MUMBAI, India, April 20 -- Intellectual Property India has published a patent application (202441078385 A) filed by St. Martin's Engineering College, Secunderabad, Telangana, on Oct. 15, 2024, for 'network traffic analysis for iot device identification and classification using machine learning.'
Inventor(s) include G Sathish; Challaram Raveena; Ganneri Akshaya; Appala Indra Sena Reddy; Tejavath Harshavardhan Naik; Cheerla Manikumar; Butti Sridhar; Kuninti Srinith Reddy; Poruti Namitha Reddy; D Roshan; Bhurla Vikranth; Manchisaraf Nithin Kumar; Peechu Sathvik Reddy; D Tejaswi; Guthy Aishwarya; Musuku Vishnu Vardhan Reddy; Peddolla Uday Kiran; Divya Sandeep Akula; and Palem Venkata Shiva Sai Kumar.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "To know the device and its working status we are using machine learning classification algorithm to classify device based on its data. All devices will send data and store in server and then apply BOG (bag of words which means convert data into matrix where matrix header contains words and matrix rows contains count of those word) to form matrix. Naive Bayes will process matrix to get those words which are high in occurrence or count. In this application we are passing domain names, port numbers to BOG. Naive Bayes will give high occurrence of domain name and port number, and this becomes value of the dataset. By analysing this data using machine learning Random Forest algorithm we can classify/predict device name."
Disclaimer: Curated by HT Syndication.
