ASSESSMENT OF AVIATION SECURITY SCREENERS PROFFICIENCY BY MEANS OF APPLYING THE A. BIRNBAUM TWO-PARAMETER MODEL

The necessity to improve assessment of aviation security screeners’ competence has been analyzed. Computer based training systems have been widely used in the process of screeners’ training and evaluating the results of training. The main advantage of similar systems application is the possibility of adaptation to the individual screeners’ requirements by changing the level of training task complexity. The efficiency of applying these systems is proved by foreign researches. To assess the results of screeners’ activity the dangerous image projection data is also used. The analysis of modern approaches to assess the screeners’ activity efficiency showed that they do not completely take into account x-ray image complexity factors affecting the results of screeners’ activity monitoring. There have been presented and tested A. Birnbaum two-parameter model, which is used to assess the screeners’ proficiency competence by means of testing. According to International Civil Aviation Organization recommendations the x-ray image data base has been formed; it includes four blocks of prohibited items. Within the suggested model the probability of detecting prohibited items by aviation security screeners is considered as functions of such parameters as the difference between level of qualification and level of x-ray images complexity, and also between the aviation security screeners’ structure of their professional knowledge. The solution of the task to search A. Birnbaum model parameters values by using maximum likelihood method have been offered. Within the model the qualification level characteristic functions, which describe multi-complexity level of x-ray image interpretation competency of the aviation security screener, were generated and explored. Complex criterion to assess the level of the aviation security screener qualification is offered and tested. The suggested criterion allows to evaluate aviation security screeners’ competency taking into account not only the average level of qualification, but its possible variance. The suggested criterion may be used while selecting and certificating the screeners when the requirement to detect at least 95% prohibited items is applied.

1. Schwaninger, A., Hardmeier, D. and Hofer, F. (2004). Measuring visual abilities and visual knowledge of aviation security screeners. IEEE International Carnahan Conference on Security Technology Proceedings, pp. 258–264.

2. Schwaninger, A., Bolfing, A. and Michel, S. (2009). A statistical approach for image difficulty estimation in x-ray screening using image measurements. IEEE International Carnahan Conference on Security Technology Proceedings, vol. 43, pp. 303–308.

3. Zhang, N. and Zhu, J. (2015). A study of x-ray machine image local semantic features extraction model based on bag-of-words for airport security. International journal on smart sensing and intelligent systems, vol. 1(38), pp. 45–4.

4. Schwaninger, A. (2005). Increasing efficiency in airport security screening. Safety and Security Engineering, vol. 82, pp. 405–416.

5. Hofer, F. and Schwaninger, A. (2005). Using threat image projection data for assessing individual screener performance. Safety and Security Engineering, vol. 82, pp. 417–426.

6. Michel, S., Mendes, M., de Ruiter, J.C., GerKoomen, C.M. and Schwaninger, A. (2014). Increasing x-ray image interpretation competency of cargo security screeners. International journal of industrial ergonomics, vol. 44, pp. 551–560.

7. Hofer, F. and Schwaninger, A. (2004). Reliable and valid measures of threat detection performance in X-ray screening. IEEE International Carnahan Conference on Security Technology Proceedings, vol. 38, pp. 303–308.

8. Volkov, Al.K., Aidarkin, D.V. and Volkov, An.K. (2017). Primenenie dvukhparametricheskoi modeli IRT dlya otsenki veroyatnostnykh kharakteristik obnaruzheniya zapreshchennykh predmetov operatorami dosmotrovoi tekhniki [The two-parameter IRT model application to assess probabilistic charecterisrics of detecting prohibited items by aviation security screeners]. Civil Aviation High Technologies, vol. 3(20), pp. 100–109. (in Russian)

9. Baker, F.B. (2001). The Basic of Item Response Theory. ERIC, 172 p.

10. Neiman, Yu.M. and Khlebnikov, V.A. (2000). Vvedeniе v teoriyu modelirovaniya i parametrizatsii pedagogicheskikh testov [Introduction to the theory of modeling and parameterization of pedagogical tests]. Moscow: Prometheus, 168 p. (in Russian)

11. Chelyshkova, M.B. (2002). Teoriya i praktika konstruirovaniya pedagogicheskikh testov: Uchebnoe posobie [Theory and practice of pedagogical tests designing: Manual]. Moscow: Logos, 432 p. (in Russian)

12. Aidarkin, D.V. and Kosachevskii, S.G. (2008). Razrabotka algoritma adaptivnogo testirovaniya dlya avtomaticheskikh obuchayushchikh sistem professional'noi podgotovki letnogo sostava [Adaptive test algorithm design for flight personnel computer based training application]. Scientific Bulletin of the Moscow State Technical University of Civil Aviation, no. 125, pp. 167–172. (in Russian)