Volume 10, Issue 6, June 2018

 

 

OpenFlow Switches with Integrated Tiny NIDS to Mitigate Network Attacks
 

OpenFlow Switches with Integrated Tiny NIDS to Mitigate Network Attacks

Pages: 85-91 (7) | [Full Text] PDF (507 KB)
B Tran-Thanh, C Pham-Quoc, TN Thinh
Faculty of Computer Science and Engineering, Ho Chi Minh city University of Technology, Vietnam

Abstract -
In the IoT era, billions of devices connect to the Internet and generate a vast amount of data across the network. However, the traditional networks cannot handle those volumes of data as well as connections because of its limitations. To deal with that issue, Software Defined Networking (SDN) has been introduced as an emerging solution. Similar traditional networks, SDN suffers from challenges. In this paper, we propose an approach to mitigate the network attacking by integrating tiny Snort-based Network Intrusion Detection Systems (NIDS) into OpenFlow switches, instances of SDN. Our proposed architecture is able route packet according to Open Network Protocols (ONP) to detect instruction to protect the network from attacking. To prove the feasibility of the proposed approach, we use Verilog Hardware description language (HDL) to implement the system on a NetFPGA 10G board. In addition, we design two testing scenarios for the throughput and accuracy experiments. The experimental results show that our system runs at up to 105.854 MHz, handles the traffic rate up to 9.809 Gigabit per second (Gbps), and detects up to 62% of network threats.
 
Index Terms - Network Intrusion Detection Systems, Software-Defined Networking, OpenFlow Protocol, Snort, FPGA

Citation - B Tran-Thanh, C Pham-Quoc, TN Thinh. "OpenFlow Switches with Integrated Tiny NIDS to Mitigate Network Attacks." International Journal of Computer Engineering and Information Technology 10, no. 6 (2018): 85-91.

SSL-QA: Analysis of Semi-Supervised Learning for Question-Answering
 

SSL-QA: Analysis of Semi-Supervised Learning for Question-Answering

Pages: 92-94 (3) | [Full Text] PDF (308 KB)
P Patel, J Prajapati
Vadodara Institute of Engineering, India

Abstract -
Open domain natural language question answering (QA) is a process of automatically finding answers to questions searching collections of text files. Question answering (QA) is a long-standing challenge in NLP, and the community has introduced several paradigms and datasets for the task over the past few years. These patterns differ from each other in the type of questions and answers and the size of the training data, from a few hundreds to millions of examples. Context-aware QA paradigm and two most notable types of supervisions are coarse sentence-level and fine-grained span-level. In this paper we analyse different intensive researches in semi-supervised learning for question-answering.
 
Index Terms - SSL-QA, Semi-Supervised, Learning, Question-Answering

Citation - P Patel, J Prajapati. "SSL-QA: Analysis of Semi-Supervised Learning for Question-Answering." International Journal of Computer Engineering and Information Technology 10, no. 6 (2018): 92-94.

Twitter Sentiment Analysis on Demonetization tweets in India Using R language
 

Twitter Sentiment Analysis on Demonetization tweets in India Using R language

Pages: 95-101 (7) | [Full Text] PDF (602 KB)
K Arun, A Srinagesh, M Ramesh
Dept of CSE, RVR & JC College of Engineering, Guntur, India

Abstract -
In this global village social media is in the front row to interact with people, Twitter is a the ninth largest social networking website in the world, only because of micro blogging people can share information by way of the short message up to 140 characters called tweets, It allows the registered users to search for the latest news on the topics they have an interest, Lakhs of tweets shared daily on a real-time basis by the members, it has more than 328 million active users per month , Twitter is the best source for the sentiment and opinion analysis on product reviews, movie reviews and current issues in the world. In this paper we present the sentiment analysis on the current twitters like Demonetization, Indians and all our the world people are share their opinions in twitter about current news in the country. The sentiment analysis extracts positive and negative opinions from the twitter data set, R studio provides best environment for this twitter sentiment analysis. Access twitter data from Twitter API, data is written into txt files as the input dataset. Sentiment analysis is performed on the input dataset that initially performs data cleaning by removing the stop words, followed by classifying the tweets as positive and negative by polarity of the words. Generate the word cloud. Finally that generates positive and negative word cloud, comparison of positive and negative scores to get the current public pulse and opinion..
 
Index Terms - Twitter Data, Text Mining, Sentiment Analysis, Natural Language Processing, R-Studio

Citation - K Arun, A Srinagesh, M Ramesh. "Twitter Sentiment Analysis on Demonetization tweets in India Using R language." International Journal of Computer Engineering and Information Technology 10, no. 6 (2018): 95-101.