Scientific and Technical Journal

ELECTROTECHNIC AND COMPUTER SYSTEMS

ISSN Print 2221-3937
ISSN Online 2221-3805
AUTOMATION OF THE SUBMISSION AND RETRIEVAL OF DECLARATIVE KNOWLEDGE IN THE DIGITAL LAYOUT OF THE ENTERPRISE DURING THE INITIALIZATION OF THE PROJECTS OF OCCUPATIONAL SAFETY
Abstract:
To reflect the current level of organization and working conditions in the company and support of decision-making on project initialization OSH proposed to use the digital mockup on a frame model based on the knowledge base that includes declarative knowledge in the form of models, reflecting the level of organization and working conditions in the company of a group of factors and procedural knowledge as a method of learning, allowing to assess the need for initialization of labor protection projects, as well as the script of the meeting on the basis of input features with the base state models. To represent declarative knowledge on the organization and working conditions data on the enterprise structure suggested qualitative and complex quantitative and qualitative characteristics. Extraction of knowledge about the state of working conditions at the plant is the result of the examination, which holds the decision-maker based on the analysis of declarative data. To check the quality of expert solutions for initialization OSH projects, proposed to use the methodology of the automated extraction of expert knowledge through the clustering of data by groups of organizations and working conditions. The process of clustering provides a consistent implementation of procedures of self-organizing Kohonen layer neuron computing, calibration of the output vector elements of the training sample and final marking layer neurons Kohonenana. Testing of the proposed method for real data on levels of aerosol, electromagnetic, acoustic, chemical and biological effects of ionizing radiation, microclimate, light and vibration showed rise in the relative proportion of true positive cases, an average of 20% and 50% reduction in the relative proportion of truly negative cases, all these groups working conditions.
Authors:
Keywords
DOI
References
  1. Gogunskiy V.D., and Chernega Yu.S. Upravlinnya rizikami v proektah z ohoroni pratsI yak metod usunennya shkidlivih i nebezpechnih umov pratsi, [Risk Management in Pprojects for the Protection of Labor as a Method of Eliminating Harmful and Dangerous Working Conditions], (2013), Vost.-Evropeyskiy Zhurnal Peredovyih Tehnologiy, No. 1/10 (61), Kharkov, Ukraine, Tehnolog. Tsentr, pp. 83 – 85 (In Ukrainian).
  2. Rukovodstvo po sistemam upravleniya ohranoy truda. MOT-SUOT 2001 [Guide to System Safety Management], (2003), ILOOSH 2001. Zheneva, Shvejcariya, Mezhdunarodnoe Byuro Truda (In Russian).
  3. Arsiriy E.A., and Antoschuk S.G. Tsifrovoy maket oborudovaniya energeticheskogo predpriyatiya [Digital Layout of Equipment Energy Companies], (2013), Electrotechnic and Computer Systems, Kiev, Ukraine, TehnIka, No. 12 (88), pp. 71 – 82 (In Russian).
  4. Moskalyuk A.U., and Manikaeva O.S. Vikoristannya neyronnih merezh dlya otsInki stanu umov pratsI [The Use of Neural Networks to Assess the State of Labour Conditions], (2014), Upravlinnya Proektami: Innovatsiyi, ne Liniynist, Sinergetika: Materialy v Mizhnarodnoyi Naukovo-praktichnoyi Konferentsiyii Magistrantiv, AspIrantiv ta Naukovtsiv, [u 2 t.], Vidpovidniy za Vipusk P.O. Teslenko, Odessa, Ukraine, ODABA, Vol. 2, pp. 147 – 149 (In Ukrainian).
  5. Moskalyuk A.Yu., and Teslenko P.A. Proektizatsiya protsessov ohranyi truda [Practical Processes of Labour Protection], (2011), Upravlinnya Proektami: Stan ta Perspektivi: Materialy 7-i Mizhnarodnoyi Naukovo-praktichnoyi Konferentcii, Nikolayev, Ukraine, NUK, pp. 208 – 210 (In Russian).
  6. Pampuha I.V. Obosnovanie ispolzovaniya neyronnyih setey v sistemah podderzhki prinyatiya resheniya pri funktsionirovanii slozhnyih sistem [The Justification for the Use of Neural Networks in Decision Support Systems Decisions in the Operation of Complex Systems], (2013), Zbirnik Naukovih Prats Viyskovogo Institutu Kiiivskogo NatsIonalnogo UnIversitetu ImenI Tarasa Shevchenka, Vip. 42, pp. 85 – 90 (In Russian).
  7. Uosserman F. Neyrokompyuternaya tehnika: Teoriya i praktika [Neurocomputing Technique], (1992), per. s angl., Moscow, Russian Federation, Mir, 240 p. (In Russian).
  8. Kohonen T. Samoorganizuyuschiesya kartyi [Self-organizing Maps], (2008), 3-go angl. izd., Moscow, Russian Federation, BINOM Laboratoriya Znaniy, 655 p. (In Russian).
  9. Paklin N. Logisticheskaya regressiya i ROC-analiz – matematicheskiy apparat. [Logistic Regression and ROC Analysis is Mathematics] (In Russian) [Electronic Resource]. available at: http://www.basegroup.ru /library/analisys/ regression/logistic (accessed 25.04.2015).
  10. Davis J., and Goadrich M., (2006), The Relationship Between Precision-Recall and ROC Curves, Proc. Of 23 International Conference on Machine Learning, Pittsburgh, PA (In English)
Published:
Last download:
2017-11-17 18:37:10

[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2014. Any use of information from the site is possible only under the condition that the source link! ]
Яндекс.Метрика