TO TRAVEL, TO EXPLORE AND TO ADVENTURE USING TRAVELMATE
Srushti Dantulwar1, Sanskruti Itankar1 , Kashish Surjuse1, Mrunmayee Awatade1 , Pinky Gangwani2
1Students,Department of Computer Engineering,Cummins College of Engineering for Women Nagpur, India
2Assistant Professor, Department of Computer Engineering, Cummins College Of Engineering For Women, Nagpur, India
ABSTRACT
Welcome to TravelMate, your ultimate companion for seamless travel experiences. At TravelMate, we understand that every journey is a unique adventure, and we are dedicated to enhancing your travel moments with convenience, inspiration, and personalized services. It simplifies the entire travel process. With a user-friendly interface and advanced technology, we empower you to customize your travel plans effortlessly. Whether you are a spontaneous traveler or a meticulous planner, TravelMate adapts to your style, offering real-time suggestions and insights to make informed decisions. Our team of travel experts scours the globe to bring you insider tips, hidden gems, and unique experiences, ensuring that your journey is not only memorable but also enriched with cultural discoveries. At TravelMate, we prioritize your safety and peace of mind. We also provide comprehensive travel insurance options, giving you the confidence to explore the world worry-free join vibrant community of fellow travelers through the TravelMate social platform. Let TravelMate be your compass, guiding you to extraordinary destinations and unforgettable memories. Start your journey with us today and redefine the way you explore the world.
Keywords –Travel Planner, Customized Itineraries, Curated Travel Guides, Real-time Updates, Solo Travel, Social Networking
Optimizing Cloud Security with Fusion Feature Selection Techniques and an Ensemble Classifier for Intrusion Detection
M.Kavitha¹, Dr.A.John Sanjeev Kumar²
¹Assistant Professor, Department of Computer Science, Thiagarajar College, Madurai, India
²Head and Assistant Professor, Department of Data Science, The American College, Madurai, India
ABSTRACT
With growing usage of cloud computing environments in various organizations, both public and private usage models, has led to a significant rise in cyber related threats, posing risks to data confidentiality and integrity. On addressing this concern, a cloud based intrusion detection system (IDS) is proposed in this paper, focusing on enhancement of classification accuracy through improved feature selection and the application of the crow search mechanism (CSA) to weigh the ensemble model. The feature selection process integrates both filter based system and automation supportive prototypes, aiming in deriving an enhanced feature sets. The ensemble classifier comprises diverse machine and deep learning models, including long short term memory (LSTM), and a fast adaptable learning network (FLN). It is utilized on generation of optimal weights for the ensemble model, enhancing prediction results. The performance evaluation Experiments were conducted on datasets and outcomes indicates that the proposed methodology outperformed than conventional approaches in terms of data originality and it’s integrity. Additionally, the identification lev and falsehood alarming rate (FAR) for numerous attack types demonstrated with improved efficacy across datasets.
Keywords – Cloud infrastructure, threat detection, LSTM, deep learning.