Search results for: computer assisted learning

Authors: Teja Koduru

Abstract:

Untreated Lyme disease can lead to neurological, cardiac, and dermatological complications. Rapid diagnosis of the erythema migrans (EM) rash, a characteristic symptom of Lyme disease is therefore crucial to early diagnosis and treatment. In this study, we aim to utilize deep learning frameworks including Tensorflow and Keras to create deep convolutional neural networks (DCNN) to detect images of acute Lyme Disease from images of erythema migrans. This study uses a custom database of erythema migrans images of varying quality to train a DCNN capable of classifying images of EM rashes vs. non-EM rashes. Images from publicly available sources were mined to create an initial database. Machine-based removal of duplicate images was then performed, followed by a thorough examination of all images by a clinician. The resulting database was combined with images of confounding rashes and regular skin, resulting in a total of 683 images. This database was then used to create a DCNN with an accuracy of 93% when classifying images of rashes as EM vs. non EM. Finally, this model was converted into a web and mobile application to allow for rapid diagnosis of EM rashes by both patients and clinicians. This tool could be used for patient prescreening prior to treatment and lead to a lower mortality rate from Lyme disease.

Keywords: Lyme, untreated Lyme, erythema migrans rash, EM rash

Procedia PDF Downloads 230

Authors: Shanshan Zhou, Massimo Battaglia

Abstract:

Identity plays a critical role when an organization faces disasters. Individuals reflect on their working identities and identify themselves with the group and the organization, which facilitate collective sensemaking under crisis situations and enable coordinated actions to respond to and recover from disasters. In addition, an organization’s identity links it to its regional community, which fosters the mobilization of resources and contributes to rapid recovery. However, identity is also problematic for disaster prevention because of its persistence. An organization’s ego-defenses system prohibits the rethink of its identity and a rigid identity obstructs disaster prevention. This research aims to tackle the ‘problem’ of identity by study in-depth a case of an Italian multi–utility which experienced the 2012 Northern Italy earthquakes. Collecting data from 11 interviews with top managers and key players in the local community and archived materials, we find that the earthquakes triggered the rethink of the organization’s identity, which got reinforced afterward. This research highlighted the importance of identity in disaster response and recovery. More importantly, it explored the solution of overcoming the barrier of ego-defense that is to transform the organization into a learning organization which constantly rethinks its identity.

Keywords: community identity, disaster, identity, organizational learning

Procedia PDF Downloads 717

Authors: Guanqiao Wang, Hongyang Yu

Abstract:

There is a lot of repetitive work in the traditional construction industry. These repetitive tasks can significantly improve production efficiency by replacing manual tasks with robots. There- fore, robots appear more and more frequently in the construction industry. Navigation and positioning are very important tasks for construction robots, and the requirements for accuracy of positioning are very high. Traditional indoor robots mainly use radiofrequency or vision methods for positioning. Compared with ordinary robots, the indoor plastering robot needs to be positioned closer to the wall for wall plastering, so the requirements for construction positioning accuracy are higher, and the traditional navigation positioning method has a large error, which will cause the robot to move. Without the exact position, the wall cannot be plastered, or the error of plastering the wall is large. A new positioning method is proposed, which is assisted by line lasers and uses image processing-based positioning to perform more accurate positioning on the traditional positioning work. In actual work, filter, edge detection, Hough transform and other operations are performed on the images captured by the camera. Each time the position of the laser line is found, it is compared with the standard value, and the position of the robot is moved or rotated to complete the positioning work. The experimental results show that the actual positioning error is reduced to less than 0.5 mm by this accurate positioning method.

Keywords: indoor plastering robot, navigation, precise positioning, line laser, image processing

Procedia PDF Downloads 141

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125Hz to 8000Hz. The data contains patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R\textsuperscript{2} values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R\textsuperscript{2} values for the best models for KNN ranges from .89 to .95. The best imputation models received R\textsuperscript{2} between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our best imputation models versus constant imputations by a two percent increase.

Keywords: machine learning, audiograms, data imputations, single imputations

Procedia PDF Downloads 76

Authors: Rosdyana Mangir Irawan Kusuma, Wei-Chun Kao, Ho-Thi Trang, Yu-Yen Ou, Kai-Lung Hua

Abstract:

Stock market prediction is still a challenging problem because there are many factors that affect the stock market price such as company news and performance, industry performance, investor sentiment, social media sentiment, and economic factors. This work explores the predictability in the stock market using deep convolutional network and candlestick charts. The outcome is utilized to design a decision support framework that can be used by traders to provide suggested indications of future stock price direction. We perform this work using various types of neural networks like convolutional neural network, residual network and visual geometry group network. From stock market historical data, we converted it to candlestick charts. Finally, these candlestick charts will be feed as input for training a convolutional neural network model. This convolutional neural network model will help us to analyze the patterns inside the candlestick chart and predict the future movements of the stock market. The effectiveness of our method is evaluated in stock market prediction with promising results; 92.2% and 92.1 % accuracy for Taiwan and Indonesian stock market dataset respectively.

Keywords: candlestick chart, deep learning, neural network, stock market prediction

Procedia PDF Downloads 434

Authors: S. Jagadeesh Kumar

Abstract:

Face detection and recognition is an authoritative technology for image database management, video surveillance, and human computer interface (HCI). Face recognition is a rapidly nascent method, which has been extensively discarded in forensics such as felonious identification, tenable entree, and custodial security. This paper recommends an erudite technique using curvature analysis (CA) that has less false positives incidence, operative in different light environments and confiscates the artifacts that are introduced during image acquisition by ring correction in polar coordinate (RCP) method. This technique affronts mean and median filtering technique to remove the artifacts but it works in polar coordinate during image acquisition. Investigational fallouts for face detection and recognition confirms decent recitation even in diagonal orientation and stance variation.

Keywords: curvature analysis, ring correction in polar coordinate method, face detection, face recognition, human computer interaction

Procedia PDF Downloads 277

Authors: Jeewan Rai, Kinzang, Yeshi Jigme Choden

Abstract:

Accumulation of dust on solar panels impacts the overall efficiency and the amount of energy it produces. Detecting and mitigating dust accumulation is, therefore, crucial for optimizing solar energy production. While various techniques exist for detecting dust to schedule cleaning, many of these methods use licensed software like MATLAB, which can be financially burdensome. This study proposes the use of a modified pre-trained ResNet-50 model architecture with an adjusted fully connected layer for binary classification. An experimental setup was installed utilizing a single 75 Wp panel with an inclination maintained at a 30-degree angle. The fine dirt particles were artificially introduced and datasets of images of clean and dusty panels were collected from five different sides were taken, to compensate for the surface reflectance from the PV panel due to camera angles. Those datasets were used to train and test the model, and the accuracy achieved was 90%. The model's ability to detect dust with minimal false positives ensures more efficient maintenance scheduling. This research demonstrates the potential of AI-driven dust detection systems to enhance the operational efficiency of solar PV installations.

Keywords: AI, dust detection, deep learning, image processing, ResNet-50, PV panels

Procedia PDF Downloads 11

Authors: Bhrugesh Radadiya, Jaydeep Shah

Abstract:

In Indian foundry industry, there is a need of defect free casting with minimum production cost in short lead time. Casting defect is a very large issue in foundry shop which increases the rejection rate of casting and wastage of materials. The various parameters influences on casting process such as mold machine related parameters, green sand related parameters, cast metal related parameters, mold related parameters and shake out related parameters. The mold related parameters are most influences on casting defects in sand casting process. This paper review the casting produced by foundry with shrinkage and blow holes as a major defects was analyzed and identified that mold related parameters such as mold temperature, pouring temperature and runner size were not properly set in sand casting process. These parameters were optimized using different optimization techniques such as Taguchi method, Response surface methodology, Genetic algorithm and Teaching-learning based optimization algorithm. Finally, concluded that a Teaching-learning based optimization algorithm give better result than other optimization techniques.

Keywords: casting defects, genetic algorithm, parametric optimization, Taguchi method, TLBO algorithm

Procedia PDF Downloads 722

Authors: Christopher J. Johnston

Abstract:

This paper presents the finding of a research study in which novice (first and second year) elementary teachers (grades Kindergarten – six) evaluated various mathematics Virtual Manipulatives, websites, and Applets (tools) for use in mathematics instruction. Participants identified the criteria they used for evaluating these types of resources and provided recommendations for or against five pre-selected tools. During the study, participants participated in three data collection activities: (1) A brief Likert-scale survey which gathered information about their attitudes toward technology use; (2) An identification of criteria for evaluating technology tools; and (3) A review of five pre-selected technology tools in light of their self-identified criteria. Data were analyzed qualitatively using four theoretical categories (codes): Software Features (41%), Mathematics (26%), Learning (22%), and Motivation (11%). These four theoretical categories were then grouped into two broad categories: Content and Instruction (Mathematics and Learning), and Surface Features (Software Features and Motivation). These combined, broad categories suggest novice teachers place roughly the same weight on pedagogical features as they do technological features. Implications for mathematics teacher educators are discussed, and suggestions for future research are provided.

Keywords: mathematics education, novice teachers, technology, virtual manipulatives

Procedia PDF Downloads 127

Authors: Goh Yung Hong, Mona Masood

Abstract:

This paper explores the effects of gamification on lower secondary school students’ motivation and engagement in the classroom. Two-group posttest-only experimental design were employed to study the influence of gamification teaching method (GTM) when compared with conventional teaching method (CTM) on 60 lower secondary school students. The Student Engagement Instrument (SEI) and Intrinsic Motivation Inventory (IMI) were used to assess students’ intrinsic motivation and engagement level towards the respective teaching method. Finding indicates that students who completed the GTM lesson were significantly higher in intrinsic motivation to learn than those from the CTM. Although the result were insignificant and only marginal difference in the engagement mean, GTM still show better potential in raising student’s engagement in class when compared with CTM. This finding proves that the GTM is likely to solve the current issue of low motivation to learn and low engagement in class among lower secondary school students in Malaysia. On the other hand, despite being not significant, higher mean indicates that CTM positively contribute to higher peer support for learning and better teacher and student relationship when compared with GTM. As a conclusion, gamification approach is flexible and can be adapted into many learning content to enhance the intrinsic motivation to learn and to some extent, encourage better student engagement in class.

Keywords: conventional teaching method, gamification teaching method, motivation, engagement

Procedia PDF Downloads 519

Authors: Salha Mohamed Hussain

Abstract:

As part of the review on the Malay Language curriculum and pedagogy in Singapore conducted in 2010, some recommendations were made to nurture active learners who are able to use the Malay Language efficiently in their daily lives. In response to the review, a new Malay Language teaching and learning package for primary school, called CEKAP (Cungkil – Elicit; Eksplorasi – Exploration; Komunikasi – Communication; Aplikasi – Application; Penilaian – Assessment), was developed from 2012 and implemented for Primary 1 in all primary schools from 2015. Resources developed in this package include the text book, activity book, teacher’s guide, big books, small readers, picture cards, flash cards, a game kit and Information and Communication Technology (ICT) resources. The development of the CEKAP package is continuous until 2020. This paper will look at a model incorporated in the development of the teaching materials in the new Malay Language Curriculum for Primary Schools and the rationale for each phase of development to ensure that the resources meet the needs of every pupil in the teaching and learning of Malay Language in the primary schools. This paper will also focus on the preliminary findings of the effectiveness of the model based on the feedback given by members of the working and steering committees. These members are academicians and educators who were appointed by the Ministry of Education to provide professional input on the soundness of pedagogical approach proposed in the revised syllabus and to make recommendations on the content of the new instructional materials. Quantitative data is derived from the interviews held with these members to gather their input on the model. Preliminary findings showed that the members provided positive feedback on the model and that the comprehensive process has helped to develop good and effective instructional materials for the schools. Some recommendations were also gathered from the interview sessions. This research hopes to provide useful information to those involved in the planning of materials development for teaching and learning.

Keywords: Malay language, materials development, model, primary school

Procedia PDF Downloads 109

Authors: Happy Kumar Das, Md. Shahriar Shafiq

Abstract:

This paper portrays an assumed change in the primary teacher education program in Bangladesh. An initiative has been taken with a vision to ensure an integrated approach to developing trainee teachers’ knowledge and understanding about learning at a deeper level, and with that aim, the Diploma in Primary Education (DPEd) program replaces the Certificate-in-Education (C-in-Ed) program in Bangladeshi context for primary teachers. The stated professional values of the existing program such as ‘learner-centered’, ‘reflective’ approach to pedagogy tend to contradict the practice exemplified through the delivery mechanism. To address the challenges, through the main two components (i) Training Institute-based learning and (ii) School-based learning, the new program tends to cover knowledge and value that underpin the actual practice of teaching. These two components are given approximately equal weighting within the program in terms of both time, content and assessment as the integration seeks to combine theoretical knowledge with practical knowledge and vice versa. The curriculum emphasizes a balance between the taught modules and the components of the practicum. For example, the theories of formative and summative assessment techniques are elaborated through focused reflection on case studies as well as observation and teaching practice in the classroom. The key ideology that is reflected through this newly developed program is teacher’s belief in ‘holistic education’ that can lead to creating opportunities for skills development in all three (Cognitive, Social and Affective) domains simultaneously. The proposed teacher education program aims to address these areas of generic skill development alongside subject-specific learning outcomes. An exploratory study has been designed in this regard where 7 Primary Teachers’ Training Institutes (PTIs) in 7 divisions of Bangladesh was used for experimenting DPEd program. The analysis was done based on document analysis, periodical monitoring report and empirical data gathered from the experimental PTIs. The findings of the study revealed that the intervention brought positive change in teachers’ professional beliefs, attitude and skills along with improvement of school environment. Teachers in training schools work together for collective professional development where they support each other through lesson study, action research, reflective journals, group sharing and so on. Although the DPEd program addresses the above mentioned factors, one of the challenges of the proposed program is the issue of existing capacity and capabilities of the PTIs towards its effective implementation.

Keywords: Bangladesh, effective implementation, primary teacher education, reflective approach

Procedia PDF Downloads 210

Authors: Shivangi Agrawal, Hsiu-I Ting

Abstract:

Entrepreneurship is an essential source of economic growth and a prominent factor influencing socio-economic development. Entrepreneurship education educates and enhances entrepreneurial activity. This study aims to understand current trends in entrepreneurship education and evaluate the effectiveness of diverse entrepreneurship education programs. An increasing number of universities offer entrepreneurship education courses to create and successfully continue entrepreneurial ventures. Despite the prevalence of entrepreneurship education, research studies lack inconsistency about the effectiveness of entrepreneurship education to promote and develop entrepreneurship. Strategies to develop entrepreneurial attitudes and intentions among individuals are hindered by a lack of understanding of entrepreneurs' educational purposes, components, methodology, and resources required. Lack of adequate entrepreneurship education has been linked with low self-efficacy and lack of entrepreneurial intent. Moreover, in the age of digitisation and during the COVID-19 pandemic, digital learning platforms (e.g., online entrepreneurship education courses and programs) and other digital tools (e.g., digital game-based entrepreneurship education) have become more relevant to entrepreneurship education. This paper contributes to the continuation of academic literature in entrepreneurship education by evaluating and assessing current trends in entrepreneurship education programs, leading to better understanding to reduce gaps between entrepreneurial development requirements and higher education institutions.

Keywords: entrepreneurship education, digital technologies, academic entrepreneurship, COVID-19

Procedia PDF Downloads 250

Authors: Jyoti Rani, Ashima Anand, Shivendra Shivani

Abstract:

In recent years, physiological signals obtained in telemedicine have been stored independently from patient information. In addition, people have increasingly turned to mobile devices for information on health-related topics. Major authentication and security issues may arise from this storing, degrading the reliability of diagnostics. This study introduces an approach to reversible watermarking, which ensures security by utilizing the electrocardiogram (ECG) signal as a carrier for embedding patient information. In the proposed work, Pan-Tompkins++ is employed to convert the 1D ECG signal into a 2D signal. The frequency subbands of a signal are extracted using RDWT(Redundant discrete wavelet transform), and then one of the subbands is subjected to MSVD (Multiresolution singular valued decomposition for masking. Finally, the encrypted watermark is embedded within the signal. The experimental results show that the watermarked signal obtained is indistinguishable from the original signals, ensuring the preservation of all diagnostic information. In addition, the DnCNN (Denoising convolutional neural network) concept is used to denoise the retrieved watermark for improved accuracy. The proposed ECG signal-based watermarking method is supported by experimental results and evaluations of its effectiveness. The results of the robustness tests demonstrate that the watermark is susceptible to the most prevalent watermarking attacks.

Keywords: ECG, VMD, watermarking, PanTompkins++, RDWT, DnCNN, MSVD, chaotic encryption, attacks

Procedia PDF Downloads 91

Authors: Yooncheol Lee, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

This paper deals with the establishment of a short-term operational plan for an air conditioner for efficient energy management of exhibition hall. The short-term operational plan is composed of a time series of operational schedules, which we have searched using genetic algorithms. Establishing operational schedule should be considered the future trends of the variables affecting the exhibition hall environment. To reflect continuously changing factors such as external temperature and occupant, short-term operational plans should be updated in real time. But it takes too much time to evaluate a short-term operational plan using EnergyPlus, a building emulation tool. For that reason, it is difficult to update the operational plan in real time. To evaluate the short-term operational plan, we designed prediction models based on machine learning with fast evaluation speed. This model, which was created by learning the past operational data, is accurate and fast. The collection of operational data and the verification of operational plans were made using EnergyPlus. Experimental results show that the proposed method can save energy compared to the reactive control method.

Keywords: exhibition hall, energy management, predictive model, simulation-based optimization

Procedia PDF Downloads 332

Authors: Jerry Szatko, Edan L. Jorgensen, Stacia Jorgensen

Abstract:

A crucial component to the success of any financial advising relationship is for the financial professional to understand the perceptions, preferences and thought-processes carried by the financial clients they serve. Armed with this information, financial professionals are more quickly able to understand how they can tailor their approach to best match the individual preferences and needs of each personal investor. Our research explores the use of a quantitative assessment tool in the financial services industry to assist in the identification of the personal investor’s consumer behaviors, especially in terms of financial risk tolerance, as it relates to their financial decision making. Through this process, the Unitifi Consumer Insight Tool (UCIT) was created and refined to capture and categorize personal investor financial behavioral categories and the financial personality tendencies of individuals prior to the initiation of a financial advisement relationship. This paper discusses the use of this tool to place individuals in one of four behavior-based financial risk tolerance categories. Our discoveries and research were aided through administration of a web-based survey to a group of over 1,000 individuals. Our findings indicate that it is possible to use a quantitative assessment tool to assist in predicting the behavioral tendencies of personal consumers when faced with consumer financial risk and decisions.

Keywords: behavior-based advising, financial relationship building, risk capacity based on behavior, risk tolerance, systematic way to assist in financial relationship building

Procedia PDF Downloads 160

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 14

Authors: Tarik Elaujali

Abstract:

This study examines a new media effective theory was developed by the author, it is called ‘The Effervescent Disk Theory’ (EDT). The theory main goal is to affect the unaffected audience who are either not exposing to a particular message or do not show interest in it. EDT suggest melting down messages that means to be affected within the media materials which are selected willingly by the audience themselves. A certain set of procedures to test EDT hypotheses were taken and illustrated in this study. A sample of 342 respondents (males & females) was collected from Tripoli University in Libya during the academic year 2013-2014. The designated sample is representing students who were failing to pass the English module for beginners’. This study aims to change the students’ negative notion about the importance of learning English, and to put their new idea into action. The theory seeks to affect audience cognition, emotions, and behaviors. EDT was applied in the present study alongside the media dependency theory. EDT hypotheses were confirmed, study results denoted that 73.6 percentage of the students responded positively and passed their English exam for beginners after being exposed selectively to their favorite TV program that contains a dissolved messages about the importance and vitality of learning English language.

Keywords: effervescent disk theory, selective exposure, media dependency, Libyan students

Procedia PDF Downloads 241

Authors: Sangeeta Rai

Abstract:

International education is Australia’s third largest export with significant revenue flowing to the economy in all state and territory jurisdictions. International students make significant economic, social and cultural contributions to all communities in which they are studying and often working. Among these international students are those from Nepal, who continue to seek Australian higher education in increasing numbers. This paper reports on findings from a literature review that highlights the gap in knowledge of the pedagogical issues that may need addressing in teaching Nepalese students in the higher education sector in Australia. Nepalese students bring to their studies a rich culture shaped by their country’s turbulent political and poor economic conditions. These factors may further contribute to their endeavors to seek education abroad to better themselves and their situation. This cohort of students faces various challenges undertaking their studies in Australia that may be due to factors including language, learning styles and engagement with peers. Hence, this paper highlights the importance of these students on Australian shores and forms the basis for further study on the issues and challenges that they face and those that need to be addressed by Australian educators.

Keywords: Nepalese students in Australia, challenges and coping mechanisms of Nepalese students, international students in Australia, socio-cultural background of Nepalese students

Procedia PDF Downloads 204

Authors: Rita Chattopadhyay, Vivek Anand Thoutam

Abstract:

Speech is the most acceptable means of communication where we can quickly exchange our feelings and thoughts. Quite often, people can communicate orally but cannot interact or work with computers or devices. It’s easy and quick to give speech commands than typing commands to computers. In the same way, it’s easy listening to audio played from a device than extract output from computers or devices. Especially with Robotics being an emerging market with applications in warehouses, the hospitality industry, consumer electronics, assistive technology, etc., speech-based human-machine interaction is emerging as a lucrative feature for robot manufacturers. Considering this factor, the objective of this paper is to design the “Audio-Visual Co-Data Processing Pipeline.” This pipeline is an integrated version of Automatic speech recognition, a Natural language model for text understanding, object detection, and text-to-speech modules. There are many Deep Learning models for each type of the modules mentioned above, but OpenVINO Model Zoo models are used because the OpenVINO toolkit covers both computer vision and non-computer vision workloads across Intel hardware and maximizes performance, and accelerates application development. A speech command is given as input that has information about target objects to be detected and start and end times to extract the required interval from the video. Speech is converted to text using the Automatic speech recognition QuartzNet model. The summary is extracted from text using a natural language model Generative Pre-Trained Transformer-3 (GPT-3). Based on the summary, essential frames from the video are extracted, and the You Only Look Once (YOLO) object detection model detects You Only Look Once (YOLO) objects on these extracted frames. Frame numbers that have target objects (specified objects in the speech command) are saved as text. Finally, this text (frame numbers) is converted to speech using text to speech model and will be played from the device. This project is developed for 80 You Only Look Once (YOLO) labels, and the user can extract frames based on only one or two target labels. This pipeline can be extended for more than two target labels easily by making appropriate changes in the object detection module. This project is developed for four different speech command formats by including sample examples in the prompt used by Generative Pre-Trained Transformer-3 (GPT-3) model. Based on user preference, one can come up with a new speech command format by including some examples of the respective format in the prompt used by the Generative Pre-Trained Transformer-3 (GPT-3) model. This pipeline can be used in many projects like human-machine interface, human-robot interaction, and surveillance through speech commands. All object detection projects can be upgraded using this pipeline so that one can give speech commands and output is played from the device.

Keywords: OpenVINO, automatic speech recognition, natural language processing, object detection, text to speech

Procedia PDF Downloads 74

Authors: Kafeero Frank

Abstract:

This study aimed at developing a frame work for open source software adoption in an institution of higher learning in Uganda, with the case of KIU as a study area. There were mainly four research questions based on; individual staff interaction with open source software forum, perceived FOSS characteristics, organizational characteristics and external characteristics as factors that affect open source software adoption. The researcher used causal-correlation research design to study effects of these variables on open source software adoption. A quantitative approach was used in this study with self-administered questionnaire on a purposively and randomly sampled sample of university ICT staff. Resultant data was analyzed using means, correlation coefficients and multivariate multiple regression analysis as statistical tools. The study reveals that individual staff interaction with open source software forum and perceived FOSS characteristics were the primary factors that significantly affect FOSS adoption while organizational and external factors were secondary with no significant effect but significant correlation to open source software adoption. It was concluded that for effective open source software adoption to occur there must be more effort on primary factors with subsequent reinforcement of secondary factors to fulfill the primary factors and adoption of open source software. Lastly recommendations were made in line with conclusions for coming up with Kyambogo University frame work for open source software adoption in institutions of higher learning. Areas of further research recommended include; Stakeholders’ analysis of open source software adoption in Uganda; Challenges and way forward. Evaluation of Kyambogo University frame work for open source software adoption in institutions of higher learning. Framework development for cloud computing adoption in Ugandan universities. Framework for FOSS development in Uganda IT industry

Keywords: open source software., organisational characteristics, external characteristics, cloud computing adoption

Procedia PDF Downloads 63

Authors: Matthew Edmunds, Andrew Hunter, Clare Littlewood, Wisha Gul, Gabriel Heppenstall-Harris, Thomas Humphries

Abstract:

Background: Revision courses for medical students undertaking their final examinations are commonplace throughout the UK. Traditionally these take the form of a series of lectures over multiple weeks or a single day of intensive lectures. The COVID-19 pandemic, however, has required medical educators to create new teaching formats to ensure they adhere to social distancing requirements. It has provided an unexpected opportunity to accelerate the development of students proficiency in the use of ‘technology-enabled communication platforms’, as mandated in the 2018 GMC Outcomes of Graduates. Recent advances in technology have made distance learning possible, whilst also providing novel and more engaging learning opportunities for students. Foundation Year 2 doctors at Aintree University Hospital developed an online series of videos to help prepare medical students in the North West and byond for their final medical school examinations. Method: Eight hour-long videos covering the key topics in medicine and surgery were posted on the Peer Learning Liverpool Youtube channel. These videos were created using new technology such as the screen and audio recording platform, Loom. Each video compromised at least 20 single best answer (SBA) questions, in keeping with the format in most medical school finals. Explanations of the answers were provided, and additional important material was covered. Students were able to ask questions by commenting on the videos, with the authors replying as soon as possible. Feedback was collated using an online Google form. Results: An average of 327 people viewed each video, with 113 students filling in the feedback form. 65.5% of respondents were within one month of their final medical school examinations. The average rating for how well prepared the students felt for their finals was 6.21/10 prior to the course and 8.01/10 after the course. A paired t-test demonstrated a mean increase of 1.80 (95% CI 1.66-1.93). Overall, 98.2% said the online format worked well or very well, and 99.1% would recommend the course to a peer. Conclusions: Based on the feedback received, the online revision course was successful both in terms of preparing students for their final examinations, and with regards to how well the online format worked. Free-text qualitative feedback highlighted advantages such as; students could learn at their own pace, revisit key concepts important to them, and practice exam style questions via the case-based format. Limitations identified included inconsistent audiovisual quality, and requests for a live online Q&A session following the conclusion of the course. This course will be relaunched later in the year with increased opportunities for students to access live feedback. The success of this online course has shown the roll that technology can play in medical education. As well as providing novel teaching modes, online learning allows students to access resources that otherwise would not be available locally, and ensure that they do not miss out on teaching that was previously provided face to face, in the current climate of social distancing.

Keywords: COVID-19 pandemic, Medical School, Online learning, Revision course

Procedia PDF Downloads 145

Authors: Ouafa Amira, Jiangshe Zhang

Abstract:

Clustering is an unsupervised machine learning technique; its aim is to extract the data structures, in which similar data objects are grouped in the same cluster, whereas dissimilar objects are grouped in different clusters. Clustering methods are widely utilized in different fields, such as: image processing, computer vision , and pattern recognition, etc. Fuzzy c-means clustering (fcm) is one of the most well known fuzzy clustering methods. It is based on solving an optimization problem, in which a minimization of a given cost function has been studied. This minimization aims to decrease the dissimilarity inside clusters, where the dissimilarity here is measured by the distances between data objects and cluster centers. The degree of belonging of a data point in a cluster is measured by a membership function which is included in the interval [0, 1]. In fcm clustering, the membership degree is constrained with the condition that the sum of a data object’s memberships in all clusters must be equal to one. This constraint can cause several problems, specially when our data objects are included in a noisy space. Regularization approach took a part in fuzzy c-means clustering technique. This process introduces an additional information in order to solve an ill-posed optimization problem. In this study, we focus on regularization by relative entropy approach, where in our optimization problem we aim to minimize the dissimilarity inside clusters. Finding an appropriate membership degree to each data object is our objective, because an appropriate membership degree leads to an accurate clustering result. Our clustering results in synthetic data sets, gaussian based data sets, and real world data sets show that our proposed model achieves a good accuracy.

Keywords: clustering, fuzzy c-means, regularization, relative entropy

Procedia PDF Downloads 257

Authors: Taekyong Lee, Joon-Young Kim, Jae-Min Cha

Abstract:

Piping and instrumentation diagram (P&ID) is an essential design drawing describing the interconnection of process equipment and the instrumentation installed to control the process. P&IDs are modified and managed throughout a whole life cycle of a process plant. For the ease of data transfer, P&IDs are generally handed over from a design company to an engineering company as portable document format (PDF) which is hard to be modified. Therefore, engineering companies have to deploy a great deal of time and human resources only for manually converting P&ID images into a computer aided design (CAD) file format. To reduce the inefficiency of the P&ID conversion, various symbols and texts in P&ID images should be automatically recognized. However, recognizing information in P&ID images is not an easy task. A P&ID image usually contains hundreds of symbol and text objects. Most objects are pretty small compared to the size of a whole image and are densely packed together. Traditional recognition methods based on geometrical features are not capable enough to recognize every elements of a P&ID image. To overcome these difficulties, state-of-the-art deep learning models, RetinaNet and connectionist text proposal network (CTPN) were used to build a system for recognizing symbols and texts in a P&ID image. Using the RetinaNet and the CTPN model carefully modified and tuned for P&ID image dataset, the developed system recognizes texts, equipment symbols, piping symbols and instrumentation symbols from an input P&ID image and save the recognition results as the pre-defined extensible markup language format. In the test using a commercial P&ID image, the P&ID information recognition system correctly recognized 97% of the symbols and 81.4% of the texts.

Keywords: object recognition system, P&ID, symbol recognition, text recognition

Procedia PDF Downloads 147

Authors: Adekunle Taiwo Adenike, I. K. Ogundoyin

Abstract:

Lassa fever is a neglected tropical virus that has become a significant public health issue in Nigeria, with the country having the greatest burden in Africa. This paper presents a Geo-Computational Model for Analysis and Prediction of Lassa Fever Dynamics and Outbreaks in Nigeria. The model investigates the dynamics of the virus with respect to environmental factors and human populations. It confirms the role of the rodent host in virus transmission and identifies how climate and human population are affected. The proposed methodology is carried out on a Linux operating system using the OSGeoLive virtual machine for geographical computing, which serves as a base for spatial ecology computing. The model design uses Unified Modeling Language (UML), and the performance evaluation uses machine learning algorithms such as random forest, fuzzy logic, and neural networks. The study aims to contribute to the control of Lassa fever, which is achievable through the combined efforts of public health professionals and geocomputational and machine learning tools. The research findings will potentially be more readily accepted and utilized by decision-makers for the attainment of Lassa fever elimination.

Keywords: geo-computational model, lassa fever dynamics, lassa fever, outbreak prediction, nigeria

Procedia PDF Downloads 85

Authors: Yuhang Wang, Jorg Schluter, Sergiy Shelyag

Abstract:

The high cost associated with high-resolution computational fluid dynamics (CFD) is one of the main challenges that inhibit the design, development, and optimisation of new combustion systems adapted for renewable fuels. In this study, we propose a physics-guided CNN-based model to predict turbulence evolution and mixing without requiring a traditional CFD solver. The model architecture is built upon U-Net and the inception module, while a physics-guided loss function is designed by introducing two additional physical constraints to allow for the conservation of both mass and pressure over the entire predicted flow fields. Then, the model is trained on the Large Eddy Simulation (LES) results of a natural turbulent mixing layer with two different Reynolds number cases (Re = 3000 and 30000). As a result, the model prediction shows an excellent agreement with the corresponding CFD solutions in terms of both spatial distributions and temporal evolution of turbulent mixing. Such promising model prediction performance opens up the possibilities of doing accurate high-resolution manifold-based combustion simulations at a low computational cost for accelerating the iterative design process of new combustion systems.

Keywords: computational fluid dynamics, turbulence, machine learning, combustion modelling

Procedia PDF Downloads 85

Authors: Justin Morton, Mohammad Khavari, Abhinav Priyadarshi, Nicole Grobert, Dmitry G. Eskin, Jiawei Mi, Kriakos Porfyrakis, Paul Prentice

Abstract:

Ultrasonic cavitation is used for various processes and applications. Recently, ultrasonic assisted liquid phase exfoliation has been implemented to produce two dimensional nanomaterials. Depending on parameters such as input transducer power and the operational frequency used to induce the cavitation, bubble dynamics can be controlled and optimised. Using ultra-high-speed imagining and acoustic pressure measurements, a dual-frequency systemand its effect on bubble dynamics was investigated. A high frequency transducer (1.174 MHz) showed that bubble fragments and satellite bubbles induced from a low frequency transducer (24 kHz) were able to extend their lifecycle. In addition, this combination of ultrasonic frequencies generated higher acoustic emissions (∼24%) than the sum of the individual transducers. The dual-frequency system also produced an increase in cavitation zone size of∼3 times compared to the low frequency sonotrode. Furthermore, the high frequency induced cavitation bubbleswere shown to rapidly oscillate, although remained stable and did not transiently collapse, even in the presence of a low pressure field. Finally, the spatial distribution of satellite and fragment bubbles from the sonotrode were shown to increase, extending the active cavitation zone. These observations elucidated the benefits of using a dual-frequency system for generating nanomaterials with the aid of ultrasound, in deionised water.

Keywords: dual-frequency, cavitation, bubble dynamics, graphene

Procedia PDF Downloads 189

Authors: Ya Ting Tang

Abstract:

Social learning theory has told us that the cognitions of gender roles come from learning. Thus, the images of gender roles which media describes will shape our cognitions. Taiwan and Japan are both in the East Asian cultural Sphere, and more or less influenced by the traditional Chinese culture. But our social structure and changes must be different. Others, the study also concerns that, with the rise of female consciousness in society, whether the female stereotype in drama of Taiwan and Japan are improved. This research first uses content analysis to analyze drama of Taiwan and Japan in 2003 and 2013 on how to shape female roles. Then use text analysis to conduct a qualitative analysis. Result of this study showed that drama on how to depict women indeed have changed, women are no longer just talk about love, but can serve as president or doctor, and show its mettle in the workplace. In Japanese drama, the female roles have diverse occupation than Taiwanese drama, and not just a background character set. But in most Taiwanese drama, female roles are given a career, but it always put emphasis on women emotionally. To include, although the stereotype in the drama of Taiwan and Japan are improved, female will still be derided due to their ages, love or marriage situations. Taiwanese drama must depict the occupation of female more diverse and let the female roles have more space to play, rather than focusing on romance which women of any occupation can have.

Keywords: female images, stereotype, TV drama, gender roles

Procedia PDF Downloads 269

Authors: Saori Fujimoto, Hiromi Kawasaki, Mari Murakami, Yoko Ueno

Abstract:

Background: Coronavirus disease (COVID-19) has been spreading throughout the world. In Japan, many nursing universities have conducted online clinical practices to secure students’ learning opportunities. In the field of women’s health nursing, even after the pandemic ended, it will be worthwhile to utilize online practice in declining birthrate and reducing the burden of mothers. This study examined the learning effects of conducting online visits for mothers with infants during the COVID-19 pandemic by nursing students to enhance the students’ ability to carry out the online practice even in ordinary times effectively. Methods: Students were divided into groups of three, and information on the mothers was assessed, and the visits were planned. After role-play was conducted by the students and teachers, an online visit was conducted. The analysis target was the self-evaluation score of nine students who conducted online visits in June 2020 and had consented to participate. The evaluation contents included three items for assessment, two items for planning, one item for ethical consideration, five items for nursing practice, and two items for evaluation. The self-evaluation score ranged from 4 (‘Can do with a little advice’) to 1 (‘Can’t do with a little advice’). A univariate statistical analysis was performed. This study was approved by the Ethical Committee for Epidemiology of Hiroshima University. Results: The items with the highest mean (standard deviation) scores were ‘advocates for the dignity and the rights of mothers’ (3.89 (0.31)) and ‘communication behavior needed to create a trusting relationship’ (3.89 (0.31)).’ Next were the ‘individual nursing practice tailored to mothers (3.78 (0.42))’ and ‘review own practice and work on own task (3.78 (0.42)).’ The mean (standard deviation) of the items by type were as follows: three assessment items, 3.26 (0.70), two planning items, 3.11 (0.49), one ethical consideration item, 3.89 (0.31), five nursing practice items, 3.56 (0.54), and two evaluation items, 3.67 (0.47). Conclusion: The highest self-evaluations were for ‘advocates for the dignity and the rights of mothers’ and ‘communication behavior needed to create a trusting relationship.’ These findings suggest that the students were able to form good relationships with the mothers by improving their ability to effectively communicate and by presenting a positive attitude, even when conducting health visits online. However, the self-evaluation scores for assessment and planning were lower than those of ethical consideration, nursing practice, and evaluation. This was most likely due to a lack of opportunities and time to gather information and the need to modify and add plans in a short amount of time during one online visit. It is necessary to further consider the methods used in conducting online visits from the following viewpoints: methods of gathering information and the ability to make changes through multiple visits.

Keywords: infants, learning effects, mothers, online visit practice

Procedia PDF Downloads 133

Authors: Ahokas Mikko, Taskila Sanna, Varrio Kalle, Tanskanen Juha

Abstract:

The present research aimed at the development of an energy efficient process for the concentration of starchy waste waters. The selected principle is mechanical vapor recompression evaporation (MVR) which leads to concentrated solid material and evaporated water phase. Evaporation removes water until a certain viscosity limit is reached. Materials with high viscosity cannot be concentrated using standard evaporators due to limitations of pumps and other constraints, such as wetting. Control of viscosity is thus essential for efficient evaporation. This applies especially to fluids in which due starch or other compounds the viscosity tends to increase via removal of water. In the present research, the effect of enzymes on evaporation of highly viscous starch industry waste waters was investigated. Wastewater samples were received from starch industry at pH of 4.8. Response surface methodology (RSM) was applied for the investigation of factor effects on the behaviour of concentrate during evaporation. The RSM was prepared using quadratic face-centered central composite design (CCF). The evaporation performance was evaluated by monitoring the viscosity of fluid during processing. Based on viscosity curves, the addition of glucoamylase reduced the viscosity during evaporation. This assumption was confirmed by CCF, suggesting that the use of starch decomposing glucoamylase allowed evaporation of the starchy wastewater to a relatively high total solid concentration without a detrimental increase in the viscosity. The results suggest that use of enzymes for reduction of viscosity during the evaporation allows more effective concentration of the wastewater and thereby recovery of potable water.

Keywords: viscous, wastewater, treatment, evaporation, concentration

Procedia PDF Downloads 240