ABSTRACT
In 2022, the COVID-19 pandemic is still occurring. One of the optimal prevention efforts is to wear a mask properly. Several previous studies have classified the use of masks incorrectly. However, the accuracy resulting from the classification process is not optimal. This research aims to use the transfer learning method to achieve optimal accuracy. In this research, we used three classes, namely without a mask, incorrect mask, and with a mask. The use of these three classes is expected to be more detailed in detecting violations of the use of masks on the face. The classification method used in this research uses transfer learning as feature extraction and Global Average Pooling and Dense layers as classification layers. The transfer learning models used in this research are MobileNetV2, InceptionV3, and DenseNet201. We evaluate the three models' accuracy and processing time when using video data. The experimental results show that the DenseNet201 model achieves an accuracy of 93%, but the processing time per video frame is 0.291 s. In contrast to the MobileNetV2 model, which produces an accuracy of 89% and the processing speed of each video frame is 0.106 s. This result is inversely proportional to accuracy and speed. The DenseNet201 model produces high accuracy but slow processing time, while the MobileNetV2 model is less accurate but has faster processing. This research can be applied in the crowd center to monitor health protocols in the use of masks in the hope of inhibiting the transmission of the COVID-19 virus. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
This study revealed the current situation and developments in teacher evaluation in primary and secondary schools by reviewing 54 articles published in the recent decade (i.e., from January 2012 to October 2022). The coding scheme was developed based on the three components of effective teacher evaluation systems: "what”, "how”, and "who”. Specifically, we investigated the frameworks used for teacher evaluation, methods of evaluation, and participants in teacher evaluation. Based on our results, most studies evaluated teachers from the dimension of Instructional Support. Evaluation through video recording became popular due to technological advancement. Further, an increasing number of schools invited external experts to conduct teacher evaluations to ensure fairness. We also identified several crucial factors for teacher development: effective use of teaching resources and technology, high-quality feedback and communication, emotional support, classroom organization, and professional responsibilities. Due to COVID-19, many schools adopted distance learning, prompting the need to develop technological skills for teachers. Through the in-depth analysis of the current situation and development trends in the various dimensions of teacher evaluation in primary and secondary education, future research directions and issues were discussed and explored in this review.
ABSTRACT
A multi-phase investigation was conducted to question potentials within music therapy of a new electrorganic frame drum musical instrument from Japan titled the ‘aFrame'. Two professional music therapists collaborated in this third phase of testing under the work in progress. One of the two music therapists tested the aFrame within numerous sessions with two profoundly disabled clients across generations i.e., an adolescent male and an adult woman. Observations including video recordings as baseline analysis. A goal of the study was to identify strengths and weaknesses of the new instrument in the field of (re)habilitation, especially across spectrums of those with profound dysfunction, special needs situations, and across ages. A goal of the overall work of some four decades, titled SoundScapes, is to achieve an ultimate compendium of tools for human performance to create specific interactive environments to support therapists, caregivers, and for own self-training through engaged and motivated creativity, self-expression, and play. Such environments as created by the first author have been used in his stage performances and installations (e.g., at Museums of Modern Art). The tools are thus considered transdisciplinarity forming a new holistic approach aligned to his six patents. Results from the investigation question the contextual potential of the aFrame due to a typical lack of motoric control aligned to the fragility and expense of the instrument – challenges were evident for those with diminished or lack of physical limb control. To optimize use, add-on footswitches and pedals are recommended with the aFrame instrument. These give added options including remote switching and an audio streaming interface mixer for optimal Online streaming of instrument (and voice) that would have been especially useful during the Coronavirus pandemic so that the music therapists could have continued their interactions with clients remotely (i.e., beyond video conferencing quality). Alternatives to the aFrame are posit and selected from the new generation of instruments and pedals controlling digital media as presented at the end of the text. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.
ABSTRACT
In the Pharmacy master program at Utrecht University students are trained for patient centred pharmaceutical consultations. After the training, students participate in a formative Objective Structured Clinical Exam (OSCE) to experience what an OSCE is like and to gauge their ability. Students receive written feedback and a videorecording of their consultations. Students who perform well on a station get an exemption for that station in the summative OSCE. In the fall of 2020, the organisation of the OSCE was altered because of COVID-19. A survey was held to find out if these changes should be kept in the future. Immediately after the OSCE students were asked to fill a semi-structured survey. The survey contained multiple choice questions with room for elaboration about the organisation, their performance, and their experience of the OSCE. Students were asked to characterize the OSCE with four words. From 26 October – 2 November 2020 82 students participated in the formative OSCE;69 (84%) filled the survey. Students agreed that the OSCE was well organised (77%) and the assessors were friendly and put them at ease (87%). However, 80% of the students felt stressed. To characterize the OSCE students used 95 different words (total 196 words) which related to experiencing stress (22%), being an instructive experience (16%), difficult (12%), a pleasant atmosphere (8%) and general positive remarks (19%). The survey offered in-depth insight in students experience of the OSCE. Assessors experience that OSCEs are stressful and difficult for students. It is encouraging that students also mention positive aspects such as being educational and a pleasant atmosphere. The experience of the students and assessors have led to some changes in the organisation of the OSCE (more time per station, students prepare per station). In the future the survey could be repeated for comparison. [ FROM AUTHOR] Copyright of Patient Education & Counseling is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)
ABSTRACT
The COVID-19 pandemic has significantly changed learning processes. Learning, which had generally been carried out face-to-face, has now turned online. This learning strategy has both advantages and challenges. On the bright side, online learning is unbound by space and time, allowing it to take place anywhere and anytime. On the other side, it faces a common challenge in the lack of direct interaction between educators and students, making it difficult to assess students' engagement during an online learning process. Therefore, it is necessary to conduct research with the aim of automatically detecting students' engagement during online learning. The data used in this research were derived from the DAiSEE dataset (Dataset for Affective States in E-Environments), which comprises ten-second video recordings of students. This dataset classifies engagement levels into four categories: low, very low, high, and very high. However, the issue of imbalanced data found in the DAiSEE dataset has yet to be addressed in previous research. This data imbalance can cause errors in the classification model, resulting in overfitting and underfitting of the model. In this study, Convolutional Neural Network, a deep learning model, was utilized for feature extraction on the DAiSEE dataset. The OpenFace library was used to perform facial landmark detection, head pose estimation, facial expression unit recognition, and eye gaze estimation. The pre-processing stages included data selection, dimensional reduction, and normalization. The PCA and SVD techniques were used for dimensional reduction. The data were later oversampled using the SMOTE algorithm. The training and testing data were distributed at an 80:20 ratio. The results obtained from this experiment exceeded the benchmark evaluation values on the DAiSEE dataset, achieving the best accuracy of 77.97% using the SVD dimensional reduction technique. © 2023,International Journal of Advanced Computer Science and Applications. All Rights Reserved.
ABSTRACT
Advanced video compression is required due to the rise of online video content. A strong compression method can help convey video data effectively over a constrained bandwidth. We observed how more internet usage for video conferences, online gaming, and education led to decreased video quality from Netflix, YouTube, and other streaming services in Europe and other regions, particularly during the COVID-19 epidemic. They are represented in standard video compression algorithms as a succession of reference frames after residual frames, and these approaches are limited in their application. Deep learning's introduction and current advancements have the potential to overcome such problems. This study provides a deep learning-based video compression model that meets or exceeds current H.264 standards. © 2022 IEEE.
ABSTRACT
The adoption of video conferencing and video communication services, accelerated by COVID-19, has driven a rapid increase in video data traffic. The demand for higher resolutions and quality, the need for immersive video formats, and the newest, more complex video codecs increase the energy consumption in data centers and display devices. In this paper, we explore and compare the energy consumption across optimized state-of-the-art video codecs, SVT-AV1, VVenC/VVdeC, VP9, and x.265. Furthermore, we align the energy usage with various objective quality metrics and the compression performance for a set of video sequences across different resolutions. The results indicate that from the tested codecs and configurations, SVTAV1 provides the best tradeoff between energy consumption and quality. The reported results aim to serve as a guide towards sustainable video streaming while not compromising the quality of experience of the end user. © 2022 IEEE.
ABSTRACT
The increase into the Corona virus pandemic led to a higher death rate globally. The best way to prevent getting sick is to keep yourself physically or socially far. Our project provides an approach for physical isolation revealing using machine knowledge toward indicate the necessary space to be maintained to decrease the collision of the corona virus contagious widespread spread. By analyzing a videotape provide for from the camera, the detect apparatus be fashioned in the direction of notify individuals toward maintain a out of harm's way aloofness on or after one an additional. The open-source person recognition pretrained model, YOLO3 algorithm, was utilized to recognize people using the video frame from the camera as input. YOLO3 has the benefit of mortal a lot quicker than further algorithms, at a halt maintain exactness and meets the real-time requirements for person detection. In order to calculate distance from the 2D plane, the video frames are afterwards transformed into top-down views. Estimated distance between individuals and any non-compliant pair of individuals within the display is indicate by means of a red colour edge and stripe, the moderate distance is represented with orange colour and the safe distance is represented by green colour frame. The suggested technique was examined lying on a pre record videotape as well as on the live video feed of persons walking on the road. Additionally an alarm sound is provided to notify the persons. The outcome show that the planned strategy is ready toward sees the societal separation trial among many populaces withinthe videotape. © 2022 IEEE.
ABSTRACT
In response to the decline in motor function (centered on the thorax) caused by chronic muscle tension associated with strengthening exercises for competitive swimmers, we devised a training program that promotes awareness of the functional coordination of the thorax;spine, ribs, and core muscles, and restores natural and efficient body movement. This article presents the results of supporting athlete training during the novel coronavirus pandemic by providing regular coaching remotely using a web-conference system with smartphones, video recording, and a multi-sensor belt equipped with hitoe™ for measuring myoelectricity, respiration, and motion. © 2022 Nippon Telegraph and Telephone Corp.. All rights reserved.
ABSTRACT
Objective: To determine the mode of e-learning preferred by the students regarding pre-recorded lectures (asynchronous) or online zoom lectures (online synchronous learning). Methodology: This cross-sectional study was conducted at CMH Lahore Medical College and Institute of Dentistry from 21st May to 21st June 2020. An online self-administered questionnaire was shared with the students via WhatsApp. The reliability was checked after conducting a pilot study and Cronbach's alpha was 0.711. Data were analyzed using SPSS version 20. Result(s): A total of 282 responses were obtained. Most respondents were female (69.9%), while about 83.7% of responses were from MBBS students. Students who were currently not in the country strongly agreed that time zone differences made online zoom lectures harder to attend. Most students (65.2%) preferred pre-recorded lectures over online zoom lectures. The major factors influencing their choice included pre-recorded lectures being less time-consuming (72.4%) with students being able to re-watch them during the exam preparation (87.6%) and better manage their daily activities (78.8%). Approximately 70.9% of the students wanted instructors to continue uploading recorded lectures after resumption of traditional lectures. Conclusion(s): Students preferred pre-recorded lectures over online zoom lectures. An online curriculum should be developed with predominantly asynchronous learning along with reliable methods of assessment to ensure that the students achieve their academic goals.Copyright © 2023, Pakistan Medical Association. All rights reserved.
ABSTRACT
In the Pharmacy master program at Utrecht University students are trained for patient centred pharmaceutical consultations. After the training, students participate in a formative Objective Structured Clinical Exam (OSCE) to experience what an OSCE is like and to gauge their ability. Students receive written feedback and a videorecording of their consultations. Students who perform well on a station get an exemption for that station in the summative OSCE. In the fall of 2020, the organisation of the OSCE was altered because of COVID-19. A survey was held to find out if these changes should be kept in the future. Immediately after the OSCE students were asked to fill a semi-structured survey. The survey contained multiple choice questions with room for elaboration about the organisation, their performance, and their experience of the OSCE. Students were asked to characterize the OSCE with four words. From 26 October – 2 November 2020 82 students participated in the formative OSCE;69 (84%) filled the survey. Students agreed that the OSCE was well organised (77%) and the assessors were friendly and put them at ease (87%). However, 80% of the students felt stressed. To characterize the OSCE students used 95 different words (total 196 words) which related to experiencing stress (22%), being an instructive experience (16%), difficult (12%), a pleasant atmosphere (8%) and general positive remarks (19%). The survey offered in-depth insight in students experience of the OSCE. Assessors experience that OSCEs are stressful and difficult for students. It is encouraging that students also mention positive aspects such as being educational and a pleasant atmosphere. The experience of the students and assessors have led to some changes in the organisation of the OSCE (more time per station, students prepare per station). In the future the survey could be repeated for comparison. [ FROM AUTHOR] Copyright of Patient Education & Counseling is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)
ABSTRACT
Learning media is an important aspect of learning, especially with the Covid-19 pandemic encouraging the need for students to study online. Based on observations made in several vocational schools in Malang and Balikpapan, books or ppt are media used in learning. There has been no innovation in learning media in the field of sound and image processing technology. To develop interesting learning media and foster student creativity, a mobile learning media was developed using problem-based learning methods in photography and videography for class XI multimedia SMK students to increase student creativity. The R&D model used is Sadiman's version of R&D as follows: 1)need assessment;2)goal setting;3)set of ingredient formulations;4)development of success metrics;5)Create media scripts;6)inspection;7)production ready;Validation was carried out by media experts and material experts, then analyzed using the User Experience Questionnaire (UEQ) method with quantitative and qualitative data types with questionnaire-based data collection methods and feasibility tests on students. The results of the study showed a score of 95.13% for material experts, and 84% for media experts and student creativity as measured by UEQ obtained a score of 76.75%. That is, the percentage has a very good meaning. © 2022 IEEE.
ABSTRACT
CONTEXT Video usage in higher education has increased markedly over many years, but ongoing disruptions caused by the COVID-19 pandemic have accelerated this trend. Consequently, a growing number of educators are grappling with how to best approach video production. Although a range of factors such as video quality, video length, and the presenters' style are known to influence student engagement with videos, more research is needed to understand the extent to which these factors impact, particularly in higher education. This can support educators producing video content that prioritises those aspects which are most critical. PURPOSE This research seeks to understand what factors are most influential on students' decisions to engage versus disengage with video resources in the higher education context. This aims to develop a series of recommendations for educators to focus on when producing videos for inclusion in higher engineering education courses. APPROACH This research considers two mechanical engineering courses taught at different Australian universities. These courses used videos as the primary delivery mode during Semester 2 (July to November) of 2020. Approximately half of each course explicitly applied production recommendations of a highly influential study. Students were surveyed at the end of the semester about their engagement preferences. OUTCOMES The quality of the presenter's explanations and their enthusiasm in delivery were the most important factors influencing engagement, while seeing the presenter was least important. Video length and quality were more likely to cause disengagement when poor, than drive engagement when done well. CONCLUSIONS Characteristics of the presenter's delivery (that is the quality of their explanations and their enthusiasm) are more influential in producing engaging video content than technological choices relating to the video capture and length. Therefore, educators should seek to prioritise the quality of their explanations and their stage presence, before working to improve the video/audio capture quality and reducing video durations. Including the face of the instructor in educational videos has little impact on students' usage decisions. Copyright © J. Khanna and A. Bigham, 2021.
ABSTRACT
CONTEXT In the autumn session of 2020, COVID-19 outbreak forced the transition of teaching and learning from face-to-face mode into remote delivery in Australian universities. Over this unplanned, unprepared, and rapid move to remote delivery for lecturers and online learning for students, many strategies, designs, and technologies were applied to replace conventional classes, tutorials, laboratory classes, project assignments, and assessments. PURPOSE OR GOAL This study investigated the design, use and impact of videos for lectures, tutorials, and laboratory experiments for a combined undergraduate and postgraduate Environmental Engineering course during the COVID-19 pandemic in 2020. The course was delivered through both face-to-face and online delivery modes, which we employed conventional video recordings and H5P interactive videos to support e-learning on the Moodle platform. APPROACH OR METHODOLOGY/METHODS H5P interactive videos, slides and quizzes were also used to design the pre-lab and recorded lab experiments, as our labs were closed due to social distancing requirements. Students' performance was evaluated through their marks of weekly quizzes;and their engagement was analyzed using Moodle activity logs and anonymous surveys through teacher evaluation and polling in Zoom meetings. ACTUAL OR ANTICIPATED OUTCOMES The attendance to online Zoom lecture and tutorials ranged from 70-87%. These data collectively demonstrate a high level of student engagement and satisfaction under the COVID-19 impacted teaching and learning environment compared to rate of lecture attendance at traditional lectures. H5P interactive videos helped students to achieve higher marks, compared to conventional videos. Student has watched the video more than once to obtain enough information to write the lab class report. CONCLUSIONS/RECOMMENDATIONS/SUMMARY It was shown that H5P interactive videos had higher views than conventional videos, which subsequently led to higher marks in weekly quizzes. The tutorials were delivered using Zoom meetings, supplemented with pre-recorded videos which supported students who could not attend the tutorial or for their revisions. The virtual laboratory experiments enabled with H5P provided adequate data and information for students to write their lab reports comparable to the requirements of a real-life lab class. Different approaches of video design and their limitations and improvements are discussed for the future development of e-learning in the post-COVID era. Copyright © Guangming Jiang, Ashley Ansari, Muttucumaru Sivakumar, Timothy McCarthy, 2021.
ABSTRACT
Self-isolation is step or effort to stop the spread of the Covid-19 virus that can carried out by individuals infected with the corona virus. However, they do not show enough symptoms seriously. This is one method to push amount Covid-19 cases. People who do self-isolation must stay at home around 7 days until they are free from Covid-19. To help monitoring by effective condition patient in self-isolation at home and reduce risk the symptoms of Covid-19 experienced, it requires a support system. In this research, it makes a system that can help inhabitant of village to monitor condition patients in the room during self-isolation through camera-based detection object and some sensors to monitor their health such as temperature, heart rate, and oxygen saturation. Camera can classify condition patient based on real-time video recording. If patient is detected lie down or fall on the floor, it will be assumed need help and message emergency sent to the telegram bot. However, if the patient is in a position like stand up, it will be assumed that patient in health condition. By using Mobilenet V2 320x320 SSD object model the average of accuracy is obtained by 86.8%. The results in this system could be monitored through web page. © 2022 IEEE.
ABSTRACT
In recent years, globalization has progressed, and Japan's international students have increased. However, many international students study while working part-time, and due to the impact of Covid-19, face-to-face conversation with people has become difficult. Therefore, regular study time alone has become insufficient for practicing the Japanese language. On the other hand, there are video distribution services that have become popular in recent years. Therefore, we thought we could create a language learning support system by using them. This research aims to develop a language learning support system that uses the subtitle function of a video distribution service to improve learning motivation and to solve the lack of time to learn a foreign language(the Japanese, in this case). This paper mainly reports on the development of the system by using those video content. © 2022 IEEE.
ABSTRACT
During the COVID crisis we had to perform distance learning. We used Microsoft Teams for remote teaching. Our students found as a very useful feature to make video recordings of the lectures, but we had some difficulties to rely on Teams for storing videos and regulating the access to them. We created a specialized platform for management of the video recordings. The present paper presents the Hydra Educational Platform (HEP) - specially developed for teaching purposes in our university. © 2022 IEEE.
ABSTRACT
Public displays are some of the most challenging interfaces to design because of two key characteristics. First, the experience should be engaging, to attract and maintain users' attention. Second, the interaction with the display should be natural, meaning that users should be able to receive the desired output with little or no training. Holographic displays are increasingly popular in public spaces such as museums and concert halls but there is little published research on users' experiences with such displays. Previous research has suggested both tangible and intangible inputs as engaging and natural options for holographic displays, but there is no conclusive evidence on their relative merits. Hence, we run a study to investigate the user experience with a holographic display comparing the level of engagement and feeling of natural experience in the interacting process. We used a mix of surveys, interviews, video recordings, and task-based metrics to measure users' performance on a specific task, the perceived usability, and levels of engagement and satisfaction. Our findings suggest that a tangible input was reported as more natural than the intangible one, however, both tangible and intangible inputs were found to be equally engaging. The latter findings contribute to the efforts of designing intangible public holographic displays and other interactive systems that take into consideration health safety issues, especially during the Covid-19 pandemic era in which contamination can be established with tangible and physical interaction between users and public displays, yet without affecting the level of engagement compared to the tangible experience. © 2022 IEEE.
ABSTRACT
In today's scheme where COVID-19 is the biggest problem faced by the entire world in which it almost forced all schools to suspend and obliged the students to stay at home for their safety., a video recorded lecture is one of the best solutions and ways to help students in their studies. The researchers were intended to improve distance learning as well as its effectiveness to deliver a high-quality video by developing an intelligent system that can be beneficial for both users and viewers. The usage of Arduino Uno served as the brain that controls everything, which makes the system a one-person operation. Given the scenarios of having different values of lux in a room caused by multiple kinds of events, achieving the preferred luminance will be difficult. Nevertheless, our prototype will automatically produce and attain the necessary amount of lighting needed using the LDR sensor along with the code in Arduino. The movement of the platform where the camera is placed follows wherever the user goes in front of the rig as much as the face is recognized. It was then tested using different calibrations by testing and simulating different situations where there are different variables included, such as camera movement and light. The data will be examined using ANOVA test. © 2022 IEEE.
ABSTRACT
The evolution of wearable cameras has revolutionized the exponential growth of the industry due to the production of video content. This has ultimately generated the need for storage management, video management, video summarization, methods to reduce the cost of resources, etc. The present paper compares and evaluates the different techniques available for video summarization nowadays and to visualize the need of applying these methods to the content of online classes delivered during the COVID-19 pandemic. This pandemic has affected the lives of children as they all have got stuck totally onto the screen for their education and learning through their respective organizations. But this trend has raised many challenges among the parents, educational lists, and health experts. These challenges mainly include the availability of online gadgets with internet connectivity, especially in rural areas, and the health issues generated because of the overexposure to online gadgets by students all over the world. As per the educational experts, including UNESCO and UNICEF, this continuous exposure to online gadgets has alarmed the different potential dangers to their health including obesity, stubbornness, heart diseases, vision loss, etc. This paper mainly focuses on the need for summarizing the online class videos not only to reduce the burden of the overhead cost of Internet and resources, but also to reduce the harmful effects produced on the health of these students due to the continuous exposure of the unnatural light and waves generated through these gadgets. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.