Search results for: non-formal learning contexts

Authors: Ali Mahfouz

Abstract:

Egypt's cultural heritage and artistic riches find themselves at a complex intersection of preservation and urban development, where they face intricate challenges exacerbated by climate change, pollution, urbanization, and construction activities. In this research, it delves into the multifaceted dynamics involved in conserving Egypt's heritage within urban contexts, spotlighting the historic Cairo cemetery as a poignant and timely case study. The historic Cairo cemetery serves as a repository of priceless cultural assets, housing the final resting places of public figures, artists, historians, politicians, and other luminaries. These graves are adorned with magnificent artworks and rare tombstones, collectively representing an irreplaceable slice of Egypt's history and culture. Yet, the looming threat of demolition to make way for new infrastructure projects underscores the delicate equilibrium that preservation efforts must maintain in the face of urban development pressures. This paper illuminates the collaborative efforts of historians, intellectuals, and civil society organizations who are determined to forestall the destruction of this invaluable cultural heritage. Their initiatives, driven by a shared commitment to documenting and safeguarding the cemetery's treasures, underscore the urgent imperative of protecting Egypt's cultural legacy. Through this case study, It gain insights into how Egypt navigates the challenges of preserving its rich heritage amidst urban expansion and a changing climate, emphasizing the broader importance of heritage conservation in an evolving world.

Keywords: Egypt’s cultural heritage, urban development, historic Cairo cemetery, tombstone artworks, demolition threat, heritage conservation, civil society initiatives

Procedia PDF Downloads 62

Authors: Jacqueline Jasmine Kumar

Abstract:

This paper seeks to challenge the predominate Western-centric paradigm concerning empathy by conducting an exploration of its presence within both Western and Eastern philosophical traditions. The primary focus of this inquiry is the examination of the Indian yogic tradition, encompassing the four yogas: bhakti (love/devotion), karma (action), jnāna (knowledge), and rāja (psychic control). Through this examination, it is demonstrated that empathy does not exclusively originate from Western philosophical thought. Rather than superimposing the Western conceptualization of empathy onto the tenets of Indian philosophy, this study endeavours to unearth a distinct array of ideas and concepts within the four yogas, which significantly contribute to our comprehension of empathy as a universally relevant phenomenon. To achieve this objective, an innovative approach is adopted, delving into various facets of empathy, including the propositional, affective/intuitive, perspective-taking, and actionable dimensions. This approach intentionally deviates from conventional Western frameworks, shifting the emphasis towards lived morally as opposed to engagement in abstract theoretical discourse. While it is acknowledged that the explicit term “empathy” may not be overly articulated within the yogic tradition, a scrupulous examination reveals the underlying substance and significance of this phenomenon. Throughout this comparative analysis, the paper aims to lay a robust foundation for the discourse of empathy within the contexts of the human experience. By assimilating insights gleaned from the Indian yogic tradition, it contributes to the expansion of our comprehension of empathy, enabling an exploration of its multifaceted dimensions. Ultimately, this scholarly endeavour facilitates the development of a more comprehensive and inclusive perspective on empathy, transcending cultural boundaries and enriching our collective repository of knowledge.

Keywords: Bhakti, Yogic, Jnana, Karma

Procedia PDF Downloads 59

Authors: Abdulmjeid Aljerawi

Abstract:

This study aimed to investigate the students' attitudes towards the use of social networking in education. Due to the nature of the study, and on the basis of its problem, objectives, and questions, the researcher used the descriptive approach. An appropriate questionnaire was prepared and validity and reliability were ensured. The questionnaire was then applied to the study sample of 434 students from King Saud University.

Keywords: social networks, education, learning, students

Procedia PDF Downloads 263

Authors: Riin Seema

Abstract:

Guidance and counseling as a whole-school responsibility is a global trend. Counseling is a specific competence, that consist of cognitive, emotional, attitudinal, and behavioral components. To authors best knowledge, there are no self-assessment scales for teachers in the whole world to measure teachers’ counseling competency. In 2016 an Estonian scale on teachers counseling competence was developed during an Interdisciplinary Project at Tallinn University. The team consisted of 10 interdisciplinary students (psychology, nursery school, special and adult education) and their supervisor. In 2017 another international Interdisciplinary Project was carried out for adapting the scale in English for international students. Firstly, the Estonian scale was translated by 2 professional translators, and then a group of international Erasmus students (again from psychology, nursery school, special and adult education) selected the most suitable translation for the scale. The developed ‘Teacher’s Counselling Competence Self-Efficacy Scale’ measures teacher’s self-efficacy beliefs in their own competence to perform different counseling tasks (creating a counseling relationship, using different reflection techniques, etc.). The scale consists of 47 questions in a 5-point numeric scale. The scale is created based on counseling theory and scale development and validation theory. The scale has been used as a teaching and learning material for counseling courses by 174 Estonian and 10 international student teachers. After filling out the scale, the students also reflected on the scale and their own counseling competencies. The study showed that the scale is unidimensional and has an excellent Cronbach alpha coefficient. Student’s qualitative feedback on the scale has been very positive, as the scale supports their self-reflection. In conclusion, the developed ‘Teacher’s Counselling Competence Self-Efficacy Scale’ is a useful tool for supporting student teachers’ learning.

Keywords: competency, counseling, self-efficacy, teacher students

Procedia PDF Downloads 130

Authors: Klara Królewiak-Detsi, Anna Orylska, Anna Gorgolewska, Marta Boczkowska, Agata Graczykowska

Abstract:

This study investigates the communication between students and teachers in inclusive education in Poland. Specifically, we examine the communication and interaction of students with special educational needs during online learning compared to traditional face-to-face instruction. Our research questions are (1) how children with special educational needs communicate with their teachers and peers during online learning, and (2) what strategies can improve their communication skills. We conducted five focus groups with: (1) 55 children with special educational needs, (2) 65 typically developing pupils, (3) 28 professionals (psychologists and special education therapists), (4) 16 teachers, and (5) 16 parents of children with special educational needs. Our analysis focused on primary schools and used thematic analysis according to the 6-step procedure of Braun and Clarke. Our findings reveal that children with disabilities faced more difficulties communicating and interacting with others online than in face-to-face lessons. The online tools used for education were not adapted to the needs of children with disabilities, and schools lacked clear guidelines on how to pursue inclusive education online. Based on the results, we offer recommendations for online communication training and tools that are dedicated to children with special educational needs. Additionally, our results demonstrate that typically developing pupils are better in interpersonal relations and more often and effectively use social support. Children with special educational needs had similar emotional and communication challenges compared to their typically developing peers. In conclusion, our study highlights the importance of providing adequate support for the online education of children with special educational needs in inclusive classrooms.

Keywords: Inclusive education, Special educational needs, Social skills development, Online communication

Procedia PDF Downloads 108

Authors: Sade Ogundipe

Abstract:

The private healthcare sector in the United Kingdom has experienced unprecedented challenges during times of crisis, necessitating effective leadership adaptability. This qualitative study delves into the dynamic landscape of leadership within the sector, particularly during crises, employing the lenses of complexity theory and institutional theory to unravel the intricate mechanisms at play. Through in-depth interviews with 25 various levels of leaders in the UK private healthcare sector, this research explores how leaders in UK private healthcare organizations navigate complex and often chaotic environments, shedding light on their adaptive strategies and decision-making processes during crises. Complexity theory is used to analyze the complicated, volatile nature of healthcare crises, emphasizing the need for adaptive leadership in such contexts. Institutional theory, on the other hand, provides insights into how external and internal institutional pressures influence leadership behavior. Findings from this study highlight the multifaceted nature of leadership adaptability, emphasizing the significance of leaders' abilities to embrace uncertainty, engage in sensemaking, and leverage the institutional environment to enact meaningful changes. Furthermore, this research sheds light on the challenges and opportunities that leaders face when adapting to crises within the UK private healthcare sector. The study's insights contribute to the growing body of literature on leadership in healthcare, offering practical implications for leaders, policymakers, and stakeholders within the UK private healthcare sector. By employing the dual perspectives of complexity theory and institutional theory, this research provides a holistic understanding of leadership adaptability in the face of crises, offering valuable guidance for enhancing the resilience and effectiveness of healthcare leadership within this vital sector.

Keywords: leadership, adaptability, decision-making, complexity, complexity theory, institutional theory, organizational complexity, complex adaptive system (CAS), crises, healthcare

Procedia PDF Downloads 39

Authors: Thomas Trouton, Sebastian Tanner, Manvir Sandher

Abstract:

The use of simulation in undergraduate and postgraduate medical curricula is ever-growing, is a useful addition to the traditional apprenticeship model of learning within medical education, and better prepares graduates for the team-based approach to healthcare seen in real-life clinical practice. As a learning tool, however, undergraduate medical students often have little understanding of the theory behind the use of medical simulation and have little experience in planning and delivering their own simulated teaching sessions. We designed and implemented a student-selected component (SSC) as part of the undergraduate medical curriculum at the University of Buckingham Medical School to introduce students to the concepts behind the use of medical simulation in education and allow them to plan and deliver their own simulated medical scenario to their peers. The SSC took place over a 2-week period in the 3rd year of the undergraduate course. There was a mix of lectures, seminars and interactive group work sessions, as well as hands-on experience in the simulation suite, to introduce key concepts related to medical simulation, including technical considerations in simulation, human factors, debriefing and troubleshooting scenarios. We evaluated the success of our SSC using “Net Promotor Scores” (NPS) to assess students’ confidence in planning and facilitating a simulation-based teaching session, as well as leading a debrief session. In all three domains, we showed an increase in the confidence of the students. We also showed an increase in confidence in the management of common medical emergencies as a result of the SSC. Overall, the students who chose our SSC had the opportunity to learn new skills in medical education, with a particular focus on the use of simulation-based teaching, and feedback highlighted that a number of students would take these skills forward in their own practice. We demonstrated an increase in confidence in several domains related to the use of medical simulation in education and have hopefully inspired a new generation of medical educators.

Keywords: simulation, SSC, teaching, medical students

Procedia PDF Downloads 108

Authors: Michael Smalenberger

Abstract:

Intelligent tutoring systems (ITS) are computer-based platforms which can incorporate artificial intelligence to provide step-by-step guidance as students practice problem-solving skills. ITS can replicate and even exceed some benefits of one-on-one tutoring, foster transactivity in collaborative environments, and lead to substantial learning gains when used to supplement the instruction of a teacher or when used as the sole method of instruction. A common facet of many ITS is their use of Bayesian Knowledge Tracing (BKT) to estimate parameters necessary for the implementation of the artificial intelligence component, and for the probability of mastery of a knowledge component relevant to the ITS. While various techniques exist to estimate these parameters and probability of mastery, none directly and reliably ask the user to self-assess these. In this study, 111 undergraduate students used an ITS in a college-level introductory statistics course for which detailed transaction-level observations were recorded, and users were also routinely asked direct questions that would lead to such a self-assessment. Comparisons were made between these self-assessed values and those obtained using commonly used estimation techniques. Our findings show that such self-assessments are particularly relevant at the early stages of ITS usage while transaction level data are scant. Once a user’s transaction level data become available after sufficient ITS usage, these can replace the self-assessments in order to eliminate the identifiability problem in BKT. We discuss how these findings are relevant to the number of exercises necessary to lead to mastery of a knowledge component, the associated implications on learning curves, and its relevance to instruction time.

Keywords: Bayesian Knowledge Tracing, Intelligent Tutoring System, in vivo study, parameter estimation

Procedia PDF Downloads 160

Authors: Karen Koellner, Nanette Seago, Jennifer Jacobs, Helen Garnier

Abstract:

Although studies of teacher professional development (PD) are prevalent, surprisingly most have only produced incremental shifts in teachers’ learning and their impact on students. There is a critical need to understand what teachers take up and use in their classroom practice after attending PD and why we often do not see greater changes in learning and practice. This paper is based on a mixed methods efficacy study of the Learning and Teaching Geometry (LTG) video-based mathematics professional development materials. The extent to which the materials produce a beneficial impact on teachers’ mathematics knowledge, classroom practices, and their students’ knowledge in the domain of geometry through a group-randomized experimental design are considered. Included is a close-up examination of a small group of teachers to better understand their interpretations of the workshops and their classroom uptake. The participants included 103 secondary mathematics teachers serving grades 6-12 from two US states in different regions. Randomization was conducted at the school level, with 23 schools and 49 teachers assigned to the treatment group and 18 schools and 54 teachers assigned to the comparison group. The case study examination included twelve treatment teachers. PD workshops for treatment teachers began in Summer 2016. Nine full days of professional development were offered to teachers, beginning with the one-week institute (Summer 2016) and four days of PD throughout the academic year. The same facilitator-led all of the workshops, after completing a facilitator preparation process that included a multi-faceted assessment of fidelity. The overall impact of the LTG PD program was assessed from multiple sources: two teacher content assessments, two PD embedded assessments, pre-post-post videotaped classroom observations, and student assessments. Additional data were collected from the case study teachers including additional videotaped classroom observations and interviews. Repeated measures ANOVA analyses were used to detect patterns of change in the treatment teachers’ content knowledge before and after completion of the LTG PD, relative to the comparison group. No significant effects were found across the two groups of teachers on the two teacher content assessments. Teachers were rated on the quality of their mathematics instruction captured in videotaped classroom observations using the Math in Common Observation Protocol. On average, teachers who attended the LTG PD intervention improved their ability to engage students in mathematical reasoning and to provide accurate, coherent, and well-justified mathematical content. In addition, the LTG PD intervention and instruction that engaged students in mathematical practices both positively and significantly predicted greater student knowledge gains. Teacher knowledge was not a significant predictor. Twelve treatment teachers self-selected to serve as case study teachers to provide additional videotapes in which they felt they were using something from the PD they learned and experienced. Project staff analyzed the videos, compared them to previous videos and interviewed the teachers regarding their uptake of the PD related to content knowledge, pedagogical knowledge and resources used. The full paper will include the case study of Ana to illustrate the factors involved in what teachers take up and use from participating in the LTG PD.

Keywords: geometry, mathematics professional development, pedagogical content knowledge, teacher learning

Procedia PDF Downloads 110

Authors: Joy Chadwick

Abstract:

There is no doubt that classrooms of today are more complex and diverse than ever before. Preparing teacher candidates to meet these challenges is essential to ensure the retention of teachers within the profession and to ensure that graduates begin their teaching careers with the knowledge and understanding of how to effectively meet the diversity of students they will encounter. Creating inclusive classrooms requires teachers to have a repertoire of effective instructional skills and strategies. Teachers must also have the mindset to embrace diversity and value the uniqueness of individual students in their care. This qualitative study analyzed teacher candidates' experiences as they completed a fourteen-week teaching practicum while simultaneously completing a university course focused on inclusive pedagogy. The research investigated the challenges and successes teacher candidates had in navigating the translation of theory related to inclusive pedagogy into their teaching practice. Applying threshold concept theory as a framework, the research explored the troublesome concepts, liminal spaces, and transformative experiences as connected to inclusive practices. Threshold concept theory suggests that within all disciplinary fields, there exists particular threshold concepts that serve as gateways or portals into previously inaccessible ways of thinking and practicing. It is in these liminal spaces that conceptual shifts in thinking and understanding and deep learning can occur. The threshold concept framework provided a lens to examine teacher candidate struggles and successes with the inclusive education course content and the application of this content to their practicum experiences. A qualitative research approach was used, which included analyzing twenty-nine course reflective journals and six follow up one-to-one semi structured interviews. The journals and interview transcripts were coded and themed using NVivo software. Threshold concept theory was then applied to the data to uncover the liminal or stuck spaces of learning and the ways in which the teacher candidates navigated those challenging places of teaching. The research also sought to uncover potential transformative shifts in teacher candidate understanding as connected to teaching in an inclusive classroom. The findings suggested that teacher candidates experienced difficulties when they did not feel they had the knowledge, skill, or time to meet the needs of the students in the way they envisioned they should. To navigate the frustration of this thwarted vision, they relied on present and previous course content and experiences, collaborative work with other teacher candidates and their mentor teachers, and a proactive approach to planning for students. Transformational shifts were most evident in their ability to reframe their perceptions of children from a deficit or disability lens to a strength-based belief in the potential of students. It was evident that through their course work and practicum experiences, their beliefs regarding struggling students shifted as they saw the value of embracing neurodiversity, the importance of relationships, and planning for and teaching through a strength-based approach. Research findings have implications for teacher education programs and for understanding threshold concepts theory as connected to practice-based learning experiences.

Keywords: inclusion, inclusive education, liminal space, teacher education, threshold concepts, troublesome knowledge

Procedia PDF Downloads 61

Authors: A. Brach

Abstract:

The architecture of modern museums in the historical center should refer to a place in a cultural, historical, urban and architectural sense, using adequate and contemporary forms of architecture. The research and architectural analysis of selected museums in Cracow were conducted to illustrate which elements were decisive for the choice of architectural form. The evaluation of selected objects took into the consideration the following aspects: continuation of the historical form, contemporary form referring to the place, the individual-author form omitting the cultural aspect of the place. The presented projects showed the compromise as positive solutions rejecting both the direct imitation or 'historical continuation' as well as an individual form focused on an abstract form. In order to carry out research and confirm the thesis, three designs of Assoc. Prof. Eng. Arch. Krzysztof Ingarden in the historic city of Cracow were selected. Despite being constructed in one city, the neighborhood and cultural contexts of the locations are completely different. The neighborhood of the historical Royal Road and gothic church with unique decorations from the Polish Art Nouveau, artist Stanislaw Wyspianski (Wyspianski Pavilion), the bend of the Vistula hosting the Japanese culture (Museum of Japanese Art and Technology Manggha) and finally the old area of a horse riding school from the Austrian Empire times (Malopolska Garden of Art). All three buildings are dedicated to the culture of Japan, Polish artist Stanislaw Wyspianski, contemporary achievements and the promotion of art at its widest sense. Important fact for this research is that there is one author of all presented projects.

Keywords: adaptation of existing buildings, architecture in cracow, modern architecture, museums located in historic center

Procedia PDF Downloads 155

Authors: Sara Fioretti

Abstract:

In the 2nd millennium BCE, maritime networks became essential to the Mediterranean lifestyle, creating an interconnected world. This phenomenon of interconnected cultures has often been misinterpreted as an “effect” of the Mycenaean “influence” without considering the complexity and role of regional and cross-cultural exchanges. This paper explores the socio-economic relationships, in both cross-cultural and potentially inter-regional settings, present within the archaeological repertoire of the southern Italian Late Bronze Age (LBA 1600 -1140 BCE). The emergence of economic relations within the connectivity of the regional settlements is explored through ceramic contexts found in the case studies Punta di Zambrone, Broglio di Trebisacce, and Nuraghe Antigori. This work-in-progress research is situated in the shifting theoretical views of the last ten years that discuss the Late Bronze Age’s connectivity through Social Networks, Entanglement, and Assertive Objects combined with a comparative statistical study of ceramic frequency distribution. Applying these theoretical frameworks with a quantitative approach demonstrates the specific regional economic relationships that shaped the cultural interactions of the Late Bronze Age. Through this intersection of theory and statistical analysis, the case studies establish a small percentage of pottery as imported, whilst assertive productions have a relatively higher quantity. Overall, the majority still adheres to regional Italian traditions. Therefore, we can dissect the rhizomatic relationships cultivated by the Italian coasts and Mycenaeans and their roles within their networks through the intersection of theoretical and statistical analysis. This research offers a new perspective on the connectivity of the Late Bronze Age relational structures.

Keywords: late bronze age, mediterranean archaeology, exchanges and trade, frequency distribution of ceramic assemblages

Procedia PDF Downloads 26

Authors: Marta Lisowska

Abstract:

The growing trend of market specialization imposes upon translators the need for proficiency in the working knowledge of specialist discourse. The notion of specialization differs from a broad general category to a highly specialized narrow field. The specialised discourse is used in the channel of communication based upon distinctive features typical for communities of practice whose co-existence is codified and hermetically locked against outsiders. Consequently, any translator deprived of professional discourse competence and social skills is incapable of providing competent translation product from source language into target language. In this paper, we report on research that explores the pedagogical practices aiming to bridge the dichotomy between the professionals and the specialist translators, while accounting for the reality of the world of professional communities entered by undergraduates on two levels: the text-based generic, and the social one. Drawing from the functional social constructivist approach, seen here as situated learning, this paper reports on the case of English-Polish, Polish-English undergraduate BA Level LSP of law translation class run in line with the simulated classroom-based and the reality-based (apprenticeship) approach. This blended method serves the purpose of introducing the young trainees to the professional world. The research provides new insights into how the LSP translation undergraduates become legitimized through discursive and social participation and engagement. The undergraduates, situated peripherally at the outset, experience their own transformation towards becoming members of these professional groups. With subjective evaluation, the trainees take a stance on this dual mode class and development of their skills. Comparing and contrasting their own work done in line with two models of translation teaching: authentic and near-authentic, the undergraduates answer research questions devised by a questionnaire survey The responses take us closer to how students feel about their LSP translation competence development. The major findings show how the trainees perceive the benefits and hardships of their functional translation class. In terms of skills, they related to communication as the most enhanced one; they highly valued the fact of being ‘exposed’ to a variety of texts (cf. multi literalism), team work, learning how to schedule work, IT skills boost and the ability to learn how to work individually. Another finding indicates that students struggled most with specialized language, and co-working with other students. The short-term research shows the momentum when the undergraduate LSP translation trainees entered the path of transformation i.e. gained consciousness of ‘how it is’ to be a participant-translator of real-life communities of practice, gaining pragmatic dint of the social and linguistic skills understood here as discursive competence (text > genre > discourse > professional practice). The undergraduates need to be aware of the work they have to do and challenges they are to face before arriving at the expert level of professional translation competence.

Keywords: communities of practice in LSP translation teaching, learning LSP translation as situated experience, peripheral participation, professional discourse for LSP translation teaching, professional translation competence

Procedia PDF Downloads 86

Authors: Rohtash

Abstract:

Academically, the concept of Justice in the literature is vast, and theories are voluminous and definitions are numerous but it is very difficult to define. Through the ages, justice has been evolving and developing reasoning that how individuals and communities do the right thing that is just and fair to all in that society. Justice is a relative and dynamic concept, not absolute one. It is different in different societies based on their morality and ethics. The idea of justice cannot arise from a single morality but interaction of competing moralities and contending perspectives. Justice is the conditional and circumstantial term. Therefore, justice takes different meanings in different contexts. Justice is the application of the Laws. It is a values-based concept in order to protect the rights and liberties of the people. It is a socially created concept that has no physical reality. It exists in society on the basis of the spirit of sharing by the communities and members of society. The conception of justice in society or among communities and individuals is based on their social coordination. It can be effective only when people’s judgments are based on collective reasoning. Their behavior is shaped by social values, norms and laws. People must accept, share and respect the set of principles for delivering justice. Thus justice can be a reasonable solution to conflicts and to coordinate behavior in society. The subject matter of distributive justice is the Public Good and societal resources that should be evenly distributed among the different sections of society on the principles developed and established by the State through legislation, public policy and Executive orders. The Socioeconomic transformation of the society is adopted by the constitution within the limit of its morality and gives a new dimension to transformative justice. Therefore, both Procedural and Transformative justice is part of Distributive justice. Distributive justice is purely an economic phenomenon. It concerns the allocation of resources among the communities and individuals. The subject matter of distributive justice is the distribution of rights, responsibilities, burdens and benefits in society on the basis of the capacity and capability of individuals.

Keywords: distributive justice, constitutionalism, institutionalism, constitutional morality

Procedia PDF Downloads 69

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 60

Authors: Yan Zhang

Abstract:

Predictive maintenance is a technique to predict when an in-service machine will fail so that maintenance can be planned in advance. Analytics-driven predictive maintenance is gaining increasing attention in many industries such as manufacturing, utilities, aerospace, etc., along with the emerging demand of Internet of Things (IoT) applications and the maturity of technologies that support Big Data storage and processing. This study aims to build an end-to-end analytics solution that includes both real-time machine condition monitoring and machine learning based predictive analytics capabilities. The goal is to showcase a general predictive maintenance solution architecture, which suggests how the data generated from field machines can be collected, transmitted, stored, and analyzed. We use a publicly available aircraft engine run-to-failure dataset to illustrate the streaming analytics component and the batch failure prediction component. We outline the contributions of this study from four aspects. First, we compare the predictive maintenance problems from the view of the traditional reliability centered maintenance field, and from the view of the IoT applications. When evolving to the IoT era, predictive maintenance has shifted its focus from ensuring reliable machine operations to improve production/maintenance efficiency via any maintenance related tasks. It covers a variety of topics, including but not limited to: failure prediction, fault forecasting, failure detection and diagnosis, and recommendation of maintenance actions after failure. Second, we review the state-of-art technologies that enable a machine/device to transmit data all the way through the Cloud for storage and advanced analytics. These technologies vary drastically mainly based on the power source and functionality of the devices. For example, a consumer machine such as an elevator uses completely different data transmission protocols comparing to the sensor units in an environmental sensor network. The former may transfer data into the Cloud via WiFi directly. The latter usually uses radio communication inherent the network, and the data is stored in a staging data node before it can be transmitted into the Cloud when necessary. Third, we illustrate show to formulate a machine learning problem to predict machine fault/failures. By showing a step-by-step process of data labeling, feature engineering, model construction and evaluation, we share following experiences: (1) what are the specific data quality issues that have crucial impact on predictive maintenance use cases; (2) how to train and evaluate a model when training data contains inter-dependent records. Four, we review the tools available to build such a data pipeline that digests the data and produce insights. We show the tools we use including data injection, streaming data processing, machine learning model training, and the tool that coordinates/schedules different jobs. In addition, we show the visualization tool that creates rich data visualizations for both real-time insights and prediction results. To conclude, there are two key takeaways from this study. (1) It summarizes the landscape and challenges of predictive maintenance applications. (2) It takes an example in aerospace with publicly available data to illustrate each component in the proposed data pipeline and showcases how the solution can be deployed as a live demo.

Keywords: Internet of Things, machine learning, predictive maintenance, streaming data

Procedia PDF Downloads 374

Authors: Tassadit Issaadi Hamitouche, Nicolas Gillard, Jean Petit, Valerie Lavaste, Celine Mayousse

Abstract:

Water is a fundamental resource for the industry. It is taken from the environment either from municipal distribution networks or from various natural water sources such as the sea, ocean, rivers, aquifers, etc. Once used, water is discharged into the environment, reprocessed at the plant or treatment plants. These withdrawals and discharges have a direct impact on natural water resources. These impacts can apply to the quantity of water available, the quality of the water used, or to impacts that are more complex to measure and less direct, such as the health of the population downstream from the watercourse, for example. Based on the analysis of data (meteorological, river characteristics, physicochemical substances), we wish to predict water stress episodes and anticipate prefectoral decrees, which can impact the performance of plants and propose improvement solutions, help industrialists in their choice of location for a new plant, visualize possible interactions between companies to optimize exchanges and encourage the pooling of water treatment solutions, and set up circular economies around the issue of water. The development of a system for the collection, processing, and use of data related to water resources requires the functional constraints specific to the latter to be made explicit. Thus the system will have to be able to store a large amount of data from sensors (which is the main type of data in plants and their environment). In addition, manufacturers need to have 'near-real-time' processing of information in order to be able to make the best decisions (to be rapidly notified of an event that would have a significant impact on water resources). Finally, the visualization of data must be adapted to its temporal and geographical dimensions. In this study, we set up an infrastructure centered on the TICK application stack (for Telegraf, InfluxDB, Chronograf, and Kapacitor), which is a set of loosely coupled but tightly integrated open source projects designed to manage huge amounts of time-stamped information. The software architecture is coupled with the cross-industry standard process for data mining (CRISP-DM) data mining methodology. The robust architecture and the methodology used have demonstrated their effectiveness on the study case of learning the level of a river with a 7-day horizon. The management of water and the activities within the plants -which depend on this resource- should be considerably improved thanks, on the one hand, to the learning that allows the anticipation of periods of water stress, and on the other hand, to the information system that is able to warn decision-makers with alerts created from the formalization of prefectoral decrees.

Keywords: data mining, industry, machine Learning, shortage, water resources

Procedia PDF Downloads 110

Authors: Meng Su

Abstract:

High-dimensional data analysis often presents challenges in capturing the complex, nonlinear relationships and manifold structures inherent to the data. This article presents a novel approach that leverages the strengths of two powerful techniques, Diffusion Maps and Diffusion Probabilistic Models (DPMs), to address these challenges. By integrating the dimensionality reduction capability of Diffusion Maps with the data modeling ability of DPMs, the proposed method aims to provide a comprehensive solution for analyzing and generating high-dimensional data. The Diffusion Map technique preserves the nonlinear relationships and manifold structure of the data by mapping it to a lower-dimensional space using the eigenvectors of the graph Laplacian matrix. Meanwhile, DPMs capture the dependencies within the data, enabling effective modeling and generation of new data points in the low-dimensional space. The generated data points can then be mapped back to the original high-dimensional space, ensuring consistency with the underlying manifold structure. Through a detailed example implementation, the article demonstrates the potential of the proposed hybrid approach to achieve more accurate and effective modeling and generation of complex, high-dimensional data. Furthermore, it discusses possible applications in various domains, such as image synthesis, time-series forecasting, and anomaly detection, and outlines future research directions for enhancing the scalability, performance, and integration with other machine learning techniques. By combining the strengths of Diffusion Maps and DPMs, this work paves the way for more advanced and robust data analysis methods.

Keywords: diffusion maps, diffusion probabilistic models (DPMs), manifold learning, high-dimensional data analysis

Procedia PDF Downloads 86

Authors: Dumith Kulasekara

Abstract:

This paper examines the representation of the body that particularly stresses the anatomical organs and the psychic conditions in contemporary art. The paper looks closely at the works that address personal and social meanings implying psychic conditions by bringing the internal hidden anatomical organs of the body to the surface of the visual language. The paper argues that contemporary artists conceptualize the idea of the body as a site of generating psychic conditions by excavating the body as material, subject, and object in art practice. The paper conceptualizes this excavating process of the body acts similarly to the idea of dissecting the corporeal body to understand its internal organism that again shapes the materiality of the surface of the body. In doing so, the paper brings together this argument, knowledge produced in the historical and contemporary anatomical education in art and science, and psychoanalytical approaches to the theme to develop new interpretations of representing psyche in the anatomical-bodied. The present paper defines this new form of body conceptually and materially addresses the issues related to psychic conditions: sexual desires, gender, traumas, and memories. The paper suggests that representation of the anatomical-bodied brings a new direction of the multidisciplinary approach introduced by artists to visualize the body and psyche in the contemporary context. The paper also presents an in-depth- discussion on technological, scientific, and philosophical knowledge employed in representing the idea of the body in addressing different psychic conditions to challenge the experiencing the body in contemporary art. Therefore, the paper focuses on examining the theme in the different forms of visual language and contexts in contemporary art. Finally, this research aims to offer a theoretical and conceptual background to curate an exhibition on the title of the anatomical-bodied and psyche in contemporary art with the body of work discussed in this paper.

Keywords: anatomy, body, contemporary art, psyche, psychoanalysis, representation, trauma

Procedia PDF Downloads 131

Authors: Tianqi Wu, Min Wang

Abstract:

Research investigating language acquisition from a constructionist perspective has demonstrated that language is learned as constructions at various linguistic levels, which is related to factors of frequency, semantic prototypicality, and form-meaning contingency. However, previous research on construction learning tended to focus on clause-level constructions such as verb argument constructions but few attempts were made to study morpheme-level constructions such as the progressive construction, which is regarded as a source of acquisition problems for English learners from diverse L1 backgrounds, especially for those whose L1 do not have an equivalent construction such as German and Chinese. To trace the developmental trajectory of Chinese EFL learners’ use of the progressive with respect to verb frequency, verb-progressive contingency, and verbal prototypicality and generality, a learner corpus consisting of three sub-corpora representing three different English proficiency levels was extracted from the Chinese Learners of English Corpora (CLEC). As the reference point, a native speakers’ corpus extracted from the Louvain Corpus of Native English Essays was also established. All the texts were annotated with C7 tagset by part-of-speech tagging software. After annotation all valid progressive hits were retrieved with AntConc 3.4.3 followed by a manual check. Frequency-related data showed that from the lowest to the highest proficiency level, (1) the type token ratio increased steadily from 23.5% to 35.6%, getting closer to 36.4% in the native speakers’ corpus, indicating a wider use of verbs in the progressive; (2) the normalized entropy value rose from 0.776 to 0.876, working towards the target score of 0.886 in native speakers’ corpus, revealing that upper-intermediate learners exhibited a more even distribution and more productive use of verbs in the progressive; (3) activity verbs (i.e., verbs with prototypical progressive meanings like running and singing) dropped from 59% to 34% but non-prototypical verbs such as state verbs (e.g., being and living) and achievement verbs (e.g., dying and finishing) were increasingly used in the progressive. Apart from raw frequency analyses, collostructional analyses were conducted to quantify verb-progressive contingency and to determine what verbs were distinctively associated with the progressive construction. Results were in line with raw frequency findings, which showed that contingency between the progressive and non-prototypical verbs represented by light verbs (e.g., going, doing, making, and coming) increased as English proficiency proceeded. These findings altogether suggested that beginning Chinese EFL learners were less productive in using the progressive construction: they were constrained by a small set of verbs which had concrete and typical progressive meanings (e.g., the activity verbs). But with English proficiency increasing, their use of the progressive began to spread to marginal members such as the light verbs.

Keywords: Construction learning, Corpus-based, Progressives, Prototype

Procedia PDF Downloads 116

Authors: Bernard Igoche Igoche, Olumuyiwa Matthew, Peter Bednar, Alexander Gegov

Abstract:

This study presents an ontology-driven approach for knowledge discovery and validation from admission databases in Nigerian polytechnic institutions. The research aims to address the challenges of extracting meaningful insights from vast amounts of admission data and utilizing them for decision-making and process improvement. The proposed methodology combines the knowledge discovery in databases (KDD) process with a structural causal model (SCM) ontological framework. The admission database of Benue State Polytechnic Ugbokolo (Benpoly) is used as a case study. The KDD process is employed to mine and distill knowledge from the database, while the SCM ontology is designed to identify and validate the important features of the admission process. The SCM validation is performed using the conditional independence test (CIT) criteria, and an algorithm is developed to implement the validation process. The identified features are then used for machine learning (ML) modeling and prediction of admission status. The results demonstrate the adequacy of the SCM ontological framework in representing the admission process and the high predictive accuracies achieved by the ML models, with k-nearest neighbors (KNN) and support vector machine (SVM) achieving 92% accuracy. The study concludes that the proposed ontology-driven approach contributes to the advancement of educational data mining and provides a foundation for future research in this domain.

Keywords: admission databases, educational data mining, machine learning, ontology-driven knowledge discovery, polytechnic education, structural causal model

Procedia PDF Downloads 43

Authors: Noriyuki Suyama

Abstract:

The progress and spread of digitalization have led to the provision of a variety of new services. The recent progress in digitization can be attributed to rapid developments in science and technology. First, the research and diffusion of artificial intelligence (AI) has made dramatic progress. Around 2000, the third wave of AI research, which had been underway for about 50 years, arrived. Specifically, machine learning and deep learning were made possible in AI, and the ability of AI to acquire knowledge, define the knowledge, and update its own knowledge in a quantitative manner made the use of big data practical even for commercial PCs. On the other hand, with the spread of social media, information exchange has become more common in our daily lives, and the lending and borrowing of goods and services, in other words, the sharing economy, has become widespread. The scope of this trend is not limited to any industry, and its momentum is growing as the SDGs take root. In addition, the Social Network Service (SNS), a part of social media, has brought about the evolution of the retail business. In the past few years, social network services (SNS) involving users or companies have especially flourished. The People's Republic of China (hereinafter referred to as "China") is a country that is stimulating enormous consumption through its own unique SNS, which is different from the SNS used in developed countries around the world. This paper focuses on the effectiveness and challenges of influencer marketing by focusing on the influence of influencers on users' behavior and satisfaction with Chinese SNSs. Specifically, Conducted was the quantitative survey of Tik Tok users living in China, with the aim of gaining new insights from the analysis and discussions. As a result, we found several important findings and knowledge.

Keywords: customer satisfaction, social networking services, influencer marketing, Chinese consumers’ behavior

Procedia PDF Downloads 82

Authors: Mahmoud Nabilu

Abstract:

The present study explored the effect of using Mobile listening applications on developing listening skills by Iranian intermediate EFL learners. Fifty male intermediate English learners whose age range was between 15 and 20, participated in the study. The participants were placed in two groups on the basis of their scores on a placement test. Therefore, the participants of the study were homogenized in terms of general proficiency, and groups were assigned as one experimental group and one control group. The experimental group was instructed by the treatment which was using mobile applications to develop their listening skills while the control group received traditional methods. The research data were obtained from the 40-item multiple-choice tests as a pre-test and a post-test. The results of the t-test clearly revealed that the learners in the experimental group performed better in the post-test than the pre-test. This implies that using a mobile application for developing listening skills as a treatment was effective in helping the language learners perform better on post-test. However, a statistically significant difference was found between the post-tests scores of the two groups. The mean of the experimental group was greater compared to the control group. The participants were Iranian and from an Iranian Language Institute, so care should be taken while generalizing the results to the learners of other nationalities. However, in the researcher's view, the findings of this study have valuable implications for teachers and learners, methodologists and syllabus designers, linguists and MALL/CALL (mobile/computer-assisted language learning) experts. Using the result of the present paper is an aim of raising the consciousness of a better technique of developing listening skills in order to make language learning more efficient for the learners.

Keywords: Mobile listening applications, intermediate EFL learners, MALL, CALL

Procedia PDF Downloads 181

Authors: Pedro Mota Veiga

Abstract:

This study comprehensively evaluates the repercussions of innovation, digital advancements, and technological capabilities on the operational performance of companies across fifteen European Union countries following the initial wave of the COVID-19 pandemic. Drawing insights from longitudinal data sourced from the 2019 World Bank business surveys and subsequent 2020 World Bank COVID-19 follow-up business surveys, our extensive examination involves a diverse sample of 5763 family businesses. In exploring the relationships between these variables, we adopt a nuanced approach to assess the impact of innovation and digital and technological capabilities on performance. This analysis unfolds along two distinct perspectives: one rooted in necessity and the other insufficiency. The methodological framework employed integrates partial least squares structural equation modeling (PLS-SEM) with condition analysis (NCA), providing a robust foundation for drawing meaningful conclusions. The findings of the study underscore a positive influence on the performance of family firms stemming from both technological capabilities and digital advancements. Furthermore, it is pertinent to highlight the indirect contribution of innovation to enhanced performance, operating through its impact on digital capabilities. This research contributes valuable insights to the broader understanding of how innovation, coupled with digital and technological capabilities, can serve as pivotal factors in shaping the post-COVID-19 landscape for businesses across the European Union. The intricate analysis of family businesses, in particular adds depth to the comprehension of the dynamics at play in diverse economic contexts within the European Union.

Keywords: digital capabilities, technological capabilities, family firms performance, innovation, NCA, PLS-SEM

Procedia PDF Downloads 53

Authors: Carol S. Binnekade, Deon Scott, Christina C. Shuttleworth, Annelien A. Van Rooyen

Abstract:

Higher education institutions are constantly challenged to deliver skilled graduates into the workplace. Employers expect graduates to have the required technical knowledge as well as various pervasive skills. This also applies to accountants who need to know the technical requirements of financial reporting and be able to communicate with individuals, teams and clients at a high level. Accountants need to develop effective business conversational skills and use these skills to communicate up, down and across organizations, taking into consideration cultural and gender diversity. In addition, they need to master business writing and presentation skills. However, providing students with these skills in a distance-learning environment where interaction between students and instructors is limited, is a challenge for academics. The study on which this paper reports, forms part of a larger body of research, which explored the perceptions of accounting practitioners of the communication skills (or lack thereof) of recently qualified accounting students. Feedback (qualitative and quantitative) was obtained from various accounting practitioners in South Africa. Taking into consideration that distance learners communicate mainly with their instructors via email communication and their assignments are submitted using various word processor software, the researchers were of the opinion that the accounting graduates would be capable of communicating effectively once they entered the workplace. However, the research findings, inter alia, suggested that the accounting graduates lacked communication skills and that training was needed to differentiate between business and social communication once they entered the workplace. Recommendations on how these communication challenges may be addressed by higher education institutions are provided.

Keywords: accounting practitioners, communication skills, distance education, pervasive skills

Procedia PDF Downloads 191

Authors: Sayed Ahmed

Abstract:

Religious activities that have evolved the sacred into a dynamic cultural phenomenon in the public realm of Sylhet, Bangladesh, and the spatiality of sacred sites and everyday practices in certain built forms have framed these phenomena. Religious rituals in Sylhet gave birth to unique practices of their own and have a vast impact even on contemporary spatial practices, while most Western researchers are not hopeful about the future of religion. However, despite extensive research on urban morphology and religion separately, there is limited literature on the relationship between these two topics to capture religious perceptions and experiences in urban spaces. This research will try to fill the existing gap and explain sacred within the range of Western sociological and philosophical tools implemented in third-world contexts, which was never highlighted before. This perspective of research puts forth the argument that urban morphology influences sacred experiences and how consecrated entities and religious activities shape the city's structure in return. The methodology of the research will map key morphological and religious variables. This mapping might include festival trajectories, street life observations, pedestrian densities, religious activities, public and private interface types with religious commodification, and the identification of blurred boundaries between sacred and profane on smaller to broader urban scales. To relate the derived cartography, illustrative (not representative) interviews about religious signs and symbols will be conducted and compared accordingly. The possible findings might reintroduce the diversity of religious practices in urban places and develop a decent concept of how sacred and urban morphology are mutually reinforcing the city, which has remained a vital nutrient for the survival of its inhabitants. Such infrequent conceptualizations of urban morphology and its relationship to symbolic sacralization are truly ‘outside’ to those that exist in the West.

Keywords: sylhet, religion, urban morphology, symbolic exchange, Baudrillard

Procedia PDF Downloads 19

Authors: Jeremy Jenrette, Z. Y. C. Liu, Pranav Chimote, Edward Fox, Trevor Hastie, Francesco Ferretti

Abstract:

Suitable shark conservation depends on well-informed population assessments. Direct methods such as scientific surveys and fisheries monitoring are adequate for defining population statuses, but species-specific indices of abundance and distribution coming from these sources are rare for most shark species. We can rapidly fill these information gaps by boosting media-based remote monitoring efforts with machine learning and automation. We created a database of shark images by sourcing 24,546 images covering 219 species of sharks from the web application spark pulse and the social network Instagram. We used object detection to extract shark features and inflate this database to 53,345 images. We packaged object-detection and image classification models into a Shark Detector bundle. We developed the Shark Detector to recognize and classify sharks from videos and images using transfer learning and convolutional neural networks (CNNs). We applied these models to common data-generation approaches of sharks: boosting training datasets, processing baited remote camera footage and online videos, and data-mining Instagram. We examined the accuracy of each model and tested genus and species prediction correctness as a result of training data quantity. The Shark Detector located sharks in baited remote footage and YouTube videos with an average accuracy of 89\%, and classified located subjects to the species level with 69\% accuracy (n =\ eight species). The Shark Detector sorted heterogeneous datasets of images sourced from Instagram with 91\% accuracy and classified species with 70\% accuracy (n =\ 17 species). Data-mining Instagram can inflate training datasets and increase the Shark Detector’s accuracy as well as facilitate archiving of historical and novel shark observations. Base accuracy of genus prediction was 68\% across 25 genera. The average base accuracy of species prediction within each genus class was 85\%. The Shark Detector can classify 45 species. All data-generation methods were processed without manual interaction. As media-based remote monitoring strives to dominate methods for observing sharks in nature, we developed an open-source Shark Detector to facilitate common identification applications. Prediction accuracy of the software pipeline increases as more images are added to the training dataset. We provide public access to the software on our GitHub page.

Keywords: classification, data mining, Instagram, remote monitoring, sharks

Procedia PDF Downloads 100

Authors: Raptis Sotirios

Abstract:

Health and social care (HSc) services planning and scheduling are facing unprecedented challenges due to the pandemic pressure and also suffer from unplanned spending that is negatively impacted by the global financial crisis. Data-driven can help to improve policies, plan and design services provision schedules using algorithms assist healthcare managers’ to face unexpected demands using fewer resources. The paper discusses services packing using statistical significance tests and machine learning (ML) to evaluate demands similarity and coupling. This is achieved by predicting the range of the demand (class) using ML methods such as CART, random forests (RF), and logistic regression (LGR). The significance tests Chi-Squared test and Student test are used on data over a 39 years span for which HSc services data exist for services delivered in Scotland. The demands are probabilistically associated through statistical hypotheses that assume that the target service’s demands are statistically dependent on other demands as a NULL hypothesis. This linkage can be confirmed or not by the data. Complementarily, ML methods are used to linearly predict the above target demands from the statistically found associations and extend the linear dependence of the target’s demand to independent demands forming, thus groups of services. Statistical tests confirm ML couplings making the prediction also statistically meaningful and prove that a target service can be matched reliably to other services, and ML shows these indicated relationships can also be linear ones. Zero paddings were used for missing years records and illustrated better such relationships both for limited years and in the entire span offering long term data visualizations while limited years groups explained how well patients numbers can be related in short periods or can change over time as opposed to behaviors across more years. The prediction performance of the associations is measured using Receiver Operating Characteristic(ROC) AUC and ACC metrics as well as the statistical tests, Chi-Squared and Student. Co-plots and comparison tables for RF, CART, and LGR as well as p-values and Information Exchange(IE), are provided showing the specific behavior of the ML and of the statistical tests and the behavior using different learning ratios. The impact of k-NN and cross-correlation and C-Means first groupings is also studied over limited years and the entire span. It was found that CART was generally behind RF and LGR, but in some interesting cases, LGR reached an AUC=0 falling below CART, while the ACC was as high as 0.912, showing that ML methods can be confused padding or by data irregularities or outliers. On average, 3 linear predictors were sufficient, LGR was found competing RF well, and CART followed with the same performance at higher learning ratios. Services were packed only if when significance level(p-value) of their association coefficient was more than 0.05. Social factors relationships were observed between home care services and treatment of old people, birth weights, alcoholism, drug abuse, and emergency admissions. The work found that different HSc services can be well packed as plans of limited years, across various services sectors, learning configurations, as confirmed using statistical hypotheses.

Keywords: class, cohorts, data frames, grouping, prediction, prob-ability, services

Procedia PDF Downloads 214

Authors: M. Taheri Tehrani, H. Ajorloo

Abstract:

In this paper, an intelligent multi-agent framework is developed for each router in which agents have two vital functionalities, traffic shaping and buffer allocation and are positioned in the ports of the routers. With traffic shaping functionality agents shape the traffic forward by dynamic and real time allocation of the rate of generation of tokens in a Token Bucket algorithm and with buffer allocation functionality agents share their buffer capacity between each other based on their need and the conditions of the network. This dynamic and intelligent framework gives this opportunity to some ports to work better under burst and more busy conditions. These agents work intelligently based on Reinforcement Learning (RL) algorithm and will consider effective parameters in their decision process. As RL have limitation considering much parameter in its decision process due to the volume of calculations, we utilize our novel method which invokes Principle Component Analysis (PCA) on the RL and gives a high dimensional ability to this algorithm to consider as much as needed parameters in its decision process. This implementation when is compared to our previous work where traffic shaping was done without any sharing and dynamic allocation of buffer size for each port, the lower packet drop in the whole network specifically in the source routers can be seen. These methods are implemented in our previous proposed intelligent simulation environment to be able to compare better the performance metrics. The results obtained from this simulation environment show an efficient and dynamic utilization of resources in terms of bandwidth and buffer capacities pre allocated to each port.

Keywords: principal component analysis, reinforcement learning, buffer allocation, multi- agent systems

Procedia PDF Downloads 498

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 114