Search results for: task based learning

Authors: Sara ElElimy, Samir Moustafa

Abstract:

Mobile network operators start to face many challenges in the digital era, especially with high demands from customers. Since mobile network operators are considered a source of big data, traditional techniques are not effective with new era of big data, Internet of things (IoT) and 5G; as a result, handling effectively different big datasets becomes a vital task for operators with the continuous growth of data and moving from long term evolution (LTE) to 5G. So, there is an urgent need for effective Big data analytics to predict future demands, traffic, and network performance to full fill the requirements of the fifth generation of mobile network technology. In this paper, we introduce data science techniques using machine learning and deep learning algorithms: the autoregressive integrated moving average (ARIMA), Bayesian-based curve fitting, and recurrent neural network (RNN) are employed for a data-driven application to mobile network operators. The main framework included in models are identification parameters of each model, estimation, prediction, and final data-driven application of this prediction from business and network performance applications. These models are applied to Telecom Italia Big Data challenge call detail records (CDRs) datasets. The performance of these models is found out using a specific well-known evaluation criteria shows that ARIMA (machine learning-based model) is more accurate as a predictive model in such a dataset than the RNN (deep learning model).

Keywords: big data analytics, machine learning, CDRs, 5G

Procedia PDF Downloads 137

Authors: Ruchi Makani, B. V. R. Reddy

Abstract:

Mobile Adhoc Networks (MANETs) are gaining popularity due to their potential of providing low-cost mobile connectivity solutions to real-world communication problems. Integrating Intrusion Detection Systems (IDS) in MANETs is a tedious task by reason of its distinctive features such as dynamic topology, de-centralized authority and highly controlled/limited resource environment. IDS primarily use automated soft-computing techniques to monitor the inflow/outflow of traffic packets in a given network to detect intrusion. Use of machine learning techniques in IDS enables system to make decisions on intrusion while continuous keep learning about their dynamic environment. An appropriate IDS model is essential to be selected to expedite this application challenges. Thus, this paper focused on fuzzy-logic based machine learning IDS technique for MANETs and presented their applicability for achieving effectiveness in identifying the intrusions. Further, the selection of appropriate protocol attributes and fuzzy rules generation plays significant role for accuracy of the fuzzy-logic based IDS, have been discussed. This paper also presents the critical attributes of MANET’s routing protocol and its applicability in fuzzy logic based IDS.

Keywords: AODV, mobile adhoc networks, intrusion detection, anomaly detection, fuzzy logic, fuzzy membership function, fuzzy inference system

Procedia PDF Downloads 174

Authors: Kumiko Inagaki

Abstract:

Qualitative changes to the undergraduate education have recently become the focus of attention in Japan. This is occurring against the backdrop of declining birthrate and increasing university enrollment, as well as drastic societal changes of advance toward globalization and a knowledge-based society. This paper describes the cases of Japanese universities that promoted various forms of experiential learning around the theme of social participation. The opportunity of learning through practical experience, where students turn their attention to social problems and take pains to consider means of resolving them, creates opportunities to demonstrate “human power” applicable to all sorts of activities the following graduation, thereby guaranteeing students’ continuous growth throughout their careers.

Keywords: career education, experiential learning, subjective learning, university education

Procedia PDF Downloads 306

Authors: Jie Liu, Xudong Luo, Pingping Lin, Yifan Fan

Abstract:

Facebook, Twitter, Weibo, and other social media and significant e-commerce sites generate a massive amount of online texts, which can be used to analyse people’s opinions or sentiments for better decision-making. So, sentiment analysis, especially fine-grained sentiment analysis, is a very active research topic. In this paper, we survey various methods for fine-grained sentiment analysis, including traditional sentiment lexicon-based methods, machine learning-based methods, and deep learning-based methods in aspect/target/attribute-based sentiment analysis tasks. Besides, we discuss their advantages and problems worthy of careful studies in the future.

Keywords: sentiment analysis, fine-grained, machine learning, deep learning

Procedia PDF Downloads 256

Authors: M. Sarrab, M. Elbasir

Abstract:

Most of mobile learning applications currently available are developed for the formal education and learning environment. Those applications are characterized by the improvement of the interaction process between instructors and learners to provide more collaboration and flexibility in the learning process. Despite the long history and large amount of research on Instruction design model and mobile learning there is no complete and well defined set of steps to follow in designing mobile learning applications. Based on this scenario, this paper focuses on identifying instruction design phases considerations and influencing factors in developing mobile learning application. This set of instruction design steps includes analysis, design, development, implementation, evaluation and continuous has been built from a literature study with focus on standards for learning and mobile application software quality and guidelines. The effort is part of an Omani-funded research project investigating the development, adoption and dissemination of mobile learning in Oman.

Keywords: instruction design, mobile learning, mobile application

Procedia PDF Downloads 598

Authors: Cristóbal Moënne-Loccoz, Rodrigo C. Vergara, Vladimir López, Domingo Mery, Diego Cosmelli

Abstract:

Our daily interaction with computational interfaces is plagued of situations in which we go from inexperienced users to experts through self-motivated exploration of the same task. In many of these interactions, we must learn to find our way through a sequence of decisions and actions before obtaining the desired result. For instance, when drawing cash from an ATM machine, choices are presented in a step-by-step fashion so that a specific sequence of actions must be performed in order to produce the expected outcome. But, as they become experts in the use of such interfaces, do users adopt specific search and learning strategies? Moreover, if so, can we use this information to follow the process of expertise development and, eventually, predict future actions? This would be a critical step towards building truly adaptive interfaces that can facilitate interaction at different moments of the learning curve. Furthermore, it could provide a window into potential mechanisms underlying decision-making behavior in real world scenarios. Here we tackle this question using a simple game interface that instantiates a 4-level binary decision tree (BDT) sequential decision-making task. Participants have to explore the interface and discover an underlying concept-icon mapping in order to complete the game. We develop a Hidden Markov Model (HMM)-based approach whereby a set of stereotyped, hierarchically related search behaviors act as hidden states. Using this model, we are able to track the decision-making process as participants explore, learn and develop expertise in the use of the interface. Our results show that partitioning the problem space into such stereotyped strategies is sufficient to capture a host of exploratory and learning behaviors. Moreover, using the modular architecture of stereotyped strategies as a Mixture of Experts, we are able to simultaneously ask the experts about the user's most probable future actions. We show that for those participants that learn the task, it becomes possible to predict their next decision, above chance, approximately halfway through the game. Our long-term goal is, on the basis of a better understanding of real-world decision-making processes, to inform the construction of interfaces that can establish dynamic conversations with their users in order to facilitate the development of expertise.

Keywords: behavioral modeling, expertise acquisition, hidden markov models, sequential decision-making

Procedia PDF Downloads 250

Authors: Nadia Soledad Peralta

Abstract:

Within the framework of socio-cognitive interaction, argumentation is understood as a psychological process that supports and induces reasoning and learning. Most authors emphasize the great potential of argumentation to negotiate with contradictions and complex decisions. So argumentation is a target for researchers who highlight the importance of social and cognitive processes in learning. In the context of social interaction among university students, different types of arguments are analyzed according to group size (dyads and triads) and the type of task (reading of frequency tables, causal explanation of physical phenomena, the decision regarding moral dilemma situations, and causal explanation of social phenomena). Eighty-nine first-year social sciences students of the National University of Rosario participated. Two groups were formed from the results of a pre-test that ensured the heterogeneity of points of view between participants. Group 1 consisted of 56 participants (performance in dyads, total: 28), and group 2 was formed of 33 participants (performance in triads, total: 11). A quasi-experimental design was performed in which effects of the two variables (group size and type of task) on the argumentation were analyzed. Three types of argumentation are described: authentic dialogical argumentative resolutions, individualistic argumentative resolutions, and non-argumentative resolutions. The results indicate that individualistic arguments prevail in dyads. That is, although people express their own arguments, there is no authentic argumentative interaction. Given that, there are few reciprocal evaluations and counter-arguments in dyads. By contrast, the authentically dialogical argument prevails in triads, showing constant feedback between participants’ points of view. It was observed that, in general, the type of task generates specific types of argumentative interactions. However, it is possible to emphasize that the authentically dialogic arguments predominate in the logical tasks, whereas the individualists or pseudo-dialogical are more frequent in opinion tasks. Nerveless, these relationships between task type and argumentative mode are best clarified in an interactive analysis based on group size. Finally, it is important to stress the value of dialogical argumentation in educational domains. Argumentative function not only allows a metacognitive reflection about their own point of view but also allows people to benefit from exchanging points of view in interactive contexts.

Keywords: sociocognitive interaction, argumentation, university students, size of the grup

Procedia PDF Downloads 78

Authors: Martina Holenko Dlab, Natasa Hoic-Bozic, Ivica Boticki

Abstract:

This paper presents technologically innovative and scalable mobile learning solution within the SCOLLAm project (“Opening up education through Seamless and COLLAborative mobile learning on tablet computers”). The main research method applied during the development of the SCOLLAm mobile learning system is design-based research. It assumes iterative refinement of the system guided by collaboration between researches and practitioners. Following the identification of requirements, a multiplatform mobile learning system SCOLLAm [in]Form was developed. Several experiments were designed and conducted in the first and second grade of elementary school. SCOLLAm [in]Form system was used to design learning activities for math classes during which students practice calculation. System refinements were based on experience and interaction data gathered during class observations. In addition to implemented improvements, the data were used to outline possible improvements and deficiencies of the system that should be addressed in the next phase of the SCOLLAm [in]Form development.

Keywords: adaptation, collaborative learning, educational technology, mobile learning, tablet computers

Procedia PDF Downloads 268

Authors: Joseph George, Anne Kotteswara Roa

Abstract:

Skin disease is one of the most common and popular kinds of health issues faced by people nowadays. Skin cancer (SC) is one among them, and its detection relies on the skin biopsy outputs and the expertise of the doctors, but it consumes more time and some inaccurate results. At the early stage, skin cancer detection is a challenging task, and it easily spreads to the whole body and leads to an increase in the mortality rate. Skin cancer is curable when it is detected at an early stage. In order to classify correct and accurate skin cancer, the critical task is skin cancer identification and classification, and it is more based on the cancer disease features such as shape, size, color, symmetry and etc. More similar characteristics are present in many skin diseases; hence it makes it a challenging issue to select important features from a skin cancer dataset images. Hence, the skin cancer diagnostic accuracy is improved by requiring an automated skin cancer detection and classification framework; thereby, the human expert’s scarcity is handled. Recently, the deep learning techniques like Convolutional neural network (CNN), Deep belief neural network (DBN), Artificial neural network (ANN), Recurrent neural network (RNN), and Long and short term memory (LSTM) have been widely used for the identification and classification of skin cancers. This survey reviews different DL techniques for skin cancer identification and classification. The performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measures are used to evaluate the effectiveness of SC identification using DL techniques. By using these DL techniques, the classification accuracy increases along with the mitigation of computational complexities and time consumption.

Keywords: skin cancer, deep learning, performance measures, accuracy, datasets

Procedia PDF Downloads 125

Authors: Madhavi-Priya Singh, Liam Lowe, Farouk Arnaout, Ludmilla Pillay, Giordan Perez, Luke Mischker, Steve Costa

Abstract:

Introduction: An Emergency Department consultant identified the failure of medical students to complete the task of clerking a patient in its entirety. As six medical students on our first clinical placement, we recognised our own failure and endeavored to examine why this failure was consistent among all medical students that had been given this task, despite our best motivations as adult learners. Aim: Our aim is to understand and investigate the elements which impeded our ability to learn and perform as medical students in the clinical environment, with reference to the prescribed task. We also aim to generate a discussion around the delivery of medical education with potential solutions to these barriers. Methods: Six medical students gathered together to have a comprehensive reflective discussion to identify possible factors leading to the failure of the task. First, we thoroughly analysed the delivery of the instructions with reference to the literature to identify potential flaws. We then examined personal, social, ethical, and cultural factors which may have impacted our ability to complete the task in its entirety. Results: Through collation of our shared experiences, with support from discussion in the field of medical education and ethics, we identified two major areas that impacted our ability to complete the set task. First, we experienced an ethical conflict where we believed the inconvenience and potential harm inflicted on patients did not justify the positive impact the patient interaction would have on our medical learning. Second, we identified a lack of confidence stemming from multiple factors, including the conflict between preclinical and clinical learning, perceptions of perfectionism in the culture of medicine, and the influence of upward social comparison. Discussion: After discussions, we found that the various factors we identified exacerbated the fears and doubts we already had about our own abilities and that of the medical education system. This doubt led us to avoid completing certain aspects of the tasks that were prescribed and further reinforced our vulnerability and perceived incompetence. Exploration of philosophical theories identified the importance of the role of doubt in education. We propose the need for further discussion around incorporating both pedagogic and andragogic teaching styles in clinical medical education and the acceptance of doubt as a driver of our learning. Conclusion: Doubt will continue to permeate our thoughts and actions no matter what. The moral or psychological distress that arises from this is the key motivating factor for our avoidance of tasks. If we accept this doubt and education embraces this doubt, it will no longer linger in the shadows as a negative and restrictive emotion but fuel a brighter dialogue and positive learning experience, ultimately assisting us in achieving our full potential.

Keywords: ethics, medical student, doubt, medical education, faith

Procedia PDF Downloads 103

Authors: Yuxuan Tang

Abstract:

Cognitive diagnostic assessment has received much attention in second language education, and assessment for it can provide pedagogically useful feedback for language learners. However, there is a lack of research on how students interpret and use cognitive diagnostic feedback. Thus the present study aims to adopt a mixed-method approach mainly to explore the relationship between the goal-orientation and students' response to cognitive diagnostic feedback. Almost 200 Chinese undergraduates from two universities in Xi'an, China, will be invited to do a cognitive diagnostic reading test, and each student will receive specialized cognitive diagnostic feedback, comprising of students' reading attributes mastery level generated by applying a well-selected cognitive diagnostic model, students' perceived reading ability assessed by a self-assessing questionnaire and students’ level position in the whole class. And a goal-orientation questionnaire and a self-generated questionnaire on the perception of feedback will be given to students the moment they receive feedback. In addition, interviews of students will be conducted on their future plans to see whether they have awareness of carrying out studying plans. The study aims to find a new perspective towards how students use and interpret cognitive diagnostic feedback in terms of their different goal-orientation (self-based, task-based, and other-based goals) by applying the newest goal orientation model, which is an important construct of motivation in psychology, seldom researched under language learning area. And the study is expected to provide evidence on how diagnostic feedback promotes students' learning under the educational belief of assessment for learning. Practically speaking, according to the personalized diagnostic feedback, students can take remedial self-learning more purposefully, and teachers can target students' weaknesses to adjust teaching methods and carry out tailored teaching.

Keywords: assessment for learning, cognitive diagnostic assessment, goal-orientation, personalized feedback

Procedia PDF Downloads 129

Authors: O. Bourkoukou, Essaid El Bachari

Abstract:

The group composing is one of the key issue in collaborative learning to achieve a positive educational experience. The goal of this work is to propose for teachers and tutors a method to create effective collaborative learning groups in e-learning environment based on the learner profile. For this purpose, a new function was defined to rate implicitly learning objects used by the learner during his learning experience. This paper describes the proposed algorithm to build an adequate collaborative learning group. In order to verify the performance of the proposed algorithm, several experiments were conducted in real data set in virtual environment. Results show the effectiveness of the method for which it appears that the proposed approach may be promising to produce better outcomes.

Keywords: building groups, collaborative learning, e-learning, learning objects

Procedia PDF Downloads 295

Authors: A. Meydanlioglu, F. Arikan

Abstract:

In recent years, thanks to the development of information and communication technologies, the computer and internet have been used widely in higher education. Internet-based education is impacting traditional higher education as online components increasingly become integrated into face-to-face (FTF) courses. The goal of combined internet-based and traditional education is to take full advantage of the benefits of each platform in order to provide an educational opportunity that can promote student learning better than can either platform alone. Research results show that the use of hybrid learning is more effective than online or FTF models in higher education. Due to the potential benefits, an increasing number of institutions are interested in developing hybrid courses, programs, and degrees. Future research should evaluate the effectiveness of hybrid learning. This paper is designed to determine the impact of hybrid learning on higher education.

Keywords: e-learning, higher education, hybrid learning, online education

Procedia PDF Downloads 902

Authors: Lei Zhang, Li Ji

Abstract:

Formal learning and informal learning represent two distinct learning styles: one is systematic and organized, another is causal and unstructured. Although there are many factors influencing online learning satisfaction, including self-regulation, self-efficacy, and interaction, factors influencing online formal learning and informal learning satisfaction may differ from each other. This paper investigated and compared influential factors of online formal and informal learning. Two questionnaires were created based on previous studies to explore factors influencing online formal learning and online informal learning satisfaction, respectively. A sample of 105 college students from different departments in a university located in the eastern part of China was selected to participate in this study. They all had an online learning experience and agreed to fill out questionnaires. Correlation analysis, variance analysis, and regression analysis were employed in this study. In addition, five participants were chosen for interviews. The study found that student-content, interaction, self-regulation, and self-efficacy related positively to both online formal learning and informal learning satisfaction. In addition, compared to online formal learning, student-content interaction in informal learning was the most influential factor for online learning satisfaction, perhaps that online informal learning was more goal-oriented and learners paid attention to the quality of content. In addition, results also revealed that interactions among students or teachers had little impact on online informal learning satisfaction. This study compared influential factors in online formal and informal learning satisfaction helped to add discussions to online learning satisfaction and contributed to further practices of online learning.

Keywords: learning satisfaction, formal learning, informal learning, online learning

Procedia PDF Downloads 159

Authors: Somtop Keawchuer

Abstract:

This research aims to study (1) the relationship between competency-based learning and learning efficiency of new media communication students at Suan Sunandha University (2) the demographic factor effect on learning efficiency of students at Suan Sunandha University. This research method will use quantitative research; data was collected by questionnaires distributed to students from new media communication in management science faculty of Suan Sunandha Rajabhat University for 1340 sample by purposive sampling method. Data was analyzed by descriptive statistic including percentage, mean, standard deviation and inferential statistic including T-test, ANOVA and Pearson correlation for hypothesis testing. The results showed that the competency-based learning in term of ability to communicate, ability to think and solve the problem, life skills and ability to use technology has a significant relationship with learning efficiency in term of the cognitive domain, psychomotor domain and affective domain at the 0.05 level and which is in harmony with the research hypotheses.

Keywords: competency-based learning, learning efficiency, new media communication students, Suan Sunandha Rajabhat University

Procedia PDF Downloads 239

Authors: Jiaqi Huang, Yuheng Wang

Abstract:

Premises selection, the task of selecting a set of axioms for proving a given conjecture, is a major bottleneck in automated theorem proving. An array of deep-learning-based methods has been established for premises selection, but a perfect performance remains challenging. Our study examines the inaccuracy of deep neural networks in premises selection. Through training network models using encoded conjecture and axiom pairs from the Mizar Mathematical Library, two potential biases are found: the network models classify more premises as necessary than unnecessary, referred to as the ‘positive bias’, and the network models perform better in proving conjectures that paired with more axioms, referred to as ‘length bias’. The ‘positive bias’ and ‘length bias’ discovered could inform the limitation of existing deep neural networks.

Keywords: automated theorem proving, premises selection, deep learning, interpreting deep learning

Procedia PDF Downloads 179

Authors: Hao-Hsi Tseng, Hsin-Yun Lee, Yu-Cheng Kuo

Abstract:

In order to understand whether there is a better than the learning function of learning methods and improve the CAD Courses for enterprise’s design human resource development, this research is applied in learning practical learning computer graphics software. In this study, Revit building information model for learning content, design of two different modes of learning curriculum to learning, learning functions, respectively, and project learning. Via a post-test, questionnaires and student interviews, etc., to study the effectiveness of a comparative analysis of two different modes of learning. Students participate in a period of three weeks after a total of nine-hour course, and finally written and hands-on test. In addition, fill in the questionnaire response by the student learning, a total of fifteen questionnaire title, problem type into the base operating software, application software and software-based concept features three directions. In addition to the questionnaire, and participants were invited to two different learning methods to conduct interviews to learn more about learning students the idea of two different modes. The study found that the ad hoc short-term courses in learning, better learning outcomes. On the other hand, functional style for the whole course students are more satisfied, and the ad hoc style student is difficult to accept the ad hoc style of learning.

Keywords: development, education, human resource, learning

Procedia PDF Downloads 356

Authors: Catherine Thompson, Maryam Jalali, Peter Hills

Abstract:

The allocation of visual attention is critical when driving and anything that limits attention will have a detrimental impact on safety. Engaging in a secondary task reduces the amount of attention directed to the road because drivers allocate resources towards this task, leaving fewer resources to process driving-relevant information. Yet the dangers associated with a secondary task do not end when the driver returns their attention to the road. Instead, the attentional settings adopted to complete a secondary task may persist to the road, affecting attention, and therefore affecting driver performance. This 'attentional inertia' effect was investigated in the current work. Forty drivers searched for hazards in driving video clips while their eye-movements were recorded. At varying intervals they were instructed to attend to a secondary task displayed on a tablet situated to their left-hand side. The secondary task consisted of three separate computer games that induced horizontal, vertical, and random eye movements. Visual search and hazard detection in the driving clips were compared across the three conditions of the secondary task. Results showed that the layout of information in the secondary task, and therefore the allocation of attention in this task, had an impact on subsequent search in the driving clips. Vertically presented information reduced the wide horizontal spread of search usually associated with accurate driving and had a negative influence on the detection of hazards. The findings show the additional dangers of engaging in a secondary task while driving. The attentional inertia effect has significant implications for semi-autonomous and autonomous vehicles in which drivers have greater opportunity to direct their attention away from the driving task.

Keywords: attention, eye-movements, hazard perception, visual search

Procedia PDF Downloads 160

Authors: C. Maphosa, Ndileleni Mudzielwana, Lufuno Phillip Netshifhefhe

Abstract:

In line with established mission and vision, a university articulates its focus and purpose of existence. The conduct of business in a university should be for the furtherance of the mission and vision. Teaching and learning should play a pivotal role in driving the purpose of a university. In this paper, the researchers examine how service learning could be significant in driving the purpose of a rural-based university whose focus is to promote rural development. The importance of institutions’ vision and mission statement is explored and the vision and mission of the said university examined closely. The concept rural development and the contribution of a university in its promotion is discussed. Service learning as a teaching and learning approach is examined and its significance in driving the purpose of a rural-based university explained.

Keywords: relevance, differentiation, purpose, teaching, learning

Procedia PDF Downloads 312

Authors: Sebastián Olivares Lizana, Marianna Oyanedel González

Abstract:

This study takes part of a major project based on implementing a CLIL program (Content and Language Integrated Learning) at Universidad Técnica Federico Santa María, a leading Chilean tertiary Institution. It aims at examining the relationship between the development of Reflective Processes (RP) and Cognitive Academic Language Proficiency (CALP) in weekly learning logs written by faculty members, participants of an initial professional development online course on English for Academic Purposes (EAP). Such course was designed with a genre-based approach, and consists of multiple tasks directed to academic writing proficiency. The results of this analysis will be described and classified in a scale of key indicators that represent both the Reflective Processes and the advances in CALP, and that also consider linguistic proficiency and task progression. Such indicators will evidence affordances and constrains of using a genre-based approach in an EFL Engineering CLIL program implementation at tertiary level in Chile, and will serve as the starting point to the design of a professional development course directed to teaching methodologies in a CLIL EFL environment in Engineering education at Universidad Técnica Federico Santa María.

Keywords: EFL, EAL, genre, CLIL, engineering

Procedia PDF Downloads 392

Authors: Hyeongbok Kim, Lingling Zhao, Xiaohong Su

Abstract:

Deep reinforcement learning has been applied to address various problems in robotics, such as autonomous driving and unmanned aerial vehicle. However, because of the sparse reward penalty for a collision with obstacles during the navigation mission, the agent fails to learn the optimal policy or requires a long time for convergence. Therefore, using obstacles and enemy agents, in this paper, we present a curriculum-based boost learning method to effectively train compound skills during multi-agent reinforcement learning. First, to enable the agents to solve challenging tasks, we gradually increased learning difficulties by adjusting reward shaping instead of constructing different learning environments. Then, in a benchmark environment with static obstacles and moving enemy agents, the experimental results showed that the proposed curriculum learning strategy enhanced cooperative navigation and compound collision avoidance skills in uncertain environments while improving learning efficiency.

Keywords: curriculum learning, hard exploration, multi-agent reinforcement learning, robotic navigation, sparse reward

Procedia PDF Downloads 87

Authors: Tian Lan, Yixiang Wang, Wenxin Tai, Yilan Lyu, Zufeng Wu

Abstract:

The monaural speech enhancement task in the time-frequencydomain has a myriad of approaches, with the stacked con-volutional neural network (CNN) demonstrating superiorability in feature extraction and selection. However, usingstacked single convolutions method limits feature represen-tation capability and generalization ability. In order to solvethe aforementioned problem, we propose an attention-basedadaptive convolutional network that integrates the multi-scale convolutional operations into a operation-specific blockvia input dependent attention to adapt to complex auditoryscenes. In addition, we introduce a two-stage progressivelearning method to enlarge the receptive field without a dra-matic increase in computation burden. We conduct a series ofexperiments based on the TIMIT corpus, and the experimen-tal results prove that our proposed model is better than thestate-of-art models on all metrics.

Keywords: speech enhancement, adaptive convolu-tion, progressive learning, time-frequency domain

Procedia PDF Downloads 118

Authors: Ma. Gracia Corazon Cayanan, Kai Yuen Cheong, Li Sha

Abstract:

Training a language model for a minority language has been a challenging task. The lack of available corpora to train and fine-tune state-of-the-art language models is still a challenge in the area of Natural Language Processing (NLP). Moreover, the need for high computational resources and bulk data limit the attainment of this task. In this paper, we presented the following contributions: (1) we introduce and used a translation pair set of Tagalog and English (TL-EN) in pre-training a language model to a minority language resource; (2) we fine-tuned and evaluated top-ranking and pre-trained semantic textual similarity binary task (STSB) models, to both TL-EN and STS dataset pairs. (3) then, we reduced the size of the model to offset the need for high computational resources. Based on our results, the models that were pre-trained to translation pairs and STS pairs can perform well for STSB task. Also, having it reduced to a smaller dimension has no negative effect on the performance but rather has a notable increase on the similarity scores. Moreover, models that were pre-trained to a similar dataset have a tremendous effect on the model’s performance scores.

Keywords: semantic matching, semantic textual similarity binary task, low resource minority language, fine-tuning, dimension reduction, transformer models

Procedia PDF Downloads 201

Authors: Chalise Kiran

Abstract:

The learning difficulties of children with disabilities are always a matter of concern when we talk about educational needs and quality education of children with disabilities. This paper is the outcome of the review of the literatures based on the literatures on the educational needs and learning difficulties of children with disabilities. For the paper, different studies written on children with disabilities and their education were collected through search engines. The literature put together was analyzed from the angle of learning difficulties faced by children with disabilities and the same were used as a precursor to arrive at the findings on the learning of the children. The analysis showed that children with disabilities face learning difficulties. The reasons for these difficulties could be attributed to factors in terms of authority, structure, school environment, and behaviors of teachers and parents, and the society as a whole.

Keywords: children with disabilities, learning difficulties, education, disabled children

Procedia PDF Downloads 109

Authors: YuLung Wu, YuTien Wu, ShuMey Yu

Abstract:

Game-based learning can enhance the learning motivation of students and provide a means for them to learn through playing games. This study used augmented reality technology to develop an interactive card game as a game-based teaching aid for delivering elementary school science course content with the aim of enhancing student learning processes and outcomes. Through playing the proposed card game, students can familiarize themselves with appearance, features, and foraging behaviors of insects. The system records the actions of students, enabling teachers to determine their students’ learning progress. In this study, 37 students participated in an assessment experiment and provided feedback through questionnaires. Their responses indicated that they were significantly more motivated to learn after playing the game, and their feedback was mostly positive.

Keywords: game-based learning, learning motivation, teaching aid, augmented reality

Procedia PDF Downloads 372

Authors: Ajay Krishan Tiwari

Abstract:

Studies on educational psychology have demonstrated the interest of the child's psychological and cognitive environment in the quality of their school commitment. The educational psychologist works with children and adolescents to remedy these factors. The task of the educational psychologist is to liberate the child and adolescent intellectually. Its purpose is to harmonize the child with the system of learning. Psychoanalytic support requires practice in creativity, reading, math, and meditation methods. The goal of educational psychology is to restore the desire and enjoyment of learning. The educational psychologist takes into account the concerns and personality traits that hinder student learning and restores self-esteem. Educational psychologists specialize in supporting children or adolescents who have a different approach to learning. Its role is to consider the child as a whole (cognitive, affective, physical, school, family factors, etc.). It welcomes the child's way of thinking and participates in its development. It is an essential point of contact between the child and his school environment.

Keywords: educational psychology, educational theories, psychologist, cognitive environment, psychoanalytic support, enjoyment of learning

Procedia PDF Downloads 71

Authors: Jennifer Fane, Mike Gray, Melissa Sager

Abstract:

Children with diagnosed or suspected learning disabilities frequently experience significant skill gaps in foundational learning areas such as reading, writing, and math. Remedial one-to-one instruction is a highly effective means of supporting children with learning differences in building these foundational skills and closing the learning gap between them and their same-age peers. However, due to the learning challenges children with learning disabilities face, and ensuing challenges with self-confidence, many children with learning differences struggle with motivation and self-regulation within remedial one-to-one learning environments - despite the benefits of these sessions. Socially Assistive Robots (SARs) are an innovative educational technology tool that has been trialled in a range of educational settings to support diverse learning needs. Yet, little is known about the impact of SARs on the learning of children with learning differences in a one-to-one remedial instructional setting. This study sought to explore the impact of SARs on the engagement of children (n=9) with learning differences attending one-to-one remedial instruction sessions at a non-profit remedial education provider. The study used a mixed-methods design to explore learner engagement during learning tasks both with and without the use of a SAR to investigate how the use of SARs impacts student learning. The study took place over five weeks, with each session within the study followed the same procedure with the SAR acting as a teaching assistant when in use. Data from the study included analysis of time-sample video segments of the instructional sessions, instructor recorded information about the student’s progress towards their session learning goal and student self-reported mood and energy levels before and after the session. Analysis of the findings indicates that the use of SARs resulted in fewer instances of off-task behaviour and less need for instructor re-direction during learning tasks, allowing students to work in more sustained ways towards their learning goals. This initial research indicates that the use of SARs does have a material and measurable impact on learner engagement for children with learning differences and that further exploration of the impact of SARs during one-to-one remedial instruction is warranted.

Keywords: engagement, learning differences, learning disabilities, instruction, social robotics.

Procedia PDF Downloads 211

Authors: Sanchali Das, Swapan Debbarma

Abstract:

Music mood classification is developing in both the areas of music information retrieval (MIR) and natural language processing (NLP). Some of the Indian languages like Hindi English etc. have considerable exposure in MIR. But research in mood classification in regional language is very less. In this paper, powerful audio based feature for Kokborok Christian song is identified and mood classification task has been performed. Kokborok is an Indo-Burman language especially spoken in the northeastern part of India and also some other countries like Bangladesh, Myanmar etc. For performing audio-based classification task, useful audio features are taken out by jMIR software. There are some standard audio parameters are there for the audio-based task but as known to all that every language has its unique characteristics. So here, the most significant features which are the best fit for the database of Kokborok song is analysed. The regression-based model is used to find out the independent parameters that act as a predictor and predicts the dependencies of parameters and shows how it will impact on overall classification result. For classification WEKA 3.5 is used, and selected parameters create a classification model. And another model is developed by using all the standard audio features that are used by most of the researcher. In this experiment, the essential parameters that are responsible for effective audio based mood classification and parameters that do not significantly change for each of the Christian Kokborok songs are analysed, and a comparison is also shown between the two above model.

Keywords: Christian Kokborok song, mood classification, music information retrieval, regression

Procedia PDF Downloads 216

Authors: Patricia M. Boechler, Heather M. Gautreau

Abstract:

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

Keywords: avatar-based, virtual environment, paired learning, individual differences

Procedia PDF Downloads 112

Authors: Lizhi Ma, Dan Liu

Abstract:

Pipeline parallelism has been widely used to accelerate distributed deep learning to alleviate GPU memory bottlenecks and to ensure that models can be trained and deployed smoothly under limited graphics memory conditions. However, in highly heterogeneous distributed clusters, traditional model partitioning methods are not able to achieve load balancing. The overlap of communication and computation is also a big challenge. In this paper, HePipe is proposed, an efficient pipeline parallel training method for highly heterogeneous clusters. According to the characteristics of the neural network model pipeline training task, oriented to the 2-level heterogeneous cluster computing topology, a training method based on the 2-level stage division of neural network modeling and partitioning is designed to improve the parallelism. Additionally, a multi-forward 1F1B scheduling strategy is designed to accelerate the training time of each stage by executing the computation units in advance to maximize the overlap between the forward propagation communication and backward propagation computation. Finally, a dynamic recomputation strategy based on task memory requirement prediction is proposed to improve the fitness ratio of task and memory, which improves the throughput of the cluster and solves the memory shortfall problem caused by memory differences in heterogeneous clusters. The empirical results show that HePipe improves the training speed by 1.6×−2.2× over the existing asynchronous pipeline baselines.

Keywords: pipeline parallelism, heterogeneous cluster, model training, 2-level stage partitioning

Procedia PDF Downloads 11