Search results for: self-regulated learning (SRL)
4646 Alexa (Machine Learning) in Artificial Intelligence
Authors: Loulwah Bokhari, Jori Nazer, Hala Sultan
Abstract:
Nowadays, artificial intelligence (AI) is used as a foundation for many activities in modern computing applications at home, in vehicles, and in businesses. Many modern machines are built to carry out a specific activity or purpose. This is where the Amazon Alexa application comes in, as it is used as a virtual assistant. The purpose of this paper is to explore the use of Amazon Alexa among people and how it has improved and made simple daily tasks easier for many people. We gave our participants several questions regarding Amazon Alexa and if they had recently used or heard of it, as well as the different tasks it provides and whether it successfully satisfied their needs. Overall, we found that participants who have recently used Alexa have found it to be helpful in their daily tasks.Keywords: artificial intelligence, Echo system, machine learning, feature for feature match
Procedia PDF Downloads 1094645 A Generalized Framework for Adaptive Machine Learning Deployments in Algorithmic Trading
Authors: Robert Caulk
Abstract:
A generalized framework for adaptive machine learning deployments in algorithmic trading is introduced, tested, and released as open-source code. The presented software aims to test the hypothesis that recent data contains enough information to form a probabilistically favorable short-term price prediction. Further, the framework contains various adaptive machine learning techniques that are geared toward generating profit during strong trends and minimizing losses during trend changes. Results demonstrate that this adaptive machine learning approach is capable of capturing trends and generating profit. The presentation also discusses the importance of defining the parameter space associated with the dynamic training data-set and using the parameter space to identify and remove outliers from prediction data points. Meanwhile, the generalized architecture enables common users to exploit the powerful machinery while focusing on high-level feature engineering and model testing. The presentation also highlights common strengths and weaknesses associated with the presented technique and presents a broad range of well-tested starting points for feature set construction, target setting, and statistical methods for enforcing risk management and maintaining probabilistically favorable entry and exit points. The presentation also describes the end-to-end data processing tools associated with FreqAI, including automatic data fetching, data aggregation, feature engineering, safe and robust data pre-processing, outlier detection, custom machine learning and statistical tools, data post-processing, and adaptive training backtest emulation, and deployment of adaptive training in live environments. Finally, the generalized user interface is also discussed in the presentation. Feature engineering is simplified so that users can seed their feature sets with common indicator libraries (e.g. TA-lib, pandas-ta). The user also feeds data expansion parameters to fill out a large feature set for the model, which can contain as many as 10,000+ features. The presentation describes the various object-oriented programming techniques employed to make FreqAI agnostic to third-party libraries and external data sources. In other words, the back-end is constructed in such a way that users can leverage a broad range of common regression libraries (Catboost, LightGBM, Sklearn, etc) as well as common Neural Network libraries (TensorFlow, PyTorch) without worrying about the logistical complexities associated with data handling and API interactions. The presentation finishes by drawing conclusions about the most important parameters associated with a live deployment of the adaptive learning framework and provides the road map for future development in FreqAI.Keywords: machine learning, market trend detection, open-source, adaptive learning, parameter space exploration
Procedia PDF Downloads 794644 Teacher Trainers’ Motivation in Transformation of Teaching and Learning: The Fun Way Approach
Authors: Malathi Balakrishnan, Gananthan M. Nadarajah, Noraini Abd Rahim, Amy Wong On Mei
Abstract:
The purpose of the study is to investigate the level of intrinsic motivation of trainers after attending a Continuous Professional Development Course (CPD) organized by Institute of Teacher Training Malaysia titled, ‘Transformation of Teaching and Learning the Fun Way’. This study employed a survey whereby 96 teacher trainers were given Situational Intrinsic Motivational Scale (SIMS) Instruments. Confirmatory factor analysis was carried out to get validity of this instrument in local setting. Data were analyzed with SPSS for descriptive statistic. Semi structured interviews were also administrated to collect qualitative data on participants experiences after participating in the two-day fun-filled program. The findings showed that the participants’ level of intrinsic motivation showed higher mean than the amotivation. The results revealed that the intrinsic motivation mean is 19.0 followed by Identified regulation with a mean of 17.4, external regulation 9.7 and amotivation 6.9. The interview data also revealed that the participants were motivated after attending this training program. It can be concluded that this program, which was organized by Institute of Teacher Training Malaysia, was able to enhance participants’ level of motivation. Self-Determination Theory (SDT) as a multidimensional approach to motivation was utilized. Therefore, teacher trainers may have more success using the ‘The fun way approach’ in conducting training program in future.Keywords: teaching and learning, motivation, teacher trainer, SDT
Procedia PDF Downloads 4504643 Neural Network based Risk Detection for Dyslexia and Dysgraphia in Sinhala Language Speaking Children
Authors: Budhvin T. Withana, Sulochana Rupasinghe
Abstract:
The educational system faces a significant concern with regards to Dyslexia and Dysgraphia, which are learning disabilities impacting reading and writing abilities. This is particularly challenging for children who speak the Sinhala language due to its complexity and uniqueness. Commonly used methods to detect the risk of Dyslexia and Dysgraphia rely on subjective assessments, leading to limited coverage and time-consuming processes. Consequently, delays in diagnoses and missed opportunities for early intervention can occur. To address this issue, the project developed a hybrid model that incorporates various deep learning techniques to detect the risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16, and YOLOv8 models were integrated to identify handwriting issues. The outputs of these models were then combined with other input data and fed into an MLP model. Hyperparameters of the MLP model were fine-tuned using Grid Search CV, enabling the identification of optimal values for the model. This approach proved to be highly effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention. The Resnet50 model exhibited a training accuracy of 0.9804 and a validation accuracy of 0.9653. The VGG16 model achieved a training accuracy of 0.9991 and a validation accuracy of 0.9891. The MLP model demonstrated impressive results with a training accuracy of 0.99918, a testing accuracy of 0.99223, and a loss of 0.01371. These outcomes showcase the high accuracy achieved by the proposed hybrid model in predicting the risk of Dyslexia and Dysgraphia.Keywords: neural networks, risk detection system, dyslexia, dysgraphia, deep learning, learning disabilities, data science
Procedia PDF Downloads 554642 Nuclear Near Misses and Their Learning for Healthcare
Authors: Nick Woodier, Iain Moppett
Abstract:
Background: It is estimated that one in ten patients admitted to hospital will suffer an adverse event in their care. While the majority of these will result in low harm, patients are being significantly harmed by the processes meant to help them. Healthcare, therefore, seeks to make improvements in patient safety by taking learning from other industries that are perceived to be more mature in their management of safety events. Of particular interest to healthcare are ‘near misses,’ those events that almost happened but for an intervention. Healthcare does not have any guidance as to how best to manage and learn from near misses to reduce the chances of harm to patients. The authors, as part of a larger study of near-miss management in healthcare, sought to learn from the UK nuclear sector to develop principles for how healthcare can identify, report, and learn from near misses to improve patient safety. The nuclear sector was chosen as an exemplar due to its status as an ultra-safe industry. Methods: A Grounded Theory (GT) methodology, augmented by a scoping review, was used. Data collection included interviews, scenario discussion, field notes, and the literature. The review protocol is accessible online. The GT aimed to develop theories about how nuclear manages near misses with a focus on defining them and clarifying how best to support reporting and analysis to extract learning. Near misses related to radiation release or exposure were focused on. Results: Eightnuclear interviews contributed to the GT across nuclear power, decommissioning, weapons, and propulsion. The scoping review identified 83 articles across a range of safety-critical industries, with only six focused on nuclear. The GT identified that nuclear has a particular focus on precursors and low-level events, with regulation supporting their management. Exploration of definitions led to the recognition of the importance of several interventions in a sequence of events, but that do not solely rely on humans as these cannot be assumed to be robust barriers. Regarding reporting and analysis, no consistent methods were identified, but for learning, the role of operating experience learning groups was identified as an exemplar. The safety culture across nuclear, however, was heard to vary, which undermined reporting of near misses and other safety events. Some parts of the industry described that their focus on near misses is new and that despite potential risks existing, progress to mitigate hazards is slow. Conclusions: Healthcare often sees ‘nuclear,’ as well as other ultra-safe industries such as ‘aviation,’ as homogenous. However, the findings here suggest significant differences in safety culture and maturity across various parts of the nuclear sector. Healthcare can take learning from some aspects of management of near misses in nuclear, such as how they are defined and how learning is shared through operating experience networks. However, healthcare also needs to recognise that variability exists across industries, and comparably, it may be more mature in some areas of safety.Keywords: culture, definitions, near miss, nuclear safety, patient safety
Procedia PDF Downloads 974641 Using Q Methodology to Capture Attitudes about Academic Resilience in an Online Postgraduate Psychology Course
Authors: Eleanor F. Willard
Abstract:
The attrition rate on distance learning courses can be high. This research examines how online students often react when faced with poor results. Using q methodology, it was found that the emotional response level and the type of social support sought by students were key influences on their attitude to failure. As educational and psychological researchers, we are adept at measuring learning and achievement, but examining attitudes towards barriers to learning are not so well researched. The distance learning student has differing needs from onsite learners and, as the attrition rate is notoriously high in the online student population, examining learners’ attitude towards adversity and barriers is important. Self-report measures such as questionnaires are useful in terms of ascertaining levels of constructs such as resilience and academic confidence. Interviewing, too, can gain in depth detail of the opinions of such a population, but only in individuals. The aim of this research was to ascertain what the feelings and attitudes of online students were when faced with a setback. This was achieved using q methodology due to its use of both quantitative and qualitative methodology and its suitability for exploratory research. The emphasis with this methodology is the attitudes, not the individuals. The work was focused upon a population of distance learning students who attended a school on site for one week as part of their studies. They were engaged in a psychology masters conversion course and, as such, were graduate students. The Q sort had 30 items taken from the Academic Resilience Scale (ARS-30). The scale items represent three constructs; perseverance, reflecting (including adaptive help-seeking) and negative affect. These are widely acknowledged as being relevant concepts underpinning psychological resilience. The q sort was conducted with 19 students in total. This is done by participants arranging statement cards regarding how similar to themselves they believe each statement to be. This was done after reading a vignette describing an experience of academic failure. Commonalities and differences between the sorts from all participants are then analyzed in terms of correlations and response patterns. Following data collection, the participants' responses were initially analyzed and the key perspectives (factors) to emerge were labelled ‘persevering individuals’ and ‘emotional networkers’. The differences between the two perspectives centre around the level of emotion felt when faced with barriers and the extent that students enlist the help of others inside and outside of the university. The dominant factor to emerge from the sorts of ‘persevering individuals’ demonstrated that many distance learners are tenacious. However, for other students, the level of emotional and social support is pivotal in helping them complete their studies when facing adversity. This was demonstrated by the ‘emotional networkers’ perspective. This research forms a starting point for further work on engaging and retaining online students at university and can potentially provide insight into how universities can lower attrition rates on distance learning courses.Keywords: academic resilience, distance learning, online learning, q methodology
Procedia PDF Downloads 1194640 Exploring Social Emotional Learning in Diverse Academic Settings
Authors: Regina Rahimi, Delores Liston
Abstract:
The advent of COVID-19 has heightened awareness of the need for social emotional learning (SEL) throughout all educational contexts. Given this, schools (most often p12 settings) have begun to embrace practices for addressing social-emotional learning. While there is a growing body of research and literature on common practices of SEL, there is no ‘standard’ for its implementation. Our work proposed here recognizes there is no universal approach for addressing SEL and rather, seeks to explore how SEL can be approached in and through diverse contexts. We assert that left unrecognized and unaddressed by teachers, issues with social and emotional well-being profoundly negatively affect students’ academic performance and exacerbate teacher stress. They contribute to negative student-teacher relationships, poor classroom management outcomes, and compromised academic outcomes. Therefore, teachers and administrators have increasingly turned to developing pedagogical and classroom practices that support the social and emotional dimensions of students. Substantive quantitative evidence indicates professional development training to improve awareness and foster positive teacher-student relationships can provide a protective function for psycho-social outcomes and a promotive factor for improved learning outcomes for students. Our work aims to add to the growing body of literature on improving student well-being by providing a unique examination of SEL through a lens of diverse contexts. Methodology: This presentation hopes to present findings from an edited volume that will seek to highlight works that examine SEL practices in a variety of academic settings. The studies contained within the work represent varied forms of qualitative research. Conclusion: This work provides examples of SEL in higher education/postsecondary settings, a variety of P12 academic settings (public; private; rural, urban; charter, etc.), and international contexts. This work demonstrates the variety of ways educational institutions and educators have used SEL to address the needs of students, providing examples for others to adapt to their own diverse contexts. This presentation will bring together exemplar models of SEL in diverse practice settings.Keywords: social emotional learning, teachers, classrooms, diversity
Procedia PDF Downloads 514639 Stack Overflow Detection and Prevention on Operating Systems Using Machine Learning and Control-Flow Enforcement Technology
Authors: Cao Jiayu, Lan Ximing, Huang Jingjia, Burra Venkata Durga Kumar
Abstract:
The first virus to attack personal computers was born in early 1986, called C-Brain, written by a pair of Pakistani brothers. In those days, people still used dos systems, manipulating computers with the most basic command lines. In the 21st century today, computer performance has grown geometrically. But computer viruses are also evolving and escalating. We never stop fighting against security problems. Stack overflow is one of the most common security vulnerabilities in operating systems. It may result in serious security issues for an operating system if a program in it has a vulnerability with administrator privileges. Certain viruses change the value of specific memory through a stack overflow, allowing computers to run harmful programs. This study developed a mechanism to detect and respond to time whenever a stack overflow occurs. We demonstrate the effectiveness of standard machine learning algorithms and control flow enforcement techniques in predicting computer OS security using generating suspicious vulnerability functions (SVFS) and associated suspect areas (SAS). The method can minimize the possibility of stack overflow attacks occurring.Keywords: operating system, security, stack overflow, buffer overflow, machine learning, control-flow enforcement technology
Procedia PDF Downloads 1084638 The Experiences of Secondary School Students in History Lessons in Distance and Formal Education
Authors: Osman Okumuş
Abstract:
The pandemic has significantly affected every aspect of life. Especially in recenttimes, as a result of this effect, we have come closer to technology. Distance education has taken the place of formal education rather than supporting formal education. Thiscreatednewexperiencesforbothteachersandstudents. This research focused on revealing the experiences of the same students in distance and formal education, especially in history lessons. In the study, which was designed as a case study, 20 students were interviewed through a semi-structured interview form prepared by the researcher. The results show that both learning environments provide students with important experiences. However, despite the fact that the students developed their digital competencies and experienced different learning environments, they focused on formal education in the name of socialization.Keywords: history lessons, distance education, pandemic., formal education
Procedia PDF Downloads 934637 Applications of Evolutionary Optimization Methods in Reinforcement Learning
Authors: Rahul Paul, Kedar Nath Das
Abstract:
The paradigm of Reinforcement Learning (RL) has become prominent in training intelligent agents to make decisions in environments that are both dynamic and uncertain. The primary objective of RL is to optimize the policy of an agent in order to maximize the cumulative reward it receives throughout a given period. Nevertheless, the process of optimization presents notable difficulties as a result of the inherent trade-off between exploration and exploitation, the presence of extensive state-action spaces, and the intricate nature of the dynamics involved. Evolutionary Optimization Methods (EOMs) have garnered considerable attention as a supplementary approach to tackle these challenges, providing distinct capabilities for optimizing RL policies and value functions. The ongoing advancement of research in both RL and EOMs presents an opportunity for significant advancements in autonomous decision-making systems. The convergence of these two fields has the potential to have a transformative impact on various domains of artificial intelligence (AI) applications. This article highlights the considerable influence of EOMs in enhancing the capabilities of RL. Taking advantage of evolutionary principles enables RL algorithms to effectively traverse extensive action spaces and discover optimal solutions within intricate environments. Moreover, this paper emphasizes the practical implementations of EOMs in the field of RL, specifically in areas such as robotic control, autonomous systems, inventory problems, and multi-agent scenarios. The article highlights the utilization of EOMs in facilitating RL agents to effectively adapt, evolve, and uncover proficient strategies for complex tasks that may pose challenges for conventional RL approaches.Keywords: machine learning, reinforcement learning, loss function, optimization techniques, evolutionary optimization methods
Procedia PDF Downloads 704636 Serious Game as a Performance Assessment Tool that Reduces Examination Anxiety
Authors: R. Ajith, Kamal Bijlani
Abstract:
Over the past few years, tremendous evolutions have happened in the educational discipline. Serious game, which is regarded as one of the most important inventions is being widely for learning purposes. Serious games can be used to negate the various drawbacks that the current evaluation and assessment methods have, like examination anxiety and the lack of proper feedback given to the learners. This paper proposes serious game as a tool for conducting evaluations and assessments. The examination anxiety faced by learners can be reduced, as they are provided with a game as an examination. The serious game also tracks learner’s actions, records them and provide feedback based on the predefined set of actions according to the course objectives. The appropriate feedback given to the learner will help in developmental activities in the learning process.Keywords: serious games, evaluation, performance assessment, examination anxiety, performance feedback
Procedia PDF Downloads 5914635 Predictive Analysis of the Stock Price Market Trends with Deep Learning
Authors: Suraj Mehrotra
Abstract:
The stock market is a volatile, bustling marketplace that is a cornerstone of economics. It defines whether companies are successful or in spiral. A thorough understanding of it is important - many companies have whole divisions dedicated to analysis of both their stock and of rivaling companies. Linking the world of finance and artificial intelligence (AI), especially the stock market, has been a relatively recent development. Predicting how stocks will do considering all external factors and previous data has always been a human task. With the help of AI, however, machine learning models can help us make more complete predictions in financial trends. Taking a look at the stock market specifically, predicting the open, closing, high, and low prices for the next day is very hard to do. Machine learning makes this task a lot easier. A model that builds upon itself that takes in external factors as weights can predict trends far into the future. When used effectively, new doors can be opened up in the business and finance world, and companies can make better and more complete decisions. This paper explores the various techniques used in the prediction of stock prices, from traditional statistical methods to deep learning and neural networks based approaches, among other methods. It provides a detailed analysis of the techniques and also explores the challenges in predictive analysis. For the accuracy of the testing set, taking a look at four different models - linear regression, neural network, decision tree, and naïve Bayes - on the different stocks, Apple, Google, Tesla, Amazon, United Healthcare, Exxon Mobil, J.P. Morgan & Chase, and Johnson & Johnson, the naïve Bayes model and linear regression models worked best. For the testing set, the naïve Bayes model had the highest accuracy along with the linear regression model, followed by the neural network model and then the decision tree model. The training set had similar results except for the fact that the decision tree model was perfect with complete accuracy in its predictions, which makes sense. This means that the decision tree model likely overfitted the training set when used for the testing set.Keywords: machine learning, testing set, artificial intelligence, stock analysis
Procedia PDF Downloads 864634 Fine-Tuned Transformers for Translating Multi-Dialect Texts to Modern Standard Arabic
Authors: Tahar Alimi, Rahma Boujebane, Wiem Derouich, Lamia Hadrich Belguith
Abstract:
Machine translation task of low-resourced languages such as Arabic is a challenging task. Despite the appearance of sophisticated models based on the latest deep learning techniques, namely the transfer learning and transformers, all models prove incapable of carrying out an acceptable translation, which includes Arabic Dialects (AD), because they do not have official status. In this paper, we present a machine translation model designed to translate Arabic multidialectal content into Modern Standard Arabic (MSA), leveraging both new and existing parallel resources. The latter achieved the best results for both Levantine and Maghrebi dialects with a BLEU score of 64.99.Keywords: Arabic translation, dialect translation, fine-tune, MSA translation, transformer, translation
Procedia PDF Downloads 424633 Integrating Technology into Foreign Language Teaching: A Closer Look at Arabic Language Instruction at the Australian National University
Authors: Kinda Alsamara
Abstract:
Foreign language education is a complex endeavor that often presents educators with a range of challenges and difficulties. This study shed light on the specific challenges encountered in the context of teaching Arabic as a foreign language at the Australian National University (ANU). Drawing from real-world experiences and insights, we explore the multifaceted nature of these challenges and discuss strategies that educators have employed to address them. The challenges in teaching the Arabic language encompass various dimensions, including linguistic intricacies, cultural nuances, and diverse learner backgrounds. The complex Arabic script, grammatical structures, and pronunciation patterns pose unique obstacles for learners. Moreover, the cultural context embedded within the language demands a nuanced understanding of cultural norms and practices. The diverse backgrounds of learners further contribute to the challenge of tailoring instruction to meet individual needs and proficiency levels. This study also underscores the importance of technology in tackling these challenges. Technological tools and platforms offer innovative solutions to enhance language acquisition and engagement. Online resources, interactive applications, and multimedia content can provide learners with immersive experiences, aiding in overcoming barriers posed by traditional teaching methods. Furthermore, this study addresses the role of instructors in mitigating challenges. Educators often find themselves adapting teaching approaches to accommodate different learning styles, abilities, and motivations. Establishing a supportive learning environment and fostering a sense of community can contribute significantly to overcoming challenges related to learner diversity. In conclusion, this study provides a comprehensive overview of the challenges faced in teaching Arabic as a foreign language at ANU. By recognizing these challenges and embracing technological and pedagogical advancements, educators can create more effective and engaging learning experiences for students pursuing Arabic language proficiency.Keywords: Arabic, Arabic online, blended learning, teaching and learning, Arabic language, educational aids, technology
Procedia PDF Downloads 534632 Analysis and Prediction of COVID-19 by Using Recurrent LSTM Neural Network Model in Machine Learning
Authors: Grienggrai Rajchakit
Abstract:
As we all know that coronavirus is announced as a pandemic in the world by WHO. It is speeded all over the world with few days of time. To control this spreading, every citizen maintains social distance and self-preventive measures are the best strategies. As of now, many researchers and scientists are continuing their research in finding out the exact vaccine. The machine learning model finds that the coronavirus disease behaves in an exponential manner. To abolish the consequence of this pandemic, an efficient step should be taken to analyze this disease. In this paper, a recurrent neural network model is chosen to predict the number of active cases in a particular state. To make this prediction of active cases, we need a database. The database of COVID-19 is downloaded from the KAGGLE website and is analyzed by applying a recurrent LSTM neural network with univariant features to predict the number of active cases of patients suffering from the corona virus. The downloaded database is divided into training and testing the chosen neural network model. The model is trained with the training data set and tested with a testing dataset to predict the number of active cases in a particular state; here, we have concentrated on Andhra Pradesh state.Keywords: COVID-19, coronavirus, KAGGLE, LSTM neural network, machine learning
Procedia PDF Downloads 1494631 Child-Friendly Digital Storytelling to Promote Young Learners' Critical Thinking in English Learning
Authors: Setyarini Sri, Nursalim Agus
Abstract:
Integrating critical thinking and digital based learning is one of demands in teaching English in 21st century. Child-friendly digital storytelling (CFDS) is an innovative learning model to promote young learners’ critical thinking. Therefore, this study aims to (1) investigate how child-friendly digital storytelling is implemented to promote young learners’ critical thinking in speaking English; (2) find out the benefits gained by the students in their learning based on CFDS. Classroom Action Research (CAR) took place in two cycles in which each of the cycle covered four phases namely: Planning, Acting, Observing, and Evaluating. Three classes of seventh graders were selected as the subjects of this study. Data were collected through observation, interview with some selected students as respondents, and document analysis in the form individual recorded storytelling. Sentences, phrases, words found in the transcribed data were identified and categorized based on Bloom taxonomy. The findings from the first cycle showed that the students seemed to speak critically that can be seen from the way they understood the story and related the story to their real life. Meanwhile, the result investigated from the second cycle likely indicated their higher level of critical thinking since the students spoke in English critically through comparing, questioning, analyzing, and evaluating the story by giving arguments, opinions, and comments. Such higher levels of critical thinking were also found in the students’ final project of individual recorded digital story. It is elaborated from the students’ statements in the interview who claimed CFDS offered opportunity to the students to promote their critical thinking because they comprehended the story deeply as they experienced in their real life. This learning model created good learning atmosphere and engaged the students directly so that they looked confident to retell the story in various perspectives. In term of the benefits of child-friendly digital storytelling, the students found it beneficial for some enjoyable classroom activities through watching beautiful and colorful pictures, listening to clear and good sounds, appealing moving motion and emotionally they were involved in that story. In the interview, the students also stated that child-friendly digital storytelling eased them to understand the meaning of the story as they were motivated and enthusiastic to speak in English critically.Keywords: critical thinking, child-friendly digital storytelling, English speaking, promoting, young learners
Procedia PDF Downloads 2774630 The Impact of Low-Systematization Level in Physical Education in Primary School
Authors: Wu Hong, Pan Cuilian, Wu Panzifan
Abstract:
The student’s attention during the class is one of the most important indicators for the learning evaluation; the level of attention is directly related to the results of primary education. In recent years, extensive research has been conducted across China on improving primary school students’ attention during class. During the specific teaching activities in primary school, students have the characteristics of short concentration periods, high probability of distraction, and difficulty in long-term immersive learning. In physical education teaching, where there are mostly outdoor activities, this characteristic is particularly prominent due to the large changes in the environment and the strong sense of freshness among students. It is imperative to overcome this characteristic in a targeted manner, improve the student’s experience in the course, and raise the degree of systematization. There are many ways to improve the systematization of teaching and learning, but most of them lack quantitative indicators, which makes it difficult to evaluate the improvements before and after changing the teaching methods. Based on the situation above, we use the case analysis method, combined with a literature review, to study the negative impact of low systematization levels in primary school physical education teaching, put forward targeted improvement suggestions, and make a quantitative evaluation of the method change.Keywords: attention, adolescent, evaluation, systematism, training-method
Procedia PDF Downloads 324629 Machine Learning-Based Techniques for Detecting and Mitigating Cyber-attacks on Automatic Generation Control in Smart Grids
Authors: Sami M. Alshareef
Abstract:
The rapid growth of smart grid technology has brought significant advancements to the power industry. However, with the increasing interconnectivity and reliance on information and communication technologies, smart grids have become vulnerable to cyber-attacks, posing significant threats to the reliable operation of power systems. Among the critical components of smart grids, the Automatic Generation Control (AGC) system plays a vital role in maintaining the balance between generation and load demand. Therefore, protecting the AGC system from cyber threats is of paramount importance to maintain grid stability and prevent disruptions. Traditional security measures often fall short in addressing sophisticated and evolving cyber threats, necessitating the exploration of innovative approaches. Machine learning, with its ability to analyze vast amounts of data and learn patterns, has emerged as a promising solution to enhance AGC system security. Therefore, this research proposal aims to address the challenges associated with detecting and mitigating cyber-attacks on AGC in smart grids by leveraging machine learning techniques on automatic generation control of two-area power systems. By utilizing historical data, the proposed system will learn the normal behavior patterns of AGC and identify deviations caused by cyber-attacks. Once an attack is detected, appropriate mitigation strategies will be employed to safeguard the AGC system. The outcomes of this research will provide power system operators and administrators with valuable insights into the vulnerabilities of AGC systems in smart grids and offer practical solutions to enhance their cyber resilience.Keywords: machine learning, cyber-attacks, automatic generation control, smart grid
Procedia PDF Downloads 774628 Bridging the Gap between Teaching and Learning: A 3-S (Strength, Stamina, Speed) Model for Medical Education
Authors: Mangala. Sadasivan, Mary Hughes, Bryan Kelly
Abstract:
Medical Education must focus on bridging the gap between teaching and learning when training pre-clinical year students in skills needed to keep up with medical knowledge and to meet the demands of health care in the future. The authors were interested in showing that a 3-S Model (building strength, developing stamina, and increasing speed) using a bridged curriculum design helps connect teaching and learning and improves students’ retention of basic science and clinical knowledge. The authors designed three learning modules using the 3-S Model within a systems course in a pre-clerkship medical curriculum. Each module focused on a bridge (concept map) designed by the instructor for specific content delivered to students in the course. This with-in-subjects design study included 304 registered MSU osteopathic medical students (3 campuses) ranked by quintile based on previous coursework. The instructors used the bridge to create self-directed learning exercises (building strength) to help students master basic science content. Students were video coached on how to complete assignments, and given pre-tests and post-tests designed to give them control to assess and identify gaps in learning and strengthen connections. The instructor who designed the modules also used video lectures to help students master clinical concepts and link them (building stamina) to previously learned material connected to the bridge. Boardstyle practice questions relevant to the modules were used to help students improve access (increasing speed) to stored content. Unit Examinations covering the content within modules and materials covered by other instructors teaching within the units served as outcome measures in this study. This data was then compared to each student’s performance on a final comprehensive exam and their COMLEX medical board examinations taken some time after the course. The authors used mean comparisons to evaluate students’ performances on module items (using 3-S Model) to non-module items on unit exams, final course exam and COMLEX medical board examination. The data shows that on average, students performed significantly better on module items compared to non-module items on exams 1 and 2. The module 3 exam was canceled due to a university shut down. The difference in mean scores (module verses non-module) items disappeared on the final comprehensive exam which was rescheduled once the university resumed session. Based on Quintile designation, the mean scores were higher for module items than non-module items and the difference in scores between items for Quintiles 1 and 2 were significantly better on exam 1 and the gap widened for all Quintile groups on exam 2 and disappeared in exam 3. Based on COMLEX performance, all students on average as a group, whether they Passed or Failed, performed better on Module items than non-module items in all three exams. The gap between scores of module items for students who passed COMLEX to those who failed was greater on Exam 1 (14.3) than on Exam 2 (7.5) and Exam 3 (10.2). Data shows the 3-S Model using a bridge effectively connects teaching and learningKeywords: bridging gap, medical education, teaching and learning, model of learning
Procedia PDF Downloads 524627 Decision-Making, Student Empathy, and Cold War Historical Events: A Case Study of Abstract Thinking through Content-Centered Learning
Authors: Jeffrey M. Byford
Abstract:
The conceptualized theory of decision making on historical events often does not conform to uniform beliefs among students. When presented the opportunity, many students have differing opinions and rationales associated with historical events and outcomes. The intent of this paper was to provide students with the economic, social and political dilemmas associated with the autonomy of East Berlin. Students ranked seven possible actions from the most to least acceptable. In addition, students were required to provide both positive and negative factors for each decision and relative ranking. Results from this activity suggested that while most students chose a financial action towards West Berlin, some students had trouble justifying their actions.Keywords: content-centered learning, cold war, Berlin, decision-making
Procedia PDF Downloads 4474626 Preliminary Results on a Maximum Mean Discrepancy Approach for Seizure Detection
Authors: Boumediene Hamzi, Turky N. AlOtaiby, Saleh AlShebeili, Arwa AlAnqary
Abstract:
We introduce a data-driven method for seizure detection drawing on recent progress in Machine Learning. The method is based on embedding probability measures in a high (or infinite) dimensional reproducing kernel Hilbert space (RKHS) where the Maximum Mean Discrepancy (MMD) is computed. The MMD is metric between probability measures that are computed as the difference between the means of probability measures after being embedded in an RKHS. Working in RKHS provides a convenient, general functional-analytical framework for theoretical understanding of data. We apply this approach to the problem of seizure detection.Keywords: kernel methods, maximum mean discrepancy, seizure detection, machine learning
Procedia PDF Downloads 2284625 A Service-Learning Experience in the Subject of Adult Nursing
Authors: Eva de Mingo-Fernández, Lourdes Rubio Rico, Carmen Ortega-Segura, Montserrat Querol-García, Raúl González-Jauregui
Abstract:
Today, one of the great challenges that the university faces is to get closer to society and transfer knowledge. The competency-based training approach favours a continuous interaction between practice and theory, which is why it is essential to establish real experiences with reflection and debate and to contrast them with personal and professional knowledge. Service-learning (SL) consists of an integration of academic learning with service in the community, which enables teachers to transfer knowledge with social value and students to be trained on the basis of experience of real needs and problems with the aim of solving them. SLE combines research, teaching, and social value knowledge transfer with the real social needs and problems of a community. Goal: The objective of this study was to design, implement, and evaluate a service-learning program in the subject of adult nursing for second-year nursing students. Methodology: After establishing collaboration with eight associations of people with different pathologies, the students were divided into eight groups, and each group was assigned an association. The groups were made up of 10-12 students. The associations willing to participate were for the following conditions: diabetes, multiple sclerosis, cancer, inflammatory bowel disease, fibromyalgia, heart, lung, and kidney diseases. The methodological design consisting of 5 activities was then applied. Three activities address personal and individual reflections, where the student initially describes what they think it is like to live with a certain disease. They then express their reflections resulting from an interview conducted by peers, in person or online, with a person living with this particular condition, and after sharing the results of their reflections with the rest of the group, they make an oral presentation in which they present their findings to the other students. This is followed by a service task in which the students collaborate in different activities of the association, and finally, a third individual reflection is carried out in which the students express their experience of collaboration. The evaluation of this activity is carried out by means of a rubric for both the reflections and the presentation. It should be noted that the oral presentation is evaluated both by the rest of the classmates and by the teachers. Results: The evaluation of the activity, given by the students, is 7.80/10, commenting that the experience is positive and brings them closer to the reality of the people and the area.Keywords: academic learning integration, knowledge transfer, service-learning, teaching methodology
Procedia PDF Downloads 584624 Neural Network-based Risk Detection for Dyslexia and Dysgraphia in Sinhala Language Speaking Children
Authors: Budhvin T. Withana, Sulochana Rupasinghe
Abstract:
The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science
Procedia PDF Downloads 894623 Managing Cognitive Load in Accounting: An Analysis of Three Instructional Designs in Financial Accounting
Authors: Seedwell Sithole
Abstract:
One of the persistent problems in accounting education is how to effectively support students’ learning. A promising technique to this issue is to investigate the extent that learning is determined by the design of instructional material. This study examines the academic performance of students using three instructional designs in financial accounting. Student’s performance scores and reported mental effort ratings were used to determine the instructional effectiveness. The findings of this study show that accounting students prefer graph and text designs that are integrated. The results suggest that spatially separated graph and text presentations in accounting should be reorganized to align with the requirements of human cognitive architecture.Keywords: accounting, cognitive load, education, instructional preferences, students
Procedia PDF Downloads 1364622 Benchmarking Machine Learning Approaches for Forecasting Hotel Revenue
Authors: Rachel Y. Zhang, Christopher K. Anderson
Abstract:
A critical aspect of revenue management is a firm’s ability to predict demand as a function of price. Historically hotels have used simple time series models (regression and/or pick-up based models) owing to the complexities of trying to build casual models of demands. Machine learning approaches are slowly attracting attention owing to their flexibility in modeling relationships. This study provides an overview of approaches to forecasting hospitality demand – focusing on the opportunities created by machine learning approaches, including K-Nearest-Neighbors, Support vector machine, Regression Tree, and Artificial Neural Network algorithms. The out-of-sample performances of above approaches to forecasting hotel demand are illustrated by using a proprietary sample of the market level (24 properties) transactional data for Las Vegas NV. Causal predictive models can be built and evaluated owing to the availability of market level (versus firm level) data. This research also compares and contrast model accuracy of firm-level models (i.e. predictive models for hotel A only using hotel A’s data) to models using market level data (prices, review scores, location, chain scale, etc… for all hotels within the market). The prospected models will be valuable for hotel revenue prediction given the basic characters of a hotel property or can be applied in performance evaluation for an existed hotel. The findings will unveil the features that play key roles in a hotel’s revenue performance, which would have considerable potential usefulness in both revenue prediction and evaluation.Keywords: hotel revenue, k-nearest-neighbors, machine learning, neural network, prediction model, regression tree, support vector machine
Procedia PDF Downloads 1224621 Exploring Problem-Based Learning and University-Industry Collaborations for Fostering Students’ Entrepreneurial Skills: A Qualitative Study in a German Urban Setting
Authors: Eylem Tas
Abstract:
This empirical study aims to explore the development of students' entrepreneurial skills through problem-based learning within the context of university-industry collaborations (UICs) in curriculum co-design and co-delivery (CDD). The research question guiding this study is: "How do problem-based learning and university-industry collaborations influence the development of students' entrepreneurial skills in the context of curriculum co-design and co-delivery?” To address this question, the study was conducted in a big city in Germany and involved interviews with stakeholders from various industries, including the private sector, government agencies (govt), and non-governmental organizations (NGOs). These stakeholders had established collaborative partnerships with the targeted university for projects encompassing entrepreneurial development aspects in CDD. The study sought to gain insights into the intricacies and subtleties of UIC dynamics and their impact on fostering entrepreneurial skills. Qualitative content analysis, based on Mayring's guidelines, was employed to analyze the interview transcriptions. Through an iterative process of manual coding, 442 codes were generated, resulting in two main sections: "the role of problem-based learning and UIC in fostering entrepreneurship" and "challenges and requirements of problem-based learning within UIC for systematical entrepreneurship development.” The chosen experimental approach of semi-structured interviews was justified by its capacity to provide in-depth perspectives and rich data from stakeholders with firsthand experience in UICs in CDD. By enlisting participants with diverse backgrounds, industries, and company sizes, the study ensured a comprehensive and heterogeneous sample, enhancing the credibility of the findings. The first section of the analysis delved into problem-based learning and entrepreneurial self-confidence to gain a deeper understanding of UIC dynamics from an industry standpoint. It explored factors influencing problem-based learning, alignment of students' learning styles and preferences with the experiential learning approach, specific activities and strategies, and the role of mentorship from industry professionals in fostering entrepreneurial self-confidence. The second section focused on various interactions within UICs, including communication, knowledge exchange, and collaboration. It identified key elements, patterns, and dynamics of interaction, highlighting challenges and limitations. Additionally, the section emphasized success stories and notable outcomes related to UICs' positive impact on students' entrepreneurial journeys. Overall, this research contributes valuable insights into the dynamics of UICs and their role in fostering students' entrepreneurial skills. UICs face challenges in communication and establishing a common language. Transparency, adaptability, and regular communication are vital for successful collaboration. Realistic expectation management and clearly defined frameworks are crucial. Responsible data handling requires data assurance and confidentiality agreements, emphasizing the importance of trust-based relationships when dealing with data sharing and handling issues. The identified key factors and challenges provide a foundation for universities and industrial partners to develop more effective UIC strategies for enhancing students' entrepreneurial capabilities and preparing them for success in today's digital age labor market. The study underscores the significance of collaborative learning and transparent communication in UICs for entrepreneurial development in CDD.Keywords: collaborative learning, curriculum co-design and co-delivery, entrepreneurial skills, problem-based learning, university-industry collaborations
Procedia PDF Downloads 524620 Using Indigenous Games to Demystify Probability Theorem in Ghanaian Classrooms: Mathematical Analysis of Ampe
Authors: Peter Akayuure, Michael Johnson Nabie
Abstract:
Similar to many colonized nations in the world, one indelible mark left by colonial masters after Ghana’s independence in 1957 has been the fact that many contexts used to teach statistics and probability concepts are often alien and do not resonate with the social domain of our indigenous Ghanaian child. This has seriously limited the understanding, discoveries, and applications of mathematics for national developments. With the recent curriculum demands of making the Ghanaian child mathematically literate, this qualitative study involved video recordings and mathematical analysis of play sessions of an indigenous girl game called Ampe with the aim to demystify the concepts in probability theorem, which is applied in mathematics related fields of study. The mathematical analysis shows that the game of Ampe, which is widely played by school girls in Ghana, is suitable for learning concepts of the probability theorems. It was also revealed that as a girl game, the use of Ampe provides good lessons to educators, textbook writers, and teachers to rethink about the selection of mathematics tasks and learning contexts that are sensitive to gender. As we undertake to transform teacher education and student learning, the use of indigenous games should be critically revisited.Keywords: Ampe, mathematical analysis, probability theorem, Ghanaian girl game
Procedia PDF Downloads 3594619 Non-Targeted Adversarial Image Classification Attack-Region Modification Methods
Authors: Bandar Alahmadi, Lethia Jackson
Abstract:
Machine Learning model is used today in many real-life applications. The safety and security of such model is important, so the results of the model are as accurate as possible. One challenge of machine learning model security is the adversarial examples attack. Adversarial examples are designed by the attacker to cause the machine learning model to misclassify the input. We propose a method to generate adversarial examples to attack image classifiers. We are modifying the successfully classified images, so a classifier misclassifies them after the modification. In our method, we do not update the whole image, but instead we detect the important region, modify it, place it back to the original image, and then run it through a classifier. The algorithm modifies the detected region using two methods. First, it will add abstract image matrix on back of the detected image matrix. Then, it will perform a rotation attack to rotate the detected region around its axes, and embed the trace of image in image background. Finally, the attacked region is placed in its original position, from where it was removed, and a smoothing filter is applied to smooth the background with foreground. We test our method in cascade classifier, and the algorithm is efficient, the classifier confident has dropped to almost zero. We also try it in CNN (Convolutional neural network) with higher setting and the algorithm was successfully worked.Keywords: adversarial examples, attack, computer vision, image processing
Procedia PDF Downloads 3294618 Computational Model of Human Cardiopulmonary System
Authors: Julian Thrash, Douglas Folk, Michael Ciracy, Audrey C. Tseng, Kristen M. Stromsodt, Amber Younggren, Christopher Maciolek
Abstract:
The cardiopulmonary system is comprised of the heart, lungs, and many dynamic feedback mechanisms that control its function based on a multitude of variables. The next generation of cardiopulmonary medical devices will involve adaptive control and smart pacing techniques. However, testing these smart devices on living systems may be unethical and exceedingly expensive. As a solution, a comprehensive computational model of the cardiopulmonary system was implemented in Simulink. The model contains over 240 state variables and over 100 equations previously described in a series of published articles. Simulink was chosen because of its ease of introducing machine learning elements. Initial results indicate that physiologically correct waveforms of pressures and volumes were obtained in the simulation. With the development of a comprehensive computational model, we hope to pioneer the future of predictive medicine by applying our research towards the initial stages of smart devices. After validation, we will introduce and train reinforcement learning agents using the cardiopulmonary model to assist in adaptive control system design. With our cardiopulmonary model, we will accelerate the design and testing of smart and adaptive medical devices to better serve those with cardiovascular disease.Keywords: adaptive control, cardiopulmonary, computational model, machine learning, predictive medicine
Procedia PDF Downloads 1624617 An Improved Convolution Deep Learning Model for Predicting Trip Mode Scheduling
Authors: Amin Nezarat, Naeime Seifadini
Abstract:
Trip mode selection is a behavioral characteristic of passengers with immense importance for travel demand analysis, transportation planning, and traffic management. Identification of trip mode distribution will allow transportation authorities to adopt appropriate strategies to reduce travel time, traffic and air pollution. The majority of existing trip mode inference models operate based on human selected features and traditional machine learning algorithms. However, human selected features are sensitive to changes in traffic and environmental conditions and susceptible to personal biases, which can make them inefficient. One way to overcome these problems is to use neural networks capable of extracting high-level features from raw input. In this study, the convolutional neural network (CNN) architecture is used to predict the trip mode distribution based on raw GPS trajectory data. The key innovation of this paper is the design of the layout of the input layer of CNN as well as normalization operation, in a way that is not only compatible with the CNN architecture but can also represent the fundamental features of motion including speed, acceleration, jerk, and Bearing rate. The highest prediction accuracy achieved with the proposed configuration for the convolutional neural network with batch normalization is 85.26%.Keywords: predicting, deep learning, neural network, urban trip
Procedia PDF Downloads 125