Search results for: multiple instance learning
11474 Deep Learning to Enhance Mathematics Education for Secondary Students in Sri Lanka
Authors: Selvavinayagan Babiharan
Abstract:
This research aims to develop a deep learning platform to enhance mathematics education for secondary students in Sri Lanka. The platform will be designed to incorporate interactive and user-friendly features to engage students in active learning and promote their mathematical skills. The proposed platform will be developed using TensorFlow and Keras, two widely used deep learning frameworks. The system will be trained on a large dataset of math problems, which will be collected from Sri Lankan school curricula. The results of this research will contribute to the improvement of mathematics education in Sri Lanka and provide a valuable tool for teachers to enhance the learning experience of their students.Keywords: information technology, education, machine learning, mathematics
Procedia PDF Downloads 8311473 Reactive Learning about Food Waste Reduction in a Food Processing Plant in Gauteng Province, South Africa
Authors: Nesengani Elelwani Clinton
Abstract:
This paper presents reflective learning as an opportunity commonly available and used for food waste learning in a food processing company in the transition to sustainable and just food systems. In addressing how employees learn about food waste during food processing, the opportunities available for food waste learning were investigated. Reflective learning appeared to be the most used approach to learning about food waste. In the case of food waste learning, reflective learning was a response after employees wasted a substantial amount of food, where process controllers and team leaders would highlight the issue to employees who wasted food and explain how food waste could be reduced. This showed that learning about food waste is not proactive, and there continues to be a lack of structured learning around food waste. Several challenges were highlighted around reflective learning about food waste. Some of the challenges included understanding the language, lack of interest from employees, set times to reach production targets, and working pressures. These challenges were reported to be hindering factors in understanding food waste learning, which is not structured. A need was identified for proactive learning through structured methods. This is because it was discovered that in the plant, where food processing activities happen, the signage and posters that are there are directly related to other sustainability issues such as food safety and health. This indicated that there are low levels of awareness about food waste. Therefore, this paper argues that food waste learning should be proactive. The proactive learning approach should include structured learning materials around food waste during food processing. In the structuring of the learning materials, individual trainers should be multilingual. This will make it possible for those who do not understand English to understand in their own language. And lastly, there should be signage and posters in the food processing plant around food waste. This will bring more awareness around food waste, and employees' behaviour can be influenced by the posters and signage in the food processing plant. Thus, will enable a transition to a just and sustainable food system.Keywords: sustainable and just food systems, food waste, food waste learning, reflective learning approach
Procedia PDF Downloads 12911472 A Qualitative Student-Perspective Study of Student-Centered Learning Practices in the Context of Irish Teacher Education
Authors: Pauline Logue
Abstract:
In recent decades, the Irish Department of Education and Skills has pro-actively promoted student-center learning methodologies. Similarly, the National Forum for the Enhancement of Teaching and Learning has advocated such strategies, aligning them with student success. These developments have informed the author’s professional practice as a teacher educator. This qualitative student-perspective study focuses on a review of one pilot initiative in the academic year 2020-2021, namely, the implementation of universal design for learning strategies within teacher education, employing student-centered learning strategies. Findings included: that student-centered strategies enhanced student performance and success overall, with some minor evidence of student resistance. It was concluded that a dialogical review with student teachers on prior learning experiences (from intellectual and affective perspectives) and learning environments (physical, virtual, and emotional) could facilitate greater student ownership of learning. It is recommended to more formally structure such a dialogical review in a future delivery.Keywords: professional practice, student-centered learning, teacher education, universal design for learning
Procedia PDF Downloads 19511471 Learning Mandarin Chinese as a Foreign Language in a Bilingual Context: Adult Learners’ Perceptions of the Use of L1 Maltese and L2 English in Mandarin Chinese Lessons in Malta
Authors: Christiana Gauci-Sciberras
Abstract:
The first language (L1) could be used in foreign language teaching and learning as a pedagogical tool to scaffold new knowledge in the target language (TL) upon linguistic knowledge that the learner already has. In a bilingual context, code-switching between the two languages usually occurs in classrooms. One of the reasons for code-switching is because both languages are used for scaffolding new knowledge. This research paper aims to find out why both the L1 (Maltese) and the L2 (English) are used in the classroom of Mandarin Chinese as a foreign language (CFL) in the bilingual context of Malta. This research paper also aims to find out the learners’ perceptions of the use of a bilingual medium of instruction. Two research methods were used to collect qualitative data; semi-structured interviews with adult learners of Mandarin Chinese and lesson observations. These two research methods were used so that the data collected in the interviews would be triangulated with data collected in lesson observations. The L1 (Maltese) is the language of instruction mostly used. The teacher and the learners switch to the L2 (English) or to any other foreign language according to the need at a particular instance during the lesson.Keywords: Chinese, bilingual, pedagogical purpose of L1 and L2, CFL acquisition
Procedia PDF Downloads 20011470 A Case Study of Meaningful Learning in Play for Young Children
Authors: Baoliang Xu
Abstract:
The future of education should focus on creating meaningful learning for learners. Play is a basic form and an important means of carrying out kindergarten educational activities, which promotes the creation and development of meaningful learning and is of great importance in the harmonious physical and mental development of young children. Through literature research and case studies, this paper finds that: meaningful learning has the characteristics of contextuality, interaction and constructiveness; teachers should pay great attention to the guidance of children's games, fully respect children's autonomy and create a prepared game environment; children's meaningful learning exists in games and hidden in things that interest them, and "the generation of questions The "generation of questions" fuels the depth of children's meaningful learning, and teachers' professional support helps children's meaningful learning to develop continuously. In short, teachers' guidance of young children's play should be emphasized to effectively provide scaffolding instruction to promote meaningful learning in a holistic manner.Keywords: meaningful learning, young childhood, game, case study
Procedia PDF Downloads 7111469 Analysing Perceptions of Online Games-Based Learning: Case Study of the University of Northampton
Authors: Alison Power
Abstract:
Games-based learning aims to enhance students’ engagement with and enjoyment of learning opportunities using games-related principles to create a fun yet productive learning environment. Motivating students to learn in an online setting can be particularly challenging, so a cross-Faculty synchronous online session provided students with the opportunity to engage with ‘GAMING’: an interactive, flexible and scalable e-resource for students to work synchronously in groups to complete a series of e-tivities designed to enhance their skills of leadership, collaboration and negotiation. Findings from a post-session online survey found the majority of students had a positive learning experience, finding 'GAMING' to be an innovative and engaging e-resource which motivated their group to learn.Keywords: collaboration, games-based learning, groupwork, synchronous online learning, teamwork
Procedia PDF Downloads 12611468 Disparity of Learning Styles and Cognitive Abilities in Vocational Education
Authors: Mimi Mohaffyza Mohamad, Yee Mei Heong, Nurfirdawati Muhammad Hanafi, Tee Tze Kiong
Abstract:
This study is conducted to investigate the disparity of between learning styles and cognitive abilities specifically in Vocational Education. Felder and Silverman Learning Styles Model (FSLSM) was applied to measure the students’ learning styles while the content in Building Construction Subject consists; knowledge, skills and problem solving were taken into account in constructing the elements of cognitive abilities. There are four dimension of learning styles proposed by Felder and Silverman intended to capture student learning preferences with regards to processing either active or reflective, perception based on sensing or intuitive, input of information used visual or verbal and understanding information represent with sequential or global learner. The study discovered that students are tending to be visual learners and each type of learner having significant difference whereas cognitive abilities. The finding may help teachers to facilitate students more effectively and to boost the student’s cognitive abilities.Keywords: learning styles, cognitive abilities, dimension of learning styles, learning preferences
Procedia PDF Downloads 40211467 E–Learning System in Virtual Learning Environment to Develop Problem Solving Ability and Team Learning for Learners in Higher Education
Authors: Noawanit Songkram
Abstract:
This paper is a report on the findings of a study conducted on e–learning system in virtual learning environment to develop problem solving ability and team learning for learners in higher education. The methodology of this study was R&D research. The subjects were 18 undergraduate students in Faculty of Education, Chulalongkorn University in the academic year of 2013. The research instruments were a problem solving ability assessment, a team learning evaluation form, and an attitude questionnaire. The data was statistically analyzed using mean, standard deviation, one way repeated measure ANOVA and t–test. The research findings discovered the e –learning system in virtual learning environment to develop problem solving ability and team learning for learners in higher education consisted of five components:(1) online collaborative tools, (2) active learning activities, (3) creative thinking, (4) knowledge sharing process, (5) evaluation and nine processes which were (1) preparing in group working, (2) identifying interested topic, (3) analysing interested topic, (4) collecting data, (5) concluding idea (6) proposing idea, (7) creating workings, (8) workings evaluation, (9) sharing knowledge from empirical experience.Keywords: e-learning system, problem solving ability, team leaning, virtual learning environment
Procedia PDF Downloads 43811466 E-Learning Approaches Based on Artificial Intelligence Techniques: A Survey
Authors: Nabila Daly, Hamdi Ellouzi, Hela Ltifi
Abstract:
In last year’s, several recent researches’ that focus on e-learning approaches having as goal to improve pedagogy and student’s academy level assessment. E-learning-related works have become an important research file nowadays due to several problems that make it impossible for students join classrooms, especially in last year’s. Among those problems, we note the current epidemic problems in the word case of Covid-19. For those reasons, several e-learning-related works based on Artificial Intelligence techniques are proposed to improve distant education targets. In the current paper, we will present a short survey of the most relevant e-learning based on Artificial Intelligence techniques giving birth to newly developed e-learning tools that rely on new technologies.Keywords: artificial intelligence techniques, decision, e-learning, support system, survey
Procedia PDF Downloads 22511465 The Link Between Knowledge Management, Organizational Learning and Collective Competence
Authors: Amira Khelil, Habib Affes
Abstract:
The XXIst century is characterized by promoting teamwork as one of the main drivers of firms` performance. Collective competence is becoming crucial in developing and maintaining a firm’s competitive advantage, as well as its contributions to organizational innovation. In other words, the improvement of collective competence for a firm is no longer a choice, but rather an obligation. Learning capabilities of a firm in the context of knowledge management are assumed to be the main drivers of collective competence. Although there are some efforts to consider these concepts together; they are mostly discussed separately in the management theory. Thus, this paper aims to offer a holistic approach for development collective competence on the basis of Knowledge Management and Organizational Learning Capabilities. A theoretical model that defines a relationship between knowledge management, organizational learning and collective competence is presented at the end of this paper.Keywords: collective competence, exploitation learning, exploration learning, knowledge management, organizational learning capabilities
Procedia PDF Downloads 50711464 Scalable Performance Testing: Facilitating The Assessment Of Application Performance Under Substantial Loads And Mitigating The Risk Of System Failures
Authors: Solanki Ravirajsinh
Abstract:
In the software testing life cycle, failing to conduct thorough performance testing can result in significant losses for an organization due to application crashes and improper behavior under high user loads in production. Simulating large volumes of requests, such as 5 million within 5-10 minutes, is challenging without a scalable performance testing framework. Leveraging cloud services to implement a performance testing framework makes it feasible to handle 5-10 million requests in just 5-10 minutes, helping organizations ensure their applications perform reliably under peak conditions. Implementing a scalable performance testing framework using cloud services and tools like JMeter, EC2 instances (Virtual machine), cloud logs (Monitor errors and logs), EFS (File storage system), and security groups offers several key benefits for organizations. Creating performance test framework using this approach helps optimize resource utilization, effective benchmarking, increased reliability, cost savings by resolving performance issues before the application is released. In performance testing, a master-slave framework facilitates distributed testing across multiple EC2 instances to emulate many concurrent users and efficiently handle high loads. The master node orchestrates the test execution by coordinating with multiple slave nodes to distribute the workload. Slave nodes execute the test scripts provided by the master node, with each node handling a portion of the overall user load and generating requests to the target application or service. By leveraging JMeter's master-slave framework in conjunction with cloud services like EC2 instances, EFS, CloudWatch logs, security groups, and command-line tools, organizations can achieve superior scalability and flexibility in their performance testing efforts. In this master-slave framework, JMeter must be installed on both the master and each slave EC2 instance. The master EC2 instance functions as the "brain," while the slave instances operate as the "body parts." The master directs each slave to execute a specified number of requests. Upon completion of the execution, the slave instances transmit their results back to the master. The master then consolidates these results into a comprehensive report detailing metrics such as the number of requests sent, encountered errors, network latency, response times, server capacity, throughput, and bandwidth. Leveraging cloud services, the framework benefits from automatic scaling based on the volume of requests. Notably, integrating cloud services allows organizations to handle more than 5-10 million requests within 5 minutes, depending on the server capacity of the hosted website or application.Keywords: identify crashes of application under heavy load, JMeter with cloud Services, Scalable performance testing, JMeter master and slave using cloud Services
Procedia PDF Downloads 2711463 Detecting Music Enjoyment Level Using Electroencephalogram Signals and Machine Learning Techniques
Authors: Raymond Feng, Shadi Ghiasi
Abstract:
An electroencephalogram (EEG) is a non-invasive technique that records electrical activity in the brain using scalp electrodes. Researchers have studied the use of EEG to detect emotions and moods by collecting signals from participants and analyzing how those signals correlate with their activities. In this study, researchers investigated the relationship between EEG signals and music enjoyment. Participants listened to music while data was collected. During the signal-processing phase, power spectral densities (PSDs) were computed from the signals, and dominant brainwave frequencies were extracted from the PSDs to form a comprehensive feature matrix. A machine learning approach was then taken to find correlations between the processed data and the music enjoyment level indicated by the participants. To improve on previous research, multiple machine learning models were employed, including K-Nearest Neighbors Classifier, Support Vector Classifier, and Decision Tree Classifier. Hyperparameters were used to fine-tune each model to further increase its performance. The experiments showed that a strong correlation exists, with the Decision Tree Classifier with hyperparameters yielding 85% accuracy. This study proves that EEG is a reliable means to detect music enjoyment and has future applications, including personalized music recommendation, mood adjustment, and mental health therapy.Keywords: EEG, electroencephalogram, machine learning, mood, music enjoyment, physiological signals
Procedia PDF Downloads 6111462 Parental Involvement and Motivation as Predictors of Learning Outcomes in Yoruba Language Value Concepts among Senior Secondary School Students in Ibadan, Nigeria
Authors: Adeyemi Adeyinka, Yemisi Ilesanmi
Abstract:
This study investigated parental involvement and motivation as predictors of students’ learning outcomes in value concepts in Yoruba language in Ibadan, Nigeria. Value concepts in Yoruba language aimed at teaching moral lessons and transmitting Yoruba culture. However, feelers from schools and the society reported students’ poor achievement in examinations and negative attitude to the subject. Previous interventions focused on teaching strategies with little consideration for student-related factors. The study was anchored on psychosocial learning theory. The respondents were senior secondary II students with mean age of 15.50 ± 2.25 from 20 public schools in Ibadan, Oyo-State. In all, 1000 students were selected (486 males and 514 females) through proportionate to sample size technique. Instruments used were Students’ Motivation (r=0.79), Parental Involvement (r=0.87), and Attitude to Yoruba Value Concepts (r=0.94) scales and Yoruba Value Concepts Achievement Test (r=0.86). Data were analyzed using descriptive statistics, Pearson product moment correlation and Multiple regressions at 0.05 level of significance. Findings revealed a significant relationship between parental involvement (r=0.54) and students’ achievement in and attitude to (r=0.229) value concepts in Yoruba. The composite contribution of parental involvement and motivation to students’ achievement and attitude was significant, contributing 20.3% and 5.1% respectively. The relative contributions of parental involvement to students’ achievement (β = 0.073; t = 1.551) and attitude (β = 0.228; t = 7.313) to value concepts in Yoruba were significant. Parental involvement was the independent variable that strongly predicts students’ achievement in and attitude to Yoruba value concepts. Parents should inculcate indigenous knowledge in their children and support its learning at school.Keywords: parental involvement, motivation, predictors, learning outcomes, value concepts in Yoruba
Procedia PDF Downloads 20111461 Impact of Pedagogical Techniques on the Teaching of Sports Sciences
Authors: Muhammad Saleem
Abstract:
Background: The teaching of sports sciences encompasses a broad spectrum of disciplines, including biomechanics, physiology, psychology, and coaching. Effective pedagogical techniques are crucial in imparting both theoretical knowledge and practical skills necessary for students to excel in the field. The impact of these techniques on students’ learning outcomes, engagement, and professional preparedness remains a vital area of study. Objective: This study aims to evaluate the effectiveness of various pedagogical techniques used in the teaching of sports sciences. It seeks to identify which methods most significantly enhance student learning, retention, engagement, and practical application of knowledge. Methods: A mixed-methods approach was employed, including both quantitative and qualitative analyses. The study involved a comparative analysis of traditional lecture-based teaching, experiential learning, problem-based learning (PBL), and technology-enhanced learning (TEL). Data were collected through surveys, interviews, and academic performance assessments from students enrolled in sports sciences programs at multiple universities. Statistical analysis was used to evaluate academic performance, while thematic analysis was applied to qualitative data to capture student experiences and perceptions. Results: The findings indicate that experiential learning and PBL significantly improve students' understanding and retention of complex sports science concepts compared to traditional lectures. TEL was found to enhance engagement and provide students with flexible learning opportunities, but its impact on deep learning varied depending on the quality of the digital resources. Overall, a combination of experiential learning, PBL, and TEL was identified as the most effective pedagogical approach, leading to higher student satisfaction and better preparedness for real-world applications. Conclusion: The study underscores the importance of adopting diverse and student-centered pedagogical techniques in the teaching of sports sciences. While traditional lectures remain useful for foundational knowledge, integrating experiential learning, PBL, and TEL can substantially improve student outcomes. These findings suggest that educators should consider a blended approach to pedagogy to maximize the effectiveness of sports science education.Keywords: sport sciences, pedagogical techniques, health and physical education, problem-based learning, student engagement
Procedia PDF Downloads 2411460 Effect of Hybrid Learning in Higher Education
Authors: A. Meydanlioglu, F. Arikan
Abstract:
In recent years, thanks to the development of information and communication technologies, the computer and internet have been used widely in higher education. Internet-based education is impacting traditional higher education as online components increasingly become integrated into face-to-face (FTF) courses. The goal of combined internet-based and traditional education is to take full advantage of the benefits of each platform in order to provide an educational opportunity that can promote student learning better than can either platform alone. Research results show that the use of hybrid learning is more effective than online or FTF models in higher education. Due to the potential benefits, an increasing number of institutions are interested in developing hybrid courses, programs, and degrees. Future research should evaluate the effectiveness of hybrid learning. This paper is designed to determine the impact of hybrid learning on higher education.Keywords: e-learning, higher education, hybrid learning, online education
Procedia PDF Downloads 90911459 Pros and Cons of Distance Learning in Europe and Perspective for the Future
Authors: Aleksandra Ristic
Abstract:
The Coronavirus Disease – 2019 hit Europe in February 2020, and infections took place in four waves. It left consequences and demanded changes for the future. More than half of European countries responded quickly by declaring a state of emergency and introducing various containment measures that have had a major impact on individuals’ lives in recent years. Closing public lives was largely achieved by limited access and/or closing public institutions and services, including the closure of educational institutions. Teaching in classrooms converted to distance learning. In the research, we used a quantitative study to analyze various factors of distance learning that influenced pupils in different segments: teachers’ availability, family support, entire online conference learning, successful distance learning, time for themselves, reliable sources, teachers’ feedback, successful distance learning, online participation classes, motivation and teachers’ communication and theoretical review of the importance of digital skills, e-learning Index, World comparison of e-learning in the past, digital education plans for the field of Europe. We have gathered recommendations and distance learning solutions to improve the learning process by strengthening teachers and creating more tiered strategies for setting and achieving learning goals by the children.Keywords: availability, digital skills, distance learning, resources
Procedia PDF Downloads 10211458 Presenting a Model Based on Artificial Neural Networks to Predict the Execution Time of Design Projects
Authors: Hamed Zolfaghari, Mojtaba Kord
Abstract:
After feasibility study the design phase is started and the rest of other phases are highly dependent on this phase. forecasting the duration of design phase could do a miracle and would save a lot of time. This study provides a fast and accurate Machine learning (ML) and optimization framework, which allows a quick duration estimation of project design phase, hence improving operational efficiency and competitiveness of a design construction company. 3 data sets of three years composed of daily time spent for different design projects are used to train and validate the ML models to perform multiple projects. Our study concluded that Artificial Neural Network (ANN) performed an accuracy of 0.94.Keywords: time estimation, machine learning, Artificial neural network, project design phase
Procedia PDF Downloads 9711457 Learning Environments in the Early Years: A Case Study of an Early Childhood Centre in Australia
Authors: Mingxi Xiao
Abstract:
Children’s experiences in the early years build and shape the brain. The early years learning environment plays a significantly important role in children’s development. A well-constructed environment will facilitate children’s physical and mental well-being. This case study used an early learning centre in Australia called SDN Hurstville as an example, describing the learning environment in the centre, as well as analyzing the functions of the affordances. In addition, this report talks about the sustainability of learning in the centre, and how the environment supports cultural diversity and indigenous learning. The early years for children are significant. Different elements in the early childhood centre should work together to help children develop better. This case study found that the natural environment and the artificial environment are both critical to children; only when they work together can children have better development in physical and mental well-being and have a sense of belonging when playing and learning in the centre.Keywords: early childhood center, early childhood education, learning environment, Australia
Procedia PDF Downloads 24211456 Socio-Emotional Skills of Children with Learning Disability, Their Perceived Self-Efficacy and Academic Achievement
Authors: P. Maheshwari, M. Brindavan
Abstract:
The present research aimed to study the level of socio-emotional skills and perceived self-efficacy of children with learning disability. The study further investigated the relationship between the levels of socio-emotional skills, perceived self-efficacy and academic achievement of children with learning disability. The sample comprised of 40 children with learning disability as their primary condition, belonging to middle or upper middle class, living with both the parents, residing in Mumbai. Purposive or Judgmental and snowball sampling technique was used to select the sample for the study. Proformas in the form of questionnaires were used to obtain the background information of the children with learning disability. A self-constructed Child’s Perceived Self-Efficacy Assessment Scale and Child’s Social and Emotional Skills Assessment Scale was used to measure the level of child’s perceived self-efficacy and their level of social and emotional skill respectively. Academic scores of the child were collected from the child’s parents or teachers and were converted into a percentage. The data was analyzed quantitatively using SPSS. Spearman rho or Pearson Product Moment correlation was used to ascertain the multiple relationships between child’s perceived self-efficacy, child’s social and emotional skills and child’s academic achievement. The findings revealed majority (27) of the children with learning disability perceived themselves having above average level of social and emotional skills while 13 out of 40 perceived their level of social and emotional skills at an average level. Domain wise analyses revealed that, in the domain of self- management (26) and relationship skills (22) more number of the children perceived themselves as having average or below average level of social and emotional skills indicating that they perceived themselves as having average or below average skills in regulating their emotions, thoughts, and behaviors effectively in different situations, establishing and maintaining healthy and rewarding relationships with diverse groups and individuals. With regard to perceived self-efficacy, the majority of the children with learning disability perceived themselves as having above average level of self-efficacy. Looking at the data domain wise it was found that, in the domains of self-regulated learning and emotional self-efficacy, 50% of the children perceived themselves at average or below average level, indicating that they perceived themselves as average on competencies like organizing academic activities, structuring environment to make it conducive for learning, expressing emotions in a socially acceptable manner. Further, the correlations were computed, and significant positive correlations were found between children’s social and emotional skills and academic achievement (r=.378, p < .01), and between children’s social and emotional skills and child’s perceived self-efficacy (r = .724, p < .01) and a positive significant correlation was also found between children’s perceived self-efficacy and academic achievement (r=.332, p < .05). Results of the study emphasize on planning intervention for children with learning disability focusing on improving self-management and relationship skills, self-regulated learning and emotional self-efficacy.Keywords: learning disability, social and emotional skills, perceived self-efficacy, academic achievement
Procedia PDF Downloads 24111455 Hate Speech Detection Using Deep Learning and Machine Learning Models
Authors: Nabil Shawkat, Jamil Saquer
Abstract:
Social media has accelerated our ability to engage with others and eliminated many communication barriers. On the other hand, the widespread use of social media resulted in an increase in online hate speech. This has drastic impacts on vulnerable individuals and societies. Therefore, it is critical to detect hate speech to prevent innocent users and vulnerable communities from becoming victims of hate speech. We investigate the performance of different deep learning and machine learning algorithms on three different datasets. Our results show that the BERT model gives the best performance among all the models by achieving an F1-score of 90.6% on one of the datasets and F1-scores of 89.7% and 88.2% on the other two datasets.Keywords: hate speech, machine learning, deep learning, abusive words, social media, text classification
Procedia PDF Downloads 13611454 Preprocessing and Fusion of Multiple Representation of Finger Vein patterns using Conventional and Machine Learning techniques
Authors: Tomas Trainys, Algimantas Venckauskas
Abstract:
Application of biometric features to the cryptography for human identification and authentication is widely studied and promising area of the development of high-reliability cryptosystems. Biometric cryptosystems typically are designed for patterns recognition, which allows biometric data acquisition from an individual, extracts feature sets, compares the feature set against the set stored in the vault and gives a result of the comparison. Preprocessing and fusion of biometric data are the most important phases in generating a feature vector for key generation or authentication. Fusion of biometric features is critical for achieving a higher level of security and prevents from possible spoofing attacks. The paper focuses on the tasks of initial processing and fusion of multiple representations of finger vein modality patterns. These tasks are solved by applying conventional image preprocessing methods and machine learning techniques, Convolutional Neural Network (SVM) method for image segmentation and feature extraction. An article presents a method for generating sets of biometric features from a finger vein network using several instances of the same modality. Extracted features sets were fused at the feature level. The proposed method was tested and compared with the performance and accuracy results of other authors.Keywords: bio-cryptography, biometrics, cryptographic key generation, data fusion, information security, SVM, pattern recognition, finger vein method.
Procedia PDF Downloads 15011453 Optimize Data Evaluation Metrics for Fraud Detection Using Machine Learning
Authors: Jennifer Leach, Umashanger Thayasivam
Abstract:
The use of technology has benefited society in more ways than one ever thought possible. Unfortunately, though, as society’s knowledge of technology has advanced, so has its knowledge of ways to use technology to manipulate people. This has led to a simultaneous advancement in the world of fraud. Machine learning techniques can offer a possible solution to help decrease this advancement. This research explores how the use of various machine learning techniques can aid in detecting fraudulent activity across two different types of fraudulent data, and the accuracy, precision, recall, and F1 were recorded for each method. Each machine learning model was also tested across five different training and testing splits in order to discover which testing split and technique would lead to the most optimal results.Keywords: data science, fraud detection, machine learning, supervised learning
Procedia PDF Downloads 19511452 Harnessing the Opportunities of E-Learning and Education in Promoting Literacy in Nigeria
Authors: Victor Oluwaseyi Olowonisi
Abstract:
The paper aimed at presenting an overview on the concept of e-learning as it relates to higher education and how it provides opportunities for students, instructors and the government in developing the educational sector. It also touched on the benefits and challenges attached to e-learning as a new medium of reaching more students especially in the Nigerian context. The opportunities attributed to e-learning in the paper includes breaking boundaries barriers, reaching a larger number of students, provision of jobs for ICT experts, etc. In contrary, poor power supply, cost of implementation, poor computer literacy, technophobia (fear of technology), computer crime and system failure were some of the challenges of e-learning discussed in the paper. The paper proffered that the government can help the people gain more from e-learning through its financing. Also, it was stated that instructors/lecturers and students need to undergo training on computer application in order for e-learning to be more effective in developing higher education in Nigeria.Keywords: e-learning, education, higher education, increasing literacy
Procedia PDF Downloads 26811451 Students Perception of a Gamified Student Engagement Platform as Supportive Technology in Learning
Authors: Pinn Tsin Isabel Yee
Abstract:
Students are increasingly turning towards online learning materials to supplement their education. One such approach would be the gamified student engagement platforms (GSEPs) to instill a new learning culture. Data was collected from closed-ended questions via content analysis techniques. About 81.8% of college students from the Monash University Foundation Year agreed that GSEPs (Quizizz) was an effective tool for learning. Approximately 85.5% of students disagreed that games were a waste of time. GSEPs were highly effective among students to facilitate the learning process.Keywords: engagement, gamified, Quizizz, technology
Procedia PDF Downloads 10711450 Examining E-learning Capability in Chinese Higher Education: A Case Study of Hong Kong
Authors: Elson Szeto
Abstract:
Over the past 15 years, digital technology has ubiquitously penetrated societies around the world. New values of e-learning are emerging in the preparation of future talents, while e-learning is a key driver of widening participation and knowledge transfer in Chinese higher education. As a vibrant, Chinese society in Asia, Hong Kong’s new generation university students, perhaps the digital natives, have been learning with e-learning since their basic education. They can acquire new knowledge with the use of different forms of e-learning as a generic competence. These students who embrace this competence further their study journeys in higher education. This project reviews the Government’s policy of Information Technology in Education which has largely put forward since 1998. So far, primary to secondary education has embraced advantages of e-learning capability to advance the learning of different subject knowledge. Yet, e-learning capacity in higher education is yet to be fully examined in Hong Kong. The study reported in this paper is a pilot investigation into e-learning capacity in Chinese higher education in the region. By conducting a qualitative case study of Hong Kong, the investigation focuses on (1) the institutional ICT settings in general; (2) the pedagogic responses to e-learning in specific; and (3) the university students’ satisfaction of e-learning. It is imperative to revisit the e-learning capacity for promoting effective learning amongst university students, supporting new knowledge acquisition and embracing new opportunities in the 21st century. As a pilot case study, data will be collected from individual interviews with the e-learning management team members of a university, teachers who use e-learning for teaching and students who attend courses comprised of e-learning components. The findings show the e-learning capacity of the university and the key components of leveraging e-learning capability as a university-wide learning settings. The findings will inform institutions’ senior management, enabling them to effectively enhance institutional e-learning capacity for effective learning and teaching and new knowledge acquisition. Policymakers will be aware of new potentials of e-learning for the preparation of future talents in this society at large.Keywords: capability, e-learning, higher education, student learning
Procedia PDF Downloads 27411449 Factors of English Language Learning and Acquisition at Bisha College of Technology
Authors: Khlaid Albishi
Abstract:
This paper participates in giving new vision and explains the learning and acquisition processes of English language by analyzing a certain context. Five important factors in English language acquisition and learning are discussed and suitable solutions are provided. The factors are compared with the learners' linguistic background at Bisha College of Technology BCT attempting to link the issues faced by students and the research done on similar situations. These factors are phonology, age of acquisition, motivation, psychology and courses of English. These factors are very important; because they interfere and affect specific learning processes at BCT context and general English learning situations.Keywords: language acquisition, language learning, factors, Bisha college
Procedia PDF Downloads 49911448 Unsupervised Learning of Spatiotemporally Coherent Metrics
Authors: Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun
Abstract:
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity. We establish a connection between slow feature learning to metric learning and show that the trained encoder can be used to define a more temporally and semantically coherent metric.Keywords: machine learning, pattern clustering, pooling, classification
Procedia PDF Downloads 45611447 Evaluation of Aggregate Risks in Sustainable Manufacturing Using Fuzzy Multiple Attribute Decision Making
Authors: Gopinath Rathod, Vinod Puranik
Abstract:
Sustainability is regarded as a key concept for survival in the competitive scenario. Industrial risk and diversification of risk type’s increases with industrial developments. In the context of sustainable manufacturing, the evaluation of risk is difficult because of the incomplete information and multiple indicators. Fuzzy Multiple Attribute Decision Method (FMADM) has been used with a three level hierarchical decision making model to evaluate aggregate risk for sustainable manufacturing projects. A case study has been presented to reflect the risk characteristics in sustainable manufacturing projects.Keywords: sustainable manufacturing, decision making, aggregate risk, fuzzy logic, fuzzy multiple attribute decision method
Procedia PDF Downloads 51911446 Aerodynamic Analysis of Multiple Winglets for Aircrafts
Authors: S. Pooja Pragati, B. Sudarsan, S. Raj Kumar
Abstract:
This paper provides a practical design of a new concept of massive Induced Drag reductions of stream vise staggered multiple winglets. It is designed to provide an optimum performance of a winglet from conventional designs. In preparing for a mechanical design, aspects such as shape, dimensions are analyzed to yield a huge amount of reduction in fuel consumption and increased performance. Owing to its simplicity of application and effectiveness we believe that it will enable us to consider its enhanced version for the grid effect of the staggered multiple winglets on the deflected mass flow of the wing system. The objective of the analysis were to compare the aerodynamic characteristics of two winglet configuration and to investigate the performance of two winglets shape simulated at selected cant angle of 0,45,60 degree.Keywords: multiple winglets, induced drag, aerodynamics analysis, low speed aircrafts
Procedia PDF Downloads 48011445 The Impact of a Lower Health Literacy in the Self-Management of Patients with a Multiple Sclerosis: A Literature Review
Authors: Helga Martins, Idália Matias
Abstract:
Background:Multiple sclerosis is a chronic inflammatory autoimmune demyelinating disease that affects young adults. Multiple sclerosis is a chronic disease in which the patient needs to self-manage the disease and the therapeutic regimen. Consequently, the promotion of health literacy assumes a relevant role for the accessibility, understanding, and use of information in order to promote and maintain the health of patients with multiple sclerosis. Aim: To determine the impact of lower health literacy in the self-management of patients with a multiple sclerosis. Methods: Literature review based on a search on the following electronic databases: CINAHLand MEDLINE; comprising all results published between September 2016 and September 2021. The search strategy was: (“Self-management [MeSH]” AND “Multiple sclerosis[MeSH]”AND “Health literacy[MeSH]”). The inclusion criteria were: original papers reporting about multiple sclerosis patients; participants with age above 18 years old, written in English, Spanish, French, or Portuguese. Two independent reviewers have done the screening and analysis of the results. 38 citations were identified, and after duplicates removal, a total of 25 results were screened; 14 were included after the application of the inclusion criteria. Results: The lower health literacy in the self-management of patients with a multiple sclerosis is related toless healthy choices, riskier health behavior, poor health outcomes, decreased of adhering to the therapeutic regimen after discharge, less self-management of chronic illness, and increased the time of hospitalization. Conclusion: Inadequate levels of health literacy contribute to poor health outcomes, unsuccessful self-management of chronic illness, and inadequate adherence to the therapeutic regimen. Therefore, health literacy is important for health policy and the healthcare services, as it can be understood as a mediator of self-management of multiple sclerosis disease.Keywords: health literacy, multiple sclerosis, review, self-management
Procedia PDF Downloads 153