Search results for: language acquisition and learning

Authors: Sankalp Devanand, Prateek Agasimani, Shamith V. S., Rohith Neeraje

Abstract:

Machine translation has witnessed significant advancements in recent years, but the translation of languages with distinct linguistic characteristics, such as English and Sanskrit, remains a challenging task. This research presents the development of a dedicated English-to-Sanskrit machine translation model, aiming to bridge the linguistic and cultural gap between these two languages. Using a variety of natural language processing (NLP) approaches, including FastText embeddings, this research proposes a thorough method to improve word meaning retrieval. Data preparation, part-of-speech tagging, dictionary searches, and transliteration are all included in the methodology. The study also addresses the implementation of an interpreter pattern and uses a word similarity task to assess the quality of word embeddings. The experimental outcomes show how the suggested approach may be used to enhance word meaning retrieval tasks with greater efficacy, accuracy, and adaptability. Evaluation of the model's performance is conducted through rigorous testing, comparing its output against existing machine translation systems. The assessment includes quantitative metrics such as BLEU scores, METEOR scores, Jaccard Similarity, etc.

Keywords: machine translation, English to Sanskrit, natural language processing, word meaning retrieval, fastText embeddings

Procedia PDF Downloads 44

Authors: Jeff Dickie

Abstract:

This research paper combined grounded coding and research questions with the objective to investigate conflict resolution in the classroom. The students’ answers concerning teaching were coded according to phrasal meanings which revealed concepts. These concept codes then became input data into theoretical frameworks. The investigation indicated two conflicts: whether the information was valid and whether to make the study effort which was discussed as perceptions of teacher’s competence in helping to learn. The relevant factors in helping to learn were predominately emotional. These factors were important in the negotiation process to develop relationships. Information validity seemed to be the motivator to begin and participate effectively with the learning process. In effect, confidence in the learning negotiation process with the focus towards relationship building with the subject matter seemed to be the motivator to make the study effort.

Keywords: coding, confidence, competence, conflict resolution, risk, trust, relationship building

Procedia PDF Downloads 431

Authors: Gabrielle Brand, Christopher Etherton-Beer

Abstract:

The learning landscape of higher education environment is changing, with an increased focus over the past decade on how educators might begin to cultivate reflective skills in health professions students. In addition, changing professional requirements demand that health professionals are adequately prepared to practice in today’s complex Australian health care systems, including responding to changing demographics of population ageing. To counteract a widespread perception of health professions students’ disinterest in caring for older persons, the authors will report on an exploratory, mixed method research study that used photographs, narrative and small group work to enhance medical and nursing students’ reflective learning experience. An innovative photo-elicitation technique and reflective questioning prompts were used to increase engagement, and challenge students to consider new perspectives (around ageing) by constructing shared storylines in small groups. The qualitative themes revealed how photographs, narratives and small group work created learning spaces for reflection whereby students could safely explore their own personal and professional values, beliefs and perspectives around ageing. By providing the space for reflection, the students reported how they found connection and meaning in their own learning through a process of self-exploration that often challenged their assumptions of both older people and themselves as future health professionals. By integrating cognitive and affective elements into the learning process, this research demonstrates the importance of embedding visual methodologies that enhance reflection and transformative learning. The findings highlight the importance of integrating the arts into predominantly empirically driven health professional curricula and can be used as a catalyst for individual and/or collective reflection which can potentially enhance empathy, insight and understanding of the lived experiences of older patients. Based on these findings, the authors have developed ‘Depth of Field: Exploring Ageing’ an innovative, interprofessional, digital reflective learning resource that uses Prezi Inc. software (storytelling tool that presents ideas on a virtual canvas) to enhance students’ reflective capacity in the higher education environment.

Keywords: narrative, photo-elicitation, reflective learning, qualitative research

Procedia PDF Downloads 285

Authors: Abdulmajid Mukhtar Afat

Abstract:

This paper aims at introducing nondeterministic finite automata with ε value which is used to perform some operations on languages. a program is created to implement the algorithm that converts nondeterministic finite automata with ε value (ε-NFA) to deterministic finite automata (DFA).The program is written in c++ programming language. The program inputs are FA 5-tuples from text file and then classifies it into either DFA/NFA or ε -NFA. For DFA, the program will get the string w and decide whether it is accepted or rejected. The tracking path for an accepted string is saved by the program. In case of NFA or ε-NFA automation, the program changes the automation to DFA to enable tracking and to decide if the string w exists in the regular language or not.

Keywords: DFA, NFA, ε-NFA, eclose, finite automata, operations on languages

Procedia PDF Downloads 489

Authors: Saadia Elamin

Abstract:

The quasi-universal use of smart phones with internet connection available all the time makes it a reflex action for translation undergraduates, once they encounter the least translation problem, to turn to the freely available web resource: Google Translate. Like for other translator resources and aids, the use of Google Translate needs to be moderated in such a way that it contributes to developing translation competence. Here, instead of interfering with students’ learning by providing ready-made solutions which might not always fit into the contexts of use, it can help to consolidate the skills of analysis and transfer which students have already acquired. One way to do so is by training students to adhere to the basic principles of translation work. The most important of these is that analyzing the source text for comprehension comes first and foremost before jumping into the search for target language equivalents. Another basic principle is that certain translator aids and tools can be used for comprehension, while others are to be confined to the phase of re-expressing the meaning into the target language. The present paper reports on the experience of making a measured and reasonable use of Google Translate in translation teaching at Prince Sultan University (PSU), Riyadh. First, it traces the development that has taken place in the field of translation in this age of information technology, be it in translation teaching and translator training, or in the real-world practice of the profession. Second, it describes how, with the aim of reflecting this development onto the way translation is taught, senior students, after being trained on post-editing machine translation output, are authorized to use Google Translate in classwork and assignments. Third, the paper elaborates on the findings of this case study which has demonstrated that Google Translate, if used at the appropriate levels of training, can help to enhance students’ ability to perform different translation tasks. This help extends from the search for terms and expressions, to the tasks of drafting the target text, revising its content and finally editing it. In addition, using Google Translate in this way fosters a reflexive and critical attitude towards web resources in general, maximizing thus the benefit gained from them in preparing students to meet the requirements of the modern translation job market.

Keywords: Google Translate, post-editing machine translation output, principles of translation work, translation competence, translation teaching, translator aids and tools

Procedia PDF Downloads 473

Authors: Catherine Mary Abou-Zaid

Abstract:

This quantitative study discusses the concerns with the self-directed learning (SDL) skills of the undergraduate nursing students in a medical university in Bahrain. The nursing undergraduate student SDL study was conducted taking all 4 years and compiling data collected from the students themselves by survey questionnaire. The aim of the study is to understand and change the attitudes of self-directed learning among the undergraduate students. The SDL of the undergraduate student nurses has been noticed to be lacking and motivation to actually perform without supervision while out-with classrooms are very low. Their use of the resources available on the virtual learning environment and also within the university is not as good as it should be for a university student at this level. They do not use them to their own advantage. They are not prepared for the transition from high school to an academic environment such as a university or college. For some students it is the first time in their academic lives that they have faced sharing a classroom with the opposite sex. For some this is a major issue and we as academics need to be aware of all issues that they come to higher education with. Design Methodology: The design methodology that was chosen was a quantitative design using convenience sampling of the students who would be asked to complete survey questionnaire. This sampling method was chosen because of the time constraint. This was completed by the undergraduate students themselves while in class. The questionnaire was analyzed by the statistical package for social sciences (SPSS), the results interpreted by the researcher and the findings published in the paper. The analyzed data will also be reported on and from this information we as educators will be able to see the student’s weaknesses regarding self-directed learning. The aims and objectives of the research will be used as recommendations for the improvement of resources for the students to improve their SDL skills. Conclusion: The results will be able to give the educators an insight to how we can change the self-directed learning techniques of the students and enable them to embrace the skills and to focus more on being self-directed in their studies rather than having to be put on to a SDL pathway from the educators themselves. This evidence will come from the analysis of the statistical data. It may even change the way in which the students are selected for the nursing programme. These recommendations will be reported to the head of school and also to the nursing faculty.

Keywords: self-directed learning, undergraduate students, transition, statistical package for social sciences (SPSS), higher education

Procedia PDF Downloads 315

Authors: Jonathan May

Abstract:

This paper argues that the value of games relates to the sensation of freedom they create, and this in turn results from their nature as voluntary, non-necessary tasks. Attempts to gamify necessary learning tasks are therefore challenged to create this sensation of freedom and so they often fail to create the pleasure and value found in traditional games. It then demonstrates a route to creating this sensation of freedom through the maximization of varied and creative solutions to such problems.

Keywords: gamification, games, philosophy of games, freedom, voluntary action, necessity, motivation, value of games

Procedia PDF Downloads 177

Authors: Adedoyin Opeyemi Osokoya

Abstract:

The study assesses the influence of social media on perceived learning outcome of agricultural science students in tertiary institutions in Oyo state, Nigeria. The four-stage sampling procedure was used to select participants. All students in the seven tertiary institutions that offer agriculture science as a course of study in Oyo State was the population. A university, a college of agriculture and a college of education were sampled, and a department from each was randomly selected. Twenty percent of the students’ population in the respective selected department gave a sample size of 165. Questionnaire was used to collect information on respondents’ personal characteristics and information related to access to social media. Data were analysed using descriptive statistics, chi-square, correlation, and multiple regression at the 0.05 confidence level. Age and household size were 21.13 ± 2.64 years and 6 ± 2.1 persons respectively. All respondents had access to social media, majority (86.1%) owned Android phone, 57.6% and 52.7% use social media for course work and entertainment respectively, while the commonly visited sites were WhatsApp, Facebook, Google, Opera mini. Over half (53.9%) had an unfavourable attitude towards the use of social media for learning; benefits of the use of social media for learning was high (56.4%). Removal of information barrier created by distance (x̄=1.58) was the most derived benefit, while inadequate power supply (x̄=2.36), was the most severe constraints. Age (β=0.23), sex (β=0.37), ownership of Android phone (β=-1.29), attitude (β=0.37), constraints (β =-0.26) and use of social media (β=0.23) were significant predictors of influence on perceived learning outcomes.

Keywords: use of social media, agricultural science students, undergraduates of tertiary institutions, Oyo State of Nigeria

Procedia PDF Downloads 140

Authors: Wayne DeFehr

Abstract:

This study is rooted in a pedagogical approach that emphasizes student engagement as fundamental to meaningful learning in the classroom. This approach creates a paradigmatic shift, from a teaching practice that reinforces the teacher’s central authority to a practice that disperses that authority among the students in the classroom through networks that they themselves develop. The methodology of this study about creating optimal conditions for learning in the classroom includes providing a conceptual framework within which the students work, as well as providing clearly stated expectations for work standards, content quality, group methodology, and learning outcomes. These learning conditions are nurtured in a variety of ways. First, nearly every class includes a lecture from the professor with key concepts that students need in order to complete their work successfully. Secondly, students build on this scholarly material by forming their own networks, where students face each other and engage with each other in order to collaborate their way to solving a particular problem relating to the course content. Thirdly, students are given short, medium, and long-term goals. Short term goals relate to the week’s topic and involve workshopping particular issues relating to that stage of the course. The medium-term goals involve students submitting term assignments that are evaluated according to a well-defined rubric. And finally, long-term goals are achieved by creating a capstone project, which is celebrated and shared with classmates and interested friends on the final day of the course. The essential conclusions of the study are drawn from courses that focus on video game narrative. Enthusiastic student engagement is created not only with the dynamic energy and expertise of the instructor, but also with the inter-dependence of the students on each other to build knowledge, acquire skills, and achieve successful results.

Keywords: collaboration, education, learning networks, video games

Procedia PDF Downloads 116

Authors: Seun Mayowa Sunday

Abstract:

Loan prediction is one of the most significant and recognised fields of research in the banking, insurance, and the financial security industries. Some prediction systems on the market include the construction of static software. However, due to the fact that static software only operates with strictly regulated rules, they cannot aid customers beyond these limitations. Application of many machine learning (ML) techniques are required for loan prediction. Four separate machine learning models, random forest (RF), decision tree (DT), k-nearest neighbour (KNN), and logistic regression, are used to create the loan prediction model. Using the anaconda navigator and the required machine learning (ML) libraries, models are created and evaluated using the appropriate measuring metrics. From the finding, the random forest performs with the highest accuracy of 80.17% which was later implemented into the Django framework. For real-time testing, the web application is deployed on the Alibabacloud which is among the top 4 biggest cloud computing provider. Hence, to the best of our knowledge, this research will serve as the first academic paper which combines the model development and the Django framework, with the deployment into the Alibaba cloud computing application.

Keywords: k-nearest neighbor, random forest, logistic regression, decision tree, django, cloud computing, alibaba cloud

Procedia PDF Downloads 136

Authors: Musatafa Abbas Abbood Albadr, Masri Ayob, Sabrina Tiun, Fahad Taha Al-Dhief, Mohammad Kamrul Hasan

Abstract:

Breast Cancer (BC) is considered one of the most frequent reasons of cancer death in women between 40 to 55 ages. The BC is diagnosed by using digital images of the FNA (Fine Needle Aspirate) for both benign and malignant tumors of the breast mass. Therefore, this work proposes the Online Sequential Extreme Learning Machine (OSELM) algorithm for diagnosing BC by using the tumor features of the breast mass. The current work has used the Wisconsin Diagnosis Breast Cancer (WDBC) dataset, which contains 569 samples (i.e., 357 samples for benign class and 212 samples for malignant class). Further, numerous measurements of assessment were used in order to evaluate the proposed OSELM algorithm, such as specificity, precision, F-measure, accuracy, G-mean, MCC, and recall. According to the outcomes of the experiment, the highest performance of the proposed OSELM was accomplished with 97.66% accuracy, 98.39% recall, 95.31% precision, 97.25% specificity, 96.83% F-measure, 95.00% MCC, and 96.84% G-Mean. The proposed OSELM algorithm demonstrates promising results in diagnosing BC. Besides, the performance of the proposed OSELM algorithm was superior to all its comparatives with respect to the rate of classification.

Keywords: breast cancer, machine learning, online sequential extreme learning machine, artificial intelligence

Procedia PDF Downloads 111

Authors: Kavian Khosravinia, Mohd Khair Hassan, Ribhan Zafira Abdul Rahman, Syed Abdul Rahman Al-Haddad

Abstract:

The CAN (controller area network) bus is introduced as a multi-master, message broadcast system. The messages sent on the CAN are used to communicate state information, referred as a signal between different ECUs, which provides data consistency in every node of the system. OBD-II Dongles that are based on request and response method is the wide-spread solution for extracting sensor data from cars among researchers. Unfortunately, most of the past researches do not consider resolution and quantity of their input data extracted through OBD-II technology. The maximum feasible scan rate is only 9 queries per second which provide 8 data points per second with using ELM327 as well-known OBD-II dongle. This study aims to develop and design a programmable, and latency-sensitive vehicle data acquisition system that improves the modularity and flexibility to extract exact, trustworthy, and fresh car sensor data with higher frequency rates. Furthermore, the researcher must break apart, thoroughly inspect, and observe the internal network of the vehicle, which may cause severe damages to the expensive ECUs of the vehicle due to intrinsic vulnerabilities of the CAN bus during initial research. Desired sensors data were collected from various vehicles utilizing Raspberry Pi3 as computing and processing unit with using OBD (request-response) and direct CAN method at the same time. Two types of data were collected for this study. The first, CAN bus frame data that illustrates data collected for each line of hex data sent from an ECU and the second type is the OBD data that represents some limited data that is requested from ECU under standard condition. The proposed system is reconfigurable, human-readable and multi-task telematics device that can be fitted into any vehicle with minimum effort and minimum time lag in the data extraction process. The standard operational procedure experimental vehicle network test bench is developed and can be used for future vehicle network testing experiment.

Keywords: CAN bus, OBD-II, vehicle data acquisition, connected cars, telemetry, Raspberry Pi3

Procedia PDF Downloads 205

Authors: Mei-Chun Chang

Abstract:

Due to digital transformation and social media development in recent years, various real-time interactive digital tools have been developed to meet the design demands for virtual reality avatars, which also promote digital content learners' active participation in the creation process. As a result, new social media design tools have the characteristics of intuitive operation with a simplified interface for fast production, from which works can be simply created. This study carried out observations, records, questionnaire surveys, and interviews on the creation and learning of visual avatars made by students of the National Taiwan University of Science and Technology (NTUST) with the VRoid Studio 3D modeling tool so as to explore their learning effectiveness on the design of visual avatars. According to the results of this study, the VRoid Studio 3D character modeling tool has a positive impact on the learners and helps to improve their learning effectiveness. Students with low academic achievements said that they could complete the conceived modeling with their own thinking by using the design tool, which increased their sense of accomplishment. Conclusions are drawn according to the results, and relevant future suggestions are put forward.

Keywords: virtual avatar, character design, social media, vroid studio, creation, digital learning

Procedia PDF Downloads 190

Authors: Micah Amor P. Yares

Abstract:

Aside from the provision of adequate housing, the Philippine government faces the challenge of ensuring that the housing units provided conform to the Filipino’s ambition to self as manifested by owning a small house on a big lot. The study aimed to explore the levels of satisfaction of end-users and the public perception towards socialized housing in Davao City, Philippines. The residential satisfaction survey includes three types of respondents, which are end-users of single-detached, duplex and rowhouse socialized housing units. Respondents were asked to rate their level of satisfaction and perception to the following housing components: Dwelling Unit; Public Facilities; Social Environment; Neighborhood Facilities; Management Systems; and Acquisition and Financing. The data were subjected to Exploratory Factor Analysis to determine if variables can be grouped together, and Confirmatory Factor Analysis to measure if the model fits the construct. In determining which component affects the level of perception and satisfaction, a Multiple Linear Regression Analysis was employed. Lastly, an Individual Samples T-Test was performed to compare the levels of satisfaction and perception among respondents. Results revealed that residents of socialized housing were highly satisfied with their living conditions despite concerns on management systems, public and neighborhood facilities. Residents' satisfaction is primarily influenced by the Social Environment, Acquisition and Financing, and the Dwelling Unit. However, a significant difference in residential satisfaction level was observed among different types of housing with rowhouse residents recording the lowest satisfaction level compared to single-detached and duplex units. Moreover, the general public perceived Socialized housing as moderately satisfactory having the same determinant as the end-users aside from the Public Facilities. This study recommends revisiting the current Socialized Housing policies by considering the feedback from the end-users based on their lived experience and the public according to their perception.

Keywords: public perception, residential satisfaction, rowhouse, socialized housing

Procedia PDF Downloads 237

Authors: Jay L. Fu

Abstract:

Patients with Alzheimer's disease progressively lose their memory and thinking skills and, eventually, the ability to carry out simple daily tasks. The disease is irreversible, but early detection and treatment can slow down the disease progression. In this research, publicly available MRI data and demographic data from 373 MRI imaging sessions were utilized to build models to predict dementia. Various machine learning models, including logistic regression, k-nearest neighbor, support vector machine, random forest, and neural network, were developed. Data were divided into training and testing sets, where training sets were used to build the predictive model, and testing sets were used to assess the accuracy of prediction. Key risk factors were identified, and various models were compared to come forward with the best prediction model. Among these models, the random forest model appeared to be the best model with an accuracy of 90.34%. MMSE, nWBV, and gender were the three most important contributing factors to the detection of Alzheimer’s. Among all the models used, the percent in which at least 4 of the 5 models shared the same diagnosis for a testing input was 90.42%. These machine learning models allow early detection of Alzheimer’s with good accuracy, which ultimately leads to early treatment of these patients.

Keywords: Alzheimer's disease, clinical diagnosis, magnetic resonance imaging, machine learning prediction

Procedia PDF Downloads 143

Authors: Mona Hoyng

Abstract:

In times of digitalization nowadays, the use of games became a crucial new way for digital game-based learning (DGBL) in higher education. In this regard, the development of a gameful experience (GE) among students is decisive when examining DGBL as the GE is a necessary precondition determining the effectiveness of games. In this regard, the purpose of this study is to provide deeper insights into the GE and to empirically investigate whether and how these meaningful learning experiences within games, i.e., GE, among students are created. Based on the theory of experience and flow theory, a double-mediation model was developed considering instructional support, group engagement, and flow as determinants of students’ GE. Based on data of 337 students taking part in a business simulation game at two different universities in Germany, regression-based statistical mediation analysis revealed that instructional support promoted students’ GE. This relationship was further sequentially double mediated by group engagement and flow. Consequently, in the context of DGBL, meaningful learning experiences within games in terms of GE are created and promoted through appropriate instructional support, as well as high levels of group engagement and flow among students.

Keywords: gameful experience, instructional support, group engagement, flow, education, learning

Procedia PDF Downloads 136

Authors: N. Hammid, F. Bouarab-Dahmani, T. Berkane

Abstract:

Since its appearance, the MOOC (massive open online course) is gaining more and more intention of the educational communities over the world. Apart from the current MOOCs design and purposes, the creators of MOOC focused on the importance of the connection and knowledge exchange between individuals in learning. In this paper, we present a conceptual model for massive open online blended courses where teachers over the world can collaborate and exchange their experience to get a common efficient content designed as a MOOC opened to their students to live a better learning experience. This model is based on disciplines’ concepts capitalization and the detection of the obstacles met by their students when faced with problem situations (exercises, projects, case studies, etc.). This detection is possible by analyzing the frequently of semantic errors committed by the students. The participation of teachers in the design of the course and the attendance by their students can guarantee an efficient and extensive participation (an important number of participants) in the course, the learners’ motivation and the evaluation issues, in the way that the teachers designing the course assess their students. Thus, the teachers review, together with their knowledge, offer a better assessment and efficient connections to their students.

Keywords: massive open online course, MOOC, online learning, e-learning

Procedia PDF Downloads 268

Authors: Ahmad Salman

Abstract:

Electronic Response Systems such as Kahoot, Poll Everywhere, and Google Classroom are gaining a lot of popularity when surveying audiences in events, meetings, and classroom. The reason is mainly because of the ease of use and the convenience these tools bring since they provide mobile applications with a simple user interface. In this paper, we present a case study on the effectiveness of using Electronic Response Systems on student participation and learning experience in a classroom. We use a polling application for class exercises in two different technology-oriented classes. We evaluate the effectiveness of the usage of the polling applications through statistical analysis of the students performance in these two classes and compare them to the performances of students who took the same classes without using the polling application for class participation. Our results show an increase in the performances of the students who used the Electronic Response System when compared to those who did not by an average of 11%.

Keywords: Interactive Learning, Classroom Technology, Electronic Response Systems, Polling Applications, Learning Evaluation

Procedia PDF Downloads 129

Authors: Shams Ul Hussain Zaheer, Bibi Alia, Shehla Shams

Abstract:

With the creation of human beings, almost all of them are blessed with the award of the power of expression, and this series starts from the life of Adam (A.S) in Paradise when he was blesses with language and knowledge and given priority upon the Angels. Later on, when the population spread and many other languages came into being, the method of the different people of different regions remained various. And when the Arabic was formed as a language after Ismail (A.S) and his sons spread in the gulf area, the words adopted from other gulf languages also became a part of this new language with it immense. Beside this, the tone of expression in other areas of the word was different, but the incidents, norms of bad and good, parameters for like and dislike, thinking styles, and rules of good and bad governance with social values remained round about the same. People practiced their lives according to the set norms everywhere in the world. Especially the two built, i.e., Hijaz and Khurasan, wherein Arabs and Pashtun accordingly were dwelling; it seems that their social values were much closed to each other. These norms reflect in various kinds of literature of both of the nations, but this article deals in with their proverbs specifically. This article discusses the intellectual telepathic between them in a research way. And put the defined similarities and dissimilarities between both in the proverb. And it also draws a sketch in front of readers that how the thinking and expression styles remains same in humans. As it belongs to a comparative analysis of the proverbs so, the same methodology has been adopted in the articles.

Keywords: intellectual telepathy, hijaz, arab, khurasan, pashtun, proverbs, comparison

Procedia PDF Downloads 89

Authors: Tracy B.E. Omorogiuwa

Abstract:

Understanding the role of social work in improving societal well-being cannot be separated from the place of field education, which is an integral aspect of social work education. Field learning provides students with knowledge and opportunities to experience solving issues in the field and giving them a clue of the practice situation. Despite being a crucial component in social work curriculum, field education occupies a large space in learning outcome, given the issues and challenges pertaining to its purpose and significance in the society. The drive of this paper is to provide insight on the specific ways in which field education has been conceived, realized and valued in the society. Emphasis is on the significance of field instruction; the link with classroom learning; and the structure of field experience in social work education. Given documented analysis and experience, this study intends to contribute to the development of social work curriculum, by analyzing the pattern, issues and challenges fronting the social work field education in the University of Benin, Nigeria.

Keywords: challenges, curriculum, field education, social work education

Procedia PDF Downloads 299

Authors: M. Draman, S. Z. Muhamad Yassin, M. S. Alias, Z. Lambak, M. I. Zulkifli, S. N. Padhi, K. N. Baharim, F. Maskuriy, A. I. A. Rahim

Abstract:

The performance of Malay automatic speech recognition (ASR) system for the call centre environment is presented. The system utilizes Kaldi toolkit as the platform to the entire library and algorithm used in performing the ASR task. The acoustic model implemented in this system uses a deep neural network (DNN) method to model the acoustic signal and the standard (n-gram) model for language modelling. With 80 hours of training data from the call centre recordings, the ASR system can achieve 72% of accuracy that corresponds to 28% of word error rate (WER). The testing was done using 20 hours of audio data. Despite the implementation of DNN, the system shows a low accuracy owing to the varieties of noises, accent and dialect that typically occurs in Malaysian call centre environment. This significant variation of speakers is reflected by the large standard deviation of the average word error rate (WERav) (i.e., ~ 10%). It is observed that the lowest WER (13.8%) was obtained from recording sample with a standard Malay dialect (central Malaysia) of native speaker as compared to 49% of the sample with the highest WER that contains conversation of the speaker that uses non-standard Malay dialect.

Keywords: conversational speech recognition, deep neural network, Malay language, speech recognition

Procedia PDF Downloads 322

Authors: Daniele Traversaro

Abstract:

Problem: Senior citizens have been facing a challenging reality as a result of strict public health measures designed to protect people from the COVID-19 outbreak. These include the risk of social isolation due to the inability of the elderly to integrate with technology. Never before have information and communication technology (ICT) skills become essential for their everyday life. Although third-age ICT education and lifelong learning are widely supported by universities and governments, there is a lack of literature on which teaching strategy/methodology to adopt in an entirely online ICT course aimed at third-age learners. This contribution aims to present an application of the Think-Pair-Share (TPS) learning method in an ICT third-age virtual classroom with an intergenerational approach to conducting online group labs and review activities. This collaborative strategy can help increase student engagement, promote active learning and online social interaction. Research Question: Is collaborative learning applicable and effective, in terms of student engagement and learning outcomes, for an entirely online third-age ICT introductory course? Methods: In the TPS strategy, a problem is posed by the teacher, students have time to think about it individually, and then they work in pairs (or small groups) to solve the problem and share their ideas with the entire class. We performed four experiments in the ICT course of the University of the Third Age of Genova (University of Genova, Italy) on the Microsoft Teams platform. The study cohort consisted of 26 students over the age of 45. Data were collected through online questionnaires. Two have been proposed, one at the end of the first activity and another at the end of the course. They consisted of five and three close-ended questions, respectively. The answers were on a Likert scale (from 1 to 4) except two questions (which asked the number of correct answers given individually and in groups) and the field for free comments/suggestions. Results: Results show that groups perform better than individual students (with scores greater than one order of magnitude) and that most students found it helpful to work in groups and interact with their peers. Insights: From these early results, it appears that TPS is applicable to an online third-age ICT classroom and useful for promoting discussion and active learning. Despite this, our experimentation has a number of limitations. First of all, the results highlight the need for more data to be able to perform a statistical analysis in order to determine the effectiveness of this methodology in terms of student engagement and learning outcomes as a future direction.

Keywords: collaborative learning, information technology education, lifelong learning, older adult education, think-pair-share

Procedia PDF Downloads 188

Authors: Vinayaka Gude Divya Sampath

Abstract:

The research introduces an integrated prediction model to assess the susceptibility of roads in a future flooding event. The model consists of deep learning algorithm for forecasting gauge height data and Flood Inundation Mapper (FIM) for spatial flooding. An optimal architecture for Long short-term memory network (LSTM) was identified for the gauge located on Tangipahoa River at Robert, LA. Dropout was applied to the model to evaluate the uncertainty associated with the predictions. The estimates are then used along with FIM to identify the spatial flooding. Further geoprocessing in ArcGIS provides the susceptibility values for different roads. The model was validated based on the devastating flood of August 2016. The paper discusses the challenges for generalization the methodology for other locations and also for various types of flooding. The developed model can be used by the transportation department and other emergency response organizations for effective disaster management.

Keywords: deep learning, disaster management, flood prediction, urban flooding

Procedia PDF Downloads 147

Authors: Linghui Meng, James Atlas, Deborah Munro

Abstract:

There is an increasing demand for prosthetics capable of mimicking natural limb movements and hand gestures, but precise movement control of prosthetics using only electrode signals continues to be challenging. This study considers the implementation of machine learning as a means of improving accuracy and presents an initial investigation into hand gesture recognition using models based on electromyographic (EMG) signals. EMG signals, which capture muscle activity, are used as inputs to machine learning algorithms to improve prosthetic control accuracy, functionality and adaptivity. Using logistic regression, a machine learning classifier, this study evaluates the accuracy of classifying two hand gestures from the publicly available Ninapro dataset using two-time series feature extraction algorithms: Time Series Feature Extraction (TSFE) and Convolutional Neural Networks (CNNs). Trials were conducted using varying numbers of EMG channels from one to eight to determine the impact of channel quantity on classification accuracy. The results suggest that although both algorithms can successfully distinguish between hand gesture EMG signals, CNNs outperform TSFE in extracting useful information for both accuracy and computational efficiency. In addition, although more channels of EMG signals provide more useful information, they also require more complex and computationally intensive feature extractors and consequently do not perform as well as lower numbers of channels. The findings also underscore the potential of machine learning techniques in developing more effective and adaptive prosthetic control systems.

Keywords: EMG, machine learning, prosthetic control, electromyographic prosthetics, hand gesture classification, CNN, computational neural networks, TSFE, time series feature extraction, channel count, logistic regression, ninapro, classifiers

Procedia PDF Downloads 31

Authors: Samuel Faboyede, Obiamaka Nwobu, Samuel Fakile, Dickson Mukoro

Abstract:

In the present dynamic business environment of corporate governance and regulations, financial reporting is an inevitable and extremely significant process for every business enterprise. Several financial elements such as Annual Reports, Quarterly Reports, ad-hoc filing, and other statutory/regulatory reports provide vital information to the investors and regulators, and establish trust and rapport between the internal and external stakeholders of an organization. Investors today are very demanding, and emphasize greatly on authenticity, accuracy, and reliability of financial data. For many companies, the Internet plays a key role in communicating business information, internally to management and externally to stakeholders. Despite high prominence being attached to external reporting, it is disconnected in most companies, who generate their external financial documents manually, resulting in high degree of errors and prolonged cycle times. Chief Executive Officers and Chief Financial Officers are increasingly susceptible to endorsing error-laden reports, late filing of reports, and non-compliance with regulatory acts. There is a lack of common platform to manage the sensitive information – internally and externally – in financial reports. The Internet financial reporting language known as eXtensible Business Reporting Language (XBRL) continues to develop in the face of challenges and has now reached the point where much of its promised benefits are available. This paper looks at the emergence of this revolutionary twenty-first century language of digital reporting. It posits that today, the world is on the brink of an Internet revolution that will redefine the ‘business reporting’ paradigm. The new Internet technology, eXtensible Business Reporting Language (XBRL), is already being deployed and used across the world. It finds that XBRL is an eXtensible Markup Language (XML) based information format that places self-describing tags around discrete pieces of business information. Once tags are assigned, it is possible to extract only desired information, rather than having to download or print an entire document. XBRL is platform-independent and it will work on any current or recent-year operating system, or any computer and interface with virtually any software. The paper concludes that corporate stakeholders and the government cannot afford to ignore the XBRL. It therefore recommends that all must act locally and think globally now via the adoption of XBRL that is changing the face of worldwide business reporting.

Keywords: XBRL, financial reporting, internet, internal and external reports

Procedia PDF Downloads 286

Authors: Xin Li, Ji-Yang Yu, Yue-Hua Niu, Lu-Yuan Wang

Abstract:

As an inevitable chain of the space data acquirement system, space-borne storage system based on Nand Flash has gradually been implemented in spacecraft. In face of massive, parallel and varied data on board, efficient data management become an important issue of storage research. Face to the requirements of high-performance and reliability in Nand Flash storage system, a combination of hardware and file system design can drastically increase system dependability, even for missions with a very long duration. More sophisticated flash storage concepts with advanced operating systems have been researched to improve the reliability of Nand Flash storage system on satellites. In this paper, architecture of file system with multi-channel data acquisition and storage on board is proposed, which obtains large-capacity and high-performance with the combine of intra-channel pipeline and device partition in Nand Flash. Multi-channel data in different rate are stored as independent files with parallel-storage system in device partition, which assures the high-effective and reliable throughput of file treatments. For massive and high-speed data storage, an efficiency assessment model is established to calculate the bandwidth formula of intra-channel pipeline. Information tables designed in Magnetoresistive RAM (MRAM) hold the management of bad block in Nand Flash and the arrangement of file system address for the high-reliability of data storage. During the full-load test, the throughput of 3D PLUS Module 160Gb Nand Flash can reach 120Mbps for store and reach 120Mbps for playback, which efficiently satisfies the requirement of multi-channel data acquisition in Satellite. Compared with previous literature, the results of experiments verify the advantages of the proposed system.

Keywords: device partition architecture, intra-channel pipelining, nand flash, parallel storage

Procedia PDF Downloads 289

Authors: Adrià Arbués-Sangüesa, Coloma Ballester, Gloria Haro

Abstract:

Tracking sports players is a widely challenging scenario, specially in single-feed videos recorded in tight courts, where cluttering and occlusions cannot be avoided. This paper presents an analysis of several geometric and semantic visual features to detect and track basketball players. An ablation study is carried out and then used to remark that a robust tracker can be built with Deep Learning features, without the need of extracting contextual ones, such as proximity or color similarity, nor applying camera stabilization techniques. The presented tracker consists of: (1) a detection step, which uses a pretrained deep learning model to estimate the players pose, followed by (2) a tracking step, which leverages pose and semantic information from the output of a convolutional layer in a VGG network. Its performance is analyzed in terms of MOTA over a basketball dataset with more than 10k instances.

Keywords: basketball, deep learning, feature extraction, single-camera, tracking

Procedia PDF Downloads 138

Authors: Dorit Alt, Nirit Raichel

Abstract:

Educational practice is continually subjected to renewal needs, due mainly to the growing proportion of information communication technology, globalization of education, and the pursuit of quality. These types of renewal needs require developing updated instructional and assessment practices that put a premium on adaptability to the emerging requirements of present society. However, university instruction is criticized for not coping with these new challenges while continuing to exemplify the traditional instruction. In order to overcome this critical inadequacy between current educational goals and instructional methods, the LLAF consortium (including 16 members from 8 countries) is collaborating to create a curricular reform for lifelong learning (LLL) in teachers' education, health care and other applied fields. This project aims to achieve its objectives by developing, and piloting models for training students in LLL and promoting meaningful learning activities that could integrate knowledge with the personal transferable skills. LLAF has created a practical guide for teachers containing updated pedagogical strategies and assessment tools based on the constructivist approach for learning. This presentation will be limited to teachers' education only and to the contribution of a pre-pilot research aimed at providing a scale designed to measure constructivist activities in higher education learning environments. A mix-method approach was implemented in two phases to construct the scale: The first phase included a qualitative content analysis involving both deductive and inductive category applications of students' observations. The results foregrounded eight categories: knowledge construction, authenticity, multiple perspectives, prior knowledge, in-depth learning, teacher- student interaction, social interaction and cooperative dialogue. The students' descriptions of their classes were formulated as 36 items. The second phase employed structural equation modeling (SEM). The scale was submitted to 597 undergraduate students. The goodness of fit of the data to the structural model yielded sufficient fit results. This research elaborates the body of literature by adding a category of in-depth learning which emerged from the content analysis. Moreover, the theoretical category of social activity has been extended to include two distinctive factors: cooperative dialogue and social interaction. Implications of these findings for the LLAF project are discussed.

Keywords: constructivist learning, higher education, mix-methodology, lifelong learning

Procedia PDF Downloads 334

Authors: Jie Zhang, Qianyu Guo, Tieyi Zhang, Zhiyong Feng, Xiaohong Li

Abstract:

With the widespread popularity of mobile devices and the development of artificial intelligence (AI), deep learning (DL) has been extensively applied in Android apps. Compared with traditional Android apps (traditional apps), deep learning based Android apps (DL-based apps) need to use more third-party application programming interfaces (APIs) to complete complex DL inference tasks. However, existing methods (e.g., FlowDroid) for detecting sensitive information leakage in Android apps cannot be directly used to detect DL-based apps as they are difficult to detect third-party APIs. To solve this problem, we design DLtrace; a new static information flow analysis tool that can effectively recognize third-party APIs. With our proposed trace and detection algorithms, DLtrace can also efficiently detect privacy leaks caused by sensitive APIs in DL-based apps. Moreover, using DLtrace, we summarize the non-sequential characteristics of DL inference tasks in DL-based apps and the specific functionalities provided by DL models for such apps. We propose two formal definitions to deal with the common polymorphism and anonymous inner-class problems in the Android static analyzer. We conducted an empirical assessment with DLtrace on 208 popular DL-based apps in the wild and found that 26.0% of the apps suffered from sensitive information leakage. Furthermore, DLtrace has a more robust performance than FlowDroid in detecting and identifying third-party APIs. The experimental results demonstrate that DLtrace expands FlowDroid in understanding DL-based apps and detecting security issues therein.

Keywords: mobile computing, deep learning apps, sensitive information, static analysis

Procedia PDF Downloads 179

Authors: M. Varin, A. M. Dubois, R. Gadbois-Langevin, B. Chalghaf

Abstract:

Good knowledge of the physical environment is essential for an integrated forest planning. This information enables better forecasting of operating costs, determination of cutting volumes, and preservation of ecologically sensitive areas. The use of satellite images in stereoscopic pairs gives the capacity to generate high precision 3D models, which are scale-adapted for harvesting operations. These models could represent an alternative to 3D LiDAR data, thanks to their advantageous cost of acquisition. The objective of the study was to assess the quality of stereo-derived canopy height models (CHM) in comparison to a traditional LiDAR CHM and ground tree-height samples. Two study sites harboring two different forest stand types (broadleaf and conifer) were analyzed using stereo pairs and tri-stereo images from the WorldView-3 satellite to calculate CHM. Acquisition of multispectral images from an Unmanned Aerial Vehicle (UAV) was also realized on a smaller part of the broadleaf study site. Different algorithms using two softwares (PCI Geomatica and Correlator3D) with various spatial resolutions and band selections were tested to select the 3D modeling technique, which offered the best performance when compared with LiDAR. In the conifer study site, the CHM produced with Corelator3D using only the 50-cm resolution panchromatic band was the one with the smallest Root-mean-square deviation (RMSE: 1.31 m). In the broadleaf study site, the tri-stereo model provided slightly better performance, with an RMSE of 1.2 m. The tri-stereo model was also compared to the UAV, which resulted in an RMSE of 1.3 m. At individual tree level, when ground samples were compared to satellite, lidar, and UAV CHM, RMSE were 2.8, 2.0, and 2.0 m, respectively. Advanced analysis was done for all of these cases, and it has been noted that RMSE is reduced when the canopy cover is higher when shadow and slopes are lower and when clouds are distant from the analyzed site.

Keywords: very high spatial resolution, satellite imagery, WorlView-3, canopy height models, CHM, LiDAR, unmanned aerial vehicle, UAV

Procedia PDF Downloads 127