Search results for: flexible learning

Authors: Çiğdem Bakır, Mecit Yüzkat

Abstract:

With the increasing emphasis on water quality worldwide, the search for and expanding the market for new and intelligent monitoring systems has increased. The current method is the laboratory process, where samples are taken from bodies of water, and tests are carried out in laboratories. This method is time-consuming, a waste of manpower, and uneconomical. To solve this problem, we used machine learning methods to detect water pollution in our study. We created decision trees with the Orange3 software we used in our study and tried to determine all the factors that cause water pollution. An automatic prediction model based on water quality was developed by taking many model inputs such as water temperature, pH, transparency, conductivity, dissolved oxygen, and ammonia nitrogen with machine learning methods. The proposed approach consists of three stages: preprocessing of the data used, feature detection, and classification. We tried to determine the success of our study with different accuracy metrics and the results. We presented it comparatively. In addition, we achieved approximately 98% success with the decision tree.

Keywords: decision tree, water quality, water pollution, machine learning

Procedia PDF Downloads 77

Authors: Hritwik Ghosh, Irfan Sadiq Rahat, Sachi Nandan Mohanty, J. V. R. Ravindra

Abstract:

In the rapidly evolving landscape of medical diagnostics, the early detection and accurate classification of skin cancer remain paramount for effective treatment outcomes. This research delves into the transformative potential of Artificial Intelligence (AI), specifically Deep Learning (DL), as a tool for discerning and categorizing various skin conditions. Utilizing a diverse dataset of 3,000 images representing nine distinct skin conditions, we confront the inherent challenge of class imbalance. This imbalance, where conditions like melanomas are over-represented, is addressed by incorporating class weights during the model training phase, ensuring an equitable representation of all conditions in the learning process. Our pioneering approach introduces a hybrid model, amalgamating the strengths of two renowned Convolutional Neural Networks (CNNs), VGG16 and ResNet50. These networks, pre-trained on the ImageNet dataset, are adept at extracting intricate features from images. By synergizing these models, our research aims to capture a holistic set of features, thereby bolstering classification performance. Preliminary findings underscore the hybrid model's superiority over individual models, showcasing its prowess in feature extraction and classification. Moreover, the research emphasizes the significance of rigorous data pre-processing, including image resizing, color normalization, and segmentation, in ensuring data quality and model reliability. In essence, this study illuminates the promising role of AI and DL in revolutionizing skin cancer diagnostics, offering insights into its potential applications in broader medical domains.

Keywords: artificial intelligence, machine learning, deep learning, skin cancer, dermatology, convolutional neural networks, image classification, computer vision, healthcare technology, cancer detection, medical imaging

Procedia PDF Downloads 81

Authors: Eniola Akande

Abstract:

Introduction: English vocabulary and reading comprehension are core to academic achievement in many school subjects. Deficiency in both accounts for dismal performance in internal and external examinations among primary school pupils in Ibadan Metropolis, Nigeria. Previous studies largely focused on factors influencing pupils’ achievement in English vocabulary and reading comprehension. In spite of what literature has shown, the problem still persists, implying the need for other kinds of intervention. This study was therefore carried out to determine the effect of two transactional strategies Picture Walk (PW) and Know-Want to Learn-Learnt (KWL) on primary four pupils’ achievement in English vocabulary and reading comprehension in Ibadan Metropolis. The moderating effects of gender and learning style were also examined. Methodology: The study was anchored on Rosenblatt’s Transactional Reading and Piaget’s Cognitive Development theories; pretest-posttest control group quasi-experimental design with 3x2x3 factorial matrix was adopted. Six public primary schools were purposively selected based on the availability of qualified English language teachers in Primary Education Studies. Six intact classes (one per school) with a total of 101 primary four pupils (48 males and 53 females) participated. The intact classes were randomly assigned to PW (27), KWL (44) and conventional (30) groups. Instruments used were English Vocabulary (r=0.83), Reading Comprehension (r=0.84) achievement tests, Pupils’ Learning Style Preference Scale (r=0.93) and instructional guides. Treatment lasted six weeks. Data were analysed using the Descriptive statistics, Analysis of Covariance and Bonferroni post-hoc test at 0.05 level of significance. The mean age was 8.86±0.84 years. Result: Treatment had a significant main effect on pupils’ reading comprehension (F(2,82)=3.17), but not on English vocabulary. Participants in KWL obtained the highest post achievement means score in reading comprehension (8.93), followed by PW (8.06) and control (7.21) groups. Pupils’ learning style had a significant main effect on pupils’ achievement in reading comprehension (F(2,82)=4.41), but not on English vocabulary. Pupils with preference for tactile learning style had the highest post achievement mean score in reading comprehension (9.40), followed by the auditory (7.43) and the visual learning style (7.37) groups. Gender had no significant main effect on English vocabulary and reading comprehension. There was no significant two-way interaction effect of treatment and gender on pupils’ achievement in English vocabulary and reading comprehension. The two-way interaction effect of treatment and learning style on pupils’ achievement in reading comprehension was significant (F(4,82)=3.37), in favour of pupils with tactile learning style in PW group. There was no significant two-way interaction effect of gender and learning style on pupils’ achievement in English vocabulary and reading comprehension. The three-way interaction effects were not significant on English vocabulary and reading comprehension. Conclusion: Picture Walk and Know-Want to learn-Learnt instructional strategies were effective in enhancing pupils’ achievement in reading comprehension but not on English vocabulary. Learning style contributed considerably to achievement in reading comprehension but not to English vocabulary. Primary school, English language teachers, should put into consideration pupils’ learning style when adopting both strategies in teaching reading comprehension for improved achievement in the subject.

Keywords: comprehension-based intervention, know-want to learn-learnt, learning style, picture walk, primary school pupils

Procedia PDF Downloads 139

Authors: Sunantha Teyarachakul

Abstract:

We consider the worker-learning Newsvendor Model, under the case of lost-sales for unmet demand, with the research objective of proposing the cost-minimization order policy and lot size, scheduled to arrive at the beginning of the selling-period. In general, the New Vendor Model is used to find the optimal order quantity for the perishable items such as fashionable products or those with seasonal demand or short-life cycles. Technically, it is used when the product demand is stochastic and available for the single selling-season, and when there is only a one time opportunity for the vendor to purchase, with possibly of long ordering lead-times. Our work differs from the classical Newsvendor Model in that we incorporate the human factor (specifically worker learning) and its influence over the costs of processing units into the model. We describe this by using the well-known Wright’s Learning Curve. Most of the assumptions of the classical New Vendor Model are still maintained in our work, such as the constant per-unit cost of leftover and shortage, the zero initial inventory, as well as the continuous time. Our problem is challenging in the way that the best order quantity in the classical model, which is balancing the over-stocking and under-stocking costs, is no longer optimal. Specifically, when adding the cost-saving from worker learning to such expected total cost, the convexity of the cost function will likely not be maintained. This has called for a new way in determining the optimal order policy. In response to such challenges, we found a number of characteristics related to the expected cost function and its derivatives, which we then used in formulating the optimal ordering policy. Examples of such characteristics are; the optimal order quantity exists and is unique if the demand follows a Uniform Distribution; if the demand follows the Beta Distribution with some specific properties of its parameters, the second derivative of the expected cost function has at most two roots; and there exists the specific level of lot size that satisfies the first order condition. Our research results could be helpful for analysis of supply chain coordination and of the periodic review system for similar problems.

Keywords: inventory management, Newsvendor model, order policy, worker learning

Procedia PDF Downloads 412

Authors: Dylan Santos De Pinho, Arnaud Gay De Combes, Matthieu Steuhlet, Claude Jeannerat, Nabil Ouerhani

Abstract:

The Industry 4.0 initiative has been launched to address huge challenges related to ever-smaller batch sizes. The end-user need for highly customized products requires highly adaptive production systems in order to keep the same efficiency of shop floors. Most of the classical Software solutions that operate the manufacturing processes in a shop floor are based on rigid Manufacturing Execution Systems (MES), which are not capable to adapt the production order on the fly depending on changing demands and or conditions. In this paper, we present a highly modular and flexible solution to orchestrate a set of production systems composed of a micro-milling machine-tool, a polishing station, a cleaning station, a part inspection station, and a rough material store. The different stations are installed according to a novel matrix configuration of a 3x3 vertical shelf. The different cells of the shelf are connected through horizontal and vertical rails on which a set of shuttles circulate to transport the machined parts from a station to another. Our software solution for orchestrating the tasks of each station is based on a Multi-Agent System. Each station and each shuttle is operated by an autonomous agent. All agents communicate with a central agent that holds all the information about the manufacturing order. The core innovation of this paper lies in the path planning of the different shuttles with two major objectives: 1) reduce the waiting time of stations and thus reduce the cycle time of the entire part, and 2) reduce the disturbances like vibration generated by the shuttles, which highly impacts the manufacturing process and thus the quality of the final part. Simulation results show that the cycle time of the parts is reduced by up to 50% compared with MES operated linear production lines while the disturbance is systematically avoided for the critical stations like the milling machine-tool.

Keywords: multi-agent systems, micro-manufacturing, flexible manufacturing, transfer systems

Procedia PDF Downloads 127

Authors: Ibtisam Mohammed Al-Quraini

Abstract:

This paper examines how introducing Omani literature in foreign language classrooms can influence the students' motivation in learning the language. The data was collected through the questionnaire which was administered to two samples (A and B) of the participants. Sample A was comprised of 30 female students from English department who are specialist in English literature in college of Arts and Social Science. Sample B in contrast was comprised of 10 female students who their major is English from college of Education. Results show that each genre in literature has different influence on the students' motivation in learning the language which proves that literacy texts are powerful. Generally, Omani English teachers tend to avoid teaching literature because they think that it is a difficult method to use in teaching field. However, the advantages and the influences of teaching poetries, short stories, and plays are discussed. Recommendations for current research and further research are also discussed at the end.

Keywords: education, foreign language, English, Omani literature, poetry, story, play

Procedia PDF Downloads 386

Authors: Ece Sarigul

Abstract:

It is an undeniable fact that, teachers need new strategies to communicate with students of the next generation and to shape enticing educational experiences for them. Many schools have launched iPad/ Tablets initiatives in an effort to enhance student learning. Despite their rapid adoption, the extent to which iPads / Tablets increase student engagement and learning is not well understood. This presentation aims to examine the use of iPads and Tablets in primary and high schools in Turkey as well as in the world to increase academic achievement through promotion of higher order thinking skills. In addition to explaining the ideas of school teachers and students who use the specific iPads or Tablets , various applications in schools and their use will be discussed and demonstrated in this study. The specific” iPads or Tablets” applications discussed in this presentation can be incorporated into the curriculum to assist in developing transformative practices and programs to meet the needs of a diverse student population. In the conclusion section of the presentation, there will be some suggestions for teachers about the effective use of technological devices in the classroom. This study can help educators understand better how students are currently using iPads and Tablets and shape future use.

Keywords: ipads, language teaching, tablets, technology

Procedia PDF Downloads 250

Authors: Suttipong Boonphadung, Thassanant Unnanantn

Abstract:

The research study aimed to (1) compare the critical thinking of the teacher students of Suan Sunandha Rajabhat University before and after applying Miller’s Model learning activities and (2) investigate the students’ opinions towards Miller’s Model learning activities for improving the critical thinking. The participants of this study were purposively selected. They were 3 groups of teacher students: (1) fourth year 33 student teachers majoring in Early Childhood Education and enrolling in semester 1 of academic year 2013 (2) third year 28 student teachers majoring in English and enrolling in semester 2 of academic year 2013 and (3) third year 22 student teachers majoring in Thai and enrolling in semester 2 of academic year 2013. The research instruments were (1) lesson plans where the learning activities were settled based on Miller’s Model (2) critical thinking assessment criteria and (3) a questionnaire on opinions towards Miller’s Model based learning activities. The statistical treatment was mean, deviation, different scores and T-test. The result unfolded that (1) the critical thinking of the students after the assigned activities was better than before and (2) the students’ opinions towards the critical thinking improvement activities based on Miller’s Model ranged from the level of high to highest.

Keywords: critical thinking, Miller’s model, opinions, pre-service teachers

Procedia PDF Downloads 475

Authors: Ngoc-Nguyen Nguyen, Hsiu-Ling Chen, Thanh-Truc Lai Huynh

Abstract:

In foreign language learning, vocabulary acquisition has consistently posed challenges to learners, especially for those at lower levels. Conventional approaches often fail to promote vocabulary learning and ensure engaging experiences alike. The emergence of mobile learning, particularly the integration of chatbot systems, has offered alternative ways to facilitate this practice. Chatbots have proven effective in educational contexts by offering interactive learning experiences in a constructivist manner. These tools have caught attention in the field of mobile-assisted language learning (MALL) in recent years. This research is conducted in an English for Specific Purposes (ESP) course at the A2 level of the CEFR, designed for non-English majors. Participants are first-year Vietnamese students aged 18 to 20 at a university. This quasi-experimental study follows a pretest-posttest control group design over five weeks, with two classes randomly assigned as the experimental and control groups. The experimental group engages in chatbot-assisted spaced practice with SRL components, while the control group uses the same spaced practice without SRL. The two classes are taught by the same lecturer. Data are collected through pre- and post-tests, cognitive load surveys, and semi-structured interviews. The combination of self-regulated learning (SRL) and distributed practice, grounded in the spacing effect, forms the basis of the present study. SRL elements, which concern goal setting and strategy planning, are integrated into the system. The spaced practice method, similar to those used in widely recognized learning platforms like Duolingo and Anki flashcards, spreads out learning over multiple sessions. This study’s design features quizzes progressively increasing in difficulty. These quizzes are aimed at targeting both the Recognition-Recall and Comprehension-Use dimensions for a comprehensive acquisition of vocabulary. The mobile-based chatbot system is built using Golang, an open-source programming language developed by Google. It follows a structured flow that guides learners through a series of 4 quizzes in each week of teacher-led learning. The quizzes start with less cognitively demanding tasks, such as multiple-choice questions, before moving on to more complex exercises. The integration of SRL elements allows students to self-evaluate the difficulty level of vocabulary items, predict scores achieved, and choose appropriate strategy. This research is part one of a two-part project. The initial findings will determine the development of an upgraded chatbot system in part two, where adaptive features in response to the integration of SRL components will be introduced. The research objectives are to assess the effectiveness of the chatbot-assisted approach, based on the combination of spaced practice and SRL, in improving vocabulary acquisition and managing cognitive load, as well as to understand students' perceptions of this learning tool. The insights from this study will contribute to the growing body of research on mobile-assisted language learning and offer practical implications for integrating chatbot systems with spaced practice into educational settings to enhance vocabulary learning.

Keywords: mobile learning, mobile-assisted language learning, MALL, chatbots, vocabulary learning, spaced practice, spacing effect, self-regulated learning, SRL, self-regulation, EFL, cognitive load

Procedia PDF Downloads 12

Authors: Nasim Eslamirad, Mahdi Rasoulinezhad, Francesco De Luca, Sadok Ben Yahia, Kimmo Sakari Lylykangas, Francesco Pilla

Abstract:

With the ongoing urbanization, cities face increasing environmental challenges impacting human well-being. To tackle these issues, data-driven approaches in urban analysis have gained prominence, leveraging urban data to promote sustainability. Integrating Machine Learning techniques enables researchers to analyze and predict complex environmental phenomena like Urban Heat Island occurrences in urban areas. This paper demonstrates the implementation of data-driven approach and interpretable Machine Learning algorithms with interpretability techniques to conduct comprehensive data analyses for sustainable urban design. The developed framework and algorithms are demonstrated for Tallinn, Estonia to develop sustainable urban strategies to mitigate urban heat waves. Geospatial data, preprocessed and labeled with UHI levels, are used to train various ML models, with Logistic Regression emerging as the best-performing model based on evaluation metrics to derive a mathematical equation representing the area with UHI or without UHI effects, providing insights into UHI occurrences based on buildings and urban features. The derived formula highlights the importance of building volume, height, area, and shape length to create an urban environment with UHI impact. The data-driven approach and derived equation inform mitigation strategies and sustainable urban development in Tallinn and offer valuable guidance for other locations with varying climates.

Keywords: data-driven approach, machine learning transparent models, interpretable machine learning models, urban heat island effect

Procedia PDF Downloads 31

Authors: A. van Staden, M. M. Coetzee

Abstract:

Despite numerous efforts to increase the literacy level of South African learners, for example, through the implementation of educational policies such as the Revised National Curriculum statement, advocating mother-tongue instruction (during a child's formative years), in reality, the majority of South African children are still being educated in a second language (in most cases English). Moreover, despite the fact that a significant percentage of our country's budget is spent on the education sector and that both policy makers and educationalists have emphasized the importance of learning English in this globalized world, the poor overall academic performance and English literacy level of a large number of school leavers are still a major concern. As we move forward in an attempt to comprehend the nuances of English language and literacy development in our country, it is imperative to explore both extrinsic and intrinsic factors that contribute or impede the effective development of English as a second language. In the present study, the researchers set out to investigate how intrinsic factors such as motivation and self-concept contribute to or affect English language learning amongst high school learners in South Africa. Emanating from the above the main research question that guided this research is the following: Is there a significant relationship between high school learners' self-concept, motivation, and English second language performances? In order to investigate this hypothesis, this study utilized quantitative research methodology to investigate the interplay of self-concept and motivation in English language learning. For this purpose, we sampled 201 high school learners from various schools in South Africa. Methods of data gathering inter alia included the following: A biographical questionnaire; the Academic Motivational Scale and the Piers-Harris Self-Concept Scale. Pearson Product Moment Correlation Analyses yielded significant correlations between L2 learners' motivation and their English language proficiency, including demonstrating positive correlations between L2 learners' self-concept and their achievements in English. Accordingly, researchers have argued that the learning context, in which students learn English as a second language, has a crucial influence on students' motivational levels. This emphasizes the important role the teacher has to play in creating learning environments that will enhance L2 learners' motivation and improve their self-concepts.

Keywords: motivation, self-concept, language learning, English second language learners (L2)

Procedia PDF Downloads 262

Authors: Victor Radich, Tania Basso, Regina Moraes

Abstract:

Lead qualification is one of the main procedures in Customer Relationship Management (CRM) projects. Its main goal is to identify potential consumers who have the ideal characteristics to establish a profitable and long-term relationship with a certain organization. Social networks can be an important source of data for identifying and qualifying leads since interest in specific products or services can be identified from the users’ expressed feelings of (dis)satisfaction. In this context, this work proposes the use of machine learning techniques and sentiment analysis as an extra step in the lead qualification process in order to improve it. In addition to machine learning models, sentiment analysis or opinion mining can be used to understand the evaluation that the user makes of a particular service, product, or brand. The results obtained so far have shown that it is possible to extract data from social networks and combine the techniques for a more complete classification.

Keywords: lead qualification, sentiment analysis, opinion mining, machine learning, CRM, lead scoring

Procedia PDF Downloads 79

Authors: Rashid Ahmed , John N. Avaritsiotis

Abstract:

Many signal subspace-based approaches have already been proposed for determining the fixed Direction of Arrival (DOA) of plane waves impinging on an array of sensors. Two procedures for DOA estimation based neural networks are presented. First, Principal Component Analysis (PCA) is employed to extract the maximum eigenvalue and eigenvector from signal subspace to estimate DOA. Second, minor component analysis (MCA) is a statistical method of extracting the eigenvector associated with the smallest eigenvalue of the covariance matrix. In this paper, we will modify a Minor Component Analysis (MCA(R)) learning algorithm to enhance the convergence, where a convergence is essential for MCA algorithm towards practical applications. The learning rate parameter is also presented, which ensures fast convergence of the algorithm, because it has direct effect on the convergence of the weight vector and the error level is affected by this value. MCA is performed to determine the estimated DOA. Preliminary results will be furnished to illustrate the convergences results achieved.

Keywords: Direction of Arrival, neural networks, Principle Component Analysis, Minor Component Analysis

Procedia PDF Downloads 448

Authors: Haifeng Wang, Haili Zhang

Abstract:

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

Keywords: computational social science, movie preference, machine learning, SVM

Procedia PDF Downloads 254

Authors: Jaisoon Baek, Gyuhwan Oh

Abstract:

In this study, we developed a puzzle game based on coding and a web-based management system to observe the user's learning status in real time and maximize the understanding of the coding of elementary students. We have improved upon and existing coding game which cannot be connected to textual language coding or comprehends learning state. We analyzed the syntax of various coding languages for the curriculum and provided a menu to convert icon into textual coding languages. In addition, the management system includes multiple types of tutoring, real-time analysis of user play data and feedback. Following its application in regular elementary school software classes, students reported positive effects on understanding and interest in coding were shown by students. It is expected that this will contribute to quality improvement in software education by providing contents with proven educational value by breaking away from simple learning-oriented coding games.

Keywords: coding education, serious game, coding, education management system

Procedia PDF Downloads 136

Authors: Vera G. Dianova, Lori P. Montross, Charles M. Burke

Abstract:

In the digital age, the widespread and frequently excessive use of mobile phones amongst university students is recognized as a significant distractor which interferes with their ability to enter a deep state of concentration during studies and diminishes their prospects of experiencing the enjoyable and instrumental state of flow, as defined and described by psychologist M. Csikszentmihalyi. This study has targeted 50 university students with the aim of teaching them to cultivate their ability to engage in deep work and to attain the state of flow, fostering more effective and enjoyable learning experiences. Prior to the start of the intervention, all participating students completed a comprehensive survey based on a variety of validated scales assessing their inclination toward lifelong learning, frequency of flow experiences during study, frustration tolerance, sense of agency, as well as their love of learning and daily time devoted to non-academic mobile phone activities. Several days after this initial assessment, students received a 90-minute lecture on the principles of flow and deep work, accompanied by a critical discourse on the detrimental effects of excessive mobile phone usage. They were encouraged to practice deep work and strive for frequent flow states throughout the semester. Subsequently, students submitted weekly surveys, including the 10-item CORE Dispositional Flow Scale, a 3-item agency scale and furthermore disclosed their average daily hours spent on non-academic mobile phone usage. As a final step, at the end of the semester students engaged in reflective report writing, sharing their experiences and evaluating the intervention's effectiveness. They considered alterations in their love of learning, reflected on the implications of their mobile phone usage, contemplated improvements in their tolerance for boredom and perseverance in complex tasks, and pondered the concept of lifelong learning. Additionally, students assessed whether they actively took steps towards managing their recreational phone usage and towards improving their commitment to becoming lifelong learners. Employing a mixed-methods approach our study offers insights into the dynamics of concentration, flow, mobile phone usage and attitudes towards learning among undergraduate and graduate university students. The findings of this study aim to promote profound contemplation, on the part of both students and instructors, on the rapidly evolving digital-age higher education environment. In an era defined by digital and AI advancements, the ability to concentrate, to experience the state of flow, and to love learning has never been more crucial. This study underscores the significance of addressing mobile phone distractions and providing strategies for cultivating deep concentration. The insights gained can guide educators in shaping effective learning strategies for the digital age. By nurturing a love for learning and encouraging lifelong learning, educational institutions can better prepare students for a rapidly changing labor market, where adaptability and continuous learning are paramount for success in a dynamic career landscape.

Keywords: deep work, flow, higher education, lifelong learning, love of learning

Procedia PDF Downloads 66

Authors: Muhammad Mooneeb Ali

Abstract:

Institutions, where religious knowledge is given are known as madrassas. They also give formal education along with religious education. This study will be a pioneer to explore if MALL can be beneficial for madrassa students or not in formal educational situations. For investigation, an experimental study was planned in Punjab where the sample size was 100 students, 10 each from 10 different madrassas of Punjab, who are studying at the intermediate level (i.e., 11th grade). The madrassas were chosen through a convenient sampling method, whereas the learners were chosen by a simple random sampling method. A pretest was conducted, and on the basis of the results, the learners were divided into two equal groups (experimental and controlled). After two months of treatment, a posttest was conducted, and the results of both groups were compared. The results indicated that the performance of the experimental group was significantly better than the control one. This indicates that MALL elevates the performance of Madrassa students.

Keywords: english language learners, madrassa students, formal education, mobile assisted language learning (MALL), Pakistan.

Procedia PDF Downloads 68

Authors: Luo Jiaoyang, Yu Hongyang

Abstract:

In this paper, we explore a method that can be used in the working scene of intelligent industrial robots to confirm the identity information of operators to ensure that the robot executes instructions in a sufficiently safe environment. This approach uses three information modalities, namely visible light, depth, and sound. We explored a variety of fusion modes for the three modalities and finally used the joint feature learning method to improve the performance of the model in the case of noise compared with the single-modal case, making the maximum noise in the experiment. It can also maintain an accuracy rate of more than 90%.

Keywords: multimodal, kinect, machine learning, distance image

Procedia PDF Downloads 76

Authors: Erva Akin

Abstract:

– The use of copyrighted material for machine learning purposes is a challenging issue in the field of artificial intelligence (AI). While machine learning algorithms require large amounts of data to train and improve their accuracy and creativity, the use of copyrighted material without permission from the authors may infringe on their intellectual property rights. In order to overcome copyright legal hurdle against the data sharing, access and re-use of data, the use of copyrighted material for machine learning purposes may be considered permissible under certain circumstances. For example, if the copyright holder has given permission to use the data through a licensing agreement, then the use for machine learning purposes may be lawful. It is also argued that copying for non-expressive purposes that do not involve conveying expressive elements to the public, such as automated data extraction, should not be seen as infringing. The focus of such ‘copy-reliant technologies’ is on understanding language rules, styles, and syntax and no creative ideas are being used. However, the non-expressive use defense is within the framework of the fair use doctrine, which allows the use of copyrighted material for research or educational purposes. The questions arise because the fair use doctrine is not available in EU law, instead, the InfoSoc Directive provides for a rigid system of exclusive rights with a list of exceptions and limitations. One could only argue that non-expressive uses of copyrighted material for machine learning purposes do not constitute a ‘reproduction’ in the first place. Nevertheless, the use of machine learning with copyrighted material is difficult because EU copyright law applies to the mere use of the works. Two solutions can be proposed to address the problem of copyright clearance for AI training data. The first is to introduce a broad exception for text and data mining, either mandatorily or for commercial and scientific purposes, or to permit the reproduction of works for non-expressive purposes. The second is that copyright laws should permit the reproduction of works for non-expressive purposes, which opens the door to discussions regarding the transposition of the fair use principle from the US into EU law. Both solutions aim to provide more space for AI developers to operate and encourage greater freedom, which could lead to more rapid innovation in the field. The Data Governance Act presents a significant opportunity to advance these debates. Finally, issues concerning the balance of general public interests and legitimate private interests in machine learning training data must be addressed. In my opinion, it is crucial that robot-creation output should fall into the public domain. Machines depend on human creativity, innovation, and expression. To encourage technological advancement and innovation, freedom of expression and business operation must be prioritised.

Keywords: artificial intelligence, copyright, data governance, machine learning

Procedia PDF Downloads 81

Authors: C. W. Kan

Abstract:

Cotton fibre is a commonly-used natural fibre because of its good fibre strength, high moisture absorption behaviour and minimal static problems. However, one of the main drawbacks of cotton fibre is wrinkling after washing, which is recently overcome by wrinkle-resistant treatment. 1,2,3,4-butanetetracarboxylic acid (BTCA) could improve the wrinkle-resistant properties of cotton fibre. Although the BTCA process is an effective method for wrinkle resistant application of cotton fabrics, reduced fabric strength was observed after treatment. Therefore, this paper would explore the use of atmospheric pressure plasma treatment under different discharge powers as a pretreatment process to enhance the application of BTCA process on cotton fabric without generating adverse effect. The aim of this study is to provide learning information to the users to know how the atmospheric pressure plasma treatment can be incorporated in textile finishing process with positive impact.

Keywords: learning materials, atmospheric pressure plasma treatment, cotton, wrinkle-resistant, BTCA

Procedia PDF Downloads 297

Authors: Hervice Roméo Fogno Fotsoa, Germaine Djuidje Kenmoe, Claude Vidal Aloyem Kazé

Abstract:

One of the main applications of machine learning is the prediction of time series. But a more accurate prediction requires a more optimal model of machine learning. Several optimization techniques have been developed, but without considering the input variables disposition of the system. Thus, this work aims to present a new machine learning architecture optimization technique based on their optimal input variables disposition. The validations are done on the prediction of wind time series, using data collected in Cameroon. The number of possible dispositions with four input variables is determined, i.e., twenty-four. Each of the dispositions is used to perform the prediction, with the main criteria being the training and prediction performances. The results obtained from a static architecture and a dynamic architecture of neural networks have shown that these performances are a function of the input variable's disposition, and this is in a different way from the architectures. This analysis revealed that it is necessary to take into account the input variable's disposition for the development of a more optimal neural network model. Thus, a new neural network training algorithm is proposed by introducing the search for the optimal input variables disposition in the traditional back-propagation algorithm. The results of the application of this new optimization approach on the two single neural network architectures are compared with the previously obtained results step by step. Moreover, this proposed approach is validated in a collaborative optimization method with a single objective optimization technique, i.e., genetic algorithm back-propagation neural networks. From these comparisons, it is concluded that each proposed model outperforms its traditional model in terms of training and prediction performance of time series. Thus the proposed optimization approach can be useful in improving the accuracy of time series forecasts. This proves that the proposed optimization approach can be useful in improving the accuracy of time series prediction based on machine learning.

Keywords: input variable disposition, machine learning, optimization, performance, time series prediction

Procedia PDF Downloads 104

Authors: Thomas Meier

Abstract:

One of the major challenges for sustainable smart building systems is to support device interoperability, i.e. connecting sensor or actuator devices from different vendors, and present their functionality to the external applications. Furthermore, smart building systems are supposed to connect with devices that are not available yet, i.e. devices that become available on the market sometime later. It is of vital importance that a sustainable smart building platform provides an appropriate external interface that can be leveraged by external applications and smart services. An external platform interface must be stable and independent of specific devices and should support flexible and scalable usage scenarios. A typical approach applied in smart home systems is based on a generic device interface used within the smart building platform. Device functions, even of rather complex devices, are mapped to that generic base type interface by means of specific device drivers. Our new approach, presented in this work, extends that approach by using the smart building system’s rule engine to create complex virtual devices that can represent the most diverse properties of real devices. We examined and evaluated both approaches by means of a practical case study using a smart building system that we have developed. We show that the solution we present allows the highest degree of flexibility without affecting external application interface stability and scalability. In contrast to other systems our approach supports complex virtual device configuration on application layer (e.g. by administration users) instead of device configuration at platform layer (e.g. platform operators). Based on our work, we can show that our approach supports almost arbitrarily flexible use case scenarios without affecting the external application interface stability. However, the cost of this approach is additional appropriate configuration overhead and additional resource consumption at the IoT platform level that must be considered by platform operators. We conclude that the concept of complex virtual devices presented in this work can be applied to improve the usability and device interoperability of sustainable intelligent building systems significantly.

Keywords: Internet of Things, smart building, device interoperability, device integration, smart home

Procedia PDF Downloads 267

Authors: Motahareh Fadaei

Abstract:

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

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

Procedia PDF Downloads 312

Authors: Azyz Sharafy

Abstract:

3D Text Toys is an innovative and creative approach that utilizes 3D text objects to enhance creativity, literacy, and basic learning in an enjoyable and gamified manner. By using 3D Text Toys, children can develop their creativity, visually learn words and texts, and apply their artistic talents within their creative abilities. This process incorporates haptic engagement with 2D and 3D texts, word building, and mechanical construction of everyday objects, thereby facilitating better word and text retention. The concept involves constructing visual objects made entirely out of 3D text/words, where each component of the object represents a word or text element. For instance, a bird can be recreated using words or text shaped like its wings, beak, legs, head, and body, resulting in a 3D representation of the bird purely composed of text. This can serve as an art piece or a learning tool in the form of a 3D text toy. These 3D text objects or toys can be crafted using natural materials such as leaves, twigs, strings, or ropes, or they can be made from various physical materials using traditional crafting tools. Digital versions of these objects can be created using 2D or 3D software on devices like phones, laptops, iPads, or computers. To transform digital designs into physical objects, computerized machines such as CNC routers, laser cutters, and 3D printers can be utilized. Once the parts are printed or cut out, students can assemble the 3D texts by gluing them together, resulting in natural or everyday 3D text objects. These objects can be painted to create artistic pieces or text toys, and the addition of wheels can transform them into moving toys. One of the significant advantages of this visual and creative object-based learning process is that students not only learn words but also derive enjoyment from the process of creating, painting, and playing with these objects. The ownership and creation process further enhances comprehension and word retention. Moreover, for individuals with learning disabilities such as dyslexia, ADD (Attention Deficit Disorder), or other learning difficulties, the visual and haptic approach of 3D Text Toys can serve as an additional creative and personalized learning aid. The application of 3D Text Toys extends to both the English language and any other global written language. The adaptation and creative application may vary depending on the country, space, and native written language. Furthermore, the implementation of this visual and haptic learning tool can be tailored to teach foreign languages based on age level and comprehension requirements. In summary, this creative, haptic, and visual approach has the potential to serve as a global literacy tool.

Keywords: 3D text toys, creative, artistic, visual learning for world literacy

Procedia PDF Downloads 63

Authors: Aregamalage Sujeewa Vijayanthi Polgampala, Fang Huang

Abstract:

This study explores the genesis and development of concept mapping as a useful tool for science education and its effectiveness as technique for teaching and learning and evaluation for secondary science in schools and the role played by National College of Education science teachers. Concept maps, when carefully employed and executed serves as an integral part of teaching method and measure of effectiveness of teaching and tool for evaluation. Research has shown that science concept maps can have positive influence on student learning and motivation. The success of concept maps played in an instruction class depends on the type of theme selected, the development of learning outcomes, and the flexibility of instruction in providing library unit that is equipped with multimedia equipment where learners can interact. The study was restricted to 6 male and 9 female respondents' teachers in third-year internship pre service science teachers in Gampaha district Sri Lanka. Data were collected through 15 item questionnaire provided to learners and in depth interviews and class observations of 18 science classes. The two generated hypotheses for the study were rejected, while the results revealed that significant difference exists between factors influencing teachers' choice of concept maps, its usefulness and problems hindering the effectiveness of concept maps for teaching and learning process of secondary science in schools. It was examined that concept maps can be used as an effective measure to evaluate students understanding of concepts and misconceptions. Even the teacher trainees could not identify, key concept is on top, and subordinate concepts fall below. It is recommended that pre service science teacher trainees should be provided a thorough training using it as an evaluation instrument.

Keywords: concept maps, evaluation, learning science, misconceptions

Procedia PDF Downloads 271

Authors: Bo-Bin Xiaoa, Chia-Yi Liua

Abstract:

In the task of searching for anomalous radiation sources, personnel holding radiation detectors to search for radiation sources may be exposed to unnecessary radiation risk, and automated search using machines becomes a required project. The research uses various sophisticated algorithms, which are double Q learning, dueling network, and NoisyNet, of deep reinforcement learning to search for radiation sources. The simulation environment, which is a 10*10 grid and one shielding wall setting in it, improves the development of the AI model by training 1 million episodes. In each episode of training, the radiation source position, the radiation source intensity, agent position, shielding wall position, and shielding wall length are all set randomly. The three algorithms are applied to run AI model training in four environments where the training shielding wall is a full-shielding wall, a lead wall, a concrete wall, and a lead wall or a concrete wall appearing randomly. The 12 best performance AI models are selected by observing the reward value during the training period and are evaluated by comparing these AI models with the gradient search algorithm. The results show that the performance of the AI model, no matter which one algorithm, is far better than the gradient search algorithm. In addition, the simulation environment becomes more complex, the AI model which applied Double DQN combined Dueling and NosiyNet algorithm performs better.

Keywords: double Q learning, dueling network, NoisyNet, source searching

Procedia PDF Downloads 105

Authors: Nitin Singh, Meng Ling, Talha Ahmed, Tianxia Zhao, Reinier van de Pol

Abstract:

We propose the use of reinforcement learning (RL) as a viable alternative for optimizing supply chain management, particularly in scenarios with stochasticity in product demands. RL’s adaptability to changing conditions and its demonstrated success in diverse fields of sequential decision-making makes it a promising candidate for addressing supply chain problems. We investigate the impact of demand fluctuations in a multi-product supply chain system and develop RL agents with learned generalizable policies. We provide experimentation details for training RL agents and statistical analysis of the results. We study the generalization ability of RL agents for different demand uncertainty scenarios and observe superior performance compared to the agents trained with fixed demand curves. The proposed methodology has the potential to lead to cost reduction and increased profit for companies dealing with frequent inventory movement between supply and demand nodes.

Keywords: inventory management, reinforcement learning, supply chain optimization, uncertainty

Procedia PDF Downloads 103

Authors: Ci Lin, Tet Yeap, Iluju Kiringa

Abstract:

This paper introduces the subspace rotation algorithm (SRA) to train the Restricted Hopfield Network (RHN) as an auto-associative memory. Subspace rotation algorithm is a gradient-free subspace tracking approach based on the singular value decomposition (SVD). In comparison with Backpropagation Through Time (BPTT) on training RHN, it is observed that SRA could always converge to the optimal solution and BPTT could not achieve the same performance when the model becomes complex, and the number of patterns is large. The AUTS case study showed that the RHN model trained by SRA could achieve a better structure of attraction basin with larger radius(in general) than the Hopfield Network(HNN) model trained by Hebbian learning rule. Through learning 10000 patterns from MNIST dataset with RHN models with different number of hidden nodes, it is observed that an several components could be adjusted to achieve a balance between recovery accuracy and noise resistance.

Keywords: hopfield neural network, restricted hopfield network, subspace rotation algorithm, hebbian learning rule

Procedia PDF Downloads 113

Authors: AnjalI A. Prasad

Abstract:

Nowadays, social media played an important role in spreading misinformation or fake news. This study analyzes the fake news related to the COVID-19 pandemic spread in social media. This paper aims at evaluating and comparing different approaches that are used to mitigate this issue, including popular deep learning approaches, such as CNN, RNN, LSTM, and BERT algorithm for classification. To evaluate models’ performance, we used accuracy, precision, recall, and F1-score as the evaluation metrics. And finally, compare which algorithm shows better result among the four algorithms.

Keywords: BERT, CNN, LSTM, RNN

Procedia PDF Downloads 201

Authors: Hongliang Ding, Ziqu Ouyang

Abstract:

Under the basic national conditions that the energy structure is dominated by coal, it is of great significance to realize deep and flexible peak shaving of boilers in pulverized coal power plants, and maximize the consumption of renewable energy in the power grid, to ensure China's energy security and scientifically achieve the goals of carbon peak and carbon neutrality. With the promising self-preheating combustion technology, which had the potential of broad-load regulation and rapid response to load changes, this study mainly investigated the different load operation and rapid load-change characteristics of pulverized coal combustion. Four effective load-stabilization bases were proposed according to preheating temperature, coal gas composition (calorific value), combustion temperature (spatial mean temperature and mean square temperature fluctuation coefficient), and flue gas emissions (CO and NOx concentrations), on the basis of which the load-change rates were calculated to assess the load response characteristics. Due to the improvement of the physicochemical properties of pulverized coal after preheating, stable ignition and combustion conditions could be obtained even at a low load of 25%, with a combustion efficiency of over 97.5%, and NOx emission reached the lowest at 50% load, with the concentration of 50.97 mg/Nm3 (@6%O2). Additionally, the load ramp-up stage displayed higher load-change rates than the load ramp-down stage, with maximum rates of 3.30 %/min and 3.01 %/min, respectively. Furthermore, the driving force formed by high step load was conducive to the increase of load-change rate. The rates based on the preheating indicator attained the highest value of 3.30 %/min, while the rates based on the combustion indicator peaked at 2.71 %/min. In comparison, the combustion indicator accurately described the system’s combustion state and load changes, whereas the preheating indicator was easier to acquire, with a higher load-change rate, hence the appropriate evaluation strategy should depend on the actual situation. This study verified a feasible method for deep and flexible peak shaving of coal-fired power units, further providing basic data and technical supports for future engineering applications.

Keywords: clean coal combustion, load-change rate, peak shaving, self-preheating

Procedia PDF Downloads 66