Informatics Publishing Limited

Nitin Mishra ¹, Ranjit Kumar ¹, Shishir Kumar Shandilya ¹

Affiliations
1 N.I.I.S.T., Bhopal, (M.P.), IN

Abstract

This paper proposes a HMM (Hidden Markov Model) based fraud detection system for credit card fraud detection. The method works on the statistical behavior of user’s transactions. Since the original transactions are not available due to privacy policies of bank we used here synthetically generated data for a credit card user, and then HMM model is trained using different size of sample of generated labeled data we also discuss the performance of the HMM model on this data set in terms of detection accuracy and earliness of fraud detection. The system has been tested on a Pentium 4 PC with 2 GB of RAM, the test program is coded in MATLAB 7.5.

Keywords

Fraud Detection, HMM (Hidden Markov Model).

Full Text

   

Mukunda M. Gogoi ¹, S. Suresh Babu ¹, B. S. Arun ¹, K. Krishna Moorthy ², A. Ajay ³, P. Ajay ⁴, Arun Suryavanshi ⁵, Arup Borgohain ⁶, Anirban Guha ⁷, Atiba Shaikh ⁸, Binita Pathak ⁴, Biswadip Gharai ⁹, Boopathy Ramasamy ¹⁰, G. Balakrishnaiah ¹¹, Harilal B. Menon ⁸, Jagdish Chandra Kuniyal ¹², Jayabala Krishnan ¹³, K. Rama Gopal ¹¹, M. Maheswari ¹³, Manish Naja ¹⁴, Parminder Kaur ⁷, Pradip K. Bhuyan ⁴, Pratima Gupta ¹⁵, Prayagraj Singh ¹⁶, Priyanka Srivastava ¹⁴, R. S. Singh ¹⁷, Ranjit Kumar ¹⁵, Shantanu Rastogi ¹⁶, Shyam Sundar Kundu ⁶, Sobhan Kumar Kompalli ¹, Subhasmita Panda ¹⁰, Tandule Chakradhar Rao ¹¹, Trupti Das ¹⁰, Yogesh Kant ¹⁸

Affiliations
1 Space Physics Laboratory, Vikram Sarabhai Space Centre, Thiruvananthapuram 695 022, IN
2 Centre for Atmospheric and Oceanic Sciences, Indian Institute of Science, Bengaluru 560 012, IN
3 Divecha Centre for Climate Change, Indian Institute of Science, Bengaluru 560 012, IN
4 Centre for Atmospheric Studies, Dibrugarh University, Dibrugarh 786 004, IN
5 Regional Remote Sensing Centre, Indian Space Research Organisation, Nagpur 440 033, IN
6 North Eastern – Space Application Centres, Shillong 793 103, IN
7 Department of Physics, Tripura University, Suryamaninagar, Agartala 799 022, IN
8 Department of Marine Sciences, Goa University, Goa 403 206, IN
9 National Remote Sensing Centre, Indian Space Research Organisation, Hyderabad 500 037, IN
10 Indian Institute of Mineral and Materials Technology, Bhubaneswar 751 013, IN
11 Sri Krishna Devaraya University, Anantapur 515 003, IN
12 G. B. Pant Institute of Himalayan Environment and Development, Kullu 175 126, IN
13 Tamil Nadu Agricultural University, Coimbatore 641 003, IN
14 Aryabhatta Research Institute of Observational Sciences, Nainital 263 002, IN
15 Department of Chemistry, Dayalbagh Educational Institute, Agra 282 005, IN
16 Department of Physics, D.D.U. Gorakhpur University, Gorakhpur 273 009, IN
17 Department of Chemical Engineering, IIT-BHU, Varanasi 221 005, IN
18 Indian Institute of Remote Sensing, Indian Space Research Organisation, Dehradun 248 001, IN

Abstract

In this study, we assess the response of ambient aero-sol black carbon (BC) mass concentrations and spec-tral absorption properties across Indian mainland during the nation-wide lockdown (LD) in connection with the Coronavirus Disease 19 (COVID-19) pan-demic. The LD had brought near to total cut-off of emissions from industrial, traffic (road, railways, ma-rine and air) and energy sectors, though the domestic emissions remained fairly unaltered. This provided a unique opportunity to delineate the impact of fossil fuel combustion sources on atmospheric BC characte-ristics. In this context, the primary data of BC meas-ured at the national network of aerosol observatories (ARFINET) under ISRO-GBP are examined to assess the response to the seizure of emissions over distinct geographic parts of the country. Results indicate that average BC concentrations over the Indian mainland are curbed down significantly (10–40%) from pre-lockdown observations during the first and most in-tense phase of lockdown. This decline is significant with respect to the long-term (2015–2019) averaged (climatological mean) values. The drop in BC is most pronounced over the Indo-Gangetic Plain (>60%) and north-eastern India (>30%) during the second phase of lockdown, while significant reduction is seen during LD1 (16–60%) over central and peninsular Indian as well as Himalayan and sub-Himalayan regions. De-spite such a large reduction, the absolute magnitude of BC remained higher over the IGP and north-eastern sites compared to other parts of India. Notably, the spectral absorption index of aerosols changed very little over most of the locations, indicating the still persisting contribution of fossil-fuel emissions over most of the locations.

Keywords

ARFINET, Black Carbon, COVID-19.

Full Text