Search results for: cold-start learning

Authors: Besma Khalfoun

Abstract:

In many current Human Activity Recognition (HAR) applications, users' data is frequently shared and centrally stored by third parties, posing a significant privacy risk. This practice makes these entities attractive targets for extracting sensitive information about users, including their identity, health status, and location, thereby directly violating users' privacy. To tackle the issue of centralized data storage, a relatively recent paradigm known as federated learning has emerged. In this approach, users' raw data remains on their smartphones, where they train the HAR model locally. However, users still share updates of their local models originating from raw data. These updates are vulnerable to several attacks designed to extract sensitive information, such as determining whether a data sample is used in the training process, recovering the training data with inversion attacks, or inferring a specific attribute or property from the training data. In this paper, we first introduce PUR-Attack, a parameter-based user re-identification attack developed for HAR applications within a federated learning setting. It involves associating anonymous model updates (i.e., local models' weights or parameters) with the originating user's identity using background knowledge. PUR-Attack relies on a simple yet effective machine learning classifier and produces promising results. Specifically, we have found that by considering the weights of a given layer in a HAR model, we can uniquely re-identify users with an attack success rate of almost 100%. This result holds when considering a small attack training set and various data splitting strategies in the HAR model training. Thus, it is crucial to investigate protection methods to mitigate this privacy threat. Along this path, we propose SAFER, a privacy-preserving mechanism based on adaptive local differential privacy. Before sharing the model updates with the FL server, SAFER adds the optimal noise based on the re-identification risk assessment. Our approach can achieve a promising tradeoff between privacy, in terms of reducing re-identification risk, and utility, in terms of maintaining acceptable accuracy for the HAR model.

Keywords: federated learning, privacy risk assessment, re-identification risk, privacy preserving mechanisms, local differential privacy, human activity recognition

Procedia PDF Downloads 11

Authors: Eugenia Vomvoridi-Ivanovic

Abstract:

It is broadly assumed that participation in field experiences will help pre-service teachers (PSTs) bridge theory to practice. However, this is often not the case since PSTs who are placed in classrooms with large numbers of students from diverse linguistic, cultural, racial, and ethnic backgrounds (culturally diverse students (CDS)) usually observe ineffective mathematics teaching practices that are in contrast to those discussed in their teacher preparation program. Over the past decades, the educational research community has paid increasing attention to investigating out-of-school learning contexts and how participation in such contexts can contribute to the achievement of underrepresented groups in Science, Technology, Engineering, and mathematics (STEM) education and their expanded participation in STEM fields. In addition, several research studies have shown that students display different kinds of mathematical behaviors and discourse practices in out-of-school contexts than they do in the typical mathematics classroom since they draw from a variety of linguistic and cultural resources to negotiate meanings and participate in joint problem solving. However, almost no attention has been given to exploring these contexts as field experiences for pre-service mathematics teachers. The purpose of this study was to explore how participation in a community based after-school field experience promotes understanding of the content pedagogy concepts introduced in elementary mathematics methods courses, particularly as they apply to teaching mathematics to CDS. This study draws upon a situated, socio-cultural theory of teacher learning that centers on the concept of learning as situated social practice, which includes discourse, social interaction, and participation structures. Consistent with exploratory case study methodology, qualitative methods were employed to investigate how a cohort of twelve participating pre-service teacher's approach to pedagogy and their conversations around teaching and learning mathematics to CDS evolved through their participation in the after-school field experience, and how they connected the content discussed in their mathematics methods course with their interactions with the CDS in the after-school. Data were collected over a period of one academic year from the following sources: (a) audio recordings of the PSTs' interactions with the students during the after-school sessions, (b) PSTs' after-school field-notes, (c) audio-recordings of weekly methods course meetings, and (d) other document data (e.g., PST and student generated artifacts, PSTs' written course assignments). The findings of this study reveal that the PSTs benefitted greatly through their participation in the after-school field experience. Specifically, after-school participation promoted a deeper understanding of the content pedagogy concepts introduced in the mathematics methods course and gained a greater appreciation for how students learn mathematics with understanding. Further, even though many of PSTs' assumptions about the mathematical abilities of CDS were challenged and PSTs began to view CDSs' cultural and linguistic backgrounds as resources (rather than obstacles) for learning, some PSTs still held negative stereotypes about CDS and teaching and learning mathematics to CDS in particular. Insights gained through this study contribute to a better understanding of how informal mathematics learning contexts may provide a valuable context for pre-service teacher's learning to teach mathematics to CDS.

Keywords: after-school mathematics program, pre-service mathematical education of teachers, qualitative methods, situated socio-cultural theory, teaching culturally diverse students

Procedia PDF Downloads 130

Authors: Liam Martin, Martha Watson

Abstract:

Patients with learning disabilities (LD) are at increased risk of physical and mental illness due to health inequality. To address this, NICE recommends that people from the age of 14 with a learning disability should have an annual LD health check. This consultation should include a holistic review of the patient’s physical, mental and social health needs with a view of creating an action plan to support the patient’s care. The expected standard set by the Quality and Outcomes Framework (QOF) is that each general practice should review at least 75% of their LD patients annually. During COVID-19, there have been barriers to primary care, including health anxiety, the shift to online general practice and the increase in GP workloads. A surgery in North London wanted to assess whether they were falling short of the expected standard for LD patient annual reviews in order to optimize care post Covid-19. A baseline audit was completed to assess how many LD patients were receiving their annual reviews over the period of 29th September 2020 to 29th September 2021. This information was accessed using EMIS Web Health Care System (EMIS). Patients included were aged 14 and over as per QOF standards. Doctors were not notified of this audit taking place. Following the results of this audit, the creation of learning disability clinics was recommended. These clinics were recommended to be on the ground floor and should be a dedicated time for LD reviews. A re-audit was performed via the same process 6 months later in March 2022. At the time of the baseline audit, there were 71 patients aged 14 and over that were on the LD register. 54% of these LD patients were found to have documentation of an annual LD review within the last 12 months. None of the LD patients between the ages of 14-18 years old had received their annual review. The results were discussed with the practice, and dedicated clinics were set up to review their LD patients. A second pass of the audit was completed 6 months later. This showed an improvement, with 84% of the LD patients registered at the surgery now having a documented annual review within the last 12 months. 78% of the patients between the ages of 14-18 years old had now been reviewed. The baseline audit revealed that the practice was not meeting the expected standard for LD patient’s annual health checks as outlined by QOF, with the most neglected patients being between the ages of 14-18. Identification and awareness of this vulnerable cohort is important to ensure measures can be put into place to support their physical, mental and social wellbeing. Other practices could consider an audit of their annual LD health checks to make sure they are practicing within QOF standards, and if there is a shortfall, they could consider implementing similar actions as used here; dedicated clinics for LD patient reviews.

Keywords: COVID-19, learning disability, learning disability health review, quality and outcomes framework

Procedia PDF Downloads 85

Authors: Zhikal Qadir Salih, Hanife Bensen

Abstract:

As the advent of modern technology continues to make towering impacts on everything, its relevance permeates to all spheres, language learning, and writing skills in particular not an exception. This study aimed at finding out how EFL learners perceive online tools to improve their writing skills. The study was carried out at Tishk University. Copies of the questionnaire were distributed to the participants, in order to elicit their perceptions. The collected data were subjected to descriptive and inferential statistics. The outcome revealed that the participants have positive perceptions about online tools in using them to enhance their writing skills. The study however found out that both gender and the class level of the participants do not make any significant difference in their perceptions about the use of online tools, as far as writing skill is concerned. Based on these outcomes, relevant recommendations were made.

Keywords: online tools, writing skills, EFL learners, language learning

Procedia PDF Downloads 102

Authors: Kishor T. Zingre, Seshadhri Srinivasan

Abstract:

Energy consumption by the building sector is increasing at an alarming rate throughout the world and leading to more building-related CO₂ emissions into the environment. In buildings, the main contributors to energy consumption are heating, ventilation, and air-conditioning (HVAC) systems, lighting, and electrical appliances. It is hypothesised that the energy efficiency in buildings can be achieved by implementing sustainable technologies such as i) enhancing the thermal resistance of fabric materials for reducing heat gain (in hotter climates) and heat loss (in colder climates), ii) enhancing daylight and lighting system, iii) HVAC system and iv) occupant localization. Energy performance of various sustainable technologies is highly dependent on climatic conditions. This paper investigated the use of machine learning techniques for accurate prediction of air-conditioning energy in seasonal climates. The data required to train the machine learning techniques is obtained using the computational simulations performed on a 3-story commercial building using EnergyPlus program plugged-in with OpenStudio and Google SketchUp. The EnergyPlus model was calibrated against experimental measurements of surface temperatures and heat flux prior to employing for the simulations. It has been observed from the simulations that the performance of sustainable fabric materials (for walls, roof, and windows) such as phase change materials, insulation, cool roof, etc. vary with the climate conditions. Various renewable technologies were also used for the building flat roofs in various climates to investigate the potential for electricity generation. It has been observed that the proposed technique overcomes the shortcomings of existing approaches, such as local linearization or over-simplifying assumptions. In addition, the proposed method can be used for real-time estimation of building air-conditioning energy.

Keywords: building energy efficiency, energyplus, machine learning techniques, seasonal climates

Procedia PDF Downloads 114

Authors: Ali Kirkbas

Abstract:

R peaks in an electrocardiogram (ECG) are signs of cardiac activity in individuals that reveal valuable information about cardiac abnormalities, which can lead to mortalities in some cases. This paper examines the problem of detecting R-peaks in ECG signals, which is a two-class pattern classification problem in fact. To handle this problem with a reliable high accuracy, we propose to use the common vector approach which is a successful machine learning algorithm. The dataset used in the proposed method is obtained from MIT-BIH, which is publicly available. The results are compared with the other popular methods under the performance metrics. The obtained results show that the proposed method shows good performance than that of the other. methods compared in the meaning of diagnosis accuracy and simplicity which can be operated on wearable devices.

Keywords: ECG, R-peak classification, common vector approach, machine learning

Procedia PDF Downloads 64

Authors: Julio Jesus Salazar, Julio Jesus De Lama

Abstract:

the fundamental objective of hydrological studies applied to the engineering field is to determine the statistically consistent volumes or water flows that, in each case, allow us to size or design a series of elements or structures to effectively manage and develop a river basin. To determine these values, there are several ways of working within the framework of traditional hydrology: (1) Study each of the factors that influence the hydrological cycle, (2) Study the historical behavior of the hydrology of the area, (3) Study the historical behavior of hydrologically similar zones, and (4) Other studies (rain simulators or experimental basins). Of course, this range of studies in a certain basin is very varied and complex and presents the difficulty of collecting the data in real time. In this complex space, the study of variables can only be overcome by collecting and transmitting data to decision centers through the Internet of things and artificial intelligence. Thus, this research work implemented the learning project of the sub-basin of the Shullcas river in the Andean basin of the Mantaro river in Peru. The sensor firmware to collect and communicate hydrological parameter data was programmed and tested in similar basins of the European Union. The Machine Learning applications was programmed to choose the algorithms that direct the best solution to the determination of the rainfall-runoff relationship captured in the different polygons of the sub-basin. Tests were carried out in the mountains of Europe, and in the sub-basins of the Shullcas river (Huancayo) and the Yauli river (Jauja) with heights close to 5000 m.a.s.l., giving the following conclusions: to guarantee a correct communication, the distance between devices should not pass the 15 km. It is advisable to minimize the energy consumption of the devices and avoid collisions between packages, the distances oscillate between 5 and 10 km, in this way the transmission power can be reduced and a higher bitrate can be used. In case the communication elements of the devices of the network (internet of things) installed in the basin do not have good visibility between them, the distance should be reduced to the range of 1-3 km. The energy efficiency of the Atmel microcontrollers present in Arduino is not adequate to meet the requirements of system autonomy. To increase the autonomy of the system, it is recommended to use low consumption systems, such as the Ashton Raggatt McDougall or ARM Cortex L (Ultra Low Power) microcontrollers or even the Cortex M; and high-performance direct current (DC) to direct current (DC) converters. The Machine Learning System has initiated the learning of the Shullcas system to generate the best hydrology of the sub-basin. This will improve as machine learning and the data entered in the big data coincide every second. This will provide services to each of the applications of the complex system to return the best data of determined flows.

Keywords: hydrology, internet of things, machine learning, river basin

Procedia PDF Downloads 160

Authors: Hajer Chaker Ben Hadj Kacem, Thouraya Slama, Néjiba El Yetim Zribi

Abstract:

This paper analyzes the effects of gender, affiliation, prior work experience, social work, and vicarious learning through family role models on entrepreneurial skills development by students when they have learned through the entrepreneurship method in Tunisia. Authors suggest that these variables enhance the development of students’ entrepreneurial skills when combined with teaching through entrepreneurship. The article assesses the impact of these combinations by comparing their effects on the development of thirteen students’ entrepreneurial competencies, namely entrepreneurial mindset, core self-evaluation, entrepreneurial attitude, entrepreneurial knowledge, creativity, financial literacy, managing ambiguity, marshaling of resources, planning, teaching methods, entrepreneurial teachers, innovative employee, and Entrepreneurial intention. Authors use a two-sample independent t-test to make the comparison, and the results indicate that, when combined with teaching through the entrepreneurship method, students with prior work experience developed better six entrepreneurial skills; students with social work developed better three entrepreneurial skills, men developed better four entrepreneurial skills than women. However, all students developed their entrepreneurial skills through this practical method regardless of their affiliation and their vicarious learning through family role models.

Keywords: affiliation, entrepreneurial skills, gender, role models, social work, teaching through entrepreneurship, vicarious learning, work experience

Procedia PDF Downloads 110

Authors: Shiuh-Jer Huang, Chen-Zon Yan, C. K. Huang, Chun-Chien Ting

Abstract:

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Keywords: deep learning, image processing, convolution neural network, YOLOv2, 7A6 series manipulator

Procedia PDF Downloads 250

Authors: A. U. Ugwu

Abstract:

Post-Apartheid South African education system had witnessed waves of curriculum reforms. Accordingly, there have been evidences of responsiveness towards local and global challenges of sustainable development over the past decade. In other words, the curriculum shows sensitivity towards issues of Sustainable Development (SD). Moreover, the paradigm of Sustainable Development Goals (SDGs) was introduced by the UNESCO in year 2015. The SDGs paradigm is essentially a vision towards actualizing sustainability in all aspects of the global society. Education for Sustainable Development (ESD) in retrospect entails teaching and learning to actualize the intended UNESCO 2030 SDGs. This paper explores how teaching and learning of ESD can be improved, by drawing from local context of the South African schooling system. Preservice natural sciences and technology teachers in their 2nd to 4th years of study at a university’s college of education in South Africa were contacted as participants of the study. Using qualitative case study research design, the study drew from the views and experiences of five (5) purposively selected participants from a broader study, aiming to closely understating how ESD is implemented pedagogically in teaching and learning. The inquiry employed questionnaires and a focus group discussion as qualitative data generation tools. A qualitative data analysis of generated data was carried out using content and thematic analysis, underpinned by interpretive paradigm. The result of analyzed data, suggests that ESD pedagogy at the location where this research was conducted is largely influenced by contextual factors. Furthermore, the result of the study shows that there is a critical need to employ/adopt local experiences or occurrences while teaching sustainable development. Certain pedagogical approaches such as the use of videos relative to local context should also be considered in order to achieve a more realistic application. The paper recommends that educational institutions through teaching and learning should implement ESD by drawing on local contexts and problems, thereby foregrounding constructivism, appreciating and fostering students' prior knowledge and lived experiences.

Keywords: context, education for sustainable development, natural sciences and technology preservice teachers, qualitative research, sustainable development goals

Procedia PDF Downloads 169

Authors: Wei Li, Tuo Yang

Abstract:

In order to satisfy the real-time and accurate requirements of cigarette smoke detection in complex scenes, a cigarette smoke detection technology based on the combination of deep learning and color features was proposed. Firstly, based on the color features of cigarette smoke, the suspicious cigarette smoke area in the image is extracted. Secondly, combined with the efficiency of cigarette smoke detection and the problem of network overfitting, a network model for cigarette smoke detection was designed according to YOLOV3 algorithm to reduce the false detection rate. The experimental results show that the method is feasible and effective, and the accuracy of cigarette smoke detection is up to 99.13%, which satisfies the requirements of real-time cigarette smoke detection in complex scenes.

Keywords: deep learning, computer vision, cigarette smoke detection, YOLOV3, color feature extraction

Procedia PDF Downloads 87

Authors: Ismene Ithai Bras-Ruiz

Abstract:

Learning Analytics (LA) is employed by universities not only as a tool but as a specialized ground to enhance students and professors. However, not all the academic programs apply LA with the same goal and use the same tools. In fact, LA is formed by five main fields of study (academic analytics, action research, educational data mining, recommender systems, and personalized systems). These fields can help not just to inform academic authorities about the situation of the program, but also can detect risk students, professors with needs, or general problems. The highest level applies Artificial Intelligence techniques to support learning practices. LA has adopted different techniques: statistics, ethnography, data visualization, machine learning, natural language process, and data mining. Is expected that any academic program decided what field wants to utilize on the basis of his academic interest but also his capacities related to professors, administrators, systems, logistics, data analyst, and the academic goals. The Open and Distance University System (SUAYED in Spanish) of the University National Autonomous of Mexico (UNAM), has been working for forty years as an alternative to traditional programs; one of their main supports has been the employ of new information and communications technologies (ICT). Today, UNAM has one of the largest network higher education programs, twenty-six academic programs in different faculties. This situation means that every faculty works with heterogeneous populations and academic problems. In this sense, every program has developed its own Learning Analytic techniques to improve academic issues. In this context, an investigation was carried out to know the situation of the application of LA in all the academic programs in the different faculties. The premise of the study it was that not all the faculties have utilized advanced LA techniques and it is probable that they do not know what field of study is closer to their program goals. In consequence, not all the programs know about LA but, this does not mean they do not work with LA in a veiled or, less clear sense. It is very important to know the grade of knowledge about LA for two reasons: 1) This allows to appreciate the work of the administration to improve the quality of the teaching and, 2) if it is possible to improve others LA techniques. For this purpose, it was designed three instruments to determinate the experience and knowledge in LA. These were applied to ten faculty coordinators and his personnel; thirty members were consulted (academic secretary, systems manager, or data analyst, and coordinator of the program). The final report allowed to understand that almost all the programs work with basic statistics tools and techniques, this helps the administration only to know what is happening inside de academic program, but they are not ready to move up to the next level, this means applying Artificial Intelligence or Recommender Systems to reach a personalized learning system. This situation is not related to the knowledge of LA, but the clarity of the long-term goals.

Keywords: academic improvements, analytical techniques, learning analytics, personnel expertise

Procedia PDF Downloads 128

Authors: A. Kalizhanova, T. Shelestova

Abstract:

Teacher professional development (TPD) in Kazakhstan has followed a fairly standard format for centuries, with teachers learning new information from a lecturer and being tested using multiple-choice questions. In the online world, self-access courses have become increasingly popular. Due to their extensive multimedia content, peer-reviewed assignments, adaptable class times, and instruction from top university faculty from across the world, massive open online courses (MOOCs) have found a home in Kazakhstan's system for lifelong learning. Recent studies indicate the limited use of connectivism-based tools such as discussion forums by Kazakhstani pre-service and in-service English teachers, whose professional interests are limited to obtaining certificates rather than enhancing their teaching abilities and exchanging knowledge with colleagues. This paper highlights the significance of connectivism-based tools and instruments, such as MOOCs, for the continuous professional development of pre- and in-service English teachers, facilitators' roles, and their strategies for enhancing trainees' conceptual knowledge within the MOOCs' curriculum and online learning skills. Reviewing the most pertinent papers on Connectivism Theory, facilitators' function in TPD, and connectivism-based tools, such as MOOCs, a code extraction method was utilized. Three experts, former active participants in a series of projects initiated across Kazakhstan to improve the efficacy of MOOCs, evaluated the excerpts and selected the most appropriate ones to propose the matrix of teacher professional competencies that can be acquired through MOOCs. In this paper, we'll look at some of the strategies employed by course instructors to boost their students' English skills and knowledge of course material, both inside and outside of the MOOC platform. Participants' interactive learning contributed to their language and subject conceptual knowledge and prepared them for peer-reviewed assignments in the MOOCs, and this approach of small group interaction was given to highlight the outcomes of participants' interactive learning. Both formal and informal continuing education institutions can use the findings of this study to support teachers in gaining experience with MOOCs and creating their own online courses.

Keywords: connectivism-based tools, teacher professional development, massive open online courses, facilitators, Kazakhstani context

Procedia PDF Downloads 80

Authors: Sumit Sen, Sohan Khedekar, Umang Shinde, Shivam Bhargava

Abstract:

This study has been undertaken to investigate whether the deep learning models are able to predict the future stock prices by training the model with the historical stock price data. Since this work required time series analysis, various models are present today to perform time series analysis such as Recurrent Neural Network LSTM, ARIMA and Facebook Prophet. Applying these models the movement of stock price of stocks are predicted and also tried to provide the future prediction of the stock price of a stock. Final product will be a stock price prediction web application that is developed for providing the user the ease of analysis of the stocks and will also provide the predicted stock price for the next seven days.

Keywords: Autoregressive Integrated Moving Average, Deep Learning, Long Short Term Memory, Time-series

Procedia PDF Downloads 141

Authors: Ezgiamn Abraha Hagos

Abstract:

The primary objective of this study was to assess the existential concerns and related manifestations of higher learning students by investigating their perception of meaningful life and evaluating their purpose in life. In addition, this study was aimed at assessing the manifestations of existential pain among the students. Data was procured using Purpose in Life test (PIL), Well-being Manifestation Measure Scale (WBMMS), and focus group discussion. The total numbers of participants was 478, of which 299 were males and the remaining 179 females. They were selected using a simple random sampling technique. Data was analyzed using two ways. SPSS-version 20 was used to analyze the quantitative part, and narrative modes were utilized to analyze the qualitative data. The research finding revealed that students are involved in risk taking behaviors like alcohol ingestion, drug use, Khat (chat) chewing, and unsafe sex. In line with this it is found out that life in campus was perceived as temporary and as a result the sense of hedonism was prevalent at any cost. Of course, the most important thing for the majority of the students was to know about the purpose of life. Regarding WBMMS, there was no statistically significant difference among males and females and with the exception of the sub-scale of happiness; in all the sub-scales the mean is low. At last, assisting adolescents to develop holistically in terms of body, mind, and spirit is recommended.

Keywords: existential concerns, higher learning institutions, Ethiopia, Aksum University

Procedia PDF Downloads 427

Authors: Wei Zhao

Abstract:

The pandemic crisis disrupted normal classroom practices so that the constraints of the traditional practice became apparent. This turns out to be new opportunities for technology-based learning and teaching. However, how the technology supports the preschool teachers go through this sudden crisis and how preschool teachers conceived of the use of technology, appropriate and design technological artifacts as a mediator of knowledge construction in order to suit young children’s literacy level are rarely explored. This study addresses these issues by looking at the influence of a web-supported teacher community on changes/shifts in preschool teachers’ epistemological beliefs and practices. This teachers’ professional development community was formulated before the pandemic time and developed virtually throughout the home-based learning caused by Covid-19. It served as a virtual and asynchronous community for those teachers to collaboratively plan for and conduct online lessons using the knowledge-building approach for the purpose of sustaining children’s learning curiosity and opening up new learning opportunities during the lock-down period. The knowledge-building approach helps to increase teachers’ collective responsibility to collaboratively work on shared educational goals in the teacher community and awareness of noticing new ideas or innovations in their classroom. Based on the data collected across five months during and after the lock-down period and the activity theory, results show a dynamic interplay between the evolution of the community culture, the growth of teacher community and teachers’ identity transformation and professional development. Technology is useful in this regard not only because it transforms the geographical distance and new gathering guidelines after the outbreak of pandemic into new ways of communal communication and collaboration. More importantly, while teachers selected, monitored and adapted the technology, it acts as a catalyst for changes in teachers’ old teaching practices and epistemological dispositions.

Keywords: activity theory, changes in epistemology and practice, knowledge building, web-based teachers’ professional development community

Procedia PDF Downloads 182

Authors: K. Doi, T. Nishimura, H. Fujimoto

Abstract:

The number of people who become visually impaired and do not have sufficient tactile experiences has increased by various disease. Especially, many acquired visually impaired persons due to accidents, disorders, and aging cannot adequately read Braille. It is known that learning Braille requires a great deal of time and the acquisition of various skills. In our previous studies, we reported one of the problems in learning Braille. Concretely, the standard Braille size is too small for Braille beginners. And also we are short of the objective data regarding easily readable Braille size. Therefore, it is necessary to conduct various experiments for evaluating Braille size that would make learning easier for beginners. In this study, for the purpose of investigating easy-to-read conditions of vertical and horizontal dot spacing for beginners, we conducted one Braille reading experiment. In this our experiment, we prepared test pieces by use of our original Braille printer with controlling function of Braille size. We specifically considered Braille beginners with acquired visual impairments who were unfamiliar with Braille. Therefore, ten sighted subjects with no experience of reading Braille participated in this experiment. Size of vertical and horizontal dot spacing was following conditions. Each dot spacing was 2.0, 2.3, 2.5, 2.7, 2.9, 3.1mm. The subjects were asked to read one Braille character with controlled Braille size. The results of this experiment reveal that Braille beginners can read Braille accurately and quickly when both vertical and horizontal dot spacing are 3.1 mm or more. This knowledge will be helpful data in considering Braille size for acquired visually impaired persons.

Keywords: paper-based Braille, vertical and horizontal dot spacing, readability, acquired visual impairment, Braille beginner

Procedia PDF Downloads 178

Authors: Saahith M. S., Sivakami R.

Abstract:

In the realm of football analytics, particularly focusing on predicting football player performance, the ability to forecast player success accurately is of paramount importance for teams, managers, and fans. This study introduces an elaborate examination of predicting football player performance through the integration of data visualization methods and machine learning algorithms. The research entails the compilation of an extensive dataset comprising player attributes, conducting data preprocessing, feature selection, model selection, and model training to construct predictive models. The analysis within this study will involve delving into feature significance using methodologies like Select Best and Recursive Feature Elimination (RFE) to pinpoint pertinent attributes for predicting player performance. Various machine learning algorithms, including Random Forest, Decision Tree, Linear Regression, Support Vector Regression (SVR), and Artificial Neural Networks (ANN), will be explored to develop predictive models. The evaluation of each model's performance utilizing metrics such as Mean Squared Error (MSE) and R-squared will be executed to gauge their efficacy in predicting player performance. Furthermore, this investigation will encompass a top player analysis to recognize the top-performing players based on the anticipated overall performance scores. Nationality analysis will entail scrutinizing the player distribution based on nationality and investigating potential correlations between nationality and player performance. Positional analysis will concentrate on examining the player distribution across various positions and assessing the average performance of players in each position. Age analysis will evaluate the influence of age on player performance and identify any discernible trends or patterns associated with player age groups. The primary objective is to predict a football player's overall performance accurately based on their individual attributes, leveraging data-driven insights to enrich the comprehension of player success on the field. By amalgamating data visualization and machine learning methodologies, the aim is to furnish valuable tools for teams, managers, and fans to effectively analyze and forecast player performance. This research contributes to the progression of sports analytics by showcasing the potential of machine learning in predicting football player performance and offering actionable insights for diverse stakeholders in the football industry.

Keywords: football analytics, player performance prediction, data visualization, machine learning algorithms, random forest, decision tree, linear regression, support vector regression, artificial neural networks, model evaluation, top player analysis, nationality analysis, positional analysis

Procedia PDF Downloads 38

Authors: Shreya Goyal

Abstract:

The study aims to build user-friendly software to understand patient arrival patterns and compute the number of potential patients who will visit a particular health facility for a given period by using a machine learning algorithm. The underlying machine learning algorithm used in this study is the Support Vector Machine (SVM). Accurate prediction of patient arrival allows hospitals to operate more effectively, providing timely and efficient care while optimizing resources and improving patient experience. It allows for better allocation of staff, equipment, and other resources. If there's a projected surge in patients, additional staff or resources can be allocated to handle the influx, preventing bottlenecks or delays in care. Understanding patient arrival patterns can also help streamline processes to minimize waiting times for patients and ensure timely access to care for patients in need. Another big advantage of using this software is adhering to strict data protection regulations such as the Health Insurance Portability and Accountability Act (HIPAA) in the United States as the hospital will not have to share the data with any third party or upload it to the cloud because the software can read data locally from the machine. The data needs to be arranged in. a particular format and the software will be able to read the data and provide meaningful output. Using software that operates locally can facilitate compliance with these regulations by minimizing data exposure. Keeping patient data within the hospital's local systems reduces the risk of unauthorized access or breaches associated with transmitting data over networks or storing it in external servers. This can help maintain the confidentiality and integrity of sensitive patient information. Historical patient data is used in this study. The input variables used to train the model include patient age, time of day, day of the week, seasonal variations, and local events. The algorithm uses a Supervised learning method to optimize the objective function and find the global minima. The algorithm stores the values of the local minima after each iteration and at the end compares all the local minima to find the global minima. The strength of this study is the transfer function used to calculate the number of patients. The model has an output accuracy of >95%. The method proposed in this study could be used for better management planning of personnel and medical resources.

Keywords: machine learning, SVM, HIPAA, data

Procedia PDF Downloads 65

Authors: Revoti Prasad Bora, Nikita Katyal

Abstract:

Promotion is a key element in the retail business. Thus, analysis of promotions to quantify their effectiveness in terms of Revenue and/or Margin is an essential activity in the retail industry. However, measuring the sales/revenue uplift is based on estimations, as the actual sales/revenue without the promotion is not present. Further, the presence of Halo and Cannibalization in a multiple parallel promotions’ scenario complicates the problem. Calculating Baseline by considering inter-brand/competitor items or using Halo and Cannibalization's impact on Revenue calculations by considering Baseline as an interpretation of items’ unit sales in neighboring nonpromotional weeks individually may not capture the overall Revenue uplift in the case of multiple parallel promotions. Hence, this paper proposes a Machine Learning based method for calculating the Revenue uplift by considering the Halo and Cannibalization impact on the Baseline and the Revenue. In the first section of the proposed methodology, Baseline of an item is calculated by incorporating the impact of the promotions on its related items. In the later section, the Revenue of an item is calculated by considering both Halo and Cannibalization impacts. Hence, this methodology enables correct calculation of the overall Revenue uplift due a given promotion.

Keywords: Halo, Cannibalization, promotion, Baseline, temporary price reduction, retail, elasticity, cross price elasticity, machine learning, random forest, linear regression

Procedia PDF Downloads 177

Authors: Maha Jazouli

Abstract:

Suicide is one of the most important causes of death in the prison environment, both in Canada and internationally. Rates of attempts of suicide and self-harm have been on the rise in recent years, with hangings being the most frequent method resorted to. The objective of this article is to propose a method to automatically detect in real time suicidal behaviors. We present a gesture recognition system that consists of three modules: model-based movement tracking, feature extraction, and gesture recognition using machine learning algorithms (MLA). Our proposed system gives us satisfactory results. This smart video surveillance system can help assist staff responsible for the safety and health of inmates by alerting them when suicidal behavior is detected, which helps reduce mortality rates and save lives.

Keywords: suicide detection, Kinect azure, RGB-D camera, SVM, machine learning, gesture recognition

Procedia PDF Downloads 188

Authors: Arpit Patil, Atharav Bhagwat, Rajas Bhope, Pramod Bide

Abstract:

This research integrates IoT and ML to predict heart failure risks, utilizing the Framingham dataset. IoT devices gather real-time physiological data, focusing on heart rate dynamics, while ML, specifically Random Forest, predicts heart failure. Rigorous feature selection enhances accuracy, achieving over 90% prediction rate. This amalgamation marks a transformative step in proactive healthcare, highlighting early detection's critical role in cardiovascular risk mitigation. Challenges persist, necessitating continual refinement for improved predictive capabilities.

Keywords: cardiovascular diseases, internet of things, machine learning, cardiac risk assessment, heart failure prediction, early detection, cardio data analysis

Procedia PDF Downloads 11

Authors: Alper Akin, Ibrahim Aydogdu

Abstract:

This study presents a hybrid metaheuristic algorithm to obtain optimum designs for steel space buildings. The optimum design problem of three-dimensional steel frames is mathematically formulated according to provisions of LRFD-AISC (Load and Resistance factor design of American Institute of Steel Construction). Design constraints such as the strength requirements of structural members, the displacement limitations, the inter-story drift and the other structural constraints are derived from LRFD-AISC specification. In this study, a hybrid algorithm by using teaching-learning based optimization (TLBO) and harmony search (HS) algorithms is employed to solve the stated optimum design problem. These algorithms are two of the recent additions to metaheuristic techniques of numerical optimization and have been an efficient tool for solving discrete programming problems. Using these two algorithms in collaboration creates a more powerful tool and mitigates each other’s weaknesses. To demonstrate the powerful performance of presented hybrid algorithm, the optimum design of a large scale steel building is presented and the results are compared to the previously obtained results available in the literature.

Keywords: optimum structural design, hybrid techniques, teaching-learning based optimization, harmony search algorithm, minimum weight, steel space frame

Procedia PDF Downloads 545

Authors: Georgios Charizanos, Haydar Demirhan, Duygu Icen

Abstract:

Two of the most impactful issues in classical logistic regression are class imbalance and complete separation. These can result in model predictions heavily leaning towards the imbalanced class on the binary response variable or over-fitting issues. Fuzzy methodology offers key solutions for handling these problems. However, most studies propose the transformation of the binary responses into a continuous format limited within [0,1]. This is called the possibilistic approach within fuzzy logistic regression. Following this approach is more aligned with straightforward regression since a logit-link function is not utilized, and fuzzy probabilities are not generated. In contrast, we propose a method of fuzzifying binary response variables that allows for the use of the logit-link function; hence, a probabilistic fuzzy logistic regression model with the Monte Carlo method. The fuzzy probabilities are then classified by selecting a fuzzy threshold. Different combinations of fuzzy and crisp input, output, and coefficients are explored, aiming to understand which of these perform better under different conditions of imbalance and separation. We conduct numerical experiments using both synthetic and real datasets to demonstrate the performance of the fuzzy logistic regression framework against seven crisp machine learning methods. The proposed framework shows better performance irrespective of the degree of imbalance and presence of separation in the data, while the considered machine learning methods are significantly impacted.

Keywords: fuzzy logistic regression, fuzzy, logistic, machine learning

Procedia PDF Downloads 74

Authors: Sebastianus Menggo

Abstract:

The aim of communicative language teaching is to enable learners to communicate in the target language. Each learner is required to perform the micro and macro components in each utterance produced. Utterances produced must be in line with the understanding of competence and performance of each speaker. These are inter-depended. Competence and performance are obliged to be appeared proportionally in creating the utterances. The representative of competence and performance reflects the linguistics identity of a speaker in providing sentences in each certain language community. Each lexicon spoken may lead that interlocutor in comprehending the intentions utterances given. However proportional performance of both components in an utterance needed to be further elaborated. Finding appropriate gap between competence and performance components in a communicative competence must be supported positive response given by the learners.The learners’ inability to keep communicative competence proportionally is caused by inside and outside factors. The inside factors are certain lacks such as lack of self-confidence and lack of motivation which could make students feel ashamed to produce utterances, scared to make mistakes, and have no enough confidence. Knowing learner’s English learning motivation is an urgent variable to be considered in creating conducive atmosphere classroom which will raise the learners to do more toward the achievement of communicative competence. Meanwhile, the outside factor is related with the teacher. The teacher should be able to recognize the students’ problem in creating conducive atmosphere in the classroom that will raise the students’ ability to be an English speaker qualified. Moreover, the aim of this research is to know and describe the English learning motivation affecting students’ communicative competence of 48 students of XI grade of science program at catholic senior of Saint Ignasius Loyola Labuan Bajo, West Flores, Indonesia. Correlation design with purposive procedure applied in this research. Data were collected through questionnaire, interview, and students’ speaking achievement document. Result shows the description of motivation significantly affecting students’ communicative competence.

Keywords: communicative, competence, English, learning, motivation

Procedia PDF Downloads 200

Authors: Muhammad Saqib Manzoor, Camille Dickson-Deane, Prashan Karunaratne

Abstract:

Cobb-Douglas production (utility) function is a fundamental function widely used in economics teaching and research. The key reason is the function's characteristics to describe the actual production using inputs like labour and capital. The characteristics of the function like returns to scale, marginal, and diminishing marginal productivities are covered in the introductory units in both microeconomics and macroeconomics with a 2-dimensional static visualisation of the function. However, less insight is provided regarding three-dimensional surface, changes in the curvature properties due to returns to scale, the linkage of the short-run production function with its long-run counterpart and marginal productivities, the level curves, and the constraint optimisation. Since (freshman) learners have diverse prior knowledge and cognitive skills, the existing “one size fits all” approach is not very helpful. The aim of this study is to bridge this gap by introducing technological intervention with interactive animations of the three-dimensional surface and sequential unveiling of the characteristics mentioned above using Python software. A small classroom intervention has helped students enhance their analytical and visualisation skills towards active and authentic learning of this topic. However, to authenticate the strength of our approach, a quasi-Delphi study will be conducted to ask domain-specific experts, “What value to the learning process in economics is there using a 2-dimensional static visualisation compared to using a 3-dimensional dynamic visualisation?’ Here three perspectives of the intervention were reviewed by a panel comprising of novice students, experienced students, novice instructors, and experienced instructors in an effort to determine the learnings from each type of visualisations within a specific domain of knowledge. The value of this approach is key to suggesting different pedagogical methods which can enhance learning outcomes.

Keywords: cobb-douglas production function, quasi-Delphi method, effective teaching and learning, 3D-visualisations

Procedia PDF Downloads 145

Authors: Silvia Zanazzi

Abstract:

Artificial intelligence (AI) has become an integral part of our world, transitioning from scientific exploration to practical applications that impact daily life. The emergence of generative AI is reshaping education, prompting new questions about the role of teachers, the nature of learning, and the overall purpose of schooling. While AI offers the potential for optimizing teaching and learning processes, concerns about discrimination and bias arising from training data and algorithmic decisions persist. There is a risk of a disconnect between the rapid development of AI and the goals of building inclusive educational environments. The prevailing discourse on AI in education often prioritizes efficiency and individual skill acquisition. This narrow focus can undermine the importance of collaborative learning and shared experiences. A growing body of research challenges this perspective, advocating for AI that enhances, rather than replaces, human interaction in education. This study aims to examine the relationship between AI and education critically. Reviewing existing research will identify both AI implementation’s potential benefits and risks. The goal is to develop a framework that supports the ethical and effective integration of AI into education, ensuring it serves the needs of all learners. The theoretical reflection will be developed based on a review of national and international scientific literature on artificial intelligence in education. The primary objective is to curate a selection of critical contributions from diverse disciplinary perspectives and/or an inter- and transdisciplinary viewpoint, providing a state-of-the-art overview and a critical analysis of potential future developments. Subsequently, the thematic analysis of these contributions will enable the creation of a framework for understanding and critically analyzing the role of artificial intelligence in schools and education, highlighting promising directions and potential pitfalls. The expected results are (1) a classification of the cognitive biases present in representations of AI in education and the associated risks and (2) a categorization of potentially beneficial interactions between AI applications and teaching and learning processes, including those already in use or under development. While not exhaustive, the proposed framework will serve as a guide for critically exploring the complexity of AI in education. It will help to reframe dystopian visions often associated with technology and facilitate discussions on fostering synergies that balance the ‘dream’ of quality education for all with the realities of AI implementation. The discourse on artificial intelligence in education, highlighting reductionist models rooted in fragmented and utilitarian views of knowledge, has the merit of stimulating the construction of alternative perspectives that can ‘return’ teaching and learning to education, human growth, and the well-being of individuals and communities.

Keywords: education, artificial intelligence, teaching, learning

Procedia PDF Downloads 20

Authors: Robyn Moloney, HuiLing Xu

Abstract:

Many countries wish to produce Asia-literate citizens, through language education. International contexts of Chinese language education are seeking pedagogical innovation to meet local contextual factors frequently holding back learner success. In multicultural Australia, innovative pedagogy is urgently needed to support motivation in sustained study, with greater strategic integration of technology. This research took a qualitative approach to identify need and solutions. The paper analyses strategies that three secondary school teachers are adopting to meet specific challenges in the Australian context. The data include teacher interviews, classroom observations and student interviews. We highlight the use of task-based learning and differentiated teaching for multilevel classes, and the role which digital technologies play in facilitating both areas. The strategy examples are analysed in reference both to a research-based framework for describing quality teaching, and to current understandings of motivation in language learning. The analysis of data identifies learning featuring deep knowledge, higher-order thinking, engagement, social support, utilisation of background knowledge, and connectedness, all of which work towards the learners having a sense of autonomy and an imagination of becoming an adult Chinese language user.

Keywords: Chinese pedagogy, digital technologies, motivation, secondary school

Procedia PDF Downloads 268

Authors: Martha Wilson

Abstract:

With the peak of Computer-Assisted Language Learning slowly coming to pass and Mobile-Assisted Language Learning, at times, a bit lacking in the communicative department, we are now faced with a challenging question: How can we engage the interest of our digital native students and, most importantly, sustain it? As previously mentioned, our classrooms are now experiencing an influx of “digital natives” – people who have grown up using and having unlimited access to technology. While modernizing our curriculum and digitalizing our classrooms are necessary in order to accommodate this new learning style, it is a huge financial burden and a massive undertaking for language institutes. Instead, opting for a more compact, simple, yet multidimensional pedagogical tool may be the solution to the issue at hand. This paper aims to give a brief overview into an existing device referred to as Student Response Systems (SRS) and to expand on this notion to include a new prototype of response system that will be designed as a mobile application to eliminate the need for costly hardware and software. Additionally, an analysis into recent attempts by other institutes to develop the Mobile Response System (MRS) and customer reviews of the existing MRSs will be provided, as well as the lessons learned from those projects. Finally, while the new model of MRS is still in its infancy stage, this paper will discuss the implications of incorporating such an application as a tool to support and to enrich traditional techniques and also offer practical classroom applications with the existing response systems that are immediately available on the market.

Keywords: app, clickers, mobile app, mobile response system, student response system

Procedia PDF Downloads 371

Authors: Shayan Mohajer Hamidi

Abstract:

Federated Learning (FL) has emerged as a promising paradigm for training machine learning models on distributed data without the need for centralized data aggregation. In the realm of wireless communications, FL has the potential to leverage the vast amounts of data generated by wireless devices to improve model performance and enable intelligent applications. However, the fairness aspect of FL in wireless communications remains largely unexplored. This abstract presents an idea for fair federated learning in wireless communications, addressing the challenges of imbalanced data distribution, privacy preservation, and resource allocation. Firstly, the proposed approach aims to tackle the issue of imbalanced data distribution in wireless networks. In typical FL scenarios, the distribution of data across wireless devices can be highly skewed, resulting in unfair model updates. To address this, we propose a weighted aggregation strategy that assigns higher importance to devices with fewer samples during the aggregation process. By incorporating fairness-aware weighting mechanisms, the proposed approach ensures that each participating device's contribution is proportional to its data distribution, thereby mitigating the impact of data imbalance on model performance. Secondly, privacy preservation is a critical concern in federated learning, especially in wireless communications where sensitive user data is involved. The proposed approach incorporates privacy-enhancing techniques, such as differential privacy, to protect user privacy during the model training process. By adding carefully calibrated noise to the gradient updates, the proposed approach ensures that the privacy of individual devices is preserved without compromising the overall model accuracy. Moreover, the approach considers the heterogeneity of devices in terms of computational capabilities and energy constraints, allowing devices to adaptively adjust the level of privacy preservation to strike a balance between privacy and utility. Thirdly, efficient resource allocation is crucial for federated learning in wireless communications, as devices operate under limited bandwidth, energy, and computational resources. The proposed approach leverages optimization techniques to allocate resources effectively among the participating devices, considering factors such as data quality, network conditions, and device capabilities. By intelligently distributing the computational load, communication bandwidth, and energy consumption, the proposed approach minimizes resource wastage and ensures a fair and efficient FL process in wireless networks. To evaluate the performance of the proposed fair federated learning approach, extensive simulations and experiments will be conducted. The experiments will involve a diverse set of wireless devices, ranging from smartphones to Internet of Things (IoT) devices, operating in various scenarios with different data distributions and network conditions. The evaluation metrics will include model accuracy, fairness measures, privacy preservation, and resource utilization. The expected outcomes of this research include improved model performance, fair allocation of resources, enhanced privacy preservation, and a better understanding of the challenges and solutions for fair federated learning in wireless communications. The proposed approach has the potential to revolutionize wireless communication systems by enabling intelligent applications while addressing fairness concerns and preserving user privacy.

Keywords: federated learning, wireless communications, fairness, imbalanced data, privacy preservation, resource allocation, differential privacy, optimization

Procedia PDF Downloads 75