-4d90550d17f4602e0893477 20220722021709828 beie:beie director@blueeyesintelligence.org WEB-FORM International Journal of Innovative Technology and Exploring Engineering IJITEE 22783075 10.35940/ijitee https://www.ijitee.org/ 08 30 2022 11 9 Department of Computer Science and Engineering, R V College of Engineering, Bangalore (Karnataka), India. Mahesh Subray Hegde Dr. Ramakanth Kumar P Department of Computer Science and Engineering, R V College of Engineering, Bangalore (Karnataka), India. Server Room is the main part when it comes to any organization since any malicious activity in the server room may bring down the whole server room bringing the work of organization to halt. Hence, we need a server room monitoring system which works on real time images and monitors using compressed circuit television (CCTV). The framework used for server room monitoring is YOLO (You Only look Once). YOLO employs Convolutional neural networks (CNN) for image processing. In CNN image must pass through different layers like Convolutional layer, pooling layer, ReLu layer and fully connected layer. 08 30 2022 18 22 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijitee.org true 10.35940/ijitee.G9211.0811922 https://www.ijitee.org/portfolio-item/G92110811922/ Research Scholar, Motherhood University, Roorkee (Uttarakhand), India. Amit Sharma Dr. V.K. Singh Professor, Motherhood University, Roorkee (Uttarakhand), India. Dr. Pushpendra Singh Raj Kumar Goel Institute of Technology, Ghaziabad (Uttar Pradesh), India. The popularity of deep features based image retrieval and classification task has grown a lot in the recent years. Feature representation based on Convolutional Neural Networks (CNNs) found to be very effective in terms of accuracy by various researchers in the field of visual content based image retrieval. The features which are neutral to their domain knowledge with automatic learning capability from their images are in demand in various image applications. For improving accuracy and expressive power, pre-trained CNN models with the use of transfer learning can be utilized by training them on huge volume of datasets. In this paper, a hybrid model for image retrieval is being proposed by using pre-trained values of hyper parameters as input learning parameters. The performance of the model is being compared with existing pre-trained models showing higher performance on precision and recall parameters 08 30 2022 23 28 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijitee.org true 10.35940/ijitee.G9203.0811922 https://www.ijitee.org/portfolio-item/g92030811922/ Department of Computer Network Engineering at RV College of Engineering (RVCE) Bengaluru (Karnataka), India. Supreetha H V Dr. Sandhya S Assistant Professor, Department of Computer Science and Engineering, RV College of Engineering (RVCE) Bengaluru (Karnataka), India. The growth in Artificial Intelligence (AI), Big-data,and Internet-of-Things (IOT) technologies has increased chabot’s application in many areas. Some of the applications of chatbot can be seen in areas such as social media, e-commerce, healthcare, stock market, education, banking sector etc. Most of the high-end chatbots are deployed inside e-commerce, banking and health websites. There is a need to deploy the chatbots in educational website to improve interactivity of the educational platforms. The main target users of this website is rural students. In rural areas, probability of students dropping school after some age is common because, there won’t be proper monitoring of students and also sometimes facilities will be less. With e- learning, anyone can learn everything with limited cost. The key insight of developing this e-learning website is to provide a chatbot which can motivate rural students towards education. Thus a single platform where users can learn different courses, take quizzes, and chat with the bot is developed. It also provides an additional facility of tracking the scores of the quizzes and giving personalized recommendation systems to improve the scores. The chatbot will also help users to find details aboutfaculties and help users to set an appointment with distant faculties in online mode for doubts clarification. Flask micro- framework is used for developing the website. Firebase is used to store the data. RASA framework is used in developing the chatbot. Finally a content based filtering is used to givepersonalized recommendation systems. 08 30 2022 29 35 CC BY-NC-ND 4.0 10.35940/BEIESP.CrossMarkPolicy www.ijitee.org true 10.35940/ijitee.G9189.0811922 https://www.ijitee.org/portfolio-item/g91890811922/