@inproceedings{scholars1155,
         journal = {International Conference on Computer and Communication Engineering, ICCCE'10},
           title = {Recursive linear network modeling for predicting and detecting gas leak of a pipe},
         address = {Kuala Lumpur},
            note = {cited By 3; Conference of International Conference on Computer and Communication Engineering, ICCCE'10 ; Conference Date: 11 May 2010 Through 12 May 2010; Conference Code:81802},
            year = {2010},
             doi = {10.1109/ICCCE.2010.5556835},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-77957758879&doi=10.1109\%2fICCCE.2010.5556835&partnerID=40&md5=26d5aa79cf2aceba2905b6edf603f4da},
        keywords = {Flammable gas; Gas release; Leakage; Mass flow rate; Recursive algorithms; Relative mass; Safety, Accident prevention; Algorithms; Dispersions; Firedamp; Flammability; Forecasting; Health hazards; Mass transfer; Pipe; Pipe flow, Computer simulation},
        abstract = {In many industries, there are serious safety concerns related to the used of flammable gases in both indoor and outdoor environments. Any accidental and dispersion of toxic gases were always major hazards for public health and safety that industries had to deal with. Accident can happen due to many reasons, such as damaged pipes, leakage at storage tank, or while the gas being transport. For these reasons, it is crucial to develop reliable method of analyses of flammable gas release and dispersion. Relative mass loss of the leakage is introduced as the input for the simulation model and the data from the simulation model is taken at real time (on-line) to feed into the recursive algorithm. The objective of this paper is to describe the use of recursive solution in order to predict the release of mass flow rate using on-line data. Recursive Least Square (RLS) and Recursive Instrument Variable (RIV) are used to predict the mass flow rate of the leakage and prediction error is observed. This paper proposed that, RIV algorithm model with Inversion Lemma update scheme can predict the release flow rate at very high accuracy comparatively and able to adopt the learning process very well. {\^A}{\copyright} 2010 IEEE.},
          author = {Akib, A. B. Md. and Saad, N. and Asirvadam, V.},
            isbn = {9781424462346}
}