Bernard Kamsu-Foguem

Mining association rules for the quality improvement of the production process

Academics and practitioners have a common interest in the continuing development of methods and computer applications that support or perform knowledge-intensive engineering tasks. Operations management dysfunctions and lost production time are problems of enormous magnitude that impact the performance and quality of industrial systems as well as their cost of production. Association rule mining is a data mining technique used to find out useful and invaluable information from huge databases. This work develops a better conceptual base for improving the application of association rule mining methods to extract knowledge on operations and information management. The emphasis of the paper is on the improvement of the operations processes. The application example details an industrial experiment in which association rule mining is used to analyze the manufacturing process of a fully integrated provider of drilling products. The study reports some new interesting results with data mining and knowledge discovery techniques applied to a drill production process. Experiments results on real-life data sets show that the proposed approach is useful in finding effective knowledge associated to dysfunctions causes.

Continuous improvement through knowledge-guided analysis in experience feedback

Continuous improvement in industrial processes is increasingly a key element of competitiveness for industrial systems. The management of experience feedback in this framework is designed to build, analyze and facilitate the knowledge sharing among problem solving practitioners of an organization in order to improve processes and products achievement. During Problem Solving Processes, the intellectual investment of experts is often considerable and the opportunities for expert knowledge exploitation are numerous: decision making, problem solving under uncertainty, and expert configuration. In this paper, our contribution relates to the structuring of a cognitive experience feedback framework, which allows a flexible exploitation of expert knowledge during Problem Solving Processes and a reuse such collected experience. To that purpose, the proposed approach uses the general principles of root cause analysis for identifying the root causes of problems or events, the conceptual graphs formalism for the semantic conceptualization of the domain vocabulary and the Transferable Belief Model for the fusion of information from different sources. The underlying formal reasoning mechanisms (logic-based semantics) in conceptual graphs enable intelligent information retrieval for the effective exploitation of lessons learned from past projects. An example will illustrate the application of the proposed approach of experience feedback processes formalization in the transport industry sector.

Conceptual graph-based knowledge representation for supporting reasoning in African traditional medicine

Although African patients use both conventional or modern and traditional healthcare simultaneously, it has been proven that 80% of people rely on African traditional medicine (ATM). ATM includes medical activities stemming from practices, customs and traditions which were integral to the distinctive African cultures. It is based mainly on the oral transfer of knowledge, with the risk of losing critical knowledge. Moreover, practices differ according to the regions and the availability of medicinal plants. Therefore, it is necessary to compile tacit, disseminated and complex knowledge from various Tradi-Practitioners (TP) in order to determine interesting patterns for treating a given disease. Knowledge engineering methods for traditional medicine are useful to model suitably complex information needs, formalize knowledge of domain experts and highlight the effective practices for their integration to conventional medicine. The work described in this paper presents an approach which addresses two issues. First it aims at proposing a formal representation model of ATM knowledge and practices to facilitate their sharing and reusing. Then, it aims at providing a visual reasoning mechanism for selecting best available procedures and medicinal plants to treat diseases. The approach is based on the use of the Delphi method for capturing knowledge from various experts which necessitate reaching a consensus. Conceptual graph formalism is used to model ATM knowledge with visual reasoning capabilities and processes. The nested conceptual graphs are used to visually express the semantic meaning of Computational Tree Logic (CTL) constructs that are useful for formal specification of temporal properties of ATM domain knowledge. Our approach presents the advantage of mitigating knowledge loss with conceptual development assistance to improve the quality of ATM care (medical diagnosis and therapeutics), but also patient safety (drug monitoring).

Knowledge-based support in Non-Destructive Testing for health monitoring of aircraft structures

Maintenance manuals include general methods and procedures for industrial maintenance and they contain information about principles of maintenance methods. Particularly, Non-Destructive Testing (NDT) methods are important for the detection of aeronautical defects and they can be used for various kinds of material and in different environments. Conventional non-destructive evaluation inspections are done at periodic maintenance checks. Usually, the list of tools used in a maintenance program is simply located in the introduction of manuals, without any precision as regards to their characteristics, except for a short description of the manufacturer and tasks in which they are employed. Improving the identification concepts of the maintenance tools is needed to manage the set of equipments and establish a system of equivalence: it is necessary to have a consistent maintenance conceptualization, flexible enough to fit all current equipment, but also all those likely to be added/used in the future. Our contribution is related to the formal specification of the system of functional equivalences that can facilitate the maintenance activities with means to determine whether a tool can be substituted for another by observing their key parameters in the identified characteristics. Reasoning mechanisms of conceptual graphs constitute the baseline elements to measure the fit or unfit between an equipment model and a maintenance activity model. Graph operations are used for processing answers to a query and this graph-based approach to the search method is in-line with the logical view of information retrieval. The methodology described supports knowledge formalization and capitalization of experienced NDT practitioners. As a result, it enables the selection of a NDT technique and outlines its capabilities with acceptable alternatives.

Graph-based reasoning in collaborative knowledge management for industrial maintenance

Capitalization and sharing of lessons learned play an essential role in managing the activities of industrial systems. This is particularly the case for the maintenance management, especially for distributed systems often associated with collaborative decision-making systems. Our contribution focuses on the formalization of the expert knowledge required for maintenance actors that will easily engage support tools to accomplish their missions in collaborative frameworks. To do this, we use the conceptual graphs formalism with their reasoning operations for the comparison and integration of several conceptual graph rules corresponding to different viewpoint of experts. The proposed approach is applied to a case study focusing on the maintenance management of a rotary machinery system.

Using conceptual graphs for clinical guidelines representation and knowledge visualization

The intrinsic complexity of the medical domain requires the building of some tools to assist the clinician and improve the patient’s health care. Clinical practice guidelines and protocols (CGPs) are documents with the aim of guiding decisions and criteria in specific areas of healthcare and they have been represented using several languages, but these are difficult to understand without a formal background. This paper uses conceptual graph formalism to represent CGPs. The originality here is the use of a graph-based approach in which reasoning is based on graph-theory operations to support sound logical reasoning in a visual manner. It allows users to have a maximal understanding and control over each step of the knowledge reasoning process in the CGPs exploitation. The application example concentrates on a protocol for the management of adult patients with hyperosmolar hyperglycemic state in the Intensive Care Unit.

Telemedicine framework using case-based reasoning with evidences

Telemedicine is the medical practice of information exchanged from one location to another through electronic communications to improve the delivery of health care services. This research article describes a telemedicine framework with knowledge engineering using taxonomic reasoning of ontology modeling and semantic similarity. In addition to being a precious support in the procedure of medical decision-making, this framework can be used to strengthen significant collaborations and traceability that are important for the development of official deployment of telemedicine applications. Adequate mechanisms for information management with traceability of the reasoning process are also essential in the fields of epidemiology and public health. In this paper we enrich the case-based reasoning process by taking into account former evidence-based knowledge. We use the regular four steps approach and implement an additional (iii) step: (i) establish diagnosis, (ii) retrieve treatment, (iii) apply evidence, (iv) adaptation, (v) retain. Each step is performed using tools from knowledge engineering and information processing (natural language processing, ontology, indexation, algorithm, etc.). The case representation is done by the taxonomy component of a medical ontology model. The proposed approach is illustrated with an example from the oncology domain. Medical ontology allows a good and efficient modeling of the patient and his treatment. We are pointing up the role of evidences and specialists opinions in effectiveness and safety of care.

Adverse drug reactions in some African herbal medicine: literature review and stakeholders' interview

Background In view of the large consumption of herbal medicine in Africa countries, it is likely that many adverse drugs reactions go unrecorded with either patients failing to present to health services, or no pharmacovigilance analysis being made, or the analysis not being reported centrally. This problem is of interest especially for those who are working in the general area of adverse drug reactions or stakeholders in the domain of herbal medicine for considering safety issues. Methods We are particularly interested in the way that the use of very well-known and highly valued plants is linked to the observation of adverse drug reactions in African countries. We investigated, through a literature review and using the Internet (with a semantic search strategy), some well-known or popular medicinal plants used in African herbal medicine (AHM). Other information on the properties related to use, and characteristics of medicinal plants was complemented by some interviews with stakeholders. Results Although substantial progress has been made in elucidating the mechanisms of action of many drugs, the pharmacological actions of many medicinal plants are generally not well understood. The results of a literature review suggest that the reported adverse drug reactions of herbal remedies are often due to a lack of understanding of their preparation and appropriate use. The results of stakeholders’ interviews suggest that there is a growing need to provide patients with correct information about the herbal medicines they consume. Conclusion An important aspect of herbal medicine is the correct, timely, and integrated communication of emerging data on risk as an essential part of pharmacovigilance, which could actually improve the health and safety of patients. This calls for improved collaboration between traditional practitioners and modern healthcare professionals, researchers, and drug regulatory authorities. In addition, there is a need for an adverse drug reaction reporting system to facilitate the collection, monitoring, and evaluation of adverse drug events.

Verifying a medical protocol with temporal graphs: The case of a nosocomial disease

OBJECTIVE Our contribution focuses on the implementation of a formal verification approach for medical protocols with graphical temporal reasoning paths to facilitate the understanding of verification steps. MATERIALS AND METHODS Formal medical guideline specifications and background knowledge are represented through conceptual graphs, and reasoning is based on graph homomorphism. These materials explain the underlying principles or rationale that guide the functioning of verifications. RESULTS An illustration of this proposal is made using a medical protocol defining guidelines for the monitoring and prevention of nosocomial infections. Such infections, which are acquired in the hospital, increase morbidity and mortality and add noticeably to economic burden. An evaluation of the use of the graphical verification found that this method aids in the improvement of both clinical knowledge and the quality of actions made. DISCUSSION As conceptual graphs, representations based on diagrams can be translated into computational tree logic. However, diagrams are much more natural and explicitly human, emphasizing a theoretical and practical consistency. CONCLUSION The proposed approach allows for the visual modeling of temporal reasoning and a formalization of knowledge that can assist in the diagnosis and treatment of nosocomial infections and some clinical problems. This is the first time that one emphasizes the temporal situation modeling in conceptual graphs. It will also deliver a formal verification method for clinical guideline analyses.

Modeling for effective collaboration in telemedicine

Requirements and modeling for supporting collaborative activities in telemedicine.Identification of types of exchanged data for information sharing in telemedicine.Functional specifications associated with achieving an effective telemedicine work.Semantic formalization to give good meaning and substance to shared information.Management of the acquired knowledge through the capitalization of the reasoning. Telemedicine is a remote medical practice, which utilizes advanced telecommunications and information technologies for the delivery of healthcare and the exchange of heath information across distances. The development of telemedicine has significantly changed the medical collaborative decision making and doctor-patient relationships and has an impact on the responsibilities of physicians to patients and how to treat them. Moreover, in the chain of medical care information exchanged between a requesting physician and medical expert should assist in decision making. In this regard, we propose means for the formalization of exchanges, which is very important because it facilitates a transparent and traceable understanding of the remote process. So, we engage knowledge-based modeling for supporting collaborative activities in telemedicine. This includes the engagement of formal ontologies to ensure structuration of terminology and identification across all entities in a domain so that multiple sources of data can be aggregated through comparable reference terms. The provided benefit is the generated support for logic-based intelligent applications that are able to perform complex reasoning tasks such as checking for errors and inconsistencies and deriving logical inferences.