Search results for: incremental learning

Authors: Mitat Uysal, Aynur Uysal

Abstract:

Artificial Intelligence (AI) is fundamentally driven by mathematics, with many of its core algorithms rooted in mathematical principles such as linear algebra, probability theory, calculus, and optimization techniques. This paper explores the deep connection between AI and mathematics, highlighting the role of mathematical concepts in key AI techniques like machine learning, neural networks, and optimization. To demonstrate this connection, a case study involving the implementation of a neural network using Python is presented. This practical example illustrates the essential role that mathematics plays in training a model and solving real-world problems.

Keywords: AI, mathematics, machine learning, optimization techniques, image processing

Procedia PDF Downloads 18

Authors: Muhammed Kök & Adem Kantar

Abstract:

Learning a foreign language can be affected by various factors such as age, aptitude, motivation, L2 disposition, etc. Among these factors, masculine gender roles stress (MGRS) that male learners possess is the least touched area that has been examined so far.MGRS can be defined as the traditional male role stress when the male learners feel the masculinity threat against their traditionally adopted masculinity norms. Traditional masculine norms include toughness, accuracy, completeness, and faultlessness. From this perspective, these norms are diametrically opposed to the language learning process since learning a language, by its nature, involves stages such as making mistakes and errors, not recalling words, pronouncing sounds incorrectly, creating wrong sentences, etc. Considering the potential impact of MGRS on the language learning process, the main purpose of this study is to investigate the mediating role of MGRS on the relationship between the EFL learners’ self-disclosure and English class anxiety. Data were collected from Turkish EFL learners (N=282) who study different majors in various state universities across Turkey. Data were analyzed by means of the Bootstraping method using the SPSS Process Macro plugin. The findings show that the indirect effect of self-disclosure level on the English Class Anxiety via MGRS was significant. We conclude that one of the reasons why Turkish EFL learners have English class anxiety might be the pressure that they feel because of their traditional gender role stress.

Keywords: masculine, gender role stress, english class anxiety, self-disclosure, masculinity norms

Procedia PDF Downloads 99

Authors: Bernardo Cortez, Florian Peter, Thomas Lausenhammer, Paulo Oliveira

Abstract:

Designing missiles’ autopilot controllers have been a complex task, given the extensive flight envelope and the nonlinear flight dynamics. A solution that can excel both in nominal performance and in robustness to uncertainties is still to be found. While Control Theory often debouches into parameters’ scheduling procedures, Reinforcement Learning has presented interesting results in ever more complex tasks, going from videogames to robotic tasks with continuous action domains. However, it still lacks clearer insights on how to find adequate reward functions and exploration strategies. To the best of our knowledge, this work is a pioneer in proposing Reinforcement Learning as a framework for flight control. In fact, it aims at training a model-free agent that can control the longitudinal non-linear flight dynamics of a missile, achieving the target performance and robustness to uncertainties. To that end, under TRPO’s methodology, the collected experience is augmented according to HER, stored in a replay buffer and sampled according to its significance. Not only does this work enhance the concept of prioritized experience replay into BPER, but it also reformulates HER, activating them both only when the training progress converges to suboptimal policies, in what is proposed as the SER methodology. The results show that it is possible both to achieve the target performance and to improve the agent’s robustness to uncertainties (with low damage on nominal performance) by further training it in non-nominal environments, therefore validating the proposed approach and encouraging future research in this field.

Keywords: Reinforcement Learning, flight control, HER, missile autopilot, TRPO

Procedia PDF Downloads 267

Authors: Swarna Pundir, Prabuddha Hans

Abstract:

As AI has already stepped into the daily life of human society, one cannot be ignorant about the data it collects and used it to provide a quality of services depending up on the individuals’ choices. It also helps in giving option for making decision Vs choice selection with a calculation based on the history of our search criteria. Over the past decade or so, the way Artificial Intelligence (AI) has impacted society is undoubtedly large.AI has changed the way we shop, the way we entertain and challenge ourselves, the way information is handled, and has automated some sections of our life. We have answered as to what AI is, but not why one may see it as useful. AI is useful because it is capable of learning and predicting outcomes, using Machine Learning (ML) and Deep Learning (DL) with the help of Artificial Neural Networks (ANN). AI can also be a system that can act like humans. One of the major impacts be Joblessness through automation via AI which is seen mostly in manufacturing sectors, especially in the routine manual and blue-collar occupations and those without a college degree. It raises some serious concerns about AI in regards of less employment, ethics in making moral decisions, Individuals privacy, human judgement’s, natural emotions, biased decisions, discrimination. So, the question is if an error occurs who will be responsible, or it will be just waved off as a “Machine Error”, with no one taking the responsibility of any wrongdoing, it is essential to form some rules for using the AI where both machines and humans are involved.

Keywords: AI, ML, DL, ANN

Procedia PDF Downloads 99

Authors: Abdullah Bal

Abstract:

This paper presents a one-class classification (OCC) technique based on Fukunaga-Koontz Transform (FKT) for binary classification problems. The FKT is originally a powerful tool to feature selection and ordering for two-class problems. To utilize the standard FKT for data domain description problem (i.e., one-class classification), in this paper, a set of non-class samples which exist outside of positive class (target class) describing boundary formed with limited training data has been constructed synthetically. The tunnel-like decision boundary around upper and lower border of target class samples has been designed using statistical properties of feature vectors belonging to the training data. To capture higher order of statistics of data and increase discrimination ability, the proposed method, termed one-class FKT (OC-FKT), has been extended to its nonlinear version via kernel machines and referred as OC-KFKT for short. Multiple kernel learning (MKL) is a favorable family of machine learning such that tries to find an optimal combination of a set of sub-kernels to achieve a better result. However, the discriminative ability of some of the base kernels may be low and the OC-KFKT designed by this type of kernels leads to unsatisfactory classification performance. To address this problem, the quality of sub-kernels should be evaluated, and the weak kernels must be discarded before the final decision making process. MKL/OC-FKT and selective MKL/OC-FKT frameworks have been designed stimulated by ensemble learning (EL) to weight and then select the sub-classifiers using the discriminability and diversities measured by eigenvalue ratios. The eigenvalue ratios have been assessed based on their regions on the FKT subspaces. The comparative experiments, performed on various low and high dimensional data, against state-of-the-art algorithms confirm the effectiveness of our techniques, especially in case of small sample size (SSS) conditions.

Keywords: ensemble methods, fukunaga-koontz transform, kernel-based methods, multiple kernel learning, one-class classification

Procedia PDF Downloads 25

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision-making has not been far-fetched. Proper classification of this textual information in a given context has also been very difficult. As a result, we decided to conduct a systematic review of previous literature on sentiment classification and AI-based techniques that have been used in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that can correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy by assessing different artificial intelligence techniques. We evaluated over 250 articles from digital sources like ScienceDirect, ACM, Google Scholar, and IEEE Xplore and whittled down the number of research to 31. Findings revealed that Deep learning approaches such as CNN, RNN, BERT, and LSTM outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also necessary for developing a robust sentiment classifier and can be obtained from places like Twitter, movie reviews, Kaggle, SST, and SemEval Task4. Hybrid Deep Learning techniques like CNN+LSTM, CNN+GRU, CNN+BERT outperformed single Deep Learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of sentiment analyzer development due to its simplicity and AI-based library functionalities. Based on some of the important findings from this study, we made a recommendation for future research.

Keywords: artificial intelligence, natural language processing, sentiment analysis, social network, text

Procedia PDF Downloads 116

Authors: Kripesh Adhikari, Hamid Bouchachia, Hammadi Nait-Charif

Abstract:

Falls are one of the major causes of injury and death among elderly people aged 65 and above. A support system to identify such kind of abnormal activities have become extremely important with the increase in ageing population. Pose estimation is a challenging task and to add more to this, it is even more challenging when pose estimations are performed on challenging poses that may occur during fall. Location of the body provides a clue where the person is at the time of fall. This paper presents a vision-based tracking strategy where available joints are grouped into three different feature points depending upon the section they are located in the body. The three feature points derived from different joints combinations represents the upper region or head region, mid-region or torso and lower region or leg region. Tracking is always challenging when a motion is involved. Hence the idea is to locate the regions in the body in every frame and consider it as the tracking strategy. Grouping these joints can be beneficial to achieve a stable region for tracking. The location of the body parts provides a crucial information to distinguish normal activities from falls.

Keywords: fall detection, machine learning, deep learning, pose estimation, tracking

Procedia PDF Downloads 190

Authors: Mutiara Amalina Khairisa, Purnama Arafah, Rahayu Listiana Ramli

Abstract:

In recent years, so many cases of divorce increasingly occur. Betrayal in form of infidelity, less communication one another, economically problems, selfishness of two sides, intervening parents from both sides which frequently occurs in Asia, especially in Indonesia, the differences of both principles and beliefs, “Sense of Romantism” depletion, role confict, a large difference in the purpose of marriage,and sex satisfaction are expected as the primary factors of the causes of divorce. Every couple of marriage wants to reach happy life in their family but severe problems brought about by either of those main factors come as a reasonable cause of failure marriage. The purpose of this study is to find out how marital adjustment and supporting factors in ensuring the success of that previous marital adjusment are inseparable two things assumed as a framework can affect the success in marriage becoming a resolution to reduce the desires to divorce. Those two inseparable things are able to become an aspect of learning from the success of the different ethnics marriage to keep holding on wholeness.

Keywords: marital adjustment, marital sustainability, learning process, successful ethnicity differences marriage, basical cultural values

Procedia PDF Downloads 432

Authors: Yu-Chi Chou

Abstract:

The purpose of this study was to establish a logical path of an instructional model of empathy and social regulation, providing feasibility evidence on the model implementation in students with autism spectrum disorder (ASD). This newly developed Emotional Bug-Out Bag (BoB) curriculum was designed to enhance the empathy and socially shared regulation of students with ASD. The BoB model encompassed three instructional phases of basic theory lessons (BTL), action plan practices (APP), and final theory practices (FTP) during implementation. Besides, a learning flow (teacher-directed instruction, student self-directed problem-solving, group-based task completion, group-based reflection) was infused into the progress of instructional phases to deliberately promote the social regulatory process in group-working activities. A total of 23 junior high school students with ASD were implemented with the BoB curriculum. To examine the logical path for model implementation, data was collected from the participating students’ self-report scores on the learning nodes and understanding questions. Path analysis using structural equation modeling (SEM) was utilized for analyzing scores on 10 learning nodes and 41 understanding questions through the three phases of the BoB model. Results showed (a) all participants progressed throughout the implementation of the BoB model, and (b) the models of learning nodes and phases were positive and significant as expected, confirming the hypothesized logic path of this curriculum.

Keywords: autism spectrum disorder, empathy, regulation, socially shared regulation

Procedia PDF Downloads 66

Authors: Heewon Jeong, Seongpyo Kim, Joon Ha Kim

Abstract:

Over the last few tens of years, the coastal regions of Korea have experienced red tide algal blooms, which are harmful and toxic to both humans and marine organisms due to their potential threat. It was accelerated owing to eutrophication by human activities, certain oceanic processes, and climate change. Previous studies have tried to monitoring and predicting the algae concentration of the ocean with the bio-optical algorithms applied to color images of the satellite. However, the accurate estimation of algal blooms remains problems to challenges because of the complexity of coastal waters. Therefore, this study suggests a new method to identify the concentration of red tide algal bloom from images of geostationary ocean color imager (GOCI) which are representing the water environment of the sea in Korea. The method employed GOCI images, which took the water leaving radiances centered at 443nm, 490nm and 660nm respectively, as well as observed weather data (i.e., humidity, temperature and atmospheric pressure) for the database to apply optical characteristics of algae and train deep learning algorithm. Convolution neural network (CNN) was used to extract the significant features from the images. And then artificial neural network (ANN) was used to estimate the concentration of algae from the extracted features. For training of the deep learning model, backpropagation learning strategy is developed. The established methods were tested and compared with the performances of GOCI data processing system (GDPS), which is based on standard image processing algorithms and optical algorithms. The model had better performance to estimate algae concentration than the GDPS which is impossible to estimate greater than 5mg/m³. Thus, deep learning model trained successfully to assess algae concentration in spite of the complexity of water environment. Furthermore, the results of this system and methodology can be used to improve the performances of remote sensing. Acknowledgement: This work was supported by the 'Climate Technology Development and Application' research project (#K07731) through a grant provided by GIST in 2017.

Keywords: deep learning, algae concentration, remote sensing, satellite

Procedia PDF Downloads 184

Authors: Nir Wittenberg, Moshe Farhi

Abstract:

This mixed-methods study examines the integration of artificial intelligence (AI) tools in a first-year social work course to assess their potential for enhancing professional knowledge and skills. The incorporation of digital technologies, such as AI, in social work interventions, training, and research has increased, with the expectation that AI will become as commonplace as email and mobile phones. However, policies and ethical guidelines regarding AI, as well as empirical evaluations of its usefulness, are lacking. As AI is gradually being adopted in the field, it is prudent to explore AI thoughtfully in alignment with pedagogical goals. The outcomes assessed include professional identity, course satisfaction, and motivation. AI offers unique reflective learning opportunities through personalized simulations, feedback, and queries to complement face-to-face lessons. For instance, AI simulations provide low-risk practices for situations such as client interactions, enabling students to build skills with less stress. However, it is essential to recognize that AI alone cannot ensure real-world competence or cultural sensitivity. Outcomes related to student learning, experience, and perceptions will help to elucidate the best practices for AI integration, guiding faculty, and advancing pedagogical innovation. This strategic integration of selected AI technologies is expected to diversify course methodology, improve learning outcomes, and generate new evidence on AI’s educational utility. The findings will inform faculty seeking to thoughtfully incorporate AI into teaching and learning.

Keywords: artificial intelligence (AI), social work education, students, developing a professional identity, ethical considerations

Procedia PDF Downloads 81

Authors: Irum Naz

Abstract:

In the Arabian higher education context, linguistic proficiency in the English language is considered crucial for the developmental sustainability, economic growth, and stability of communities and societies. Qatar’s educational reforms package, through the 2030 vision, identifies the acquisition of English at K-12 as an essential survival communication tool for globalization, believing that Qatari students need better preparation to take on the responsibilities of leadership and to participate effectively in the country’s surging economy. The idea of introducing Qatari students to modern curricula benchmarked to high-student-performance curricula in developed countries is one of the components of reformatory design principles of Education for New Era reform project that is mutually consented to and supported by the Office of Shared Services, Communications Office, and Supreme Education Council. In appreciation of the government’s vision, the English Language Centre (ELC) at the Community College of Qatar ran an internal educational audit and conducted evaluative research to understand and appraise the value, impact, and practicality of the existing ELC language development program. This study sought to identify the type of change that could identify and improve the quality of Foundation Program courses and the manners in which second language learners could be assisted to transit smoothly between (ELC) levels. Following the interpretivist paradigm and mixed research method, the data was gathered through a bicyclic research model and a triangular design. The analyses of the data suggested that there was a need for improvement in the ELC program as a whole, and particularly in terms of curriculum, student learning outcomes, and the general learning environment in the department. Key findings suggest that the target program would benefit from significant revisions, which would include narrowing the focus of the courses, providing sets of specific learning objectives, and preventing repetition between levels. Another promising finding was about the assessment tools and process. The data suggested that a set of standardized assessments that more closely suited the programs of study should be devised. It was also recommended that students undergo a more comprehensive placement process to ensure that they begin the program at an appropriate level and get the maximum benefit from their learning experience. Although this ties into the idea of curriculum revamp, it was expected that students could leave the ELC having had exposure to courses in English for specific purposes. The idea of a more reliable exit assessment for students was raised frequently so ELC could regulate itself and ensure optimum learning outcomes. Another important recommendation was the provision of a Student Learning Center for students that would help them to receive personalized tuition, differentiated instruction, and self-driven and self-evaluated learning experience. In addition, an extra study level was recommended to be added to the program to accommodate the different levels of English language proficiency represented among ELC students. The evidence collected in the course of conducting the study suggests that significant change is needed in the structure of the ELC program, specifically about curriculum, the program learning outcomes, and the learning environment in general.

Keywords: educational audit, ESL, optimum learning outcomes, Qatar’s educational reforms, self-driven and self-evaluated learning experience, Student Learning Center

Procedia PDF Downloads 187

Authors: Covadonga Rodrigo, Felipe Alvarez Arrieta, Ana Garcia Serrano

Abstract:

Mobile augmented reality technologies have become very popular in the last years in the educational field. Researchers have studied how these technologies improve the engagement of the student and better understanding of the process of learning. But few studies have been made regarding the accessibility of these new technologies applied to digital humanities. The goal of our research is to develop an accessible mobile application with embedded augmented reality main characters of the art work and gamification events accompanied by multi-sensorial activities. The mobile app conducts a learning itinerary around the artistic work, driving the user experience in and out the museum. The learning design follows the inquiry-based methodology and social learning conducted through interaction with social networks. As for the software application, it’s being user-centered designed, following the universal design for learning (UDL) principles to assure the best level of accessibility for all. The mobile augmented reality application starts recognizing a marker from a masterpiece of a museum using the camera of the mobile device. The augmented reality information (history, author, 3D images, audio, quizzes) is shown through virtual main characters that come out from the art work. To comply with the UDL principles, we use a version of the technology acceptance model (TAM) to study the easiness of use and perception of usefulness, extended by the authors with specific indicators for measuring accessibility issues. Following a rapid prototype method for development, the first app has been recently produced, fulfilling the EN 301549 standard and W3C accessibility guidelines for mobile development. A TAM-based web questionnaire with 214 participants with different kinds of disabilities was previously conducted to gather information and feedback on user preferences from the artistic work on the Museo del Prado, the level of acceptance of technology innovations and the easiness of use of mobile elements. Preliminary results show that people with disabilities felt very comfortable while using mobile apps and internet connection. The augmented reality elements seem to offer an added value highly engaging and motivating for the students.

Keywords: H.5.1 (multimedia information systems), artificial, augmented and virtual realities, evaluation/methodology

Procedia PDF Downloads 137

Authors: Atakan Aral Ormancı, Tuğçe Arslantaş, Murat Özcü

Abstract:

This study presents the design and implementation of an experimental chassis-level system for various control applications. Specifically, the height level of the chassis is controlled using proportional integrated derivative, fuzzy logic, and deep learning control methods. Real-time data obtained from height and pressure sensors installed in a 6x2 truck chassis, in combination with pulse-width modulation signal values, are utilized during the tests. A prototype pneumatic system of a 6x2 truck is added to the setup, which enables the Smart Pneumatic Actuators to function as if they were in a real-world setting. To obtain real-time signal data from height sensors, an Arduino Nano is utilized, while a Raspberry Pi processes the data using Matlab/Simulink and provides the correct output signals to control the Smart Pneumatic Actuator in the truck chassis. The objective of this research is to optimize the time it takes for the chassis to level down and up under various loads. To achieve this, proportional integrated derivative control, fuzzy logic control, and deep learning techniques are applied to the system. The results show that the deep learning method is superior in optimizing time for a non-linear system. Fuzzy logic control with a triangular membership function as the rule base achieves better outcomes than proportional integrated derivative control. Traditional proportional integrated derivative control improves the time it takes to level the chassis down and up compared to an uncontrolled system. The findings highlight the superiority of deep learning techniques in optimizing the time for a non-linear system, and the potential of fuzzy logic control. The proposed approach and the experimental results provide a valuable contribution to the field of control, automation, and systems engineering.

Keywords: automotive, chassis level control, control systems, pneumatic system control

Procedia PDF Downloads 82

Authors: Shakirat Abimbola Adesola, Shuaib Akintunde Asifat, Jelili Olalekan Amoo

Abstract:

This paper presented the impact of students’ emotions on learning when receiving lectures and when taking tests. It was observed that students experience different types of emotions during the study, and this was found to have a significant effect on their academic performance. A total of one thousand six hundred and seventy-five (1675) students from the department of Computer Science in two Colleges of Education in South-West Nigeria took part in this study. The students were randomly selected for the research. Sample comprises of 968 males representing 58%, and 707 females representing 42%. A structured questionnaire, of Motivated Strategies for Learning Questionnaire (MSLQ) was distributed to the participants to obtain their opinions. Data gathered were analyzed using the IBM SPSS 20 to obtain ANOVA, descriptive analysis, stepwise regression, and reliability tests. The results revealed that emotion moderately shape students’ motivation and engagement in learning; and that self-regulation and self-determination do have significant impact on academic performance. It was further revealed that test anxiety has a significant correlation with academic performance.

Keywords: motivation, self-determination, test anxiety, academic performance, and academic engagement

Procedia PDF Downloads 83

Authors: Saugata Bose, Ritambhra Korpal

Abstract:

The internet has increased the copy-paste scenarios amongst students as well as amongst researchers leading to different levels of plagiarized documents. For this reason, much of research is focused on for detecting plagiarism automatically. In this paper, an initiative is discussed where Natural Language Processing (NLP) techniques as well as supervised machine learning algorithms have been combined to detect plagiarized texts. Here, the major emphasis is on to construct a framework which detects external plagiarism from monolingual texts successfully. For successfully detecting the plagiarism, n-gram frequency comparison approach has been implemented to construct the model framework. The framework is based on 120 characteristics which have been extracted during pre-processing the documents using NLP approach. Afterwards, filter metrics has been applied to select most relevant characteristics and then supervised classification learning algorithm has been used to classify the documents in four levels of plagiarism. Confusion matrix was built to estimate the false positives and false negatives. Our plagiarism framework achieved a very high the accuracy score.

Keywords: lexical matching, shallow NLP, supervised machine learning algorithm, word n-gram

Procedia PDF Downloads 359

Authors: Ahmet Karakuş, Akif Can Kilic, Emre Alptekin

Abstract:

A growing number of studies have been conducted to determine how well-being may be predicted using well-designed models. It is necessary to investigate the backgrounds of features in order to construct a viable Subjective Well-Being (SWB) model. We have picked the suitable variables from the literature on SWB that are acceptable for real-world data instructions. The goal of this work is to evaluate the model by feeding it with SWB characteristics and then categorizing the stress levels using machine learning methods to see how well it performs on a real dataset. Despite the fact that it is a multiclass classification issue, we have achieved significant metric scores, which may be taken into account for a specific task.

Keywords: machine learning, multiclassification problem, subjective well-being, perceived stress scale

Procedia PDF Downloads 133

Authors: Sandy Black, Calum McLaughlin, Alessandro Pranzitelli, Marc Laing

Abstract:

Multiphase flow structures of two-phase multicomponent fluids were experimentally investigated in a large diameter high-pressure pipeline up to 130 bar at TÜV SÜD’s National Engineering Laboratory Advanced Multiphase Facility. One of the main objectives of the experimental test campaign was to evaluate the impact of pressure on multiphase flow patterns as much of the existing information is based on low-pressure measurements. The experiments were performed in a horizontal and vertical orientation in both 4-inch and 6-inch pipework using nitrogen, ExxsolTM D140 oil, and a 6% aqueous solution of NaCl at incremental pressures from 10 bar to 130 bar. To visualise the detailed structure of the flow of the entire cross-section of the pipe, a fast response X-ray tomography system was used. A wide range of superficial velocities from 0.6 m/s to 24.0 m/s for gas and 0.04 m/s and 6.48 m/s for liquid was examined to evaluate different flow regimes. The results illustrated the suppression of instabilities between the gas and the liquid at the measurement location and that intermittent or slug flow was observed less frequently as the pressure was increased. CFD modellings of low and high-pressure simulations were able to successfully predict the likelihood of intermittent flow; however, further tuning is necessary to predict the slugging frequency. The dataset generated is unique as limited datasets exist above 100 bar and is of considerable value to multiphase flow specialists and numerical modellers.

Keywords: computational fluid dynamics, high pressure, multiphase, X-ray tomography

Procedia PDF Downloads 147

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Manufacturing companies are facing global competition and enormous cost pressure. The use of machine learning applications can help reduce production costs and create added value. Predictive quality enables the securing of product quality through data-supported predictions using machine learning models as a basis for decisions on test results. Furthermore, machine learning methods are able to process large amounts of data, deal with unfavourable row-column ratios and detect dependencies between the covariates and the given target as well as assess the multidimensional influence of all input variables on the target. Real production data are often subject to highly fluctuating boundary conditions and unbalanced data sets. Changes in production data manifest themselves in trends, systematic shifts, and seasonal effects. Thus, Machine learning applications require intensive pre-processing and feature selection. Data preprocessing includes rule-based data cleaning, the application of dimensionality reduction techniques, and the identification of comparable data subsets. Within the used real data set of Bosch hydraulic valves, the comparability of the same production conditions in the production of hydraulic valves within certain time periods can be identified by applying the concept drift method. Furthermore, a classification model is developed to evaluate the feature importance in different subsets within the identified time periods. By selecting comparable and stable features, the number of features used can be significantly reduced without a strong decrease in predictive power. The use of cross-process production data along the value chain of hydraulic valves is a promising approach to predict the quality characteristics of workpieces. In this research, the ada boosting classifier is used to predict the leakage of hydraulic valves based on geometric gauge blocks from machining, mating data from the assembly, and hydraulic measurement data from end-of-line testing. In addition, the most suitable methods are selected and accurate quality predictions are achieved.

Keywords: classification, achine learning, predictive quality, feature selection

Procedia PDF Downloads 162

Authors: Syamimi Shamsuddin, Hanafiah Yussof, Fazah Akhtar Hanapiah, Salina Mohamed, Nur Farah Farhan Jamil, Farhana Wan Yunus

Abstract:

Robot-based intervention for children with autism is an evolving research niche in human-robot interaction (HRI). Recent studies in this area mostly covered the role of robots in the clinical and experimental setting. Our previous work had shown that interaction with a robot pose no adverse effects on the children. Also, the presence of the robot, together with specific modules of interaction was associated with less autistic behavior. Extending this impact on school-going children, interactions that are in-tune with special education lessons are needed. This methodological paper focuses on how a robot can be incorporated in a current learning environment for autistic children. Six interaction scenarios had been designed based on the existing syllabus to teach communication skills, using the Applied Behavior Analysis (ABA) technique as the framework. Development of the robotic experience in class also covers the required set-up involving participation from teachers. The actual research conduct involving autistic children, teachers and robot shall take place in the next phase.

Keywords: autism spectrum disorder, ASD, humanoid robot, communication skills, robot-assisted learning

Procedia PDF Downloads 368

Authors: Valentina Zhang

Abstract:

While facial expression is a complex and individualized behavior, all facial emotion recognition (FER) systems known to us rely on a single facial representation and are trained on universal data. We conjecture that: (i) different facial representations can provide different, sometimes complementing views of emotions; (ii) when employed collectively in a discussion group setting, they enable more accurate emotion reading which is highly desirable in autism care and other applications context sensitive to errors. In this paper, we first study FER using pixel-based DL vs semantics-based DL in the context of deepfake videos. Our experiment indicates that while the semantics-trained model performs better with articulated facial feature changes, the pixel-trained model outperforms on subtle or rare facial expressions. Armed with these findings, we have constructed an adaptive FER system learning from both types of models for dyadic or small interacting groups and further leveraging the synthesized group emotions as the ground truth for individualized FER training. Using a collection of group conversation videos, we demonstrate that FER accuracy and personalization can benefit from such an approach.

Keywords: neurodivergence care, facial emotion recognition, deep learning, ground truth for supervised learning

Procedia PDF Downloads 148

Authors: Durri Andriani, Irsan Tahar, Lilian Sarah Hiariey

Abstract:

Every institution has to develop, implement, and control its policies to ensure the effectiveness of the institution. In doing so, all related stakeholders have to be involved to maximize the benefit of the policies and minimize the potential constraints and resistances. Open and distance education (ODE) institution is no different. As an education institution, ODE institution has to focus their attention to fulfilling academic needs of their students through open and distance measures. One of them is quality learning support system. Significant stakeholders in learning support system are tutors since they are the ones who directly communicate with students. Tutors are commonly seen as objects whose main responsibility is limited to implementing policies decided by management in ODE institutions. Nonetheless, tutors’ perceptions of tutorials are believed to influence tutors’ performances in facilitating learning support. It is therefore important to analyze tutors’ perception on various aspects of learning support. This paper presents analysis of tutors’ perceptions on policies of tutoriala in ODE institution using Policy Analysis Framework (PAF) modified by King, Nugent, Russell, and Lacy. Focus of this paper is on on-line tutors, those who provide tutorials via Internet. On-line tutors were chosen to stress the increasingly important used of Internet in ODE system. The research was conducted in Universitas Terbuka (UT), Indonesia. UT is purposely selected because of its large number (1,234) of courses offered and large area coverage (6000 inhabited islands). These posed UT in a unique position where learning support system has, to some extent, to be standardized while at the same time it has to be able to cater the needs of different courses in different places for students with different backgrounds. All 598 listed on-line tutors were sent the research questionnaires. Around 20% of the email addresses could not be reached. Tutors were asked to fill out open-ended questionnaires on their perceptions on definition of on-line tutorial, roles of tutors and students in on-line tutorials, requirement for on-line tutors, learning materials, and student evaluation in on-line tutorial. Data analyzed was gathered from 40 on-line tutors who sent back filled-out questionnaires. Data were analyzed qualitatively using content analysis from all 40 tutors. The results showed that using PAF as entry point in choosing learning support services as area of policy with delivery learning materials as the issue at UT has been able to provide new insights of aspects need to be consider in formulating policies in online tutorial and in learning support services. Involving tutors as source of information could be proven to be productive. In general, tutors had clear understanding about definition of online tutorial, roles of tutors and roles of students, and requirement of tutor. Tutors just need to be more involved in the policy formulation since they could provide data on students and problem faced in online tutorial. However, tutors need an adjustment in student evaluation which according tutors too focus on administrative aspects and subjective.

Keywords: distance education, on-line tutorial, tutorial policy, tutors’ perspectives

Procedia PDF Downloads 254

Authors: Tonislav Ivanov, Oleksii Nedashkivskyi, Denis Babeshko, Vadim Pinskiy, Matthew Putman

Abstract:

Training a machine learning model for object detection that generalizes well is known to benefit from a training dataset with diverse examples. However, training datasets usually contain many repeats of common examples of a class and lack rarely seen examples. This is due to the process commonly used during human annotation where a person would proceed sequentially through a list of images labeling a sufficiently high total number of examples. Instead, the method presented involves an active process where, after the initial labeling of several images is completed, the next subset of images for labeling is selected by an algorithm. This process of algorithmic image selection and manual labeling continues in an iterative fashion. The algorithm used for the image selection is a deep learning algorithm, based on the U-shaped architecture, which quantifies the presence of unseen data in each image in order to find images that contain the most novel examples. Moreover, the location of the unseen data in each image is highlighted, aiding the labeler in spotting these examples. Experiments performed using semiconductor wafer data show that labeling a subset of the data, curated by this algorithm, resulted in a model with a better performance than a model produced from sequentially labeling the same amount of data. Also, similar performance is achieved compared to a model trained on exhaustive labeling of the whole dataset. Overall, the proposed approach results in a dataset that has a diverse set of examples per class as well as more balanced classes, which proves beneficial when training a deep learning model.

Keywords: computer vision, deep learning, object detection, semiconductor

Procedia PDF Downloads 137

Authors: Ntite Orji Kalu, Martina Kurowski

Abstract:

Until recently, the Czech Republic had an educational system dominated by indigenous people, who accounted for 95% of the school population. With the increasing influx of migrants and foreign students, especially from outside European Union, came a great disparity among the quality of learners and their learning needs and consideration for the challenges associated with being a minority and living within a foreign culture. This has prompted the research into ways of tailoring the educational system to meet the rising demand of learning styles and needs for the diverse learners in the Czech classrooms. Literature is reviewed regarding the various ways to accommodate the international students considering racial differences, focusing on theoretical approach and pedagogical principles. This study examines the compulsory educational system of the Czech Republic and the position and responsibility of the teacher in fostering a culturally sensitive and inclusive learning environment. Descriptive and content analysis is relied upon for this study. Recommendations are made for stakeholders to imbibe a more responsive environment that enhances the cultural and social integration of all learners.

Keywords: culturally responsive teaching, cultural competence, diversity, learners, inclusive education, Czech schools

Procedia PDF Downloads 148

Authors: Agastya Pratap Singh

Abstract:

This review paper examines the emerging applications of generative adversarial networks (GANs) in the fields of image recognition and anomaly detection. With the rapid growth of digital image data, the need for efficient and accurate methodologies to identify and classify images has become increasingly critical. GANs, known for their ability to generate realistic data, have gained significant attention for their potential to enhance traditional image recognition systems and improve anomaly detection performance. The paper systematically analyzes various GAN architectures and their modifications tailored for image recognition tasks, highlighting their strengths and limitations. Additionally, it delves into the effectiveness of GANs in detecting anomalies in diverse datasets, including medical imaging, industrial inspection, and surveillance. The review also discusses the challenges faced in training GANs, such as mode collapse and stability issues, and presents recent advancements aimed at overcoming these obstacles.

Keywords: generative adversarial networks, image recognition, anomaly detection, synthetic data generation, deep learning, computer vision, unsupervised learning, pattern recognition, model evaluation, machine learning applications

Procedia PDF Downloads 32

Authors: Agnes Anyango Andollo, Jane Achieng Achola

Abstract:

The use of Information and Communication Technologies (ICTs) has become one of the driving forces in facilitation of learning in most colleges. The ability to effectively harness the technology varies from college to college. The study objective was to determine the lecturers’, institutional attributes and policies that influence the utilization of ICT by the lecturers’. A cross sectional survey design was employed in order to empirically investigate the extent to which lecturers’ personal, institutional attributes and policies influence the utilization of ICT to facilitate learning. The target population of the study was 295 lecturers who facilitate learning at KMTC-Nairobi. Structured self-administered questionnaire was given to the lecturers. Quantitative data was scrutinized for completeness, accuracy and uniformity then coded. Data were analyzed in frequencies and percentages using Statistical Package for Social Sciences (SPSS) version 19, this was a reliable tool for quantitative data analysis. A total of 155 completed questionnaires administered were obtained from the respondents for the study that were subjected to analysis. The study found out that 93 (60%) of the respondents were male while 62 (40%) of the respondents were female. Individual’s educational level, age, gender and educational experience had the greatest impact on use of ICT. Lecturers’ own beliefs, values, ideas and thinking had moderate impact on use of ICT. And that institutional support by provision of resources for ICT related training such as internet, computers, laptops and projectors had moderate impact (p = 0.049) at 5% significant level on use of ICT. The study concluded that institutional attributes and ICT policy were keys to utilization of ICT by lecturers at KMTC Nairobi also mandatory policy on use of ICT by lecturers to facilitate learning was key. It recommended that policies should be put in place for Technical support to lecturers when in problem during utilization of ICT and also a mechanism should be put in place to make the use of ICT in teaching and learning mandatory.

Keywords: policy, computers education, medical training institutions, ICTs

Procedia PDF Downloads 359

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 83

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 57

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 503

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 184