Search results for: Experience based learning

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: Convolutional Neural Network, Deep Learning, Deep Learning Based FER, Facial Emotion Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1371

Authors: N. Ismail, O. Thammajinda, U. Thongpanya

Abstract:

Games-based learning (GBL) has become increasingly important in teaching and learning. This paper explains the first two phases (analysis and design) of a GBL development project, ending up with a prototype design based on students’ and teachers’ perceptions. The two phases are part of a full cycle GBL project aiming to help secondary school students in Thailand in their study of Comprehensive Sex Education (CSE). In the course of the study, we invited 1,152 students to complete questionnaires and interviewed 12 secondary school teachers in focus groups. This paper found that GBL can serve students in their learning about CSE, enabling them to gain understanding of their sexuality, develop skills, including critical thinking skills and interact with others (peers, teachers, etc.) in a safe environment. The objectives of this paper are to outline the development of GBL variables from the research question(s) into the developers’ flow chart, to be responsive to the GBL beneficiaries’ preferences and expectations, and to help in answering the research questions. This paper details the steps applied to generate GBL variables that can feed into a game flow chart to develop a GBL prototype. In our approach, we detailed two models: (1) Game Elements Model (GEM) and (2) Game Object Model (GOM). There are three outcomes of this research – first, to achieve the objectives and benefits of GBL in learning, game design has to start with the research question(s) and the challenges to be resolved as research outcomes. Second, aligning the educational aims with engaging GBL end users (students) within the data collection phase to inform the game prototype with the game variables is essential to address the answer/solution to the research question(s). Third, for efficient GBL to bridge the gap between pedagogy and technology and in order to answer the research questions via technology (i.e. GBL) and to minimise the isolation between the pedagogists “P” and technologist “T”, several meetings and discussions need to take place within the team.

Keywords: Games-based learning, design, engagement, pedagogy, preferences, prototype, variables.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 737

Authors: Nicholas Milburn, Yu Liang, Dalei Wu

Abstract:

Athlete performance scoring within the climbing domain presents interesting challenges as the sport does not have an objective way to assign skill. Assessing skill levels within any sport is valuable as it can be used to mark progress while training, and it can help an athlete choose appropriate climbs to attempt. Machine learning-based methods are popular for complex problems like this. The dataset available was composed of dynamic force data recorded during climbing; however, this dataset came with challenges such as data scarcity, imbalance, and it was temporally heterogeneous. Investigated solutions to these challenges include data augmentation, temporal normalization, conversion of time series to the spectral domain, and cross validation strategies. The investigated solutions to the classification problem included light weight machine classifiers KNN and SVM as well as the deep learning with CNN. The best performing model had an 80% accuracy. In conclusion, there seems to be enough information within climbing force data to accurately categorize climbers by skill.

Keywords: Classification, climbing, data imbalance, data scarcity, machine learning, time sequence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 567

Authors: Costin Pribeanu, Rytis Vilkonis, Dragoş Daniel Iordache

Abstract:

User interaction components of Augmented Reality (AR) systems have to be tested with users in order to find and fix usability problems as early as possible. In this paper we will report on a user-centered design approach for AR systems following the experience acquired during the design and evaluation of a software prototype for an AR-based educational platform. In this respect we will focus on the re-design of the user task based on the results from a formative usability evaluation. The basic idea of our approach is to describe task scenarios in a tabular format, to develop a task model in a task modeling environment and then to simulate the execution.

Keywords: AR-based educational systems, task-based design, usability evaluation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2485

Authors: Omar Alshehri, Vic Lally

Abstract:

This paper examined the attitudes of using social media tools to support learning at a university in Saudi Arabia. Moreover, it investigated the students’ current usage of these tools and examined the barriers they could face during the use of social media tools in the education process. Participants in this study were 42 university students. A web-based survey was used to collect data for this study. The results indicate that all of the students were familiar with social media and had used at least one type of social media for learning. It was found out that all students had very positive attitudes towards the use of social media and welcomed using these tools as a supplementary to the curriculum. However, the results indicated that the major barriers to using these tools in learning were distraction, opposing Islamic religious teachings, privacy issues, and cyberbullying. The study recommended that this study could be replicated at other Saudi universities to investigate factors and barriers that might affect Saudi students’ attitudes toward using social media to support learning.

Keywords: Saudi Arabia, social media, benefits of social media use, barriers to social media use, higher education.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2349

Authors: Jo Rhodes, Peter Lok, Zahra Sadeghinejad

Abstract:

The aim of this study is to determine the impact of metacognition on top management team members and firm performance based on full team integration. A survey of 1500 small to medium enterprises (SMEs) was initiated and 140 firms were obtained in this study (with response rate of 9%). The result showed that different metacognitive abilities of managers [knowledge and experience] could enhance team decision-making and problem solving, resulting in greater firm performance. This is a significant finding for SMEs because these organisations have small teams with owner leadership and entrepreneurial orientation.

Keywords: Metacognition, behavioural integration, top management team, performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1290

Authors: Praveen Boinee, Alessandro De Angelis, Gian Luca Foresti

Abstract:

Leo Breimans Random Forests (RF) is a recent development in tree based classifiers and quickly proven to be one of the most important algorithms in the machine learning literature. It has shown robust and improved results of classifications on standard data sets. Ensemble learning algorithms such as AdaBoost and Bagging have been in active research and shown improvements in classification results for several benchmarking data sets with mainly decision trees as their base classifiers. In this paper we experiment to apply these Meta learning techniques to the random forests. We experiment the working of the ensembles of random forests on the standard data sets available in UCI data sets. We compare the original random forest algorithm with their ensemble counterparts and discuss the results.

Keywords: Random Forests [RF], ensembles, UCI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2711

Authors: Kaushik Sathupadi, Sandesh Achar

Abstract:

Human action recognition (HAR) modeling is a critical task in machine learning. These systems require better techniques for recognizing body parts and selecting optimal features based on vision sensors to identify complex action patterns efficiently. Still, there is a considerable gap and challenges between images and videos, such as brightness, motion variation, and random clutters. This paper proposes a robust approach for classifying human actions over cloud-based image data. First, we apply pre-processing and detection, human and outer shape detection techniques. Next, we extract valuable information in terms of cues. We extract two distinct features: fuzzy local binary patterns and sequence representation. Then, we applied a greedy, randomized adaptive search procedure for data optimization and dimension reduction, and for classification, we used a random forest. We tested our model on two benchmark datasets, AAMAZ and the KTH Multi-view Football datasets. Our HAR framework significantly outperforms the other state-of-the-art approaches and achieves a better recognition rate of 91% and 89.6% over the AAMAZ and KTH Multi-view Football datasets, respectively.

Keywords: Computer vision, human motion analysis, random forest, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 36

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as an explicit input. In this paper, we study how the performance of predictive models change as a function of different look-back window sizes and different amounts of time to predict into the future. We also consider the performance of the recent attention-based transformer models, which had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the website of University of California, Irvine (UCI), which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean   Absolute Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: Air quality prediction, deep learning algorithms, time series forecasting, look-back window.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1168

Authors: Sun-Young Jang, Sung-Ah Kim, Dongyoun Shin

Abstract:

The Intelligent transportation system is essential to build smarter cities. Machine learning based transportation prediction could be highly promising approach by delivering invisible aspect visible. In this context, this research aims to make a prototype model that predicts transportation network by using big data and machine learning technology. In detail, among urban transportation systems this research chooses bus system.  The research problem that existing headway model cannot response dynamic transportation conditions. Thus, bus delay problem is often occurred. To overcome this problem, a prediction model is presented to fine patterns of bus delay by using a machine learning implementing the following data sets; traffics, weathers, and bus statues. This research presents a flexible headway model to predict bus delay and analyze the result. The prototyping model is composed by real-time data of buses. The data are gathered through public data portals and real time Application Program Interface (API) by the government. These data are fundamental resources to organize interval pattern models of bus operations as traffic environment factors (road speeds, station conditions, weathers, and bus information of operating in real-time). The prototyping model is designed by the machine learning tool (RapidMiner Studio) and conducted tests for bus delays prediction. This research presents experiments to increase prediction accuracy for bus headway by analyzing the urban big data. The big data analysis is important to predict the future and to find correlations by processing huge amount of data. Therefore, based on the analysis method, this research represents an effective use of the machine learning and urban big data to understand urban dynamics.

Keywords: Big data, bus headway prediction, machine learning, public transportation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1562

Authors: Mohammed I. Abouheaf, Sofie Haesaert, Wei-Jen Lee, Frank L. Lewis

Abstract:

Economic Dispatch is one of the most important power system management tools. It is used to allocate an amount of power generation to the generating units to meet the load demand. The Economic Dispatch problem is a large scale nonlinear constrained optimization problem. In general, heuristic optimization techniques are used to solve non-convex Economic Dispatch problem. In this paper, ideas from Reinforcement Learning are proposed to solve the non-convex Economic Dispatch problem. Q-Learning is a reinforcement learning techniques where each generating unit learn the optimal schedule of the generated power that minimizes the generation cost function. The eligibility traces are used to speed up the Q-Learning process. Q-Learning with eligibility traces is used to solve Economic Dispatch problems with valve point loading effect, multiple fuel options, and power transmission losses.

Keywords: Economic Dispatch, Non-Convex Cost Functions, Valve Point Loading Effect, Q-Learning, Eligibility Traces.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2087

Authors: Tlou J. Ramabu

Abstract:

Programming is one of the challenging subjects in the field of computing. In the higher education sphere, some programming novices’ performance, retention rate, and success rate are not improving. Most of the time, the problem is caused by the slow pace of learning, difficulty in grasping the syntax of the programming language and poor logical skills. More importantly, programming forms part of major subjects within the field of computing. As a result, specialized pedagogical methods and innovation are highly recommended. Little research has been done on the potential productivity of the WhatsApp platform as part of a blended learning model. In this article, the authors discuss the WhatsApp group as a part of blended learning model incorporated for a group of programming novices. We discuss possible administrative activities for productive utilisation of the WhatsApp group on the blended learning overview. The aim is to take advantage of the popularity of WhatsApp and the time students spend on it for their educational purpose. We believe that blended learning featuring a WhatsApp group may ease novices’ cognitive load and strengthen their foundational programming knowledge and skills. This is a work in progress as the proposed blended learning model with WhatsApp incorporated is yet to be implemented.

Keywords: Blended learning, higher education, WhatsApp, programming, novices, lecturers.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1177

Authors: S. J. Hachar

Abstract:

The goal of this paper is to provide educators an overview of international practices supporting young learners, arming us with adequate information to lead effective change. We will report on research and observations of Service Learning Projects conducted by one South Texas University. The intent of the paper is also to provide readers an overview of service learning in the preparation of teacher candidates pursuing a Bachelor of Science in Elementary Education. The objective of noting the efficiency and effectiveness of programs leading to literacy and oral fluency in a native language and second language will be discussed. This paper also highlights experiential learning for academic credit that combines community service with student learning. Six weeks of visits to a variety of community sites, making personal observations with faculty members, conducting extensive interviews with parents and key personnel at all sites will be discussed. The culminating Service Learning Expo will be reported as well.

Keywords: Elementary education, junior achievement, service learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 964

Authors: Sajed A. Habib

Abstract:

Problem-based learning (PBL) is a student-centered pedagogy that originated in the medical field and has also been used extensively in other knowledge disciplines with recognized advantages and limitations. PBL has been used in various undergraduate engineering programs with mixed outcomes. The current fourth industrial revolution (digital era or Industry 4.0) has made it essential for many science and engineering students to receive effective training in advanced courses such as industrial automation and robotics. This paper presents a case study at Assumption University of Thailand, where a PBL-like approach was used to teach some aspects of automation and robotics to selected groups of undergraduate engineering students. These students were given some basic level training in automation prior to participating in a subsequent training session in order to solve technical problems with increased complexity. The participating students’ evaluation of the training sessions in terms of learning effectiveness, skills enhancement, and incremental knowledge following the problem-solving session was captured through a follow-up survey consisting of 14 questions and a 5-point scoring system. From the most recent training event, an overall 70% of the respondents indicated that their skill levels were enhanced to a much greater level than they had had before the training, whereas 60.4% of the respondents from the same event indicated that their incremental knowledge following the session was much greater than what they had prior to the training. The instructor-facilitator involved in the training events suggested that this method of learning was more suitable for senior/advanced level students than those at the freshmen level as certain skills to effectively participate in such problem-solving sessions are acquired over a period of time, and not instantly.

Keywords: Automation, industry 4.0, model-based design training, problem-based learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1098

Authors: Rudolf Egger

Abstract:

This paper explores the relationships between the basic learning processes of leading trade union workers and their methods for coping with the changes in the life-courses of societies today. It will discuss the fragile discourse on lifelong learning in trade unions and the “production of self-techniques” to get in touch with the new economic forms. On the basis of an empirical project, different processes of the socialization of leading trade union workers will be analysed to discover the consequences of the lifelong learning discourse. The results show what competences they need to develop for the “wider benefits of negotiations”. The main challenge remains to make visible how deeply intertwined trade union learning and education are with development in an ongoing dynamic economic process, rather than a quick-fix injection of skills and information. There is a complex relationship existing between the three ‘partners’, work, learning and society forming. The author suggests that contemporary trade unions could be trendsetters who make their own learning agendas by drawing less on formal education and more on informal and non-formal learning contexts. This is in parallel with growing political and scientific consciousness of the need to arrive at new educational/vocational policies and practices.

Keywords: Lifelong learning, Trade unions, Non-formal learning, Educational/vocational policies.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1231

Authors: Hassan Haleh, Zohreh Nasiri, Parisa Farahpour

Abstract:

During recent years, the traditional learning approaches have undergone fundamental changes due to the emergence of new technologies such as multimedia, hypermedia and telecommunication. E-learning is a modern world phenomenon that has come into existence in the information age and in a knowledgebased society. E-learning has developed significantly within a short period of time. Thus it is of a great significant to secure information, allow a confident access and prevent unauthorized accesses. Making use of individuals- physiologic or behavioral (biometric) properties is a confident method to make the information secure. Among the biometrics, fingerprint is more acceptable and most countries use it as an efficient methods of identification. This article provides a new method to compare the fingerprint comparison by pattern recognition and image processing techniques. To verify fingerprint, the shortest distance method is used together with perceptronic multilayer neural network functioning based on minutiae. This method is highly accurate in the extraction of minutiae and it accelerates comparisons due to elimination of false minutiae and is more reliable compared with methods that merely use directional images.

Keywords: Fingerprint, minutiae, extraction of properties, multilayer neural network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1649

Authors: H. Mashhady, B. Lotfi, M. Doosti, M. Fatollahi

Abstract:

An exploration of the related literature reveals that all instruction methods aim at training autonomous learners. After the turn of second language pedagogy toward learner-oriented strategies, learners’ needs were more focused. Yet; the historical, social and political aspects of learning were still neglected. The present study investigates the notion of autonomous learning and explains its various facets from a pedagogical point of view. Furthermore; different elements, fields and scopes of autonomous learning will be explored. After exploring different aspects of autonomy, it is postulated that liberatory autonomy is highlighted since it not only covers social autonomy but also reveals learners’ capabilities and human potentials. It is also recommended that learners consider different elements of autonomy such as motivation, knowledge, confidence, and skills.

Keywords: Critical pedagogy, social autonomy, academic learning, cultural notions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2044

Authors: Maziar A. Sharbafi, Caro Lucas, Aida Mohammadinejad, Mostafa Yaghobi

Abstract:

The Combination of path planning and path following is the main purpose of this paper. This paper describes the developed practical approach to motion control of the MRL small size robots. An intelligent controller is applied to control omni-directional robots motion in simulation and real environment respectively. The Brain Emotional Learning Based Intelligent Controller (BELBIC), based on LQR control is adopted for the omni-directional robots. The contribution of BELBIC in improving the control system performance is shown as application of the emotional learning in a real world problem. Optimizing of the control effort can be achieved in this method too. Next the implicit communication method is used to determine the high level strategies and coordination of the robots. Some simple rules besides using the environment as a memory to improve the coordination between agents make the robots' decision making system. With this simple algorithm our team manifests a desirable cooperation.

Keywords: multi-agent systems (MAS), Emotional learning, MIMO system, BELBIC, LQR, Communication via environment

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1853

Authors: Petra Horváthová, Andrej Miklosik

Abstract:

One part of the total employee’s reward is apart from basic wages or salary, employee’s benefits and intangible remuneration also so called contingent (variable) pay. Contingent pay is connected to performance, contribution, cap competency or skills of individual employees, and to team’s or company-wide performance or to combination of few of the mentioned possibilities. Sometimes among the contingent pay is also incorporated the remuneration based on length of employment, when the financial reward is not connected to performance or skills, but to length of continuous employment either on one working position or in one level of remuneration scale. Main aim of this article is to define, based on available information, contingent pay, describe individual forms, its advantages and disadvantages and possibilities to utilization in practice; but also bring information not only about its extent and level of utilization of contingent pay by companies in one of the Czech Republic’s regions, but also mention their practical experience with this type of remuneration.

Keywords: Contingent pay, individual contingent pay, team contingent pay, company-wide contingent pay

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1398

Authors: José R. G. Braga, Joice B. Mendes, Guilherme H. Caponetto, Alexandre C. B. Ramos

Abstract:

With major technological advances and to reduce the cost of training apprentices for real-time critical systems, it was necessary the development of Intelligent Tutoring Systems for training apprentices in these systems. These systems, in general, have interactive features so that the learning is actually more efficient, making the learner more familiar with the mechanism in question. In the home stage of learning, tests are performed to obtain the student's income, a measure on their use. The aim of this paper is to present a framework to model an Intelligent Tutoring Systems using the UML language. The various steps of the analysis are considered the diagrams required to build a general model, whose purpose is to present the different perspectives of its development.

Keywords: Computer based training, Hypermedia, Software modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1607

Authors: Ioannis Pratikakis, Anna Karahaliou, Katerina Vassiou, Vassilis Virvilis, Dimitrios Kosmopoulos, Stavros Perantonis

Abstract:

In this paper, a Web-based e-Training platform that is dedicated to multimodal breast imaging is presented. The assets of this platform are summarised in (i) the efficient representation of the curriculum flow that will permit efficient training; (ii) efficient tagging of multimodal content appropriate for the completion of realistic cases and (iii) ubiquitous accessibility and platform independence via a web-based approach.

Keywords: Breast imaging, e-Training, web-based learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1686

Authors: Marios Poulos, Sozon Papavlasopoulos, V. S. Belesiotis

Abstract:

In the proposed method for Web page-ranking, a novel theoretic model is introduced and tested by examples of order relationships among IP addresses. Ranking is induced using a convexity feature, which is learned according to these examples using a self-organizing procedure. We consider the problem of selforganizing learning from IP data to be represented by a semi-random convex polygon procedure, in which the vertices correspond to IP addresses. Based on recent developments in our regularization theory for convex polygons and corresponding Euclidean distance based methods for classification, we develop an algorithmic framework for learning ranking functions based on a Computational Geometric Theory. We show that our algorithm is generic, and present experimental results explaining the potential of our approach. In addition, we explain the generality of our approach by showing its possible use as a visualization tool for data obtained from diverse domains, such as Public Administration and Education.

Keywords: Computational Geometry, Education, e-Governance, Semantic Web.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1756

Authors: Dewan Md. Farid, Nouria Harbi, Emna Bahri, Mohammad Zahidur Rahman, Chowdhury Mofizur Rahman

Abstract:

Recently, information security has become a key issue in information technology as the number of computer security breaches are exposed to an increasing number of security threats. A variety of intrusion detection systems (IDS) have been employed for protecting computers and networks from malicious network-based or host-based attacks by using traditional statistical methods to new data mining approaches in last decades. However, today's commercially available intrusion detection systems are signature-based that are not capable of detecting unknown attacks. In this paper, we present a new learning algorithm for anomaly based network intrusion detection system using decision tree algorithm that distinguishes attacks from normal behaviors and identifies different types of intrusions. Experimental results on the KDD99 benchmark network intrusion detection dataset demonstrate that the proposed learning algorithm achieved 98% detection rate (DR) in comparison with other existing methods.

Keywords: Detection rate, decision tree, intrusion detectionsystem, network security.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3630

Authors: Robert F. Kenny, Glenda A. Gunter

Abstract:

Current technological advances pale in comparison to the changes in social behaviors and 'sense of place' that is being empowered since the Internet made it on the scene. Today-s students view the Internet as both a source of entertainment and an educational tool. The development of virtual environments is a conceptual framework that needs to be addressed by educators and it is important that they become familiar with who these virtual learners are and how they are motivated to learn. Massively multiplayer online role playing games (MMORPGs), if well designed, could become the vehicle of choice to deliver learning content. We suggest that these games, in order to accomplish these goals, must begin with well-established instructional design principles that are co-aligned with established principles of video game design. And have the opportunity to provide an instructional model of significant prescriptive power. The authors believe that game designers need to take advantage of the natural motivation player-learners have for playing games by developing them in such a way so as to promote, intrinsic motivation, content learning, transfer of knowledge, and naturalization.

Keywords: serious games, endogenous fantasy, intrinsic motivation, online learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2234

Authors: Eunji Choi, Borang Park, Youngjae Choi, Jinwoo Moon

Abstract:

In this study, a predictive model for estimating the metabolism (MET) of human body was developed for the optimal control of indoor thermal environment. Human body images for indoor activities and human body joint coordinated values were collected as data sets, which are used in predictive model. A deep learning algorithm was used in an initial model, and its number of hidden layers and hidden neurons were optimized. Lastly, the model prediction performance was analyzed after the model being trained through collected data. In conclusion, the possibility of MET prediction was confirmed, and the direction of the future study was proposed as developing various data and the predictive model.

Keywords: Deep learning, indoor quality, metabolism, predictive model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1193

Authors: Julius Onyancha, Valentina Plekhanova

Abstract:

One of the significant issues facing web users is the amount of noise in web data which hinders the process of finding useful information in relation to their dynamic interests. Current research works consider noise as any data that does not form part of the main web page and propose noise web data reduction tools which mainly focus on eliminating noise in relation to the content and layout of web data. This paper argues that not all data that form part of the main web page is of a user interest and not all noise data is actually noise to a given user. Therefore, learning of noise web data allocated to the user requests ensures not only reduction of noisiness level in a web user profile, but also a decrease in the loss of useful information hence improves the quality of a web user profile. Noise Web Data Learning (NWDL) tool/algorithm capable of learning noise web data in web user profile is proposed. The proposed work considers elimination of noise data in relation to dynamic user interest. In order to validate the performance of the proposed work, an experimental design setup is presented. The results obtained are compared with the current algorithms applied in noise web data reduction process. The experimental results show that the proposed work considers the dynamic change of user interest prior to elimination of noise data. The proposed work contributes towards improving the quality of a web user profile by reducing the amount of useful information eliminated as noise.

Keywords: Web log data, web user profile, user interest, noise web data learning, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1734

Authors: Haifeng Wang, Haili Zhang

Abstract:

Most movie recommendation systems have been developed for customers to find items of interest. This work introduces a predictive model usable by small and medium-sized enterprises (SMEs) who are in need of a data-based and analytical approach to stock proper movies for local audiences and retain more customers. We used classification models to extract features from thousands of customers’ demographic, behavioral and social information to predict their movie genre preference. In the implementation, a Gaussian kernel support vector machine (SVM) classification model and a logistic regression model were established to extract features from sample data and their test error-in-sample were compared. Comparison of error-out-sample was also made under different Vapnik–Chervonenkis (VC) dimensions in the machine learning algorithm to find and prevent overfitting. Gaussian kernel SVM prediction model can correctly predict movie genre preferences in 85% of positive cases. The accuracy of the algorithm increased to 93% with a smaller VC dimension and less overfitting. These findings advance our understanding of how to use machine learning approach to predict customers’ preferences with a small data set and design prediction tools for these enterprises.

Keywords: Computational social science, movie preference, machine learning, SVM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1650

Authors: Luis Fonseca, Filipe Cabral Pinto, Susana Sargento

Abstract:

The increase of the world population, especially in large urban centers, has resulted in new challenges particularly with the control and optimization of public safety. Thus, in the present work, a solution is proposed for the prediction of criminal occurrences in a city based on historical data of incidents and demographic information. The entire research and implementation will be presented start with the data collection from its original source, the treatment and transformations applied to them, choice and the evaluation and implementation of the Machine Learning model up to the application layer. Classification models will be implemented to predict criminal risk for a given time interval and location. Machine Learning algorithms such as Random Forest, Neural Networks, K-Nearest Neighbors and Logistic Regression will be used to predict occurrences, and their performance will be compared according to the data processing and transformation used. The results show that the use of Machine Learning techniques helps to anticipate criminal occurrences, which contributed to the reinforcement of public security. Finally, the models were implemented on a platform that will provide an API to enable other entities to make requests for predictions in real-time. An application will also be presented where it is possible to show criminal predictions visually.

Keywords: Crime prediction, machine learning, public safety, smart city.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1324

Authors: Rosie Borup, Hanifa Shah

Abstract:

This paper aims to describe how student satisfaction is measured for work-based learners as these are non-traditional learners, conducting academic learning in the workplace, typically their curricula have a high degree of negotiation, and whose motivations are directly related to their employers- needs, as well as their own career ambitions. We argue that while increasing WBL participation, and use of SSD are both accepted as being of strategic importance to the HE agenda, the use of WBL SSD is rarely examined, and lessons can be learned from the comparison of SSD from a range of WBL programmes, and increased visibility of this type of data will provide insight into ways to improve and develop this type of delivery. The key themes that emerged from the analysis of the interview data were: learners profiles and needs, employers drivers, academic staff drivers, organizational approach, tools for collecting data and visibility of findings. The paper concludes with observations on best practice in the collection, analysis and use of WBL SSD, thus offering recommendations for both academic managers and practitioners.

Keywords: Student satisfaction data, work based learning, employer engagement, NSS.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1493

Authors: Hamad Hussain Balhareth, Kecheng Liu, Sharm Manwani

Abstract:

Business and IT alignment has continued as a top concern for business and IT executives for almost three decades. Many researchers have conducted empirical studies on the relationship between business-IT alignment and performance. Yet, these approaches, lacking a social perspective, have had little impact on sustaining performance and competitive advantage. In addition to the limited alignment literature that explores organisational learning that is represented in shared understanding, communication, cognitive maps and experiences. Hence, this paper proposes an integrated process that enables social and intellectual dimensions through the concept of organisational learning. In particular, the feedback and feedforward process which provide a value creation across dynamic multilevel of learning. This mechanism enables on-going effectiveness through development of individuals, groups and organisations, which improves the quality of business and IT strategies and drives to performance.

Keywords: business-IT alignment, social dimension, intellectual dimension, organisational learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1740