Paper Title

SELECTION AND APPLICATION OF MACHINE LEARNING- ALGORITHMS FOR ASSESSMENT OF INSTRUMENTATION AND ITS PRODUCTION QUALITY

Abstract

Because of the increase in digitalization Machine Learning (ML)- calculations exposed high opportunities for method streamlining within the creation high-quality area. These days, ML-calculations aren\'t in truth actualized within the technology circumstance. Right now, gift a giant use case wherein ML-calculations are done for looking forward to the nature of items in a manner chain and gift the bodily activities took in we eliminated from the software. In the depicted task, the way within the route of choosing ML-calculations become a bottleneck. There-fore we depict a promising approach how a primary control tool can help selecting ML-calculations issue explicitly
KEYWORDS :

Paper Title

A MACHINE LEARNING BASED FRAMEWORK FOR LEVERAGING ANDROID MALWARE DETECTION

Abstract

Spreading malware through Android devices and applications became an important strategy of cyber attackers. Therefore, malware detection in Android applications has become an important area of research. In this context, it is important to answer the question that reads “how can we develop a model based on Machine Learning (ML) to detect malware in Android devices/applications?” When malware is detected in real time from Android mobile applications, it can relive the users of Android phones from the risk of malware. It will also help stakeholders of Android devices to be safe from malicious software. The proposed system extracts feature from. APK files and training is given for supervised learning. Different ML models like Multinomial Naïve Bayes, Random Forest and SVM are used as prediction models. With these ML techniques a framework is realized to have provision for protection of malware in Android devices or applications. The proposed solution continues giving support with increased quality. The rationale behind this is that as the applications are protected and malware is detected, the training data gets increased. With increased training data, it will become much more accurate as time goes on. With some changes, it can be made to detect Android applications live when it is associated with a competing device.
KEYWORDS : Malware detection, feature extraction, machine learning, SVM, Random Forest, Multinomial Naïve Bayes

Paper Title

A HYBRID APPROACH FOR INTRUSION DETECTION SYSTEM USING K-MEANS AND RANDOM FOREST

Abstract

Intrusion detection systems play important role in real world applications. Every organization or government that uses any sort of networking and information systems need protection from various kinds of intrusions. Many existing intrusion detection systems provide very highly verbose output and it is not easier for administrators to identify the issues immediately. With the Artificial Intelligence (AI) techniques with underlying Machine Learning (ML) algorithms, there is scope of developing IDS based on AI. In this project, a hybrid IDS is developed using machine learning approaches. It combines Random Forest classification and K-Means clustering. This will use both misuse detection and anomaly detection for improving performance of the IDS. These algorithms are evaluated for the four categories of attacks based on precision, recall, F1-score, false-alarm-rate, and detection-rate. The proposed IDS is evaluated with NSL-KDD dataset which is highly optimized for intrusion detection research. The results of experiments showed that the hybrid IDS performs well in terms of detection rate and other metrics.
KEYWORDS : Intrusion Detection System (IDS), Random Forest (RF), K-Means clustering, machine learning

Paper Title

ANALYSIS OF GAS TURBINE BLADES THROUGH MODELLING

Abstract

Turbine blade is the individual component which makes up the turbine part of a gas turbine. The turbine is a mechanical power generating rotary device which uses power of flowing fluid and converts it into useful work. The aim of the project is to design a turbine blade using 3D modeling software CATIA by using the CMM point data available. CMM data taken from coordinate measuring machine. This project involve structural analysis by applying the angular velocities for various materials in evaluating stresses developed and mode shapes of the blade. CATIA is the standard tool in 3D product design, featuring industry leading productivity tool that promote best practices in design. Structural analysis performed on the blade using commercial software ANSYS.
KEYWORDS : Turbine Blade; Structural Analysis, CATIA.