Search results for: contrastive learning

Authors: Ziying Wu, Danfeng Yan

Abstract:

Multi-Access Edge Computing (MEC) is one of the key technologies of the future 5G network. By deploying edge computing centers at the edge of wireless access network, the computation tasks can be offloaded to edge servers rather than the remote cloud server to meet the requirements of 5G low-latency and high-reliability application scenarios. Meanwhile, with the development of IOV (Internet of Vehicles) technology, various delay-sensitive and compute-intensive in-vehicle applications continue to appear. Compared with traditional internet business, these computation tasks have higher processing priority and lower delay requirements. In this paper, we design a 5G-based Vehicle-Aware Multi-Access Edge Computing Network (VAMECN) and propose a joint optimization problem of minimizing total system cost. In view of the problem, a deep reinforcement learning-based joint computation offloading and task migration optimization (JCOTM) algorithm is proposed, considering the influences of multiple factors such as concurrent multiple computation tasks, system computing resources distribution, and network communication bandwidth. And, the mixed integer nonlinear programming problem is described as a Markov Decision Process. Experiments show that our proposed algorithm can effectively reduce task processing delay and equipment energy consumption, optimize computing offloading and resource allocation schemes, and improve system resource utilization, compared with other computing offloading policies.

Keywords: multi-access edge computing, computation offloading, 5th generation, vehicle-aware, deep reinforcement learning, deep q-network

Procedia PDF Downloads 118

Authors: Adhi Susilo

Abstract:

This paper addresses the roles of distance education in the agricultural extension workers’ education. Agriculture plays an important role in both poverty reduction and economic growth. The technology of agriculture in the developing world should change continuously to keep pace with rising populations and rapidly changing social, economic, and environmental conditions. Therefore, agricultural extension workers should have several competencies in order to carry out their duties properly. One of the essential competencies that they must possess is the professional competency that is directly related to their duties in carrying out extension activities. Such competency can be acquired through studying at Universitas Terbuka (UT). With its distance learning system, agricultural extension workers can study at UT without leaving their duties. This paper presenting sociological analysis and lessons learnt from the specific context of Indonesia. Diversities in geographic, demographic, social cultural and economic conditions of the country provide specific challenges for its distance education practice and the process of social transformation to which distance education can contribute. Extension officers used distance education for personal benefits and increased professional productivity. An increase in awareness is important for the further adoption of distance learning for extension purposes. Organizations in both the public and private sector must work to increase knowledge of ICTs for the benefit of stakeholders. The use of ICTs can increase productivity for extensions officers and expand educational opportunities for learners. The use of distance education by extension to disseminate educational materials around the world is widespread. Increasing awareness and use of distance learning can lead to more productive relationships between extension officers and agricultural stakeholders.

Keywords: agricultural extension, demographic and geographic condition, distance education, ICTs

Procedia PDF Downloads 515

Authors: Giuseppina Settanni, Antonio Panarese, Raffaele Vaira, Maurizio Galiano

Abstract:

Nowdays, artificial intelligence is used successfully in academia and industry for its ability to learn from a large amount of data. In particular, in recent years the use of machine learning algorithms in the field of e-commerce has spread worldwide. In this research study, a prototype software platform was designed and implemented in order to suggest to users the most suitable products for their needs. The platform includes a chatbot and a recommender system based on artificial intelligence algorithms that provide suggestions and decision support to the customer. The recommendation systems perform the important function of automatically filtering and personalizing information, thus allowing to manage with the IT overload to which the user is exposed on a daily basis. Recently, international research has experimented with the use of machine learning technologies with the aim to increase the potential of traditional recommendation systems. Specifically, support vector machine algorithms have been implemented combined with natural language processing techniques that allow the user to interact with the system, express their requests and receive suggestions. The interested user can access the web platform on the internet using a computer, tablet or mobile phone, register, provide the necessary information and view the products that the system deems them most appropriate. The platform also integrates a dashboard that allows the use of the various functions, which the platform is equipped with, in an intuitive and simple way. Artificial intelligence algorithms have been implemented and trained on historical data collected from user browsing. Finally, the testing phase allowed to validate the implemented model, which will be further tested by letting customers use it.

Keywords: machine learning, recommender system, software platform, support vector machine

Procedia PDF Downloads 134

Authors: Aadityaa Singla

Abstract:

The big five personality traits are as follows: openness, conscientiousness, extraversion, agreeableness, and neuroticism. In order to get an insight into their personality, many flocks to these categories, which each have different meanings/characteristics. This information is important not only to individuals but also to career professionals and psychologists who can use this information for candidate assessment or job recruitment. The links between AI and psychology have been well studied in cognitive science, but it is still a rather novel development. It is possible for various AI classification models to accurately predict a personality question via ten input questions. This would contrast with the hundred questions that normal humans have to answer to gain a complete picture of their five personality traits. In order to approach this problem, various AI classification models were used on a dataset to predict what a user may answer. From there, the model's prediction was compared to its actual response. Normally, there are five answer choices (a 20% chance of correct guess), and the models exceed that value to different degrees, proving their significance. By utilizing an MLP classifier, decision tree, linear model, and K-nearest neighbors, they were able to obtain a test accuracy of 86.643, 54.625, 47.875, and 52.125, respectively. These approaches display that there is potential in the future for more nuanced predictions to be made regarding personality.

Keywords: machine learning, personally, big five personality traits, cognitive science

Procedia PDF Downloads 145

Authors: Kausik Halder, Nabendu Chaki, Ranjan Dasgupta

Abstract:

We present a modelling framework that supports the engineering of early requirements specifications for design of learner centric dynamic Learning Management System. The framework is based on i* modelling tool and Means End Analysis, that adopts primitive concepts for modelling early requirements (such as actor, goal, and strategic dependency). We show how pedagogical and computational requirements for designing a learner centric Learning Management system can be adapted for the automatic early requirement engineering specifications. Finally, we presented a model on a Learner Quanta based adaptive Courseware. Our early requirement analysis shows that how means end analysis reveals gaps and inconsistencies in early requirements specifications that are by no means trivial to discover without the help of formal analysis tool.

Keywords: adaptive courseware, early requirement engineering, means end analysis, organizational modelling, requirement modelling

Procedia PDF Downloads 500

Authors: Waleed Al-Nuaimy, Luke Anastassiou, Manjinder Kainth

Abstract:

As the process of teaching has evolved with the advent of new technologies over the ages, so has the process of learning. Educators have perpetually found themselves on the lookout for new technology-enhanced methods of teaching in order to increase learning efficiency and decrease ever expanding workloads. Shortly after the invention of the internet, web-based learning started to pick up in the late 1990s and educators quickly found that the process of providing learning material and marking assignments could change thanks to the connectivity offered by the internet. With the creation of early web-based virtual learning environments (VLEs) such as SPIDER and Blackboard, it soon became apparent that VLEs resulted in higher reported computer self-efficacy among students, but at the cost of students being less satisfied with the learning process . It may be argued that the impersonal nature of VLEs, and their limited functionality may have been the leading factors contributing to this reported dissatisfaction. To this day, often faced with the prospects of assigning colossal engineering cohorts their homework and assessments, educators may frequently choose optimally curated assessment formats, such as multiple-choice quizzes and numerical answer input boxes, so that automated grading software embedded in the VLEs can save time and mark student submissions instantaneously. A crucial skill that is meant to be learnt during most science and engineering undergraduate degrees is gaining the confidence in using, solving and deriving mathematical equations. Equations underpin a significant portion of the topics taught in many STEM subjects, and it is in homework assignments and assessments that this understanding is tested. It is not hard to see that this can become challenging if the majority of assignment formats students are engaging with are multiple-choice questions, and educators end up with a reduced perspective of their students’ ability to manipulate equations. Artificial intelligence (AI) has in recent times been shown to be an important consideration for many technologies. In our paper, we explore the use of new AI based software designed to work in conjunction with current VLEs. Using our experience with the software, we discuss its potential to solve a selection of problems ranging from impersonality to the reduction of educator workloads by speeding up the marking process. We examine the software’s potential to increase learning efficiency through its features which claim to allow more customized and higher-quality feedback. We investigate the usability of features allowing students to input equation derivations in a range of different forms, and discuss relevant observations associated with these input methods. Furthermore, we make ethical considerations and discuss potential drawbacks to the software, including the extent to which optical character recognition (OCR) could play a part in the perpetuation of errors and create disagreements between student intent and their submitted assignment answers. It is the intention of the authors that this study will be useful as an example of the implementation of AI in a practical assessment scenario insofar as serving as a springboard for further considerations and studies that utilise AI in the setting and marking of science and engineering assignments.

Keywords: engineering education, assessment, artificial intelligence, optical character recognition (OCR)

Procedia PDF Downloads 122

Authors: Marilei Amadeu Sabino

Abstract:

The aim of this study is to establish differences between the terms ‘false cognates’, ‘false friends’ and ‘deceptive cognates’, usually considered to be synonyms. It will be shown they are not synonyms, since they do not designate the same linguistic process or phenomenon. Despite their differences in meaning, many pairs of formally similar words in two (or more) different languages are true cognates, although they are usually known as ‘false’ cognates – such as, for instance, the English and Italian lexical items ‘assist x assistere’; ‘attend x attendere’; ‘argument x argomento’; ‘apology x apologia’; ‘camera x camera’; ‘cucumber x cocomero’; ‘fabric x fabbrica’; ‘factory x fattoria’; ‘firm x firma’; ‘journal x giornale’; ‘library x libreria’; ‘magazine x magazzino’; ‘parent x parente’; ‘preservative x preservativo’; ‘pretend x pretendere’; ‘vacancy x vacanza’, to name but a few examples. Thus, one of the theoretical objectives of this paper is firstly to elaborate definitions establishing a distinction between the words that are definitely ‘false cognates’ (derived from different etyma) and those that are just ‘deceptive cognates’ (derived from the same etymon). Secondly, based on Set Theory and on the concepts of equal sets, subsets, intersection of sets and disjoint sets, this study is intended to elaborate some theoretical and practical questions that will be useful in identifying more precisely similarities and differences between cognate words of different languages, and according to graphic interpretation of sets it will be possible to classify them and provide discernment about the processes of semantic changes. Therefore, these issues might be helpful not only to the Learning of Second and Foreign Languages, but they could also give insights into Foreign and Second Language Teaching Methodology. Acknowledgements: FAPESP – São Paulo State Research Support Foundation – the financial support offered (proc. n° 2017/02064-7).

Keywords: deceptive cognates, false cognates, foreign language learning, teaching methodology

Procedia PDF Downloads 337

Authors: Ronit Chakraborty, Sugata Banerji

Abstract:

There has been a marked increase in the reported prevalence of Autism Spectrum Disorder (ASD) among children in the US over the past two decades. This research has analyzed the growth in state-level ASD prevalence against 45 different potentially explanatory factors, including socio-economic, demographic, healthcare, public policy, and political factors. The goal was to understand if these factors have adequate predictive power in modeling the differential growth in ASD prevalence across various states and if they do, which factors are the most influential. The key findings of this study include (1) the confirmation that the chosen feature set has considerable power in predicting the growth in ASD prevalence, (2) the identification of the most influential predictive factors, (3) given the nature of the most influential predictive variables, an indication that a considerable portion of the reported ASD prevalence differentials across states could be attributable to over and under diagnosis, and (4) identification of Florida as a key outlier state pointing to a potential under-diagnosis of ASD there.

Keywords: autism spectrum disorder, clustering, machine learning, predictive modeling

Procedia PDF Downloads 103

Authors: Neal Rupani

Abstract:

Background: A surgical trainee has limited learning opportunities in the operating room in order to gain an ever-increasing standard of surgical skill, competency, and proficiency. These opportunities continue to decline due to numerous factors such as the European Working Time Directive and increasing requirement for service provision. It is therefore imperative to obtain the highest educational value from each educational opportunity. A measure that has yet to be validated in England on surgical trainees called the Operating Room Educational Environment Measure (OREEM) has been developed to identify and evaluate each component of the educational environment with a view to steer future change in optimising educational events in theatre. Aims: The aims of the study are to assess the reliability of the OREEM within England and to evaluate the surgical trainee’s objective perspective of the current operating room educational environment within one region within England. Methods: Using a quantitative study approach, data was collected over one month from surgical trainees within Health Education Thames Valley (Oxford) using an online questionnaire consisting of demographic data, the OREEM, a global satisfaction score. Results: 140 surgical trainees were invited to the study, with an online response of 54 participants (response rate = 38.6%). The OREEM was shown to have good internal consistency (α = 0.906, variables = 40) and unidimensionality, along with all four of its subgroups. The mean OREEM score was 79.16%. The areas highlighted for improvement predominantly focused on improving learning opportunities (average subscale score = 72.9%) and conducting pre- and post-operative teaching (average score = 70.4%). The trainee perception is most satisfactory for the level of supervision and workload (average subscale score = 82.87%). There was no differences found between gender (U = 191.5, p = 0.535) or type of hospital (U = 258.0, p = 0.099), but the learning environment was favoured towards senior trainees (U = 223.5, p = 0.017). There was strong correlation between OREEM and the global satisfaction score (r = 0.755, p<0.001). Conclusions: The OREEM was shown to be reliable in measuring the educational environment in the operating room. This can be used to identify potentially modifiable components for improvement and as an audit tool to ensure high standards are being met. The current perception of the education environment in Health Education Thames Valley is satisfactory, and modifiable internal and external factors such as reducing service provision requirements, empowering trainees to plan lists, creating a team-working ethic between all personnel, and using tools that maximise learning from each operation have been identified to improve learning in the future. There is a favourable attitude to use of such improvement tools, especially for those currently dissatisfied.

Keywords: education environment, surgery, post-graduate education, OREEM

Procedia PDF Downloads 184

Authors: Kamal KC, Zhendong Yin, Dasen Li, Zhilu Wu

Abstract:

Intra-plant disease classification based on leaf images is a challenging computer vision task due to similarities in texture, color, and shape of leaves with a slight variation of leaf spot; and external environmental changes such as lighting and background noises. Deep convolutional neural network (DCNN) has proven to be an effective tool for binary classification. In this paper, two methods for binary classification of diseased plant leaves using DCNN are presented; model created from scratch and transfer learning. Our main contribution is a thorough evaluation of 4 networks created from scratch and transfer learning of 5 pre-trained models. Training and testing of these models were performed on a plant leaf images dataset belonging to 16 distinct classes, containing a total of 22,265 images from 8 different plants, consisting of a pair of healthy and diseased leaves. We introduce a deep CNN model, Optimized MobileNet. This model with depthwise separable CNN as a building block attained an average test accuracy of 99.77%. We also present a fine-tuning method by introducing the concept of a convolutional block, which is a collection of different deep neural layers. Fine-tuned models proved to be efficient in terms of accuracy and computational cost. Fine-tuned MobileNet achieved an average test accuracy of 99.89% on 8 pairs of [healthy, diseased] leaf ImageSet.

Keywords: deep convolution neural network, depthwise separable convolution, fine-grained classification, MobileNet, plant disease, transfer learning

Procedia PDF Downloads 186

Authors: Man-Yun Liu, Emily Chia-Yu Su

Abstract:

Alzheimer's disease (AD) is the public health crisis of the 21st century. AD is a degenerative brain disease and the most common cause of dementia, a costly disease on the healthcare system. Unfortunately, the cause of AD is poorly understood, furthermore; the treatments of AD so far can only alleviate symptoms rather cure or stop the progress of the disease. Currently, there are several ways to diagnose AD; medical imaging can be used to distinguish between AD, other dementias, and early onset AD, and cerebrospinal fluid (CSF). Compared with other diagnostic tools, blood (plasma) test has advantages as an approach to population-based disease screening because it is simpler, less invasive also cost effective. In our study, we used blood biomarkers dataset of The Alzheimer’s disease Neuroimaging Initiative (ADNI) which was funded by National Institutes of Health (NIH) to do data analysis and develop a prediction model. We used independent analysis of datasets to identify plasma protein biomarkers predicting early onset AD. Firstly, to compare the basic demographic statistics between the cohorts, we used SAS Enterprise Guide to do data preprocessing and statistical analysis. Secondly, we used logistic regression, neural network, decision tree to validate biomarkers by SAS Enterprise Miner. This study generated data from ADNI, contained 146 blood biomarkers from 566 participants. Participants include cognitive normal (healthy), mild cognitive impairment (MCI), and patient suffered Alzheimer’s disease (AD). Participants’ samples were separated into two groups, healthy and MCI, healthy and AD, respectively. We used the two groups to compare important biomarkers of AD and MCI. In preprocessing, we used a t-test to filter 41/47 features between the two groups (healthy and AD, healthy and MCI) before using machine learning algorithms. Then we have built model with 4 machine learning methods, the best AUC of two groups separately are 0.991/0.709. We want to stress the importance that the simple, less invasive, common blood (plasma) test may also early diagnose AD. As our opinion, the result will provide evidence that blood-based biomarkers might be an alternative diagnostics tool before further examination with CSF and medical imaging. A comprehensive study on the differences in blood-based biomarkers between AD patients and healthy subjects is warranted. Early detection of AD progression will allow physicians the opportunity for early intervention and treatment.

Keywords: Alzheimer's disease, blood-based biomarkers, diagnostics, early detection, machine learning

Procedia PDF Downloads 322

Authors: Dzhavidan Zeinalov, Bugra Sen, Firangiz Aslanova

Abstract:

Most text-to-speech models cannot operate well in low-resource languages and require a great amount of high-quality training data to be considered good enough. Yet, with the improvements made in ASR systems, it is now much easier than ever to collect data for the design of custom text-to-speech models. In this work, our work on using the ASR model to collect data to build a viable text-to-speech system for one of the leading financial institutions of Azerbaijan will be outlined. NVIDIA’s implementation of the Tacotron 2 model was utilized along with the HiFiGAN vocoder. As for the training, the model was first trained with high-quality audio data collected from the Internet, then fine-tuned on the bank’s single speaker call center data. The results were then evaluated by 50 different listeners and got a mean opinion score of 4.17, displaying that our method is indeed viable. With this, we have successfully designed the first text-to-speech model in Azerbaijani and publicly shared 12 hours of audiobook data for everyone to use.

Keywords: Azerbaijani language, HiFiGAN, Tacotron 2, text-to-speech, transfer learning, whisper

Procedia PDF Downloads 44

Authors: Lisa Chandler, Alistair Ward

Abstract:

A significant component of design pedagogy is the need to foster design thinking in various contexts and to support students in understanding links between educational exercises and their potential application in professional design practice. It is also important that educators provide opportunities for students to engage with new technologies and encourage them to imagine applying their design skills for a range of outcomes. Problem solving is central to design so it is also essential that students understand that there can be multiple solutions to a design brief, and are supported in undertaking creative experimentation to generate imaginative outcomes. This paper presents a case study examining some innovative approaches to addressing these elements of design pedagogy. It investigates the effectiveness of the Immerse Lab, a three wall projection room at the University of the Sunshine Coast, Australia, as a learning context for design practice, for generating ideas and for supporting learning involving the comparative display of design outcomes. The project required first year design students to create a simple graphic design derived from an ordinary object and to incorporate specific design criteria. Utilizing custom-designed software, the students’ solutions were projected together onto the Immerse walls to create a large-scale, immersive grid of images, which was used to compare and contrast various responses to the same problem. The software also enabled individual student designs to be transformed, multiplied and enlarged in multiple ways and prompted discussions around the applicability of the designs in real world contexts. Teams of students interacted with their projected designs, brainstorming imaginative applications for their outcomes. Analysis of 77 anonymous student surveys revealed that the majority of students found: learning in the Immerse Lab to be beneficial; comparative review more effective than in standard tutorial rooms; that the activity generated new ideas; it encouraged students to think differently about their designs; it inspired students to develop their existing designs or create new ones. The project demonstrates that curricula involving immersive spaces can be effective in supporting engaging and relevant design pedagogy and might be utilized in other disciplinary areas.

Keywords: design pedagogy, immersive education, technology-enhanced learning, visualization

Procedia PDF Downloads 258

Authors: Brindha Senthil Kumar, Payel Chakraborty, Senthil Kumar Nachimuthu, Arindam Maitra, Prem Nath

Abstract:

Gastric cancer is predominantly caused by demographic and diet factors as compared to other cancer types. The aim of the study is to predict Early Gastric Cancer (ECG) from diet and lifestyle factors using supervised machine learning algorithms. For this study, 160 healthy individual and 80 cases were selected who had been followed for 3 years (2016-2019), at Civil Hospital, Aizawl, Mizoram. A dataset containing 11 features that are core risk factors for the gastric cancer were extracted. Supervised machine algorithms: Logistic Regression, Naive Bayes, Support Vector Machine (SVM), Multilayer perceptron, and Random Forest were used to analyze the dataset using Python Jupyter Notebook Version 3. The obtained classified results had been evaluated using metrics parameters: minimum_false_positives, brier_score, accuracy, precision, recall, F1_score, and Receiver Operating Characteristics (ROC) curve. Data analysis results showed Naive Bayes - 88, 0.11; Random Forest - 83, 0.16; SVM - 77, 0.22; Logistic Regression - 75, 0.25 and Multilayer perceptron - 72, 0.27 with respect to accuracy and brier_score in percent. Naive Bayes algorithm out performs with very low false positive rates as well as brier_score and good accuracy. Naive Bayes algorithm classification results in predicting ECG showed very satisfactory results using only diet cum lifestyle factors which will be very helpful for the physicians to educate the patients and public, thereby mortality of gastric cancer can be reduced/avoided with this knowledge mining work.

Keywords: Early Gastric cancer, Machine Learning, Diet, Lifestyle Characteristics

Procedia PDF Downloads 161

Authors: Mehmet Akif Bütüner, İlhan Koşalay

Abstract:

Hydroelectric power plants (HEPPs) are renewable energy power plants with the highest installed power in the world. While the control systems operating in these power plants ensure that the system operates at the desired operating point, it is also responsible for stopping the relevant unit safely in case of any malfunction. While these control systems are expected not to miss signals that require stopping, on the other hand, it is desired not to cause unnecessary stops. In traditional control systems including modern systems with SCADA infrastructure, alarm conditions to create warnings or trip conditions to put relevant unit out of service automatically are usually generated with predefined limits regardless of different operating conditions. This approach results in alarm/trip conditions to be less likely to detect minimal changes which may result in serious malfunction scenarios in near future. With the methods proposed in this research, routine behavior of the oil circulation of hydraulic governor of a HEPP will be modeled with machine learning methods using historical data obtained from SCADA system. Using the created model and recently gathered data from control system, oil pressure of hydraulic accumulators will be estimated. Comparison of this estimation with the measurements made and recorded instantly by the SCADA system will help to foresee failure before becoming worse and determine remaining useful life. By using model outputs, maintenance works will be made more planned, so that undesired stops are prevented, and in case of any malfunction, the system will be stopped or several alarms are triggered before the problem grows.

Keywords: hydroelectric, governor, anomaly detection, machine learning, regression

Procedia PDF Downloads 97

Authors: Dipti Parida, Atasi Mohanty

Abstract:

The focus of this research is to examine the interaction effect of flipped teaching and traditional teaching mode across two different medium (English and Odia) of instructional groups. Both Science and History subjects were taken to be taught in the Class- VIII in two different instructional mode/s. In total, 180 students of Class-VIII of both Odia and English medium schools were taken as the samples of this study; 90 participants (each group) were from both English and Odia medium schools ; 45 participants of each of these two groups were again assigned either to flip or traditional teaching method. We have two independent variables and each independent variable with two levels. Medium and mode of instruction are the two independent variables. Medium of instruction has two levels of Odia medium and English medium groups. The mode of instruction has also two levels of flip and traditional teaching method. Here we get 4 different groups, such as Odia medium students with traditional mode of teaching (O.M.T), Odia medium students with flipped mode of teaching (O.M.F), English medium students with traditional mode of teaching (E.M.T) and English medium students with flipped mode of teaching (E.M.F). Before the instructional administration, these four groups were given a test on the concerned topic to be taught. Based on this result, a one-way ANOVA was computed and the obtained result showed that these four groups don’t differ significantly from each other at the beginning. Then they were taught the concerned topic either in traditional or flip mode of teaching method. After that a 2×2×2 repeated measures ANOVA was done to analyze the group differences as well as the learning outcome before and after the teaching. The result table also shows that in post-test the learning outcome is highest in case of English medium students with flip mode of instruction. From the statistical analysis it is clear that the flipped mode of teaching is as effective for Odia medium students as it is for English medium students.

Keywords: medium of instruction, mode of instruction, test mode, vernacular medium

Procedia PDF Downloads 355

Authors: P. Wlodarczak, J. Soar, M. Ally

Abstract:

The dramatic rise in the use of Social Media (SM) platforms such as Facebook and Twitter provide access to an unprecedented amount of user data. Users may post reviews on products and services they bought, write about their interests, share ideas or give their opinions and views on political issues. There is a growing interest in the analysis of SM data from organisations for detecting new trends, obtaining user opinions on their products and services or finding out about their online reputations. A recent research trend in SM analysis is making predictions based on sentiment analysis of SM. Often indicators of historic SM data are represented as time series and correlated with a variety of real world phenomena like the outcome of elections, the development of financial indicators, box office revenue and disease outbreaks. This paper examines the current state of research in the area of SM mining and predictive analysis and gives an overview of the analysis methods using opinion mining and machine learning techniques.

Keywords: social media, text mining, knowledge discovery, predictive analysis, machine learning

Procedia PDF Downloads 423

Authors: Evelyn Fabian

Abstract:

The focus of this discussion centres on the emerging issues in Early Childhood Care and development in Nigeria. Early childhood care is the bedrock of Nigeria’s educational system. However, there are critical issues that had not been addressed and it is frustrating the entire educational process. Thus, this paper will show the inter-connectedness between these issues such as poor funding, trained skillful teachers that would supervise the learning process of the kids, unconducive learning environment and lack of relevant facilities. For a clear grasp of these issues, the researcher visited 36 early childhood centres distributed across the 36 spates of Nigeria. The findings which were expressed in simple percentages revealed a near total absence or government neglect of these critical areas. The findings equally showed a misplaced priority in the government allocation of funds to early child care education and development. The study concludes that this mismatch in the training of these categories of pupils, government should expedite action in addressing these emerging issues in early childhood care and development in Nigeria.

Keywords: early childhood, ECCE, education, emerging issues

Procedia PDF Downloads 533

Authors: Jarek Krajewski, Andre Wittenborn, Martin Sauerland

Abstract:

This abstract describes a promising approach for estimating post-traumatic stress disorder (PTSD) based on prosodic speech characteristics. It illustrates the validity of this method by briefly discussing results from an Arabic refugee sample (N= 47, 32 m, 15 f). A well-established standardized self-report scale “Reaction of Adolescents to Traumatic Stress” (RATS) was used to determine the ground truth level of PTSD. The speech material was prompted by telling about autobiographical related sadness inducing experiences (sampling rate 16 kHz, 8 bit resolution). In order to investigate PTSD-induced speech changes, a self-developed set of 136 prosodic speech features was extracted from the .wav files. This set was adapted to capture traumatization related speech phenomena. An artificial neural network (ANN) machine learning model was applied to determine the PTSD level and reached a correlation of r = .37. These results indicate that our classifiers can achieve similar results to those seen in speech-based stress research.

Keywords: speech prosody, PTSD, machine learning, feature extraction

Procedia PDF Downloads 90

Authors: Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, Hadri Hussain, Syed Rasul

Abstract:

In this paper, a data-driven dictionary approach is proposed for the automatic detection and classification of cardiovascular abnormalities. Electrocardiography (ECG) signal is represented by the trained complete dictionaries that contain prototypes or atoms to avoid the limitations of pre-defined dictionaries. The data-driven trained dictionaries simply take the ECG signal as input rather than extracting features to study the set of parameters that yield the most descriptive dictionary. The approach inherently learns the complicated morphological changes in ECG waveform, which is then used to improve the classification. The classification performance was evaluated with ECG data under two different preprocessing environments. In the first category, QT-database is baseline drift corrected with notch filter and it filters the 60 Hz power line noise. In the second category, the data are further filtered using fast moving average smoother. The experimental results on QT database confirm that our proposed algorithm shows a classification accuracy of 92%.

Keywords: electrocardiogram, dictionary learning, sparse coding, classification

Procedia PDF Downloads 386

Authors: L. S. Chathurika

Abstract:

Early prediction of student performance is an important factor to be gained academic excellence. Whatever the study stream in secondary education, students lay the foundation for higher studies during the first year of their degree or diploma program in Sri Lanka. The information technology (IT) field has certain improvements in the education domain by selecting specialization areas to show the talents and skills of students. These specializations can be software engineering, network administration, database administration, multimedia design, etc. After completing the first-year, students attempt to select the best path by considering numerous factors. The purpose of this experiment is to predict the best study path using machine learning algorithms. Five classification algorithms: decision tree, support vector machine, artificial neural network, Naïve Bayes, and logistic regression are selected and tested. The support vector machine obtained the highest accuracy, 82.4%. Then affecting features are recognized to select the best study path.

Keywords: algorithm, classification, evaluation, features, testing, training

Procedia PDF Downloads 119

Authors: S. Chee Choy, Pauline Swee Choo Goh, Yow Lin Liew

Abstract:

The purpose of this study is to evaluate the English version and a Malay translation of the 21-item Learner Awareness Questionnaire for its application to assess student learning in higher education. The Learner Awareness Questionnaire, originally written in English, is a quantitative measure of how and why students learn. The questionnaire gives an indication of the process and motives to learn using four scales: survival, establishing stability, approval, and loving to learn. Data in the present study came from 680 university students enrolled in various programs in Malaysia. The Malay version of the questionnaire supported a similar four-factor structure and internal consistency to the English version. The four factors of the Malay version also showed moderate to strong correlations with those of the English versions. The results suggest that the Malay version of the questionnaire is similar to the English version. However, further refinement for the questions is needed to strengthen the correlations between the two questionnaires.

Keywords: student learning, learner awareness, questionnaire development, instrument validation

Procedia PDF Downloads 428

Authors: Taksina Bunbut

Abstract:

Personality and grooming are vital for creating professionalism and safety image for all staffs in the airline industry. Airline Business Program also has an aim to educate students through the subject Personality Development and Grooming in order to elevate the quality of students to meet standard requirements of the airline industry. However, students agree that there are many difficulties that cause unsuccessful learning experience in this subject. The research is to study problems that can afflict students from getting good results in the classroom. Furthermore, exploring possible solutions to overcome challenges are also included in this study. The research sample consists of 140 students who attended the class of Personality Development and Grooming. The employed research instrument is a questionnaire. Statistic for data analysis is t-test and Multiple Regression Analysis. The result found that although students are satisfied with teaching and learning of this subject, they considered that teaching in English and teaching topics in social etiquette in different cultures are difficult for them to understand.

Keywords: personality development, grooming, Airline Business Program, soft skill

Procedia PDF Downloads 238

Authors: Subhajit Das, Nirjhar Dhang

Abstract:

Structural damage detection is a challenging work in the field of structural health monitoring (SHM). The damage detection methods mainly focused on the determination of the location and severity of the damage. Model updating is a well known method to locate and quantify the damage. In this method, an error function is defined in terms of difference between the signal measured from ‘experiment’ and signal obtained from undamaged finite element model. This error function is minimised with a proper algorithm, and the finite element model is updated accordingly to match the measured response. Thus, the damage location and severity can be identified from the updated model. In this paper, an error function is defined in terms of modal data viz. frequencies and modal assurance criteria (MAC). MAC is derived from Eigen vectors. This error function is minimized by teaching-learning-based optimization (TLBO) algorithm, and the finite element model is updated accordingly to locate and quantify the damage. Damage is introduced in the model by reduction of stiffness of the structural member. The ‘experimental’ data is simulated by the finite element modelling. The error due to experimental measurement is introduced in the synthetic ‘experimental’ data by adding random noise, which follows Gaussian distribution. The efficiency and robustness of this method are explained through three examples e.g., one truss, one beam and one frame problem. The result shows that TLBO algorithm is efficient to detect the damage location as well as the severity of damage using modal data.

Keywords: damage detection, finite element model updating, modal assurance criteria, structural health monitoring, teaching learning based optimization

Procedia PDF Downloads 215

Authors: Justin D. Olmanson, Fitsum Abebe, Valerie Jones, Eric Kyle, Xianquan Liu, Katherine Robbins, Guieswende Rouamba

Abstract:

The history of education technology--and designing, adapting, and adopting technologies for use in educational spaces--is nuanced, complex, and dynamic. Yet, despite a range of continually emerging technologies, the design and development process often yields results that appear quite similar in terms of affordances and interactions. Through this study we (1) verify the extent to which designs have been constrained, (2) consider what might account for it, and (3) offer a way forward in terms of how we might identify and strategically sidestep these influences--thereby increasing the diversity of our designs with a given technology or within a particular learning domain. We begin our inquiry from the perspective that a host of co-influencing elements, fields, and meta narratives converge on the education technology design process to exert a tangible, often homogenizing effect on the resultant designs. We identify several elements that influence design in often implicit or unquestioned ways (e.g. curriculum, learning theory, economics, learning context, pedagogy), we describe our methodology for identifying the elemental positionality embedded in a design, we direct our analysis to a particular subset of technologies in the field of literacy, and unpack our findings. Our early analysis suggests that the majority of education technologies designed for use/used in US public schools are heavily influenced by a handful of mainstream theories and meta narratives. These findings have implications for how we approach the education technology design process--which we use to suggest alternative methods for designing/ developing with emerging technologies. Our analytical process and re conceptualized design process hold the potential to diversify the ways emerging and established technologies get incorporated into our designs.

Keywords: curriculum, design, innovation, meta narratives

Procedia PDF Downloads 509

Authors: Sofia Horjales, Florencia Palma

Abstract:

Our society is currently experiencing a profound transformation, demanding a proactive response from governmental bodies and higher education institutions to empower the next generation as catalysts for change. Environmental sustainability is rooted in the critical need to maintain the equilibrium and integrity of natural ecosystems, ensuring the preservation of precious natural resources and biodiversity for the benefit of both present and future generations. It is an essential cornerstone of sustainable development, complementing social and economic sustainability. In this evolving landscape, active methodologies take a central role, aligning perfectly with the principles of the 2030 Agenda for Sustainable Development and emerging as a pivotal element of teacher education. The emphasis on active learning methods has been driven by the urgent need to nurture sustainability and instill social responsibility in our future leaders. The Universidad Tecnológica of Uruguay (UTEC) is a public, technologically-oriented institution established in 2012. UTEC is dedicated to decentralization, expanding access to higher education throughout Uruguay, and promoting inclusive social development. Operating through Regional Technological Institutes (ITRs) and associated centers spread across the country, UTEC faces the challenge of remote student populations. To address this, UTEC utilizes e-learning for equal opportunities, self-regulated learning, and digital skills development, enhancing communication among students, teachers, and peers through virtual classrooms. The Interdisciplinary Continuing Education Program is part of the Innovation and Entrepreneurship Department of UTEC. The main goal is to strengthen innovation skills through a transversal and multidisciplinary approach. Within this Program, we have developed a Case of Study and Project-Based Learning Virtual Course designed for university students and open to the broader UTEC community. The primary aim of this course is to establish a strong foundation for comprehending and addressing environmental sustainability issues from an interdisciplinary perspective. Upon completing the course, we expect students not only to understand the intricate interactions between social and ecosystem environments but also to utilize their knowledge and innovation skills to develop projects that offer enhancements or solutions to real-world challenges. Our course design centers on innovative learning experiences, rooted in active methodologies. We explore the intersection of these methods with sustainability and social responsibility in the education of university students. A paramount focus lies in gathering student feedback, empowering them to autonomously generate ideas with guidance from instructors, and even defining their own project topics. This approach underscores that when students are genuinely engaged in subjects of their choice, they not only acquire the necessary knowledge and skills but also develop essential attributes like effective communication, critical thinking, and problem-solving abilities. These qualities will benefit them throughout their lifelong learning journey. We are convinced that education serves as the conduit to merge knowledge and cultivate interdisciplinary collaboration, igniting awareness and instigating action for environmental sustainability. While systemic changes are undoubtedly essential for society and the economy, we are making significant progress by shaping perspectives and sparking small, everyday actions within the UTEC community. This approach empowers our students to become engaged global citizens, actively contributing to the creation of a more sustainable future.

Keywords: active learning, environmental education, project-based learning, soft skills development

Procedia PDF Downloads 71

Authors: Michael Brazley

Abstract:

Virtual Reality (VR) and 3D videos are the most current generation of learning technology today. Virtual Reality and 3D videos are being used in professional offices and Schools now for marketing and education. Technology in the field of design has progress from two dimensional drawings to 3D models, using computers and sophisticated software. Virtual Reality is being used as collaborative means to allow designers and others to meet and communicate inside models or VR platforms using avatars. This research proposes to teach students from different backgrounds how to take a digital model into a 3D video, then into VR, and finally VR with multiple avatars communicating with each other in real time. The next step would be to develop the model where people from three or more different locations can meet as avatars in real time, in the same model and talk to each other. This research is longitudinal, studying the use of 3D videos in graduate design and Virtual Reality in XR (Extended Reality) courses. The research methodology is a combination of quantitative and qualitative methods. The qualitative methods begin with the literature review and case studies. The quantitative methods come by way of student’s 3D videos, survey, and Extended Reality (XR) course work. The end product is to develop a VR platform with multiple avatars being able to communicate in real time. This research is important because it will allow multiple users to remotely enter your model or VR platform from any location in the world and effectively communicate in real time. This research will lead to improved learning and training using Virtual Reality and Avatars; and is generalizable because most Colleges, Universities, and many citizens own VR equipment and computer labs. This research did produce a VR platform with multiple avatars having the ability to move and speak to each other in real time. Major implications of the research include but not limited to improved: learning, teaching, communication, marketing, designing, planning, etc. Both hardware and software played a major role in project success.

Keywords: virtual reality, avatars, education, XR

Procedia PDF Downloads 98

Authors: Thelma Mort

Abstract:

This empirical, qualitative research uses interviews of four intermediate phase English language student teachers at one university in South Africa and is an exploration of student teacher learning on their teaching practicum in their penultimate year of the initial teacher education course. The country’s post-apartheid language in education policy provides a context to this study in that children move from mother tongue language of instruction in foundation phase to English as a language of instruction in Intermediate phase. There is another layer of context informing this study which is the school context; the student teachers’ reflections are from their teaching practicum in resource constrained schools, which make up more than 75% of schools in South Africa. The findings were that in these schools, deep biases existed to local languages, that language was being used as a proxy for social class, and that conditions necessary for language acquisition were absent. The student teachers’ attitudes were in contrast to those found in the schools, namely that they had various pragmatic approaches to overcoming obstacles and that they saw language as enabling interdisciplinary work. This study describes language issues, tensions created by policy in South African schools and also supplies a regional account of learning to teach in resource constrained schools in Cape Town, where such language tensions are more inflated. The central findings in this research illuminate attitudes to language and language education in these teaching practicum schools and the complexity of learning to be a language teacher in these contexts. This study is one of the few local empirical studies regarding language teaching in the classroom and language teacher education; as such it offers some background to the country’s poor performance in both international and national literacy assessments.

Keywords: language teaching, narrative, post apartheid, South Africa, student teacher

Procedia PDF Downloads 147

Authors: Joseph M. Rich, Vinay A. Duddalwar, Assad A. Oberai

Abstract:

Prostate adenocarcinoma is the most common cancer in males, with osseous metastases as the commonest site of metastatic prostate carcinoma (mPC). Treatment monitoring is based on the evaluation and characterization of lesions on multiple imaging studies, including Computed Tomography (CT). Monitoring of the osseous disease burden, including follow-up of lesions and identification and characterization of new lesions, is a laborious task for radiologists. Deep learning algorithms are increasingly used to perform tasks such as identification and segmentation for osseous metastatic disease and provide accurate information regarding metastatic burden. Here, nnUNet was used to produce a model which can segment CT scan images of prostate adenocarcinoma vertebral bone metastatic lesions. nnUNet is an open-source Python package that adds optimizations to deep learning-based UNet architecture but has not been extensively combined with transfer learning techniques due to the absence of a readily available functionality of this method. The IRB-approved study data set includes imaging studies from patients with mPC who were enrolled in clinical trials at the University of Southern California (USC) Health Science Campus and Los Angeles County (LAC)/USC medical center. Manual segmentation of metastatic lesions was completed by an expert radiologist Dr. Vinay Duddalwar (20+ years in radiology and oncologic imaging), to serve as ground truths for the automated segmentation. Despite nnUNet’s success on some medical segmentation tasks, it only produced an average Dice Similarity Coefficient (DSC) of 0.31 on the USC dataset. DSC results fell in a bimodal distribution, with most scores falling either over 0.66 (reasonably accurate) or at 0 (no lesion detected). Applying more aggressive data augmentation techniques dropped the DSC to 0.15, and reducing the number of epochs reduced the DSC to below 0.1. Datasets have been identified for transfer learning, which involve balancing between size and similarity of the dataset. Identified datasets include the Pancreas data from the Medical Segmentation Decathlon, Pelvic Reference Data, and CT volumes with multiple organ segmentations (CT-ORG). Some of the challenges of producing an accurate model from the USC dataset include small dataset size (115 images), 2D data (as nnUNet generally performs better on 3D data), and the limited amount of public data capturing annotated CT images of bone lesions. Optimizations and improvements will be made by applying transfer learning and generative methods, including incorporating generative adversarial networks and diffusion models in order to augment the dataset. Performance with different libraries, including MONAI and custom architectures with Pytorch, will be compared. In the future, molecular correlations will be tracked with radiologic features for the purpose of multimodal composite biomarker identification. Once validated, these models will be incorporated into evaluation workflows to optimize radiologist evaluation. Our work demonstrates the challenges of applying automated image segmentation to small medical datasets and lays a foundation for techniques to improve performance. As machine learning models become increasingly incorporated into the workflow of radiologists, these findings will help improve the speed and accuracy of vertebral metastatic lesions detection.

Keywords: deep learning, image segmentation, medicine, nnUNet, prostate carcinoma, radiomics

Procedia PDF Downloads 96

Authors: Sakshi V. Tantak, Vishap K. Malik, Neelanjney Pilarisetty

Abstract:

A patent is an exclusive right granted for an invention. It can be a product or a process that provides an innovative method of doing something, or offers a new technical perspective or solution to a problem. A patent can be obtained by making the technical information and details about the invention publicly available. The patent owner has exclusive rights to prevent or stop anyone from using the patented invention for commercial uses. Any commercial usage, distribution, import or export of a patented invention or product requires the patent owner’s consent. It has been observed that the central and important parts of patents are scripted in idiosyncratic and complex linguistic structures that can be difficult to read, comprehend or interpret for the masses. The abstracts of these patents tend to obfuscate the precise nature of the patent instead of clarifying it via direct and simple linguistic constructs. This makes it necessary to have an efficient access to this knowledge via concise and transparent summaries. However, as mentioned above, due to complex and repetitive linguistic constructs and extremely long sentences, common extraction-oriented automatic text summarization methods should not be expected to show a remarkable performance when applied to patent documents. Other, more content-oriented or abstractive summarization techniques are able to perform much better and generate more concise summaries. This paper proposes an efficient summarization system for patents using artificial intelligence, natural language processing and deep learning techniques to condense the knowledge and essential information from a patent document into a single summary that is easier to understand without any redundant formatting and difficult jargon.

Keywords: abstractive summarization, deep learning, natural language Processing, patent document

Procedia PDF Downloads 123