You are on page 1of 1

Machine Learning

Problem Statements
1) Develop cyber world models for security, data privacy and information sharing for the cyber-
physical devices, manufacturing applications, and the supply chain using Machine Learning,
that will be tested using intrusion detection, penetration testing and cryptography tools.

2) Develop physical world models for data collection and generation based on powerful FPGA
boards using ML that can physically communicate with several real cyber-physical devices at
the same time.

3) The growing prevalence of network attacks is a well-known problem which can impact the
availability, confidentiality, and integrity of critical information for both individuals and
enterprises. In this context, design a real-time intrusion detection approach using a
supervised machine learning technique. The proposed approach will be simple and efficient
and can be used with many machine learning techniques. Further, apply different well-
known machine learning techniques to evaluate the performance of the proposed IDS
approach.

4) The difficulties in obtaining adequate attack data for the supervised classifiers to model the
attack patterns, and the data acquisition task is always time-consuming and greatly relies on
the domain experts. In this context, develop a novel supervised network intrusion detection
method based on TCM-KNN (Transductive Confidence Machines for K-Nearest Neighbors)
machine learning algorithm and active learning based training data selection method. It can
effectively detect anomalies with high detection rate, low false positives under the
circumstance of using much fewer selected data as well as selected features for training in
comparison with the traditional supervised intrusion detection methods.

5) Fake news is a phenomenon which is having a significant impact on our social life, in
particular in the political world. Fake news detection is an emerging research area which is
gaining interest but involved some challenges due to the limited amount of resources (i.e.,
datasets, published literature) available. Design and develop, a fake news detection model
that use n-gram analysis and machine learning techniques. Further, investigate and compare
two different features extraction techniques and six different machine classification
techniques.

6) Sentiment analysis of this user generated data is very useful in knowing the opinion of the
crowd. Twitter sentiment analysis is difficult compared to general sentiment analysis due to
the presence of slang words and misspellings. The maximum limit of characters that are
allowed in Twitter is 140. Knowledge base approach and Machine learning approach are the
two strategies used for analyzing sentiments from the text. In this regard, try to analyze the
twitter posts about electronic products like mobiles, laptops etc using Machine Learning
approach. By doing sentiment analysis in a specific domain, it is possible to identify the
effect of domain information in sentiment classification. Also, present a new feature vector
for classifying the tweets as positive, negative and extract peoples' opinion about products.

You might also like