Search results for: Hebbian learning

Authors: Sarita Agarwal, Deepika Delsa Dean

Abstract:

Like the task of transferring photo images to artistic images, image-to-image translation aims to translate the data to the imitated data which belongs to the target domain. Neural Style Transfer and CycleGAN are two well-known deep learning architectures used for photo image-to-art image transfer. However, studies involving these two models concentrate on one-to-one domain translation, not one-to-multi domains translation. Our study tries to investigate deep learning architectures, which can be controlled to yield multiple artistic style translation only by adding a conditional vector. We have expanded CycleGAN and constructed Conditional CycleGAN for 5 kinds of categories translation. Our study found that the architecture inserting conditional vector into the middle layer of the Generator could output multiple artistic images.

Keywords: genetic counseling, FMR1 gene, fragile x-associated primary ovarian insufficiency, premutation

Procedia PDF Downloads 130

Authors: Rima Al-Awadhi, Abdul Jaleel Tharayil

Abstract:

On a regular basis, KOC engages into various types of Projects. However, due to very nature and complexity involved, each project experience generates a lot of ‘learnings’ that need to be factored into while drafting a new contract and thus avoid repeating the same mistakes. But, many a time these learnings are localized and remain as tacit leading to scope re-work, larger cycle time, schedule overrun, adjustment orders and claims. Also, these experiences are not readily available to new employees leading to steep learning curve and longer time to competency. This is to share our experience in designing and implementing a process driven architecture for the ‘lessons learnt’ knowledge sharing framework in KOC. It high-lights the ‘lessons learnt’ sharing process adopted, integration with the organizational processes, governance framework, the challenges faced and learning from our experience in implementing a ‘lessons learnt’ framework.

Keywords: lessons learnt, knowledge transfer, knowledge sharing, successful practices, Lessons Learnt Workshop, governance framework

Procedia PDF Downloads 577

Authors: Anna Sanczyk

Abstract:

Teacher agency plays a crucial role in effective teaching, supporting diverse students, and providing an enriching learning environment; therefore, it is significant to gain a deeper understanding of language teachers’ sense of agency in teaching linguistically and culturally diverse students. This paper presents an overview of qualitative research on how language teachers exercise their agency in diverse classrooms. The analysis of the literature reveals that language teachers strive for addressing students’ needs and challenging educational inequalities, but experience educational constraints in enacting their agency. The examination of the research on language teacher agency identifies four major areas where language teachers experience challenges in enacting their agency: (1) implementing curriculum; (2) adopting school reforms and policies; (3) engaging in professional learning; (4) and negotiating various identities as professionals. The practical contribution of this literature review is that it provides a much-needed compilation of the studies on how language teachers exercise agency amid educational constraints. The discussion of the overview points to the importance of teacher identity, learner advocacy, and continuous professional learning and the critical need of promoting empowerment, activism, and transformation in language teacher education. The findings of the overview indicate that language teacher education programs should prepare teachers to be active advocates for English language learners and guide teachers to become more conscious of complexities of teaching in constrained educational settings so that they can become agentic professionals. This literature overview illustrates agency work in English language teaching contexts and contributes to understanding of the important link between experiencing educational constraints and development of teacher agency.

Keywords: advocacy, educational constraints, language teacher agency, language teacher education

Procedia PDF Downloads 177

Authors: Abhigyan Hedau, Priya Shelke, Riddhi Mirajkar, Shreyash Chaple, Mrunali Gadekar, Himanshu Akula

Abstract:

The heart is the coordinating centre of the major endocrine glandular structure of the body, which produces hormones that profoundly affect the operations of the body, and diagnosing cardiovascular disease is a difficult but critical task. By extracting knowledge and information about the disease from patient data, data mining is a more practical technique to help doctors detect disorders. We use a variety of machine learning methods here, including logistic regression and support vector classifiers (SVC), K-nearest neighbours Classifiers (KNN), Decision Tree Classifiers, Random Forest classifiers and Gradient Boosting classifiers. These algorithms are applied to patient data containing 13 different factors to build a system that predicts heart disease in less time with more accuracy.

Keywords: logistic regression, support vector classifier, k-nearest neighbour, decision tree, random forest and gradient boosting

Procedia PDF Downloads 50

Authors: Harun Bozna

Abstract:

MOOC (massive open online course) is a groundbreaking education platform and a current buzzword in higher education. Although MOOCs offer many appreciated learning experiences to learners from various universities and institutions, they have considerably higher dropout rates than traditional education. Only about 10% of the learners who enroll in MOOCs actually complete the course. In this case, perceptions of participants and a comprehensive analysis of MOOCs have become an essential part of the research in this area. This study aims to explore the MOOCs in detail for better understanding its content, purpose and primarily drop out issues. The researcher conducted an online questionnaire to get perceptions of graduate students on their learning experiences in MOOCs and arranged a semi- structured oral interview with some participants. The participants are Turkish graduate level students doing their MA and Ph.D. in various programs. The findings show that participants are more likely to drop out courses due to lack of time and lack of pressure.

Keywords: distance education, MOOCs, drop out, perception of graduate students

Procedia PDF Downloads 240

Authors: Min Chen, Rubi Gupta

Abstract:

Understanding and predicting stock market movements is a challenging problem. It is believed stock markets are partially driven by public sentiments, which leads to numerous research efforts to predict stock market trend using public sentiments expressed on social media such as Twitter but with limited success. Recently a microblogging website StockTwits is becoming increasingly popular for users to share their discussions and sentiments about stocks and financial market. In this project, we analyze the text content of StockTwits tweets and extract financial sentiment using text featurization and machine learning algorithms. StockTwits tweets are first pre-processed using techniques including stopword removal, special character removal, and case normalization to remove noise. Features are extracted from these preprocessed tweets through text featurization process using bags of words, N-gram models, TF-IDF (term frequency-inverse document frequency), and latent semantic analysis. Machine learning models are then trained to classify the tweets' sentiment as positive (bullish) or negative (bearish). The correlation between the aggregated daily sentiment and daily stock price movement is then investigated using Pearson’s correlation coefficient. Finally, the sentiment information is applied together with time series stock data to predict stock price movement. The experiments on five companies (Apple, Amazon, General Electric, Microsoft, and Target) in a duration of nine months demonstrate the effectiveness of our study in improving the prediction accuracy.

Keywords: machine learning, sentiment analysis, stock price prediction, tweet processing

Procedia PDF Downloads 156

Authors: Ursula Das, Manavjit Singh Dhindsa, Kshirasagar Naik, Marzia Zaman, Richard Purcell, Srinivas Sampalli, Abdul Mutakabbir, Chung-Horng Lung, Thambirajah Ravichandran

Abstract:

Wildland fires, also known as forest fires or wildfires, are exhibiting an alarming surge in frequency in recent times, further adding to its perennial global concern. Forest fires often lead to devastating consequences ranging from loss of healthy forest foliage and wildlife to substantial economic losses and the tragic loss of human lives. Despite the existence of substantial literature on the detection of active forest fires, numerous potential research avenues in forest fire management, such as preventative measures and ancillary effects of forest fires, remain largely underexplored. This paper undertakes a systematic review of these underexplored areas in forest fire research, meticulously categorizing them into distinct phases, namely pre-fire, during-fire, and post-fire stages. The pre-fire phase encompasses the assessment of fire risk, analysis of fuel properties, and other activities aimed at preventing or reducing the risk of forest fires. The during-fire phase includes activities aimed at reducing the impact of active forest fires, such as the detection and localization of active fires, optimization of wildfire suppression methods, and prediction of the behavior of active fires. The post-fire phase involves analyzing the impact of forest fires on various aspects, such as the extent of damage in forest areas, post-fire regeneration of forests, impact on wildlife, economic losses, and health impacts from byproducts produced during burning. A comprehensive understanding of the three stages is imperative for effective forest fire management and mitigation of the impact of forest fires on both ecological systems and human well-being. Artificial intelligence and machine learning (AI/ML) methods have garnered much attention in the cyber-physical systems domain in recent times leading to their adoption in decision-making in diverse applications including disaster management. This paper explores the current state of AI/ML applications for managing the activities in the aforementioned phases of forest fire. While conventional machine learning and deep learning methods have been extensively explored for the prevention, detection, and management of forest fires, a systematic classification of these methods into distinct AI research domains is conspicuously absent. This paper gives a comprehensive overview of the state of forest fire research across more recent and prominent AI/ML disciplines, including big data, classical machine learning, computer vision, explainable AI, generative AI, natural language processing, optimization algorithms, and time series forecasting. By providing a detailed overview of the potential areas of research and identifying the diverse ways AI/ML can be employed in forest fire research, this paper aims to serve as a roadmap for future investigations in this domain.

Keywords: artificial intelligence, computer vision, deep learning, during-fire activities, forest fire management, machine learning, pre-fire activities, post-fire activities

Procedia PDF Downloads 72

Authors: Tolulope Aremu

Abstract:

The key process steps to produce liquid detergent products will introduce potential defects, such as formulation, mixing, filling, and packaging, which might compromise product quality, consumer safety, and operational efficiency. Real-time identification and characterization of such defects are of prime importance for maintaining high standards and reducing waste and costs. Usually, defect detection is performed by human inspection or rule-based systems, which is very time-consuming, inconsistent, and error-prone. The present study overcomes these limitations in dealing with optimization in defect characterization within the process for making liquid detergents using Machine Learning algorithms. Performance testing of various machine learning models was carried out: Support Vector Machine, Decision Trees, Random Forest, and Convolutional Neural Network on defect detection and classification of those defects like wrong viscosity, color deviations, improper filling of a bottle, packaging anomalies. These algorithms have significantly benefited from a variety of optimization techniques, including hyperparameter tuning and ensemble learning, in order to greatly improve detection accuracy while minimizing false positives. Equipped with a rich dataset of defect types and production parameters consisting of more than 100,000 samples, our study further includes information from real-time sensor data, imaging technologies, and historic production records. The results are that optimized machine learning models significantly improve defect detection compared to traditional methods. Take, for instance, the CNNs, which run at 98% and 96% accuracy in detecting packaging anomaly detection and bottle filling inconsistency, respectively, by fine-tuning the model with real-time imaging data, through which there was a reduction in false positives of about 30%. The optimized SVM model on detecting formulation defects gave 94% in viscosity variation detection and color variation. These values of performance metrics correspond to a giant leap in defect detection accuracy compared to the usual 80% level achieved up to now by rule-based systems. Moreover, this optimization with models can hasten defect characterization, allowing for detection time to be below 15 seconds from an average of 3 minutes using manual inspections with real-time processing of data. With this, the reduction in time will be combined with a 25% reduction in production downtime because of proactive defect identification, which can save millions annually in recall and rework costs. Integrating real-time machine learning-driven monitoring drives predictive maintenance and corrective measures for a 20% improvement in overall production efficiency. Therefore, the optimization of machine learning algorithms in defect characterization optimum scalability and efficiency for liquid detergent companies gives improved operational performance to higher levels of product quality. In general, this method could be conducted in several industries within the Fast moving consumer Goods industry, which would lead to an improved quality control process.

Keywords: liquid detergent manufacturing, defect detection, machine learning, support vector machines, convolutional neural networks, defect characterization, predictive maintenance, quality control, fast-moving consumer goods

Procedia PDF Downloads 18

Authors: Paul Nadasdy

Abstract:

In 2020, oral communication classes at many universities in Japan switched to online and hybrid lessons because of the coronavirus pandemic. Teachers had to adapt their practices immediately and deal with the challenges of the online environment. Even for experienced teachers, this still presented a problem as many had not conducted online classes before. Simultaneously, for many students, this type of learning was completely alien to them, and they had to adapt to the challenges faced by communicating in English online. This study collected data from 418 first grade students in the first semester of English communication classes at a technical university in Tokyo, Japan. Zoom software was used throughout the learning period. Though there were many challenges in the setting up and implementation of Zoom classes at the university, the results indicated that the students enjoyed the format and made the most of the circumstances. This proved the robustness of the course that was taught in regular lessons and the adaptability of teachers and students to challenges in a very short timeframe.

Keywords: zoom, hybrid lessons, communicative english, online teaching

Procedia PDF Downloads 84

Authors: Bernard Morais Joosa

Abstract:

Kerala, the southern state of India, is known for its accomplishments in universal education and enrollments. Through this mission, the Government proposes comprehensive educational reforms including 1000 Government schools into international standards during the first phase. The idea is not only to improve the infrastructural facilities but also to reform the teaching and learning process to the present day needs by introducing ICT enabled learning and providing smart classrooms. There will be focus on creating educational programmes which are useful for differently abled students. It is also meant to reinforce the teaching–learning process by providing ample opportunities to each student to construct their own knowledge using modern technology tools. The mission will redefine the existing classroom learning process, coordinate resource mobilization efforts and develop ‘Janakeeya Vidyabhyasa Mathruka.' Special packages to support schools which are in existence for over 100 years will also be attempted. The implementation will enlist full involvement and partnership of the Parent Teacher Association. Kerala was the first state in the country to attain 100 percent literacy more than two and a half decades ago. Since then the State has not rested on its laurels. It has moved forward in leaps and bounds conquering targets that no other State could achieve. Now the government of Kerala is taking off towards new goal of comprehensive educational reforms. And it focuses on Betterment of educational surroundings, use of technology in education, renewal of learning method and 1000 schools will be uplifted as Smart Schools. Need to upgrade 1000 schools into international standards and turning classrooms from standard 9 to 12 in high schools and higher secondary into high-tech classrooms and a special unique package for the renovation of schools, which have completed 50 and 100 years. The government intends to focus on developing standards first to eighth standards in tune with the times by engaging the teachers, parents, and alumni to recapture the relevance of public schools. English learning will be encouraged in schools. The idea is not only to improve the infrastructure facilities but also reform the curriculum to the present day needs. Keeping in view the differently-abled friendly approach of the government, there will be focus on creating educational program which is useful for differently abled students. The idea is to address the infrastructural deficiencies being faced by such schools. There will be special emphasis on ensuring internet connectivity to promote IT-friendly existence. A task-force and a full-time chief executive will be in charge of managing the day to day affairs of the mission. Secretary of the Public Education Department will serve as the Mission Secretary and the Chairperson of Task Force. As the Task Force will stress on teacher training and the use of information technology, experts in the field, as well as Directors of SCERT, IT School, SSA, and RMSA, will also be a part of it.

Keywords: educational standards, methodology, pedagogy, technology

Procedia PDF Downloads 133

Authors: Brogan Guest, Amy Donaldson-Perrott

Abstract:

The Master’s of Physician Associate Studies (MPAS) programme at St George’s, University of London (SGUL), is an intensive two-year course that trains students to become physician associates (PAs). PAs are generalized healthcare providers who work in primary and secondary care across the UK. PA programmes face the difficult task of preparing students to become safe medical providers in two short years. Our goal is to teach students to develop clinical reasoning early on in their studies and historically, this has been done predominantly though problem-based learning (PBL). We have had an increase concern about student engagement in PBL and difficulty recruiting facilitators to maintain the low student to facilitator ratio required in PBL. To address this issue, we created ‘Clinical Application of Anatomy and Physiology (CAAP)’. These peer-led, interactive, problem-based, small group sessions were designed to facilitate students’ clinical reasoning skills. The sessions were designed using the concept of Team-Based Learning (TBL). Students were divided into small groups and each completed a pre-session quiz consisting of difficult questions devised to assess students’ application of medical knowledge. The quiz was completed in small groups and they were not permitted access of external resources. After the quiz, students worked through a series of openended, clinical tasks using all available resources. They worked at their own pace and the session was peer-led, rather than facilitator-driven. For a group of 35 students, there were two facilitators who observed the sessions. The sessions utilised an infinite space whiteboard software. Each group member was encouraged to actively participate and work together to complete the 15-20 tasks. The session ran for 2 hours and concluded with a post-session quiz, identical to the pre-session quiz. We obtained subjective feedback from students on their experience with CAAP and evaluated the objective benefit of the sessions through the quiz results. Qualitative feedback from students was generally positive with students feeling the sessions increased engagement, clinical understanding, and confidence. They found the small group aspect beneficial and the technology easy to use and intuitive. They also liked the benefit of building a resource for their future revision, something unique to CAAP compared to PBL, which out students participate in weekly. Preliminary quiz results showed improvement from pre- and post- session; however, further statistical analysis will occur once all sessions are complete (final session to run December 2022) to determine significance. As a post-graduate healthcare professional programme, we have a strong focus on self-directed learning. Whilst PBL has been a mainstay in our curriculum since its inception, there are limitations and concerns about its future in view of student engagement and facilitator availability. Whilst CAAP is not TBL, it draws on the benefits of peer-led, small group work with pre- and post- team-based quizzes. The pilot of these sessions has shown that students are engaged by CAAP, and they can make significant progress in clinical reasoning in a short amount of time. This can be achieved with a high student to facilitator ratio.

Keywords: problem based learning, team based learning, active learning, peer-to-peer teaching, engagement

Procedia PDF Downloads 80

Authors: Wang Jiankun

Abstract:

This paper analyses how different educational backgrounds affect the mathematics performance of middle and high school students in terms of three dimensions: parental involvement, school teaching ability, and demographic variables and personal attributes of the student. Based on the analysis of Beijing High School Mathematics Competition in 2022, it was found that students from high level schools won significantly more awards than those from low level schools. In addition, a significant positive correlation (p<0.05) was identified between school level and students' mathematics performance. This study also confirms that parents' education level and family environment show a significant impact on the next generation’s mathematics learning performance. The findings suggest that interest and student’s habits, the family environment and the quality of teaching and learning at school are the main factors affecting the mathematics performance of middle and high school students.

Keywords: educational background, academic performance, middle and high school education, teenager

Procedia PDF Downloads 82

Authors: Akella Amarendra Babu, Rama Devi Yellasiri, Natukula Sainath

Abstract:

Where human beings can easily learn and adopt pronunciation variations, machines need training before put into use. Also humans keep minimum vocabulary and their pronunciation variations are stored in front-end of their memory for ready reference, while machines keep the entire pronunciation dictionary for ready reference. Supervised methods are used for preparation of pronunciation dictionaries which take large amounts of manual effort, cost, time and are not suitable for real time use. This paper presents an unsupervised adaptation model for building agile and dynamic pronunciation dictionaries online. These methods mimic human approach in learning the new pronunciations in real time. A new algorithm for measuring sound distances called Dynamic Phone Warping is presented and tested. Performance of the system is measured using an adaptation model and the precision metrics is found to be better than 86 percent.

Keywords: pronunciation variations, dynamic programming, machine learning, natural language processing

Procedia PDF Downloads 175

Authors: Ahmad Rouhani, Masood Jabbari, Sima Honarmand

Abstract:

This paper introduces a method to optimal design of a hybrid Wind/Photovoltaic/Fuel cell generation system for a typical domestic load that is not located near the electricity grid. In this configuration the combination of a battery, an electrolyser, and a hydrogen storage tank are used as the energy storage system. The aim of this design is minimization of overall cost of generation scheme over 20 years of operation. The Matlab/Simulink is applied for choosing the appropriate structure and the optimization of system sizing. A teaching learning based optimization is used to optimize the cost function. An overall power management strategy is designed for the proposed system to manage power flows among the different energy sources and the storage unit in the system. The results have been analyzed in terms of technics and economics. The simulation results indicate that the proposed hybrid system would be a feasible solution for stand-alone applications at remote locations.

Keywords: hybrid energy system, optimum sizing, power management, TLBO

Procedia PDF Downloads 578

Authors: George Kurian, Hongmei Chi

Abstract:

Digital evidence plays a critical role in most legal investigations. In many cases, thumbnail databases show important information in that investigation. The probability of having digital evidence retrieved from a computer or smart device has increased, even though the previous user removed data and deleted apps on those devices. Due to the increase in digital forensics, the ability to store residual information from various thumbnail applications has improved. This paper will focus on investigating thumbnail information from Windows 10. Thumbnail images of interest in forensic investigations may be intact even when the original pictures have been deleted. It is our research goal to recover useful information from thumbnails. In this research project, we use various forensics tools to collect left thumbnail information from deleted videos or pictures. We examine and describe the various thumbnail sources in Windows and propose a methodology for thumbnail collection and analysis from laptops or desktops. A machine learning algorithm is adopted to help speed up content from thumbnail pictures.

Keywords: digital forensic, forensic tools, soundness, thumbnail, machine learning, OCR

Procedia PDF Downloads 132

Authors: Arun Prasad Jaganathan

Abstract:

In today's dynamic industrial world, traditional task allocation methods often fall short in adapting to evolving operational conditions. This paper introduces an AI-enabled task assistance and management system designed to overcome the limitations of conventional approaches. By using artificial intelligence (AI) and machine learning (ML), the system intelligently interprets user instructions, analyzes tasks, and allocates resources based on real-time data and environmental factors. Additionally, geolocation tracking enables proactive identification of potential delays, ensuring timely interventions. With its transparent reporting mechanisms, the system provides stakeholders with clear insights into task progress, fostering accountability and informed decision-making. The paper presents a comprehensive overview of the system architecture, algorithm, and implementation, highlighting its potential to revolutionize task management across diverse industries.

Keywords: artificial intelligence, machine learning, task allocation, operational efficiency, resource optimization

Procedia PDF Downloads 59

Authors: Bernardita Tornero

Abstract:

Cognitive Acceleration in Mathematics Education (CAME) programmes have been used successfully for promoting the development of thinking skills in school students for the last 30 years. Given that the approach has had a tremendous impact on the thinking capabilities of participating students, this study explored the experience of using the programme with prospective primary teachers in Chile. Therefore, this study not only looked at the experience of prospective primary teachers during the CAME course as learners, but also examined how they perceived the approach from their perspective as future teachers, as well as how they could transfer the teaching strategies they observed to their future classrooms. Given the complexity of the phenomenon under study, this research used a mixed methods approach. For this reason, the impact that the CAME course had on prospective teachers’ thinking skills was not only approached by using a test that assessed the participants’ improvements in these skills, but their learning and teaching experiences were also recorded through qualitative research tools (learning journals, interviews and field notes). The main findings indicate that, at the end of the CAME course, prospective teachers not only demonstrated higher thinking levels, but also showed positive attitudinal changes towards teaching and learning in general, and towards mathematics in particular. The participants also had increased confidence in their ability to teach mathematics and to promote thinking skills in their students. In terms of the CAME methodology, prospective teachers not only found it novel and motivating, but also commented that dealing with the thinking skills topic during a university course was both unusual and very important for their professional development. This study also showed that, at the end of the CAME course, prospective teachers felt they had developed strategies that could be used in their classrooms in the future. In this context, the relevance of the study is not only that it described the impact and the positive results of the first experience of using a CAME approach with prospective teachers, but also that some of the conclusions have significant implications for the teaching of thinking skills and the training of primary school teachers.

Keywords: cognitive acceleration, formal reasoning, prospective teachers, initial teacher training

Procedia PDF Downloads 403

Authors: Mohammed A. M. Ibrahim

Abstract:

This paper investigate the utilization of wire and wireless networks to be platform for distributed educational monitoring system. Universities in developing countries suffer from a lot of shortages(staff, equipment, and finical budget) and optimal utilization of the wire and wireless network, so universities can mitigate some of the mentioned problems and avoid the problems that maybe humble the education processes in many universities by using our implementation of the examinations system as a test-bed to utilize the network as a solution to the shortages for academic staff in Taiz University. This paper selects a two areas first one quizzes activities is only a test bed application for wireless network learning environment system to be distributed among students. Second area is the features and the security of wireless, our tested application implemented in a promising area which is the use of WLAN in higher education for leering environment.

Keywords: networking wire and wireless technology, wireless network security, distributed computing, algorithm, encryption and decryption

Procedia PDF Downloads 337

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 266

Authors: Peter Williams

Abstract:

Mobile digital technology, in the form of smart phones, tablets, laptops and their accompanying functionality/apps etc., is becoming ever more used by people with Learning Disabilities (LD) - for entertainment, to communicate and socialize, and enjoy self-expression. Despite this, there has been very little research into the experiences of such technology by this cohort, it’s role in articulating personal identity and self-advocacy and the barriers encountered in negotiating technology in everyday life. The proposed talk describes research funded by the British Academy addressing these issues. It aims to explore: i) the experiences of people with LD in using mobile technology in their everyday lives – the benefits, in terms of entertainment, self-expression and socialising, and possible greater autonomy; and the barriers, such as accessibility or usability issues, privacy or vulnerability concerns etc. ii) how the technology, and in particular the software/apps and interfaces, can be improved to enable the greater access to entertainment, information, communication and other benefits it can offer. It is also hoped that results will inform parents, carers and other supporters regarding how they can use the technology with their charges. Rather than the project simply following the standard research procedure of gathering and analysing ‘data’ to which individual ‘research subjects’ have no access, people with Learning Disabilities (and their supporters) will help co-produce an accessible, annotated and hyperlinked living e-archive of their experiences. Involving people with LD as informants, contributors and, in effect, co-researchers will facilitate digital inclusion and empowerment. The project is working with approximately 80 adults of all ages who have ‘mild’ learning disabilities (people who are able to read basic texts and write simple sentences). A variety of methods is being used. Small groups of participants have engaged in simple discussions or storytelling about some aspect of technology (such as ‘when my phone saved me’ or ‘my digital photos’ etc.). Some individuals have been ‘interviewed’ at a PC, laptop or with a mobile device etc., and asked to demonstrate their usage and interests. Social media users have shown their Facebook pages, Pinterest uploads or other material – giving them an additional focus they have used to discuss their ‘digital’ lives. During these sessions, participants have recorded (or employed the researcher to record) their observations on to the e-archive. Parents, carers and other supporters are also being interviewed to explore their experiences of using mobile technology with the cohort, including any difficulties they have observed their charges having. The archive is supplemented with these observations. The presentation will outline the methods described above, highlighting some of the special considerations required when working inclusively with people with LD. It will describe some of the preliminary findings and demonstrate the e-archive with a commentary on the pages shown.

Keywords: inclusive research, learning disabilities, methods, technology

Procedia PDF Downloads 224

Authors: John Lloyd Angolluan, Jennile Caday, Crystal Mae Estrella, Reike Alliyah Taladua, Zion Michael Ysulat

Abstract:

One of the requirements of having the ability to communicate in English is by having adequate vocabulary. Nowadays, people are more engaged in watching movie streams on which they can watch movies in a very portable way, such as Netflix. Wherein Netflix became global demand for online media has taken off in recent years. This research aims to know whether the use of bimodal subtitles on Netflix English movies can enhance vocabulary. This study is quantitative and utilizes a descriptive method, and this study aims to explore the use of bimodal subtitles on Netflix English movies to enhance the vocabulary of students. The respondents of the study were the selected Second-year English majors of Rizal Technological University Pasig and Boni Campus using the purposive sampling technique. The researcher conducted a survey questionnaire through the use of Google Forms. In this study, the weighted mean was used to evaluate the student's responses to the statement of the problems of the study of the use of bimodal subtitles on Netflix English movies. The findings of this study revealed that the bimodal subtitle on Netflix English movies enhanced students’ vocabulary learning acquisition by providing learners with access to large amounts of real and comprehensible language input, whether accidentally or intentionally, and it turns out that bimodal subtitles on Netflix English movies help students recognize vocabulary, which has a positive impact on their vocabulary building. Therefore, the researchers advocate that watching English Netflix movies enhances students' vocabulary by using bimodal subtitled movie material during their language learning process, which may increase their motivation and the usage of bimodal subtitles in learning new vocabulary. Bimodal subtitles need to be incorporated into educational film activities to provide students with a vast amount of input to expand their vocabulary.

Keywords: bimodal subtitles, Netflix, English movies, vocabulary, subtitle, language, media

Procedia PDF Downloads 85

Authors: Yun-Husan Huang

Abstract:

Many English for Specific Purposes (ESP) textbooks are distributed globally as the content development is often obliged to compromises between commercial and pedagogical demands. Therefore, the issue of regional application and usefulness of globally published ESP textbooks has received much debate. For ESP instructors, textbook selection is definitely a priority consideration for curriculum design. An appropriate ESP textbook can facilitate teaching and learning, while an inappropriate one may cause a disaster for both teachers and students. This study aims to investigate the regional application and usefulness of an ESP textbook for information technology (IT). Participants were 51 sophomores majoring in Applied Informatics and Multimedia at a university in Taiwan. As they were non-English majors, their English proficiency was mostly at elementary and elementary-to-intermediate levels. This course was offered for two semesters. The textbook selected was Oxford English for Information Technology. At class end, the students were required to complete a survey comprising five choices of Very Easy, Easy, Neutral, Difficult, and Very Difficult for each item. Based on the content design of the textbook, the survey investigated how the students viewed the difficulty of grammar, listening, speaking, reading, and writing materials of the textbook. In terms of difficulty, results reveal that only 22% of them found the grammar section difficult and very difficult. For listening, 71% responded difficult and very difficult. For general reading, 55% responded difficult and very difficult. For speaking, 56% responded difficult and very difficult. For writing, 78% responded difficult and very difficult. For advanced reading, 90% reported difficult and very difficult. These results indicate that, except the grammar section, more than half of the students found the textbook contents difficult in terms of listening, speaking, reading, and writing materials. Such contradictory results between the easy grammar section and the difficult four language skills sections imply that the textbook designers do not well understand the English learning background of regional ESP learners. For the participants, the learning contents of the grammar section were the general grammar level of junior high school, while the learning contents of the four language skills sections were more of the levels of college English majors. Implications from the findings are obtained for instructors and textbook designers. First of all, existing ESP textbooks for IT are few and thus textbook selections for instructors are insufficient. Second, existing globally published textbooks for IT cannot be applied to learners of all English proficiency levels, especially the low level. With limited textbook selections, third, instructors should modify the selected textbook contents or supplement extra ESP materials to meet the proficiency level of target learners. Fourth, local ESP publishers should collaborate with local ESP instructors who understand best the learning background of their students in order to develop appropriate ESP textbooks for local learners. Even though the instructor reduced learning contents and simplified tests in curriculum design, in conclusion, the students still found difficult. This implies that in addition to the instructor’s professional experience, there is a need to understand the usefulness of the textbook from learner perspectives.

Keywords: ESP textbooks, ESP materials, ESP textbook design, learner perspectives on ESP textbooks

Procedia PDF Downloads 339

Authors: Qi Wang

Abstract:

In the classroom, teachers have been trained to complete the target task within the limited lecture time, meanwhile learners need to receive a lot of new knowledge, however, most of the time the learners come without the proper pre-class preparation to efficiently take in the contents taught in class. Under this circumstance, teachers do have no time to check whether the learners fully understand the content or not, how the learners communicate in the different contexts, until teachers see the results when the learners are tested. In the past decade, the teaching of Chinese has taken a trend. Teaching focuses less on the use of proper grammatical terms/punctuation and is now placing a heavier focus on the materials from real life contexts. As a result, it has become a greater challenge to teachers, as this requires teachers to fully understand/prepare what they teach and explain the content with simple and understandable words to learners. On the other hand, the same challenge also applies to the learners, who come from different countries. As they have to use what they learnt, based on their personal understanding of the material to effectively communicate with others in the classroom, even in the contexts of a day to day communication. To reach this win-win stage, Feynman’s Technique plays a very important role. This practical report presents you how the Feynman’s Technique is applied into Chinese courses, both writing & oral, to motivate the learners to practice more on writing, reading and speaking in the past few years. Part 1, analysis of different teaching styles and different types of learners, to find the most efficient way to both teachers and learners. Part 2, based on the theory of Feynman’s Technique, how to let learners build the knowledge from knowing the name of something to knowing something, via different designed target tasks. Part 3. The outcomes show that Feynman’s Technique is the interaction of learning style and teaching style, the double-edged sword of Teaching & Learning Chinese as a Second Language.

Keywords: Chinese, Feynman’s technique, learners, teachers

Procedia PDF Downloads 154

Authors: M. D. D. Chathurangi, M. G. K. Nayanathara, K. M. H. M. M. Gunapala, G. M. R. G. Dayananda, Kavinga Yapa Abeywardena, Deemantha Siriwardana

Abstract:

Due to the growing popularity of social media platforms at present, there are various concerns, mostly cyberbullying, spam, bot accounts, and the spread of incorrect information. To develop a risk score calculation system as a thorough method for deciphering and exposing unethical social media profiles, this research explores the most suitable algorithms to our best knowledge in detecting the mentioned concerns. Various multiple models, such as Naïve Bayes, CNN, KNN, Stochastic Gradient Descent, Gradient Boosting Classifier, etc., were examined, and the best results were taken into the development of the risk score system. For cyberbullying, the Logistic Regression algorithm achieved an accuracy of 84.9%, while the spam-detecting MLP model gained 98.02% accuracy. The bot accounts identifying the Random Forest algorithm obtained 91.06% accuracy, and 84% accuracy was acquired for fake news detection using SVM.

Keywords: cyberbullying, spam behavior, bot accounts, fake news, machine learning

Procedia PDF Downloads 36

Authors: Bharatendra Rai

Abstract:

Predictive data analysis and modeling involving machine learning techniques become challenging in presence of too many explanatory variables or features. Presence of too many features in machine learning is known to not only cause algorithms to slow down, but they can also lead to decrease in model prediction accuracy. This study involves housing dataset with 79 quantitative and qualitative features that describe various aspects people consider while buying a new house. Boruta algorithm that supports feature selection using a wrapper approach build around random forest is used in this study. This feature selection process leads to 49 confirmed features which are then used for developing predictive random forest models. The study also explores five different data partitioning ratios and their impact on model accuracy are captured using coefficient of determination (r-square) and root mean square error (rsme).

Keywords: housing data, feature selection, random forest, Boruta algorithm, root mean square error

Procedia PDF Downloads 323

Authors: Chonmapat Torasa

Abstract:

This paper presents the performance of electricity generation and consumption from solar generator installed at Rajabhat Suan Sunandha’s learning center in Samutsongkram. The result from the experiment showed that solar cell began to work and distribute the current into the system when the solar energy intensity was 340 w/m2, starting from 8:00 am to 4:00 pm (duration of 8 hours). The highest intensity read during the experiment was 1,051.64w/m2. The solar power was 38.74kWh/day. The electromotive force from solar cell averagely was 93.6V. However, when connecting solar cell with the battery charge controller system, the voltage was dropped to 69.07V. After evaluating the power distribution ability and electricity load of tested solar cell, the result showed that it could generate power to 11 units of 36-wattfluorescent lamp bulbs, which was altogether 396W. In the meantime, the AC to DC power converter generated 3.55A to the load, and gave 781VA.

Keywords: solar cell, solar-cell power generating system, computer, systems engineering

Procedia PDF Downloads 325

Authors: K. G. Adeosun, K. Osunaiye, E. C. Chinaguh, M. A. Aliyu, C. A. Onifade

Abstract:

This study examined the effects of incompetence in the use of the mother tongue on the spoken English of selected Primary School pupils in Abeokuta South Local Government, Ogun State, Nigeria. The study used a structured questionnaire and interview guide as data collection instruments. The target population was 110 respondents. The sample was obtained by the use of simple random and stratified sampling techniques. The study samples were pupils from Government Primary Schools in Abeokuta South Local Government. The result revealed that the majority of pupils exhibited mother tongue interference in their oral production stage and that the local indigenous languages interfered with the pronunciation of English words to a large extent such that they pronounced ‘people’ as ‘fitful.’ The findings also revealed that there is no significant difference between inadequate teaching materials, shortage of funds towards the promotion of the mother tongue (Yoruba) and spoken English of Primary school pupils in the study area. The study recommended, among other things, that government should provide the necessary support for schools in the areas of teaching and learning materials, funds and other related materials that can enhance the effective use of the mother tongue towards spoken English by Primary School pupils. Government should ensure that oral English is taught to the pupils and the examination at the end of Primary school education should be made compulsory for all pupils. More so, the Government should provide language laboratories and other equipment to facilitate good teaching and learning of oral English.

Keywords: education, effective, government, learning, teaching

Procedia PDF Downloads 82

Authors: Takamitsu Kodama, Eiji Kawamoto

Abstract:

Introduction: Ultrasound in emergency room has advantages of safer, faster, repeatable and noninvasive. Especially focused Point-Of-Care Ultrasound (POCUS) is used daily for prompt and accurate diagnoses, for quickly identifying critical and life-threatening conditions. That is why ultrasound has demonstrated its usefulness in emergency medicine. The true value of ultrasound has been once again recognized in recent years. It is thought that all resident physicians working at emergency room should perform an ultrasound scan to interpret signs and symptoms of deteriorating patients in the emergency room. However, a practical education on ultrasound is still in development. To resolve this issue, we established a new educational program using high-fidelity simulators and evaluated the efficacy of this course. Methods: Educational program includes didactic lectures and skill stations in half-day course. Instructor gives a lecture on POCUS such as Rapid Ultrasound in Shock (RUSH) and/or Focused Assessment Transthoracic Echo (FATE) protocol at the beginning of the course. Then, attendees are provided for training of scanning with cooperation of normal simulated patients. In the end, attendees learn how to apply focused POCUS skills at clinical situation using high-fidelity simulators such as SonoSim® (SonoSim, Inc) and SimMan® 3G (Laerdal Medical). Evaluation was conducted through surveillance questionnaires to 19 attendees after two pilot courses. The questionnaires were focused on understanding course concept and satisfaction. Results: All attendees answered the questionnaires. With respect to the degree of understanding, 12 attendees (number of valid responses: 13) scored four or more points out of five points. High-fidelity simulators, especially SonoSim® was highly appreciated to enhance learning how to handle ultrasound at an actual practice site by 11 attendees (number of valid responses: 12). All attendees encouraged colleagues to take this course because the high level of satisfaction was achieved. Discussion: Newly introduced educational course using high-fidelity simulators realizes the circle of learning to deepen the understanding on focused POCUS by gradual stages. SonoSim® can faithfully reproduce scan images with pathologic findings of ultrasound and provide experimental learning for a growth number of beginners such as resident physicians. In addition, valuable education can be provided if it is used combined with SimMan® 3G. Conclusions: Newly introduced educational course using high-fidelity simulators is supposed to be effective and helps in providing better education compared with conventional courses for emergency physicians.

Keywords: point-of-care ultrasound, high-fidelity simulators, education, circle of learning

Procedia PDF Downloads 283

Authors: A. M. Byrne, E. Bonfiglio, C. Rigby, N. Edelstyn

Abstract:

Introduction: Neuromarketing employs numerous methodologies when investigating products and advertisement effectiveness. Electroencephalography (EEG), a non-invasive measure of electrical activity from the brain, is commonly used in neuromarketing. EEG data can be considered using time-frequency (TF) analysis, where changes in the frequency of brainwaves are calculated to infer participant’s mental states, or event-related potential (ERP) analysis, where changes in amplitude are observed in direct response to a stimulus. This presentation discusses the findings of a systematic review of EEG measures in neuromarketing. A systematic review summarises evidence on a research question, using explicit measures to identify, select, and critically appraise relevant research papers. Thissystematic review identifies which EEG measures are the most robust predictor of customer preference and purchase intention. Methods: Search terms identified174 papers that used EEG in combination with marketing-related stimuli. Publications were excluded if they were written in a language other than English or were not published as journal articles (e.g., book chapters). The review investigated which TF effect (e.g., theta-band power) and ERP component (e.g., N400) most consistently reflected preference and purchase intention. Machine-learning prediction was also investigated, along with the use of EEG combined with physiological measures such as eye-tracking. Results: Frontal alpha asymmetry was the most reliable TF signal, where an increase in activity over the left side of the frontal lobe indexed a positive response to marketing stimuli, while an increase in activity over the right side indexed a negative response. The late positive potential, a positive amplitude increase around 600 ms after stimulus presentation, was the most reliable ERP component, reflecting the conscious emotional evaluation of marketing stimuli. However, each measure showed mixed results when related to preference and purchase behaviour. Predictive accuracy was greatly improved through machine-learning algorithms such as deep neural networks, especially when combined with eye-tracking or facial expression analyses. Discussion: This systematic review provides a novel catalogue of the most effective use of each EEG measure commonly used in neuromarketing. Exciting findings to emerge are the identification of the frontal alpha asymmetry and late positive potential as markers of preferential responses to marketing stimuli. Predictive accuracy using machine-learning algorithms achieved predictive accuracies as high as 97%, and future research should therefore focus on machine-learning prediction when using EEG measures in neuromarketing.

Keywords: EEG, ERP, neuromarketing, machine-learning, systematic review, time-frequency

Procedia PDF Downloads 111

Authors: Lule Basha, Eralda Gjika

Abstract:

This study is focused on analyzing climate change in Albania and its potential effects on cereal yields. Initially, monthly temperature and rainfalls in Albania were studied for the period 1960-2021. Climacteric variables are important variables when trying to model cereal yield behavior, especially when significant changes in weather conditions are observed. For this purpose, in the second part of the study, linear and nonlinear models explaining cereal yield are constructed for the same period, 1960-2021. The multiple linear regression analysis and lasso regression method are applied to the data between cereal yield and each independent variable: average temperature, average rainfall, fertilizer consumption, arable land, land under cereal production, and nitrous oxide emissions. In our regression model, heteroscedasticity is not observed, data follow a normal distribution, and there is a low correlation between factors, so we do not have the problem of multicollinearity. Machine-learning methods, such as random forest, are used to predict cereal yield responses to climacteric and other variables. Random Forest showed high accuracy compared to the other statistical models in the prediction of cereal yield. We found that changes in average temperature negatively affect cereal yield. The coefficients of fertilizer consumption, arable land, and land under cereal production are positively affecting production. Our results show that the Random Forest method is an effective and versatile machine-learning method for cereal yield prediction compared to the other two methods.

Keywords: cereal yield, climate change, machine learning, multiple regression model, random forest

Procedia PDF Downloads 91