19c96fd517d854497e8-181f 20220225020232837 beie:beie director@blueeyesintelligence.org WEB-FORM International Journal of Recent Technology and Engineering (IJRTE) IJRTE 22773878 10.35940/ijrte.2277-3878 https://www.ijrte.org/ 05 30 2021 10 1 Liberal & Arts College, Anyang University, South Korea, Byeongtae Ahn We propose an integrated management system model for the establishment of a smart campus, such as a digital library system and a smart card system capable of providing various services using zigbee, which is currently prominent. The integrated management system can provide a higher quality education environment through transparent and efficient administrative management and one-stop service provision, away from the labor-intensive system of educational institutions, and users can provide personalized and knowledgeable intelligent education services that meet their needs and environments. 05 30 2021 120 123 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.A5876.0510121 https://www.ijrte.org/portfolio-item/A58760510121/ Department of Computing Science and Engineering, Galgotias University, Greater Noida (U.P), India. Akansha Abrol Anisha Sharma Department of Computing Science and Engineering, Galgotias University, Greater Noida (U.P), India. Kritika Karnic Department of Computing Science and Engineering, Galgotias University, Greater Noida (U.P), India. Raju Ranjan Department of Computing Science and Engineering, Galgotias University, Greater Noida (U.P), India. Activity recognition has been an emerging field of research since the past few decades. Humans have the ability to recognize activities from a number of observations in their surroundings. These observations are used in several areas like video surveillance, health sectors, gesture detection, energy conservation, fall detection systems and many more. Sensor based approaches like accelerometer, gyroscope, etc., have been discussed with its advantages and disadvantages. There are different ways of using sensors in a smartly controlled environment. A step-by-step procedure is followed in this paper to build a human activity recognizer. A general architecture of the Resnet model is explained first along with a description of its workflow. Convolutional neural network which is capable of classifying different activities is trained using the kinetic dataset which includes more than 400 classes of activities. The videos last around tenth of a second. The Resnet-34 model is used for image classification of convolutional neural networks and it provides shortcut connections which resolves the problem of vanishing gradient. The model is trained and tested successfully giving a satisfactory result by recognizing over 400 human actions. Finally, some open problems are presented which should be addressed in future research. 05 30 2021 224 228 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.A5896.0510121 https://www.ijrte.org/portfolio-item/A58960510121/ Pursuing, Graduation in Computer Science and Engineering, Kalasalingam Academy of Research and Education, Krishnankoil (Tamil Nadu), India. Mandi Akif Hussain Revoori Veeharika Reddy Pursuing, Graduation in Computer Science and Engineering, Kalasalingam Academy of Research and Education, Krishnankoil (Tamil Nadu), India. Nagella Kedharnath Pursuing, Graduation in Computer Science and Engineering, Kalasalingam Academy of Research and Education, Krishnankoil (Tamil Nadu), India. S. Vidya Associate Professor, Department Computer Science, Kalasalingam Academy of Research and Education, Krishnankoil (Tamil Nadu), India. Software Engineering is a branch of computer science that enables tight communication between system software and training it as per the requirement of the user. We have selected seven distinct algorithms from machine learning techniques and are going to test them using the data sets acquired for NASA public promise repositories. The results of our project enable the users of this software to bag up the defects are selecting the most efficient of given algorithms in doing their further respective tasks, resulting in effective results. 05 30 2021 204 208 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.A5898.0510121 https://www.ijrte.org/portfolio-item/A58980510121/ Business Intelligence Analyst, Schneider Electric, Bangalore (Karnataka), India. Kajal Singh Agile is a software development life cycle (SDLC) methodology that is based on smarter and faster operating principles and techniques. The paper aims to review the agile processes, principles, characteristics, and frameworks for the continuous development of the product while controlling the integration, scope, schedule, cost, quality, resources, risk, procurement, and stakeholder management. Traditional product development methods are not much efficient to adjust the rapid changes of the requirements and provide quality products to the stakeholders. Using agile frameworks, the software development team, customers, and team leaders work more closely to produce high-quality products responding to the changes rapidly. This paper will also present the background analysis of the agile manifesto and will serve as a guide to indicate the characteristics and framework of Agile which places customer satisfaction at the highest priority. Additionally, it will focus on the advantages and disadvantages of the agile projects for faster and frequent delivery of the development. 05 30 2021 209 215 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.A5899.0510121 https://www.ijrte.org/portfolio-item/A58990510121/ Assistant Professor, Department of Electronics and Communication Engineering, Dayananda Sagar College of Engineering, Bengaluru (Karnataka), India, Sandeep S Chapalkar K. Karibasappa Professor, Department of Electronics and Communication Engineering, Dayananda Sagar Academy of Technology and Management, Bengaluru (Karnataka), India, In embedded systems the time required for any process to complete its execution in multitasking environment is an important factor to understand the performance of Real Time System (RTS) and its ability fulfill the deadline requirement of each process under different process load conditions. Even though some non-critical systems provide flexibility over deadlines, the hard real time systems are to be designed to meet the deadline requirement of all processes under peak process load condition. The number of processes available in scheduling queue may vary with time, the dynamic load on processing unit also changes proportionately which in turn affects the relative deadlines of each process. The scheduling policies considered are widely used scheduling policies like Rate Monotonic (RM) and Earliest Deadline First (EDF) to analyze and understand the impact on relative deadline with respect to number of scheduled processes. The real time execution timings of each process is observed on Raspberry Pi 3b+ processing unit operating at standard frequency of 700 MHz in multitasking mode of operation. The results obtained will decisively conclude the suitable scheduling policy for a set of processes under different process load conditions. 05 30 2021 246 251 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijrte.org true 10.35940/ijrte.A5900.0510121 https://www.ijrte.org/portfolio-item/A59000510121/