Search results for: learning object

Authors: Κonstantinos Kalovrektis, Chryssanthi Palazi

Abstract:

Schools today face ever-increasing demands in their attempts to ensure that students are well equipped to enter the workforce and navigate a complex world. Research indicates that computer technology can help support learning, implementation of various experiments or learning games, and that it is especially useful in developing the higher-order skills of critical thinking, observation, comprehension, implementation, comparison, analysis and active attention to activities such as research, field work, simulations and scientific inquiry. The ICT in education supports the learning procedure by enabling it to be more flexible and effective, create a rich and attractive training environment and equip the students with knowledge and potential useful for the competitive social environment in which they live. This paper presents the design, the development, and the results of the evaluation analysis of an interactive educational game which using real electric vehicles - toys (material) on a toy race track. When the game starts each student selects a specific vehicle toy. Then students are answering questionnaires in the computer. The vehicles' speed is related to the percentage of right answers in a multiple choice questionnaire (software). Every question has its own significant value depending of the different level of questionnaire. Via the developed software, each right or wrong answers in questionnaire increase or decrease the real time speed of their vehicle toys. Moreover the rate of vehicle's speed increase or decrease depends on the difficulty level of each question. The aim of the work is to attract the student’s interest in a learning process and also to improve their scores. The developed real time game was tested using independent populations of students of age groups: 8-10, 11-14, 15-18 years. Standard educational and statistical analysis tools were used for the evaluation analysis of the game. Results reveal that students using the developed real time control game scored much higher (60%) than students using a traditional simulation game on the same questionnaire. Results further indicate that student's interest in repeating the developed real time control gaming was far higher (70%) than the interest of students using a traditional simulation game.

Keywords: Real time game, sensor, learning games, LabVIEW

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1731

Authors: Pan Long, Bi Dongjie, Li Xifeng, Xie Yongle

Abstract:

The near-field synthetic aperture radar (SAR) imaging is an advanced nondestructive testing and evaluation (NDT&E) technique. This paper investigates the complex-valued signal processing related to the near-field SAR imaging system, where the measurement data turns out to be noncircular and improper, meaning that the complex-valued data is correlated to its complex conjugate. Furthermore, we discover that the degree of impropriety of the measurement data and that of the target image can be highly correlated in near-field SAR imaging. Based on these observations, A modified generalized sparse Bayesian learning algorithm is proposed, taking impropriety and noncircularity into account. Numerical results show that the proposed algorithm provides performance gain, with the help of noncircular assumption on the signals.

Keywords: Complex-valued signal processing, synthetic aperture radar (SAR), 2-D radar imaging, compressive sensing, Sparse Bayesian learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1526

Authors: Sh. Yasini, M. B. Naghibi-Sistani, A. Karimpour

Abstract:

This paper employs a new approach to regulate the blood glucose level of type I diabetic patient under an intensive insulin treatment. The closed-loop control scheme incorporates expert knowledge about treatment by using reinforcement learning theory to maintain the normoglycemic average of 80 mg/dl and the normal condition for free plasma insulin concentration in severe initial state. The insulin delivery rate is obtained off-line by using Qlearning algorithm, without requiring an explicit model of the environment dynamics. The implementation of the insulin delivery rate, therefore, requires simple function evaluation and minimal online computations. Controller performance is assessed in terms of its ability to reject the effect of meal disturbance and to overcome the variability in the glucose-insulin dynamics from patient to patient. Computer simulations are used to evaluate the effectiveness of the proposed technique and to show its superiority in controlling hyperglycemia over other existing algorithms

Keywords: Insulin Delivery rate, Q-learning algorithm, Reinforcement learning, Type I diabetes.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2200

Authors: Sivapalan, S., Subramaniam, G., Clifford, M.J., Balbir Singh, M.S., Abdullah, A

Abstract:

Higher education has an important role to play in advocating environmentalism. Given this responsibility, the goal of higher education should therefore be to develop graduates with the knowledge, skills and values related to environmentalism. However, research indicates that there is a lack of consciousness amongst graduates on the need to be more environmentally aware, especially when it comes to applying the appropriate knowledge and skills related to environmentalism. Although institutions of higher learning do include environmental parameters within their undergraduate and postgraduate academic programme structures, the environmental boundaries are usually confined to specific engineering majors within an engineering programme. This makes environmental knowledge, skills and values exclusive to certain quarters of the higher education system. The incorporation of environmental literacy within higher education institutions as a whole is of utmost pertinence if a nation-s human capital is to be nurtured to become change agents for the preservation of environment. This paper discusses approaches that can be adapted by institutions of higher learning to include environmental literacy within the graduate-s higher learning experience.

Keywords: Higher education, engineering education, environmental literacy, Malaysia.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1674

Authors: Anne-Lena Kampen, Øivind Kure

Abstract:

Machine learning (ML) can be implemented in Wireless Sensor Networks (WSNs) as a central solution or distributed solution where the ML is embedded in the nodes. Embedding improves privacy and may reduce prediction delay. In addition, the number of transmissions is reduced. However, quality factors such as prediction accuracy, fault detection efficiency and coordinated control of the overall system suffer. Here, we discuss and highlight the trade-offs that should be considered when choosing between embedding and centralized ML, especially for multihop networks. In addition, we present estimations that demonstrate the energy trade-offs between embedded and centralized ML. Although the total network energy consumption is lower with central prediction, it makes the network more prone for partitioning due to the high forwarding load on the one-hop nodes. Moreover, the continuous improvements in the number of operations per joule for embedded devices will move the energy balance toward embedded prediction.

Keywords: Central ML, embedded machine learning, energy consumption, local ML, Wireless Sensor Networks, WSN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 828

Authors: Almutasim Billa A. Alanazi, Hal S. Tharp

Abstract:

Safe performance and efficient energy consumption are essential factors for designing a control system. This paper presents a reinforcement learning (RL) model that can be applied to control applications to improve safety and reduce energy consumption. As hardware constraints and environmental disturbances are imprecise and unpredictable, conventional control methods may not always be effective in optimizing control designs. However, RL has demonstrated its value in several artificial intelligence (AI) applications, especially in the field of control systems. The proposed model intelligently monitors a system's success by observing the rewards from the environment, with positive rewards counting as a success when the controlled reference is within the desired operating zone. Thus, the model can determine whether the system is safe to continue operating based on the designer/user specifications, which can be adjusted as needed. Additionally, the controller keeps track of energy consumption to improve energy efficiency by enabling the idle mode when the controlled reference is within the desired operating zone, thus reducing the system energy consumption during the controlling operation. Water temperature control for a hydroponic system is taken as a case study for the RL model, adjusting the variance of disturbances to show the model’s robustness and efficiency. On average, the model showed safety improvement by up to 15% and energy efficiency improvements by 35%-40% compared to a traditional RL model.

Keywords: Control system, hydroponics, machine learning, reinforcement learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 207

Authors: Chad Goldsworthy, B. Rajeswari Matam

Abstract:

The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.

Keywords: Convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1420

Authors: Joel S. Mtebe, Aron Kondoro, Mussa M. Kissaka, Elia Kibga

Abstract:

Sub-Saharan Africa is described as the second fastest growing in mobile phone penetration in the world more than in the United States or the European Union. Mobile phones have been used to provide a lot of opportunities to improve people’s lives in the region such as in banking, marketing, entertainment, and paying for various bills such as water, TV, and electricity. However, the potential of mobile phones to enhance teaching and learning has not been explored. This study presents an experience of developing and delivering SMS based quiz questions used to assess mastery of subject content knowledge of science and mathematics secondary school teachers in Tanzania. The SMS quizzes were used as a follow up support mechanism to 500 teachers who participated in a project to upgrade subject content knowledge of teachers in science and mathematics subjects in Tanzania. Quizzes of 10-15 questions were sent to teachers each week for 8 weeks and the results were analyzed using SPSS. Results show that teachers who participated in chemistry and biology subjects have better performance compared to those who participated in mathematics and physics subjects. Teachers reported some challenges that led to poor performance, This research has several practical implications for those who are implementing or planning to use mobile phones in teaching and learning especially in rural secondary schools in sub-Saharan Africa.

Keywords: Mobile learning, e-learning, educational technologies, SMS, secondary education, assessment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2068

Authors: Mario Gianni, Manuel A. Ruiz Garcia, Fiora Pirri

Abstract:

In this work, we present a Bayesian non-parametric approach to model the motion control of ATVs. The motion control model is based on a Dirichlet Process-Gaussian Process (DP-GP) mixture model. The DP-GP mixture model provides a flexible representation of patterns of control manoeuvres along trajectories of different lengths and discretizations. The model also estimates the number of patterns, sufficient for modeling the dynamics of the ATV.

Keywords: Dirichlet processes, Gaussian processes, robot control learning, tracked vehicles.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1783

Authors: Bingchun Liu, Pei-Chann Chang, Natasha Huang, Dun Li

Abstract:

Machine Learning and Data Mining are the two important tools for extracting useful information and knowledge from large datasets. In machine learning, classification is a wildly used technique to predict qualitative variables and is generally preferred over regression from an operational point of view. Due to the enormous increase in air pollution in various countries especially China, Air Quality Classification has become one of the most important topics in air quality research and modelling. This study aims at introducing a hybrid classification model based on information theory and Support Vector Machine (SVM) using the air quality data of four cities in China namely Beijing, Guangzhou, Shanghai and Tianjin from Jan 1, 2014 to April 30, 2016. China's Ministry of Environmental Protection has classified the daily air quality into 6 levels namely Serious Pollution, Severe Pollution, Moderate Pollution, Light Pollution, Good and Excellent based on their respective Air Quality Index (AQI) values. Using the information theory, information gain (IG) is calculated and feature selection is done for both categorical features and continuous numeric features. Then SVM Machine Learning algorithm is implemented on the selected features with cross-validation. The final evaluation reveals that the IG and SVM hybrid model performs better than SVM (alone), Artificial Neural Network (ANN) and K-Nearest Neighbours (KNN) models in terms of accuracy as well as complexity.

Keywords: Machine learning, air quality classification, air quality index, information gain, support vector machine, cross-validation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 948

Authors: Torsti Rantapuska, Sariseelia Sore

Abstract:

Acquiring commercial off-the-shelf (COTS) software applications is becoming routine in organizations. However, eliciting user requirements, finding the candidate COTS products and making the decision is a complex task, especially for SMEs who do not have the time and knowledge needed to do the task properly. The existing models intended to help the decision makers are originally designed for professional use. SMEs are obligated to rely on the software vendor’s ability to solve the problem with the systems provided.  In this paper, we develop a model for SMEs for the acquisition of Commercial Off-The-Shelf (COTS) software products. A leading idea of the model is that the ICT investment is basically a change initiative and therefore it should also be taken as a process of organizational learning. The model is designed bearing three objectives in mind: 1) business orientation, 2) agility, and 3) Learning and knowledge management orientation. The model can be applied to ICT investments in SMEs which have a professional team leader with basic business and IT knowledge. 

 

Keywords: COTS acquisition, ICT investment, organizational learning, ICT adoption.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1770

Authors: Linnea Stenliden

Abstract:

The aim of this paper is to understand emerging learning conditions, when a visual analytics is implemented and used in K 12 (education). To date, little attention has been paid to the role visual analytics (digital media and technology that highlight visual data communication in order to support analytical tasks) can play in education, and to the extent to which these tools can process actionable data for young students. This study was conducted in three public K 12 schools, in four social science classes with students aged 10 to 13 years, over a period of two to four weeks at each school. Empirical data were generated using video observations and analyzed with help of metaphors within Actor-network theory (ANT). The learning conditions are found to be distinguished by broad complexity, characterized by four dimensions. These emerge from the actors’ deeply intertwined relations in the activities. The paper argues in relation to the found dimensions that novel approaches to teaching and learning could benefit students’ knowledge building as they work with visual analytics, analyzing visualized data.

Keywords: Analytical reasoning, complexity, data use, problem space, visual analytics, visual storytelling, translation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1697

Authors: Yingqi Cui, Changran Huang, Raymond Lee

Abstract:

In this paper, we proposed an AI Tutor using ontology and natural language process techniques to generate a computer science domain knowledge graph and answer users’ questions based on the knowledge graph. We define eight types of relation to extract relationships between entities according to the computer science domain text. The AI tutor is separated into two agents: learning agent and Question-Answer (QA) agent and developed on JADE (a multi-agent system) platform. The learning agent is responsible for reading text to extract information and generate a corresponding knowledge graph by defined patterns. The QA agent can understand the users’ questions and answer humans’ questions based on the knowledge graph generated by the learning agent.

Keywords: Artificial intelligence, natural language process, knowledge graph, agent, QA system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 894

Authors: Almutasim Billa A. Alanazi, Hal S. Tharp

Abstract:

Artificial Intelligence (AI), specifically Reinforcement Learning (RL), has proven helpful in many control path planning technologies by maximizing and enhancing their performance, such as navigation systems. Since it learns from experience by interacting with the environment to determine the optimal policy, the optimal policy takes the best action in a particular state, accounting for the long-term rewards. Most navigation systems focus primarily on "arriving faster," overlooking safety and efficiency while estimating the optimum path, as safety and efficiency are essential factors when planning for a long-distance journey. This paper represents an RL control model that proposes a control mechanism for improving navigation systems. Also, the model could be applied to other control path planning applications because it is adjustable and can accept different properties and parameters. However, the navigation system application has been taken as a case and evaluation study for the proposed model. The model utilized a Q-learning algorithm for training and updating the policy. It allows the agent to analyze the quality of an action made in the environment to maximize rewards. The model gives the ability to update rewards regularly based on safety and efficiency assessments, allowing the policy to consider the desired safety and efficiency benefits while making decisions, which improves the quality of the decisions taken for path planning compared to the conventional RL approaches.

Keywords: Artificial intelligence, control system, navigation systems, reinforcement learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 201

Authors: František Mošna

Abstract:

E-learning has become an efficient and widespread means of education at all levels of human activities. Statistics is no exception. Unfortunately the main focus in statistics teaching is usually paid to the substitution in formulas. Suitable websites can simplify and automate calculations and provide more attention and time to the basic principles of statistics, mathematization of real-life situations and following interpretation of results. We now introduce our own web-site for hypothesis testing. Its didactic aspects, the technical possibilities of the individual tools, the experience of use and the advantages or disadvantages are discussed in this paper. This web-site is not a substitute for common statistical software but should significantly improve the teaching of statistics at universities.

Keywords: E-learning, hypothesis testing, PHP, websites.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2350

Authors: Pushpa B. Patil, Manesh B. Kokare

Abstract:

This paper presents content-based image retrieval (CBIR) frameworks with relevance feedback (RF) based on combined learning of support vector machines (SVM) and AdaBoosts. The framework incorporates only most relevant images obtained from both the learning algorithm. To speed up the system, it removes irrelevant images from the database, which are returned from SVM learner. It is the key to achieve the effective retrieval performance in terms of time and accuracy. The experimental results show that this framework had significant improvement in retrieval effectiveness, which can finally improve the retrieval performance.

Keywords: Image retrieval, relevance feedback, wavelet transform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1993

Authors: Rossitza M. Setchi, Qiao Tang

Abstract:

Nowadays, ontologies are the only widely accepted paradigm for the management of sharable and reusable knowledge in a way that allows its automatic interpretation. They are collaboratively created across the Web and used to index, search and annotate documents. The vast majority of the ontology based approaches, however, focus on indexing texts at document level. Recently, with the advances in ontological engineering, it became clear that information indexing can largely benefit from the use of general purpose ontologies which aid the indexing of documents at word level. This paper presents a concept indexing algorithm, which adds ontology information to words and phrases and allows full text to be searched, browsed and analyzed at different levels of abstraction. This algorithm uses a general purpose ontology, OntoRo, and an ontologically tagged corpus, OntoCorp, both developed for the purpose of this research. OntoRo and OntoCorp are used in a two-stage supervised machine learning process aimed at generating ontology tagging rules. The first experimental tests show a tagging accuracy of 78.91% which is encouraging in terms of the further improvement of the algorithm.

Keywords: Concepts, indexing, machine learning, ontology, tagging.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1678

Authors: Thinh Ngo, Paul Rad, Brian Kelley

Abstract:

Noise estimation is essential in today wireless systems for power control, adaptive modulation, interference suppression and quality of service. Deep learning (DL) has already been applied in the physical layer for modulation and signal classifications. Unacceptably low accuracy of less than 50% is found to undermine traditional application of DL classification for SNR prediction. In this paper, we use divide-and-conquer algorithm and classifier fusion method to simplify SNR classification and therefore enhances DL learning and prediction. Specifically, multiple CNNs are used for classification rather than a single CNN. Each CNN performs a binary classification of a single SNR with two labels: less than, greater than or equal. Together, multiple CNNs are combined to effectively classify over a range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained CNNs to predict SNR over a wide range of joint channel parameters including multiple Doppler shifts (0, 60, 120 Hz), power-delay profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The approach achieves individual SNR prediction accuracy of 92%, composite accuracy of 70% and prediction convergence one order of magnitude faster than that of traditional estimation.

Keywords: Classification, classifier fusion, CNN, Deep Learning, prediction, SNR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 720

Authors: K. Freedman

Abstract:

In the present study, a support vector machine (SVM) learning approach to character recognition is proposed. Simple feature detectors, similar to those found in the human visual system, were used in the SVM classifier. Alphabetic characters were rotated to 8 different angles and using the proposed cognitive model, all characters were recognized with 100% accuracy and specificity. These same results were found in psychiatric studies of human character recognition.

Keywords: Character recognition, cognitive model, support vector machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1878

Authors: C. Manjula, Lilly Florence

Abstract:

Software technology is developing rapidly which leads to the growth of various industries. Now-a-days, software-based applications have been adopted widely for business purposes. For any software industry, development of reliable software is becoming a challenging task because a faulty software module may be harmful for the growth of industry and business. Hence there is a need to develop techniques which can be used for early prediction of software defects. Due to complexities in manual prediction, automated software defect prediction techniques have been introduced. These techniques are based on the pattern learning from the previous software versions and finding the defects in the current version. These techniques have attracted researchers due to their significant impact on industrial growth by identifying the bugs in software. Based on this, several researches have been carried out but achieving desirable defect prediction performance is still a challenging task. To address this issue, here we present a machine learning based hybrid technique for software defect prediction. First of all, Genetic Algorithm (GA) is presented where an improved fitness function is used for better optimization of features in data sets. Later, these features are processed through Decision Tree (DT) classification model. Finally, an experimental study is presented where results from the proposed GA-DT based hybrid approach is compared with those from the DT classification technique. The results show that the proposed hybrid approach achieves better classification accuracy.

Keywords: Decision tree, genetic algorithm, machine learning, software defect prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1465

Authors: Linda H. Meyer, Carol S. Sternberger

Abstract:

Self-efficacy, self-reliance, and motivation were examined in a quasi-experimental study with 178 sophomore university students. Participants used an interactive cardiovascular anatomy and physiology CD-ROM, and completed a 15-item questionnaire. Reliability of the questionnaire was established using Cronbach-s alpha. Post-tests and course grades were examined using a t-test, demonstrating no significance. Results of an item-to-item analysis of the questionnaire showed overall satisfaction with the teaching methodology and varied results for self-efficacy, selfreliance, and motivation. Kendall-s Tau was calculated for all items in the questionnaire.

Keywords: Asynchronous learning environments, motivation, self-efficacy, self-reliance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3658

Authors: Yun Bai

Abstract:

Representing objects in a dynamic domain is essential in commonsense reasoning under some circumstances. Classical logics and their nonmonotonic consequences, however, are usually not able to deal with reasoning with dynamic domains due to the fact that every constant in the logical language denotes some existing object in the static domain. In this paper, we explore a logical formalization which allows us to represent nonexisting objects in commonsense reasoning. A formal system named N-theory is proposed for this purpose and its possible application in computer security is briefly discussed.

Keywords: knowledge representation and reasoning, commonsensereasoning, computer security

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1443

Authors: Hirofumi Miyajima, Kazuya Kishida, Noritaka Shigei, Hiromi Miyajima

Abstract:

Most of self-tuning fuzzy systems, which are automatically constructed from learning data, are based on the steepest descent method (SDM). However, this approach often requires a large convergence time and gets stuck into a shallow local minimum. One of its solutions is to use fuzzy rule modules with a small number of inputs such as DIRMs (Double-Input Rule Modules) and SIRMs (Single-Input Rule Modules). In this paper, we consider a (generalized) DIRMs model composed of double and single-input rule modules. Further, in order to reduce the redundant modules for the (generalized) DIRMs model, pruning and generative learning algorithms for the model are suggested. In order to show the effectiveness of them, numerical simulations for function approximation, Box-Jenkins and obstacle avoidance problems are performed.

Keywords: Box-Jenkins’s problem, Double-input rule module, Fuzzy inference model, Obstacle avoidance, Single-input rule module.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1957

Authors: Romisaa Ali

Abstract:

The Policy Gradient approach is a subset of the Deep Reinforcement Learning (DRL) combines Deep Neural Networks (DNN) with Reinforcement Learning (RL). This approach finds the optimal policy of robot movement, based on the experience it gains from interaction with its environment. Unlike previous policy gradient algorithms, which were unable to handle the two types of error variance and bias introduced by the DNN model due to over- or underestimation, this algorithm is capable of handling both types of error variance and bias. This article will discuss the state-of-the-art SOTA policy gradient technique, trust region policy optimization (TRPO), by applying this method in various environments compared to another policy gradient method, the Proximal Policy Optimization (PPO), to explain their robust optimization, using this SOTA to gather experience data during various training phases after observing the impact of hyper-parameters on neural network performance.

Keywords: Deep neural networks, deep reinforcement learning, Proximal Policy Optimization, state-of-the-art, trust region policy optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 185

Authors: Nuttanuch Munsakorn

Abstract:

This questionnaire-based study, aimed to measure and compare the awareness of English reading strategies among EFL learners at Bangkok University (BU) classified by their gender, field of study, and English learning experience. Proportional stratified random sampling was employed to formulate a sample of 380 BU students. The data were statistically analyzed in terms of the mean and standard deviation. t-Test analysis was used to find differences in awareness of reading strategies between two groups (-male and female- /-science and social-science students). In addition, one-way analysis of variance (ANOVA) was used to compare reading strategy awareness among BU students with different lengths of English learning experience. The results of this study indicated that the overall awareness of reading strategies of EFL learners at BU was at a high level (ðÑ = 3.60) and that there was no statistically significant difference between males and females, and among students who have different lengths of English learning experience at the significance level of 0.05. However, significant differences among students coming from different fields of study were found at the same level of significance.

Keywords: EFL learners, higher education, reading comprehension, reading strategies

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3938

Authors: M. R. Homaeinezhad, E. Tavakkoli, M. Habibi, S. A. Atyabi, A. Ghaffari

Abstract:

This paper describes a new supervised fusion (hybrid) electrocardiogram (ECG) classification solution consisting of a new QRS complex geometrical feature extraction as well as a new version of the learning vector quantization (LVQ) classification algorithm aimed for overcoming the stability-plasticity dilemma. Toward this objective, after detection and delineation of the major events of ECG signal via an appropriate algorithm, each QRS region and also its corresponding discrete wavelet transform (DWT) are supposed as virtual images and each of them is divided into eight polar sectors. Then, the curve length of each excerpted segment is calculated and is used as the element of the feature space. To increase the robustness of the proposed classification algorithm versus noise, artifacts and arrhythmic outliers, a fusion structure consisting of five different classifiers namely as Support Vector Machine (SVM), Modified Learning Vector Quantization (MLVQ) and three Multi Layer Perceptron-Back Propagation (MLP–BP) neural networks with different topologies were designed and implemented. The new proposed algorithm was applied to all 48 MIT–BIH Arrhythmia Database records (within–record analysis) and the discrimination power of the classifier in isolation of different beat types of each record was assessed and as the result, the average accuracy value Acc=98.51% was obtained. Also, the proposed method was applied to 6 number of arrhythmias (Normal, LBBB, RBBB, PVC, APB, PB) belonging to 20 different records of the aforementioned database (between– record analysis) and the average value of Acc=95.6% was achieved. To evaluate performance quality of the new proposed hybrid learning machine, the obtained results were compared with similar peer– reviewed studies in this area.

Keywords: Feature Extraction, Curve Length Method, SupportVector Machine, Learning Vector Quantization, Multi Layer Perceptron, Fusion (Hybrid) Classification, Arrhythmia Classification, Supervised Learning Machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2227

Authors: XianYu Zhao, JinXu Guo

Abstract:

Recently, low-dose computed tomography (CT) has become highly desirable due to increasing attention to the potential risks of excessive radiation. For low-dose CT imaging, ensuring image quality while reducing radiation dose is a major challenge. To facilitate low-dose CT imaging, we propose an improved statistical iterative reconstruction scheme based on the Penalized Weighted Least Squares (PWLS) standard combined with total variation (TV) minimization and sparse dictionary learning (DL) to improve reconstruction performance. We call this method "PWLS-TV-DL". In order to evaluate the PWLS-TV-DL method, we performed experiments on digital phantoms and physical phantoms, respectively. The experimental results show that our method is in image quality and calculation. The efficiency is superior to other methods, which confirms the potential of its low-dose CT imaging.

Keywords: Low dose computed tomography, penalized weighted least squares, total variation, dictionary learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 834

Authors: Shingo Murakami, Shinichi Enoki

Abstract:

In structures, stress concentration is a factor of fatigue fracture. Basically, the stress concentration is a phenomenon that should be avoided. However, it is difficult to avoid the stress concentration. Therefore, relaxation of the stress concentration is important. The stress concentration arises from notches and circular holes. There is a relaxation method that a composite patch covers a notch and a circular hole. This relaxation method is used to repair aerial wings, but it is not systematized. Composites are more expensive than single materials. Accordingly, we propose the relaxation method that a single material patch covers a notch and a circular hole, and aim to systematize this relaxation method. We performed FEA (Finite Element Analysis) about an object by using a three-dimensional FEA model. The object was that a patch adheres to a plate with a circular hole. And, a uniaxial tensile load acts on the patched plate with a circular hole. In the three-dimensional FEA model, it is not easy to model the adhesion layer. Basically, the yield stress of the adhesive is smaller than that of adherents. Accordingly, the adhesion layer gets to plastic deformation earlier than the adherents under the yield load of adherents. Therefore, we propose the three-dimensional FEA model which is applied a nonlinear elastic region to the adhesion layer. The nonlinear elastic region was calculated by a bilinear approximation. We compared the analysis results with the tensile test results to confirm whether the analysis model has usefulness. As a result, the analysis results agreed with the tensile test results. And, we confirmed that the analysis model has usefulness. As a result that the three-dimensional FEA model was used to the analysis, it was confirmed that an out-of-plane deformation occurred to the patched plate with a circular hole. The out-of-plane deformation causes stress increase of the patched plate with a circular hole. Therefore, we investigated that the out-of-plane deformation affects relaxation of the stress concentration in the plate with a circular hole on this relaxation method. As a result, it was confirmed that the out-of-plane deformation inhibits relaxation of the stress concentration on the plate with a circular hole.

Keywords: Stress concentration, patch, out-of-plane deformation, Finite Element Analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2293

Authors: Konstantinos C. Giotopoulos, Christos E. Alexakos, Grigorios N. Beligiannis, Spiridon D.Likothanassis

Abstract:

In this contribution an innovative platform is being presented that integrates intelligent agents and evolutionary computation techniques in legacy e-learning environments. It introduces the design and development of a scalable and interoperable integration platform supporting: I) various assessment agents for e-learning environments, II) a specific resource retrieval agent for the provision of additional information from Internet sources matching the needs and profile of the specific user and III) a genetic algorithm designed to extract efficient information (classifying rules) based on the students- answering input data. The agents are implemented in order to provide intelligent assessment services based on computational intelligence techniques such as Bayesian Networks and Genetic Algorithms. The proposed Genetic Algorithm (GA) is used in order to extract efficient information (classifying rules) based on the students- answering input data. The idea of using a GA in order to fulfil this difficult task came from the fact that GAs have been widely used in applications including classification of unknown data. The utilization of new and emerging technologies like web services allows integrating the provided services to any web based legacy e-learning environment.

Keywords: Bayesian Networks, Computational Intelligencetechniques, E-learning legacy systems, Service Oriented Integration, Intelligent Agents, Genetic Algorithms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1744

Authors: Victor Bodell, Lukas Ekstrom, Somayeh Aghanavesi

Abstract:

Fuel consumption (FC) is one of the key factors in determining expenses of operating a heavy-duty vehicle. A customer may therefore request an estimate of the FC of a desired vehicle. The modular design of heavy-duty vehicles allows their construction by specifying the building blocks, such as gear box, engine and chassis type. If the combination of building blocks is unprecedented, it is unfeasible to measure the FC, since this would first r equire the construction of the vehicle. This paper proposes a machine learning approach to predict FC. This study uses around 40,000 vehicles specific and o perational e nvironmental c onditions i nformation, such as road slopes and driver profiles. A ll v ehicles h ave d iesel engines and a mileage of more than 20,000 km. The data is used to investigate the accuracy of machine learning algorithms Linear regression (LR), K-nearest neighbor (KNN) and Artificial n eural n etworks (ANN) in predicting fuel consumption for heavy-duty vehicles. Performance of the algorithms is evaluated by reporting the prediction error on both simulated data and operational measurements. The performance of the algorithms is compared using nested cross-validation and statistical hypothesis testing. The statistical evaluation procedure finds that ANNs have the lowest prediction error compared to LR and KNN in estimating fuel consumption on both simulated and operational data. The models have a mean relative prediction error of 0.3% on simulated data, and 4.2% on operational data.

Keywords: Artificial neural networks, fuel consumption, machine learning, regression, statistical tests.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 831