Search results for: quest based learning
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32288

Search results for: quest based learning

31688 The Value of Dynamic Priorities in Motor Learning between Some Basic Skills in Beginner's Basketball, U14 Years

Authors: Guebli Abdelkader, Regiueg Madani, Sbaa Bouabdellah

Abstract:

The goals of this study are to find ways to determine the value of dynamic priorities in motor learning between some basic skills in beginner’s basketball (U14), based on skills of shooting and defense against the shooter. Our role is to expose the statistical results in compare & correlation between samples of study in tests skills for the shooting and defense against the shooter. In order to achieve this objective, we have chosen 40 boys in middle school represented in four groups, two controls group’s (CS1, CS2) ,and two experimental groups (ES1: training on skill of shooting, skill of defense against the shooter, ES2: experimental group training on skill of defense against the shooter, skill of shooting). For the statistical analysis, we have chosen (F & T) tests for the statistical differences, and test (R) for the correlation analysis. Based on the analyses statistics, we confirm the importance of classifying priorities of basketball basic skills during the motor learning process. Admit that the benefits of experimental group training are to economics in the time needed for acquiring new motor kinetic skills in basketball. In the priority of ES2 as successful dynamic motor learning method to enhance the basic skills among beginner’s basketball.

Keywords: basic skills, basketball, motor learning, children

Procedia PDF Downloads 170
31687 Malaria Parasite Detection Using Deep Learning Methods

Authors: Kaustubh Chakradeo, Michael Delves, Sofya Titarenko

Abstract:

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

Keywords: convolution neural network, deep learning, malaria, thin blood smears

Procedia PDF Downloads 130
31686 A Learning Automata Based Clustering Approach for Underwater ‎Sensor Networks to Reduce Energy Consumption

Authors: Motahareh Fadaei

Abstract:

Wireless sensor networks that are used to monitor a special environment, are formed from a large number of sensor nodes. The role of these sensors is to sense special parameters from ambient and to make connection. In these networks, the most important challenge is the management of energy usage. Clustering is one of the methods that are broadly used to face this challenge. In this paper, a distributed clustering protocol based on learning automata is proposed for underwater wireless sensor networks. The proposed algorithm that is called LA-Clustering forms clusters in the same energy level, based on the energy level of nodes and the connection radius regardless of size and the structure of sensor network. The proposed approach is simulated and is compared with some other protocols with considering some metrics such as network lifetime, number of alive nodes, and number of transmitted data. The simulation results demonstrate the efficiency of the proposed approach.

Keywords: clustering, energy consumption‎, learning automata, underwater sensor networks

Procedia PDF Downloads 314
31685 iSEA: A Mobile Based Learning Application for History and Culture Knowledge Enhancement for the ASEAN Region

Authors: Maria Visitacion N. Gumabay, Byron Joseph A. Hallar, Annjeannette Alain D. Galang

Abstract:

This study was intended to provide a more efficient and convenient way for mobile users to enhance their knowledge about ASEAN countries. The researchers evaluated the utility of the developed crossword puzzle application and assessed the general usability of its user interface for its intended purpose and audience of users. The descriptive qualitative research method for the research design and the Mobile-D methodology was employed for the development of the software application output. With a generally favorable reception from its users, the researchers concluded that the iSEA Mobile Based Learning Application can be considered ready for general deployment and use. It was also concluded that additional studies can also be done to make a more complete assessment of the knowledge gained by its users before and after using the application.

Keywords: mobile learning, eLearning, crossword, ASEAN, iSEA

Procedia PDF Downloads 313
31684 Teaching, Learning and Evaluation Enhancement of Information Communication Technology Education in Schools through Pedagogical and E-Learning Techniques in the Sri Lankan Context

Authors: M. G. N. A. S. Fernando

Abstract:

This study uses a researchable framework to improve the quality of ICT education and the Teaching Learning Assessment/ Evaluation (TLA/TLE) process. It utilizes existing resources while improving the methodologies along with pedagogical techniques and e-Learning approaches used in the secondary schools of Sri Lanka. The study was carried out in two phases. Phase I focused on investigating the factors which affect the quality of ICT education. Based on the key factors of phase I, the Phase II focused on the design of an Experimental Application Model with 6 activity levels. Each Level in the Activity Model covers one or more levels in the Revised Bloom’s Taxonomy. Towards further enhancement of activity levels, other pedagogical techniques (activity based learning, e-learning techniques, problem solving activities and peer discussions etc.) were incorporated to each level in the activity model as appropriate. The application model was validated by a panel of teachers including a domain expert and was tested in the school environment too. The validity of performance was proved using 6 hypotheses testing and other methodologies. The analysis shows that student performance with problem solving activities increased by 19.5% due to the different treatment levels used. Compared to existing process it was also proved that the embedded techniques (mixture of traditional and modern pedagogical methods and their applications) are more effective with skills development of teachers and students.

Keywords: activity models, Bloom’s taxonomy, ICT education, pedagogies

Procedia PDF Downloads 163
31683 Haptic Cycle: Designing Enhanced Museum Learning Activities

Authors: Menelaos N. Katsantonis, Athanasios Manikas, Alexandros Chatzis, Stavros Doropoulos, Anastasios Avramis, Ioannis Mavridis

Abstract:

Museums enhance their potential by adopting new technologies and techniques to appeal to more visitors and engage them in creative and joyful activities. In this study, the Haptic Cycle is presented, a cycle of museum activities proposed for the development of museum learning approaches with optimized effectiveness and engagement. Haptic Cycle envisages the improvement of the museum’s services by offering a wide range of activities. Haptic Cycle activities make the museum’s exhibitions more approachable by bringing them closer to the visitors. Visitors can interact with the museum’s artifacts and explore them haptically and sonically. Haptic Cycle proposes constructivist learning activities in which visitors actively construct their knowledge by exploring the artifacts, experimenting with them and realizing their importance. Based on the Haptic Cycle, we developed the HapticSOUND system, an innovative virtual reality system that includes an advanced user interface that employs gesture-based technology. HapticSOUND’s interface utilizes the leap motion gesture recognition controller and a 3D-printed traditional Cretan lute, utilized by visitors to perform various activities such as exploring the lute and playing notes and songs.

Keywords: haptic cycle, HapticSOUND, museum learning, gesture-based, leap motion

Procedia PDF Downloads 91
31682 Design of a Professional Development Framework in Teaching and Learning for Engineering Educators

Authors: Orla McConnell, Cormac MacMahon, Jen Harvey

Abstract:

Ireland’s national professional development framework for those who teach in higher education, aims to provide guidance and leadership in the planning, developing and engaging in professional development practices. A series of pilot projects have been initiated to help explore the framework’s likely utility and acceptance by educators and their institutions. These projects require engagement with staff in the interpretation and adaption of the framework within their working contexts. The purpose of this paper is to outline the development of one such project with engineering educators at three Institutes of Technology seeking designation as a technological university. The initiative aims to gain traction in the acceptance of the framework with the engineering education community by linking core and discipline-specific teaching and learning competencies with professional development activities most valued by engineering educators. Informed by three strands of literature: professional development in higher education; engineering education; and teaching and learning training provisions, the project begins with a survey of all those involved in teaching and learning in engineering across the three institutes. Based on engagement with key stakeholders, subsequent qualitative research informs the contextualization of the national framework for discipline-specific and institutional piloting. The paper concludes by exploring engineering educator perceptions of the national framework’s utility based on their engagement with the pilot process. Feedback from the pilot indicates that there is a significant gap between the professional development needs of engineering educators and the current professional development provision in teaching and learning.

Keywords: engineering education, pilot, professional development, teaching and learning

Procedia PDF Downloads 330
31681 Automatic Number Plate Recognition System Based on Deep Learning

Authors: T. Damak, O. Kriaa, A. Baccar, M. A. Ben Ayed, N. Masmoudi

Abstract:

In the last few years, Automatic Number Plate Recognition (ANPR) systems have become widely used in the safety, the security, and the commercial aspects. Forethought, several methods and techniques are computing to achieve the better levels in terms of accuracy and real time execution. This paper proposed a computer vision algorithm of Number Plate Localization (NPL) and Characters Segmentation (CS). In addition, it proposed an improved method in Optical Character Recognition (OCR) based on Deep Learning (DL) techniques. In order to identify the number of detected plate after NPL and CS steps, the Convolutional Neural Network (CNN) algorithm is proposed. A DL model is developed using four convolution layers, two layers of Maxpooling, and six layers of fully connected. The model was trained by number image database on the Jetson TX2 NVIDIA target. The accuracy result has achieved 95.84%.

Keywords: ANPR, CS, CNN, deep learning, NPL

Procedia PDF Downloads 306
31680 Online Teaching and Learning Processes: Declarative and Procedural Knowledge

Authors: Eulalia Torras, Andreu Bellot

Abstract:

To know whether students’ achievements are the result of online interaction and not just a consequence of individual differences themselves, it seems essential to link the teaching presence and social presence to the types of knowledge built. The research aim is to analyze the social presence in relation to two types of knowledge, declarative and procedural. Qualitative methodology has been used. The analysis of the contents was based on an observation protocol that included community of enquiry indicators and procedural and declarative knowledge indicators. The research has been conducted in three phases that focused on an observational protocol and indicators, results and conclusions. Results show that the teaching-learning processes have been characterized by the patterns of presence and types of knowledge. Results also show the importance of social presence support provided by the teacher and the students, not only in regard to the nature of the instructional support but also concerning how it is presented to the student and the importance that is attributed to it in the teaching-learning process, that is, what it is that assistance is offered on. In this study, we find that the presence based on procedural guidelines and declarative reflection, the management of shared meaning on the basis of the skills and the evidence of these skills entail patterns of learning. Nevertheless, the importance that the teacher attributes to each support aspect has a bearing on the extent to which the students reflect more on the given task.

Keywords: education, online, teaching and learning processes, knowledge

Procedia PDF Downloads 216
31679 Learning to Translate by Learning to Communicate to an Entailment Classifier

Authors: Szymon Rutkowski, Tomasz Korbak

Abstract:

We present a reinforcement-learning-based method of training neural machine translation models without parallel corpora. The standard encoder-decoder approach to machine translation suffers from two problems we aim to address. First, it needs parallel corpora, which are scarce, especially for low-resource languages. Second, it lacks psychological plausibility of learning procedure: learning a foreign language is about learning to communicate useful information, not merely learning to transduce from one language’s 'encoding' to another. We instead pose the problem of learning to translate as learning a policy in a communication game between two agents: the translator and the classifier. The classifier is trained beforehand on a natural language inference task (determining the entailment relation between a premise and a hypothesis) in the target language. The translator produces a sequence of actions that correspond to generating translations of both the hypothesis and premise, which are then passed to the classifier. The translator is rewarded for classifier’s performance on determining entailment between sentences translated by the translator to disciple’s native language. Translator’s performance thus reflects its ability to communicate useful information to the classifier. In effect, we train a machine translation model without the need for parallel corpora altogether. While similar reinforcement learning formulations for zero-shot translation were proposed before, there is a number of improvements we introduce. While prior research aimed at grounding the translation task in the physical world by evaluating agents on an image captioning task, we found that using a linguistic task is more sample-efficient. Natural language inference (also known as recognizing textual entailment) captures semantic properties of sentence pairs that are poorly correlated with semantic similarity, thus enforcing basic understanding of the role played by compositionality. It has been shown that models trained recognizing textual entailment produce high-quality general-purpose sentence embeddings transferrable to other tasks. We use stanford natural language inference (SNLI) dataset as well as its analogous datasets for French (XNLI) and Polish (CDSCorpus). Textual entailment corpora can be obtained relatively easily for any language, which makes our approach more extensible to low-resource languages than traditional approaches based on parallel corpora. We evaluated a number of reinforcement learning algorithms (including policy gradients and actor-critic) to solve the problem of translator’s policy optimization and found that our attempts yield some promising improvements over previous approaches to reinforcement-learning based zero-shot machine translation.

Keywords: agent-based language learning, low-resource translation, natural language inference, neural machine translation, reinforcement learning

Procedia PDF Downloads 128
31678 Artificial Intelligence in Duolingo

Authors: Elana Mahboub, Lamar Bakhurji, Hind Alhindi, Sara Alesayi

Abstract:

Duolingo is a revolutionary language learning platform that offers an interactive and accessible learning experience. Its gamified approach makes language learning engaging and enjoyable, with a diverse range of languages available. The platform's adaptive learning system tailors lessons to individual proficiency levels, ensuring a personalized and efficient learning journey. The incorporation of multimedia elements enhances the learning experience and promotes practical language application. Duolingo's success is attributed to its mobile accessibility, offering basic access to language courses for free, with optional premium features for those seeking additional resources. Research shows positive outcomes for users, and the app's global impact extends beyond individual learning to formal language education initiatives. Duolingo is a transformative force in language education, breaking down barriers and making language learning an attainable goal for millions worldwide.

Keywords: duolingo, artificial intelligence, artificial intelligence in duolingo, benefit of artificial intelligence

Procedia PDF Downloads 72
31677 An Investigation on Physics Teachers’ Views Towards Context Based Learning Approach

Authors: Medine Baran, Abdulkadir Maskan, Mehmet Ikbal Yetişir, Mukadder Baran, Azmi Türkan, Şeyma Yaşar

Abstract:

The purpose of this study was to determine the views of physics teachers from several secondary schools in Turkey towards context-based learning approach. In the study, the context-based learning opinion questionnaire developed by the researchers for use as the data collection tool was piloted with 250 physics teachers. The questionnaire examined by the researchers and field experts was initially made up of 53 items. Following the evaluation process of the questionnaire, it included 37 items. In this way, the reliability and validity process of the measurement tool was completed. In the end, the finalized questionnaire was applied to 144 physics teachers from several secondary schools in different cities in Turkey (F:73, M:71). In the study, the participants were determined based on ease of reaching them. The results revealed no remarkable difference between the views of the physics teachers with respect to their gender, region and school. However, when the items in the questionnaire were considered, it was found that the participants interestingly agreed on some of the choices in the items. Depending on this, it was found that there were high levels of differences between the frequencies of those who agreed and those who disagreed with the 16 items in the questionnaire. Therefore, as the following phase of the present study, further research has been planned using the same questions. Based on these questions, which received opposite responses, physics teachers will be asked for their views about the results of the study using the interview technique, one of qualitative research techniques. In this way, the results will be evaluated both by the researchers and by the participants, and the problems and difficulties will be determined. As a result, related suggestions can be put forward.

Keywords: context bases learning, physics teachers, views

Procedia PDF Downloads 373
31676 A Study on Learning Styles and Academic Performance in Relation with Kinesthetic, Verbal and Visual Intelligences

Authors: Salina Budin, Nor Liawati Abu Othman, Shaira Ismail

Abstract:

This study attempts to determine kinesthetic, verbal and visual intelligences among mechanical engineering undergraduate students and explores any probable relation with students’ learning styles and academic performance. The questionnaire used in this study is based on Howard Gardner’s multiple intelligences theory comprising of five elements of learning style; environmental, sociological, emotional, physiological and psychological. Questionnaires are distributed amongst undergraduates in the Faculty of Mechanical Engineering. Additional questions on students’ perception of learning styles and their academic performance are included in the questionnaire. The results show that one third of the students are strongly dominant in the kinesthetic intelligent (33%), followed by a combination of kinesthetic and visual intelligences (29%) and 21% are strongly dominant in all three types of intelligences. There is a statistically significant correlation between kinesthetic, verbal and visual intelligences and students learning styles and academic performances. The ANOVA analysis supports that there is a significant relationship between academic performances and level of kinesthetic, verbal and visual intelligences. In addition, it has also proven a remarkable relationship between academic performances and kinesthetic, verbal and visual learning styles amongst the male and female students. Thus, it can be concluded that, academic achievements can be enhanced by understanding as well as capitalizing the students’ types of intelligences and learning styles.

Keywords: kinesthetic intelligent, verbal intelligent, visual intelligent, learning style, academic performances

Procedia PDF Downloads 301
31675 Use of Technology Based Intervention for Continuous Professional Development of Teachers in Pakistan

Authors: Rabia Aslam

Abstract:

Overwhelming evidence from all around the world suggests that high-quality teacher professional development facilitates the improvement of teaching practices which in turn could improve student learning outcomes. The new Continuous Professional Development (CPD) model for primary school teachers in Punjab uses a blended approach in which pedagogical content knowledge is delivered through technology (high-quality instructional videos and lesson plans delivered to school tablets or mobile phones) with face-to-face support by Assistant Education Officers (AEOs). The model also develops Communities of Practice operationalized through formal meetings led by the AEOs and informal interactions through social media groups to provide opportunities for teachers to engage with each other and share their ideas, reflect on learning, and come up with solutions to issues they experience. Using Kirkpatrick’s 4 levels of the learning evaluation model, this paper investigates how school tablets and teacher mobile phones may act as transformational cultural tools to potentially expand perceptions and access to teaching and learning resources and explore some of the affordances of social media (Facebook, WhatsApp groups) in learning in an informal context. The results will be used to inform policy-level decisions on what shape could CPD of all teachers take in the context of a developing country like Pakistan.

Keywords: CPD, teaching & learning, blended learning, learning technologies

Procedia PDF Downloads 84
31674 Dynamics of Piaget’s Cognitive Learning Approach and Vygotsky’s Sociocultural Theory in Different Stages of Medical and Allied Health Education

Authors: Ferissa B. Ablola

Abstract:

The two learning theories which were evidently used in medical education include cognitive and sociocultural frameworks. The interplay of different learning theories in education is vital since most of the existing theories have specific focus of development. In addition, a certain theory is best fit with a particular learning outcome and audience profile. The application of learning theories is education is said to be dynamic and becomes more complex with increasing educational level. This systematic review aims to describe the possible shift from integration of cognitive learning theory to employment of socio-cultural approach in medical and health-allied education over the years among students, educators and the learning institution through systematic review following the PRISMA guidelines. In addition, the changes in teaching modality and individual acceptance of the shift of learning framework among cognitive constructivist and social constructivist will also be documented. This present review may serve as baseline information on the connection of two widely used theories in medical education in different year levels. Further, this study emphasizes the significance of the alignment of different learning theories and combination of insights from several educational frameworks, would permit the creation of a teaching/learning design with real theoretical depth. A more inclusive systematic review is necessary to involve more related studies, and exploration of interaction among other learning theories in health and other fields of study is encouraged.

Keywords: learning theory, cognitive, sociocultural, medical education

Procedia PDF Downloads 27
31673 Application of Deep Learning in Top Pair and Single Top Quark Production at the Large Hadron Collider

Authors: Ijaz Ahmed, Anwar Zada, Muhammad Waqas, M. U. Ashraf

Abstract:

We demonstrate the performance of a very efficient tagger applies on hadronically decaying top quark pairs as signal based on deep neural network algorithms and compares with the QCD multi-jet background events. A significant enhancement of performance in boosted top quark events is observed with our limited computing resources. We also compare modern machine learning approaches and perform a multivariate analysis of boosted top-pair as well as single top quark production through weak interaction at √s = 14 TeV proton-proton Collider. The most relevant known background processes are incorporated. Through the techniques of Boosted Decision Tree (BDT), likelihood and Multlayer Perceptron (MLP) the analysis is trained to observe the performance in comparison with the conventional cut based and count approach

Keywords: top tagger, multivariate, deep learning, LHC, single top

Procedia PDF Downloads 111
31672 Random Access in IoT Using Naïve Bayes Classification

Authors: Alhusein Almahjoub, Dongyu Qiu

Abstract:

This paper deals with the random access procedure in next-generation networks and presents the solution to reduce total service time (TST) which is one of the most important performance metrics in current and future internet of things (IoT) based networks. The proposed solution focuses on the calculation of optimal transmission probability which maximizes the success probability and reduces TST. It uses the information of several idle preambles in every time slot, and based on it, it estimates the number of backlogged IoT devices using Naïve Bayes estimation which is a type of supervised learning in the machine learning domain. The estimation of backlogged devices is necessary since optimal transmission probability depends on it and the eNodeB does not have information about it. The simulations are carried out in MATLAB which verify that the proposed solution gives excellent performance.

Keywords: random access, LTE/LTE-A, 5G, machine learning, Naïve Bayes estimation

Procedia PDF Downloads 145
31671 Digital Learning Repositories for Vocational Teaching and Knowledge Sharing

Authors: Prachyanun Nilsook, Panita Wannapiroon

Abstract:

The purpose of this research is to study a Digital Learning Repository System (DLRS) on vocational teachers and teaching in Thailand. The innobpcd.net is a DLRS being utilized by the Office of Vocational Education Commission and operationalized by the Bureau of Personnel Competency Development for vocational education teachers. The aim of the system is to support and enhance the process of vocational teaching and to improve staff development by providing teachers with a variety of network connections and information. The system provides centralized hosting and access to content, and the ability to share digital objects or files, to set permissions and controls for access to content that can be used vocational education teachers for their teaching and for their own development. The elements of DLRS include; Digital learning system, Media Library, Knowledge-based system and Mobile Application. The system aims to link vocational teachers to the most effective emerging technologies available for learning, so they are better resourced to support their vocational students. The initial results from this evaluation indicate that there is a range of services provided by the system being used by vocational teachers and this paper indicates which facilities have the greatest usage and impact on vocational teaching in Thailand.

Keywords: digital learning repositories, vocational education, knowledge sharing, learning objects

Procedia PDF Downloads 466
31670 Deliberate Learning and Practice: Enhancing Situated Learning Approach in Professional Communication Course

Authors: Susan Lee

Abstract:

Situated learning principles are adopted in the design of the module, professional communication, in its iteration of tasks and assignments to create a learning environment that simulates workplace reality. The success of situated learning is met when students are able to transfer and apply their skills beyond the classroom, in their personal life, and workplace. The learning process should help students recognize the relevance and opportunities for application. In the module’s learning component on negotiation, cases are created based on scenarios inspired by industry practices. The cases simulate scenarios that students on the course may encounter when they enter the workforce when they take on executive roles in the real estate sector. Engaging in the cases has enhanced students’ learning experience as they apply interpersonal communication skills in negotiation contexts of executives. Through the process of case analysis, role-playing, and peer feedback, students are placed in an experiential learning space to think and act in a deliberate manner not only as students but as professionals they will graduate to be. The immersive skills practices enable students to continuously apply a range of verbal and non-verbal communication skills purposefully as they stage their negotiations. The theme in students' feedback resonates with their awareness of the authentic and workplace experiences offered through visceral role-playing. Students also note relevant opportunities for the future transfer of the skills acquired. This indicates that students recognize the possibility of encountering similar negotiation episodes in the real world and realize they possess the negotiation tools and communication skills to deliberately apply them when these opportunities arise outside the classroom.

Keywords: deliberate practice, interpersonal communication skills, role-play, situated learning

Procedia PDF Downloads 214
31669 Vehicle Detection and Tracking Using Deep Learning Techniques in Surveillance Image

Authors: Abe D. Desta

Abstract:

This study suggests a deep learning-based method for identifying and following moving objects in surveillance video. The proposed method uses a fast regional convolution neural network (F-RCNN) trained on a substantial dataset of vehicle images to first detect vehicles. A Kalman filter and a data association technique based on a Hungarian algorithm are then used to monitor the observed vehicles throughout time. However, in general, F-RCNN algorithms have been shown to be effective in achieving high detection accuracy and robustness in this research study. For example, in one study The study has shown that the vehicle detection and tracking, the system was able to achieve an accuracy of 97.4%. In this study, the F-RCNN algorithm was compared to other popular object detection algorithms and was found to outperform them in terms of both detection accuracy and speed. The presented system, which has application potential in actual surveillance systems, shows the usefulness of deep learning approaches in vehicle detection and tracking.

Keywords: artificial intelligence, computer vision, deep learning, fast-regional convolutional neural networks, feature extraction, vehicle tracking

Procedia PDF Downloads 126
31668 Gaits Stability Analysis for a Pneumatic Quadruped Robot Using Reinforcement Learning

Authors: Soofiyan Atar, Adil Shaikh, Sahil Rajpurkar, Pragnesh Bhalala, Aniket Desai, Irfan Siddavatam

Abstract:

Deep reinforcement learning (deep RL) algorithms leverage the symbolic power of complex controllers by automating it by mapping sensory inputs to low-level actions. Deep RL eliminates the complex robot dynamics with minimal engineering. Deep RL provides high-risk involvement by directly implementing it in real-world scenarios and also high sensitivity towards hyperparameters. Tuning of hyperparameters on a pneumatic quadruped robot becomes very expensive through trial-and-error learning. This paper presents an automated learning control for a pneumatic quadruped robot using sample efficient deep Q learning, enabling minimal tuning and very few trials to learn the neural network. Long training hours may degrade the pneumatic cylinder due to jerk actions originated through stochastic weights. We applied this method to the pneumatic quadruped robot, which resulted in a hopping gait. In our process, we eliminated the use of a simulator and acquired a stable gait. This approach evolves so that the resultant gait matures more sturdy towards any stochastic changes in the environment. We further show that our algorithm performed very well as compared to programmed gait using robot dynamics.

Keywords: model-based reinforcement learning, gait stability, supervised learning, pneumatic quadruped

Procedia PDF Downloads 316
31667 Future Education: Changing Paradigms

Authors: Girish Choudhary

Abstract:

Education is in a state of flux. Not only one need to acquire skills in order to cope with a fast changing global world, an explosive growth in technology, on the other hand is providing a new wave of teaching tools - computer aided video instruction, hypermedia, multimedia, CD-ROMs, Internet connections, and collaborative software environments. The emerging technology incorporates the group qualities of interactive, classroom-based learning while providing individual students the flexibility to participate in an educational programme at their own time and place. The technology facilitating self learning also seems to provide a cost effective solution to the dilemma of delivering education to masses. Online education is a unique learning domain that provides for many to many communications as well. The computer conferencing software defines the boundaries of the virtual classroom. The changing paradigm provides access of instruction to a large proportion of society, promises a qualitative change in the quality of learning and echoes a new way of thinking in educational theory that promotes active learning and open new learning approaches. Putting it to practice is challenging and may fundamentally alter the nature of educational institutions. The subsequent part of paper addresses such questions viz. 'Do we need to radically re-engineer the curriculum and foster an alternate set of skills in students?' in the onward journey.

Keywords: on-line education, self learning, energy and power engineering, future education

Procedia PDF Downloads 329
31666 Examining Audiology Students: Clinical Reasoning Skills When Using Virtual Audiology Cases Aided With no Collaboration, Live Collaboration, and Virtual Collaboration

Authors: Ramy Shaaban

Abstract:

The purpose of this study was to examine the difference in clinical reasoning skills of students when using virtual audiology cases with and without collaborative assistance from major learning approaches important to clinical reasoning skills and computer-based learning models: Situated Learning Theory, Social Development Theory, Scaffolding, and Collaborative Learning. A quasi-experimental design was conducted at two United States universities to examine whether there is a significant difference in clinical reasoning skills between three treatment groups using IUP Audiosim software. Two computer-based audiology case simulations were developed, and participants were randomly placed into the three groups: no collaboration, virtual collaboration, and live collaboration. The clinical reasoning data were analyzed using One-Way ANOVA and Tukey posthoc analyses. The results show that there was a significant difference in clinical reasoning skills between the three treatment groups. The score obtained by the no collaboration group was significantly less than the scores obtained by the virtual and live collaboration groups. Collaboration, whether virtual or in person, has a positive effect on students’ clinical reasoning. These results with audiology students indicate that combining collaboration models with scaffolding and embedding situated learning and social development theories into the design of future virtual patients has the potential to improve students’ clinical reasoning skills.

Keywords: clinical reasoning, virtual patients, collaborative learning, scaffolding

Procedia PDF Downloads 214
31665 Models and Metamodels for Computer-Assisted Natural Language Grammar Learning

Authors: Evgeny Pyshkin, Maxim Mozgovoy, Vladislav Volkov

Abstract:

The paper follows a discourse on computer-assisted language learning. We examine problems of foreign language teaching and learning and introduce a metamodel that can be used to define learning models of language grammar structures in order to support teacher/student interaction. Special attention is paid to the concept of a virtual language lab. Our approach to language education assumes to encourage learners to experiment with a language and to learn by discovering patterns of grammatically correct structures created and managed by a language expert.

Keywords: computer-assisted instruction, language learning, natural language grammar models, HCI

Procedia PDF Downloads 519
31664 Using Diagnostic Assessment as a Learning and Teaching Approach to Identify Learning Gaps at a Polytechnic

Authors: Vijayan Narayananayar

Abstract:

Identifying learning gaps is crucial in ensuring learners have the necessary knowledge and skills to succeed. The Learning and Teaching (L&T) approach requires tutors to identify gaps in knowledge and improvise learning activities to close them. One approach to identifying learning gaps is through diagnostic assessment, which uses well-structured questions and answer options. The paper focuses on the use of diagnostic assessment as a learning and teaching approach in a foundational module at a polytechnic. The study used diagnostic assessment over two semesters, including the COVID and post-COVID semesters, to identify gaps in learning. The design of the diagnostic activity, pedagogical intervention, and survey responses completed by learners were analyzed. Results showed that diagnostic assessment can be an effective tool for identifying learning gaps and designing interventions to address them. Additionally, the use of diagnostic assessment provides an opportunity for tutors to engage with learners on a one-to-one basis, tailoring teaching to individual needs. The paper also discusses the design of diagnostic questions and answer options, including characteristics that need to be considered in achieving the target of identifying learning gaps. The implications of using diagnostic assessment as a learning and teaching approach include bridging the gap between theory and practice, and ensuring learners are equipped with skills necessary for their future careers. This paper can be useful in helping educators and practitioners to incorporate diagnostic assessment into their L&T approach.

Keywords: assessment, learning & teaching, diagnostic assessment, analytics

Procedia PDF Downloads 111
31663 The Impact of Training Method on Programming Learning Performance

Authors: Chechen Liao, Chin Yi Yang

Abstract:

Although several factors that affect learning to program have been identified over the years, there continues to be no indication of any consensus in understanding why some students learn to program easily and quickly while others have difficulty. Seldom have researchers considered the problem of how to help the students enhance the programming learning outcome. The research had been conducted at a high school in Taiwan. Students participating in the study consist of 330 tenth grade students enrolled in the Basic Computer Concepts course with the same instructor. Two types of training methods-instruction-oriented and exploration-oriented were conducted. The result of this research shows that the instruction-oriented training method has better learning performance than exploration-oriented training method.

Keywords: learning performance, programming learning, TDD, training method

Procedia PDF Downloads 428
31662 The Relation between Learning Styles and English Achievement in the Language Training Centre

Authors: Nurul Yusnita

Abstract:

Many studies have been developed to help the students to get good achievement in English learning. They can be from the teaching method or psychological ones. One of the psychological studies in educational research is learning style. In some ways, learning style can affect the achievement of the students. This study aimed to examine 4 (four) learning styles and their relations to English achievement among the students learning English in Language Training Center of Universitas Muhammadiyah Yogyakarta (LTC UMY). The method of this study was descriptive analytical. The sample consisted of 39 Accounting students in LTC UMY. The data was collected through questionnaires with Likert-scale. The achievement was obtained from the grade of the students. To analyze the questionnaires and to see the relation between the learning styles and the student achievement, SPSS statistical software of correlational analysis was used. The result showed that both visual and auditory had the same percentage of 35.9% (14 students). 3 students (7.7%) had kinaesthetic learning style and 8 students (20.5%) had visual and auditory ones. Meanwhile, there were 5 students (12.8%) who had visual learning style could increase their grades. Only 1 student (2.5%) who had visual and auditory could improve his grade. Besides grade increase, there were also grade decrease. Students with visual, auditory, visual and auditory, and kinaesthetic learning styles were 3 students (7.7%), 5 students (12%), 4 students (10.2%) and 1 student (2.5%) respectively. In conclusion, there was no significant relationship between learning style and English achievement. Most of the good achievers were the students with visual and auditory learning styles and most of them preferred visual method. The implication is the teachers and material designers could improve their method through visual things to achieve effective English teaching learning.

Keywords: accounting students, English achievement, language training centre, learning styles

Procedia PDF Downloads 271
31661 Teaching for Knowledge Transfer: Best Practices from a Graduate-Level Educational Psychology Distance Learning Program

Authors: Bobby Hoffman

Abstract:

One measure of effective instruction is the ability to solve authentic, real-world problems by effectively transferring and applying classroom and textbook knowledge. While many students can productively earn high grades and learn course content, they are not always able to apply the knowledge they gain. As such, this quasi-experimental study compared the comprehensive exit exam results of learners across instructional modalities who completed a prominent graduate-level educational psychology program. ANCOVA revealed superior knowledge transfer for blended-learning students compared to those who completed distance education and significantly greater transfer of declarative, procedural, and self-regulatory knowledge by the blended-learning students. This paper briefly summarizes the study results while highlighting evidence-based programmatic and course level modifications that were implemented to specifically address the transfer of learning and practical application of educational psychology knowledge.

Keywords: assessment, distance learning, educational psychology, knowledge transfer

Procedia PDF Downloads 177
31660 A Program Based on Artistic and Musical Activities to Acquire Some Educational Concepts for Children with Learning Difficulties

Authors: Ahmed Amin Mousa, Huda Mazeed, Eman Saad

Abstract:

The study aims to identify the extent of the effectiveness of the artistic formation program using some types of pastes to reduce the hyperactivity of the kindergarten child. The researcher has discussed the effectiveness of the artistic program using some types of pastes in reducing the hyperactivity of the kindergarten child. The research sample included 120 children of ages between 5 to 6 years old from the five schools for special needs section learning disability, Cairo Province. The study used the empirical like curriculum which depends on designing one group using the before and after application measurement for the group to validate the fidelity of both the hypothesis and the effectiveness of the program. The variables of the study were specified as follows; artistic formation program using paper Mache as an independent variable and its effect on skills of kindergarten child with learning disabilities as a subsequent variable. The researchers depended on applying a group of artistic formation program using pulp melding skills for kindergarten children with learning disabilities. The tools of the study, designed by the researcher, included: recording card used for recording the Effective program using pulp molding skills for kindergarten children with learning disabilities during practicing the artistic formation activity. In additional, there was a program using pulp molding skills for kindergarten children with learning disabilities. The results proved the effectiveness of the program using pulp molding skills for kindergarten children with learning disabilities.

Keywords: artistic program, developing skills, kindergarten, children, learning disabilities

Procedia PDF Downloads 160
31659 Cyber Attacks Management in IoT Networks Using Deep Learning and Edge Computing

Authors: Asmaa El Harat, Toumi Hicham, Youssef Baddi

Abstract:

This survey delves into the complex realm of Internet of Things (IoT) security, highlighting the urgent need for effective cybersecurity measures as IoT devices become increasingly common. It explores a wide array of cyber threats targeting IoT devices and focuses on mitigating these attacks through the combined use of deep learning and machine learning algorithms, as well as edge and cloud computing paradigms. The survey starts with an overview of the IoT landscape and the various types of attacks that IoT devices face. It then reviews key machine learning and deep learning algorithms employed in IoT cybersecurity, providing a detailed comparison to assist in selecting the most suitable algorithms. Finally, the survey provides valuable insights for cybersecurity professionals and researchers aiming to enhance security in the intricate world of IoT.

Keywords: internet of things (IoT), cybersecurity, machine learning, deep learning

Procedia PDF Downloads 31