To address the problems of low recognition accuracy of traditional early fire warning systems in actual scenari-os, a newly developed naive Bayes (NB) algorithm, namely, improved naive Bayes (INB), was proposed. An optimization method based on attribute weighting and an orthogonal matrix was used to improve the NB algorithm. Attribute weighting considers the influence of different values of each attribute on classification performance under every decision category;the orthogonal matrix weakens the linear relationship between the attributes reducing their correlations, which is more closely related to the conditional independence assumption. Data from the technology report of the National Institute of Standards and Technology (NIST) regarding fire research were used for the simulation, and eight datasets of different sizes were constructed for INB training and testing after filtering and normalization. A ten-fold cross-validation suggests that INB has been effectively trained and demonstrates the stable ability in fire alarms when the dataset contains 190 sets of samples; namely, the INB can be fully trained by using small datasets. A support vector machine (SVM), a back propaga-tion (BP) neural network, and NB were selected for comparison. The results showed that the recognition accuracy, aver-age precision, average recall, and average measure of INB were 96.1％, 97.3％, 97.2％, and 97.3％, respectively, which F1 is the highest among the four different algorithms. Additionally, INB has a better performance compared to NB, SVM, and BP neural networks when the training time is short . In conclusion, INB can be used as a core algorithm for fire alarm sys-tems with excellent and stable fire alarm capabilities.

Xiangyong He;Yong Jiang;Yong Hu

State Key Laboratory of Fire Science,University of Science and Technology of China,Hefei 230027,China

中国科学技术大学学报

[1]Xiangyong He;Yong Jiang;Yong Hu-.Application of a newly developed naive Bayes algorithm in fire alarm)[J].中国科学技术大学学报,2022(06):47-55

scenari

Application,newly,developed,naive,Bayes,fire,To,address,problems,low,recognition,accuracy,traditional,early,warning,systems,actual,namely,improved,INB,was,proposed,An,optimization,method,weighting,orthogonal,matrix,used,Attribute,considers,influence,different,values,each,classification,performance,under,every,decision,category,weakens,linear,relationship,between,attributes,reducing,their,correlations,which,more,closely,related,conditional,independence,assumption,Data,from,technology,report,National,Institute,Standards,Technology,NIST,regarding,research,were,simulation,datasets,sizes,constructed,training,testing,after,filtering,normalization,ten,fold,cross,validation,suggests,that,has,been,effectively,trained,demonstrates,stable,ability,alarms,when,contains,samples,can,fully,by,using,small,support,vector,machine,back,propaga,neural,selected,comparison,results,showed,precision,average,recall,measure,respectively,highest,among,four,algorithms,Additionally,better,compared,networks,short,conclusion,core,excellent,capabilities

0.530165