{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:24:31Z","timestamp":1760235871163,"version":"build-2065373602"},"reference-count":34,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T00:00:00Z","timestamp":1632960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"atural Science Foundation of Shaanxi Province","award":["2020JQ-816,20JK0608"],"award-info":[{"award-number":["2020JQ-816,20JK0608"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Maximum a posteriori estimation (MAP) with Dirichlet prior has been shown to be effective in improving the parameter learning of Bayesian networks when the available data are insufficient. Given no extra domain knowledge, uniform prior is often considered for regularization. However, when the underlying parameter distribution is non-uniform or skewed, uniform prior does not work well, and a more informative prior is required. In reality, unless the domain experts are extremely unfamiliar with the network, they would be able to provide some reliable knowledge on the studied network. With that knowledge, we can automatically refine informative priors and select reasonable equivalent sample size (ESS). In this paper, considering the parameter constraints that are transformed from the domain knowledge, we propose a Constrained adjusted Maximum a Posteriori (CaMAP) estimation method, which is featured by two novel techniques. First, to draw an informative prior distribution (or prior shape), we present a novel sampling method that can construct the prior distribution from the constraints. Then, to find the optimal ESS (or prior strength), we derive constraints on the ESS from the parameter constraints and select the optimal ESS by cross-validation. Numerical experiments show that the proposed method is superior to other learning algorithms.<\/jats:p>","DOI":"10.3390\/e23101283","type":"journal-article","created":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T10:22:42Z","timestamp":1632997362000},"page":"1283","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Constrained Adjusted Maximum a Posteriori Estimation of Bayesian Network Parameters"],"prefix":"10.3390","volume":"23","author":[{"given":"Ruohai","family":"Di","sequence":"first","affiliation":[{"name":"School of Electronics and Information Engineering, Xi\u2019an Technological University, Xi\u2019an 710021, China"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Xi\u2019an Technological University, Xi\u2019an 710021, China"}]},{"given":"Chuchao","family":"He","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Engineering, Xi\u2019an Technological University, Xi\u2019an 710021, China"}]},{"given":"Zhigao","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London E1 4NS, UK"}]}],"member":"1968","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"ref_1","unstructured":"Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems, Morgan Kaufmann Publishers."},{"key":"ref_2","unstructured":"Koller, D., and Friedman, N. (2009). Probabilistic Graphical Models, MIT Press."},{"key":"ref_3","unstructured":"Cowell, R., Dawid, A., Lauritzen, S., and Spiegelhalter, D. (1999). Probabilistic Networks and Expert Systems, Springer."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"7911","DOI":"10.1126\/science.aap7911","article-title":"Oklahoma\u2019s induced seismicity strongly linked to wastewater injection depth","volume":"359","author":"Hincks","year":"2018","journal-title":"Science"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107336","DOI":"10.1016\/j.ress.2020.107336","article-title":"Research on human error risk evaluation using extended Bayesian networks with hybrid data","volume":"209","author":"Xing","year":"2021","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1016\/j.psep.2021.01.023","article-title":"A combined physics of failure and Bayesian network reliability analysis method for complex electronic systems","volume":"148","author":"Sun","year":"2021","journal-title":"Process Saf. Environ. Prot."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2240","DOI":"10.1109\/TPAMI.2019.2908373","article-title":"Multi-source causal feature selection","volume":"42","author":"Yu","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Learn."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"101912","DOI":"10.1016\/j.artmed.2020.101912","article-title":"Bayesian networks in healthcare: Distribution by medical condition","volume":"107","author":"McLachlan","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6500","DOI":"10.1126\/scitranslmed.aah6500","article-title":"Bacterial colonization and succession in a newly opened hospital","volume":"9","author":"Lax","year":"2017","journal-title":"Sci. Transl. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.apenergy.2016.11.130","article-title":"Fault detection and diagnosis of chillers using Bayesian network merged distance rejection and multi-source non-sensor information","volume":"188","author":"Wang","year":"2017","journal-title":"Appl. Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"112258","DOI":"10.1109\/ACCESS.2019.2925654","article-title":"Multimodal fusion based on LSTM and a couple conditional hidden markov model for chinese sign language recognition","volume":"7","author":"Xiao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/BF00994016","article-title":"Learning bayesian networks: The combination of knowledge and statistical data","volume":"87","author":"Heckerman","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_13","unstructured":"Buntine, W. (1991, January 13\u201315). Theory refinement onbayesian neworks. Proceedings of the 7th Conference on Uncertainty in Artificial Intelligence, Los Angeles, CA, USA."},{"key":"ref_14","unstructured":"Scutari, M. (2016, January 6\u20139). An empirical-bayes score fordiscrete bayesian networks. Proceedings of the 8th International Conference on Probabilistic Graphical Models, Lugano, Switzerland."},{"key":"ref_15","unstructured":"Steck, H., and Jaakkola, T. (2002, January 9\u201314). On the dirichlet prior and bayesian regulation. Proceedings of the 15th International Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_16","unstructured":"Ueno, M. (2010, January 8\u201311). Learning networks determinedby the ratio of prior and data. Proceedings of the 26th International Conference on Uncertainty in Artificial Iteligence, Catalina Island, CA, USA."},{"key":"ref_17","unstructured":"Ueno, M. (2011, January 14\u201317). Robust learning bayesian networks for prior belief. Proceedings of the 27th International Conference on Uncertainty in Artificial Intelligence, Barcelona, Spain."},{"key":"ref_18","unstructured":"Silander, T., Kontkanen, P., and Myllymaki, P. (2007, January 19\u201322). On sensitivity of the map bayesian network structure to the equivalent sample size parameter. Proceedings of the 23rd International Conference on Uncertainty in Artificial Intelligence, Vancouver, BC, Canada."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1016\/j.ijar.2012.09.003","article-title":"Locally averaged bayesian dirichlet metrics for learning the structure and the parameters of bayesian networks","volume":"54","author":"Cano","year":"2013","journal-title":"Int. J. Approx. Reason."},{"key":"ref_20","unstructured":"Druzdzel, M., and Gaag, L. (1995, January 18\u201320). Elicitation of probabilities forbelief networks: Combining qualitative and quantitative information. Proceedings of the 11th International Conference on Uncertainty in Artificial Intelligence, Montreal, QC, Canada."},{"key":"ref_21","unstructured":"Gaag, L., Witteman, C., Aleman, B., and Taal, B. (August, January 30). How to elicit many probabilities. Proceedings of the 23rd International Conference on Uncertainty in Artificial Intelligence, Stockholm, Sweden."},{"key":"ref_22","first-page":"1357","article-title":"Bayesian network learning with parameter constraints","volume":"7","author":"Niculescu","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.ijar.2005.10.003","article-title":"Learning bayesian networks parameters under order constraints","volume":"42","author":"Feelders","year":"2006","journal-title":"Int. J. Approx. Reason."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.dss.2016.05.001","article-title":"An empirical study of bayesian network parameterlearning with monotonic influence constraints","volume":"87","author":"Zhou","year":"2016","journal-title":"Decis. Support Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.ijar.2017.08.009","article-title":"Learning Bayesian network parameters from small data sets: A further constrained qualitatively maximum a posteriori method","volume":"91","author":"Guo","year":"2017","journal-title":"Int. J. Approx. Reason."},{"key":"ref_26","unstructured":"Campos, C., and Qiang, J. (2008, January 8\u201311). Improving bayesian network parameter learning using constraints. Proceedings of the 19th International Conference on Pattern Recognition, Tampa, FL, USA."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/0004-3702(90)90026-V","article-title":"Fundamental concepts of qualitative probabilistic networks","volume":"44","author":"Wellman","year":"1990","journal-title":"Artif. Intell."},{"key":"ref_28","unstructured":"Dasgupta, S. (1997, January 8\u201312). The sample complexity of learning fixed structure Bayesian networks. Proceedings of the 14th International Conference on Machine Learning, Nashville, TN, USA."},{"key":"ref_29","unstructured":"Kohavi, R. (1995, January 18\u201320). A study of cross-validation andbootstrap for accuracy estimation and model selection. Proceedings of the 7th International Conference on Uncertainty in Artificial Intelligence, Montreal, QC, Canada."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"191","DOI":"10.3390\/e3030191","article-title":"Maximum entropy fundamentals","volume":"3","author":"Harremoes","year":"2001","journal-title":"Entropy"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1137\/1026034","article-title":"Mixture densities, maximum likelihood and theem algorithm","volume":"26","author":"Redner","year":"1984","journal-title":"SIAM Rev."},{"key":"ref_33","unstructured":"Campos, C., and Qiang, J. (July, January 29). Bayesian networks and the imprecise dirichlet model applied to recognition problems. Proceedings of the 11th European conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, Belfast, UK."},{"key":"ref_34","unstructured":"Campos, C., Tong, Y., and Qiang, J. (2008, January 12\u201318). Constrained maximum likelihood learning of bayesian networks for facial action recognition. Proceedings of the 10th European Conference on Computer Vision, Marseille, France."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/10\/1283\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:07:45Z","timestamp":1760166465000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/10\/1283"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,30]]},"references-count":34,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,10]]}},"alternative-id":["e23101283"],"URL":"https:\/\/doi.org\/10.3390\/e23101283","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2021,9,30]]}}}