In this article, we proposed a multi-agent concurrent neorosimulated annealing (CNSA) algorithm, which was used for the supervised training of the neural networks (NN). The proposed CNSA is a population based parallel version of the basic simulated annealing (SA) algorithm. In this work, CNSA was applied for designing an intelligent sensory system that detects proportion of component gases of manhole gas mixture. The proposed intelligent sensory system was modeled using NN, where, the training of NN was supplemented by the proposed parallel version of SA algorithm, that is, CNSA. Once the training of the NN was covered, the sensory system was used for sensing the accumulated toxic gas components of manholes. The manhole gas-mixture problem was treated as pattern recognition and noise reduction problem. This article offers a critical performance analysis of CNSA algorithm, where its performance was compared with backpropagation, conjugate gradient algorithm, particle swarm optimization, and genetic algorithm in both empirical and statistical sense. We found that the proposed CNSA performed significantly well in comparison to its counterparts as far as this case study was concerned.
WhortonJ., The insidious foe - sewer gas, West. J. Med.175(6), 2001, 427-428, pMC 1275984.
2.
Lewis, Dangerous Properties of Industrial Materials, ninth edition ed. Van Nostrand Reinhold, 1996, iSBN 0132047674.
3.
GromickoN., ``Sewer gases in the home,'' 2006, http://www. nachi.org/sewer-gases-home.html.
4.
HinduT., ``Deaths in the drains,'' 2014, http://www.thehindu. com/opinion/op-ed/deaths-in-the-drains/article5868090.ece? homepage=true., Accessed on 15 July 2015.
5.
HinduT., ``Sewer deaths,'' 2014, http://www.thehindu.com/ opinion/letters/sewer-deaths/article5873493.ece, Accessed on 15 July 2015.
6.
HinduT., ``Supreme court orders states to abolish manual scavenging,'' 2014, http://www.thehindu.com/news/national/ supreme-court-orders-states-to-abolish-manual-scavenging/article5840086.ece, Accessed on 15 July 2015.
7.
Rummelhart D.E., HintonG.E. and WilliamsR.J., Learning representations by back-propagating errors, Nature323 (6088), 1986, 533-536, doi: 10.1038/323533a0.
8.
KirkpatrickS., GelattC.D. and VecchiM.P., Optimization by simulated annealing, Science220, 1983, 671-680, doi: 10.1126/science.220.4598.671.
9.
CernyV., thermodynamical approach to the traveling salesman problem: An efficient simulation algorithm, Journal of Optimization Theory and Applications45, 1985, 41-51, doi: 10.1007/BF00940812.
10.
MetropolisN.RosenbluthA.RosenbluthM.TellerA. and TellerE., Equation of state calculations by fast computing machines, The Journal of Chemical Physics21(6), 1953, 1087-1090, doi: 10.1063/1.1699114.
11.
AllwrightJ.R.A. and CarpenterD.B., A distributed implementation of simulated annealing for the traveling salesman problem, Parallel Computation10, 1989, 335-338.
MalekM., GuruswamyM. and PandyaM., Serial and parallel simulated annealing and tabu search algorithms for the traveling salesman problem, Annals of Operations Research21, 1989, 59-84.
14.
ChenD.-J., LeeC.-Y., ParkC.-H. and MendesP., Parallelizing simulated annealing algorithms based on high-performance computer, Journal of Global Optimization39, 2007, 261-289, dOI 10.1007/s10898-007-9138-0.
15.
RandallR.E.D., SextonS. and JohnsonJ.D., Beyond backpropagation: Using simulated annealing for training neural networks, Journal of Organizational and End User Computing11(3), 1999.
16.
LiJ., A mixed gas sensor system based on thin film saw sensor array and neural network, IEEE, 1993, 179-181, 0-7803-0976-6/93.
17.
SrivastavaA.K., SrivastavaS.K. and ShuklaK.K., On the design issue of intelligent electronic nose system, IEEE, 2000, 243-248, 0-7803-5812-0/00.
18.
SrivastavaA.K., SrivastavaS.K. and ShuklaK.K., In search of a good neuro-genetic computational paradigm, IEEE, 2000, 497-502, 0-78O3-5812-0/00.
19.
E.L. et. al., Multicomponent gas mixture analysis using a single tin oxide sensor and dynamic pattern recognition, IEEE Sensors Journal1(3), 207-213, 2001, 1530437X/01.
20.
LiuJ., ZhangY., ZhangY. and ChengM., Cross sensitivity reduction of gas sensors using genetic algorithm neural network, in: Optical Methods for Industrial Processes, S. Farquharson, Ed., 4201. Proceedings of SPIE, 2001.
21.
TsirigotisG., BerryL. and GatzioniM., Neural network based recognition, of co and nh_3 reducing gases, using a metallic oxide gas sensor array, in Scientific Proceedings of RTU, ser. Series 7, Vol. 3. Telecommunications and Electronics, 2003, 6-10.
22.
LeeD.-S., BanS.-W., LeeM. and LeeD.-D., Micro gas sensor array with neural network for recognizing combustible leakage gases, IEEE Sensors Journal5(3), 2005, 530-536, dOI 10.1109/JSEN.2005.845186.
23.
AmbardM., GuoB., MartinezD. and BermakA., A spiking neural network for gas discrimination using a tin oxide sensor array, in International Symposium on Electronic Design, Test and Applications, IEEE, 2008, 394-397, 0-7695-3110-5/08.
24.
BahaH. and DibiZ., A novel neural network-based technique for smart gas sensors operating in a dynamic environment, Sensors9, 8944-8960, 2009, iSSN 1424-8220.
25.
PanW., LiN. and LiuP., Application of electronic nose in gas mixture quantitative detection, in Proceedings of IC-NIDC, IEEE, 2009, 976-980, 978-1-4244-4900-2/09.
26.
ZhangQ., LiH. and TangZ., Knowledge-based genetic algorithms data fusion and its application in mine mixed-gas detection, IEEE, 2010, 1334-1338, 978-1-4244-5182-1/10.
27.
Won SoD.S.E.S.Y. and KooJamin, The estimation of hazardous gas release rate using optical sensor and neural network, in European Symposium on Computer Aided Process Engineering ESCAPE20, S. Pierucci and G.B. Ferraris, Eds. Elsevier B.V, 2010.
28.
OjhaV.K., DutaP., SahaH. and GhoshS., Linear regression based statistical approach for detecting proportion of component gases in manhole gas mixture, in International Symposium On Physics And Technology Of Sensors. IEEE, 2012, dOI: 10.1109/ISPTS.2012.6260865.
29.
OjhaV.K., DutaP., SahaH. and GhoshS., A novel neuro simulated annealing algorithm for detecting proportion of component gases in manhole gas mixture, in International Conference on Advances in Computing and Communications. IEEE, 2012, 238-241, dOI 10.1109/ICACC.2012.54.
30.
TanC.-M., Practical considerations for simulated annealing implementation, I-Tech Education and Publishing, 2008, 420, iSBN 978-953-7619-07-7.
31.
Stuart RussellP.N., Artificial intelligence a mordern approach, Prantice Hall, iSBN: 10 0131038052.
32.
OnbasoguluE. and OzdamarL., Parallel simulated annealing algorithms in global optimization, Journal of Global Optimization19, 27-50, 2001.
CoranaA., MarchesiM., MartiniC. and RidellaS., Minimizing multimodal functions of continuous variables with the simulated annealing algorithm, ACM Transactions on Mathematical Software13(3), 262-280, 1987.
35.
BoeseK.D. and KahngA.B., Simulated annealing of neural networks: the ``cooling'' strategy reconsidered, 1993.
36.
WongchoosukaC., WisitsoraatbA., TuantranontbA. and KerdcharoenaT., Portable electronic nose based on carbon nanotube-sno_2 gas sensors and its application for detection of methanol contamination in whiskeys, Sensors and Actuators B: Chemical, 2010, doi: 10.1016/j.snb.2010.03.072.
37.
GhoshS., RoyA., SinghS., OjhaV.K., DuttaP. and SahaH., Sensor array for manhole gas analysis, in International Symposium on Physics and Technology of Sensors, Pune, India: IEEE, 2012, 978-1-4673-1040-6.
38.
GhoshS., RoychaudhuriC., SahaH., OjhaV.K. and DuttaP., Portable sensor array system for intelligent recognizer of manhole gas, in International Conference On Sensing Technology (ICST). Pune, India: IEEE, 2012, 589-594, 978-1-4673-2246-1.
39.
HaykinS., Neural Networks A Comprehensive Foundation, second edition ed. Pearson Prentice Hall, 2005, iSBN 81-7803-300-0.
40.
OjhaV.K., DutaP., SahaH. and GhoshS., Detection of proportion of different gas components present in manhole gas mixture using backpropagation neural network, International Proceedings Of Computer Science and Information Technology1, 11-15, 2012, iSBN: 978-981-07-2068-1.
41.
OjhaV.K., DuttaP., ChaudhuriA. and SahaH., Study of various conjugate gradient based ann training methods for designing intelligent manhole gas detection system, in Computational and Business Intelligence (ISCBI), 2013 International Symposium on. IEEE, 2013, 83-87.
42.
OjhaV.K., DutaP. and SahaH., Performance analysis of neuro genetic algorithm applied on detecting proportion of components in manhole gas mixture, International Journal Of Artificial Intelligence and Application3(4), 2012, 83-98, dOI: 10.5121/IJAIA.2012.3406.
43.
OjhaV.K. and DutaP., Performance analysis of neuro swarm optimization algorithm applied on detecting proportion of components in manhole gas mixture, Artificial Intelligence Research1, 2012, 31-46, dOI: 10.5430/JNEP.V1N1PX.
44.
BoesD.C., GraybillF.A. and MoodA.M., Introduction to the Theory of Statistics, 3rd ed. New York: McGraw-Hill, 1974.
45.
SheskinD.J., Handbook of Parametric and Nonparametric Statistical Procedures, 3rd ed. CRC-Press, 2003, iSBN-1-58488-440-1.
46.
DuttaP. and DuttaMajumderD., Performance Analysis of Evolutionary Algorithm. Lambert Academic Publishers, 2012, iSBN: 978-3-659-18349-2.
47.
GailM.H. and GreenS.B., Critical values for the one-sided two-sample kolmogorov-smirnov statistic, Journal of the American Statistical Association71(355), 1976, 757-760.
48.
ErnstA. and ZibrakJ.D., Carbon monoxide poisoning, The New England Journal of Medicine339(22), 1998, pMID9828249.
49.
USEPA, ``Health and environmental effects problem for hydrogen sulfide,'' West. J. Med., 1980, 118-8, eCAOCIN026A.
50.
FriedmanD., Toxicity of carbon dioxide gas exposure, co2 poisoning symptoms, carbon dioxide exposure limits, and links to toxic gas testing procedures, inspectAPedia.
51.
FaheyD., ``Twenty questions and answers about the ozone layer,'' 2002.
