Search

Face Recognition is the domain of technology in Computer Vision that deals with the process of identifying faces of known and unknown per- sons-based on facial patterns. Despite all the recent researches these years on Face Recognition technology, the development of real-time face recognition has always been a challenging task. This kind of technology has its applications widespread like security, medical diagnosis, educational sectors, etc. The advancements in High-end processors and High-Definition cameras led to the design of Face recognition systems that use offline or real-time input datasets. In this paper, our main aim is to focus on real-time video feeds taken from a framed classroom environment to identify the students or the faculty members and tag their names, com- paring them with the already stored face databases. Attendance marking is a daily routine that follows calling the name or passing the attendance books, which is very time-consuming, and they tend to begin proxy at-tendances. This study proposes a attendance marking system using face recognition and Deep Learning techniques on a Raspberry Pi board. The proposed system delivers an approach to make real-time face recognition-based attendance systems by extracting deep facial features using deep residual network (ResNet)-based CNNs. Then that deep facial feature dataset is combined with Machine Learning Algorithm such as SVM to perform face detection and recognize the faces. The maximum recognition accuracy of 80% is obtained using the planned system on the real- time face images provided and will be further improved.

Aiming at the low detection rate of the existing classroom attendance system and the inconvenience of data query, a non-perceptual classroom attendance system based on face recognition is proposed and designed. Using the Android development platform, the image collected by the front-end was first transferred to the server through OkHttp3 technology. Then the information of the class in the database MySQL was retrieved. Then the face image of each student was filtered through the improved Fust face detection algorithm, and the similarity value within the class and similarity value between the class generated VIPLFaceNet face recognition threshold, which recognized the screened face images and obtained the attendance result. Finally, the attendance result was sent to the front end, the administrator could access the server to query attendance data. The experimental results showed that the recall rate of the improved Fust face detection algorithm and the recognition rate of the VIPLFaceNet face recognition algorithm could reach 90.18% and 98.79% respectively.

While research has shown class attendance is important for undergraduate student success, few studies have examined why students choose to not attend class. What is more, existing research has focused on absenteeism among undergraduates at land-grant institutions and professional schools. The purpose of this qualitative study was to examine reasons for absenteeism among students at a small, regional, minority-serving institution. Three focus groups were used to collect data, and thematic data analysis revealed class attendance was impacted by (a) teacher attributes, (b) student attributes, (c) process variables, and (d) context variables. Based on these attributes and variables, recommendations are provided to instructors and administrators on how to improve class attendance at small, regional, minority-serving institutions.

Face Recognition is the domain of technology in Computer Vision that deals with the process of identifying faces of known and unknown persons- based on facial patterns. Despite all the recent researches these years on Face Recognition technology, the development of real-time face recognition has always been a challenging task. This kind of technology has its applications widespread like security, medical diagnosis, educational sectors, etc. The advancements in High-end processors and High-Definition cameras led to the design of Face recognition systems that use offline or real-time input datasets. In this paper, our main aim is to focus on real-time video feeds taken from a framed classroom environment to identify the students or the faculty members and tag their names, com- paring them with the already stored face databases. Attendance marking is a daily routine that follows calling the name or passing the attendance books, which is very time-consuming, and they tend to begin proxy attendances. This study proposes a attendance marking system using face recognition and Deep Learning techniques on a Raspberry Pi board. The proposed system delivers an approach to make real-time face recognition-based attendance systems by extracting deep facial features using deep residual network (ResNet)-based CNNs. Then that deep facial feature dataset is combined with Machine Learning Algorithm such as SVM to perform face detection and recognize the faces. The maximum recognition accuracy of 80% is obtained using the planned system on the real- time face images provided and will be further improved. [ABSTRACT FROM AUTHOR]

Aiming at the low detection rate of the existing classroom attendance system and the in convenience of data query. a non-perceptual classroom attendance system based on face recognition is proposed and designed. Using the Android development platform. the image collected by the front-end was first transferred to the server through OkHups technology. Then the information of the class in the database MySQL. was retrieved. Then the face image of each student was filtered through the improved Fust face detection algorithm and the similarity value within the class and similarity value between the class generated VIPLFaceNet face recognition threshold. which recognized the screened face images and obtained the attendance result. Finally. the attendance result was sent to the front end. the Administrator could access the server to query attend ance data, The experimental results showed that the recall rate of the improved Fust face deteetion algorithm and the recognition rate of the VIPLFaceNet face recognition algorithm could reach 90.18% and 98.79% respectively. [ABSTRACT FROM AUTHOR]

Introduction: Irregularity or delay in the beginning of classes at each semester, due to absence of students and/or professors, is a common problem in most Iranian universities. This study aimed to investigate the reason for irregularities at the beginning of each semester according to the viewpoints of educational experts. Method: This cross-sectional study was carried out at three universities of medical sciences namely; Babol University of Medical Sciences, Shahid Beheshti University of Medical Sciences, and Iran University of Medical Sciences in the first academic semester of 2015-2016. This study investigated the viewpoints of educational experts working in four schools of medicine, dentistry, paramedicine, and public health using a researcher-made instrument. The instrument’s face validity was surveyed and confirmed by six faculty members and its reliability was tested by test-retest method (r=0.82). Descriptive statistics were used for data analysis. Results: According to a forty-two member panel of educational experts’ opinions, the main reasons for academic irregularities at the beginning of each semester is students’ absence followed by weak disciplinary rules, lack of implementation of regulations, teachers’ reluctance to hold classes on time, as well as not completing roll calls and not passing them to the registrar’s office. Conclusion: From the educational experts’ point of view, the factors related to students and teachers have greater effect on the recession of classes at the beginning of each academic semester. Therefore, a better planning for semesters and more control by authorities are required.

Historically, attendance has been a marker of academic performance, but the current medical education literature has had mixed results. In addition, attendance is dropping in the preclinical curricula, whereas, at the same time, the focus on United States Medical Licensing Examination Step 1 performance is increasing. This present study is a mixed-method approach correlating student attendance and access to the formal curriculum in a second-year pathophysiology course to performance on Step 1. Additionally, survey and focus group data evaluated the usage and importance of both the formal curriculum and third-party resources. Out of 112 eligible students, 77 participated in the study. There was no correlation between attendance or access to the learning materials and Step 1 performance. There was a strong correlation between the performance on the final examination and that of Step 1 (r = 0.813; P < 0.001) and a moderate correlation between formative quiz (r = 0.321; P = 0.005) and individual readiness assessment test performance (r = 0.351; P = 0.002) and Step 1 performance. Survey and focus group data show that students place high importance on faculty-developed materials that they can use on their own, but not attendance. The third-party resources are highly used as an adjunct to the formal curriculum and to focus on Step 1 study. Attendance and access to the formal curriculum do not predict Step 1 performance, whereas performance on high- and low-stakes internal assessments do. Further study on how the lack of social interaction gained from attendance affects development of other competencies and the learning climate are warranted. [ABSTRACT FROM AUTHOR]

Studies completed with undergraduate populations have shown that attendance positively correlates with academic performance. A marked decline in classroom attendance within medical school has recently been noticed with the availability of video capture of lectures and other online material. This study compares these in the era of online material. It took place during the second-year Gastrointestinal and Renal Systems module. Attendance was mandatory at team-based learning and case-based learning sessions on new material and voluntary at lectures (29 sessions) and case-based learning on material previously covered (9 sessions). Attendance was recorded prospectively. All lectures were recorded, and all related files were available to students online. Performance was based on a 118 multiple-choice question final examination. Students voluntarily completed the Motivated Strategies for Learning Questionnaire (MSLQ). The study group consisted of 78 students (68% of 114 total) of whom 48 completed the MSLQ. Mean attendance was 24%, with 33% of students attending none of the nonmandatory sessions. The median score on the final exam for participants was 86.0 (range: 28.8). High levels of self-efficacy and the ability to self-regulate effort were predictive of low attendance. Attendance was positively predicted by an orientation toward peer learning and help seeking. There was no correlation between the percentage of classes attended and performance on the final exam. We conclude that different facets of self-regulated learning predict attendance, with highly confident students being the least likely to attend, and that attendance at in-class sessions is no longer a good marker for performance. [ABSTRACT FROM AUTHOR]

Introduction: Irregularity or delay in the beginning of classes at each semester, due to absence of students and/or professors, is a common problem in most Iranian universities. This study aimed to investigate the reason for irregularities at the beginning of each semester according to the viewpoints of educational experts. Method: This cross-sectional study was carried out at three universities of medical sciences namely; Babol University of Medical Sciences, Shahid Beheshti University of Medical Sciences, and Iran University of Medical Sciences in the first academic semester of 2015-2016. This study investigated the viewpoints of educational experts working in four schools of medicine, dentistry, paramedicine, and public health using a researcher-made instrument. The instrument’s face validity was surveyed and confirmed by six faculty members and its reliability was tested by test-retest method (r=0.82). Descriptive statistics were used for data analysis. Results: According to a forty-two member panel of educational experts’ opinions, the main reasons for academic irregularities at the beginning of each semester is students’ absence followed by weak disciplinary rules, lack of implementation of regulations, teachers’ reluctance to hold classes on time, as well as not completing roll calls and not passing them to the registrar’s office. Conclusion: From the educational experts’ point of view, the factors related to students and teachers have greater effect on the recession of classes at the beginning of each academic semester. Therefore, a better planning for semesters and more control by authorities are required. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Central China Normal University is the property of Huazhong Normal University 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 abstract 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 abstract. (Copyright applies to all Abstracts.)