Family education as a support to families where children are with special needs is mentioned in family politics statements. Unfortunately, family education problems in rural areas characterise present day situation in Latvia. Professionals with less specific knowledge essential to deal with special needs satisfaction is a reality in rural areas in Latvia. It is vital to advance family autonomy, develop an opportunity to deal with consequences that disabilities cause and, improve environmental conditions for children with special needs. The aim of this article is to fortify necessity of family education as a partnership comprehension development to children with special needs in rural area. The investigation was carried out in National Rehabilitation centre ”Vaivari” in April 2012, by involving families with children with special needs. Analysis of scientific resources has been done; survey and statistical analysis of data were carried out, by using non-parametric method - Mann Whitney U test. During the research, the main family education comprehension aspects to families living in rural or city area and having children with special needs are identified. The advantages in special needs satisfaction context in rural areas and city environment are analysed. Measurements of respondent attitude to innovative family education e-solutions are made. Objectively and subjectively determined social isolation risk of families having children with special needs in rural area show the necessity to use family resources related to consequences that disabilities create. It is necessary to develop ways to use modern technological opportunities, provide appropriate family education and partnership with professionals.

Deep learning algorithms are becoming default solution for application in business processes where recognition, identification and automated learning are involved. For human identification, analysis of various features can be applied. Face feature analysis is most popular method for identification of person in various stages of life, including children and infants. The aim of this research was to propose deep learning solution for long-term identification of children in educational institutions. Previously proposed conceptual model for long-term re-identification was enhanced. The enhancements include processing of unexpected persons’ scenarios, knowledge base improvements based on results of supervised and unsupervised learning, implementation of video surveillance zones within educational institutions and object tracking results’ data chaining between multiple logical processes. Object tracking results are the solution we found for long-term identification realization.