Fidèl Jiomekong Azanzi

Knowledge Extraction from Source Code Based on Hidden Markov Model: Application to EPICAM

Large software systems evolve rapidly and these evolutions are usually integrated directly into source code without updating the conceptual model. As a consequence, implementation platforms evolve faster than business logic. Thus, when extracting knowledge to enrich or build an ontology, business logic is not always a complete data source. To solve this problem, some authors have suggested to adopt an ontology learning approach in order to extract knowledge from the source code. In this paper, we show how to realize this task using Hidden Markov Models. experiments on EPICAM, a tuberculosis surveillance system shows the relevance of this approach.

2012Other

Data collection in a degraded network

Fidèl Jiomekong Azanzi, Laurent Broto, Daniel Hagimont, Suzy Temate, Maurice Tchuenté

An essential component in public administration (health systems management, municipality management, environmental protection, agriculture etc.) is the data collection service. Data collected concerns key information that can improve the living conditions of populations (epidemiological data, environmental data, weather data etc.). This collection is difficult in developing countries or in situations of crisis (notably natural disasters). Current solutions are inadequate, for they assume the availability of client terminals, the presence of outstanding (Internet) communication networks, or they provide a service based on a primitive communication via SMS and data furnishing through mobile phones which are prone to data entry errors. In this paper, we propose a compromise between these approaches. A dedicated language allows the definition of input masks with which are generated (i) HTML forms enabling a reliable entering of data from a computer (ii) in which formats of SMS messages have to be exchanged between the input terminal and the data processing server. The implementation of this approach is based on a Model-Driven Architecture (MDA) technology, and it has been applied to Health Information Systems (HIS).

View publication DOI

Fidèl Jiomekong Azanzi

Publication summary

Recurring keywords

Biography

Publications

2017

Knowledge Extraction from Source Code Based on Hidden Markov Model: Application to EPICAM

2012

Data collection in a degraded network

Additional information

Publication timeline

Co-authors

Other co-authors

Profiles & networks