Search results for: workforce diversity learning
3738 Promoting Libraries' Services and Events by Librarians Led Instagram Account: A Case Study on Qatar National Library's Research and Learning Instagram Account
Authors: Maryam Alkhalosi, Ahmad Naddaf, Rana Alani
Abstract:
Qatar National Library has its main accounts on social media, which presents the general image of the library and its daily news. A paper will be presented based on a case study researching the outcome of having a separate Instagram account led by librarians, not the Communication Department of the library. The main purpose of the librarians-led account is to promote librarians’ services and events, such as research consultation, reference questions, community engagement programs, collection marketing, etc. all in the way that librarians think it reflects their role in the community. Librarians had several obstacles to help users understanding librarians' roles. As was noticed that Instagram is the most popular social media platform in Qatar, it was selected to promote how librarians can help users through a focused account to create a direct channel between librarians and users. Which helps librarians understand users’ needs and interests. This research will use a quantitative approach depending on the case study, librarians have used their case in the department of Research and learning to find out the best practices might help in promoting the librarians' services and reaching out to a bigger number of users. Through the descriptive method, this research will describe the changes observed in the numbers of community users who interact with the Instagram account and engaged in librarians’ events. Statistics of this study are based on three main sources: 1. The internal monthly statistics sheet of events and programs held by the Research and Learning Department. 2. The weekly tracking of the Instagram account statistics. 3. Instagram’s tools such as polls, quizzes, questions, etc. This study will show the direct effect of a librarian-led Instagram account on the number of community members who participate and engage in librarian-led programs and services. In addition to highlighting the librarians' role directly with the community members. The study will also show the best practices on Instagram, which helps reaching a wider community of users. This study is important because, in the region, there is a lack of studies focusing on librarianship, especially on contemporary problems and its solution. Besides, there is a lack of understanding of the role of a librarian in the Arab region. The research will also highlight how librarians can help the public and researchers as well. All of these benefits can come through one popular easy channel in social media. From another side, this paper is a chance to share the details of this experience starting from scratch, including the phase of setting the policy and guidelines of managing the social media account, until librarians reached to a point where the benefits of this experience are in reality. This experience had even added many skills to the librarians.Keywords: librarian’s role, social media, instagram and libraries, promoting libraries’ services
Procedia PDF Downloads 963737 The Educational Philosophies and Teaching Style Preferences of College Faculty at Selected Universities in the South of Metro Manila
Authors: Grace D. Severo, Lopita U. Jung
Abstract:
This study aimed to determine the educational philosophies and teaching styles of the college faculty of the University of Perpetual Help System DALTA in the campuses of Las-Piñas, Molino, and Calamba, south of Metro Manila. It sought to determine the relationships of educational philosophy and teaching styles of the college faculty vis-à-vis the university system’s educational philosophies and teaching style preferences. A hundred and five faculty members from the Colleges of Education, Arts and Sciences responded to the survey during the academic year 2014-2015. The Philosophy of Adult Education Inventory measured the faculty’s preferred educational philosophies. The Principles of Adult Learning Scale measured the faculty’s teaching style preference. Findings show that there is a similarity between the university system and the faculty members in using the progressive educational philosophy, however both contrasted in the preferred teaching style. Majority of the faculty held progressive educational philosophy but their preference for teacher-centered teaching style did not match. This implies that the majority are certain of having progressive educational philosophy but are not utilizing the learner-centered teaching styles; a high degree of support and commitment to practice a progressive and humanist philosophical orientation in education; and a high degree of support on teacher-centered teaching style promotion from the institution can strengthen a high degree of commitment for the faculty to enunciate their values and practice through these educational philosophies and teaching styles.Keywords: educational philosophies, teaching styles, philosophy of adult education inventory, principles of adult learning scale
Procedia PDF Downloads 3673736 Parasitological Study and Its Role in Fisheries Management and Stock Assessment of Boops boops (Lineauses, 1758) along the Tunisian Coast
Authors: I. Chebbi, L. Boudaya, L. Neifar
Abstract:
The bogue, Boops boops is an economically important fishery resource and commonly captured in the Mediterranean, and its diversity in parasites has been used as a tool to differentiate between stocks along with Tunisia since it is widely acceptable in fisheries management. In this study, a total of 90 fish are investigated from three localities off Tunisia, including Kelibia, Mahdia, and Zarzis. Fifteen species of parasites totaling 1270 individuals were harvested from B. boops, whereas ten parasites were used as biological tags. Based on Mahalanobis distance, each parasite species shows a great importance in the discrimination between groups. Tetraphyllidea larvae are the most influential parasites in determining the position of samples belonging to Kelibia. Monogenean species and Hysterothylacium sp. are the most important species for determining the position of samples from Mahdia. Specimens from Zarzis are characterized by the absence of the four Monogenean species and the Tetraphyllidea larvae. Parasites allocate B. boops population correctly to their origin communities with an accuracy of 83.3%. These results were corroborated by the discriminant analyses, highlighted the presence of three stocks, and improved that the parasitological method can be considered as a reliable key to provide imperative information for discriminating among B. boops stocks in Tunisian waters.Keywords: biological marker, Boops boops, parasite, population structure
Procedia PDF Downloads 1343735 Roof and Road Network Detection through Object Oriented SVM Approach Using Low Density LiDAR and Optical Imagery in Misamis Oriental, Philippines
Authors: Jigg L. Pelayo, Ricardo G. Villar, Einstine M. Opiso
Abstract:
The advances of aerial laser scanning in the Philippines has open-up entire fields of research in remote sensing and machine vision aspire to provide accurate timely information for the government and the public. Rapid mapping of polygonal roads and roof boundaries is one of its utilization offering application to disaster risk reduction, mitigation and development. The study uses low density LiDAR data and high resolution aerial imagery through object-oriented approach considering the theoretical concept of data analysis subjected to machine learning algorithm in minimizing the constraints of feature extraction. Since separating one class from another in distinct regions of a multi-dimensional feature-space, non-trivial computing for fitting distribution were implemented to formulate the learned ideal hyperplane. Generating customized hybrid feature which were then used in improving the classifier findings. Supplemental algorithms for filtering and reshaping object features are develop in the rule set for enhancing the final product. Several advantages in terms of simplicity, applicability, and process transferability is noticeable in the methodology. The algorithm was tested in the different random locations of Misamis Oriental province in the Philippines demonstrating robust performance in the overall accuracy with greater than 89% and potential to semi-automation. The extracted results will become a vital requirement for decision makers, urban planners and even the commercial sector in various assessment processes.Keywords: feature extraction, machine learning, OBIA, remote sensing
Procedia PDF Downloads 3623734 Remote Sensing through Deep Neural Networks for Satellite Image Classification
Authors: Teja Sai Puligadda
Abstract:
Satellite images in detail can serve an important role in the geographic study. Quantitative and qualitative information provided by the satellite and remote sensing images minimizes the complexity of work and time. Data/images are captured at regular intervals by satellite remote sensing systems, and the amount of data collected is often enormous, and it expands rapidly as technology develops. Interpreting remote sensing images, geographic data mining, and researching distinct vegetation types such as agricultural and forests are all part of satellite image categorization. One of the biggest challenge data scientists faces while classifying satellite images is finding the best suitable classification algorithms based on the available that could able to classify images with utmost accuracy. In order to categorize satellite images, which is difficult due to the sheer volume of data, many academics are turning to deep learning machine algorithms. As, the CNN algorithm gives high accuracy in image recognition problems and automatically detects the important features without any human supervision and the ANN algorithm stores information on the entire network (Abhishek Gupta., 2020), these two deep learning algorithms have been used for satellite image classification. This project focuses on remote sensing through Deep Neural Networks i.e., ANN and CNN with Deep Sat (SAT-4) Airborne dataset for classifying images. Thus, in this project of classifying satellite images, the algorithms ANN and CNN are implemented, evaluated & compared and the performance is analyzed through evaluation metrics such as Accuracy and Loss. Additionally, the Neural Network algorithm which gives the lowest bias and lowest variance in solving multi-class satellite image classification is analyzed.Keywords: artificial neural network, convolutional neural network, remote sensing, accuracy, loss
Procedia PDF Downloads 1593733 Machine Learning Based Digitalization of Validated Traditional Cognitive Tests and Their Integration to Multi-User Digital Support System for Alzheimer’s Patients
Authors: Ramazan Bakir, Gizem Kayar
Abstract:
It is known that Alzheimer and Dementia are the two most common types of Neurodegenerative diseases and their visibility is getting accelerated for the last couple of years. As the population sees older ages all over the world, researchers expect to see the rate of this acceleration much higher. However, unfortunately, there is no known pharmacological cure for both, although some help to reduce the rate of cognitive decline speed. This is why we encounter with non-pharmacological treatment and tracking methods more for the last five years. Many researchers, including well-known associations and hospitals, lean towards using non-pharmacological methods to support cognitive function and improve the patient’s life quality. As the dementia symptoms related to mind, learning, memory, speaking, problem-solving, social abilities and daily activities gradually worsen over the years, many researchers know that cognitive support should start from the very beginning of the symptoms in order to slow down the decline. At this point, life of a patient and caregiver can be improved with some daily activities and applications. These activities include but not limited to basic word puzzles, daily cleaning activities, taking notes. Later, these activities and their results should be observed carefully and it is only possible during patient/caregiver and M.D. in-person meetings in hospitals. These meetings can be quite time-consuming, exhausting and financially ineffective for hospitals, medical doctors, caregivers and especially for patients. On the other hand, digital support systems are showing positive results for all stakeholders of healthcare systems. This can be observed in countries that started Telemedicine systems. The biggest potential of our system is setting the inter-user communication up in the best possible way. In our project, we propose Machine Learning based digitalization of validated traditional cognitive tests (e.g. MOCA, Afazi, left-right hemisphere), their analyses for high-quality follow-up and communication systems for all stakeholders. R. Bakir and G. Kayar are with Gefeasoft, Inc, R&D – Software Development and Health Technologies company. Emails: ramazan, gizem @ gefeasoft.com This platform has a high potential not only for patient tracking but also for making all stakeholders feel safe through all stages. As the registered hospitals assign corresponding medical doctors to the system, these MDs are able to register their own patients and assign special tasks for each patient. With our integrated machine learning support, MDs are able to track the failure and success rates of each patient and also see general averages among similarly progressed patients. In addition, our platform also supports multi-player technology which helps patients play with their caregivers so that they feel much safer at any point they are uncomfortable. By also gamifying the daily household activities, the patients will be able to repeat their social tasks and we will provide non-pharmacological reminiscence therapy (RT – life review therapy). All collected data will be mined by our data scientists and analyzed meaningfully. In addition, we will also add gamification modules for caregivers based on Naomi Feil’s Validation Therapy. Both are behaving positively to the patient and keeping yourself mentally healthy is important for caregivers. We aim to provide a therapy system based on gamification for them, too. When this project accomplishes all the above-written tasks, patients will have the chance to do many tasks at home remotely and MDs will be able to follow them up very effectively. We propose a complete platform and the whole project is both time and cost-effective for supporting all stakeholders.Keywords: alzheimer’s, dementia, cognitive functionality, cognitive tests, serious games, machine learning, artificial intelligence, digitalization, non-pharmacological, data analysis, telemedicine, e-health, health-tech, gamification
Procedia PDF Downloads 1373732 Credit Card Fraud Detection with Ensemble Model: A Meta-Heuristic Approach
Authors: Gong Zhilin, Jing Yang, Jian Yin
Abstract:
The purpose of this paper is to develop a novel system for credit card fraud detection based on sequential modeling of data using hybrid deep learning models. The projected model encapsulates five major phases are pre-processing, imbalance-data handling, feature extraction, optimal feature selection, and fraud detection with an ensemble classifier. The collected raw data (input) is pre-processed to enhance the quality of the data through alleviation of the missing data, noisy data as well as null values. The pre-processed data are class imbalanced in nature, and therefore they are handled effectively with the K-means clustering-based SMOTE model. From the balanced class data, the most relevant features like improved Principal Component Analysis (PCA), statistical features (mean, median, standard deviation) and higher-order statistical features (skewness and kurtosis). Among the extracted features, the most optimal features are selected with the Self-improved Arithmetic Optimization Algorithm (SI-AOA). This SI-AOA model is the conceptual improvement of the standard Arithmetic Optimization Algorithm. The deep learning models like Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and optimized Quantum Deep Neural Network (QDNN). The LSTM and CNN are trained with the extracted optimal features. The outcomes from LSTM and CNN will enter as input to optimized QDNN that provides the final detection outcome. Since the QDNN is the ultimate detector, its weight function is fine-tuned with the Self-improved Arithmetic Optimization Algorithm (SI-AOA).Keywords: credit card, data mining, fraud detection, money transactions
Procedia PDF Downloads 1313731 Extending BDI Multiagent Systems with Agent Norms
Authors: Francisco José Plácido da Cunha, Tassio Ferenzini Martins Sirqueira, Marx Leles Viana, Carlos José Pereira de Lucena
Abstract:
Open Multiagent Systems (MASs) are societies in which heterogeneous and independently designed entities (agents) work towards similar, or different ends. Software agents are autonomous and the diversity of interests among different members living in the same society is a fact. In order to deal with this autonomy, these open systems use mechanisms of social control (norms) to ensure a desirable social order. This paper considers the following types of norms: (i) obligation — agents must accomplish a specific outcome; (ii) permission — agents may act in a particular way, and (iii) prohibition — agents must not act in a specific way. All of these characteristics mean to encourage the fulfillment of norms through rewards and to discourage norm violation by pointing out the punishments. Once the software agent decides that its priority is the satisfaction of its own desires and goals, each agent must evaluate the effects associated to the fulfillment of one or more norms before choosing which one should be fulfilled. The same applies when agents decide to violate a norm. This paper also introduces a framework for the development of MASs that provide support mechanisms to the agent’s decision-making, using norm-based reasoning. The applicability and validation of this approach is demonstrated applying a traffic intersection scenario.Keywords: BDI agent, BDI4JADE framework, multiagent systems, normative agents
Procedia PDF Downloads 2323730 Characterization of Organic Matter in Spodosol Amazonian by Fluorescence Spectroscopy
Authors: Amanda M. Tadini, Houssam Hajjoul, Gustavo Nicolodelli, Stéphane Mounier, Célia R. Montes, Débora M. B. P. Milori
Abstract:
Soil organic matter (SOM) plays an important role in maintaining soil productivity and accounting for the promotion of biological diversity. The main components of the SOM are the humic substances which can be fractionated according to its solubility in humic acid (HA), fulvic acids (FA) and humin (HU). The determination of the chemical properties of organic matter as well as its interaction with metallic species is an important tool for understanding the structure of the humic fractions. Fluorescence spectroscopy has been studied as a source of information about what is happening at the molecular level in these compounds. Specially, soils of Amazon region are an important ecosystem of the planet. The aim of this study is to understand the molecular and structural composition of HA samples from Spodosol of Amazonia using the fluorescence Emission-Excitation Matrix (EEM) and Time Resolved Fluorescence Spectroscopy (TRFS). The results showed that the samples of HA showed two fluorescent components; one has a more complex structure and the other one has a simpler structure, which was also seen in TRFS through the evaluation of each sample lifetime. Thus, studies of this nature become important because it aims to evaluate the molecular and structural characteristics of the humic fractions in the region that is considered as one of the most important regions in the world, the Amazon.Keywords: Amazonian soil, characterization, fluorescence, humic acid, lifetime
Procedia PDF Downloads 6103729 Co-Creation of Content with the Students in Entrepreneurship Education to Capture Entrepreneurship Phenomenon in an Innovative Way
Authors: Prema Basargekar
Abstract:
Facilitating the subject ‘Entrepreneurship Education’ in higher education, such as management studies, can be exhilarating as well as challenging. It is a multi-disciplinary and ever-evolving subject. Capturing entrepreneurship as a phenomenon in a holistic manner is a daunting task as it requires covering various dimensions such as new ideas generation, entrepreneurial traits, business opportunities scanning, the role of policymakers, value creation, etc., to name a few. Implicit entrepreneurship theory and effectuation are two different theories that focus on engaging the participants to create content by using their own experiences, perceptions, and belief systems. It helps in understanding the phenomenon holistically. The assumption here is that all of us are part of the entrepreneurial ecosystem, and effective learning can come through active engagement and peer learning by all the participants together. The present study is an attempt to use these theories in the class assignment given to the students at the beginning of the course to build the course content and understand entrepreneurship as a phenomenon in a better way through peer learning. The assignment was given to three batches of MBA post-graduate students doing the program in one of the private business schools in India. The subject of ‘Entrepreneurship Management’ is facilitated in the third trimester of the first year. At the beginning of the course, the students were given the assignment to submit a brief write-up/ collage/picture/poem or in any other format about “What entrepreneurship means to you?” They were asked to give their candid opinions about entrepreneurship as a phenomenon as they perceive it. Nearly 156 students doing post-graduate MBA submitted the assignment. These assignments were further used to find answers to two research questions. – 1) Are students able to use divergent and innovative forms to express their opinions, such as poetry, illustrations, videos, etc.? 2) What are various dimensions of entrepreneurship which are emerging to understand the phenomenon in a better way? The study uses the Brawn and Clark framework of reflective thematic analysis for qualitative analysis. The study finds that students responded to this assignment enthusiastically and expressed their thoughts in multiple ways, such as poetry, illustration, personal narrative, videos, etc. The content analysis revealed that there could be seven dimensions to looking at entrepreneurship as a phenomenon. They are 1) entrepreneurial traits, 2) entrepreneurship as a journey, 3) value creation by entrepreneurs in terms of economic and social value, 4) entrepreneurial role models, 5) new business ideas and innovations, 6) personal entrepreneurial experiences and aspirations, and 7) entrepreneurial ecosystem. The study concludes that an implicit approach to facilitate entrepreneurship education helps in understanding it as a live phenomenon. It also encourages students to apply divergent and convergent thinking. It also helps in triggering new business ideas or stimulating the entrepreneurial aspirations of the students. The significance of the study lies in the application of implicit theories in the classroom to make higher education more engaging and effective.Keywords: co-creation of content, divergent thinking, entrepreneurship education, implicit theory
Procedia PDF Downloads 743728 Enhancing English Language Learning through Learners Cultural Background
Authors: A. Attahiru, Rabi Abdullahi Danjuma, Fatima Bint
Abstract:
Language and culture are two concepts which are closely related that one affects the other. This paper attempts to examine the definition of language and culture by discussing the relationship between them. The paper further presents some instructional strategies for the teaching of language and culture as well as the influence of culture on language. It also looks at its implication to language education and finally some recommendation and conclusion were drawn.Keywords: culture, language, relationship, strategies, teaching
Procedia PDF Downloads 4153727 Increasing the Dialogue in Workplaces Enhances the Age-Friendly Organisational Culture and Helps Employees Face Work-Related Dilemmas
Authors: Heli Makkonen, Eini Hyppönen
Abstract:
The ageing of employees, the availability of workforce, and employees’ engagement in work are today’s challenges in the field of health care and social services, and particularly in the care of older people. Therefore, it is important to enhance both the attractiveness of the work in the field of older people’s care and the retention of employees in the field, and also to pay attention to the length of careers. The length of careers can be affected, for example, by developing an age-friendly organisational culture. Changing the organisational culture in a workplace is, however, a slow process which requires engagement from employees and enhanced dialogue between employees. This article presents an example of age-friendly organisational culture in an older people’s care unit and presents the results of the development of this organisational culture to meet the identified development challenges. In this research-based development process, cycles used in action research were applied. Three workshops were arranged for employees in a service home for older people. The workshops worked as interventions, and the employees and their manager were given several consecutive assignments to be completed between them. In addition to workshops, the employees benchmarked two other service homes. In the workshops, data was collected by observing and documenting the conversations. After that, thematic analysis was used to identify the factors connected to an age-friendly organisational culture. By analysing the data and comparing it to previous studies, some dilemmas we recognised that were hindering or enhancing the attractiveness of work and the retention of employees in this nursing home. After each intervention, the process was reflected and evaluated, and the next steps were planned. The areas of development identified in the study were related to, for example, the flexibility of work, holistic ergonomics, the physical environment at the workplace, and the workplace culture. Some of the areas of development were taken over by the work community and carried out in cooperation with e.g. occupational health care. We encouraged the work community, and the employees provided us with information about their progress. In this research project, the focus was on the development of the workplace culture and, in particular, on the development of the culture of interaction. The workshops showed employees’ attitudes and strong opinions, which can be a challenge from the point of view of the attractiveness of work and the retention of employees in the field. On the other hand, the data revealed that the work community has an interest in developing the dialogue in the work community. Enhancing the dialogue gave the employees the opportunity and resources to face even challenging dilemmas related to the attractiveness of work and the retention of employees in the field. The psychological safety was also enhanced at the same time. The results of this study are part of a broader study that aims at building a model for extending older employees’ careers.Keywords: age-friendliness, attractiveness of work, dialogue, older people, organisational culture, workplace culture
Procedia PDF Downloads 763726 Understanding Music through the Framework of Feminist Confessional Literary Criticism: Heightening Audience Identification and Prioritising the Female Voice
Authors: Katharine Pollock
Abstract:
Feminist scholars assert that a defining aspect of feminist confessional literature is that it expresses both an individual and communal identity, one which is predicated on the commonly-shared aspects of female experience. Reading feminist confessional literature in this way accommodates a plurality of readerly experiences and textual interpretations. It affirms the individual whilst acknowledging those experiences which bind women together, and refuses traditional objective criticism. It invites readers to see themselves reflected in the text, and encourages them to share their own stories. Similarly, music which communicates women’s personal experience, fictive or not, expresses a dual identity. There is an inherent risk of imposing a confessional reading upon a musical or literary text. Understanding music as being multivocal in the same way as confessional literature negates this patriarchal tendency, and allows listeners to engage with both the subjective and collective aspects of a text. By hearing their own stories reflected in the music, listeners engage in an ongoing dialogic process in which female stories are prioritised. This refuses patriarchal silencing and ensures a diversity of female voices. To demonstrate the veracity of these claims, literary criticism is applied to Lily Allen’s music, and memoir My Thoughts Exactly.Keywords: confession, female, feminist, literature, music
Procedia PDF Downloads 1543725 Insect Diversity Assessment of Maize Crop (Zea mays L.) by Using Sweep Net, Pitfall Trap and Plant Inspection Methods
Authors: Muhammad Naeem Mushtaq, Muhammad Arshad, Shahid Majeed
Abstract:
Maize is known as queen of cereals because of its highest genetic yield potential and multipurpose characteristics in human being and animal diet. Maize crop visited by many major, minor, visitors and sporadic insect pests. This study was conducted during 2014 to evaluate the richness and evenness of these insect pests and their interaction with metrological conditions at University of Agriculture, Faisalabad. In this experiment, two localities were selected; one was treated with pesticide and second was untreated. Maize field visited by many insect pests. Those insect pests were collected by using three collection method: sweep net, pitfall trap and plant inspection. The data was collected weekly interval from August to October and statistically analyzed by using Shannon Index which showed the results of insect pest richness and evenness. The value of Shannon Index was higher with the increase in number of species and abundance of insects. Camponotus nearcticus was most abundant in sweep net and pitfall trap method while Rhopalosiphum maidis was abundant in plant inspection method. Temperature was negatively co-relate with the insect population in all three collection methods while the relative humidity and rainfall had varying results.Keywords: abundance, evenness, maize, richness
Procedia PDF Downloads 2213724 Application of the Sufficiency Economy Philosophy to Integrated Instructional Model of In-Service Teachers of Schools under the Project Initiated by H.R.H Princess in Maha Chakri Sirindhorn, Nakhonnayok Educational Service Area Office
Authors: Kathaleeya Chanda
Abstract:
The schools under the Project Initiated by H.R.H Princess in Maha Chakri Sirindhorn in Nakhonnayok Educational Service Area Office are the small schools, situated in a remote and undeveloped area.Thus, the school-age youth didn’t have or have fewer opportunities to study at the higher education level which can lead to many social and economic problems. This study aims to solve these educational issues of the schools, under The Project Initiated by H.R.H Princess in Maha Chakri Sirindhorn, Nakhonnayok Educational Service Area Office, by the development of teachers, so that teachers could develop teaching and learning system with the ultimate goal to increase students’ academic achievement, increase the educational opportunities for the youth in the area, and help them learn happily. 154 in-service teachers from 22 schools and 4 different districts in Nakhonnayok participated in this teacher training. Most teachers were satisfied with the training content and the trainer. Thereafter, the teachers were given the test to assess the skills and knowledge after training. Most of the teachers earned a score higher than 75%. Accordingly, it can be concluded that after attending the training, teachers have a clear understanding of the contents. After the training session, the teachers have to write a lesson plan that is integrated or adapted to the Sufficiency Economy Philosophy. The teachers can either adopt intradisciplinary or interdisciplinary integration according to their actual teaching conditions in the school. Two weeks after training session, the researchers went to the schools to discuss with the teachers and follow up the assigned integrated lesson plan. It was revealed that the progress of integrated lesson plan could be divided into 3 groups: 1) the teachers who have completed the integrated lesson plan, but are concerned about the accuracy and consistency, 2) teachers who almost complete the lesson plan or made a great progress but are still concerned, confused in some aspects and not fill in the details of the plan, and 3), the teachers who made few progress, are uncertain and confused in many aspects, and may had overloaded tasks from their school. However, a follow-up procedure led to the commitment of teachers to complete the lesson plan. Regarding student learning assessment, from an experiment teaching, most of the students earned a score higher than 50 %. The rate is higher than the one from actual teaching. In addition, the teacher have assessed that the student is happy, enjoys learning, and providing a good cooperates in teaching activities. The students’ interview about the new lesson plan shows that they are happy with it, willing to learn, and able to apply such knowledge in daily life. Integrated lesson plan can increases the educational opportunities for youth in the area.Keywords: sufficiency, economy, philosophy, integrated education syllabus
Procedia PDF Downloads 1873723 Investigating Students' Understanding about Mathematical Concept through Concept Map
Authors: Rizky Oktaviana
Abstract:
The main purpose of studying lies in improving students’ understanding. Teachers usually use written test to measure students’ understanding about learning material especially mathematical learning material. This common method actually has a lack point, such that in mathematics content, written test only show procedural steps to solve mathematical problems. Therefore, teachers unable to see whether students actually understand about mathematical concepts and the relation between concepts or not. One of the best tools to observe students’ understanding about the mathematical concepts is concept map. The goal of this research is to describe junior high school students understanding about mathematical concepts through Concept Maps based on the difference of mathematical ability. There were three steps in this research; the first step was choosing the research subjects by giving mathematical ability test to students. The subjects of this research are three students with difference mathematical ability, high, intermediate and low mathematical ability. The second step was giving concept mapping training to the chosen subjects. The last step was giving concept mapping task about the function to the subjects. Nodes which are the representation of concepts of function were provided in concept mapping task. The subjects had to use the nodes in concept mapping. Based on data analysis, the result of this research shows that subject with high mathematical ability has formal understanding, due to that subject could see the connection between concepts of function and arranged the concepts become concept map with valid hierarchy. Subject with intermediate mathematical ability has relational understanding, because subject could arranged all the given concepts and gave appropriate label between concepts though it did not represent the connection specifically yet. Whereas subject with low mathematical ability has poor understanding about function, it can be seen from the concept map which is only used few of the given concepts because subject could not see the connection between concepts. All subjects have instrumental understanding for the relation between linear function concept, quadratic function concept and domain, co domain, range.Keywords: concept map, concept mapping, mathematical concepts, understanding
Procedia PDF Downloads 2713722 Evaluation of Coastal Erosion in the Jurisdiction of the Municipalities of Puerto Colombia and Tubará, Atlántico – Colombia in Google Earth Engine with Landsat and Sentinel 2 Images
Authors: Francisco Reyes, Hector Ramirez
Abstract:
In the coastal zones are home to mangrove swamps, coral reefs, and seagrass ecosystems, which are the most biodiverse and fragile on the planet. These areas support a great diversity of marine life; they are also extraordinarily important for humans in the provision of food, water, wood, and other associated goods and services; they also contribute to climate regulation. The lack of an automated model that generates information on the dynamics of changes in coastlines and coastal erosion is identified as a central problem. Coastlines were determined from 1984 to 2020 on the Google Earth platform Engine from Landsat and Sentinel images, using the Normalized Differential Water Index (MNDWI) and Digital Shoreline Analysis System (DSAS) v5.0. Starting from the 2020 coastline, the 10-year prediction (Year 2031) was determined with the erosion of 238.32 hectares and an accretion of 181.96 hectares, while the 20-year prediction (Year 2041) will be presented an erosion of 544.04 hectares and an accretion of 133.94 hectares. The erosion and accretion of Playa Muelle in the municipality of Puerto Colombia were established, which will register the highest value of erosion. The coverage that presented the greatest change was that of artificialized Territories.Keywords: coastline, coastal erosion, MNDWI, Google Earth Engine, Colombia
Procedia PDF Downloads 1203721 Discrimination Against Popular Religiosity in the Dominican Republic
Authors: Sterlyn Poueriet Gil
Abstract:
Through the years, the construction of cultural identity in the Dominican Republic has been subject to multiple unfavorable conditions fostered by the elites. These conditions have led to the loss of a pattern that lasts over time; leaving this as a result of inconsistency and the diversity of elements that at first are theses and antitheses and gives form to the complexity of what we can call: "the culture of a people that tries to reinvent itself in each social-historical moment". Religion is one of those cultural elements that does not escape the will of the elites. In the country, there are multiple religious groups that, in one way or another, represent what the people are, their ancestral customs, their philosophy, and even their strengths as groups of a certain social environment. However, these have always been marginalized and discriminated against by the country's official religion and their respective denominations. The objective of this research was to verify to what extent interreligious discrimination was real, moving from the assumption to scientific evidence through the application of research techniques such as the survey, fieldwork, and qualitative analysis of the collected evidence, the supremacy of the dominant religion condemns its rites and in many cases the person himself. In many communities, freedom of worship is reserved for traditional groups, having cases in the country where the manifestations of rites such as the "gagá" and the "prillé" have been prohibited, considering them as diabolical and primitive practices; this seeks to deny the roots of a people marked by poverty and social conflicts but remains firm in the will to be.Keywords: cultural identity, freedom of worship, gagá, popular demonstrations
Procedia PDF Downloads 1763720 Multi-Labeled Aromatic Medicinal Plant Image Classification Using Deep Learning
Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih
Abstract:
Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network
Procedia PDF Downloads 1873719 Rationalizing the Utilization of Interactive Engagement Strategies in Teaching Specialized Science Courses of STEM and GA Strands in the Academic Track of Philippine Senior High School Curriculum
Authors: Raul G. Angeles
Abstract:
The Philippine government instituted major reforms in its educational system. The Department of Education pushes the K to 12 program that makes kindergarten mandatory and adds two years of senior high school to the country's basic education. In essence, the students’ stay in basic education particularly those who are supposedly going to college is extended. The majority of the students expressed that they will be taking the Academic Track of the Senior High School curriculum specifically the Science, Technology, Engineering and Mathematics (STEM) and General Academic (GA) strands. Almost certainly, instruction should match the students' styles and thus through this descriptive study a city survey was conducted to explore the teaching strategies preferences of junior high school students and teachers who will be promoted to senior high school during the Academic Year 2016-2017. This study was conducted in selected public and private secondary schools in Metro Manila. Questionnaires were distributed to students and teachers; and series of follow-up interviews were also carried out to generate additional information. Preferences of students are centered on employing innovations such as technology, cooperative and problem-based learning. While the students will still be covered by basic education their interests in science are sparking to a point where the usual teaching styles may no longer work to them and for that cause, altering the teaching methods is recommended to create a teacher-student style matching. Other effective strategies must likewise be implemented.Keywords: curriculum development, effective teaching strategies, problem-based learning, senior high school, science education, technology
Procedia PDF Downloads 2593718 Status and Image of the Nurse as Perceived by the Public
Authors: Salam Hadid, Mohammad Khatib
Abstract:
The International Council of Nurses-ICN defined nursing as a sphere integrating autonomous and collaborative care intended for the individual, family and community within and outside of the care setting. Nursing as a care profession has developed broadly over recent decades in terms of its essentials, expertise and primarily academically. Despite the impressive growth of the profession, there is still extreme diversity in the public’s perceptions and opinions of the profession and its professionals and in the knowledge on the fundamentals of its true function and spheres of engagement. The current study examines the existing knowledge among the general population regarding the nursing profession. The population consisted of 498 respondents, 236 women and 262 men, age 18-81. The respondents noted that nursing focuses on the technical, and the emotional aspects and promotion of health for the patient are not the nurse’s responsibility. Most of the respondents saw nurses working mainly in hospital and community-based clinic settings. They considered nursing to be a high prestige profession in general, but less prestigious among respondents exposed to healthcare provision. Most of the respondents considered nursing to be a humane profession but without independence and with no need for academic studies. The findings are incompatible with the definition of nursing and its spheres of action as defined in the ICN Code of Ethics. Two suggestions are to work through nursing schools addressing the student nurses, as ambassadors for the profession. The second is using the healthcare encounter between the nursing staff and the public to improve the image of nurses.Keywords: ethics, nurse image, public, nursing
Procedia PDF Downloads 2953717 Play Based Practices in Early Childhood Curriculum: The Contribution of High Scope, Modern School Movement and Pedagogy of Participation
Authors: Dalila Lino
Abstract:
The power of play for learning and development in early childhood education is beyond question. The main goal of this study is to analyse how three contemporary early childhood pedagogical approaches, the High Scope, the Modern School Movement (MEM) and the Pedagogy of Participation integrate play in their curriculum development. From this main goal the following objectives emerged: (i) to characterize how play is integrated in the daily routine of the pedagogical approaches under study; (ii) to analyse the teachers’ role during children’s playing situations; (iii) to identify the types of play that children are more often involved. The methodology used is the qualitative approach and is situated under the interpretative paradigm. Data is collected through semi-structured interviews to 30 preschool teachers and through observations of typical daily routines. The participants are 30 Portuguese preschool classrooms attending children from 3 to 6 years and working with the High Scope curriculum (10 classrooms), the MEM (10 classrooms) and the Pedagogy of Participation (10 classrooms). The qualitative method of content analysis was used to analyse the data. To ensure confidentiality, no information is disclosed without participants' consent, and the interviews were transcribed and sent to the participants for a final revision. The results show that there are differences how play is integrated and promoted in the three pedagogical approaches. The teachers’ role when children are at play varies according the pedagogical approach adopted, and also according to the teachers’ understanding about the meaning of play. The study highlights the key role that early childhood curriculum models have to promote opportunities for children to play, and therefore to be involved in meaningful learning.Keywords: curriculum models, early childhood education, pedagogy, play
Procedia PDF Downloads 2073716 The Effectiveness of Using Picture Storybooks on Young English as a Foreign Language Learners for English Vocabulary Acquisition and Moral Education: A Case Study
Authors: Tiffany Yung Hsuan Ma
Abstract:
The Whole Language Approach, which gained prominence in the 1980s, and the increasing emphasis on multimodal resources in educational research have elevated the utilization of picture books in English as a foreign language (EFL) instruction. This approach underscores real-world language application, providing EFL learners with a range of sensory stimuli, including visual elements. Additionally, the substantial impact of picture books on fostering prosocial behaviors in children has garnered recognition. These narratives offer opportunities to impart essential values such as kindness, fairness, and respect. Examining how picture books enhance vocabulary acquisition can offer valuable insights for educators in devising engaging language activities conducive to a positive learning environment. This research entails a case study involving two kindergarten-aged EFL learners and employs qualitative methods, including worksheets, observations, and interviews with parents. It centers on three pivotal inquiries: (1) The extent of young learners' acquisition of essential vocabulary, (2) The influence of these books on their behavior at home, and (3) Effective teaching strategies for the seamless integration of picture storybooks into EFL instruction for young learners. The findings can provide guidance to parents, educators, curriculum developers, and policymakers regarding the advantages and optimal approaches to incorporating picture books into language instruction. Ultimately, this research has the potential to enhance English language learning outcomes and promote moral education within the Taiwanese EFL context.Keywords: EFL, vocabulary acquisition, young learners, picture book, moral education
Procedia PDF Downloads 703715 Language and Empire: A Post-Colonial Examination of Othering and Identity in Babel: An Arcane History
Authors: Essam Hegazy
Abstract:
English has solidified its role as the global lingua franca, largely due to British colonial expansion. This research investigates the use of English as a tool for Empire-building and the subjugation of colonized peoples and their languages. The objective is to examine how linguistic Anglo-hegemony contributes to the construction of otherness and identity formation, and how these processes are depicted in R.F. Kuang's novel Babel: An Arcane History. Using a post-colonial theoretical framework, this study employs textual analysis to explore the novel's portrayal of characters' conflicting loyalties to their native cultures and the British Empire. Key methods include identifying themes of linguistic dominance, othering, and identity conflict through close reading and annotation. The analysis is contextualized with historical and cultural perspectives to understand the broader implications of these themes. The findings reveal that linguistic hegemony is a central mechanism of colonial power, deeply affecting the characters' sense of identity and belonging. The study uncovers how the imposition of English creates internalized conflicts and reinforces social hierarchies. This research highlights the need to challenge hegemonic structures to preserve authentic identities and promote cultural diversity.Keywords: linguistic hegemony, otherness, identity formation, colonialism, imperialism
Procedia PDF Downloads 243714 Facilitating Active Reading Strategies through Caps Chart to Foster Elementary EFL Learners’ Reading Skills and Reading Competency
Authors: Michelle Bulawan, Mei-Hua Chen
Abstract:
Reading comprehension is crucial for acquiring information, analyzing critically, and achieving academic proficiency. However, there is a lack of growth in reading comprehension skills beyond fourth grade. The developmental shift from "learning to read" to "reading to learn" occurs around this stage. Factual knowledge and diverse views in articles enhance reading comprehension abilities. Nevertheless, some face difficulties due to evolving textual requirements, such as expanding vocabulary and using longer, more complex terminology. Most research on reading strategies has been conducted at the tertiary and secondary levels, while few have focused on the elementary levels. Furthermore, the use of character, ask, problem, solution (CAPS) charts in teaching reading has also been hardly explored. Thus, the researcher decided to explore the facilitation of active reading strategies through the CAPS chart and address the following research questions: a) What differences existed in elementary EFL learners' reading competency among those who engaged in active reading strategies and those who did not? b) What are the learners’ metacognitive skills of those who engage in active reading strategies and those who do not, and what are their effects on their reading competency? c) For those participants who engage in active reading activities, what are their perceptions about incorporating active reading activities into their English classroom learning? Two groups of elementary EFL learners, each with 18 students of the same level of English proficiency, participated in this study. Group A served as the control group, while Group B served as the experimental group. Two teachers also participated in this research; one of them was the researcher who handled the experimental group. The treatment lasts for one whole semester or seventeen weeks. In addition to the CAPS chart, the researcher also used the metacognitive awareness of reading strategy inventory (MARSI) and a ten-item, five-point Likert scale survey.Keywords: active reading, EFL learners, metacognitive skills, reading competency, student’s perception
Procedia PDF Downloads 913713 An Integrated Label Propagation Network for Structural Condition Assessment
Authors: Qingsong Xiong, Cheng Yuan, Qingzhao Kong, Haibei Xiong
Abstract:
Deep-learning-driven approaches based on vibration responses have attracted larger attention in rapid structural condition assessment while obtaining sufficient measured training data with corresponding labels is relevantly costly and even inaccessible in practical engineering. This study proposes an integrated label propagation network for structural condition assessment, which is able to diffuse the labels from continuously-generating measurements by intact structure to those of missing labels of damage scenarios. The integrated network is embedded with damage-sensitive features extraction by deep autoencoder and pseudo-labels propagation by optimized fuzzy clustering, the architecture and mechanism which are elaborated. With a sophisticated network design and specified strategies for improving performance, the present network achieves to extends the superiority of self-supervised representation learning, unsupervised fuzzy clustering and supervised classification algorithms into an integration aiming at assessing damage conditions. Both numerical simulations and full-scale laboratory shaking table tests of a two-story building structure were conducted to validate its capability of detecting post-earthquake damage. The identifying accuracy of a present network was 0.95 in numerical validations and an average 0.86 in laboratory case studies, respectively. It should be noted that the whole training procedure of all involved models in the network stringently doesn’t rely upon any labeled data of damage scenarios but only several samples of intact structure, which indicates a significant superiority in model adaptability and feasible applicability in practice.Keywords: autoencoder, condition assessment, fuzzy clustering, label propagation
Procedia PDF Downloads 973712 Findings: Impact of a Sustained Health Promoting Workplace on Stock Price Performance and Beta; A Singapore Case
Authors: Wee Tong Liaw, Elaine Wong Yee Sing
Abstract:
The main objective and focus of this study are to establish the significance of a sustained health promoting workplace on stock and portfolio returns focusing on companies listed on the Singapore stock exchange, using a two-factor model comprising of the single factor CAPM and a 'health promoting workplace' factor. The 'health promoting workplace' factor represents the excess returns derived between two portfolios of component stocks that, when combined, would represent a top tier stock market index in Singapore, namely the STI index. The first portfolio represents companies that are independently assessed by the Singapore’s Health Award, SHA, to have a sustained and comprehensive health promoting workplace (SHA-STI portfolio) and the second portfolio represents companies that had not been independently assessed (Non-SHA STI portfolio). Since 2001, many companies in Singapore have voluntarily participated in the bi-annual Singapore HEALTH Award initiated by the Health Promotion Board of Singapore (HPB). The Singapore HEALTH Award (SHA), is an industry-wide award and assessment process. SHA assesses and recognizes employers in Singapore for implementing a comprehensive and sustainable health promotion programme at their workplaces. When using a ten year holding period instead of a one year holding period, excess returns in the SHA-STI portfolio over Non-SHA STI portfolio were consistently being observed over all test periods, during 2001 to 2013. In addition, when applied to the SHA-STI portfolio, results from the Two Factor Model consistently revealed higher explanatory powers across all test periods for the portfolio as well as all the individual component stocks in SHA-STI portfolio, than the single factor CAPM model. However, with respect to attaining higher level of achievement in the Singapore Health Award, this study did not show any incentive for selecting listed companies that have achieved a higher level of award. Results from this study would give further insights to investors and fund managers alike who intend to consider health promoting workplace as a risk factor in their stock or portfolio selection process, in particular for investors who have a preference for STI’s component stocks and with a longer investment horizon. Key micro factors like management abilities, business development strategies and production capabilities that meet the needs of market would create the demand for a company’s product(s) or service(s) and consequently contribute to its top line and profitability. Thereafter, the existence of a sustainable health promoting workplace would be a key catalytic factor in sustaining a productive workforce needed to support the continued success of a profitable business.Keywords: asset pricing model, company's performance, stock returns, financial risk factor, sustained health promoting workplace
Procedia PDF Downloads 1693711 A Methodology Based on Image Processing and Deep Learning for Automatic Characterization of Graphene Oxide
Authors: Rafael do Amaral Teodoro, Leandro Augusto da Silva
Abstract:
Originated from graphite, graphene is a two-dimensional (2D) material that promises to revolutionize technology in many different areas, such as energy, telecommunications, civil construction, aviation, textile, and medicine. This is possible because its structure, formed by carbon bonds, provides desirable optical, thermal, and mechanical characteristics that are interesting to multiple areas of the market. Thus, several research and development centers are studying different manufacturing methods and material applications of graphene, which are often compromised by the scarcity of more agile and accurate methodologies to characterize the material – that is to determine its composition, shape, size, and the number of layers and crystals. To engage in this search, this study proposes a computational methodology that applies deep learning to identify graphene oxide crystals in order to characterize samples by crystal sizes. To achieve this, a fully convolutional neural network called U-net has been trained to segment SEM graphene oxide images. The segmentation generated by the U-net is fine-tuned with a standard deviation technique by classes, which allows crystals to be distinguished with different labels through an object delimitation algorithm. As a next step, the characteristics of the position, area, perimeter, and lateral measures of each detected crystal are extracted from the images. This information generates a database with the dimensions of the crystals that compose the samples. Finally, graphs are automatically created showing the frequency distributions by area size and perimeter of the crystals. This methodological process resulted in a high capacity of segmentation of graphene oxide crystals, presenting accuracy and F-score equal to 95% and 94%, respectively, over the test set. Such performance demonstrates a high generalization capacity of the method in crystal segmentation, since its performance considers significant changes in image extraction quality. The measurement of non-overlapping crystals presented an average error of 6% for the different measurement metrics, thus suggesting that the model provides a high-performance measurement for non-overlapping segmentations. For overlapping crystals, however, a limitation of the model was identified. To overcome this limitation, it is important to ensure that the samples to be analyzed are properly prepared. This will minimize crystal overlap in the SEM image acquisition and guarantee a lower error in the measurements without greater efforts for data handling. All in all, the method developed is a time optimizer with a high measurement value, considering that it is capable of measuring hundreds of graphene oxide crystals in seconds, saving weeks of manual work.Keywords: characterization, graphene oxide, nanomaterials, U-net, deep learning
Procedia PDF Downloads 1603710 Importance of Continuous Professional Development for Teacher Educators in Myanmar Education College
Authors: Moet Moet Myint Lay
Abstract:
Continuing professional development involves acquiring new knowledge and skills for current work and improving career opportunities in the field through continuing education (OECD, 2000). This article examines the effectiveness of CPD in improving teacher quality and the resulting need for CPD for teacher educators in Myanmar. The purpose of this study is to explore a deeper understanding of teacher-to-teacher continuing professional development in improving teacher education programs. Research questions: (1) How do teachers in Myanmar understand the idea of continuous professional development for professional development? (2) What CPD activities are required for all teachers in teachers' colleges? (3) What are the main challenges of CPD implementation in Myanmar Education College? A qualitative method using semi-structured interviews was used in this study. Seven teacher educators from Mandalay Education College participated in this study. There are three male teacher educators and four female teacher educators. All participants who responded to the semi-structured interviews were between 29 and 45 years old.The interviews revealed that professional development involves acquiring the necessary pedagogical knowledge and skills to encourage students to think creatively and critically. Teachers must participate in a variety of activities, including professional interviews, lesson study, training programs, workshops, and seminars. All results showed that teachers need English and ICT skills for teaching and learning, including extended ICT courses for those who have completed a foundation course, access to e-libraries, and inclusive education (including language teaching and learning), facilitate the assessment (formative and summative), practicum, mentoring, and coaching skills. The study concludes with practical findings that suggest an urgent need for CPD activities for teachers.Keywords: continuous professional development, teacher educator, teacher training program), mentoring
Procedia PDF Downloads 583709 Emotion-Convolutional Neural Network for Perceiving Stress from Audio Signals: A Brain Chemistry Approach
Authors: Anup Anand Deshmukh, Catherine Soladie, Renaud Seguier
Abstract:
Emotion plays a key role in many applications like healthcare, to gather patients’ emotional behavior. Unlike typical ASR (Automated Speech Recognition) problems which focus on 'what was said', it is equally important to understand 'how it was said.' There are certain emotions which are given more importance due to their effectiveness in understanding human feelings. In this paper, we propose an approach that models human stress from audio signals. The research challenge in speech emotion detection is finding the appropriate set of acoustic features corresponding to an emotion. Another difficulty lies in defining the very meaning of emotion and being able to categorize it in a precise manner. Supervised Machine Learning models, including state of the art Deep Learning classification methods, rely on the availability of clean and labelled data. One of the problems in affective computation is the limited amount of annotated data. The existing labelled emotions datasets are highly subjective to the perception of the annotator. We address the first issue of feature selection by exploiting the use of traditional MFCC (Mel-Frequency Cepstral Coefficients) features in Convolutional Neural Network. Our proposed Emo-CNN (Emotion-CNN) architecture treats speech representations in a manner similar to how CNN’s treat images in a vision problem. Our experiments show that Emo-CNN consistently and significantly outperforms the popular existing methods over multiple datasets. It achieves 90.2% categorical accuracy on the Emo-DB dataset. We claim that Emo-CNN is robust to speaker variations and environmental distortions. The proposed approach achieves 85.5% speaker-dependant categorical accuracy for SAVEE (Surrey Audio-Visual Expressed Emotion) dataset, beating the existing CNN based approach by 10.2%. To tackle the second problem of subjectivity in stress labels, we use Lovheim’s cube, which is a 3-dimensional projection of emotions. Monoamine neurotransmitters are a type of chemical messengers in the brain that transmits signals on perceiving emotions. The cube aims at explaining the relationship between these neurotransmitters and the positions of emotions in 3D space. The learnt emotion representations from the Emo-CNN are mapped to the cube using three component PCA (Principal Component Analysis) which is then used to model human stress. This proposed approach not only circumvents the need for labelled stress data but also complies with the psychological theory of emotions given by Lovheim’s cube. We believe that this work is the first step towards creating a connection between Artificial Intelligence and the chemistry of human emotions.Keywords: deep learning, brain chemistry, emotion perception, Lovheim's cube
Procedia PDF Downloads 154