Search

Intrusion Detection Systems (IDS) are critical components in a secure network environment, permitting for initial discovery of malicious actions along with attacks. By means of using the data provided by IDS, it is probable to relate proper countermeasures and to alleviate attacks that extremely determine the security of a network. Widespread research was done in the field of IDS design to construct highly scalable IDS without compromising efficiency and security. The purpose of the proposed work is to develop Intelligent IDS using Log Cluster Knowledge Inference Bayes (IIDS-LCKIB) in Complex Event Processing (CEP) Environment. IIDS-LCKIB is used to examine the network traffic data effectivelyIIDS-LCKIB provide the better CEP Environment. Further, it endeavours to decrease the rate of False Positive for the solicitation of network intrusion systems in the real-world and to focus on security along with scalability in Network traffic data. In addition, it tries to test and estimate the performance using New Mathematical IIDS-LCKIB in CEP Environment. The parameters simulation is tested in Java/J2EE software.

In the financial world, stock trading is one of the most crucial activities. Investors make educated guesses to predict stock market trends by analyzing news, studying the company history, industrial history and a lot of other data. successfully predicting the stock market trends and investing in the right shares at the right time can maximize the investor’s profit or at least minimize the losses. Stock market price data is generated in huge volumes and is affected by various diverse factors. This work proposes two models to predict the stock market prices. The first model is an LSTM model that employs a backpropagation optimized LSTM network to forecast future stock prices. The second model is a hybrid model that combines an SVM model, KNN model and a Random Forest classifier using the Majority Voting algorithm to predict stock market trends. Both models have a sentiment analyzer to factor the news influencing the stock market using Natural Language Processing (NLP). The project aims to help investors who are new to the stock market and don’t possess sufficient knowledge to make share investments as well the experienced investors by predicting stock market trends.

This System helps the user for providing the recipes in which they are particularly interested in a mentioned criteria of ingredients on which the user wants to prepare a recipe. The input given by the user like the ingredient on which he/she wants to prepare a recipe can be of text, speech or visual. The process of providing a list of gathered recipes from different trusted and verified sources is performed with the help of Sentiment Analysis(SA), Watson Text-to-Speech and Watson Visual Recognition(WVR). The recipe extraction from different sources which are required for the user is retrieved with the help of a standard Web Crawler. The tools and technologies used for the proposed system are from Artificial Intelligence(AI), Natural Language Processing(NLP). The system proposed assists the user in providing a list of recipes in a prioritized order based on the optimization process performed by the Naïve Bayes Algorithm(NBA) of Sentiment Analysis. In addition, the displayed results of recipes have been reviewed and rated by different users from different sources.