Call For Papers
Contact Us

  Airline Passenger Profiling Based on Long ShortTerm Memory  
  Authors : Sameera Sulaiman; Dr.Radhakrishnan B
  Cite as:


The threat of terrorism has an important topic on airport security measures .While passengers face ever-longer lists of prohibited items, security experts increasingly argue that it is passengers themselves, not the contents of their bags, that need to be scrutinized. If passenger profiling works, it would be an effective way to prevent terrorists from attacking and save time and money for everyone else. Passenger profiling play an important role in aviation security. Some of the methods used for this is not efficient because of complication of data. Here proposed a new system that first normalizes the time related data, so that each attribute represent the data in the same data space. After normalization the dimension of data will be reduced using Principal Component Analysis. The dimensionality reduced time related data is termed as LSTM (Long Term Short Memory)to find the pattern that can distinguish between a normal passenger and risky passenger. The LSTM provides much more accuracy than a traditional neural network as it is more capable to detect the pattern in a time related data .The test data is evaluated against the trained model and predicts the result more accurate than traditional ones.


Published In : IJCSN Journal Volume 8, Issue 3

Date of Publication : June 2019

Pages : 246-249

Figures :03

Tables : 01


Sameera Sulaiman : is pursuing her M.Tech degree on Computer Science and Engineering at APJ Abdul KalamTechnological University, Thiruvananthapuram. Her research interests are in Image processing, Data Mining and Data Security.

Dr. Radhakrishnan B : is working as the Head of CSE department. He has more than 14 years experience in teaching and has published papers on data mining and image processing. His research interests include image processing, data mining, image mining.


Principal Component Analysis, Long Term Short Memory, Normal Passenger, Risky Passenger

This paper introduces a Machine Learning approach for Passenger Profiling. DR using PCA is for normalizing the input data set and preprocessing the unwanted features. LSTM method is used to train the input dataset and this is an efficient method used for time sequence processing. The proposed method provides the airline profiling more secure and it is less time consuming and avoid manual interaction.


[1] Passenger Profiling and Screening for Aviation Security in the Presence of Strategic Attackers Huseyin Cavusoglu, Young Kwark, Bin Mai, Srinivasan Raghunathan. [2] Carnival Booth: An Algorithm for Defeating the Computer-Assisted Passenger Screening System by Samidh Chakrabarti and Aaron Strauss. [3] Multilevel Passenger Screening Strategies for Aviation Security Systems. Laura A. McLay and Sheldon H. Jacobson, John E. Kobza [4] Airline Passenger Profiling Based on Fuzzy Deep Machine Learning. Yu-Jun Zheng, Wei-Guo Sheng, Xing-Ming Sun, and Sheng-Yong Chen.