for reducing carbon emissions in oil refineries. Through a comprehensive review of current practices and technologies, this study highlights innovative analytical approaches that can significantly enhance energy efficiency. We focus on the integration of advanced data analytics, including machine learning and predictive modeling, to optimize process controls and energy use. These technologies are examined for their potential to not only lower energy consumption but also reduce greenhouse gas emissions. Additionally, the article discusses the implementation of sustainability analytics to monitor and improve environmental performance across various operational facets of oil refineries. We explore case studies where predictive analytics have successfully identified opportunities for reducing energy use and emissions, providing a template for industry-wide application. The challenges associated with deploying these analytics, such as data integration and the need for skilled personnel, are also addressed. The paper concludes with strategic recommendations for oil refineries aiming to enhance their sustainability practices through the adoption of targeted analytics. By implementing these measures, refineries can achieve significant reductions in carbon emissions, aligning with global environmental goals and regulatory requirements.

Keywords: energy efficiency, sustainability analytics, carbon emissions, oil refineries, data analytics, machine learning, predictive modeling, process optimization, greenhouse gas reduction, environmental performance

Procedia PDF Downloads 34

Authors: Meherun Nahar

Abstract:

Background:The Chittagong Hill Tracts (CHT) is one of the most diverse regions in Bangladesh in terms of geography, ethnicity, culture and traditions of the people and home of thirteen indigenous ethnic people. In Bangladesh indigenous children aged 6-10 years remain out of school, and the majority of those who do enroll drop out before completing primary school. According to different study that the dropout rate of indigenous children is much higher than the estimated national rate, children dropping out especially in the early years of primary school. One of the most critical barriers for these children is that they do not understand the national language in the government pre-primary school. And also their school readiness and development become slower. In this situation, indigenous children excluded from the mainstream quality education. To address this issue Save the children in Bangladesh and other organizations are implementing community-based Mother Tongue-Based Multilingual Education program (MTBMLE) in the Chittagong Hill Tracts (CHT) for improving the enrolment rate in Government Primary Schools (GPS) reducing dropout rate as well as quality education. In connection with that Save the children conducted comparative research in Chittagong hill tracts on children readiness through Mother tongue-based and Non-mother tongue ECCD center. Objectives of the Study To assess Mother Language based ECCD centers and Non-Mother language based ECCD centers children’s school readiness and development. To assess the community perception over Mother Language based and Non-Mother Language based ECCD center. Methodology: The methodology of the study was FGD, KII, In-depth Interview and observation. Both qualitative and quantitative research methods were followed. The quantitative part has three components, School Readiness, Classroom observation and Headteacher interview and qualitative part followed FGD technique. Findings: The interviews with children under school readiness component showed that in general, Mother Language (ML) based ECCD children doing noticeably better in all four areas (Knowledge, numeracy, fine motor skill and communication) than their peers from Non-mother language based children. ML students seem to be far better skilled in concepts about print as most of them could identify cover and title of the book that was shown to them. They could also know from where to begin to read the book or could correctly point the letter that was read. A big difference was found in the area of identifying letters as 89.3% ML students of could identify letters correctly whereas for Non mother language 30% could do the same. The class room observation data shows that ML children are more active and remained engaged in the classroom than NML students. Also, teachers of ML appeared to have more engaged in explaining issues relating to general knowledge or leading children in rhyming/singing other than telling something from text books. The participants of FGDs were very enthusiastic on using mother language as medium of teaching in pre-schools. They opined that this initiative elates children to attend school and enables them to continue primary schooling without facing any language barrier.

Keywords: Chittagong hill tracts, early childhood care and development (ECCD), indigenous, mother language

Procedia PDF Downloads 120

Authors: Anita Chhatwal

Abstract:

Purpose: The purpose of this paper is to evaluate and investigate the scope of usage of Academic Social Networking Websites (ASNs) by the Science faculty members across universities of North India, viz. Panjab University, Punjabi University and University of Delhi, Delhi. Design/Methodology/Approach: The present study is based upon the primary data collected from 81 science faculty participants from three universities of North India. Questionnaire method was used as an instrument for survey. The study is descriptive and research-based to investigate the popular ASNs amongst the participants from three sample universities and the purpose for which they use them along with the problems they encounter while using ASNs. Findings: The findings of the study revealed that majority of the participants were using ASNs for their academic needs. It was observed that majority of the participants (78%) used ASNs to access scientific papers, while 73.8% of the participants used them to share their research publications. ResearchGate (60.5%) and Google Scholar (59.7%) were the top two most preferred and widely used ASNs by the participants. The critical analysis of the data shows that laptops (86.3%) emerged as major tools for accessing ASNs. Shortage of computers was found to be the chief obstacle in accessing ASNs by the participants. Results of the study demonstrate that 56.3% of participants suggested conduct of seminars and training as the most effective method to increase the awareness of ASNs. Research Limitations/Implications: The study in hand absorbed the 81 faculty (Assistant Professors) members from 15 Science teaching departments across three sample universities of North India. The findings of this study will help the Government of India to regulate and simultaneously make effort to develop and enhance ASNs usage among faculty, researchers, and students. The present study will add to the existing library and information science literature and will be advantageous for all the information professionals as well. Originality/Value: This study is original survey based on primary data investigate the usage of ASNs by the academia. This study will be useful for research scholars, academicians and students all over the world.

Keywords: academic social networks, awareness and usage, North India, scholarly communication, web 2.0

Procedia PDF Downloads 122

Authors: Duncan Wallace, M-Tahar Kechadi

Abstract:

In recent years, Machine Learning (ML) approaches have been successfully applied to an analysis of patient symptom data in the context of disease diagnosis, at least where such data is well codified. However, much of the data present in Electronic Health Records (EHR) are unlikely to prove suitable for classic ML approaches. Furthermore, as scores of data are widely spread across both hospitals and individuals, a decentralized, computationally scalable methodology is a priority. The focus of this paper is to develop a method to predict outliers in an out-of-hours healthcare provision center (OOHC). In particular, our research is based upon the early identification of patients who have underlying conditions which will cause them to repeatedly require medical attention. OOHC act as an ad-hoc delivery of triage and treatment, where interactions occur without recourse to a full medical history of the patient in question. Medical histories, relating to patients contacting an OOHC, may reside in several distinct EHR systems in multiple hospitals or surgeries, which are unavailable to the OOHC in question. As such, although a local solution is optimal for this problem, it follows that the data under investigation is incomplete, heterogeneous, and comprised mostly of noisy textual notes compiled during routine OOHC activities. Through the use of Deep Learning methodologies, the aim of this paper is to provide the means to identify patient cases, upon initial contact, which are likely to relate to such outliers. To this end, we compare the performance of Long Short-Term Memory, Gated Recurrent Units, and combinations of both with Convolutional Neural Networks. A further aim of this paper is to elucidate the discovery of such outliers by examining the exact terms which provide a strong indication of positive and negative case entries. While free-text is the principal data extracted from EHRs for classification, EHRs also contain normalized features. Although the specific demographical features treated within our corpus are relatively limited in scope, we examine whether it is beneficial to include such features among the inputs to our neural network, or whether these features are more successfully exploited in conjunction with a different form of a classifier. In this section, we compare the performance of randomly generated regression trees and support vector machines and determine the extent to which our classification program can be improved upon by using either of these machine learning approaches in conjunction with the output of our Recurrent Neural Network application. The output of our neural network is also used to help determine the most significant lexemes present within the corpus for determining high-risk patients. By combining the confidence of our classification program in relation to lexemes within true positive and true negative cases, with an inverse document frequency of the lexemes related to these cases, we can determine what features act as the primary indicators of frequent-attender and non-frequent-attender cases, providing a human interpretable appreciation of how our program classifies cases.

Keywords: artificial neural networks, data-mining, machine learning, medical informatics

Procedia PDF Downloads 134