Search results for: language learning model

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 71

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 380

Authors: A. Bentabet, A. Aydin, N. Fenineche

Abstract:

The mean penetration depth has a most important in the absorption transport phenomena. Analytical model of light ion backscattering coefficients from solid targets have been made by Vicanek and Urbassek. In the present work, we showed a mathematical expression (deterministic model) for Z1/2. In advantage, in the best of our knowledge, relatively only one analytical model exit for electron or positron mean penetration depth in solid targets. In this work, we have presented a simple geometric spherical model of absorbed particles based on CSDA scheme. In advantage, we have showed an analytical expression of the mean penetration depth by combination between our model and the Vicanek and Urbassek theory. For this, we have used the Relativistic Partial Wave Expansion Method (RPWEM) and the optical dielectric model to calculate the elastic cross sections and the ranges respectively. Good agreement was found with the experimental and theoretical data.

Keywords: Bentabet spherical geometric model, continuous slowing down approximation, stopping powers, ranges, mean penetration depth

Procedia PDF Downloads 636

Authors: Azizah Che Omar

Abstract:

Various studies have proposed factors of impulse purchase in different advertising mediums like website, mobile, traditional retail store and traditional television. However, to the best of researchers’ knowledge, none of the impulse purchase model is dedicated towards impulse purchase tendency for interactive TV (iTV) advertising. Therefore, the proposed model conceptual design model of interactive television advertising toward impulse purchase (iTVAdIP) was developed. The focus of this study is to evaluate the conceptual design model of iTVAdIP through expert review. As a result, the finding showed that majority of expert reviews agreed that the conceptual design model iTVAdIP is applicable to the development of interactive television advertising and it will increase the effectiveness of advertising. This study also shows the conceptual design model of iTVAdIP that has been reviewed.

Keywords: impulse purchase, interactive television advertising, persuasive

Procedia PDF Downloads 348

Authors: C.W. Kan

Abstract:

This paper investigates the use of atmospheric pressure plasma for improving the surface hydrophobicity of polyurethane synthetic leather with tetramethylsilane (TMS). The atmospheric pressure plasma treatment with TMS is a single-step process to enhance the hydrophobicity of polyurethane synthetic leather. The hydrophobicity of the treated surface was examined by contact angle measurement. The physical and chemical surface changes were evaluated by scanning electron microscopy (SEM) and infrared spectroscopy (FTIR). The purpose of this paper is to provide learning materials for understanding how to use atmospheric pressure plasma in the textile finishing process to transform a hydrophilic surface to hydrophobic.

Keywords: Learning materials, atmospheric pressure plasma treatment, hydrophobic, hydrophilic, surface

Procedia PDF Downloads 349

Authors: Tanmay Bisen, Aastha Shayla

Abstract:

This study introduces an advanced approach to tree canopy detection in urban environments and a regional analysis of Northern and Central Kolkata that delves into the intricate relationship between urban development and environmental conservation. Leveraging high-resolution drone imagery from diverse urban green spaces in Kolkata, we fine-tuned the deep forest model to enhance its precision and accuracy. Our results, characterized by an impressive Intersection over Union (IoU) score of 0.90 and a mean average precision (mAP) of 0.87, underscore the model's robustness in detecting and classifying tree crowns amidst the complexities of aerial imagery. This research not only emphasizes the importance of model customization for specific datasets but also highlights the potential of drone-based remote sensing in urban forestry studies. The study investigates the spatial distribution, density, and environmental impact of trees in Northern and Central Kolkata. The findings underscore the significance of urban green spaces in met-ropolitan cities, emphasizing the need for sustainable urban planning that integrates green infrastructure for ecological balance and human well-being.

Keywords: urban greenery, advanced spatial distribution analysis, drone imagery, deep learning, tree detection

Procedia PDF Downloads 44

Authors: S. Shamohammadi, L. Razavi

Abstract:

This paper based on the principle concepts of SCS-CN model, a new mathematical model for computation of retention potential (S) presented. In the mathematical model, not only precipitation-runoff concepts in SCS-CN model are precisely represented in a mathematical form, but also new concepts, called “maximum retention” and “total retention” is introduced, and concepts of potential retention capacity, maximum retention, and total retention have been separated from each other. In the proposed model, actual retention (F), maximum actual retention (Fmax), total retention (S), maximum retention (Smax), and potential retention (Sp), for the first time clearly defined, so that Sp is not variable, but a function of morphological characteristics of the watershed. Indeed, based on the mathematical relation of the conceptual curve of SCS-CN model, the proposed model provides a new method for the computation of actual retention in watershed and it simply determined runoff based on. In the corresponding relations, in addition to Precipitation (P), Initial retention (Ia), cumulative values of actual retention capacity (F), total retention (S), runoff (Q), antecedent moisture (M), potential retention (Sp), total retention (S), we introduced Fmax and Fmin referring to maximum and minimum actual retention, respectively. As well as, ksh is a coefficient which depends on morphological characteristics of the watershed. Advantages of the modified version versus the original model include a better precision, higher performance, easier calibration and speed computing.

Keywords: model, mathematical, retention, watershed, SCS

Procedia PDF Downloads 449

Authors: Diana Mitova, Krassimir Mitrev

Abstract:

To prepare the current generation for the future, education systems need to change. It implies a way of learning that meets the demands of the times and the environment in which we live. Productive interaction in the educational process implies an interactive learning environment and the possibility of personal development of learners based on communication and mutual dialogue, cooperation and good partnership in decision-making. Students need not only theoretical knowledge, but transferable skills that will help them to become inventors and entrepreneurs, to implement ideas. STEM education , is now a real necessity for the modern school. Through learning in a "learning company", students master examples from classroom practice, simulate real life situations, group activities and apply basic interactive learning strategies and techniques. The learning company is the subject of this study, reduced to entrepreneurship training in STEM - technologies that encourage students to think outside the traditional box. STEM learning focuses the teacher's efforts on modeling entrepreneurial thinking and behavior in students and helping them solve problems in the world of business and entrepreneurship. Learning based on the implementation of various STEM projects in extracurricular activities, experiential learning, and an interdisciplinary approach are means by which educators better connect the local community and private businesses. Learners learn to be creative, experiment and take risks and work in teams - the leading characteristics of any innovator and future entrepreneur. This article presents some European policies on STEM and entrepreneurship education. It also shares best practices for training company training , with the integration of STEM in the learning company training environment. The main results boil down to identifying some advantages and problems in STEM entrepreneurship education. The benefits of using integrative approaches to teach STEM within a training company are identified, as well as the positive effects of project-based learning in a training company using STEM. Best practices for teaching entrepreneurship through extracurricular activities using STEM within a training company are shared. The following research methods are applied in this research paper: Theoretical and comparative analysis of principles and policies of European Union countries and Bulgaria in the field of entrepreneurship education through a training company. Experiences in entrepreneurship education through extracurricular activities with STEM application within a training company are shared. A questionnaire survey to investigate the motivation of secondary vocational school students to learn entrepreneurship through a training company and their readiness to start their own business after completing their education. Within the framework of learning through a "learning company" with the integration of STEM, the activity of the teacher-facilitator includes the methods: counseling, supervising and advising students during work. The expectation is that students acquire the key competence "initiative and entrepreneurship" and that the cooperation between the vocational education system and the business in Bulgaria is more effective.

Keywords: STEM, entrepreneurship, training company, extracurricular activities

Procedia PDF Downloads 90

Authors: Kien Vu, Jien Min Soh, Mohamed Jahangir Abubacker, Piyawut Pattamanon, Soojin Lee, Suvro Banerjee

Abstract:

Recent advances in Generative Artificial Intelligence (GenAI), in particular Large Language Models (LLMs) have shown promise to disrupt multiple industries at scale. However, LLMs also present unique challenges, notably, these so-called "hallucination" which is the generation of outputs that are not grounded in the input data that hinders its adoption into production. Common practice to mitigate hallucination problem is utilizing Retrieval Agmented Generation (RAG) system to ground LLMs'response to ground truth. RAG converts the grounding documents into embeddings, retrieve the relevant parts with vector similarity between user's query and documents, then generates a response that is not only based on its pre-trained knowledge but also on the specific information from the retrieved documents. However, the RAG system is not suitable for tabular data and subsequent data analysis tasks due to multiple reasons such as information loss, data format, and retrieval mechanism. In this study, we have explored a novel methodology that combines planning-and-execution and code generation agents to enhance LLMs' data analysis capabilities. The approach enables LLMs to autonomously dissect a complex analytical task into simpler sub-tasks and requirements, then convert them into executable segments of code. In the final step, it generates the complete response from output of the executed code. When deployed beta version on DataSense, the property insight tool of PropertyGuru, the approach yielded promising results, as it was able to provide market insights and data visualization needs with high accuracy and extensive coverage by abstracting the complexities for real-estate agents and developers from non-programming background. In essence, the methodology not only refines the analytical process but also serves as a strategic tool for real estate professionals, aiding in market understanding and enhancement without the need for programming skills. The implication extends beyond immediate analytics, paving the way for a new era in the real estate industry characterized by efficiency and advanced data utilization.

Keywords: large language model, reasoning, planning and execution, code generation, natural language processing, prompt engineering, data analysis, real estate, data sense, PropertyGuru

Procedia PDF Downloads 76

Authors: Hossam Ali-Hassan, Michael Bliemel

Abstract:

This poster reflects upon our experiences using INNOV8, IBM’s Business Process Management (BPM) simulation game, in online MBA and undergraduate MIS classes over a period of 2 years. The game is designed to gives both business and information technology players a better understanding of how effective BPM impacts an entire business ecosystem. The game includes three different scenarios: Smarter Traffic, which is used to evaluate existing traffic patterns and re-route traffic based on incoming metrics; Smarter Customer Service where players develop more efficient ways to respond to customers in a call centre environment; and Smarter Supply Chains where players balance supply and demand and reduce environmental impact in a traditional supply chain model. We use the game as an experiential learning tool, where students have to act as managers making real time changes to business processes to meet changing business demands and environments. The students learn how information technology (IT) and information systems (IS) can be used to intelligently solve different problems and how computer simulations can be used to test different scenarios or models based on business decisions without having to actually make the potentially costly and/or disruptive changes to business processes. Moreover, when students play the three different scenarios, they quickly see how practical process improvements can help meet profitability, customer satisfaction and environmental goals while addressing real problems faced by municipalities and businesses today. After spending approximately two hours in the game, students reflect on their experience from it to apply several BPM principles that were presented in their textbook through the use of a structured set of assignment questions. For each final scenario students submit a screenshot of their solution followed by one paragraph explaining what criteria you were trying to optimize, and why they picked their input variables. In this poster we outline the course and the module’s learning objectives where we used the game to place this into context. We illustrate key features of the INNOV8 Simulation Game, and describe how we used them to reinforce theoretical concepts. The poster will also illustrate examples from the simulation, assignment, and learning outcomes.

Keywords: experiential learning, business process management, BPM, INNOV8, simulation, game

Procedia PDF Downloads 325

Authors: Zena Tredinnick-Kirby, Anna Divinsky, Brendan Berthold, Nicole Cingolani

Abstract:

Faculty members from The Pennsylvania State University, Zena Tredinnick-Kirby, Ph.D., and Anna Divinsky are at the forefront of an innovative educational approach to improve access in asynchronous online art courses. Their pioneering work weaves virtual reality (VR) technologies to construct a more equitable educational experience for students by transforming their learning and engagement. The significance of their study lies in the need to bridge the digital divide in online art courses, making them more inclusive and interactive for all distance learners. In an era where conventional classroom settings are no longer the sole means of instruction, Tredinnick-Kirby and Divinsky harness the power of instructional technologies to break down geographical barriers by incorporating an interactive VR experience that facilitates community building within an online environment transcending physical constraints. The methodology adopted by Tredinnick-Kirby, and Divinsky is centered around integrating 3D virtual spaces into their art courses. Spatial.io, a virtual world platform, enables students to develop digital avatars and engage in virtual art museums through a free browser-based program or an Oculus headset, where they can interact with other visitors and critique each other’s artwork. The goal is not only to provide students with an engaging and immersive learning experience but also to nourish them with a more profound understanding of the language of art criticism and technology. Furthermore, the study aims to cultivate critical thinking skills among students and foster a collaborative spirit. By leveraging cutting-edge VR technology, students are encouraged to explore the possibilities of their field, experimenting with innovative tools and techniques. This approach not only enriches their learning experience but also prepares them for a dynamic and ever-evolving art landscape in technology and education. One of the fundamental objectives of Tredinnick-Kirby and Divinsky is to remodel how feedback is derived through peer-to-peer art critique. Through the inclusion of 3D virtual spaces into the curriculum, students now have the opportunity to install their final artwork in a virtual gallery space and incorporate peer feedback, enabling students to exhibit their work opening the doors to a collaborative and interactive process. Students can provide constructive suggestions, engage in discussions, and integrate peer commentary into developing their ideas and praxis. This approach not only accelerates the learning process but also promotes a sense of community and growth. In summary, the study conducted by the Penn State faculty members Zena Tredinnick-Kirby, and Anna Divinsky represents innovative use of technology in their courses. By incorporating 3D virtual spaces, they are enriching the learners' experience. Through this inventive pedagogical technique, they nurture critical thinking, collaboration, and the practical application of cutting-edge technology in art. This research holds great promise for the future of online art education, transforming it into a dynamic, inclusive, and interactive experience that transcends the confines of distance learning.

Keywords: Art, community building, distance learning, virtual reality

Procedia PDF Downloads 62

Authors: Catherine Mangan, Beth Anderson

Abstract:

There has been a significant drive to use online or hybrid learning in Higher Education (HE) over recent years. HEs with a virtual presence offer their communities a range of benefits, including the potential for greater inclusivity, diversity, and collaboration; more flexible learning packages; and more engaging, dynamic content. Institutions can also experience significant challenges when seeking to extend learning spaces in this way, as can learners themselves. For example, staff members’ and learners’ digital literacy varies (as do their perceptions of technologies in use), and there can be confusion about optimal approaches to implementation. Furthermore, the speed with which HE institutions have needed to shift to fully online or hybrid models, owing to the COVID19 pandemic, has highlighted the significant barriers to successful implementation. HE environments have been shown to predict a range of organisational, academic, and experiential outcomes, both positive and negative. Much research has focused on the social aspect of virtual platforms, as well as the nature and effectiveness of the technologies themselves. There remains, however, a relative paucity of synthesised knowledge on the psychology of learners’ relationships with their institutions; specifically, how individual difference and interpersonal factors predict students’ ability and willingness to engage with novel virtual learning spaces. Accordingly, extending learning spaces remains challenging for institutions, and wholly remote courses, in particular, can experience high attrition rates. Focusing on the last five years, this pragmatic review summarises evidence from the psychological and pedagogical literature. In particular, the review highlights the importance of addressing the psychological and relational complexities of students’ shift from offline to online engagement. In doing so, it identifies considerations for HE institutions looking to deliver in this way.

Keywords: higher education, individual differences, interpersonal relationships, online learning, virtual environment

Procedia PDF Downloads 170

Authors: Nashwah Alnajjar

Abstract:

This research paper provides an overview of Replika, an AI chatbot application that uses natural language processing technology to engage in conversations with users. The app was developed to provide users with a virtual AI friend who can converse with them on various topics, including mental health. This study explores the experiences of Replika users using quantitative research methodology. A survey was conducted with 12 participants to collect data on their demographics, usage patterns, and experiences with the Replika app. The results showed that Replika has the potential to play a role in mental health support and well-being.

Keywords: Replika, chatbot, mental health, artificial intelligence, natural language processing

Procedia PDF Downloads 79

Authors: Stephen Kirkup

Abstract:

This paper discusses the implementation of the boundary element method (BEM) on an Excel spreadsheet and how it can be used in teaching vector calculus and simulation. There are two separate spreadheets, within which Laplace equation is solved by the BEM in two dimensions (LIBEM2) and axisymmetric three dimensions (LBEMA). The main algorithms are implemented in the associated programming language within Excel, Visual Basic for Applications (VBA). The BEM only requires a boundary mesh and hence it is a relatively accessible method. The BEM in the open spreadsheet environment is demonstrated as being useful as an aid to teaching and learning. The application of the BEM implemented on a spreadsheet for educational purposes in introductory vector calculus and simulation is explored. The development of assignment work is discussed, and sample results from student work are given. The spreadsheets were found to be useful tools in developing the students’ understanding of vector calculus and in simulating heat conduction.

Keywords: boundary element method, Laplace’s equation, vector calculus, simulation, education

Procedia PDF Downloads 157

Authors: Gaokai Liu

Abstract:

Automatic defect detection for nanomaterial images is widely required in industrial scenarios. Deep learning approaches are considered as the most effective solutions for the great majority of image-based tasks. In this paper, an edge guidance network for defect segmentation is proposed. First, the encoder path with multiple convolution and downsampling operations is applied to the acquisition of shared features. Then two decoder paths both are connected to the last convolution layer of the encoder and supervised by the edge and segmentation labels, respectively, to guide the whole training process. Meanwhile, the edge and encoder outputs from the same stage are concatenated to the segmentation corresponding part to further tune the segmentation result. Finally, the effectiveness of the proposed method is verified via the experiments on open nanofibrous datasets.

Keywords: deep learning, defect detection, image segmentation, nanomaterials

Procedia PDF Downloads 142

Authors: Małgorzata Anna Karczmarzyk

Abstract:

Who is the contemporary child? What are his/her distinctive features making him/her different from earlier generations? And how to teach in the dissimilar social reality? These questions will constitute the key to my reflections on contemporary early school education. For, to my mind, games have become highly significant for the modern model of education. There arise publications and research employing games to increase competence both in business, tutoring, or coaching, as well as in academic education . Thanks to games students and subordinates can be taught such abilities as problem thinking, creativity, consistent fulfillment of goals, resourcefulness and skills of communication.

Keywords: games, art, children, school education, integration

Procedia PDF Downloads 846

Authors: Diane Ghanem, Oscar Covarrubias, Michael Raad, Dawn LaPorte, Babar Shafiq

Abstract:

Introduction: Standardized exams have long been considered a cornerstone in measuring cognitive competency and academic achievement. Their fixed nature and predetermined scoring methods offer a consistent yardstick for gauging intellectual acumen across diverse demographics. Consequently, the performance of artificial intelligence (AI) in this context presents a rich, yet unexplored terrain for quantifying AI's understanding of complex cognitive tasks and simulating human-like problem-solving skills. Publicly available AI language models such as ChatGPT have demonstrated utility in text generation and even problem-solving when provided with clear instructions. Amidst this transformative shift, the aim of this study is to assess ChatGPT’s performance on the orthopaedic surgery in-training examination (OITE). Methods: All 213 OITE 2021 web-based questions were retrieved from the AAOS-ResStudy website. Two independent reviewers copied and pasted the questions and response options into ChatGPT Plus (version 4.0) and recorded the generated answers. All media-containing questions were flagged and carefully examined. Twelve OITE media-containing questions that relied purely on images (clinical pictures, radiographs, MRIs, CT scans) and could not be rationalized from the clinical presentation were excluded. Cohen’s Kappa coefficient was used to examine the agreement of ChatGPT-generated responses between reviewers. Descriptive statistics were used to summarize the performance (% correct) of ChatGPT Plus. The 2021 norm table was used to compare ChatGPT Plus’ performance on the OITE to national orthopaedic surgery residents in that same year. Results: A total of 201 were evaluated by ChatGPT Plus. Excellent agreement was observed between raters for the 201 ChatGPT-generated responses, with a Cohen’s Kappa coefficient of 0.947. 45.8% (92/201) were media-containing questions. ChatGPT had an average overall score of 61.2% (123/201). Its score was 64.2% (70/109) on non-media questions. When compared to the performance of all national orthopaedic surgery residents in 2021, ChatGPT Plus performed at the level of an average PGY3. Discussion: ChatGPT Plus is able to pass the OITE with a satisfactory overall score of 61.2%, ranking at the level of third-year orthopaedic surgery residents. More importantly, it provided logical reasoning and justifications that may help residents grasp evidence-based information and improve their understanding of OITE cases and general orthopaedic principles. With further improvements, AI language models, such as ChatGPT, may become valuable interactive learning tools in resident education, although further studies are still needed to examine their efficacy and impact on long-term learning and OITE/ABOS performance.

Keywords: artificial intelligence, ChatGPT, orthopaedic in-training examination, OITE, orthopedic surgery, standardized testing

Procedia PDF Downloads 78

Authors: Cassandra Branham, Danielle Farrar

Abstract:

As writing instructors and writing center administrators at a large research university with a significant population of English language learners (ELLs), we are interested in how peer feedback pedagogy can be effectively translated for writing center purposes, as well as how various modes of peer feedback can enrich the learning experiences of L1 and L2 writers in these spaces. Although peer feedback is widely used in classrooms and centers, instructor, student, and researcher opinions vary in respect to its effectiveness. We argue that peer feedback - traditional and digital, synchronous and asynchronous - is an indispensable element for both classrooms and centers and emphasize that it should occur with both L1 and L2 students to further develop an array of reading and writing skills. We also believe that further understanding of the best practices of peer feedback in such cross-cultural spaces, like the classroom and center, can optimize the benefits of peer feedback. After a critical review of the literature, we implemented an embedded tutoring program in our university’s writing center in collaboration with its First-Year Composition (FYC) program and Language Institute. The embedded tutoring program matches a graduate writing consultant with L1 and L2 writers enrolled in controlled-matriculation composition courses where ELLs make up at least 50% of each class. Furthermore, this program is informed by what we argue to be some best practices of peer feedback for both classroom and center purposes, including expectation-based training through rubrics, modeling effective feedback, hybridizing traditional and digital modes of feedback, recognizing the significance the body in composition (what we call writer embodiment), and maximizing digital technologies to exploit extended cognition. After conducting surveys and follow-up interviews with students, instructors, and writing consultants in the embedded tutoring program, we found that not only did students see an increased value in peer feedback, but also instructors saw an improvement in both writing style and critical thinking skills. Our L2 participants noted improvements in language acquisition while our L1 students recognized a broadening of their worldviews. We believe that both L1 and L2 students developed self-efficacy and agency in their identities as writers because they gained confidence in their abilities to offer feedback, as well as in the legitimacy of feedback they received from peers. We also argue that these best practices situate novice writers as experts, as writers become a valued and integral part of the revision process with their own and their peers’ papers. Finally, the use of iPads in embedded tutoring recovered the importance of the body and its senses in writing; the highly sensory feedback from these multi-modal sessions that offer audio and visual input underscores the significant role both the body and mind play in compositional practices. After beginning with a brief review of the literature that sparked this research, this paper will discuss the embedded tutoring program in detail, report on the results of the pilot program, and will conclude with a discussion of the pedagogical implications that arise from this research for both classroom and center.

Keywords: English language learners, peer feedback, writing center, writing classroom

Procedia PDF Downloads 396

Authors: Marios Papaevripidou, Yvoni Pavlou, Zacharias Zacharia

Abstract:

Embodied cognition and additional (touch) sensory channel theories indicate that physical manipulation is crucial to learning since it provides, among others, touch sensory input, which is needed for constructing knowledge. Given these theories, the use of Physical Manipulatives (PM) becomes a prerequisite for learning. On the other hand, empirical research on Virtual Manipulatives (VM) (e.g., simulations) learning has provided evidence showing that the use of PM, and thus haptic sensory input, is not always a prerequisite for learning. In order to investigate which means of experimentation, PM or VM, are required for enhancing student science learning at the kindergarten level, an empirical study was conducted that sought to investigate the impact of haptic feedback on the conceptual understanding of pre-school students (n=44, age mean=5,7) in three science domains: beam balance (D1), sinking/floating (D2) and springs (D3). The participants were equally divided in two groups according to the type of manipulatives used (PM: presence of haptic feedback, VM: absence of haptic feedback) during a semi-structured interview for each of the domains. All interviews followed the Predict-Observe-Explain (POE) strategy and consisted of three phases: initial evaluation, experimentation, final evaluation. The data collected through the interviews were analyzed qualitatively (open-coding for identifying students’ ideas in each domain) and quantitatively (use of non-parametric tests). Findings revealed that the haptic feedback enabled students to distinguish heavier to lighter objects when held in hands during experimentation. In D1 the haptic feedback did not differentiate PM and VM students' conceptual understanding of the function of the beam as a mean to compare the mass of objects. In D2 the haptic feedback appeared to have a negative impact on PM students’ learning. Feeling the weight of an object strengthen PM students’ misconception that heavier objects always sink, whereas the scientifically correct idea that the material of an object determines its sinking/floating behavior in the water was found to be significantly higher among the VM students than the PM ones. In D3 the PM students outperformed significantly the VM students with regard to the idea that the heavier an object is the more the spring will expand, indicating that the haptic input experienced by the PM students served as an advantage to their learning. These findings point to the fact that PMs, and thus touch sensory input, might not always be a requirement for science learning and that VMs could be considered, under certain circumstances, as a viable means for experimentation.

Keywords: haptic feedback, physical and virtual manipulatives, pre-school science learning, science experimentation

Procedia PDF Downloads 131

Authors: Yutong Xu, Wanting Zhang, Jia Wang, Zihan Guo, Weiguang Ma

Abstract:

Background: The resilience education of intern nursing students has significant implications for the development and improvement of the nursing workforce. The clinical internship period is a critical time for enhancing resilience. Aims: To evaluate the resilience level of Chinese nursing interns and identify the factors affecting resilience early in their careers. Methods: The cross-sectional study design was adopted. From March 2022 to May 2023, 512 nursing interns in tertiary care hospitals were surveyed online with the Connor-Davidson Resilience Scale, the Clinical Learning Environment scale for Nurse, and the Career Adapt-Abilities Scale. Structural equation modeling was used to clarify the relationships among these factors. Indirect effects were tested using bootstrapped Confidence Intervals. Results: The nursing interns showed a moderately high level of resilience[M(SD)=70.15(19.90)]. Gender, scholastic attainment, had a scholarship, career adaptability and clinical learning environment were influencing factors of nursing interns’ resilience. Career adaptability and clinical learning environment positively and directly affected their resilience level (β = 0.58, 0.12, respectively, p＜0.01). career adaptability also positively affected career adaptability (β = 0.26, p < 0.01), and played a fully mediating role in the relationship between clinical learning environment and resilience. Conclusion: Career adaptability can enhance the influence of clinical learning environment on resilience. The promotion of career adaptability and the clinical teaching environment should be the potential strategies for nursing interns to improve their resilience, especially for those female nursing interns with low academic performance. Implications for Nursing Educators Nursing educators should pay attention to the cultivation of nursing students' resilience; for example, by helping them integrate to the clinical learning environment and improving their career adaptability. Reporting Method: The STROBE criteria were used to report the results of the observations critically. Patient or Public Contribution No patient or public contribution.

Keywords: resilience, clinical learning environment, career adaptability, nursing interns

Procedia PDF Downloads 76

Authors: Arya Prakash Padhi, Anupam Chakrabarti, Rajib Chowdhury

Abstract:

Topology or layout optimization often gives better performing economic structures and is very helpful in the conceptual design phase. But traditionally it is being done in finite element-based optimization schemes which, although gives a good result, is very time-consuming especially in 3D structures. Among other alternatives machine learning, especially deep learning-based methods, have a very good potential in resolving this computational issue. Here convolutional neural network (3D-CNN) based variational auto encoder (VAE) is trained using a dataset generated from commercially available topology optimization code ABAQUS Tosca using solid isotropic material with penalization (SIMP) method for compliance minimization. The encoded data in latent space is then fed to a 3D generative adversarial network (3D-GAN) to generate the outcome in 64x64x64 size. Here the network consists of 3D volumetric CNN with rectified linear unit (ReLU) activation in between and sigmoid activation in the end. The proposed network is seen to provide almost optimal results with significantly reduced computational time, as there is no iteration involved.

Keywords: 3D generative adversarial network, deep learning, structural topology optimization, variational auto encoder

Procedia PDF Downloads 167

Authors: N. A. Mokhtar, A. G. Hussin, Y. Z. Zubairi

Abstract:

This paper proposes a new simultaneous simple linear functional relationship model by assuming equal error variances. We derive the maximum likelihood estimate of the parameters in the simultaneous model and the covariance. We show by simulation study the small bias values of the parameters suggest the suitability of the estimation method. As an illustration, the proposed simultaneous model is applied to real data of the wind direction and wave direction measured by two different instruments.

Keywords: simultaneous linear functional relationship model, Fisher information matrix, parameter estimation, circular variables

Procedia PDF Downloads 359

Authors: Sheena K. J., Jyoti Badge, Sayed Mohammed Zeeshan

Abstract:

A Comparative Study of Exponential and Logistic Population Growth Models in India India is the second most populous city in the world, just behind China, and is going to be in the first place by next year. The Indian population has remarkably at higher rate than the other countries from the past 20 years. There were many scientists and demographers who has formulated various models of population growth in order to study and predict the future population. Some of the models are Fibonacci population growth model, Exponential growth model, Logistic growth model, Lotka-Volterra model, etc. These models have been effective in the past to an extent in predicting the population. However, it is essential to have a detailed comparative study between the population models to come out with a more accurate one. Having said that, this research study helps to analyze and compare the two population models under consideration - exponential and logistic growth models, thereby identifying the most effective one. Using the census data of 2011, the approximate population for 2016 to 2031 are calculated for 20 Indian states using both the models, compared and recorded the data with the actual population. On comparing the results of both models, it is found that logistic population model is more accurate than the exponential model, and using this model, we can predict the future population in a more effective way. This will give an insight to the researchers about the effective models of population and how effective these population models are in predicting the future population.

Keywords: population growth, population models, exponential model, logistic model, fibonacci model, lotka-volterra model, future population prediction, demographers

Procedia PDF Downloads 119

Authors: Fiona Wahr, Sitalakshmi Venkatraman

Abstract:

Industry employers require new graduates to bring with them a range of knowledge, skills and abilities which mean these new employees can immediately make valuable work contributions. These will be a combination of discipline and professional knowledge, skills and abilities which give graduates the technical capabilities to solve practical problems whilst interacting with a range of stakeholders. Underpinning the development of these disciplines and professional knowledge, skills and abilities, are “enabling” knowledge, skills and abilities which assist students to engage in learning. These are academic and learning skills which are essential to common starting points for both the learning process of students entering the course as well as forming the foundation for the fully developed graduate knowledge, skills and abilities. This paper reports on a project created to introduce and strengthen these enabling skills into the first semester of a Bachelor of Information Technology degree in an Australian polytechnic. The project uses an action research approach in the context of ongoing continuous improvement for the course to enhance the overall learning experience, learning sequencing, graduate outcomes, and most importantly, in the first semester, student engagement and retention. The focus of this is implementing the new curriculum in first semester subjects of the course with the aim of developing the “enabling” learning skills, such as literacy, research and numeracy based knowledge, skills and abilities (KSAs). The approach used for the introduction and embedding of these KSAs, (as both enablers of learning and to underpin graduate attribute development), is presented. Building on previous publications which reported different aspects of this longitudinal study, this paper recaps on the rationale for the curriculum redevelopment and then presents the quantitative findings of entering students’ reading literacy and numeracy knowledge and skills degree as well as their perceived research ability. The paper presents the methodology and findings for this stage of the research. Overall, the cohort exhibits mixed KSA levels in these areas, with a relatively low aggregated score. In addition, the paper describes the considerations for adjusting the design and delivery of the new subjects with a targeted learning experience, in response to the feedback gained through continuous monitoring. Such a strategy is aimed at accommodating the changing learning needs of the students and serves to support them towards achieving the enabling learning goals starting from day one of their higher education studies.

Keywords: enabling skills, student retention, embedded learning support, continuous improvement

Procedia PDF Downloads 243

Authors: Hashem Dadashpoor, Sadegh Saeidi Shirvan

Abstract:

While with the evolution of the economy towards a knowledge-based economy, innovation is a requirement for metropolitan regions, the adoption of an open innovation strategy is an option and a requirement for many industrial firms in these regions. Studies show that investing in research and development units cannot alone increase innovation. Within the framework of the theory of learning regions, this gap, which scholars call it the ‘innovation gap’, is filled with regional features of firms. This paper attempts to investigate the factors affecting the open innovation of firms in metropolitan regions, and it searches for these in territorial innovation models and, in particular, the theory of learning regions. In the next step, the effect of identified factors which is considered as regional learning factors in this research is analyzed on the innovation of sample firms by SPSS software using multiple linear regression. The case study of this research is constituted of industrial enterprises from two groups of food industry and auto parts in Toos industrial town in Mashhad metropolitan region. For data gathering of this research, interviews were conducted with managers of industrial firms using structured questionnaires. Based on this study, the effect of factors such as size of firms, inter-firm competition, the use of local labor force and institutional infrastructures were significant in the innovation of the firms studied, and 44% of the changes in the firms’ innovation occurred as a result of the change in these factors.

Keywords: regional knowledge networks, learning regions, interactive learning, innovation

Procedia PDF Downloads 172

Authors: Ksenia Meshkova

Abstract:

With increasing amount of multimedia data, it is very important to automate and speed up the process of obtaining meta. This process means not just recognition of some object or its movement, but recognition of the entire scene versus separate frames and having timeline segmentation as a final result. Labeling datasets is time consuming, besides, attributing characteristics to particular scenes is clearly difficult due to their nature. In this article, we will consider autoencoders application to unsupervised scene recognition and clusterization based on interpretable features. Further, we will focus on particular types of auto encoders that relevant to our study. We will take a look at the specificity of deep learning related to information theory and rate-distortion theory and describe the solutions empowering poor interpretability of deep learning in media content processing. As a conclusion, we will present the results of the work of custom framework, based on autoencoders, capable of scene recognition as was deeply studied above, with highlights generation resulted out of this recognition. We will not describe in detail the mathematical description of neural networks work but will clarify the necessary concepts and pay attention to important nuances.

Keywords: neural networks, computer vision, representation learning, autoencoders

Procedia PDF Downloads 115

Authors: Erick C. Valverde, Wansu Lim

Abstract:

Facial emotion recognition (FER) system has been recently developed for more advanced computer vision applications. The ability to identify human emotions would enable smart healthcare facility to diagnose mental health illnesses (e.g., depression and stress) as well as better human social interactions with smart technologies. The FER system involves two steps: 1) face detection task and 2) facial emotion recognition task. It classifies the human expression in various categories such as angry, disgust, fear, happy, sad, surprise, and neutral. This system requires intensive research to address issues with human diversity, various unique human expressions, and variety of human facial features due to age differences. These issues generally affect the ability of the FER system to detect human emotions with high accuracy. Early stage of FER systems used simple supervised classification task algorithms like K-nearest neighbors (KNN) and artificial neural networks (ANN). These conventional FER systems have issues with low accuracy due to its inefficiency to extract significant features of several human emotions. To increase the accuracy of FER systems, deep learning (DL)-based methods, like convolutional neural networks (CNN), are proposed. These methods can find more complex features in the human face by means of the deeper connections within its architectures. However, the inference speed and computational costs of a DL-based FER system is often disregarded in exchange for higher accuracy results. To cope with this drawback, an optimized DL-based FER system is proposed in this study.An extreme version of Inception V3, known as Xception model, is leveraged by applying different network optimization methods. Specifically, network pruning and quantization are used to enable lower computational costs and reduce memory usage, respectively. To support low resource requirements, a 68-landmark face detector from Dlib is used in the early step of the FER system.Furthermore, a DL compiler is utilized to incorporate advanced optimization techniques to the Xception model to improve the inference speed of the FER system. In comparison to VGG-Net and ResNet50, the proposed optimized DL-based FER system experimentally demonstrates the objectives of the network optimization methods used. As a result, the proposed approach can be used to create an efficient and real-time FER system.

Keywords: deep learning, face detection, facial emotion recognition, network optimization methods

Procedia PDF Downloads 115

Authors: Mouhammad Alkasassbeh, Mohammad Almseidin

Abstract:

Network security engineers work to keep services available all the time by handling intruder attacks. Intrusion Detection System (IDS) is one of the obtainable mechanisms that is used to sense and classify any abnormal actions. Therefore, the IDS must be always up to date with the latest intruder attacks signatures to preserve confidentiality, integrity, and availability of the services. The speed of the IDS is a very important issue as well learning the new attacks. This research work illustrates how the Knowledge Discovery and Data Mining (or Knowledge Discovery in Databases) KDD dataset is very handy for testing and evaluating different Machine Learning Techniques. It mainly focuses on the KDD preprocess part in order to prepare a decent and fair experimental data set. The J48, MLP, and Bayes Network classifiers have been chosen for this study. It has been proven that the J48 classifier has achieved the highest accuracy rate for detecting and classifying all KDD dataset attacks, which are of type DOS, R2L, U2R, and PROBE.

Keywords: IDS, DDoS, MLP, KDD

Procedia PDF Downloads 232

Authors: Stephanie Liu Lu

Abstract:

With the proliferation of artificial intelligence tools in the field of education, it is crucial to explore their impact on language learning outcomes. This paper examines the use of AI tools, such as ChatGPT, in practical writing within business Chinese teaching to investigate how AI can enhance practical writing skills and teaching effectiveness. The study involved third and fourth-year university students majoring in accounting and finance from a university in Hong Kong within the context of a business correspondence writing class. Students were randomly assigned to a control group, who completed business letter writing independently, and an experimental group, who completed the writing with the assistance of AI. In the latter, the AI-assisted business letters were initially drafted by the students issuing commands and interacting with the AI tool, followed by the students' revisions of the draft. The paper assesses the performance of both groups in terms of grammatical expression, communicative effect, and situational awareness. Additionally, the study collected dialogue texts from interactions between students and the AI tool to explore factors that affect text generation and the potential impact of AI on enhancing students' communicative and identity awareness. By collecting and comparing textual performances, it was found that students assisted by AI showed better situational awareness, as well as more skilled organization and grammar. However, the research also revealed that AI-generated articles frequently lacked a proper balance of identity and writing purpose due to limitations in students' communicative awareness and expression during the instruction and interaction process. Furthermore, the revision of drafts also tested the students' linguistic foundation, logical thinking abilities, and practical workplace experience. Therefore, integrating AI tools and related teaching into the curriculum is key to the future of business Chinese teaching.

Keywords: AI-assistance, business Chinese, textual analysis, language education

Procedia PDF Downloads 51

Authors: Mu-Yen Chen, Min-Hsuan Fan, Chia-Chen Chen, Siang-Yu Jhong

Abstract:

In recent years, real estate prediction or valuation has been a topic of discussion in many developed countries. Improper hype created by investors leads to fluctuating prices of real estate, affecting many consumers to purchase their own homes. Therefore, scholars from various countries have conducted research in real estate valuation and prediction. With the back-propagation neural network that has been popular in recent years and the orthogonal array in the Taguchi method, this study aimed to find the optimal parameter combination at different levels of orthogonal array after the system presented different parameter combinations, so that the artificial neural network obtained the most accurate results. The experimental results also demonstrated that the method presented in the study had a better result than traditional machine learning. Finally, it also showed that the model proposed in this study had the optimal predictive effect, and could significantly reduce the cost of time in simulation operation. The best predictive results could be found with a fewer number of experiments more efficiently. Thus users could predict a real estate transaction price that is not far from the current actual prices.

Keywords: artificial neural network, Taguchi method, real estate valuation model, investors

Procedia PDF Downloads 480