HMM-based Scheme for Smart Instructor Activity Recognition in a Lecture Room Environment

2015 ◽  
pp. 578-590 ◽  
Author(s):  
Asim Raza ◽  
Muhammad Haroon Yousaf ◽  
Hassan Ahmed Sial ◽  
Gulistan Raja
Keyword(s):  
Activity Recognition ◽  
Lecture Room

scholarly journals Bag of Deep Features for Instructor Activity Recognition in Lecture Room

2018 ◽  
pp. 481-492
Author(s):  
Nudrat Nida ◽  
Muhammad Haroon Yousaf ◽  
Aun Irtaza ◽  
Sergio A. Velastin
Keyword(s):  
Activity Recognition ◽  
Lecture Room

scholarly journals Instructor Activity Recognition through Deep Spatiotemporal Features and Feedforward Extreme Learning Machines

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Nudrat Nida ◽  
Muhammad Haroon Yousaf ◽  
Aun Irtaza ◽  
Sergio A. Velastin
Keyword(s):  
Activity Recognition ◽  
Teaching Style ◽  
Human Action Recognition ◽  
Human Action ◽  
Connected Components ◽  
Feature Maps ◽  
Feature Representations ◽  
Lecture Room ◽  
Learning Machine ◽  
Motion Profile

Human action recognition has the potential to predict the activities of an instructor within the lecture room. Evaluation of lecture delivery can help teachers analyze shortcomings and plan lectures more effectively. However, manual or peer evaluation is time-consuming, tedious and sometimes it is difficult to remember all the details of the lecture. Therefore, automation of lecture delivery evaluation significantly improves teaching style. In this paper, we propose a feedforward learning model for instructor’s activity recognition in the lecture room. The proposed scheme represents a video sequence in the form of a single frame to capture the motion profile of the instructor by observing the spatiotemporal relation within the video frames. First, we segment the instructor silhouettes from input videos using graph-cut segmentation and generate a motion profile. These motion profiles are centered by obtaining the largest connected components and normalized. Then, these motion profiles are represented in the form of feature maps by a deep convolutional neural network. Then, an extreme learning machine (ELM) classifier is trained over the obtained feature representations to recognize eight different activities of the instructor within the classroom. For the evaluation of the proposed method, we created an instructor activity video (IAVID-1) dataset and compared our method against different state-of-the-art activity recognition methods. Furthermore, two standard datasets, MuHAVI and IXMAS, were also considered for the evaluation of the proposed scheme.

Wireless Telegraph Apparatus for the Lecture Room

1907 ◽  
Vol 64 (1650supp) ◽  
pp. 101-101
Author(s):  
Augustus B. Tripp
Keyword(s):  
Lecture Room ◽  
Wireless Telegraph

Infant Monitoring System using Activity Recognition

2014 ◽  
Vol 134 (3) ◽  
pp. 332-337 ◽  
Author(s):  
Jun Goto ◽  
Takuya Kidokoro ◽  
Tomohiro Ogura ◽  
Satoshi Suzuki
Keyword(s):  
Monitoring System ◽  
Activity Recognition

Activity Recognition using Ultra Wide Band Range-Time Scan

2021 ◽  
Author(s):  
Arijit Chowdhury ◽  
Taniya Das ◽  
Smriti Rani ◽  
Anwesha Khasnobish ◽  
Tapas Chakravarty
Keyword(s):  
Activity Recognition ◽  
Wide Band ◽  
Ultra Wide Band ◽  
Time Scan

Numerical and Experimental Modeling of Indoor Air Quality Inside a Conditioned Space with Mechanical Ventilation and DX-Air Conditioner

2020 ◽  
Vol 38 (9A) ◽  
pp. 1257-1275
Author(s):  
Wisam M. Mareed ◽  
Hasanen M. Hussen
Keyword(s):  
Air Quality ◽  
Indoor Air Quality ◽  
Indoor Air ◽  
Ventilation System ◽  
Thermal Conditions ◽  
Airflow Rate ◽  
Air Conditioner ◽  
Breathing Zone ◽  
Lecture Room ◽  
Ventilation Performance

 Elevated CO2 rates in a building affect the health of the occupant. This paper deals with an experimental and numerical analysis conducted in a full-scale test room located in the Department of Mechanical Engineering at the University of Technology. The experiments and CFD were conducted for analyzing ventilation performance. It is a study on the effect of the discharge airflow rate of the ceiling type air-conditioner on ventilation performance in the lecture room with the mixing ventilation. Most obtained findings show that database and questionnaires analyzed prefer heights between 0.2 m to 1.2 m in the middle of an occupied zone and breathing zone height of between 0.75 m to 1.8 given in the literature surveyed. It is noticed the mismatch of internal conditions with thermal comfort, and indoor air quality recommended by [ASHRAE Standard 62, ANSI / ASHRAE Standard 55-2010]. CFD simulations have been carried to provide insights on the indoor air quality and comfort conditions throughout the classroom. Particle concentrations, thermal conditions, and modified ventilation system solutions are reported.

Deep Learning Trends for Video Based Activity Recognition: A Survey

2018 ◽  
Vol 8 (3) ◽  
pp. 165-171 ◽  
Author(s):  
Chandni ◽  
Alok Kumar Singh Kushwaha ◽  
Jagwinder Kaur Dhillon
Keyword(s):  
Deep Learning ◽  
Activity Recognition
Sign in / Sign up

Export Citation Format

Share Document