Search results for: virtual case-based learning
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 8150

Search results for: virtual case-based learning

5360 Integrating Natural Language Processing (NLP) and Machine Learning in Lung Cancer Diagnosis

Authors: Mehrnaz Mostafavi

Abstract:

The assessment and categorization of incidental lung nodules present a considerable challenge in healthcare, often necessitating resource-intensive multiple computed tomography (CT) scans for growth confirmation. This research addresses this issue by introducing a distinct computational approach leveraging radiomics and deep-learning methods. However, understanding local services is essential before implementing these advancements. With diverse tracking methods in place, there is a need for efficient and accurate identification approaches, especially in the context of managing lung nodules alongside pre-existing cancer scenarios. This study explores the integration of text-based algorithms in medical data curation, indicating their efficacy in conjunction with machine learning and deep-learning models for identifying lung nodules. Combining medical images with text data has demonstrated superior data retrieval compared to using each modality independently. While deep learning and text analysis show potential in detecting previously missed nodules, challenges persist, such as increased false positives. The presented research introduces a Structured-Query-Language (SQL) algorithm designed for identifying pulmonary nodules in a tertiary cancer center, externally validated at another hospital. Leveraging natural language processing (NLP) and machine learning, the algorithm categorizes lung nodule reports based on sentence features, aiming to facilitate research and assess clinical pathways. The hypothesis posits that the algorithm can accurately identify lung nodule CT scans and predict concerning nodule features using machine-learning classifiers. Through a retrospective observational study spanning a decade, CT scan reports were collected, and an algorithm was developed to extract and classify data. Results underscore the complexity of lung nodule cohorts in cancer centers, emphasizing the importance of careful evaluation before assuming a metastatic origin. The SQL and NLP algorithms demonstrated high accuracy in identifying lung nodule sentences, indicating potential for local service evaluation and research dataset creation. Machine-learning models exhibited strong accuracy in predicting concerning changes in lung nodule scan reports. While limitations include variability in disease group attribution, the potential for correlation rather than causality in clinical findings, and the need for further external validation, the algorithm's accuracy and potential to support clinical decision-making and healthcare automation represent a significant stride in lung nodule management and research.

Keywords: lung cancer diagnosis, structured-query-language (SQL), natural language processing (NLP), machine learning, CT scans

Procedia PDF Downloads 105
5359 Spectrogram Pre-Processing to Improve Isotopic Identification to Discriminate Gamma and Neutrons Sources

Authors: Mustafa Alhamdi

Abstract:

Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.

Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification

Procedia PDF Downloads 152
5358 Land Suitability Prediction Modelling for Agricultural Crops Using Machine Learning Approach: A Case Study of Khuzestan Province, Iran

Authors: Saba Gachpaz, Hamid Reza Heidari

Abstract:

The sharp increase in population growth leads to more pressure on agricultural areas to satisfy the food supply. To achieve this, more resources should be consumed and, besides other environmental concerns, highlight sustainable agricultural development. Land-use management is a crucial factor in obtaining optimum productivity. Machine learning is a widely used technique in the agricultural sector, from yield prediction to customer behavior. This method focuses on learning and provides patterns and correlations from our data set. In this study, nine physical control factors, namely, soil classification, electrical conductivity, normalized difference water index (NDWI), groundwater level, elevation, annual precipitation, pH of water, annual mean temperature, and slope in the alluvial plain in Khuzestan (an agricultural hotspot in Iran) are used to decide the best agricultural land use for both rainfed and irrigated agriculture for ten different crops. For this purpose, each variable was imported into Arc GIS, and a raster layer was obtained. In the next level, by using training samples, all layers were imported into the python environment. A random forest model was applied, and the weight of each variable was specified. In the final step, results were visualized using a digital elevation model, and the importance of all factors for each one of the crops was obtained. Our results show that despite 62% of the study area being allocated to agricultural purposes, only 42.9% of these areas can be defined as a suitable class for cultivation purposes.

Keywords: land suitability, machine learning, random forest, sustainable agriculture

Procedia PDF Downloads 86
5357 Deepnic, A Method to Transform Each Variable into Image for Deep Learning

Authors: Nguyen J. M., Lucas G., Brunner M., Ruan S., Antonioli D.

Abstract:

Deep learning based on convolutional neural networks (CNN) is a very powerful technique for classifying information from an image. We propose a new method, DeepNic, to transform each variable of a tabular dataset into an image where each pixel represents a set of conditions that allow the variable to make an error-free prediction. The contrast of each pixel is proportional to its prediction performance and the color of each pixel corresponds to a sub-family of NICs. NICs are probabilities that depend on the number of inputs to each neuron and the range of coefficients of the inputs. Each variable can therefore be expressed as a function of a matrix of 2 vectors corresponding to an image whose pixels express predictive capabilities. Our objective is to transform each variable of tabular data into images into an image that can be analysed by CNNs, unlike other methods which use all the variables to construct an image. We analyse the NIC information of each variable and express it as a function of the number of neurons and the range of coefficients used. The predictive value and the category of the NIC are expressed by the contrast and the color of the pixel. We have developed a pipeline to implement this technology and have successfully applied it to genomic expressions on an Affymetrix chip.

Keywords: tabular data, deep learning, perfect trees, NICS

Procedia PDF Downloads 91
5356 Community Arts-Based Learning for Interdisciplinary Pedagogy: Measuring Program Effectiveness Using Design Imperatives for 'a New American University'

Authors: Kevin R. Wilson, Roger Mantie

Abstract:

Community arts-based learning and participatory education are pedagogical techniques that serve to be advantageous for students, curriculum development, and local communities. Using an interpretive approach to examine the significance of this arts-informed research in relation to the eight ‘design imperatives’ proposed as the new model for measuring quality in scholarship for Arizona State University as ‘A New American University’, the purpose of this study was to investigate personal, social, and cultural benefits resulting from student engagement in interdisciplinary community-based projects. Students from a graduate level music education class at the ASU Tempe campus (n=7) teamed with students from an undergraduate level community development class at the ASU Downtown Phoenix campus (n=14) to plan, facilitate, and evaluate seven community-based projects in several locations around the Phoenix-metro area. Data was collected using photo evidence, student reports, and evaluative measures designed by the students. The effectiveness of each project was measured in terms of their ability to meet the eight design imperatives to: 1) leverage place; 2) transform society; 3) value entrepreneurship; 4) conduct use-inspired research; 5) enable student success; 6) fuse intellectual disciplines; 7) be socially embedded; and 8) engage globally. Results indicated that this community arts-based project sufficiently captured the essence of each of these eight imperatives. Implications for how the nature of this interdisciplinary initiative allowed for the eight imperatives to manifest are provided, and project success is expounded upon in relation to utility of each imperative. Discussion is also given for how this type of service learning project formatted within the ‘New American University’ model for measuring quality in academia can be a beneficial pedagogical tool in higher education.

Keywords: community arts-based learning, participatory education, pedagogy, service learning

Procedia PDF Downloads 403
5355 The Learning Experience of Two Students with Visual Impairments in the EFL Courses: A Case Study

Authors: May Ling González-Ruiz, Ana Cristina Solís-Solís

Abstract:

Everyday more people can thrive towards the dream of pursuing a university diploma. This can be more attainable for some than for others who may face different types of limitations. Even though not all limitations come from within the individual but most of the times they come from without it may include the environment, the support of the person’s family, the school – its infrastructure, administrative procedures, and attitudes. This is a qualitative type of research that is developed through a case study. It is based on the experiences of two students who are visually impaired and who have attended a public university in Costa Rica. We enquire about the experiences of these two students in the English as a Foreign Language courses at the university scenario. An in-depth analysis of their lived experiences is presented. Their values, attitudes, and expectations serve as the guiding elements for this research. Findings are presented in light of the Social Justice Approach to inclusive education. Some of the most salient aspects found have to do with the attitudes the students used to face challenges; others point at those elements that may have hindered the learning experience of the persons observed and to those that encouraged them to continue their journey and successfully achieve a diploma.

Keywords: inclusion, case study, visually impaired student, learning experience, social justice approach

Procedia PDF Downloads 140
5354 Protocol for Dynamic Load Distributed Low Latency Web-Based Augmented Reality and Virtual Reality

Authors: Rohit T. P., Sahil Athrij, Sasi Gopalan

Abstract:

Currently, the content entertainment industry is dominated by mobile devices. As the trends slowly shift towards Augmented/Virtual Reality applications the computational demands on these devices are increasing exponentially and we are already reaching the limits of hardware optimizations. This paper proposes a software solution to this problem. By leveraging the capabilities of cloud computing we can offload the work from mobile devices to dedicated rendering servers that are way more powerful. But this introduces the problem of latency. This paper introduces a protocol that can achieve high-performance low latency Augmented/Virtual Reality experience. There are two parts to the protocol, 1) In-flight compression The main cause of latency in the system is the time required to transmit the camera frame from client to server. The round trip time is directly proportional to the amount of data transmitted. This can therefore be reduced by compressing the frames before sending. Using some standard compression algorithms like JPEG can result in minor size reduction only. Since the images to be compressed are consecutive camera frames there won't be a lot of changes between two consecutive images. So inter-frame compression is preferred. Inter-frame compression can be implemented efficiently using WebGL but the implementation of WebGL limits the precision of floating point numbers to 16bit in most devices. This can introduce noise to the image due to rounding errors, which will add up eventually. This can be solved using an improved interframe compression algorithm. The algorithm detects changes between frames and reuses unchanged pixels from the previous frame. This eliminates the need for floating point subtraction thereby cutting down on noise. The change detection is also improved drastically by taking the weighted average difference of pixels instead of the absolute difference. The kernel weights for this comparison can be fine-tuned to match the type of image to be compressed. 2) Dynamic Load distribution Conventional cloud computing architectures work by offloading as much work as possible to the servers, but this approach can cause a hit on bandwidth and server costs. The most optimal solution is obtained when the device utilizes 100% of its resources and the rest is done by the server. The protocol balances the load between the server and the client by doing a fraction of the computing on the device depending on the power of the device and network conditions. The protocol will be responsible for dynamically partitioning the tasks. Special flags will be used to communicate the workload fraction between the client and the server and will be updated in a constant interval of time ( or frames ). The whole of the protocol is designed so that it can be client agnostic. Flags are available to the client for resetting the frame, indicating latency, switching mode, etc. The server can react to client-side changes on the fly and adapt accordingly by switching to different pipelines. The server is designed to effectively spread the load and thereby scale horizontally. This is achieved by isolating client connections into different processes.

Keywords: 2D kernelling, augmented reality, cloud computing, dynamic load distribution, immersive experience, mobile computing, motion tracking, protocols, real-time systems, web-based augmented reality application

Procedia PDF Downloads 77
5353 Optimizing the Scanning Time with Radiation Prediction Using a Machine Learning Technique

Authors: Saeed Eskandari, Seyed Rasoul Mehdikhani

Abstract:

Radiation sources have been used in many industries, such as gamma sources in medical imaging. These waves have destructive effects on humans and the environment. It is very important to detect and find the source of these waves because these sources cannot be seen by the eye. A portable robot has been designed and built with the purpose of revealing radiation sources that are able to scan the place from 5 to 20 meters away and shows the location of the sources according to the intensity of the waves on a two-dimensional digital image. The operation of the robot is done by measuring the pixels separately. By increasing the image measurement resolution, we will have a more accurate scan of the environment, and more points will be detected. But this causes a lot of time to be spent on scanning. In this paper, to overcome this challenge, we designed a method that can optimize this time. In this method, a small number of important points of the environment are measured. Hence the remaining pixels are predicted and estimated by regression algorithms in machine learning. The research method is based on comparing the actual values of all pixels. These steps have been repeated with several other radiation sources. The obtained results of the study show that the values estimated by the regression method are very close to the real values.

Keywords: regression, machine learning, scan radiation, robot

Procedia PDF Downloads 82
5352 Attitudes of Secondary School Students towards Biology in Birnin Kebbi Metropolis, Kebbi State, Nigeria

Authors: I. A. Libata

Abstract:

The present study was carried out to determine the attitudes of Secondary School Students towards Biology in Birnin Kebbi metropolis. The population of the study is 2680 SS 2 Secondary School Students in Birnin Kebbi metropolis. Proportionate random sampling was used in selecting the samples. Oppinnionnaire was the only instrument used in the study. The instrument was subjected to test-retest reliability. The reliability index of the instrument was 0.69. Overall scores of the Students were analyzed and a mean score was determined, the mean score of students was 85. There were no significant differences between the attitudes of male and female students. The results also revealed that there was significant difference between the attitude of science and art students. The results also revealed that there was significant difference between the attitude of public and private school students. The study also reveals that majority of students in Birnin Kebbi Metropolis have positive attitudes towards biology. Based on the findings of this study, the researcher recommended that teachers should motivate students, which they can do through their teaching styles and by showing them the relevance of the learning topics to their everyday lives. Government and the school management should create the learning environment that helps motivate students not only to come to classes but also want to learn and enjoy learning Biology.

Keywords: attitudes, students, Birnin-Kebbi, metropolis

Procedia PDF Downloads 403
5351 Early Prediction of Disposable Addresses in Ethereum Blockchain

Authors: Ahmad Saleem

Abstract:

Ethereum is the second largest crypto currency in blockchain ecosystem. Along with standard transactions, it supports smart contracts and NFT’s. Current research trends are focused on analyzing the overall structure of the network its growth and behavior. Ethereum addresses are anonymous and can be created on fly. The nature of Ethereum network and addresses make it hard to predict their behavior. The activity period of an ethereum address is not much analyzed. Using machine learning we can make early prediction about the disposability of the address. In this paper we analyzed the lifetime of the addresses. We also identified and predicted the disposable addresses using machine learning models and compared the results.

Keywords: blockchain, Ethereum, cryptocurrency, prediction

Procedia PDF Downloads 100
5350 Barriers and Opportunities in Apprenticeship Training: How to Complete a Vocational Upper Secondary Qualification with Intermediate Finnish Language Skills

Authors: Inkeri Jaaskelainen

Abstract:

The aim of this study is to shed light on what is it like to study in apprenticeship training using intermediate (or even lower level) Finnish. The aim is to find out and describe these students' experiences and feelings while acquiring a profession in Finnish as it is important to understand how immigrant background adult learners learn and how their needs could be better taken into account. Many students choose apprenticeships and start vocational training while their language skills in Finnish are still very weak. At work, students should be able to simultaneously learn Finnish and do vocational studies in a noisy, demanding, and stressful environment. Learning and understanding new things is very challenging under these circumstances, and sometimes students get exhausted and experience a lot of stress - which makes learning even more difficult. Students are different from each other, and so are their ways to learn. Both duties at work and school assignments require reasonably good general language skills, and, especially at work, language skills are also a safety issue. The empirical target of this study is a group of students with an immigrant background who studied in various fields with intensive L2 support in 2016–2018 and who by now have completed a vocational upper secondary qualification. The interview material for this narrative study was collected from those who completed apprenticeship training in 2019–2020. The data collection methods used are a structured thematic interview, a questionnaire, and observational data. Interviewees with an immigrant background have an inconsistent cultural and educational background - some have completed an academic degree in their country of origin while others have learned to read and write only in Finland. The analysis of the material utilizes thematic analysis, which is used to examine learning and related experiences. Learning a language at work is very different from traditional classroom teaching. With evolving language skills, at an intermediate level at best, rushing and stressing makes it even more difficult to understand and increases the fear of failure. Constant noise, rapidly changing situations, and uncertainty undermine the learning and well-being of apprentices. According to preliminary results, apprenticeship training is well suited to the needs of an adult immigrant student. In apprenticeship training, students need a lot of support for learning and understanding a new communication and working culture. Stress can result in, e.g., fatigue, frustration, and difficulties in remembering and understanding. Apprenticeship training can be seen as a good path to working life. However, L2 support is a very important part of apprenticeship training, and it indeed helps students to believe that one day they will graduate and even get employed in their new country.

Keywords: apprenticeship training, vocational basic degree, Finnish learning, wee-being

Procedia PDF Downloads 134
5349 Promoting Stem Education and a Cosmic Perspective by Using 21st Century Science of Learning

Authors: Rohan Roberts

Abstract:

The purpose of this project was to collaborate with a group of high-functioning, more-able students (aged 15-18) to promote STEM Education and a love for science by bringing a cosmic perspective into the classroom and high school environment. This was done using 21st century science of learning, a focus on the latest research on Neuroeducation, and modern pedagogical methods based on Howard Gardner's theory of Multiple Intelligences, Bill Lucas’ theory of New Smarts, and Sir Ken Robinson’s recommendations on encouraging creativity. The result was an increased sense of passion, excitement, and wonder about science in general, and about the marvels of space and the universe in particular. In addition to numerous unique and innovative science-based initiatives, clubs, workshops, and science trips, this project also saw a marked rise in student-teacher collaboration in science learning and in student engagement with the general public through the press, social media, and community-based initiatives. This paper also outlines the practical impact that bringing a cosmic perspective into the classroom has had on the lives, interests, and future career prospects of the students involved in this endeavour.

Keywords: cosmic perspective, gifted and talented, neuro-education, STEM education

Procedia PDF Downloads 336
5348 Two-Dimensional Analysis and Numerical Simulation of the Navier-Stokes Equations for Principles of Turbulence around Isothermal Bodies Immersed in Incompressible Newtonian Fluids

Authors: Romulo D. C. Santos, Silvio M. A. Gama, Ramiro G. R. Camacho

Abstract:

In this present paper, the thermos-fluid dynamics considering the mixed convection (natural and forced convections) and the principles of turbulence flow around complex geometries have been studied. In these applications, it was necessary to analyze the influence between the flow field and the heated immersed body with constant temperature on its surface. This paper presents a study about the Newtonian incompressible two-dimensional fluid around isothermal geometry using the immersed boundary method (IBM) with the virtual physical model (VPM). The numerical code proposed for all simulations satisfy the calculation of temperature considering Dirichlet boundary conditions. Important dimensionless numbers such as Strouhal number is calculated using the Fast Fourier Transform (FFT), Nusselt number, drag and lift coefficients, velocity and pressure. Streamlines and isothermal lines are presented for each simulation showing the flow dynamics and patterns. The Navier-Stokes and energy equations for mixed convection were discretized using the finite difference method for space and a second order Adams-Bashforth and Runge-Kuta 4th order methods for time considering the fractional step method to couple the calculation of pressure, velocity, and temperature. This work used for simulation of turbulence, the Smagorinsky, and Spalart-Allmaras models. The first model is based on the local equilibrium hypothesis for small scales and hypothesis of Boussinesq, such that the energy is injected into spectrum of the turbulence, being equal to the energy dissipated by the convective effects. The Spalart-Allmaras model, use only one transport equation for turbulent viscosity. The results were compared with numerical data, validating the effect of heat-transfer together with turbulence models. The IBM/VPM is a powerful tool to simulate flow around complex geometries. The results showed a good numerical convergence in relation the references adopted.

Keywords: immersed boundary method, mixed convection, turbulence methods, virtual physical model

Procedia PDF Downloads 118
5347 An Ensemble Deep Learning Architecture for Imbalanced Classification of Thoracic Surgery Patients

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

Selecting appropriate patients for surgery is one of the main issues in thoracic surgery (TS). Both short-term and long-term risks and benefits of surgery must be considered in the patient selection criteria. There are some limitations in the existing datasets of TS patients because of missing values of attributes and imbalanced distribution of survival classes. In this study, a novel ensemble architecture of deep learning networks is proposed based on stacking different linear and non-linear layers to deal with imbalance datasets. The categorical and numerical features are split using different layers with ability to shrink the unnecessary features. Then, after extracting the insight from the raw features, a novel biased-kernel layer is applied to reinforce the gradient of the minority class and cause the network to be trained better comparing the current methods. Finally, the performance and advantages of our proposed model over the existing models are examined for predicting patient survival after thoracic surgery using a real-life clinical data for lung cancer patients.

Keywords: deep learning, ensemble models, imbalanced classification, lung cancer, TS patient selection

Procedia PDF Downloads 146
5346 Superordinated Control for Increasing Feed-in Capacity and Improving Power Quality in Low Voltage Distribution Grids

Authors: Markus Meyer, Bastian Maucher, Rolf Witzmann

Abstract:

The ever increasing amount of distributed generation in low voltage distribution grids (mainly PV and micro-CHP) can lead to reverse load flows from low to medium/high voltage levels at times of high feed-in. Reverse load flow leads to rising voltages that may even exceed the limits specified in the grid codes. Furthermore, the share of electrical loads connected to low voltage distribution grids via switched power supplies continuously increases. In combination with inverter-based feed-in, this results in high harmonic levels reducing overall power quality. Especially high levels of third-order harmonic currents can lead to neutral conductor overload, which is even more critical if lines with reduced neutral conductor section areas are used. This paper illustrates a possible concept for smart grids in order to increase the feed-in capacity, improve power quality and to ensure safe operation of low voltage distribution grids at all times. The key feature of the concept is a hierarchically structured control strategy that is run on a superordinated controller, which is connected to several distributed grid analyzers and inverters via broad band powerline (BPL). The strategy is devised to ensure both quick response time as well as the technically and economically reasonable use of the available inverters in the grid (PV-inverters, batteries, stepless line voltage regulators). These inverters are provided with standard features for voltage control, e.g. voltage dependent reactive power control. In addition they can receive reactive power set points transmitted by the superordinated controller. To further improve power quality, the inverters are capable of active harmonic filtering, as well as voltage balancing, whereas the latter is primarily done by the stepless line voltage regulators. By additionally connecting the superordinated controller to the control center of the grid operator, supervisory control and data acquisition capabilities for the low voltage distribution grid are enabled, which allows easy monitoring and manual input. Such a low voltage distribution grid can also be used as a virtual power plant.

Keywords: distributed generation, distribution grid, power quality, smart grid, virtual power plant, voltage control

Procedia PDF Downloads 268
5345 The Role of Synthetic Data in Aerial Object Detection

Authors: Ava Dodd, Jonathan Adams

Abstract:

The purpose of this study is to explore the characteristics of developing a machine learning application using synthetic data. The study is structured to develop the application for the purpose of deploying the computer vision model. The findings discuss the realities of attempting to develop a computer vision model for practical purpose, and detail the processes, tools, and techniques that were used to meet accuracy requirements. The research reveals that synthetic data represents another variable that can be adjusted to improve the performance of a computer vision model. Further, a suite of tools and tuning recommendations are provided.

Keywords: computer vision, machine learning, synthetic data, YOLOv4

Procedia PDF Downloads 227
5344 The Roles of Organizational Culture, Participative Leadership, Employee Satisfaction and Work Motivation Towards Organizational Capabilities

Authors: Inezia Aurelia, Soebowo Musa

Abstract:

Many firms still fail to develop organizational agility. There are more than 40% of organizations think that they are low/not agile in facing market change. Organizational culture plays an important role in developing the organizations to be adaptive in order to manage the VUCA effectively. This study examines the relationships of organizational culture towards participative leadership, employee satisfaction, employee work motivation, organizational learning, and absorptive capacity in developing organizational agility in managing the VUCA environment. 263 employees located from international chemical-based company offices across the globe who have worked for more than three years were the respondents in this study. This study showed that organizational clan culture promotes the development of participative leadership, which it has an empowering effect on people in the organization resulting in employee satisfaction. The study also confirms the role of organizational culture in creating organizational behavior within the organization that fosters organizational learning, absorptive capacity, and organizational agility, while the study also found that the relationship between participative leadership and employee work motivation is not significant.

Keywords: absorptive capacity, employee satisfaction, employee work motivation, organizational agility, organizational culture, organizational learning, participative leadership

Procedia PDF Downloads 125
5343 Talent-to-Vec: Using Network Graphs to Validate Models with Data Sparsity

Authors: Shaan Khosla, Jon Krohn

Abstract:

In a recruiting context, machine learning models are valuable for recommendations: to predict the best candidates for a vacancy, to match the best vacancies for a candidate, and compile a set of similar candidates for any given candidate. While useful to create these models, validating their accuracy in a recommendation context is difficult due to a sparsity of data. In this report, we use network graph data to generate useful representations for candidates and vacancies. We use candidates and vacancies as network nodes and designate a bi-directional link between them based on the candidate interviewing for the vacancy. After using node2vec, the embeddings are used to construct a validation dataset with a ranked order, which will help validate new recommender systems.

Keywords: AI, machine learning, NLP, recruiting

Procedia PDF Downloads 88
5342 Understanding Relationships between Listening to Music and Pronunciation Learning: An Investigation Based upon Japanese EFL Learners' Self-Evaluation

Authors: Hirokatsu Kawashima

Abstract:

In an attempt to elucidate relationships between listening to music and pronunciation learning, a classroom-based investigation was conducted with Japanese EFL learners (n=45). The subjects were instructed to listen to English songs they liked on YouTube, especially paying attention to phonologically similar vowel and consonant minimal pair words (e.g., live and leave). This kind of activity, which included taking notes, was regularly carried out in the classroom, and the same kind of task was given to the subjects as homework in order to reinforce the in-class activity. The duration of these activities was eight weeks, after which the program was evaluated on a 9-point scale (1: the lowest and 9: the highest) by learners’ self-evaluation. The main questions for this evaluation included 1) how good the learners had been at pronouncing vowel and consonant minimal pair words originally, 2) how often they had listened to songs good for pronouncing vowel and consonant minimal pair words, 3) how frequently they had moved their mouths to vowel and consonant minimal pair words of English songs, and 4) how much they thought the program would support and enhance their pronunciation learning of phonologically similar vowel and consonant minimal pair words. It has been found, for example, A) that the evaluation of this program is by no means low (Mean: 6.51 and SD: 1.23), suggesting that listening to music may support and enhance pronunciation learning, and B) that listening to consonant minimal pair words in English songs and moving the mouth to them are more related to the program’s evaluation (r =.69, p=.00 and r =.55, p=.00, respectively) than listening to vowel minimal pair words in English songs and moving the mouth to them (r =.45, p=.00 and r =.39, p=.01, respectively).

Keywords: minimal pair, music, pronunciation, song

Procedia PDF Downloads 320
5341 Communicative Language Teaching in English as a Foreign Language Classrooms: An Overview of Secondary Schools in Bangladesh

Authors: Saifunnahar

Abstract:

As a former English colony, the relationship of Bangladesh with the English language goes a long way back. English is taught as a compulsory subject in Bangladesh from an early age starting from grade 1 and continuing through the 12th, yet, students are not competent enough to communicate in English proficiently. To improve students’ English language competency, the Bangladesh Ministry of Education introduced communicative language teaching (CLT) methods in English classrooms in the 1990s. It has been decades since this effort was taken, but the students’ level of proficiency is still not satisfactory. The main reason behind this failure is that CLT-based teaching-learning methods have not been effectively implemented. Very little research has been conducted to address the issues English as a foreign language (EFL) classrooms are facing to carry out CLT methodologies in secondary schools (grades 6 to 10) in Bangladesh. Though the secondary level is crucial for students’ language learning and retention, EFL classrooms are marked with various issues that make teaching-learning harder for teachers and students. This study provides an overview of the status of CLT in EFL classrooms and the reasons behind failing to implement CLT in secondary schools in Bangladesh through an analysis of the qualitative data collected from different literature. Based on the findings, effective approaches have been recommended to employ CLT in EFL classrooms.

Keywords: Bangladesh, communicative language teaching, English as a foreign language, secondary schools, pedagogy

Procedia PDF Downloads 156
5340 Indian Premier League (IPL) Score Prediction: Comparative Analysis of Machine Learning Models

Authors: Rohini Hariharan, Yazhini R, Bhamidipati Naga Shrikarti

Abstract:

In the realm of cricket, particularly within the context of the Indian Premier League (IPL), the ability to predict team scores accurately holds significant importance for both cricket enthusiasts and stakeholders alike. This paper presents a comprehensive study on IPL score prediction utilizing various machine learning algorithms, including Support Vector Machines (SVM), XGBoost, Multiple Regression, Linear Regression, K-nearest neighbors (KNN), and Random Forest. Through meticulous data preprocessing, feature engineering, and model selection, we aimed to develop a robust predictive framework capable of forecasting team scores with high precision. Our experimentation involved the analysis of historical IPL match data encompassing diverse match and player statistics. Leveraging this data, we employed state-of-the-art machine learning techniques to train and evaluate the performance of each model. Notably, Multiple Regression emerged as the top-performing algorithm, achieving an impressive accuracy of 77.19% and a precision of 54.05% (within a threshold of +/- 10 runs). This research contributes to the advancement of sports analytics by demonstrating the efficacy of machine learning in predicting IPL team scores. The findings underscore the potential of advanced predictive modeling techniques to provide valuable insights for cricket enthusiasts, team management, and betting agencies. Additionally, this study serves as a benchmark for future research endeavors aimed at enhancing the accuracy and interpretability of IPL score prediction models.

Keywords: indian premier league (IPL), cricket, score prediction, machine learning, support vector machines (SVM), xgboost, multiple regression, linear regression, k-nearest neighbors (KNN), random forest, sports analytics

Procedia PDF Downloads 56
5339 Teachers' Technological Pedagogical and Content Knowledge and Technology Integration in Teaching and Learning in a Small Island Developing State: A Concept Paper

Authors: Aminath Waseela, Vinesh Chandra, Shaun Nykvist,

Abstract:

The success of technology integration initiatives hinges on the knowledge and skills of teachers to effectively integrate technology in classroom teaching. Consequently, gaining an understanding of teachers' technology knowledge and its integration can provide useful insights on strategies that can be adopted to enhance teaching and learning, especially in developing country contexts where research is scant. This paper extends existing knowledge on teachers' use of technology by developing a conceptual framework that recognises how three key types of knowledge; content, pedagogy, technology, and their integration are at the crux of teachers' technology use while at the same time is amenable to empirical studies. Although the aforementioned knowledge is important for effective use of technology that can result in enhanced student engagement, literature on how this knowledge leads to effective technology use and enhanced student engagement is limited. Thus, this theoretical paper proposes a framework to explore teachers' knowledge through the lens of the Technological Pedagogical and Content Knowledge (TPACK); the integration of technology in classroom teaching through the Substitution Augmentation Modification and Redefinition (SAMR) model and how this affects students' learning through the Bloom's Digital Taxonomy (BDT) lens. Studies using this framework could inform the design of professional development to support teachers to develop skills for effective use of available technology that can enhance student learning engagement.

Keywords: information and communication technology, ICT, in-service training, small island developing states, SIDS, student engagement, technology integration, technology professional development training, technological pedagogical and content knowledge, TPACK

Procedia PDF Downloads 149
5338 Towards Security in Virtualization of SDN

Authors: Wanqing You, Kai Qian, Xi He, Ying Qian

Abstract:

In this paper, the potential security issues brought by the virtualization of a Software Defined Networks (SDN) would be analyzed. The virtualization of SDN is achieved by FlowVisor (FV). With FV, a physical network is divided into multiple isolated logical networks while the underlying resources are still shared by different slices (isolated logical networks). However, along with the benefits brought by network virtualization, it also presents some issues regarding security. By examining security issues existing in an OpenFlow network, which uses FlowVisor to slice it into multiple virtual networks, we hope we can get some significant results and also can get further discussions among the security of SDN virtualization.

Keywords: SDN, network, virtualization, security

Procedia PDF Downloads 429
5337 The Diversity of Contexts within Which Adolescents Engage with Digital Media: Contributing to More Challenging Tasks for Parents and a Need for Third Party Mediation

Authors: Ifeanyi Adigwe, Thomas Van der Walt

Abstract:

Digital media has been integrated into the social and entertainment life of young children, and as such, the impact of digital media appears to affect young people of all ages and it is believed that this will continue to shape the world of young children. Since, technological advancement of digital media presents adolescents with diverse contexts, platforms and avenues to engage with digital media outside the home environment and from parents' supervision, a wide range of new challenges has further complicated the already difficult tasks for parents and altered the landscape of parenting. Despite the fact that adolescents now have access to a wide range of digital media technologies both at home and in the learning environment, parenting practices such as active, restrictive, co-use, participatory and technical mediations are important in mitigating of online risks adolescents may encounter as a result of digital media use. However, these mediation practices only focus on the home environment including digital media present in the home and may not necessarily transcend outside the home and other learning environments where adolescents use digital media for school work and other activities. This poses the question of who mediates adolescent's digital media use outside the home environment. The learning environment could be a ''loose platform'' where an adolescent can maximise digital media use considering the fact that there is no restriction in terms of content and time allotted to using digital media during school hours. That is to say that an adolescent can play the ''bad boy'' online in school because there is little or no restriction of digital media use and be exposed to online risks and play the ''good boy'' at home because of ''heavy'' parental mediation. This is the reason why parent mediation practices have been ineffective because a parent may not be able to track adolescents digital media use considering the diversity of contexts, platforms and avenues adolescents use digital media. This study argues that due to the diverse nature of digital media technology, parents may not be able to monitor the 'whereabouts' of their children in the digital space. This is because adolescent digital media usage may not only be confined to the home environment but other learning environments like schools. This calls for urgent attention on the part of teachers to understand the intricacies of how digital media continue to shape the world in which young children are developing and learning. It is, therefore, imperative for parents to liaise with the schools of their children to mediate digital media use during school hours. The implication of parents- teachers mediation practices are discussed. The article concludes by suggesting that third party mediation by teachers in schools and other learning environments should be encouraged and future research needs to consider the emergent strategy of teacher-children mediation approach and the implication for policy for both the home and learning environments.

Keywords: digital media, digital age, parent mediation, third party mediation

Procedia PDF Downloads 160
5336 Neighborhood Graph-Optimized Preserving Discriminant Analysis for Image Feature Extraction

Authors: Xiaoheng Tan, Xianfang Li, Tan Guo, Yuchuan Liu, Zhijun Yang, Hongye Li, Kai Fu, Yufang Wu, Heling Gong

Abstract:

The image data collected in reality often have high dimensions, and it contains noise and redundant information. Therefore, it is necessary to extract the compact feature expression of the original perceived image. In this process, effective use of prior knowledge such as data structure distribution and sample label is the key to enhance image feature discrimination and robustness. Based on the above considerations, this paper proposes a local preserving discriminant feature learning model based on graph optimization. The model has the following characteristics: (1) Locality preserving constraint can effectively excavate and preserve the local structural relationship between data. (2) The flexibility of graph learning can be improved by constructing a new local geometric structure graph using label information and the nearest neighbor threshold. (3) The L₂,₁ norm is used to redefine LDA, and the diagonal matrix is introduced as the scale factor of LDA, and the samples are selected, which improves the robustness of feature learning. The validity and robustness of the proposed algorithm are verified by experiments in two public image datasets.

Keywords: feature extraction, graph optimization local preserving projection, linear discriminant analysis, L₂, ₁ norm

Procedia PDF Downloads 152
5335 Attitudes, Experiences and Good Practices of Writing Online Course Material: A Case Study in Makerere University

Authors: Ruth Nsibirano

Abstract:

Online mode of delivery in higher institutions of learning, popularly known in some circles as e-Learning or distance education is a new phenomenon that is steadily taking root in African universities but specifically at Makerere University. For slightly over a decade, the Department of Open and Distance Learning has been offering the first generation mode of distance education. In this, learning and teaching experiences were based on the use of hard copy materials circulated through postal services in a rather correspondence mode. There were more challenges to this including high dropout rates, limited support to the learners and sustainability issues. Fortunately, the Department was supported by the Norwegian Government through a NORHED grant to “leapfrog” to the fifth generation of distance education that makes more use of educational technologies and tools. The capacity of faculty staff was gradually enhanced through a series of training to handle the upgraded structure of fifth generation distance education. The trained staff was then tasked to develop modules befitting an online delivery mode, for use on the program. This paper will present attitudes, experiences of the course writers with a view of sharing the good practices that enabled them leap from e-faculty trainees to distinct online course writers. This perspective will hopefully serve as building blocks to enhance the capacity of other upcoming distance education programs in low capacity universities and also promote the uptake of e-Education on the continent and beyond. Methodologically the findings were collected through individual interviews with the 30 course writers. In addition, semi structured questionnaires were designed to collect data on the profile, challenges and lessons from the writers. Findings show that the attitudes of course writers on project supported activities are so much tagged to the returns from their committed efforts. In conclusion, therefore, it is strategically useful to assess and selectively choose which individual to nominate for involvement at the initial stages.

Keywords: distance education, online course content, staff attitudes, best practices in online learning

Procedia PDF Downloads 255
5334 Machine Learning Facing Behavioral Noise Problem in an Imbalanced Data Using One Side Behavioral Noise Reduction: Application to a Fraud Detection

Authors: Salma El Hajjami, Jamal Malki, Alain Bouju, Mohammed Berrada

Abstract:

With the expansion of machine learning and data mining in the context of Big Data analytics, the common problem that affects data is class imbalance. It refers to an imbalanced distribution of instances belonging to each class. This problem is present in many real world applications such as fraud detection, network intrusion detection, medical diagnostics, etc. In these cases, data instances labeled negatively are significantly more numerous than the instances labeled positively. When this difference is too large, the learning system may face difficulty when tackling this problem, since it is initially designed to work in relatively balanced class distribution scenarios. Another important problem, which usually accompanies these imbalanced data, is the overlapping instances between the two classes. It is commonly referred to as noise or overlapping data. In this article, we propose an approach called: One Side Behavioral Noise Reduction (OSBNR). This approach presents a way to deal with the problem of class imbalance in the presence of a high noise level. OSBNR is based on two steps. Firstly, a cluster analysis is applied to groups similar instances from the minority class into several behavior clusters. Secondly, we select and eliminate the instances of the majority class, considered as behavioral noise, which overlap with behavior clusters of the minority class. The results of experiments carried out on a representative public dataset confirm that the proposed approach is efficient for the treatment of class imbalances in the presence of noise.

Keywords: machine learning, imbalanced data, data mining, big data

Procedia PDF Downloads 133
5333 A Meta Analysis of the Recent Work-Related Research of BEC-Teachers in the Graduate Programs of the Selected HEIs in Region I and CAR

Authors: Sherelle Lou Sumera Icutan, Sheila P. Cayabyab, Mary Jane Laruan, Paulo V. Cenas, Agustina R. Tactay

Abstract:

This study critically analyzed the recent theses and dissertations of the Basic Education Curriculum (BEC) teachers who finished their graduate programs in selected higher educational institutions in Region I and CAR to be able to come up with a unified result from the varied results of the analyzed research works. All theses and dissertations completed by the educators/teachers/school personnel in the secondary and elementary public and private schools in Region 1 and CAR from AY 2003–2004 to AY 2007–2008 were classified first–as to work or non-work related; second–as to the different aspects of the curriculum: implementation, content, instructional materials, assessment instruments, learning, teaching, and others; third–as to being eligible for meta-analysis or not. Only studies found eligible for meta-analysis were subjected to the procedure. Aside from documentary analysis, the statistical treatments used in meta-analysis include the standardized effect size, Pearson’s correlation (r), the chi-square test of homogeneity and the inverse of the Fisher transformation. This study found out that the BEC-teachers usually probe on work-related researchers with topics that are focused on the learning performances of the students and on factors related to teaching. The development of instructional materials and assessment of implemented programs are also equally explored. However, there are only few researches on content and assessment instrument. Research findings on the areas of learning and teaching are the only aspects that are meta-analyzable. The research findings across studies in Region I and CAR of BEC teachers that focused on similar variables correlated to teaching do not vary significantly. On the contrary, research findings across studies in Region I and CAR that focused on variables correlated to learning performance significantly vary. Within each region, variations on the findings of research works related to learning performance that considered similar variables still exist. The combined finding on the effect size or relationship of the variables that are correlated to learning performance are low which means that effect is small but definite while the combined findings on the relationship of the variables correlated to teaching are slight or almost negligible.

Keywords: meta-analysis, BEC teachers, work-related research,

Procedia PDF Downloads 428
5332 A Survey of Field Programmable Gate Array-Based Convolutional Neural Network Accelerators

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: deep learning, field programmable gate array, FPGA, hardware accelerator, convolutional neural networks, CNN

Procedia PDF Downloads 129
5331 Introduction to Multi-Agent Deep Deterministic Policy Gradient

Authors: Xu Jie

Abstract:

As a key network security method, cryptographic services must fully cope with problems such as the wide variety of cryptographic algorithms, high concurrency requirements, random job crossovers, and instantaneous surges in workloads. Its complexity and dynamics also make it difficult for traditional static security policies to cope with the ever-changing situation. Cyber Threats and Environment. Traditional resource scheduling algorithms are inadequate when facing complex decisionmaking problems in dynamic environments. A network cryptographic resource allocation algorithm based on reinforcement learning is proposed, aiming to optimize task energy consumption, migration cost, and fitness of differentiated services (including user, data, and task security). By modeling the multi-job collaborative cryptographic service scheduling problem as a multiobjective optimized job flow scheduling problem, and using a multi-agent reinforcement learning method, efficient scheduling and optimal configuration of cryptographic service resources are achieved. By introducing reinforcement learning, resource allocation strategies can be adjusted in real time in a dynamic environment, improving resource utilization and achieving load balancing. Experimental results show that this algorithm has significant advantages in path planning length, system delay and network load balancing, and effectively solves the problem of complex resource scheduling in cryptographic services.

Keywords: multi-agent reinforcement learning, non-stationary dynamics, multi-agent systems, cooperative and competitive agents

Procedia PDF Downloads 27