Search results for: learning & teaching

Authors: Albert Bou, Sebastian Dittert, Gianni de Fabritiis

Abstract:

Advancing reinforcement learning (RL) requires tools that are flexible enough to easily prototype new methods while avoiding impractically slow experimental turnaround times. To match the first requirement, the most popular RL libraries advocate for highly modular agent composability, which facilitates experimentation and development. To solve challenging environments within reasonable time frames, scaling RL to large sampling and computing resources has proved a successful strategy. However, this capability has been so far difficult to combine with modularity. In this work, we explore design choices to allow agent composability both at a local and distributed level of execution. We propose a versatile approach that allows the definition of RL agents at different scales through independent, reusable components. We demonstrate experimentally that our design choices allow us to reproduce classical benchmarks, explore multiple distributed architectures, and solve novel and complex environments while giving full control to the user in the agent definition and training scheme definition. We believe this work can provide useful insights to the next generation of RL libraries.

Keywords: deep reinforcement learning, Python, PyTorch, distributed training, modularity, library

Procedia PDF Downloads 85

Authors: Kaoutar Ben Azzou, Hanaa Talei

Abstract:

Human resources is an important department in each organization as it manages the life cycle of employees from recruitment training to retirement or termination of contracts. The recruitment process starts with a job opening, followed by a selection of the best-fit candidates from all applicants. Matching the best profile for a job position requires a manual way of looking at many CVs, which requires hours of work that can sometimes lead to choosing not the best profile. The work presented in this paper aims at reducing the workload of HR personnel by automating the preliminary stages of the candidate screening process, thereby fostering a more streamlined recruitment workflow. This tool introduces an automated system designed to help with the recruitment process by scanning candidates' CVs, extracting pertinent features, and employing machine learning algorithms to decide the most fitting job profile for each candidate. Our work employs natural language processing (NLP) techniques to identify and extract key features from unstructured text extracted from a CV, such as education, work experience, and skills. Subsequently, the system utilizes these features to match candidates with job profiles, leveraging the power of classification algorithms.

Keywords: automated recruitment, candidate screening, machine learning, human resources management

Procedia PDF Downloads 60

Authors: Farhad Asadi, Mohammad Javad Mollakazemi, Aref Ghafouri

Abstract:

Recent research in neural networks science and neuroscience for modeling complex time series data and statistical learning has focused mostly on learning from high input space and signals. Local linear models are a strong choice for modeling local nonlinearity in data series. Locally weighted projection regression is a flexible and powerful algorithm for nonlinear approximation in high dimensional signal spaces. In this paper, different learning scenario of one and two dimensional data series with different distributions are investigated for simulation and further noise is inputted to data distribution for making different disordered distribution in time series data and for evaluation of algorithm in locality prediction of nonlinearity. Then, the performance of this algorithm is simulated and also when the distribution of data is high or when the number of data is less the sensitivity of this approach to data distribution and influence of important parameter of local validity in this algorithm with different data distribution is explained.

Keywords: local nonlinear estimation, LWPR algorithm, online training method, locally weighted projection regression method

Procedia PDF Downloads 505

Authors: Suzi M. S. Cavalari, Tim Lewis

Abstract:

Teletandem is a bilingual model of virtual exchange in which two partners from different countries( and speak different languages) meet synchronously and regularly over a period of 8 weeks to learn each other’s mother tongue (or the language of proficiency). At São Paulo State University (UNESP), participants should answer a questionnaire before starting the exchanges in which one of the questions refers to setting a goal to be accomplished with the help of the teletandem partner. In this context, the present presentation aims to examine the goal-setting activity of 79 Brazilians who participated in Portuguese-English teletandem exchanges over a period of four years (2012-2015). The theoretical background is based on goal setting and self-regulated learning theories that propose that appropriate efficient goals are focused on the learning process (not on the product) and are specific, proximal (short-term) and moderately difficult. The data set used was 79 initial questionnaires retrieved from the MulTeC (Multimodal Teletandem Corpus). Results show that only approximately 10% of goals can be considered appropriate. Features of these goals are described in relation to specificities of the teletandem context. Based on the results, three mechanisms that can help learners to set attainable goals are discussed.

Keywords: foreign language learning, goal setting, teletandem, virtual exchange

Procedia PDF Downloads 185

Authors: Kari Björn, Mikael Soini

Abstract:

Higher Education system reforms, especially Finnish system of Universities of Applied Sciences in 2014 are discussed. The new steering model is based on major legislative changes, output-oriented funding and open information. The governmental steering reform, especially the financial model and the resulting institutional level responses, such as a curriculum reforms are discussed, focusing especially in engineering programs. The paper is motivated by management need to establish objective steering-related performance indicators and to apply them consistently across all educational programs. The close relationship to governmental steering and funding model imply that internally derived indicators can be directly applied. Metropolia University of Applied Sciences (MUAS) as a case institution is briefly introduced, focusing on engineering education in Information and Communications Technology (ICT), and its related programs. The reform forced consolidation of previously separate smaller programs into fewer units of student application. New curriculum ICT students have a common first year before they apply for a Major. A framework of parallel and longitudinal comparisons is introduced and used across Majors in two campuses. The new externally introduced performance criteria are applied internally on ICT Majors using data ex-ante and ex-post of program merger.  A comparative performance of the Majors after completion of joint first year is established, focusing on previously omitted Majors for completeness of analysis. Some new research questions resulting from transfer of Majors between campuses and quota setting are discussed. Practical orientation identifies best practices to share or targets needing most attention for improvement. This level of analysis is directly applicable at student group and teaching team level, where corrective actions are possible, when identified. The analysis is quantitative and the nature of the corrective actions are not discussed. Causal relationships and factor analysis are omitted, because campuses, their staff and various pedagogical implementation details contain still too many undetermined factors for our limited data. Such qualitative analysis is left for further research. Further study must, however, be guided by the relevance of the observations.

Keywords: engineering education, integrated curriculum, learning outcomes, performance measurement

Procedia PDF Downloads 244

Authors: Anna Petr Safrankova, Karla Hrbackova

Abstract:

The education of socially disadvantaged students is in the long term spotlight of many pedagogical researches in both Czech and foreign environment. These researches among others investigate this topic from the point of view of individual compensatory measure which tries to overcome or remove the social disadvantage. The focus of the study is to highlight the important role of teachers in the education of this specific group of students, among others in terms of their (teachers´) pre-graduate training. The aim of the study is to point out the importance of teachers´ self-efficacy. The study is based on the assumption that the teacher's self-efficacy may significantly affect the teacher's perception of a particular group of students and thereby affect the education of the students. The survey involved 245 teachers from the two regions in the Czech Republic. In the research were used TES questionnaire (with the dimensions personal teaching efficacy – PTE and general teaching efficacy – GTE) by Gibson and Dembo and the semantic differential (containing 12 scales with bipolar adjectives) which investigated the components of teachers' attitudes toward socially disadvantaged students. It was found that teachers’ self-efficacy significantly affects the teachers’ perception of the group of socially disadvantaged students. Based on this finding we believe that it is necessary to work with this concept (prepare teachers to educate this specific group of students) already during higher education and especially during the pre-graduate teachers training.

Keywords: teachers, socially disadvantaged students, semantic differential, teachers self-efficacy

Procedia PDF Downloads 430

Authors: Beilei Xu, Wencheng Wu, Lei Lin, Rachel Melnyk, Ahmed Ghazi

Abstract:

In operating rooms, excessive cognitive stress can impede the performance of a surgeon, while low engagement can lead to unavoidable mistakes due to complacency. As a consequence, there is a strong desire in the surgical community to be able to monitor and quantify the cognitive stress of a surgeon while performing surgical procedures. Quantitative cognitiveload-based feedback can also provide valuable insights during surgical training to optimize training efficiency and effectiveness. Various physiological measures have been evaluated for quantifying cognitive stress for different mental challenges. In this paper, we present a study using the cognitive stress measured by the task evoked pupillary response extracted from the time series eye-tracking measurements to predict task difficulties in a virtual reality based robotic surgery training environment. In particular, we proposed a differential-task-difficulty scale, utilized a comprehensive feature extraction approach, and implemented a multitask learning framework and compared the regression accuracy between the conventional single-task-based and three multitask approaches across subjects.

Keywords: surgical metric, task evoked pupillary response, multitask learning, TSFresh

Procedia PDF Downloads 148

Authors: Simao E. Luis

Abstract:

From the 1960s to the 1990s, the social-psychological framework of language attitudes that emerged from the Canadian research tradition was very influential. Integrativeness was one of the main variables in Gardner’s theory because refugees and immigrants were motivated to learn English and French to integrate into the Canadian community. Second language (L2) scholars have expressed concerns over integrativeness because it cannot explain the motivation of L2 learners in global contexts. This study aims to investigate student motivation to learn English as a foreign language in Mozambique, and to contribute to the ongoing validation of the L2 Motivational Self System theory in an under-researched country. One hundred thirty-seven (N=137) university students completed a well-established motivation questionnaire. The data were analyzed with SPSS, and descriptive statistics, correlations, multiple regressions, and MANOVA were conducted. Results show that many variables contribute to motivated learning behavior, particularly the L2 learning experience and attitudes towards the English language. Statistically significant differences were found between males and females, with males expressing more motivation to learn the English language for personal interests. Statistically significant differences were found between older and younger students, with older students reporting more vivid images of themselves as future English language users. These findings have pedagogical implications because motivational strategies are positively correlated with student motivated learning behavior. Therefore, teachers should design L2 tasks that can help students to develop their future L2 selves.

Keywords: English as a foreign language, L2 motivational self system, Mozambique, university students

Procedia PDF Downloads 125

Authors: Saeedeh Shafiee Nahrkhalaji

Abstract:

Metacognitive knowledge increases EFL students’ ability to be successful learners. Although this relationship has been investigated by a number of scholars, EFL teachers’ explicit awareness of their cognitive knowledge has not been sufficiently explored. The aim of this study was to examine the role of EFL teachers’ metacognitive knowledge in their pedagogical performance. Furthermore, the role played by years of their academic education and teaching experience was also studied. Fifty female EFL teachers were selected. They completed Metacognitive Awareness Inventory (MAI) that assessed six components of metacognition including procedural knowledge, declarative knowledge, conditional knowledge, planning, evaluating, and management strategies. Near the end of the academic semester, the students of each class filled in ‘the Language Teacher Characteristics Questionnaire’ to evaluate their teachers’ pedagogical performance. Four elements of MAI, declarative knowledge, planning, evaluating, and management strategies were found to be significantly correlated with EFL teachers’ pedagogical success. Significant correlation was also established between metacognitive knowledge and EFL teachers’ years of academic education and teaching experience. The findings obtained from this research have contributing implication for EFL teacher educators. The discussion concludes by setting out directions for future research.

Keywords: metacognotive knowledge, pedagogical performance, language teacher characteristics questionnaire, metacognitive awareness inventory

Procedia PDF Downloads 331

Authors: Barbara Peric

Abstract:

The study of acquiring a third and additional language has garnered significant focus within second language acquisition (SLA) research. Initially, it was commonly viewed as merely an extension of second language acquisition (SLA). However, in the last two decades, numerous researchers have emphasized the need to recognize the unique characteristics of third language acquisition (TLA). This recognition is crucial for understanding the intricate cognitive processes that arise from the interaction of more than two linguistic systems in the learner's mind. This study investigates cross-linguistic influences in the acquisition of Spanish as a fourth language by students who have Croatian as a first language (L1). English as a second language (L2), and Italian as a third language (L3). Observational data suggests that influence or transfer of linguistic elements can arise not only from one's native language (L1) but also from non-native languages. This implies that, for individuals proficient in multiple languages, the native language doesn't consistently hold a superior position. Instead, it should be examined alongside other potential sources of linguistic transfer. Earlier studies have demonstrated that high proficiency in a second language can significantly impact cross-linguistic influences when acquiring a third and additional language. Among the extensively examined factors, the typological relationship stands out as one of the most scrutinized variables. The goal of the present study was to explore whether language typology and formal similarity or proficiency in the second language had a more significant impact on L4 acquisition. Participants in this study were third-year undergraduate students at Rochester Institute of Technology’s subsidiary in Croatia (RIT Croatia). All the participants had exclusively Croatian as L1, English as L2, Italian as L3 and were learning Spanish as L4 at the time of the study. All the participants had a high level of proficiency in English and low level of proficiency in Italian. Based on the error analysis the findings indicate that for some types of lexical errors such as coinage, language typology had a more significant impact and Italian language was the preferred source of transfer despite the law proficiency in that language. For some other types of lexical errors, such as calques, second language proficiency had a more significant impact, and English language was the preferred source of transfer. On the other hand, Croatian, Italian, and Spanish are more similar in the area of morphology due to higher degree of inflection compared to English and the strongest influence of the Croatian language was precisely in the area of morphology. The results emphasize the need to consider linguistic resemblances between the native language (L1) and the third and additional language as well as the learners' proficiency in the second language when developing successful teaching strategies for acquiring the third and additional language. These conclusions add to the expanding knowledge in the realm of Second Language Acquisition (SLA) and offer practical insights for language educators aiming to enhance the effectiveness of learning experiences in acquiring a third and additional language.

Keywords: third and additional language acquisition, cross-linguistic influences, language proficiency, language typology

Procedia PDF Downloads 64

Authors: Modupe Beatrice Adeyinka

Abstract:

French, as a foreign language in Nigeria, is pronounced to be the second official language and a compulsory subject in the primary school level; hence, colleges of education across the nation are saddled with the responsibility of training teachers for the subject. However, it has been observed that this policy has not been fully implemented, for French teachers in training, do face many challenges, of which translation is chief. In a bid to investigate the major cause of the perceived translation problem, this study examined French translation problems of pre-service teachers in selected colleges of education in the southwest, Nigeria. This study adopted a descriptive survey research design. The simple random sampling technique was used to select four colleges of education in the southwest, where 100 French students were randomly selected by selecting 25 from each school. The pre-service teachers’ French translation problems’ questionnaire (PTFTPQ) was used as an instrument while four research questions were answered and three null hypotheses were tested. Among others, the findings revealed that students do have problems with false friends, though mainly with its interpretation when attempting French-English translation and vice versa; majority of the students make use of French dictionary as a way out and found the material very useful for their understanding of false friends. Teachers were, therefore, urged to attend in-service training where they would be exposed to new and emerging strategies, approaches and methodologies of French language teaching that will make students overcome the challenge of translation in learning French.

Keywords: false friends, French language, pre-service teachers, source language, target language, translation

Procedia PDF Downloads 166

Authors: Rose Veitch

Abstract:

Learning outcomes-based qualifications have been heralded as the means to raise vocational education and training (VET) standards, meet the needs of the changing workforce, and establish equivalence with existing academic qualifications. Characterized by explicit, measurable performance statements and atomistically specified assessment criteria, the outcomes model has been adopted by many VET systems worldwide since its inception in the United Kingdom in the 1980s. Debate to date centers on how the outcomes model treats knowledge. Flaws have been identified in terms of the overemphasis of end-points, neglect of process and a failure to treat curricula coherently. However, much of this censure has evaluated the outcomes model from a theoretical perspective; to date, there has been scant empirical research to support these criticisms. Various issues therefore remain unaddressed. This study investigates how the outcomes model impacts the teaching of subject literacies. This is of particular concern for subjects on the academic-vocational boundary such as Business Studies, since many of these students progress to higher education in the United Kingdom. This study also explores the extent to which the outcomes model is compatible with borderline vocational subjects. To fully understand if this qualification model is fit for purpose in the 16-18 year-old phase, it is necessary to investigate how teachers interpret their qualification specifications in terms of curriculum, pedagogy and assessment. Of particular concern is the nature of the interaction between the outcomes model and teachers’ understandings of their subject-procedural knowledge, and how this affects their capacity to embed literacy into their teaching. This present study is part of a broader doctoral research project which seeks to understand if and how content-area, disciplinary literacy and genre approaches can be adapted to outcomes-based VET qualifications. This qualitative research investigates the ‘what’ and ‘how’ of literacy embedding from the perspective of in-service teacher development in the 16-18 phase of education. Using ethnographic approaches, it is based on fieldwork carried out in one Further Education college in the United Kingdom. Emergent findings suggest that the outcomes model is not fit for purpose in the context of borderline vocational subjects. It is argued that the outcomes model produces inferior qualifications due to compositional fallacy; the sum of a subject’s components do not add up to the whole. Findings indicate that procedural knowledge, largely unspecified by some outcomes-based qualifications, is where subject-literacies are situated, and that this often gets lost in ‘delivery’. It seems that the outcomes model provokes an atomistic treatment of knowledge amongst teachers, along with the privileging of propositional knowledge over procedural knowledge. In other words, outcomes-based VET is a hostile environment for subject-literacy embedding. It is hoped that this research will produce useful suggestions for how this problem can be ameliorated, and will provide an empirical basis for the potential reforms required to address these issues in vocational education.

Keywords: literacy, outcomes-based, qualification design, vocational education

Procedia PDF Downloads 20

Authors: Sun-Young Jang, Sung-Ah Kim, Dongyoun Shin

Abstract:

Current real-estate value estimation, difficult for laymen, usually is performed by specialists. This paper presents an automated estimation process based on big data and machine-learning technology that calculates influences of building conditions on real-estate price measurement. The present study analyzed actual building sales sample data for Nonhyeon-dong, Gangnam-gu, Seoul, Korea, measuring the major influencing factors among the various building conditions. Further to that analysis, a prediction model was established and applied using RapidMiner Studio, a graphical user interface (GUI)-based tool for derivation of machine-learning prototypes. The prediction model is formulated by reference to previous examples. When new examples are applied, it analyses and predicts accordingly. The analysis process discerns the crucial factors effecting price increases by calculation of weighted values. The model was verified, and its accuracy determined, by comparing its predicted values with actual price increases.

Keywords: apartment complex, big data, life-cycle building value analysis, machine learning

Procedia PDF Downloads 375

Authors: Davut Uysal

Abstract:

Turkish higher education system has experienced some structural changes in recent decades, which resulted in the concentration on English language teaching as a foreign language at high education institutions. However, the number of studies examining the relationship between organizational culture and job satisfaction among language teachers at higher education institutions, who are the key elements of the teaching process, is very limited in the country. The main objective of this study is to find out the perceptions of English language instructors regarding organizational culture and its impact on their job satisfaction at School of Foreign Language, Anadolu University in Turkey. Questionnaire technique was used in data collection, and the collected data was analysed with the help of SPSS data analysis program. The findings of the study revealed that the respondents of the study had positive perceptions regarding current organizational culture indicating satisfaction with co-worker relations and administration, supervision support and the work itself, as well as their satisfaction with the available professional development opportunities provided by their institution. A significant relationship between overall organizational culture and job satisfaction was found in the study. This study also presents some key elements to increase the job satisfaction levels of the language teachers by managing corporate communication and to improve the organisational culture based on the findings of the study as they are two interrelated issues.

Keywords: corporate communication, English teacher, organizational culture, job satisfaction

Procedia PDF Downloads 174

Authors: Stephanie Liu Lu

Abstract:

The course "University Chinese," an essential component of the curriculum in Hong Kong's higher education institutions, plays a crucial role in enhancing students' creative expression, narrative construction, argumentative prowess, and literary skills through its focus on non-fiction writing. Despite its significance, the comprehensive syllabus, coupled with limited classroom time, often restricts adequate practice opportunities and leads to delayed feedback, negatively impacting students' preparation for assessments. This paper investigates the potential of generative artificial intelligence (AI) tools, such as ChatGPT and POE, to provide personalized and immediate feedback for writing tasks. The primary goal of this research is to evaluate student receptiveness to AI-generated feedback and compare it to traditional feedback provided solely by human instructors. To achieve this, participants will be systematically divided into two groups: one receiving feedback from both instructors and AI tools, and a control group that receives feedback exclusively from instructors. The study will thoroughly analyze the revisions made to texts after receiving feedback, focusing particularly on enhancements in the quality of content and language proficiency across three dimensions: content/theme, language, and structural logic. This investigation aims to determine whether AI tools can enhance the efficiency of teaching practices, encourage autonomous learning, and significantly improve the overall quality of students' written work.

Keywords: AI-generated feedback, Chinese writing, non-fiction writing, student receptiveness

Procedia PDF Downloads 10

Authors: Rui Wu

Abstract:

In the volatile modern manufacturing environment, new orders randomly occur at any time, while the pre-emptive methods are infeasible. This leads to a real-time scheduling method that can produce a reasonably good schedule quickly. The dynamic Flexible Job Shop problem is an NP-hard scheduling problem that hybrid the dynamic Job Shop problem with the Parallel Machine problem. A Flexible Job Shop contains different work centres. Each work centre contains parallel machines that can process certain operations. Many algorithms, such as genetic algorithms or simulated annealing, have been proposed to solve the static Flexible Job Shop problems. However, the time efficiency of these methods is low, and these methods are not feasible in a dynamic scheduling problem. Therefore, a dynamic rule selection scheduling system based on the reinforcement learning method is proposed in this research, in which the dynamic Flexible Job Shop problem is divided into several parallel machine problems to decrease the complexity of the dynamic Flexible Job Shop problem. Firstly, the features of jobs, machines, work centres, and flexible job shops are selected to describe the status of the dynamic Flexible Job Shop problem at each decision point in each work centre. Secondly, a framework of reinforcement learning algorithm using a double-layer deep Q-learning network is applied to select proper composite dispatching rules based on the status of each work centre. Then, based on the selected composite dispatching rule, an available operation is selected from the waiting buffer and assigned to an available machine in each work centre. Finally, the proposed algorithm will be compared with well-known dispatching rules on objectives of mean tardiness, mean flow time, mean waiting time, or mean percentage of waiting time in the real-time Flexible Job Shop problem. The result of the simulations proved that the proposed framework has reasonable performance and time efficiency.

Keywords: dynamic scheduling problem, flexible job shop, dispatching rules, deep reinforcement learning

Procedia PDF Downloads 112

Authors: Richard O’Riordan, Saritha Unnikrishnan

Abstract:

Autonomous Vehicles (AVs) are incorporating an increasing number of ADAS features, including automated lane-keeping systems. In recent years, many research papers into lane detection algorithms have been published, varying from computer vision techniques to deep learning methods. The transition from lower levels of autonomy defined in the SAE framework and the progression to higher autonomy levels requires increasingly complex models and algorithms that must be highly reliable in their operation and functionality capacities. Furthermore, these algorithms have no room for error when operating at high levels of autonomy. Although the current research details existing computer vision and deep learning algorithms and their methodologies and individual results, the research also details challenges faced by the algorithms and the resources needed to operate, along with shortcomings experienced during their detection of lanes in certain weather and lighting conditions. This paper will explore these shortcomings and attempt to implement a lane detection algorithm that could be used to achieve improvements in AV lane detection systems. This paper uses a pre-trained LaneNet model to detect lane or non-lane pixels using binary segmentation as the base detection method using an existing dataset BDD100k followed by a custom dataset generated locally. The selected roads will be modern well-laid roads with up-to-date infrastructure and lane markings, while the second road network will be an older road with infrastructure and lane markings reflecting the road network's age. The performance of the proposed method will be evaluated on the custom dataset to compare its performance to the BDD100k dataset. In summary, this paper will use Transfer Learning to provide a fast and robust lane detection algorithm that can handle various road conditions and provide accurate lane detection.

Keywords: ADAS, autonomous vehicles, deep learning, LaneNet, lane detection

Procedia PDF Downloads 111

Authors: Pei Wang

Abstract:

The concept of social-emotional learning (SEL) is becoming increasingly popular in both research and practical applications worldwide. However, there is a lack of empirical studies and implementation of SEL in China, particularly from the perspective of parents. This qualitative study examined how Chinese parents perceived SEL, how their views on SEL were shaped, and how these views affected their decisions regarding their children’s education programs. Using the Collaborative for Academic Social and Emotional Learning Interactive Wheel framework and Bronfenbrenner's bioecological theory, the study conducted interviews with eight parents whose children attended public, international, and private schools in China. All collected data were conducted a thematic analysis involving three coding phases. The findings revealed that interviewees perceived SEL as significant to children’s development but held diverse understandings and perspectives on SEL at school depending on the amount and the quality of SEL resources available in their children’s schools. Additionally, parents’ attitudes towards the exam-oriented education system and Chinese culture influenced their views on SEL in school. Nevertheless, their socioeconomic status (SES) was the most significant factor in their perspectives on SEL, which significantly impacted their choices in their children's educational programs. High-SES families had more options to pursue SEL resources by sending their children to international schools or Western countries, while lower middle-class SES families had limited SEL resources in public schools. This highlighted educational inequality in China and emphasized the need for greater attention and investment in SEL programs in Chinese public schools.

Keywords: Chinese, inequality, parent, school, social-emotional learning

Procedia PDF Downloads 69

Authors: Hexiong Liu

Abstract:

Powder metallurgy is the optimal method for the consolidation and preparation of W(Mo) alloys, which exhibit excellent application prospects at high temperatures. The properties of W(Mo) alloys are closely related to the sintered density. However, controlling the sintered density and porosity of these alloys is still challenging. In the past, the regulation methods mainly focused on time-consuming and costly trial-and-error experiments. In this study, the sintering data for more than a dozen W(Mo) alloys constituted a small-scale dataset, including both solid and liquid phases of sintering. Furthermore, simple descriptors were used to predict the sintered density of W(Mo) alloys based on the descriptor selection strategy and machine learning method (ML), where the ML algorithm included the least absolute shrinkage and selection operator (Lasso) regression, k-nearest neighbor (k-NN), random forest (RF), and multi-layer perceptron (MLP). The results showed that the interpretable descriptors extracted by our proposed selection strategy and the MLP neural network achieved a high prediction accuracy (R>0.950). By further predicting the sintered density of W(Mo) alloys using different sintering processes, the error between the predicted and experimental values was less than 0.063, confirming the application potential of the model.

Keywords: sintered density, machine learning, interpretable descriptors, W(Mo) alloy

Procedia PDF Downloads 86

Authors: My Hachem Aouragh, Hind Ragragui, Abdellah El-Hmaidi, Ali Essahlaoui, Abdelhadi El Ouali

Abstract:

This study investigates soil erosion susceptibility in the Oued Mikkes watershed, located in the Meknes-Fez region of northern Morocco, utilizing advanced techniques such as deep learning algorithms and remote sensing integrated within Geographic Information Systems (GIS). Spanning approximately 1,920 km², the watershed is characterized by a semi-arid Mediterranean climate with irregular rainfall and limited water resources. The waterways within the watershed, especially the Oued Mikkes, are vital for agricultural irrigation and potable water supply. The research assesses the extent of erosion risk upstream of the Sidi Chahed dam while developing a spatial model of soil loss. Several important factors, including topography, land use/land cover, and climate, were analyzed, with data on slope, NDVI, and rainfall erosivity processed using deep learning models (DLNN, CNN, RNN). The results demonstrated excellent predictive performance, with AUC values of 0.92, 0.90, and 0.88 for DLNN, CNN, and RNN, respectively. The resulting susceptibility maps provide critical insights for soil management and conservation strategies, identifying regions at high risk for erosion across 24% of the study area. The most high-risk areas are concentrated on steep slopes, particularly near the Ifrane district and the surrounding mountains, while low-risk areas are located in flatter regions with less rugged topography. The combined use of remote sensing and deep learning offers a powerful tool for accurate erosion risk assessment and resource management in the Mikkes watershed, highlighting the implications of soil erosion on dam siltation and operational efficiency.

Keywords: soil erosion, GIS, remote sensing, deep learning, Mikkes Watershed, Morocco

Procedia PDF Downloads 27

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 72

Authors: Masood Varshosaz, Kamyar Hasanpour

Abstract:

In recent years, we have seen growing interest in recognizing humans in drone images for post-disaster search and rescue operations. Deep learning algorithms have shown great promise in this area, but they often require large amounts of labeled data to train the models. To keep the data acquisition cost low, augmentation techniques can be used to create additional data from existing images. There are many techniques of such that can help generate variations of an original image to improve the performance of deep learning algorithms. While data augmentation is potentially assumed to improve the accuracy and robustness of the models, it is important to ensure that the performance gains are not outweighed by the additional computational cost or complexity of implementing the techniques. To this end, it is important to evaluate the impact of data augmentation on the performance of the deep learning models. In this paper, we evaluated the most currently available 2D data augmentation techniques on a standard convolutional network which was trained for recognizing humans in drone images. The techniques include rotation, scaling, random cropping, flipping, shifting, and their combination. The results showed that the augmented models perform 1-3% better compared to a base network. However, as the augmented images only contain the human parts already visible in the original images, a new data augmentation approach is needed to include the invisible parts of the human body. Thus, we suggest a new method that employs simulated 3D human models to generate new data for training the network.

Keywords: human recognition, deep learning, drones, disaster mitigation

Procedia PDF Downloads 101

Authors: C. von Essen

Abstract:

This study outlines and evaluates a constructivist design approach to the creation of educational video on postgraduate business degree programmes. Many online courses are tapping into the educational affordances of video, as this form of online learning has the potential to create rich, multimodal experiences. And yet, in many learning contexts video is still being used to transmit instruction to passive learners, rather than promote learner engagement and knowledge creation. Constructivism posits the notion that learning is shaped as students make connections between their experiences and ideas. This paper pivots on the following research question: how can we design educational video in ways which promote constructivist learning and stimulate analytic viewing? By exploring and categorizing over two thousand educational videos created since 2014 for over thirty postgraduate courses in business, economics, mathematics and statistics, this paper presents and critically reflects on a taxonomy of video styles and features. It links the pedagogical intent of video – be it concept explanation, skill demonstration, feedback, real-world application of ideas, community creation, or the cultivation of course narrative – to specific presentational characteristics such as visual effects including diagrammatic and real-life graphics and aminations, commentary and sound options, chronological sequencing, interactive elements, and presenter set-up. The findings of this study inform a framework which captures the pedagogical, technological and production considerations instructional designers and educational media specialists should be conscious of when planning and preparing the video. More broadly, the paper demonstrates how learning theory and technology can coalesce to produce informed and pedagogical grounded instructional design choices. This paper reveals how crafting video in a more conscious and critical manner can produce powerful, new educational design.

Keywords: educational video, constructivism, instructional design, business education

Procedia PDF Downloads 241

Authors: P. Senthil Kumari

Abstract:

Main concerns in data mining investigation are social controls of data mining for handling ambiguity, noise, or incompleteness on text data. We describe an innovative approach for unplanned text data detection of community networks achieved by classification mechanism. In a tangible domain claim with humble secrecy backgrounds provided by community network for evading annoying content is presented on consumer message partition. To avoid this, mining methodology provides the capability to unswervingly switch the messages and similarly recover the superiority of ordering. Here we designated learning-centered mining approaches with pre-processing technique to complete this effort. Our involvement of work compact with rule-based personalization for automatic text categorization which was appropriate in many dissimilar frameworks and offers tolerance value for permits the background of comments conferring to a variety of conditions associated with the policy or rule arrangements processed by learning algorithm. Remarkably, we find that the choice of classifier has predicted the class labels for control of the inadequate documents on community network with great value of effect.

Keywords: text mining, data classification, community network, learning algorithm

Procedia PDF Downloads 513

Authors: Yuet Wah Echo Yeung

Abstract:

Working with people from minority ethnic groups, refugees and asylum seeking communities who have limited proficiency in the language of the host country often presents a major challenge for social workers. Because of language differences, social workers need to work with interpreters to ensure accurate information is collected for their assessment and intervention. Drawing from social learning theory, this paper discusses how role play was used as an experiential learning exercise in a training session to help social work students develop skills when working with interpreters. Social learning theory posits that learning is a cognitive process that takes place in a social context when people observe, imitate and model others’ behaviours. The roleplay also helped students understand the role of the interpreter and the challenges they may face when they rely on interpreters to communicate with service users and their family. The first part of the session involved role play. A tutor played the role of social worker and deliberately behaved in an unprofessional manner and used inappropriate body language when working alongside the interpreter during a home visit. The purpose of the roleplay is not to provide a positive role model for students to ‘imitate’ social worker’s behaviours. Rather it aims to active and provoke internal thinking process and encourages students to critically consider the impacts of poor practice on relationship building and the intervention process. Having critically reflected on the implications for poor practice, students were then asked to play the role of social worker and demonstrate what good practice should look like. At the end of the session, students remarked that they learnt a lot by observing the good and bad example; it showed them what not to do. The exercise served to remind students how practitioners can easily slip into bad habits and of the importance of respect for the cultural difference when working with people from different cultural backgrounds.

Keywords: role play, social learning theory, social work practice, working with interpreters

Procedia PDF Downloads 183

Authors: Suffian Hadi Ayub, Mohammad Rezal Hamzah, Nor Hafizah Abdullah, Sharipah Nur Mursalina Syed Azmy, Hishamuddin Salim

Abstract:

The liberalisation of the education industry has exposed the institute of higher learning (IHL) in Malaysia to the financial challenges. Without good financial standing, public institution will rely on the government funding. Ostensibly, this contradicts with the government’s aspiration to make universities self-sufficient. With stiff competition from private institutes of higher learning, IHL need to be prepared at the forefront level. The corporate identity itself is the entrance to the world of higher learning and it is in this uniqueness, it will be able to distinguish itself from competitors. This paper examined the perception of the stakeholders at one of the public universities in the east coast region in Malaysia on the perceived reputation and how the university communicate its preparedness for self-sustainability through corporate identity. The findings indicated while the stakeholders embraced the challenges in facing the stiff competition and struggling market conditions, most of them felt the university should put more efforts in mobilising the corporate identity to its constituencies.

Keywords: communication, corporate identity, market conditions, universities

Procedia PDF Downloads 320

Authors: Jonathan Heng, Yoong Cheah Huei

Abstract:

A strategic model that does not trigger any false alarms to detect anomalies in Secure Water Treatment (SWaT) test bed is presented. This model uses machine learning invariants formulated from streamlining the general form of Auto-Regressive models with eXogenous input. A creative generalized CUSUM algorithm to integrate the invariants and the detection strategy technique is successfully developed and tested in the SWaT Programmable Logic Controllers (PLCs). Three steps to fine-tune parameters, b and τ in the generalized algorithm are stated and an example used to demonstrate the tuning process is discussed. This approach can swiftly and effectively detect various scopes of cyber-attacks such as multiple points single stage and multiple points multiple stages in SWaT. This technique can be applied in water treatment plants and other cyber physical systems like power and gas plants too.

Keywords: machine learning invariants, generalized CUSUM algorithm with invariants and detection strategy, scope of cyber attacks, strategic model, tuning parameters

Procedia PDF Downloads 186

Authors: Juha Kettunen

Abstract:

The purpose of this study is to develop a framework for the assessment of research and development projects. The assessment map is developed in this study based on the strategy map of the balanced scorecard approach. The assessment map is applied in a project that aims to reduce the inequality and risk of exclusion of young people from disadvantaged social groups. The assessment map denotes that not only funding but also necessary skills and qualifications should be carefully assessed in the implementation of the project plans so as to achieve the objectives of projects and the desired impact. The results of this study are useful for those who want to develop the implementation of the Erasmus+ Programme and the project teams of research and development projects.

Keywords: non-formal learning, youth work, social inclusion, innovation

Procedia PDF Downloads 302

Authors: Terence Soule, Tami Al Ghamdi

Abstract:

To study how the partial knowledge transfer may affect the Genetic Algorithm (GA) performance, we model the Transfer Learning (TL) process using GA as the model solver. The objective of the TL is to transfer the knowledge from one problem to another related problem. This process imitates how humans think in their daily life. In this paper, we proposed to study a case where the knowledge transferred from the S problem has less information than what the T problem needs. We sampled the transferred population using different strategies of TL. The results showed transfer part of the knowledge is helpful and speeds the GA process of finding a solution to the problem.

Keywords: transfer learning, partial transfer, evolutionary computation, genetic algorithm

Procedia PDF Downloads 136

Authors: Tolulope Aremu

Abstract:

This paper is based on the idea of using deep learning methodology for optimizing production yield by tuning a few key process parameters in a manufacturing environment. The study was explicitly on how to maximize production yield and minimize operational costs by utilizing advanced neural network models, specifically Long Short-Term Memory and Convolutional Neural Networks. These models were implemented using Python-based frameworks—TensorFlow and Keras. The targets of the research are the precision molding processes in which temperature ranges between 150°C and 220°C, the pressure ranges between 5 and 15 bar, and the material flow rate ranges between 10 and 50 kg/h, which are critical parameters that have a great effect on yield. A dataset of 1 million production cycles has been considered for five continuous years, where detailed logs are present showing the exact setting of parameters and yield output. The LSTM model would model time-dependent trends in production data, while CNN analyzed the spatial correlations between parameters. Models are designed in a supervised learning manner. For the model's loss, an MSE loss function is used, optimized through the Adam optimizer. After running a total of 100 training epochs, 95% accuracy was achieved by the models recommending optimal parameter configurations. Results indicated that with the use of RSM and DOE traditional methods, there was an increase in production yield of 12%. Besides, the error margin was reduced by 8%, hence consistent quality products from the deep learning models. The monetary value was annually around $2.5 million, the cost saved from material waste, energy consumption, and equipment wear resulting from the implementation of optimized process parameters. This system was deployed in an industrial production environment with the help of a hybrid cloud system: Microsoft Azure, for data storage, and the training and deployment of their models were performed on Google Cloud AI. The functionality of real-time monitoring of the process and automatic tuning of parameters depends on cloud infrastructure. To put it into perspective, deep learning models, especially those employing LSTM and CNN, optimize the production yield by fine-tuning process parameters. Future research will consider reinforcement learning with a view to achieving further enhancement of system autonomy and scalability across various manufacturing sectors.

Keywords: production yield optimization, deep learning, tuning of process parameters, LSTM, CNN, precision manufacturing, TensorFlow, Keras, cloud infrastructure, cost saving

Procedia PDF Downloads 42