Search results for: learning style.

Authors: Xiaodong Li, Peng Gao, Chao-Jung Huang, Shiying Hao, Xuefeng B. Ling, Yongxia Han, Yaqi Zhang, Le Zheng, Chengyin Ye, Modi Liu, Minjie Xia, Changlin Fu, Bo Jin, Karl G. Sylvester, Eric Widen

Abstract:

Predicting the risk of Pancreatic Adenocarcinoma (PA) in advance can benefit the quality of care and potentially reduce population mortality and morbidity. The aim of this study was to develop and prospectively validate a risk prediction model to identify patients at risk of new incident PA as early as 3 months before the onset of PA in a statewide, general population in Maine. The PA prediction model was developed using Deep Neural Networks, a deep learning algorithm, with a 2-year electronic-health-record (EHR) cohort. Prospective results showed that our model identified 54.35% of all inpatient episodes of PA, and 91.20% of all PA that required subsequent chemoradiotherapy, with a lead-time of up to 3 months and a true alert of 67.62%. The risk assessment tool has attained an improved discriminative ability. It can be immediately deployed to the health system to provide automatic early warnings to adults at risk of PA. It has potential to identify personalized risk factors to facilitate customized PA interventions.

Keywords: Cancer prediction, deep learning, electronic health records, pancreatic adenocarcinoma.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 783

Authors: Truong Quang Dang Khoa, Masahiro Nakagawa

Abstract:

Chaos and fractals are novel fields of physics and mathematics showing up a new way of universe viewpoint and creating many ideas to solve several present problems. In this paper, a novel algorithm based on the chaotic sequence generator with the highest ability to adapt and reach the global optima is proposed. The adaptive ability of proposal algorithm is flexible in 2 steps. The first one is a breadth-first search and the second one is a depth-first search. The proposal algorithm is examined by 2 functions, the Camel function and the Schaffer function. Furthermore, the proposal algorithm is applied to optimize training Multilayer Neural Networks.

Keywords: learning and evolutionary computing, Chaos Optimization Algorithm, Artificial Neural Networks, nonlinear optimization, intelligent computational technologies.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1762

Authors: Chia-Jung Chen, Rong-Shine Lin, Rong-Guey Chang

Abstract:

As networking has become popular, Web-learning tends to be a trend while designing a tool. Moreover, five-axis machining has been widely used in industry recently; however, it has potential axial table colliding problems. Thus this paper aims at proposing an efficient web-learning collision detection tool on five-axis machining. However, collision detection consumes heavy resource that few devices can support, thus this research uses a systematic approach based on web knowledge to detect collision. The methodologies include the kinematics analyses for five-axis motions, separating axis method for collision detection, and computer simulation for verification. The machine structure is modeled as STL format in CAD software. The input to the detection system is the g-code part program, which describes the tool motions to produce the part surface. This research produced a simulation program with C programming language and demonstrated a five-axis machining example with collision detection on web site. The system simulates the five-axis CNC motion for tool trajectory and detects for any collisions according to the input g-codes and also supports high-performance web service benefiting from C. The result shows that our method improves 4.5 time of computational efficiency, comparing to the conventional detection method.

Keywords: Collision detection, Five-axis machining, Separating axis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2163

Authors: Sajjad Hashemi, Khalil Monfaredi, Mohammad Masdari

Abstract:

Cloud computing is a style of computing which is formed from the aggregation and development of technologies such as grid computing distributed computing, parallel computing and service-oriented architecture. And its aim is to provide computing, communication and storage resources in a safe environment based on service, as fast as possible, which is virtually provided via Internet platform. Considering that the provided Services in e-government are available via the Internet, thus cloud computing can be used in the implementation of e-government architecture and provide better service with the lowest economic cost using its benefits. In this paper, the Methods of using cloud computing in e-government has been studied and it's been attempted to identify the challenges and benefits of the cloud to get used in the e-government and proposals have been offered to overcome its shortcomings, encourage and partnership of governments and people to use this economical and new technology.

Keywords: Benefits, Cloud computing, Committee, Challenges, E-Government, Participation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9887

Authors: Anna Mirzaiyan, Vahid Parvaresh, Mahmoud Hashemian, Masoud Saeedi

Abstract:

People usually have a telephone voice, which means they adjust their speech to fit particular situations and to blend in with other interlocutors. The question is: Do we speak differently to different people? This possibility has been suggested by social psychologists within Accommodation Theory [1]. Converging toward the speech of another person can be regarded as a polite speech strategy while choosing a language not used by the other interlocutor can be considered as the clearest example of speech divergence [2]. The present study sets out to investigate such processes in the course of everyday telephone conversations. Using Joos-s [3] model of formality in spoken English, the researchers try to explore convergence to or divergence from the addressee. The results propound the actuality that lexical choice, and subsequently, patterns of style vary intriguingly in concordance with the person being addressed.

Keywords: Convergence, divergence, lexical formality, speechaccommodation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3499

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125 Hz to 8000 Hz. The data contain patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R2 values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R2 values for the best models for KNN ranges from .89 to .95. The best imputation models received R2 between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our imputation models versus constant imputations by a two percent increase.

Keywords: Machine Learning, audiograms, data imputations, single imputations.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 103

Authors: Swathi Ganesan, Nalinda Somasiri, Rebecca Jeyavadhanam, Gayathri Karthick

Abstract:

The COVID-19 crisis presents a substantial and critical hazard to worldwide health. Since the occurrence of the disease in late January 2020 in the UK, the number of infected people confirmed to acquire the illness has increased tremendously across the country, and the number of individuals affected is undoubtedly considerably high. The purpose of this research is to figure out a predictive machine learning (ML) archetypal that could forecast the COVID-19 cases within the UK. This study concentrates on the statistical data collected from 31st January 2020 to 31st March 2021 in the United Kingdom. Information on total COVID-19 cases registered, new cases encountered on a daily basis, total death registered, and patients’ death per day due to Coronavirus is collected from World Health Organization (WHO). Data preprocessing is carried out to identify any missing values, outliers, or anomalies in the dataset. The data are split into 8:2 ratio for training and testing purposes to forecast future new COVID-19 cases. Support Vector Machine (SVM), Random Forest (RF), and linear regression (LR) algorithms are chosen to study the model performance in the prediction of new COVID-19 cases. From the evaluation metrics such as r-squared value and mean squared error, the statistical performance of the model in predicting the new COVID-19 cases is evaluated. RF outperformed the other two ML algorithms with a training accuracy of 99.47% and testing accuracy of 98.26% when n = 30. The mean square error obtained for RF is 4.05e11, which is lesser compared to the other predictive models used for this study. From the experimental analysis, RF algorithm can perform more effectively and efficiently in predicting the new COVID-19 cases, which could help the health sector to take relevant control measures for the spread of the virus.

Keywords: COVID-19, machine learning, supervised learning, unsupervised learning, linear regression, support vector machine, random forest.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 133

Authors: Eu Tteum Ha, Kwang Ryel Ryu

Abstract:

As smartphones are equipped with various sensors, there have been many studies focused on using these sensors to create valuable applications. Human activity recognition is one such application motivated by various welfare applications, such as the support for the elderly, measurement of calorie consumption, lifestyle and exercise patterns analyses, and so on. One of the challenges one faces when using smartphone sensors for activity recognition is that the number of sensors should be minimized to save battery power. In this paper, we show that a fairly accurate classifier can be built that can distinguish ten different activities by using only a single sensor data, i.e., the smartphone accelerometer data. The approach that we adopt to deal with this twelve-class problem uses various methods. The features used for classifying these activities include not only the magnitude of acceleration vector at each time point, but also the maximum, the minimum, and the standard deviation of vector magnitude within a time window. The experiments compared the performance of four kinds of basic multi-class classifiers and the performance of four kinds of ensemble learning methods based on three kinds of basic multi-class classifiers. The results show that while the method with the highest accuracy is ECOC based on Random forest.

Keywords: Ensemble learning, activity recognition, smartphone accelerometer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2147

Authors: Zahra Ramezanpanah, Joachim Carvallo, Aurelien Rodriguez

Abstract:

This paper aims to detect anomalies in streaming data using machine learning algorithms. In this regard, we designed two separate pipelines and evaluated the effectiveness of each separately. The first pipeline, based on supervised machine learning methods, consists of two phases. In the first phase, we trained several supervised models using the UNSW-NB15 data set. We measured the efficiency of each using different performance metrics and selected the best model for the second phase. At the beginning of the second phase, we first, using Argus Server, sniffed a local area network. Several types of attacks were simulated and then sent the sniffed data to a running algorithm at short intervals. This algorithm can display the results of each packet of received data in real-time using the trained model. The second pipeline presented in this paper is based on unsupervised algorithms, in which a Temporal Graph Network (TGN) is used to monitor a local network. The TGN is trained to predict the probability of future states of the network based on its past behavior. Our contribution in this section is introducing an indicator to identify anomalies from these predicted probabilities.

Keywords: Cyber-security, Intrusion Detection Systems, Temporal Graph Network, Anomaly Detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 454

Authors: N. Z. Azlan, H. Yamaura

Abstract:

The experimental study of position control of a light weight and small size robotic finger during non-contact motion is presented in this paper. The finger possesses fingertip pinching and self adaptive grasping capabilities, and is made of a seven bar linkage mechanism with a slider in the middle phalanx. The control system is tested under the Proportional Integral Derivative (PID) control algorithm and Recursive Least Square (RLS) based Feedback Error Learning (FEL) control scheme to overcome the uncertainties present in the plant. The experiments conducted in Matlab Simulink and xPC Target environments show that the overall control strategy is efficient in controlling the finger movement.

Keywords: Anthropomorphic finger, position control, feedback error learning, experimental study

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1559

Authors: Eric P. Jiang

Abstract:

As the Internet continues to grow at a rapid pace as the primary medium for communications and commerce and as telecommunication networks and systems continue to expand their global reach, digital information has become the most popular and important information resource and our dependence upon the underlying cyber infrastructure has been increasing significantly. Unfortunately, as our dependency has grown, so has the threat to the cyber infrastructure from spammers, attackers and criminal enterprises. In this paper, we propose a new machine learning based network intrusion detection framework for cyber security. The detection process of the framework consists of two stages: model construction and intrusion detection. In the model construction stage, a semi-supervised machine learning algorithm is applied to a collected set of network audit data to generate a profile of normal network behavior and in the intrusion detection stage, input network events are analyzed and compared with the patterns gathered in the profile, and some of them are then flagged as anomalies should these events are sufficiently far from the expected normal behavior. The proposed framework is particularly applicable to the situations where there is only a small amount of labeled network training data available, which is very typical in real world network environments.

Keywords: classification, data analysis and mining, network intrusion detection, semi-supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1781

Authors: Zelal Çinar

Abstract:

This paper aims to expose the effects of the ideological program of Turkish Republic on city planning, through the first plan of Ankara. As the new capital, Ankara was planned to be the ‘showcase’ of modern Turkey. It was to represent all new ideologies and the country’s cultural similarities with the west. At the same time it was to underline the national identity and independence of Turkish republic. To this end, a new plan for the capital was designed by German city planner Carl Christopher Lörcher. Diametrically opposed with the existing fabric of the city, this plan was built on the basis of papers and plans, on ideological aims. On the contrary, this paper argues that the city is a machine of possibilities, rather than a clear, materialized system.

Keywords: Architecture, ideology, modernization, urban planning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1826

Authors: Konstantinos E. Evangelidis, Evangelos Kehris, Theodore H. Kaskalis

Abstract:

We propose that Virtual Learning Environments (VLEs) should be designed by taking into account the characteristics, the special needs and the specific operating rules of the academic institutions in which they are employed. In this context, we describe a VLE module that extends the support of the organization and delivery of course material by including administration activities related to the various stages of teaching. These include the co-ordination, collaboration and monitoring of the course material development process and institution-specific course material delivery modes. Our specialized module, which enhances VLE capabilities by Helping Educators and Learners through a Laboratory Assistance System, is willing to assist the Greek tertiary technological sector, which includes Technological Educational Institutes (T.E.I.).

Keywords: Virtual learning environments, Teachingcoordination, Laboratorial education, Technological institutes.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1355

Authors: Ang Ling Weay, Mona Masood

Abstract:

This paper discusses the potential benefits of an interactive multimedia information representation in enhancing students’ critical thinking aligned with history reasoning in learning history amongst Secondary School students in Malaysia. Two modes of multimedia information representation were implemented; chronologic and thematic information representations. A qualitative study of an unstructured interview was conducted among two history teachers, one history education lecturer, two i-think experts, and five students from Form Four secondary school. The interview was to elicit their opinions on the implementation of thinking maps and interactive multimedia information representation in history learning. The key elements of the interactive multimedia (e.g. multiple media, user control, interactivity and use of timelines and concept maps) were then considered to improve the learning process. Findings of the preliminary investigation reveal that the interactive multimedia information representations have the potential benefits to be implemented as an instructional resource in enhancing students’ higher order thinking skills (HOTs). This paper concludes by giving suggestions for future work.

Keywords: Multimedia Information Representation, Critical Thinking, History Reasoning, Chronological and Thematic Information Representation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2370

Authors: Amira, A. Goma, U. E. Mahrous

Abstract:

Measuring the effect of perinatal lead exposure on learning ability of offspring is considered as a sensitive and selective index for providing an early marker for central nervous system damage produced by this toxic metal. A total of 35 Sprague-Dawley adult rats were used to investigate the effect of lead acetate toxicity on behavioral patterns of adult female rats and learning ability of offspring. Rats were allotted into 4 groups, group one received 1g/l lead acetate (n=10), group two received 1.5g/l lead acetate (n=10), group three received 2g/l lead acetate in drinking water (n=10) and control group did not receive lead acetate (n=5) from 8^th day of pregnancy till weaning of pups.

The obtained results revealed a dose dependent increase in the feeding time, drinking frequency, licking frequency, scratching frequency, licking litters, nest building and retrieving frequencies, while standing time increased significantly in rats treated with 1.5g/l lead acetate than other treated groups and control, on contrary lying time decreased gradually in a dose dependent manner. Moreover, movement activities were higher in rats treated with 1g/l lead acetate than other treated groups and control. Furthermore, time spent in closed arms was significantly lower in rats given 2g/l lead acetate than other treated groups, while, they spent significantly much time spent in open arms than other treated groups which could be attributed to occurrence of adaptation. Furthermore, number of entries in open arms was dose dependent. However, the ratio between open/closed arms revealed a significant decrease in rats treated with 2g/l lead acetate than control group.

Keywords: Lead toxicity, rats, learning ability, behavior.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2667

Authors: Alfonso Bastías, Álvaro González

Abstract:

The actual grow of the infrastructure in develop country require sophisticate ways manage the operation and control the quality served. This research wants to concentrate in the operation of this infrastructure beyond the construction. The infrastructure-s operation involves an uncertain environment, where unexpected variables are present every day and everywhere. Decision makers need to make right decisions with right information/data analyzed most in real time. To adequately support their decisions and decrease any negative impact and collateral effect, they need to use computational tools called decision support systems (DSS), but now the main source of information came from common users thought an extensive crowdsourcing

Keywords: Crowdsourcing, Learning Systems, Decision Support Systems, Infrastructure, Construction.

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

Authors: Kerstin Grunden, Ann Svensson, Berit Forsman, Christina Karlsson, Ayman Obeid

Abstract:

The research question of the article is to explore whether the dialogue meetings method could be relevant for reflective learning among researchers and practitioners when welfare technology should be implemented in municipalities, or not. A testbed was planned to be implemented in a retirement home in a Swedish municipality, and the practitioners worked with a pre-study of that testbed. In the article, the dialogue between the researchers and the practitioners in the dialogue meetings is described and analyzed. The potential of dialogue meetings as an arena for learning and reflection among researchers and practitioners is discussed. The research methodology approach is participatory action research with mixed methods (dialogue meetings, focus groups, participant observations). The main findings from the dialogue meetings were that the researchers learned more about the use of traditional research methods, and the practitioners learned more about how they could improve their use of the methods to facilitate change processes in their organization. These findings have the potential both for the researchers and the practitioners to result in more relevant use of research methods in change processes in organizations. It is concluded that dialogue meetings could be relevant for reflective learning among researchers and practitioners when welfare technology should be implemented in a health care organization.

Keywords: Dialogue meetings, implementation, reflection, test bed, welfare technology, participatory action research.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 438

Authors: Ashly Joseph, Jithu Paulose

Abstract:

The increased usage of cloud computing has revolutionized the IT landscape, but it has also raised new security concerns. DevSecOps emerged as a way for tackling these difficulties by integrating security into the software development process. However, the rising complexity and sophistication of cyber threats need more advanced solutions. This paper looks into the usage of artificial intelligence (AI) techniques in the DevSecOps framework to increase cloud security. This study uses quantitative and qualitative techniques to assess the usefulness of AI approaches such as machine learning, natural language processing, and deep learning in reducing security issues. This paper thoroughly examines the symbiotic relationship between AI and DevSecOps, concentrating on how AI may be seamlessly integrated into the continuous integration and continuous delivery (CI/CD) pipeline, automated security testing, and real-time monitoring methods. The findings emphasize AI's huge potential to improve threat detection, risk assessment, and incident response skills. Furthermore, the paper examines the implications and challenges of using AI in DevSecOps workflows, considering factors like as scalability, interpretability, and adaptability. This paper adds to a better understanding of AI's revolutionary role in cloud security and provides valuable insights for practitioners and scholars in the field.

Keywords: Cloud Security, DevSecOps, Artificial Intelligence, AI, Machine Learning, Natural Language Processing, NLP, cybersecurity, AI-driven Security.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 61

Authors: Babatunde Kasim Oladele

Abstract:

One of the major objectives of the Nigeria national policy on education is the provision of equal educational opportunities to all citizens at different levels of education. With regards to higher education, an aspect of the policy encourages distance learning to be organized and delivered by tertiary institutions in Nigeria. This study therefore, determines how much of the Government resources are committed, how the resources are utilized and what alternative sources of funding are available for this system of education. This study investigated the trends in recurrent costs between 2004/2005 and 2013/2014 at University of Ibadan Distance Learning Centre (DLC). A descriptive survey research design was employed for the study. Questionnaire was the research instrument used for the collection of data. The population of the study was 280 current distance learning education students, 70 academic staff and 50 administrative staff. Only 354 questionnaires were correctly filled and returned. Data collected were analyzed and coded using the frequencies, ratio, average and percentages were used to answer all the research questions. The study revealed that staff salaries and allowances of academic and non-academic staff represent the most important variable that influences the cost of education. About 55% of resources were allocated to this sector alone. The study also indicates that costs rise every year with increase in enrolment representing a situation of diseconomies of scale. This study recommends that Universities who operates distance learning program should strive to explore other internally generated revenue option to boost their revenue. University of Ibadan, being the premier university in Nigeria, should be given foreign aid and home support, both financially and materially, to enable the institute to run a formidable distance education program that would measure up in planning and implementation with those of developed nation.

Keywords: Open education, distance education, University of Ibadan, cost of education, Nigeria.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 916

Authors: Ana Mafalda Gonçalves, Neuza Pedro

Abstract:

The evolution of ICT has changed all sections of society and these changes have been creating an irreversible impact on higher education institutions, which are expected to adopt innovative technologies in their teaching practices. As theorical framework this study select Rogers theory of innovation diffusion which is widely used to illustrate how technologies move from a localized invented to a widespread evolution on organizational practices. Based on descriptive statistical data collected in a European higher education institution three years longitudinal study was conducted for analyzing and discussion the different stages of a LMS adoption process. Results show that ICT integration in higher education is not progressively successful and a linear process and multiple aspects must be taken into account.

Keywords: e-learning, higher education, LMS, innovation, technologies

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2443

Authors: Carlos V. Regueiro, Jose E. Domenech, Roberto Iglesias, Jose L. Correa

Abstract:

In this work a visual and reactive contour following behaviour is learned by reinforcement. With artificial vision the environment is perceived in 3D, and it is possible to avoid obstacles that are invisible to other sensors that are more common in mobile robotics. Reinforcement learning reduces the need for intervention in behaviour design, and simplifies its adjustment to the environment, the robot and the task. In order to facilitate its generalisation to other behaviours and to reduce the role of the designer, we propose a regular image-based codification of states. Even though this is much more difficult, our implementation converges and is robust. Results are presented with a Pioneer 2 AT on a Gazebo 3D simulator.

Keywords: Image-based State Codification, Mobile Robotics, ReinforcementLearning, Visual Behaviour.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1586

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: Deep learning, data mining, gender predication, MOOCs.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1335

Authors: Adriano Bessa Albuquerque, Francisco Jose Barreto Nunes

Abstract:

Software vulnerabilities are increasing and not only impact services and processes availability as well as information confidentiality, integrity and privacy, but also cause changes that interfere in the development process. Security test could be a solution to reduce vulnerabilities. However, the variety of test techniques with the lack of real case studies of applying tests focusing on software development life cycle compromise its effective use. This paper offers an overview of how a Systematic Mapping Study (MS) about security verification, validation and test (VVT) was performed, besides presenting general results about this study.

Keywords: Software test, software security verification validation and test, security test institutionalization, systematic mapping study.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1600

Authors: F. Apaydın

Abstract:

In this empirical research, how marketing managers evaluate their firms- performances and decide to make innovation is examined. They use some standards which are past performance of the firm, target performance of the firm, competitor performance, and average performance of the industry to compare and evaluate the firms- performances. It is hypothesized that marketing managers and owners of the firm compare the firms- current performance with these four standards at the same time to decide when to make innovation relating to any aspects of the firm, either management style or products. Relationship between the comparison of the firm-s performance with these standards and innovation are searched in the same regression model. The results of the regression analysis are discussed and some recommendations are made for future studies and applicants.

Keywords: Innovation, performance evaluation standards

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1490

Authors: M. Kobylanski, D. Buskulic, P.-H. Duron, D. Revuz, F. Ruggieri, E. Sandier, C. Tijus

Abstract:

In order to design a cooperative e-learning platform, we observed teams of Teacher [T], Computer Scientist [CS] and exerciser's programmer-designer [ED] cooperating for the conception of a self-correcting exercise, but without the use of such a device in order to catch the kind of interactions a useful platform might provide. To do so, we first run a task analysis on how T, CS and ED should be cooperating in order to achieve, at best, the task of creating and implementing self-directed, self-paced, repeatable self-correcting exercises (RSE) in the context of open educational resources. The formalization of the whole process was based on the “objectives, activities and evaluations” theory of educational task analysis. Second, using the resulting frame as a “how-to-do it” guide, we run a series of three contrasted Hackathon of RSE-production to collect data about the cooperative process that could be later used to design the collaborative e-learning platform. Third, we used two complementary methods to collect, to code and to analyze the adequate survey data: the directional flow of interaction among T-CS-ED experts holding a functional role, and the Means-End Problem Solving analysis. Fourth, we listed the set of derived recommendations useful for the design of the exerciser as a cooperative e-learning platform. Final recommendations underline the necessity of building (i) an ecosystem that allows to sustain teams of T-CS-ED experts, (ii) a data safety platform although offering accessibility and open discussion about the production of exercises with their resources and (iii) a good architecture allowing the inheritance of parts of the coding of any exercise already in the data base as well as fast implementation of new kinds of exercises along with their associated learning activities.

Keywords: Distance open educational resources, pedagogical alignment, self-correcting exercises, teacher’s involvement, team roles.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 489

Authors: Sri Sumartiningsih, Anies Setiowati

Abstract:

The purpose of this study is to investigate the influence of breaststroke swimming exercise to improving the peak expiratory flow. Methode: This study used 17 students of men aged 19-21 years, APE values measured before and after the study. Style swimming workout done in accordance with a program that has been made. Result: Value of peak expiratory flow in male students obtained on average before exercise (530 ± 15 811) liters / min and after doing the exercises (540.59 ± 17 092) liters / minute. Paired ttest showed t = -6.446 and p = 0.000, which means there are differences in peak expiratory flow values before and after exercise swimming breaststroke. Conclusion: The conclusion is the breaststroke swimming exercise can be improving of peak expiratory flow.

Keywords: Breaststroke, peak expiratory flow.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2551

Authors: Yusoff Y. S., Streftaris, G., Waters, H. R

Abstract:

Death within 30 days is an important factor to be looked into, as there is a significant risk of deaths immediately following or soon after, myocardial infarction (MI) or stroke. In this paper, we will model the deaths within 30 days following a myocardial infarction (MI) or stroke in the UK. We will see how the probabilities of sudden deaths from MI or stroke have changed over the period 1981-2000. We will model the sudden deaths using a generalized linear model (GLM), fitted using the R statistical package, under a Binomial distribution for the number of sudden deaths. We parameterize our model using the extensive and detailed data from the Framingham Heart Study, adjusted to match UK rates. The results show that there is a reduction for the sudden deaths following a MI over time but no significant improvement for sudden deaths following a stroke.

Keywords: Sudden deaths, myocardial infarction, stroke, ischemic heart disease.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1773

Authors: Nhon Do, Thuong Huynh, An Pham

Abstract:

Nowadays, organizing a repository of documents and resources for learning on a special field as Information Technology (IT), together with search techniques based on domain knowledge or document-s content is an urgent need in practice of teaching, learning and researching. There have been several works related to methods of organization and search by content. However, the results are still limited and insufficient to meet user-s demand for semantic document retrieval. This paper presents a solution for the organization of a repository that supports semantic representation and processing in search. The proposed solution is a model which integrates components such as an ontology describing domain knowledge, a database of document repository, semantic representation for documents and a file system; with problems, semantic processing techniques and advanced search techniques based on measuring semantic similarity. The solution is applied to build a IT learning materials management system of a university with semantic search function serving students, teachers, and manager as well. The application has been implemented, tested at the University of Information Technology, Ho Chi Minh City, Vietnam and has achieved good results.

Keywords: document retrieval system, knowledgerepresentation, document representation, semantic search, ontology.

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

Authors: Rampal Singh, S. Balasundaram

Abstract:

In this paper, we study the application of Extreme Learning Machine (ELM) algorithm for single layered feedforward neural networks to non-linear chaotic time series problems. In this algorithm the input weights and the hidden layer bias are randomly chosen. The ELM formulation leads to solving a system of linear equations in terms of the unknown weights connecting the hidden layer to the output layer. The solution of this general system of linear equations will be obtained using Moore-Penrose generalized pseudo inverse. For the study of the application of the method we consider the time series generated by the Mackey Glass delay differential equation with different time delays, Santa Fe A and UCR heart beat rate ECG time series. For the choice of sigmoid, sin and hardlim activation functions the optimal values for the memory order and the number of hidden neurons which give the best prediction performance in terms of root mean square error are determined. It is observed that the results obtained are in close agreement with the exact solution of the problems considered which clearly shows that ELM is a very promising alternative method for time series prediction.

Keywords: Chaotic time series, Extreme learning machine, Generalization performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3497

Authors: Nebi Gedik

Abstract:

Regardless of age or gender, cardiovascular illnesses are a serious health concern because of things like poor eating habits, stress, a sedentary lifestyle, hard work schedules, alcohol use, and weight. It tends to happen suddenly and has a high rate of recurrence. Machine learning models can be implemented to assist healthcare systems in the accurate detection and diagnosis of cardiovascular disease (CVD) in patients. Improved heart failure prediction is one of the primary goals of researchers using the heart disease dataset. The purpose of this study is to identify the feature or features that offer the best classification prediction for CVD detection. The support vector machine classifier is used to compare each feature's performance. It has been determined which feature produces the best results.

Keywords: Cardiovascular disease, feature extraction, supervised learning, support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 109