Search results for: module based teaching and learning

Authors: Diego Aguirre, Olac Fuentes

Abstract:

In this paper, we present a taxonomy of weight initialization schemes used in deep learning. We survey the most representative techniques in each class and compare them in terms of overhead cost, convergence rate, and applicability. We also introduce a new weight initialization scheme. In this technique, we perform an initial feedforward pass through the network using an initialization mini-batch. Using statistics obtained from this pass, we initialize the weights of the network, so the following properties are met: 1) weight matrices are orthogonal; 2) ReLU layers produce a predetermined number of non-zero activations; 3) the output produced by each internal layer has a unit variance; 4) weights in the last layer are chosen to minimize the error in the initial mini-batch. We evaluate our method on three popular architectures, and a faster converge rates are achieved on the MNIST, CIFAR-10/100, and ImageNet datasets when compared to state-of-the-art initialization techniques.

Keywords: deep learning, image classification, supervised learning, weight initialization

Procedia PDF Downloads 139

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 389

Authors: Rangika Perera, Shyamani Hettiarachchi, Fran Hagstrom

Abstract:

Dyslexia is the most common reading reading-related difficulty among the school school-aged population and currently, 5-10% are showing the features of dyslexia in Sri Lanka. As there is an insufficient number of speech and language pathologists in the country and few speech and language pathologists working in government mainstream school settings, these children who are at risk of dyslexia are not receiving enough quality early intervention services to develop their reading skills. As teachers are the key professionals who are directly working with these children, using them as the primary facilitators to improve their reading skills will be the most effective approach. This study aimed to identify the efficacy of a two and half a day of intensive training provided to fifteen mainstream government school teachers of grade two classes. The goal of the training was to enhance their knowledge of dyslexia and provide full classroom skills training that could be used to support the development of the students’ reading competencies. A closed closed-ended multiple choice questionnaire was given to these teachers pre and -post-training to measure teachers’ knowledge of dyslexia, the areas in which these children needed additional support, and the best strategies to facilitate reading competencies. The data revealed that the teachers’ knowledge in all areas was significantly poorer prior to the training and that there was a clear improvement in all areas after the training. The gain in target areas of teaching skills selected to improve the reading skills of children was evaluated through peer feedback. Teachers were assigned to three groups and expected to model how they were going to introduce the skills in recommended areas using researcher developed, validated and reliability reliability-tested materials and the strategies which were introduced during the training within the given tasks. Peers and the primary investigator rated teachers’ performances and gave feedback on organizational skills, presentation skills of materials, clarity of instruction, and appropriateness of vocabulary. After modifying their skills according to the feedback the teachers received, they were expected to modify and represent the same tasks to the group the following day. Their skills were re-evaluated by the peers and primary investigator using the same rubrics to measure the improvement. The findings revealed a significant improvement in their teaching skills development. The data analysis of both knowledge and skills gains of the teachers was carried out using quantitative descriptive data analysis. The overall findings of the study yielded promising results that support intensive training as a method for improving teachers’ knowledge and teaching skill development for use with children in a whole class intervention setting who are at risk of dyslexia.

Keywords: Dyslexia, knowledge, teaching skills, training program

Procedia PDF Downloads 77

Authors: Ulriikka Savela-Huovinen, Hanni Muukkonen, Auli Toom

Abstract:

The development of workplace as a learning environment has been emphasized in research field of workplace learning. The prior literature on sensory performance emphasized the individual’s competences as assessor, while the competences in the collaborative interactional and knowledge creation practices as workplace learning method are not often mentioned. In the present study aims to find out what kinds of competences and contexts are central when assessor conducts food sensory evaluation in authentic professional context. The aim was to answer the following questions: first, what kinds of competences does sensory evaluation require according to assessors? And second, what kinds of contexts for sensory evaluation do assessors report? Altogether thirteen assessors from three Finnish food companies were interviewed by using semi-structural thematic interviews to map practices and development intentions as well as to explicate already established practices. The qualitative data were analyzed by following the principles of abductive and inductive content analysis. Analysis phases were combined and their results were considered together as a cross-analysis. When evaluated independently required competences were perception, knowledge of specific domains and methods and cognitive skills e.g. memory. Altogether, 42% of analysis units described individual evaluation contexts, 53% of analysis units described collaborative interactional contexts, and 5% of analysis units described collaborative knowledge creation contexts. Related to collaboration, analysis reviewed learning, sharing and reviewing both external and in-house consumer feedback, developing methods to moderate small-panel evaluation and developing product vocabulary collectively between the assessors. Knowledge creation contexts individualized from daily practices especially in cases product defects were sought and discussed. The study findings contribute to the explanation that sensory assessors learn extensively from one another in the collaborative interactional and knowledge creation context. Assessors learning and abilities to work collaboratively in the interactional and knowledge creation contexts need to be ensured in the development of the expertise.

Keywords: assessor, collaboration, competences, contexts, learning and practices, sensory evaluation

Procedia PDF Downloads 240

Authors: Vicky Khasandi-Telewa, Sinfree Makoni

Abstract:

This paper examines the lived experiences of Kenyans caught between the two main varieties of English and the communication challenges they often face. The paper aims to provide evidence for the challenges that Kenyan speakers of English have experienced as a result of the confluence between British English (BrE) and American English (AmE). The study is explorative thus, qualitative and a descriptive research design was used. The objectives were to describe the communication challenges Kenyans encounter due to the differences in grammar, pronunciation, vocabulary, and pragmatics between AmE and BrE and, to illuminate these variations to enable the Kenyan English learner to communicate appropriately. The purposive sample consisted of sixty five subjects, all who were from a top girls national high school in Kenya, therefore, many are in high-end positions nationally and internationally and well-travelled; in fact, seven are based in the USA, two in the United Kingdom and one lives in Australia. Using interviews, they were asked about their experiences with the different varieties of English, and their responses recorded. Autoethnography, a qualitative research method that involves introspection and cultural analysis, was also used. Thematic content analysis was used to extract the themes and group them for data analysis. The theoretical framework used is World Englishes by Kachru. The results indicate that there is indeed some communication breakdown due to linguistic varieties, but the differences are largely understood by speakers of the different varieties. Attitude plays a major role in communication challenges between the different Englishes, especially among teachers. The study urges acceptance of different varieties of English so long as communication takes place. This has implications for teaching English to Kenyan and speakers of other languages to whom English is taught as a Second Language or Foreign language.

Keywords: American english, british english, kenyan english, englishes, teaching of english to speakers of other languages (TeSOL)

Procedia PDF Downloads 74

Authors: Amber Hatch, Eric Wright, Feihong Wang

Abstract:

Research suggests that attachment in close relationships affects one’s emotional processes, mindfulness, conflict-management behaviors, and interpersonal interactions. Attachment insecurity is often associated with maladaptive social interactions and suboptimal relationship qualities. Past studies have considered how the nature of emotion regulation and mindfulness in teachers may be related to student or classroom outcomes. Still, no research has examined how the relationship between such internal experiences and classroom management outcomes may also be related to teachers’ attachment insecurity. This study examined the interrelationships between teachers’ attachment insecurity, mindfulness tendencies, emotion regulation abilities, and classroom management efficacy as indexed by students’ classroom behavior and teachers’ response effectiveness. Teachers’ attachment insecurity was evaluated using the global ECRS-SF, which measures both attachment anxiety and avoidance. The present study includes a convenient sample of 357 American elementary school teachers who responded to a survey regarding their classroom management efficacy, attachment in/security, dispositional mindfulness, emotion regulation strategies, and difficulties in emotion regulation, primarily assessed via pre-existing instruments. Good construct validity was demonstrated for all scales used in the survey. Sample demographics, including gender (94% female), race (92% White), age (M = 41.9 yrs.), years of teaching experience (M = 15.2 yrs.), and education level were similar to the population from which it was drawn, (i.e., American elementary school teachers). However, white women were slightly overrepresented in our sample. Correlational results suggest that teacher attachment insecurity is associated with poorer classroom management efficacy as indexed by students’ disruptive behavior and teachers’ response effectiveness. Attachment anxiety was a much stronger predictor of adverse student behaviors and ineffective teacher responses to adverse behaviors than attachment avoidance. Mindfulness, emotion regulation abilities, and years of teaching experience predicted positive classroom management outcomes. Attachment insecurity and mindfulness were more strongly related to frequent adverse student behaviors, while emotion regulation abilities were more strongly related to teachers’ response effectiveness. The teaching experience was negatively related to attachment insecurity and positively related to mindfulness and emotion regulation abilities. Although the data were cross-sectional, path analyses revealed that attachment insecurity is directly related to classroom management efficacy. Through two routes, this relationship is further mediated by emotion regulation and mindfulness in teachers. The first route of indirect effect suggests double mediation by teacher’s emotion regulation and then teacher mindfulness in the relationship between teacher attachment insecurity and classroom management efficacy. The second indirect effect suggests mindfulness directly mediated the relationship between attachment insecurity and classroom management efficacy, resulting in improved model fit statistics. However, this indirect effect is much smaller than the double mediation route through emotion regulation and mindfulness in teachers. Given the significant predication of teacher attachment insecurity, mindfulness, and emotion regulation on teachers’ classroom management efficacy both directly and indirectly, the authors recommend improving teachers’ classroom management efficacy via a three-pronged approach aiming at enhancing teachers’ secure attachment and supporting their learning adaptive emotion regulation strategies and mindfulness techniques.

Keywords: Classroom management efficacy, student behavior, teacher attachment, teacher emotion regulation, teacher mindfulness

Procedia PDF Downloads 89

Authors: Jian-Jun Gao

Abstract:

Repetition is used for a variety of functions in conversation. When young children first learn to speak, they often repeat words from the adult’s recent utterance with the learning and social function. The objective of this study was to ascertain whether the repetitions are equivalent in indicating attention to new words and the initial repeat of information in conversation. Based on the observation of naturally occurring language use in Taiwan Corpus of Child Mandarin (TCCM), the results in this study provided empirical support to the previous findings that children are more likely to repeat new words they are offered than to repeat new information. When children get older, there would be a drop in the repetition of both new words and new information.

Keywords: acquisition, corpus, mandarin, new words, new information, repetition

Procedia PDF Downloads 153

Authors: Joy Cao, Min Zhou

Abstract:

Purpose: Acute Type A aortic dissection is a well-known cause of extremely high mortality rate. A highly accurate and cost-effective non-invasive predictor is critically needed so that the patient can be treated at earlier stage. Although various CFD approaches have been tried to establish some prediction frameworks, they are sensitive to uncertainty in both image segmentation and boundary conditions. Tedious pre-processing and demanding calibration procedures requirement further compound the issue, thus hampering their clinical applicability. Using the latest physics informed deep learning methods to establish an accurate and cost-effective predictor framework are amongst the main goals for a better Type A aortic dissection treatment. Methods: Via training a novel physics-informed deep residual network, with non-invasive 4D MRI displacement vectors as inputs, the trained model can cost-effectively calculate all these biomarkers: aortic blood pressure, WSS, and OSI, which are used to predict potential type A aortic dissection to avoid the high mortality events down the road. Results: The proposed deep learning method has been successfully trained and tested with both synthetic 3D aneurysm dataset and a clinical dataset in the aortic dissection context using Google colab environment. In both cases, the model has generated aortic blood pressure, WSS, and OSI results matching the expected patient’s health status. Conclusion: The proposed novel physics-informed deep residual network shows great potential to create a cost-effective, non-invasive predictor framework. Additional physics-based de-noising algorithm will be added to make the model more robust to clinical data noises. Further studies will be conducted in collaboration with big institutions such as Cleveland Clinic with more clinical samples to further improve the model’s clinical applicability.

Keywords: type-a aortic dissection, deep residual networks, blood flow modeling, data-driven modeling, non-invasive diagnostics, deep learning, artificial intelligence.

Procedia PDF Downloads 94

Authors: N. D'Amico, E. Grossi, B. Colombo, F. Rigiroli, M. Buscema, D. Fazzini, G. Cornalba, S. Papa

Abstract:

Purpose: To characterize, through a radiomic approach, the nature of nodules considered non-specific by expert radiologists, recognized in magnetic resonance mammography (MRm) with T1-weighted (T1w) sequences with paramagnetic contrast. Material and Methods: 47 cases out of 1200 undergoing MRm, in which the MRm assessment gave uncertain classification (non-specific nodules), were admitted to the study. The clinical outcome of the non-specific nodules was later found through follow-up or further exams (biopsy), finding 35 benign and 12 malignant. All MR Images were acquired at 1.5T, a first basal T1w sequence and then four T1w acquisitions after the paramagnetic contrast injection. After a manual segmentation of the lesions, done by a radiologist, and the extraction of 150 radiomic features (30 features per 5 subsequent times) a machine learning (ML) approach was used. An evolutionary algorithm (TWIST system based on KNN algorithm) was used to subdivide the dataset into training and validation test and to select features yielding the maximal amount of information. After this pre-processing, different machine learning systems were applied to develop a predictive model based on a training-testing crossover procedure. 10 cases with a benign nodule (follow-up older than 5 years) and 18 with an evident malignant tumor (clear malignant histological exam) were added to the dataset in order to allow the ML system to better learn from data. Results: NaiveBayes algorithm working on 79 features selected by a TWIST system, resulted to be the best performing ML system with a sensitivity of 96% and a specificity of 78% and a global accuracy of 87% (average values of two training-testing procedures ab-ba). The results showed that in the subset of 47 non-specific nodules, the algorithm predicted the outcome of 45 nodules which an expert radiologist could not identify. Conclusion: In this pilot study we identified a radiomic approach allowing ML systems to perform well in the diagnosis of a non-specific nodule at MR mammography. This algorithm could be a great support for the early diagnosis of malignant breast tumor, in the event the radiologist is not able to identify the kind of lesion and reduces the necessity for long follow-up. Clinical Relevance: This machine learning algorithm could be essential to support the radiologist in early diagnosis of non-specific nodules, in order to avoid strenuous follow-up and painful biopsy for the patient.

Keywords: breast, machine learning, MRI, radiomics

Procedia PDF Downloads 271

Authors: Tolulope Aremu

Abstract:

The key process steps to produce liquid detergent products will introduce potential defects, such as formulation, mixing, filling, and packaging, which might compromise product quality, consumer safety, and operational efficiency. Real-time identification and characterization of such defects are of prime importance for maintaining high standards and reducing waste and costs. Usually, defect detection is performed by human inspection or rule-based systems, which is very time-consuming, inconsistent, and error-prone. The present study overcomes these limitations in dealing with optimization in defect characterization within the process for making liquid detergents using Machine Learning algorithms. Performance testing of various machine learning models was carried out: Support Vector Machine, Decision Trees, Random Forest, and Convolutional Neural Network on defect detection and classification of those defects like wrong viscosity, color deviations, improper filling of a bottle, packaging anomalies. These algorithms have significantly benefited from a variety of optimization techniques, including hyperparameter tuning and ensemble learning, in order to greatly improve detection accuracy while minimizing false positives. Equipped with a rich dataset of defect types and production parameters consisting of more than 100,000 samples, our study further includes information from real-time sensor data, imaging technologies, and historic production records. The results are that optimized machine learning models significantly improve defect detection compared to traditional methods. Take, for instance, the CNNs, which run at 98% and 96% accuracy in detecting packaging anomaly detection and bottle filling inconsistency, respectively, by fine-tuning the model with real-time imaging data, through which there was a reduction in false positives of about 30%. The optimized SVM model on detecting formulation defects gave 94% in viscosity variation detection and color variation. These values of performance metrics correspond to a giant leap in defect detection accuracy compared to the usual 80% level achieved up to now by rule-based systems. Moreover, this optimization with models can hasten defect characterization, allowing for detection time to be below 15 seconds from an average of 3 minutes using manual inspections with real-time processing of data. With this, the reduction in time will be combined with a 25% reduction in production downtime because of proactive defect identification, which can save millions annually in recall and rework costs. Integrating real-time machine learning-driven monitoring drives predictive maintenance and corrective measures for a 20% improvement in overall production efficiency. Therefore, the optimization of machine learning algorithms in defect characterization optimum scalability and efficiency for liquid detergent companies gives improved operational performance to higher levels of product quality. In general, this method could be conducted in several industries within the Fast moving consumer Goods industry, which would lead to an improved quality control process.

Keywords: liquid detergent manufacturing, defect detection, machine learning, support vector machines, convolutional neural networks, defect characterization, predictive maintenance, quality control, fast-moving consumer goods

Procedia PDF Downloads 24

Authors: Merav Hayakac, Orit Avidov-Ungarab

Abstract:

The current study adopted an interpretive-constructivist approach to examine how senior academics from a large sample of Israeli teacher education colleges serving general or religious populations perceived the integration of digital games into their teacher instruction and what their policy and vision were in this regard in the context of the COVID-19 pandemic. Half the participants expressed a desire to integrate digital games into their teaching and learning but acknowledged that this practice was uncommon. Only a small minority believed they had achieved successful integration, with doubt and skepticism expressed by some religious colleges. Most colleges had policies encouraging technology integration supported by ongoing funding. Although a considerable gap between policy and implementation remained, the COVID-19 pandemic was viewed as having accelerated the integration of digital games into pre-service teacher instruction. The findings suggest that discussions around technology-related vision and policy and their translation into practice should relate to the specific cultural needs and academic preparedness of the population(s) served by the college.

Keywords: COVID-19, digital games, pedagogy, teacher education colleges

Procedia PDF Downloads 101

Authors: Saurabh Kumar

Abstract:

In the fiercely competitive landscape of e-commerce, understanding and mitigating customer churn has become paramount for sustainable business growth. This paper presents a thorough investigation into the application of machine learning techniques for churn prediction in e-commerce, aiming to provide actionable insights for businesses seeking to enhance customer retention strategies. We conduct a comparative study of various machine learning algorithms, including traditional statistical methods and ensemble techniques, leveraging a rich dataset sourced from Kaggle. Through rigorous evaluation, we assess the predictive performance, interpretability, and scalability of each method, elucidating their respective strengths and limitations in capturing the intricate dynamics of customer churn. We identified the XGBoost classifier to be the best performing. Our findings not only offer practical guidelines for selecting suitable modeling approaches but also contribute to the broader understanding of customer behavior in the e-commerce domain. Ultimately, this research equips businesses with the knowledge and tools necessary to proactively identify and address churn, thereby fostering long-term customer relationships and sustaining competitive advantage.

Keywords: customer churn, e-commerce, machine learning techniques, predictive performance, sustainable business growth

Procedia PDF Downloads 36

Authors: Terence Soule, Tami Al Ghamdi

Abstract:

To study how to transfer knowledge from multiple source problems to the target problem, we modeled the Transfer Learning (TL) process using Genetic Algorithms as the model solver. TL is the process that aims to transfer learned data from one problem to another problem. The TL process aims to help Machine Learning (ML) algorithms find a solution to the problems. The Genetic Algorithms (GA) give researchers access to information that we have about how the old problem is solved. In this paper, we have five different source problems, and we transfer the knowledge to the target problem. We studied different scenarios of the target problem. The results showed combined knowledge from multiple source problems improves the GA performance. Also, the process of combining knowledge from several problems results in promoting diversity of the transferred population.

Keywords: transfer learning, genetic algorithm, evolutionary computation, source and target

Procedia PDF Downloads 143

Authors: Arif Ahmed Mohammed Al-Ahdal

Abstract:

Poetry, tales, and fables have always been a part of the L1 repertoire and one that takes the learners to another amazing and fascinating world of imagination. The storytelling class and the genre of poems are activities greatly enjoyed by all age groups. The very significant idea behind their inclusion in the language curriculum is to sensitize young minds to a wide range of human emotions that are believed to greatly contribute to building their social resilience, emotional stability, empathy towards fellow creatures, and literacy. Quite certainly, the learning objective at this stage is not language acquisition (though it happens as an automatic process) but getting the young learners to be acquainted with an entire spectrum of what may be called the ‘noble’ abilities of the human race. They enrich their very existence, inspiring them to unearth ‘selves’ that help them as adults and enable them to co-exist fruitfully and symbiotically with their fellow human beings. By extension, ‘higher’ training in these literature genres shows the universality of human emotions, sufferings, aspirations, and hopes. The current study is anchored on the Reader-Response-Theory in literature learning, which suggests that the reader reconstructs work and re-enacts the author's creative role. Reiteratingly, literary works provide clues or verbal symbols in a linguistic system, widely accepted by everyone who shares the language, but everyone reads their own life experiences and situations into them. The significance of words depends on the reader, even if they have a typical relationship. In every reading, there is an interaction between the reader and the text. The process of reading is an experience in which the reader tries to comprehend the literary work, which surpasses its full potential since it provides emotional and intellectual reactions that are not anticipated from the document but cannot be affirmed just by the reader as a part of the text. The idea is that the text forms the basis of a unifying experience. A reinterpretation of the literary text may transform it into a guiding principle to respond to actual experiences and personal memories. The impulses delivered to the reader vary according to poetry or texts; nevertheless, the readers differ considerably even with the same material. Previous studies confirm that poetry is a useful tool for learning a language. This present paper works on these hypotheses and proposes to study the impetus given to L2 learning as a factor of exposure to poetry and meaningful stories in L1. The driving force behind the choice of this topic is the first-hand experience that the researcher had while teaching a literary text to a group of BA students who, as a reaction to the text, initially burst into tears and ultimately turned the class into an interactive session. The study also intends to compare the performance of male and female students post intervention using pre and post-tests, apart from undertaking a detailed inquiry via interviews with college learners of English to understand how L1 literature plays a great role in the acquisition of L2.

Keywords: SLA, literary text, poetry, tales, affective factors

Procedia PDF Downloads 83

Authors: James Ladzekpo

Abstract:

Background: The urgent need to identify new pharmacological targets for diabetes treatment and prevention has been amplified by the disease's extensive impact on individuals and healthcare systems. A deeper insight into the biological underpinnings of diabetes is crucial for the creation of therapeutic strategies aimed at these biological processes. Current predictive models based on genetic variations fall short of accurately forecasting diabetes. Objectives: Our study aims to pinpoint key epigenetic factors that predispose individuals to diabetes. These factors will inform the development of an advanced predictive model that estimates diabetes risk from genetic profiles, utilizing state-of-the-art statistical and data mining methods. Methodology: We have implemented a recursive feature elimination with cross-validation using the support vector machine (SVM) approach for refined feature selection. Building on this, we developed six machine learning models, including logistic regression, k-Nearest Neighbors (k-NN), Naive Bayes, Random Forest, Gradient Boosting, and Multilayer Perceptron Neural Network, to evaluate their performance. Findings: The Gradient Boosting Classifier excelled, achieving a median recall of 92.17% and outstanding metrics such as area under the receiver operating characteristics curve (AUC) with a median of 68%, alongside median accuracy and precision scores of 76%. Through our machine learning analysis, we identified 31 genes significantly associated with diabetes traits, highlighting their potential as biomarkers and targets for diabetes management strategies. Conclusion: Particularly noteworthy were the Gradient Boosting Classifier and Multilayer Perceptron Neural Network, which demonstrated potential in diabetes outcome prediction. We recommend future investigations to incorporate larger cohorts and a wider array of predictive variables to enhance the models' predictive capabilities.

Keywords: diabetes, machine learning, prediction, biomarkers

Procedia PDF Downloads 61

Authors: Sudheer Dhume, T. Prasad

Abstract:

There are distinct signs of Business Education losing its sheen. It is more so in developing countries. One of the reasons is the value addition at the end of 2 year MBA program is not matching with the requirements of present times and expectations of the students. In this backdrop, Pedagogy Innovation has become prerequisite for making our MBA programs relevant and useful. This paper is the description and analysis of innovative Action Learning pedagogical approach adopted by a group of faculty members at NITIE Mumbai. It not only promotes multidisciplinary research but also enhances integration of the functional areas skillsets in the students. The paper discusses the theoretical bases of this pedagogy and evaluates the effectiveness of it vis-à-vis conventional pedagogical tools. The evaluation research using Bloom’s taxonomy framework showed that this blended method of Business Education is much superior as compared to conventional pedagogy.

Keywords: action learning, blooms taxonomy, business education, innovation, pedagogy

Procedia PDF Downloads 274

Authors: B. L. Ho, L. Shi, D. F. Wang, V. C. T. Mok

Abstract:

The brain’s functional connectivity while temporally non-stationary does express consistency at a macro spatial level. The study of stable resting state connectivity patterns hence provides opportunities for identification of diseases if such stability is severely perturbed. A mathematical model replicating the brain’s spatial connections will be useful for understanding brain’s representative geometry and complements the empirical model where it falls short. Empirical computations tend to involve large matrices and become infeasible with fine parcellation. However, the proposed analytical model has no such computational problems. To improve replicability, 92 subject data are obtained from two open sources. The proposed methodology, inspired by financial theory, uses multivariate regression to find relationships of every cortical region of interest (ROI) with some pre-identified hubs. These hubs acted as representatives for the entire cortical surface. A variance-covariance framework of all ROIs is then built based on these relationships to link up all the ROIs. The result is a high level of match between model and empirical correlations in the range of 0.59 to 0.66 after adjusting for sample size; an increase of almost forty percent. More significantly, the model framework provides an intuitive way to delineate between systemic drivers and idiosyncratic noise while reducing dimensions by more than 30 folds, hence, providing a way to conduct attribution analysis. Due to its analytical nature and simple structure, the model is useful as a standalone toolkit for network dependency analysis or as a module for other mathematical models.

Keywords: functional magnetic resonance imaging, multivariate regression, network hubs, resting state functional connectivity

Procedia PDF Downloads 155

Authors: Katherine Karayianis

Abstract:

Children with Attention Deficit Hyperactivity Disorder (ADHD) have trouble learning in traditional classrooms. These children miss out on important developmental opportunities in school, which leads to challenges starting in early childhood, and these problems persist throughout their adult lives. Despite receiving supplemental support in school, children with ADHD still perform below their non-ADHD peers. Thus, there is a great need to find better ways of facilitating learning in children with ADHD. Evidence has shown that children with ADHD learn best through interactive engagement, but this is not always possible in schools, given classroom restraints and the large student-to-teacher ratio. Redesigning classrooms may not be feasible, so informal learning opportunities provide a possible alternative. One popular informal learning opportunity is educational TV shows like Sesame Street. These types of educational shows can teach children foundational skills taught in pre-K and early elementary school. One downside to these shows is the lack of interactive dialogue between the TV characters and the child viewers. Pseudo-interaction is often deployed, but the benefits are limited if the characters can neither understand nor contingently respond to the child. AI technology has become extremely advanced and is now popular in many electronic devices that both children and adults have access to. AI has been successfully used to create interactive dialogue in children’s educational TV shows, and results show that this enhances children’s learning and engagement, especially when children perceive the character as a reliable teacher. It is likely that children with ADHD, whose minds may otherwise wander, may especially benefit from this type of interactive technology, possibly to a greater extent depending on their perception of the animated dialogic agent. To investigate this issue, I have begun examining the moderating role of inattention among children’s learning from an educational TV show with different types of dialogic interactions. Preliminary results have shown that when character interactions are neither immediate nor accurate, children who are more easily distracted will have greater difficulty learning from the show, but contingent interactions with a TV character seem to buffer these negative effects of distractibility by keeping the child engaged. To extend this line of work, the moderating role of the child’s perception of the dialogic agent as a reliable teacher will be examined in the association between children’s attention and the type of dialogic interaction in the TV show. As such, the current study will investigate this moderated moderation.

Keywords: attention, dialogic TV, informal learning, educational TV, perception of teacher

Procedia PDF Downloads 89

Authors: Priyashri Kamlesh Sridhar, Suranga Nanayakkara

Abstract:

Current frameworks in assessment follow lesson delivery and rely heavily on test performance or teacher’s observations. This, however, neglects the underlying cognitive load during the learning process. Identifying the pivotal points when the load occurs helps design effective pedagogies and tools that respond to learners’ cognitive state. There has been limited research on quantifying cognitive load in preschoolers, real-time. In this study, we recorded electrodermal activity and heart rate variability (HRV) from 10 kindergarteners performing executive function tasks and Johnson Woodcock test of cognitive abilities. Preliminary findings suggest that there are indeed sensitive task-dependent markers in skin conductance (number of SCRs and average amplitude of SCRs) and HRV (mean heart rate and low frequency component) captured during the learning process.

Keywords: early childhood, learning, methodologies, pedagogies

Procedia PDF Downloads 322

Authors: Ruby A. L. Espineli

Abstract:

The study assessed the Philippine National Police strategies in the implementation of ‘Peace and Order Agenda for Transformation and Upholding of the Rule-of-Law’ P.A.T.R.O.L Plan 2030. Its operational roadmap presents four perspectives which include resource management, learning and growth, process excellence; and community. Focused group discussion, observation, and distribution of survey questionnaire to selected PNP officers and community members were done to identify and describe the implementation, problems encountered and measures to address the problems of the PNP P.A.T.R.O.L Plan 2030. In resource management, PNP allocates most sufficient funds in providing service firearms, patrol vehicle, and internet connections. In terms of learning and growth, the attitude of PNP officers is relatively higher than their knowledge and skills. Moreover, in terms of process excellence, the PNP use several crime preventions and crime solution strategies to deliver an immediate response to calls of the community. As regards, community perspective, PNP takes effort in establishing partnership with community. It is also interesting to note that PNP officers and community were both undecided on the existence of problems encountered in the implementation of P.A.T.R.O.L Plan 2030. But, they had proactive behavior as they agreed on all the specified measures to address the problems encountered in implementation of PNP P.A.T.R.O.L. Plan 2030. A strategic framework, based on the findings was formulated in this study that could improve and entrench the harmonious working relationship between the PNP and stakeholders in the enhancement of the implementation of PNP P.A.T.R.O.L. Plan 2030.

Keywords: community perspectives, learning and growth, process excellence, resource management

Procedia PDF Downloads 237

Authors: Uswah Ahmad Khan, Muhammad Moazam Fraz, Humayoon Shafique Satti, Qasim Aziz

Abstract:

Approximately 10-14% of the global population experiences a functional disorder known as irritable bowel syndrome (IBS). The disorder is defined by persistent abdominal pain and an irregular bowel pattern. IBS significantly impairs work productivity and disrupts patients' daily lives and activities. Although IBS is widespread, there is still an incomplete understanding of its underlying pathophysiology. This study aims to help characterize the phenotype of IBS patients by differentiating the comorbidities found in IBS patients from those in non-IBS patients using machine learning algorithms. In this study, we extracted samples coding for IBS from the UK BioBank cohort and randomly selected patients without a code for IBS to create a total sample size of 18,000. We selected the codes for comorbidities of these cases from 2 years before and after their IBS diagnosis and compared them to the comorbidities in the non-IBS cohort. Machine learning models, including Decision Trees, Gradient Boosting, Support Vector Machine (SVM), AdaBoost, Logistic Regression, and XGBoost, were employed to assess their accuracy in predicting IBS. The most accurate model was then chosen to identify the features associated with IBS. In our case, we used XGBoost feature importance as a feature selection method. We applied different models to the top 10% of features, which numbered 50. Gradient Boosting, Logistic Regression and XGBoost algorithms yielded a diagnosis of IBS with an optimal accuracy of 71.08%, 71.427%, and 71.53%, respectively. Among the comorbidities most closely associated with IBS included gut diseases (Haemorrhoids, diverticular diseases), atopic conditions(asthma), and psychiatric comorbidities (depressive episodes or disorder, anxiety). This finding emphasizes the need for a comprehensive approach when evaluating the phenotype of IBS, suggesting the possibility of identifying new subsets of IBS rather than relying solely on the conventional classification based on stool type. Additionally, our study demonstrates the potential of machine learning algorithms in predicting the development of IBS based on comorbidities, which may enhance diagnosis and facilitate better management of modifiable risk factors for IBS. Further research is necessary to confirm our findings and establish cause and effect. Alternative feature selection methods and even larger and more diverse datasets may lead to more accurate classification models. Despite these limitations, our findings highlight the effectiveness of Logistic Regression and XGBoost in predicting IBS diagnosis.

Keywords: comorbidities, disease association, irritable bowel syndrome (IBS), predictive analytics

Procedia PDF Downloads 123

Authors: Praveen S. Muthukumarana, Achala C. Aponso

Abstract:

A large percentage of global crop harvest is lost due to crop diseases. Timely identification and treatment of crop diseases is difficult in many developing nations due to insufficient trained professionals in the field of agriculture. Many crop diseases can be accurately diagnosed by visual symptoms. In the past decade, deep learning has been successfully utilized in domains such as healthcare but adoption in agriculture for plant disease detection is rare. The literature shows that models trained with popular datasets such as PlantVillage does not generalize well on real world images. This paper attempts to find out how to make plant disease identification models that generalize well with real world images.

Keywords: agriculture, convolutional neural network, deep learning, plant disease classification, plant disease detection, plant disease diagnosis

Procedia PDF Downloads 149

Authors: Sara Blanc, José V. Benlloch-Dualde, Laura Grindei, Ana C. Torres, Angélica Monteiro

Abstract:

This paper presents a study that leads a new experience by introducing digital learning applied to a case study focused on primary and secondary school garden-based education. The approach represents an example of interaction among different education and research agents at different countries and levels, such as universities, public and private research, and schools, to get involved in the implementation of education for sustainable development that will make students become more sensible to natural environment, more responsible for their consumption, more aware about waste reduction and recycling, more conscious of the sustainable use of natural resources and, at the same time, more ‘digitally competent’. The experience was designed attending to the European digital education context and OECD directives in transversal skills education. The paper presents the methodology carried out in the study as well as outcomes obtained from experience.

Keywords: school gardens, primary education, secondary education, science technology and innovation in education, digital learning, sustainable development goals, university, knowledge transference

Procedia PDF Downloads 123

Authors: C. N. Vanitha, M. Usha

Abstract:

In a real world scenario, the viability of the sensor networks has been proved by standardizing the technologies. Wireless sensor networks are vulnerable to both electronic and physical security breaches because of their deployment in remote, distributed, and inaccessible locations. The compromised sensor nodes send malicious data to the base station, and thus, the total network effectiveness will possibly be compromised. To detect and seclude the Route modifiers, a neural network based Pattern Learning predictor (PLP) is presented. This algorithm senses data at any node on present and previous patterns obtained from the en-route nodes. The eminence of any node is upgraded by their predicted and reported patterns. This paper propounds a solution not only to detect the route modifiers, but also to seclude the malevolent nodes from the network. The simulation result proves the effective performance of the network by the presented methodology in terms of energy level, routing and various network conditions.

Keywords: neural networks, pattern learning, security, wireless sensor networks

Procedia PDF Downloads 408

Authors: Safaa H. Sindi, Michael Roe

Abstract:

This project divides supply chain (SC) models into seven Eras, according to the evolution of the market’s needs throughout time. The five earliest Eras describe the emergence of supply chains, while the last two Eras are to be created. Research objectives: The aim is to generate the two latest Eras with their respective models that focus on the consumable goods. Era Six contains the Optimal Multidimensional Matrix (OMM) that incorporates most characteristics of the SC and allocates them into four quarters (Agile, Lean, Leagile, and Basic SC). This will help companies, especially (SMEs) plan their optimal SC route. Era Seven creates an Automated Multidimensional Model (AMM) which upgrades the matrix of Era six, as it accounts for all the supply chain factors (i.e. Offshoring, sourcing, risk) into an interactive system with Heuristic Learning that helps larger companies and industries to select the best SC model for their market. Methodologies: The data collection is based on a Fuzzy-Delphi study that analyses statements using Fuzzy Logic. The first round of Delphi study will contain statements (fuzzy rules) about the matrix of Era six. The second round of Delphi contains the feedback given from the first round and so on. Preliminary findings: both models are applicable, Matrix of Era six reduces the complexity of choosing the best SC model for SMEs by helping them identify the best strategy of Basic SC, Lean, Agile and Leagile SC; that’s tailored to their needs. The interactive heuristic learning in the AMM of Era seven will help mitigate error and aid large companies to identify and re-strategize the best SC model and distribution system for their market and commodity, hence increasing efficiency. Potential contributions to the literature: The problematic issue facing many companies is to decide which SC model or strategy to incorporate, due to the many models and definitions developed over the years. This research simplifies this by putting most definition in a template and most models in the Matrix of era six. This research is original as the division of SC into Eras, the Matrix of Era six (OMM) with Fuzzy-Delphi and Heuristic Learning in the AMM of Era seven provides a synergy of tools that were not combined before in the area of SC. Additionally the OMM of Era six is unique as it combines most characteristics of the SC, which is an original concept in itself.

Keywords: Leagile, automation, heuristic learning, supply chain models

Procedia PDF Downloads 396

Authors: Fatima Faraz

Abstract:

BACKGROUND: While Artificial intelligence (AI) provides new opportunities across a wide variety of industries, healthcare is no exception. AI can lead to advancements in how the healthcare system functions and improves the quality of patient care. Developing countries like Pakistan are lagging in the implementation of AI-based solutions in healthcare. This demands increased knowledge and AI literacy among health care professionals. OBJECTIVES: To assess the level of awareness among medical students and faculty about AI in preparation for teaching AI basics and data science applications in clinical practice in an integrated medical curriculum. METHODS: An online 15-question semi-structured questionnaire, previously tested and validated, was delivered among participants through convenience sampling. The questionnaire composed of 3 parts: participant’s background knowledge, AI awareness, and attitudes toward AI applications in medicine. RESULTS: A total of 182 students and 39 faculty members from Rawalpindi Medical University, Pakistan, participated in the study. Only 26% of students and 46.2% of faculty members responded that they were aware of AI topics in clinical medicine. The major source of AI knowledge was social media (35.7%) for students and professional talks and colleagues (43.6%) for faculty members. 23.5% of participants answered that they personally had a basic understanding of AI. Students and faculty (60.1%) were interested in AI in patient care and teaching domain. These findings parallel similar published AI survey results. CONCLUSION: This survey concludes interest among students and faculty in AI developments and technology applications in healthcare. Further studies are required in order to correctly fit AI in the integrated modular curriculum of medical education.

Keywords: medical education, data science, artificial intelligence, curriculum

Procedia PDF Downloads 106

Authors: Paulina Clara Appiah, Kofi Issah, Timothy Letsa, Kennedy Nartey, Amanua Chinbuah, Adoma Dwomo-Fokuo, Jacqeline G. Asibey

Abstract:

Background: The Every Newborn Action Plan provides evidence–based interventions to end preventable deaths in high burden countries. Brong Ahafo Region is one of ten regions in Ghana with less than half of its district hospitals having sick newborn units. Facility-based neonatal care is not prioritized and under-funded, and there is also inadequate knowledge and competence to manage the sick. The aim of this intervention was to make available in–patient care for sick newborns in all 19 district hospitals through the strengthening of facility-based systems. Methods: With the development and dissemination of the National Newborn Strategy and Action Plan 2014-2018, the country was able to attract PATH which provided the region with basic resuscitation equipment, supported hospital providers’ capacity building in Helping Babies Breathe, Essential Care of Every Baby, Infection Prevention and Management and held a symposia on managing the sick newborn. Newborn advocacy was promoted through newborn champions at the facility and community levels. Hospital management was then able to mobilize resources from communities, corporate organizations and from internally generated funds; created or expanded sick newborn care units and provided essential medicines and equipment. Kangaroo Mother Care was initiated in 6 hospitals. Pediatric specialist outreach services initiated comprised telephone consultations, teaching ward rounds and participating in perinatal death audits meetings. Newborn data capture and management was improved through the provision and training on the use of standard registers provided from the national level. Results: From February 2015 to November 2017, hospitals with sick newborn units increased from 7 to 19 (37%-100%). 180 pieces each of newborn ventilation bags and masks size 0, 1 and penguin suction bulbs were distributed to the hospitals, in addition to 20 newborn mannequin sets and 90 small clinical reminder posters. 802 providers (96.9%) were trained in resuscitation, of which 96% were successfully followed up in 6 weeks, 91% in 6 months and 80% in 12 months post-training. 53 clinicians (65%) were trained and mentored to manage sick newborns. 56 specialist teaching ward rounds were conducted. Data completeness improved from 92.6% - 99.9%. Availability of essential medicines improved from 11% to 100%. Number of hospital cots increased from 116 to 248 (214%). Cot occupancy rate increased from 57.4% to 92.5%. Hospitals with phototherapy equipment increased from 0 to 12 (63%). Hospitals with incubators increased from 1 to 12 (5%-63%). Newborn deaths among admissions reduced from 6.3% to 5.4%. Conclusion: Access to in-patient care increased significantly. Newborn advocacy successfully mobilized resources required for strengthening facility –based systems.

Keywords: facility-based systems, Ghana, in-patient care, newborn advocacy

Procedia PDF Downloads 254

Authors: Karina Zaccari, Ernesto Cordeiro Marujo

Abstract:

This paper presents a Machine Learning (ML) approach to support Meningitis diagnosis in patients at a children’s hospital in Sao Paulo, Brazil. The aim is to use ML techniques to reduce the use of invasive procedures, such as cerebrospinal fluid (CSF) collection, as much as possible. In this study, we focus on predicting the probability of Meningitis given the results of a blood and urine laboratory tests, together with the analysis of pain or other complaints from the patient. We tested a number of different ML algorithms, including: Adaptative Boosting (AdaBoost), Decision Tree, Gradient Boosting, K-Nearest Neighbors (KNN), Logistic Regression, Random Forest and Support Vector Machines (SVM). Decision Tree algorithm performed best, with 94.56% and 96.18% accuracy for training and testing data, respectively. These results represent a significant aid to doctors in diagnosing Meningitis as early as possible and in preventing expensive and painful procedures on some children.

Keywords: machine learning, medical diagnosis, meningitis detection, pediatric research

Procedia PDF Downloads 152

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: visual search, deep learning, convolutional neural network, machine learning

Procedia PDF Downloads 219

Authors: Jing Zhao, Yongqing Bai, Qiaofang Shi, Huaihao Zhang

Abstract:

Advances in software technology enable computational chemistry to be commonly applied in various research fields, especially in pedagogy. Thus, in order to expand and improve experimental instructions of computational chemistry for undergraduates, we designed an introductory experiment—research on acrylamide molecular structure and physicochemical properties. Initially, students construct molecular models of acrylamide and polyacrylamide in Gaussian and Materials Studio software respectively. Then, the infrared spectral data, atomic charge and molecular orbitals of acrylamide as well as solvation effect of polyacrylamide are calculated to predict their physicochemical performance. At last, rheological experiments are used to validate these predictions. Through the combination of molecular simulation (performed on Gaussian, Materials Studio) with experimental verification (rheology experiment), learners have deeply comprehended the chemical nature of acrylamide and polyacrylamide, achieving good learning outcomes.

Keywords: upper-division undergraduate, computer-based learning, laboratory instruction, molecular modeling

Procedia PDF Downloads 138