Search results for: learning effectiveness

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: Visual search, deep learning, convolutional neural network, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 815

Authors: Nihal Esam Abuzinadah, Areej Abbas Malibari, Arwa Abdulaziz Allinjawi, Paul Krause

Abstract:

Deaf and hearing-impaired students face many obstacles throughout their education, especially with learning applied sciences such as computer programming. In addition, there is no clear signs in the Arabic Sign Language that can be used to identify programming logic terminologies such as while, for, case, switch etc. However, hearing disabilities should not be a barrier for studying purpose nowadays, especially with the rapid growth in educational technology. In this paper, we develop an Avatar based system to teach computer programming to deaf and hearing-impaired students using Arabic Signed language with new signs vocabulary that is been developed for computer programming education. The system is tested on a number of high school students and results showed the importance of visualization in increasing the comprehension or understanding of concepts for deaf students through the avatar.

Keywords: Hearing-impaired students, isolation, self-esteem, learning difficulties.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1202

Authors: Esma Gizem Daskiran, Mehmet Mustafa Daskiran

Abstract:

This paper investigates the effectiveness of two natural zeolites in reducing expansion of concrete due to alkali-silica reaction. These natural zeolites have different reactive silica content. Three aggregates; two natural sands and one crushed stone aggregate were used while preparing mortar bars in accordance with accelerated mortar bar test method, ASTM C1260. Performances of natural zeolites are compared by examining the expansions due to alkali silica reaction. Natural zeolites added to the mixtures at 10% and 20% replacement levels by weight of cement. Natural zeolite with high reactive silica content had better performance on reducing expansions due to ASR. In this research, using high reactive zeolite at 20% replacement levels was effective in mitigating expansions.

Keywords: Alkali silica reaction, natural zeolite, durability, expansion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2585

Authors: Ratima Damkham, Natasha Dejdumrong, Priyakorn Pusawiro

Abstract:

This paper explored the solution in game design to help game designers in the educational game designing using digital educational game model canvas (DEGMC) and digital educational game form (DEGF) based on Outcome-based Education program. DEGMC and DEGF can help designers develop an overview of the game while designing and planning their own game. The way to clearly assess players’ ability from learning outcomes and support their game learning design is by using the tools. Designers can balance educational content and entertainment in designing a game by using the strategies of the Business Model Canvas and design the gameplay and players’ ability assessment from learning outcomes they need by referring to the Constructive Alignment. Furthermore, they can use their design plan in this research to write their Game Design Document (GDD). The success of the research was evaluated by four experts’ perspectives in the education and computer field. From the experiments, the canvas and form helped the game designers model their game according to the learning outcomes and analysis of their own game elements. This method can be a path to research an educational game design in the future.

Keywords: Constructive alignment, constructivist theory, educational game, outcome-based education.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 824

Authors: Yu-Lin Liao, Ya-Fu Peng

Abstract:

An adaptive dynamic cerebellar model articulation controller (DCMAC) neural network used for solving the prediction and identification problem is proposed in this paper. The proposed DCMAC has superior capability to the conventional cerebellar model articulation controller (CMAC) neural network in efficient learning mechanism, guaranteed system stability and dynamic response. The recurrent network is embedded in the DCMAC by adding feedback connections in the association memory space so that the DCMAC captures the dynamic response, where the feedback units act as memory elements. The dynamic gradient descent method is adopted to adjust DCMAC parameters on-line. Moreover, the analytical method based on a Lyapunov function is proposed to determine the learning-rates of DCMAC so that the variable optimal learning-rates are derived to achieve most rapid convergence of identifying error. Finally, the adaptive DCMAC is applied in two computer simulations. Simulation results show that accurate identifying response and superior dynamic performance can be obtained because of the powerful on-line learning capability of the proposed DCMAC.

Keywords: adaptive, cerebellar model articulation controller, CMAC, prediction, identification

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1392

Authors: Carlos Mendez Galindo, Toshiro Hayashikawa, Javier Gil Belda

Abstract:

This paper investigates the effectiveness of the use of seismic isolation devices on the overall 3D seismic response of curved highway viaducts with an emphasis on expansion joints. Furthermore, an evaluation of the effectiveness of the use of cable restrainers is presented. For this purpose, the bridge seismic performance has been evaluated on four different radii of curvature, considering two cases: restrained and unrestrained curved viaducts. Depending on the radius of curvature, three-dimensional non-linear dynamic analysis shows the vulnerability of curved viaducts to pounding and deck unseating damage. In this study, the efficiency of using LRB supports combined with cable restrainers on curved viaducts is demonstrated, not only by reducing in all cases the possible damage, but also by providing a similar behavior in the viaducts despite of curvature radius.

Keywords: Nonlinear dynamic response, seismic design, seismic isolation, unseating prevention system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1845

Authors: Karina Zaccari, Ernesto Cordeiro Marujo

Abstract:

This paper presents a Machine Learning (ML) approach to support Meningitis diagnosis in patients at a children’s hospital in Sao Paulo, Brazil. The aim is to use ML techniques to reduce the use of invasive procedures, such as cerebrospinal fluid (CSF) collection, as much as possible. In this study, we focus on predicting the probability of Meningitis given the results of a blood and urine laboratory tests, together with the analysis of pain or other complaints from the patient. We tested a number of different ML algorithms, including: Adaptative Boosting (AdaBoost), Decision Tree, Gradient Boosting, K-Nearest Neighbors (KNN), Logistic Regression, Random Forest and Support Vector Machines (SVM). Decision Tree algorithm performed best, with 94.56% and 96.18% accuracy for training and testing data, respectively. These results represent a significant aid to doctors in diagnosing Meningitis as early as possible and in preventing expensive and painful procedures on some children.

Keywords: Machine learning, medical diagnosis, meningitis detection, gradient boosting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1091

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 1548

Authors: Nishant Rodrigues, Nicole Spanedda, Chilukuri K. Mohan, Arindam Chakraborty

Abstract:

A crucial objective in quantum chemistry is the computation of the energy levels of chemical systems. This task requires electron-repulsion integrals as inputs and the steep computational cost of evaluating these integrals poses a major numerical challenge in efficient implementation of quantum chemical software. This work presents a moment-based machine learning approach for the efficient evaluation of electron-repulsion integrals. These integrals were approximated using linear combinations of a small number of moments. Machine learning algorithms were applied to estimate the coefficients in the linear combination. A random forest approach was used to identify promising features using a recursive feature elimination approach, which performed best for learning the sign of each coefficient, but not the magnitude. A neural network with two hidden layers was then used to learn the coefficient magnitudes, along with an iterative feature masking approach to perform input vector compression, identifying a small subset of orbitals whose coefficients are sufficient for the quantum state energy computation. Finally, a small ensemble of neural networks (with a median rule for decision fusion) was shown to improve results when compared to a single network.

Keywords: Quantum energy calculations, atomic orbitals, electron-repulsion integrals, ensemble machine learning, random forests, neural networks, feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 141

Authors: Bashaiar Alsanaa

Abstract:

Never has a revolution affected all aspects of humanity as the communication revolution during the past two decades. This revolution, with all its advances and utilities, swept the world thus becoming an integral part of our lives, hence giving way to emerging applications at the social, economic, political, and educational levels. More specifically, such applications have changed the delivery system through which learning is acquired by students. Interaction with educators, accessibility to content, and creative delivery options are but a few facets of the new learning experience now being offered through the use of technology in the educational field. With different success rates, third world countries have tried to pace themselves with use of educational technology in advanced parts of the world. One such country is the small rich-oil state of Kuwait which has tried to adopt the e-educational model, however, an evaluation of such trial is yet to be done. This study aimed to fill the void of research conducted around that topic. The study explored students' acceptance of incorporating communication technologies in higher education in Kuwait. Students' responses to survey questions presented an overview of the e-learning experience in this country, and drew a framework through which implications and suggestions for future research were discussed to better serve the advancement of e-education in developing countries.

Keywords: Communication technologies, E-learning, Kuwait, Social media

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1692

Authors: M. Farshbaf, M. R. Feizi-Derakhshi

Abstract:

Graph partitioning is a NP-hard problem with multiple conflicting objectives. The graph partitioning should minimize the inter-partition relationship while maximizing the intra-partition relationship. Furthermore, the partition load should be evenly distributed over the respective partitions. Therefore this is a multiobjective optimization problem (MOO). One of the approaches to MOO is Pareto optimization which has been used in this paper. The proposed methods of this paper used to improve the performance are injecting best solutions of previous runs into the first generation of next runs and also storing the non-dominated set of previous generations to combine with later generation's non-dominated set. These improvements prevent the GA from getting stuck in the local optima and increase the probability of finding more optimal solutions. Finally, a simulation research is carried out to investigate the effectiveness of the proposed algorithm. The simulation results confirm the effectiveness of the proposed method.

Keywords: Graph partitioning, Genetic algorithm, Multiobjective optimization, Pareto front.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1960

Authors: Yee-May Chan

Abstract:

In recent decades, it is observed that social work agencies have participated actively, and thus, have gradually been more influential in social work education in Hong Kong. The neo-liberal welfare ideologies and changing funding mode have transformed the landscape in social work practice and have also had a major influence on the fieldwork environment in Hong Kong. The aim of this research is to explore the educational role of social work agencies and examine in particular whether they are able to enhance or hinder critical reflective learning in fieldwork. In-depth interviews with 15 frontline social workers and managers in different social work agencies were conducted to collect their views and experience in helping social work students in fieldwork. The overall findings revealed that under the current social welfare context most social workers consider that the most important role of social work agencies in fieldwork is to help students prepare to fit-in the practice requirements and work within agencies’ boundary. The fit-for-purpose and down-to-earth view of fieldwork practice is seen as prevalent among most social workers. This narrow perception of agency’s role seems to be more favourable to competence-based approaches. In contrast, though critical reflection has been seen as important in addressing the changing needs of service users, the role of enhancing critical reflective learning has not been clearly expected or understood by most agency workers. The notion of critical reflection, if considered, has been narrowly perceived in fieldwork learning. The findings suggest that the importance of critical reflection is found to be subordinate to that of practice competence. The lack of critical reflection in the field is somehow embedded in the competence-based social work practice. In general, social work students’ critical reflection has not been adequately supported or enhanced in fieldwork agencies, nor critical reflective practice has been encouraged in fieldwork process. To address this situation, the role of social work agencies in fieldwork should be re-examined. To maximise critical reflective learning in the field, critical reflection as an avowed objective in fieldwork learning should be clearly stated. Concrete suggestions are made to help fieldwork agencies become more prepared to critical reflective learning. It is expected that the research can help social work communities to reflect upon the current realities of fieldwork context and to identify ways to strengthen agencies’ capacities to enhance critical reflective learning and practice of social work students.

Keywords: Competence-based social work, fieldwork, neo-liberal welfare, critical reflective learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 995

Authors: Shankar Subramanian Iyer

Abstract:

The vocational education, enhanced by technology and Recognition of Prior Learning (RPL) is going to be the main ingredient of the future of education. This is coming from the various issues of the current educational system like cost, time, type of course, type of curriculum, unemployment, to name the major reasons. Most millennials like to perform and learn rather than learning how to perform. This is the essence of vocational education be it any field from cooking, painting, plumbing to modern technologies using computers. Even a more theoretical course like entrepreneurship can be taught as to be an entrepreneur and learn about its nuances. The best way to learn accountancy is actually keeping accounts for a small business or grocer and learn the ropes of accountancy and finance. The purpose of this study is to investigate the relationship between vocational skills, RPL and new technologies with future employability. This study implies that individual's knowledge and skills are essential aspects to be emphasized in future education and to give credit for prior experience for future employability. Virtual reality can be used to stimulate workplace situations for vocational learning for fields like hospitality, medical emergencies, healthcare, draughtsman ship, building inspection, quantity surveying, estimation, to name a few. All disruptions in future education, especially vocational education, are going to be technology driven with the advent of AI, ML, IoT, VR, VI etc. Vocational education not only helps institutes cut costs drastically, but allows all students to have hands-on experiences, rather than to be observers. The earlier experiential learning theory and the recent theory of knowledge and skills-based learning modified and applied to the vocational education and development of skills is the proposed contribution of this paper. Apart from secondary research study on major scholarly articles, books, primary research using interviews, questionnaire surveys have been used to validate and test the reliability of the suggested model using Partial Least Square- Structural Equation Method (PLS-SEM), the factors being assimilated using an existing literature review. Major findings have been that there exists high relationship between the vocational skills, RPL, new technology to the future employability through mediation of future employability skills.

Keywords: Vocational education, vocational skills, competencies, modern technologies, Recognition of Prior Learning, RPL.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 747

Authors: Cory A. Bennett

Abstract:

Teaching and learning through the use of discourse support students’ conceptual understanding by attending to key concepts and relationships. One discourse structure used in primary classrooms is number talks wherein students mentally calculate, discuss, and reason about the appropriateness and efficiency of their strategies. In the secondary mathematics classroom, the mathematics understudy does not often lend itself to mental calculations yet learning to reason, and articulate reasoning, is central to learning mathematics. This qualitative case study discusses how one secondary school in the Middle East adapted the number talk protocol for secondary mathematics classrooms. Several challenges in implementing ‘reasoning talks’ became apparent including shifting current discourse protocols and practices to a more student-centric model, accurately recording and probing student thinking, and specifically attending to reasoning rather than computations.

Keywords: Discourse, reasoning, secondary mathematics, teacher development.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 984

Authors: Ellen A. Kalinga, R. B. Bagile Burchard, Lena Trojer

Abstract:

Tanzania secondary schools in rural areas are geographically and socially isolated, hence face a number of problems in getting learning materials resulting in poor performance in National examinations. E-learning as defined to be the use of information and communication technology (ICT) for supporting the educational processes has motivated Tanzania to apply ICT in its education system. There has been effort to improve secondary school education using ICT through several projects. ICT for e-learning to Tanzania rural secondary school is one of the research projects conceived by the University of Dar-es-Salaam through its College of Engineering and Technology. The main objective of the project is to develop a tool to enable ICT support rural secondary school. The project is comprehensive with a number of components, one being development of e-learning management system (e-LMS) for Tanzania secondary schools. This paper presents strategies of developing e-LMS. It shows the importance of integrating action research methodology with the modeling methods as presented by model driven architecture (MDA) and the usefulness of Unified Modeling Language (UML) on the issue of modeling. The benefit of MDA will go along with the development based on software development life cycle (SDLC) process, from analysis and requirement phase through design and implementation stages as employed by object oriented system analysis and design approach. The paper also explains the employment of open source code reuse from open source learning platforms for the context sensitive development of the e-LMS for Tanzania secondary schools.

Keywords: Action Research Methodology, OOSA&D, MDA, UML, Open Source LMS.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2228

Authors: Chaitanya Chawla, Divya Panwar, Gurneesh Singh Anand, M. P. S Bhatia

Abstract:

This paper presents a deep-learning mechanism for classifying computer generated images and photographic images. The proposed method accounts for a convolutional layer capable of automatically learning correlation between neighbouring pixels. In the current form, Convolutional Neural Network (CNN) will learn features based on an image's content instead of the structural features of the image. The layer is particularly designed to subdue an image's content and robustly learn the sensor pattern noise features (usually inherited from image processing in a camera) as well as the statistical properties of images. The paper was assessed on latest natural and computer generated images, and it was concluded that it performs better than the current state of the art methods.

Keywords: Image forensics, computer graphics, classification, deep learning, convolutional neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1163

Authors: Izaz Ahmad, Farhatullah, Shahbaz Ali, Farhad Ali, Faiza, Hazrat Junaid, Farhan Zaid

Abstract:

Current trends in remote health monitoring to monetize on the Internet of Things applications have been raised in efficient and interference free communications in Wireless Body Area Network (WBAN) scenario. Co-existence interference in WBANs have aggravates the over-congested radio bands, thereby requiring efficient Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) strategies and improve interference management. Existing solutions utilize simplistic heuristics to approach interference problems. The scope of this research article is to investigate reinforcement learning for efficient interference management under co-existing scenarios with an emphasis on homogenous interferences. The aim of this paper is to suggest a smart CSMA/CA mechanism based on reinforcement learning called QIM-MAC that effectively uses sense slots with minimal interference. Simulation results are analyzed based on scenarios which show that the proposed approach maximized Average Network Throughput and Packet Delivery Ratio and minimized Packet Loss Ratio, Energy Consumption and Average Delay.

Keywords: WBAN, IEEE 802.15.4 Standard, CAP Super-frame, Q-Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 627

Authors: Fiasal Assiri, Joanna Wincenciak, David Morrison-Love

Abstract:

With the rapid spread of the COVID-19 pandemic, the Saudi government suspended students from going to school to combat the outbreak. As e-learning was not applied at all in schools, online teaching and learning have been revived in Saudi Arabia by providing a new platform called ‘Madrasati’. The Decomposed Theory of Planned Behaviour (DTPB) is used to examine individuals’ intention behaviour in many fields. Nevertheless, the factors that affect teachers’ continuance intention of the Madrasati platform have not yet been investigated. The purpose of this paper is to present a conceptual model in light with DTPB. To enhance the predictability of the model, the study incorporates other variables including learning content quality and interactivity as sub-factors under the perceived usefulness, students and government influences under the subjective norms, and technical support and prior e-learning experience under the perceived behavioural control. The model will be further validated using a mixed methods approach. Such findings would help administrators and stakeholders to understand teachers’ needs and develop new methods that might encourage teachers to continue using Madrasati effectively in their teaching.

Keywords: Madrasati, Decomposed Theory of Planned Behaviour, continuance intention, attitude, subjective norms, perceived behavioural control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 474

Authors: Jung-Eun Park, Kyung-Whan Oh

Abstract:

Intelligent systems are required in order to quickly and accurately analyze enormous quantities of data in the Internet environment. In intelligent systems, information extracting processes can be divided into supervised learning and unsupervised learning. This paper investigates intelligent clustering by unsupervised learning. Intelligent clustering is the clustering system which determines the clustering model for data analysis and evaluates results by itself. This system can make a clustering model more rapidly, objectively and accurately than an analyzer. The methodology for the automatic clustering intelligent system is a multi-agent system that comprises a clustering agent and a cluster performance evaluation agent. An agent exchanges information about clusters with another agent and the system determines the optimal cluster number through this information. Experiments using data sets in the UCI Machine Repository are performed in order to prove the validity of the system.

Keywords: Intelligent Clustering, Multi-Agent System, PCA, SOM, VC(Variance Criterion)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1714

Authors: Walid Cherif

Abstract:

Data mining has, over recent years, seen big advances because of the spread of internet, which generates everyday a tremendous volume of data, and also the immense advances in technologies which facilitate the analysis of these data. In particular, classification techniques are a subdomain of Data Mining which determines in which group each data instance is related within a given dataset. It is used to classify data into different classes according to desired criteria. Generally, a classification technique is either statistical or machine learning. Each type of these techniques has its own limits. Nowadays, current data are becoming increasingly heterogeneous; consequently, current classification techniques are encountering many difficulties. This paper defines new measure functions to quantify the resemblance between instances and then combines them in a new approach which is different from actual algorithms by its reliability computations. Results of the proposed approach exceeded most common classification techniques with an f-measure exceeding 97% on the IRIS Dataset.

Keywords: Data mining, knowledge discovery, machine learning, similarity measurement, supervised classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1518

Authors: Raluca Ionela Maxim

Abstract:

Designing a gender responsive Science, Technology, Engineering and Mathematics (STEM) mobile game based learning solution (mGBL) is a challenge in terms of content, gamification level and equal engagement of girls and boys. The goal of this case study was to research and create a high-fidelity prototype design of a mobile game that contains role-models as avatars that guide and expose girls and boys to STEM learning content. For this research purpose it was applied the methodology of design sprint with five-phase process that combines design thinking principles. The technique of this methodology comprises smart interviews with STEM experts, mind-map creation, sketching, prototyping and usability testing of the interactive prototype of the gender responsive STEM mGBL. The results have shown that the effect of the avatar/role model had a positive impact. Therefore, by exposing students (boys and girls) to STEM role models in an mGBL tool is helpful for the decreasing of the gender inequalities in STEM fields.

Keywords: Design thinking, design sprint, gender-responsive STEM education, mobile game based learning, role-models.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1348

Authors: Mina Alibeigi, Sattar Hashemi, Ali Hamzeh

Abstract:

Since dealing with high dimensional data is computationally complex and sometimes even intractable, recently several feature reductions methods have been developed to reduce the dimensionality of the data in order to simplify the calculation analysis in various applications such as text categorization, signal processing, image retrieval, gene expressions and etc. Among feature reduction techniques, feature selection is one the most popular methods due to the preservation of the original features. In this paper, we propose a new unsupervised feature selection method which will remove redundant features from the original feature space by the use of probability density functions of various features. To show the effectiveness of the proposed method, popular feature selection methods have been implemented and compared. Experimental results on the several datasets derived from UCI repository database, illustrate the effectiveness of our proposed methods in comparison with the other compared methods in terms of both classification accuracy and the number of selected features.

Keywords: Feature, Feature Selection, Filter, Probability Density Function

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2067

Authors: Sobhy Fathy A. Hashesh

Abstract:

This study aimed at investigating the effect of Andalus Knowledge Phases and Times (ANPT) model of learning and the effect of 'Intel Education Contribution in ANPT' on the development of students’ academic performance and emotional quotient. The society of the study composed of Andalus Private Schools, elementary school students (N=700), while the sample of the study composed of four randomly assigned groups (N=80) with one experimental group and one control group to study "ANPT" effect and the "Intel Contribution in ANPT" effect respectively. The study followed the quantitative and qualitative approaches in collecting and analyzing data to answer the study questions. Results of the study revealed that there were significant statistical differences between students’ academic performances and emotional quotients for the favor of the experimental groups. The study recommended applying this model on different educational variables and on other age groups to generate more data leading to more educational results for the favor of students’ learning outcomes.

Keywords: ANPT, Flipped Classroom, 5Es learning Model, Kagan structures.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1252

Authors: Niousha Bagheri Khulenjani, Mohammad Saniee Abadeh

Abstract:

Learning from very big datasets is a significant problem for most present data mining and machine learning algorithms. MicroRNA (miRNA) is one of the important big genomic and non-coding datasets presenting the genome sequences. In this paper, a hybrid method for the classification of the miRNA data is proposed. Due to the variety of cancers and high number of genes, analyzing the miRNA dataset has been a challenging problem for researchers. The number of features corresponding to the number of samples is high and the data suffer from being imbalanced. The feature selection method has been used to select features having more ability to distinguish classes and eliminating obscures features. Afterward, a Convolutional Neural Network (CNN) classifier for classification of cancer types is utilized, which employs a Genetic Algorithm to highlight optimized hyper-parameters of CNN. In order to make the process of classification by CNN faster, Graphics Processing Unit (GPU) is recommended for calculating the mathematic equation in a parallel way. The proposed method is tested on a real-world dataset with 8,129 patients, 29 different types of tumors, and 1,046 miRNA biomarkers, taken from The Cancer Genome Atlas (TCGA) database.

Keywords: Cancer classification, feature selection, deep learning, genetic algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1243

Authors: Anita Khadka, Gregory Epiphaniou, Carsten Maple

Abstract:

There is a dramatic surge in the adoption of Machine Learning (ML) techniques in many areas, including the nuclear industry (such as fault diagnosis and fuel management in nuclear power plants), autonomous systems (including self-driving vehicles), space systems (space debris recovery, for example), medical surgery, network intrusion detection, malware detection, to name a few. Artificial Intelligence (AI) has become a part of everyday modern human life. To date, the predominant focus has been developing underpinning ML algorithms that can improve accuracy, while factors such as resiliency and robustness of algorithms have been largely overlooked. If an adversarial attack is able to compromise the learning method or data, the consequences can be fatal, especially but not exclusively in safety-critical applications. In this paper, we present an in-depth analysis of five adversarial attacks and two defence methods on a crack detection ML model. Our analysis shows that it can be dangerous to adopt ML techniques without rigorous testing, since they may be vulnerable to adversarial attacks, especially in security-critical areas such as the nuclear industry. We observed that while the adopted defence methods can effectively defend against different attacks, none of them could protect against all five adversarial attacks entirely.

Keywords: Resilient Machine Learning, attacks, defences, nuclear industry, crack detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 477

Authors: Matthias Kirmse, Uwe Petersohn, Elief Paffrath

Abstract:

As in today's semiconductor industries test costs can make up to 50 percent of the total production costs, an efficient test error detection becomes more and more important. In this paper, we present a new machine learning approach to test error detection that should provide a faster recognition of test system faults as well as an improved test error recall. The key idea is to learn a classifier ensemble, detecting typical test error patterns in wafer test results immediately after finishing these tests. Since test error detection has not yet been discussed in the machine learning community, we define central problem-relevant terms and provide an analysis of important domain properties. Finally, we present comparative studies reflecting the failure detection performance of three individual classifiers and three ensemble methods based upon them. As base classifiers we chose a decision tree learner, a support vector machine and a Bayesian network, while the compared ensemble methods were simple and weighted majority vote as well as stacking. For the evaluation, we used cross validation and a specially designed practical simulation. By implementing our approach in a semiconductor test department for the observation of two products, we proofed its practical applicability.

Keywords: Ensemble methods, fault detection, machine learning, semiconductor test.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2261

Authors: Peng Hao Wang, Garam Kim, Ronald Sterkenburg

Abstract:

In composite manufacturing, the fabrication of tooling and tooling maintenance contributes to a large portion of the total cost. However, as the applications of composite materials continue to increase, there is also a growing demand for more tooling. The demand for more tooling places heavy emphasis on the industry’s ability to fabricate high quality tools while maintaining the tool’s cost effectiveness. One of the popular techniques of tool fabrication currently being developed utilizes additive manufacturing technology known as 3D printing. The popularity of 3D printing is due to 3D printing’s ability to maintain low material waste, low cost, and quick fabrication time. In this study, a team of Purdue University School of Aviation and Transportation Technology (SATT) faculty and students investigated the effectiveness of a 3D printed composite mold. A steel valve cover from an aircraft reciprocating engine was modeled utilizing 3D scanning and computer-aided design (CAD) to create a 3D printed composite mold. The mold was used to fabricate carbon fiber versions of the aircraft reciprocating engine valve cover. The carbon fiber valve covers were evaluated for dimensional accuracy and quality while the 3D printed composite mold was evaluated for durability and dimensional stability. The data collected from this study provided valuable information in the understanding of 3D printed composite molds, potential improvements for the molds, and considerations for future tooling design.

Keywords: Additive manufacturing, carbon fiber, composite tooling, molds.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 896

Authors: Hager Kammoun, Jean Charles Lamirel, Mohamed Ben Ahmed

Abstract:

In this paper, a model for an information retrieval system is proposed which takes into account that knowledge about documents and information need of users are dynamic. Two methods are combined, one qualitative or symbolic and the other quantitative or numeric, which are deemed suitable for many clustering contexts, data analysis, concept exploring and knowledge discovery. These two methods may be classified as inductive learning techniques. In this model, they are introduced to build “long term" knowledge about past queries and concepts in a collection of documents. The “long term" knowledge can guide and assist the user to formulate an initial query and can be exploited in the process of retrieving relevant information. The different kinds of knowledge are organized in different points of view. This may be considered an enrichment of the exploration level which is coherent with the concept of document/query structure.

Keywords: Information Retrieval Systems, machine learning, classification, Galois lattices, Self Organizing Map.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1181

Authors: Tsuyoshi Okita, Tatsuya Niwa

Abstract:

For a given specific problem an efficient algorithm has been the matter of study. However, an alternative approach orthogonal to this approach comes out, which is called a reduction. In general for a given specific problem this reduction approach studies how to convert an original problem into subproblems. This paper proposes a formal modeling language to support this reduction approach. We show three examples from the wide area of learning problems. The benefit is a fast prototyping of algorithms for a given new problem.

Keywords: Formal language, statistical inference problem, reduction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1605

Authors: Chunming Xu

Abstract:

Sparse representation which can represent high dimensional data effectively has been successfully used in computer vision and pattern recognition problems. However, it doesn-t consider the label information of data samples. To overcome this limitation, we develop a novel dimensionality reduction algorithm namely dscriminatively regularized sparse subspace learning(DR-SSL) in this paper. The proposed DR-SSL algorithm can not only make use of the sparse representation to model the data, but also can effective employ the label information to guide the procedure of dimensionality reduction. In addition,the presented algorithm can effectively deal with the out-of-sample problem.The experiments on gene-expression data sets show that the proposed algorithm is an effective tool for dimensionality reduction and gene-expression data classification.

Keywords: sparse representation, dimensionality reduction, labelinformation, sparse subspace learning, gene-expression data classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1440