TWO-PARAMETER IRT MODEL APPLICATION TO ASSESS PROBABILISTIC CHARACTERISTICS OF PROHIBITED ITEMS DETECTION BY AVIATION SECURITY SCREENERS

The modern approaches to the aviation security screeners’ efficiency have been analyzedand, certain drawbacks have been considered. The main drawback is the complexity of ICAO recommendations implementation concerning taking into account of shadow x-ray image complexity factors during preparation and evaluation of prohibited items detection efficiency by aviation security screeners. Х-ray image based factors are the specific properties of the x-ray image that influence the ability to detect prohibited items by aviation security screeners. The most important complexity factors are: geometric characteristics of a prohibited item; view difficulty of prohibited items; superposition of prohibited items byother objects in the bag; bag content complexity; the color similarity of prohibited and usual items in the luggage.The one-dimensional two-parameter IRT model and the related criterion of aviation security screeners’ qualification have been suggested. Within the suggested model the probabilistic detection characteristics of aviation security screeners are 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’ responsibility and structure of their professional knowledge. On the basis of the given model it is possible to consider two characteristic functions: first of all, characteristic function of qualification level which describes multi-complexity level of x-ray image interpretation competency of the aviation security screener; secondly, characteristic function of the x-ray image complexity which describes the range of x-ray image interpretation competency of the aviation security screeners having various training levels to interpret the x-ray image of a certain level of complexity. The suggested complex criterion to assess the level of the aviation security screener qualification allows to evaluate his or her competency taking into account not only the average level qualification, but its possible variance. The important feature of implementing IRT models logistic functions is the necessity of preliminary selection of test images. Test x-ray images have to be selected in the ascending order of their complexity taking into consideration the influence of various factors.The suggested model may be applied both in the field of improving of aviation security screeners’ training methods to provide screening procedures, and while solving problems of increasing the efficiency of the screening system functioning.

probability of prohibited items detection, aviation security screeners, competency assessment, x-ray images complexity

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

2. Ionov V.V., Kurchavov V.V. Mnogoparametricheskaya otsenka deyatel'nosti opera-torov introskopov [Multiparametric evaluation of aviation security screeners activity]. Mir transporta [World of transport], 2014, no. 2 (51), pp. 194–201. (in Russian)

3. Zhang N., Zhu J. 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, 2015, vol. 38 (1), pp. 45–64.

4. Biggs A.T., Cain M.S., Clark K., Darling E.F., Mitroff S.R. Assessing visual search performance differences between transportation security administration officers and nonprofessional visual searchers. Applied cognitive psychology, 2014, vol. 29 (1), pp. 142–148.

5. Biggs A.T., Mitroff S.R. Improving the efficacy of security Screening tasks: a review of visual search challenges and ways to mitigate their adverse effects. Visual cognition, 2013, vol. 21 (3), pp. 330–352.

6. Steiner-Koller S.M., Bolfing A., Schwaninger A. Assessment of x-ray image interpretation competency of aviation security screeners. IEEE International Carnahan Conference on Security Technology Proceedings, 2009, vol. 43, pp. 303–308.

7. Schwaninger A., Bolfing A., Halbherr T., Helman S., Belyavin A., Hay L. The impact of image based factors and training on threat detection performance in x-ray. International Conference on Research in Air Transportation Proceedings. 2008, vol. 3, pp. 317–324.

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

9. Halbherr T., Schwaninger A., Budgell G.R., Wales A. Airport security competency: A cross-sectional and longitudinal analysis. The international journal of aviation psychology, 2013, vol. 23(2), pp. 113–129.

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

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

12. Gmurman V.E. Teoriya veroyatnostei i matematicheskaya statistika: Ucheb. posobie dlya stud. vuzov [Theory of probability and mathematical statistics: Textbook for students of higher educational institutions]. Issue 6. Moscow, Higher school, 1998, 478 p. (in Russian)