Grading Multiple Choice Questions Based On Similarity Measure (Published)
Recent findings show the poor performances of students in Multiple Choice Questions (MCQ) examinations. This could be attributed to the administration of questions on application of knowledge rather than on fundamental of knowledge. Candidates doing these examinations at times choose options that are close to the actual answer but get zero (0) as the reward. The objective of developing a system that rewards a candidate based on the approximation of an option chosen not on the exactness of the option to the answer was therefore formulated in this study. 500 MCQs with their model answers, students’ answers and scores obtained from two universities in Nigeria were collected. Jaro similarity measure was used to compute the degree of similarity between the model answers and the student answers. Results of the experiment show an average deviation of 13.3 marks. The adoption of this method of grading would be very beneficial in evaluating learners on e-learning platforms. The result is encouraging but could be improved upon with semantic similarity measure hybridized with string similarity.
Keywords: E-learning, Examinations, Fuzzy Logic, Jaro, MCQ, approximation, average deviation, exactness, semantic, similarity measure
Steam Package Boiler Expert System for Control and Maintenance of Fertilizer Plants using Rule-Base Fuzzy Logic (Published)
Generally, expert systems have been found very useful branch of artificial intelligence that makes extensive use of specialized knowledge to solve complex problems and even in fertilizer plants it has been deployed in handling operations in critical sections, such as material handling systems, online leak detection systems, granulation, air compressor among others. This paper presents research work for steam package boiler expert system for control and maintenance of fertilizer plants using rule-base fuzzy logic hybrid system, which has not been benefited much from expert system. The system handles cause of boiler failures in terms of controlling and maintaining the functional chemical components of the boiler drum and feed water parameters. validation on the system consistency, correctness, and its precision with six (6) steam package boiler parameters test value cases was conducted involving fourteen (14) fertilizer plant boiler domain partitioners. The boiler drum and feed water qualities with less or higher test value worst-cases validates the boiler system, showing each of the parameter’s bar turns red, as displayed on the boiler’s panel, while on test value best-cases, validates the system, displaying green on the boiler’s panel as users entered the right value of parameters per the design specification. We discovered that from 1 to 10 minutes run time for auto system run gives 10.8% errors as compared from 1 to 10 minutes time interval on manual system run that gives 80.2% error, this results to less effort in user interface application usage on auto operations better than manual. The expert system prevents damaged and malfunctioning as control the alkalinity, prevent scaling, both mechanical & chemical corrosion, forming, correct pH values and then the conductivity which deals with the feed boiler water and monitored the level in the boiler drum using the industry measurement parameters (pressure, temperature, level, and flow).
Keywords: Expert System, Fuzzy Logic, dynamic simulation, rule-base system, steam package boilers
Application of Expert System for Diagnosing Medical Conditions: A Methodological Review (Published)
Naturally, human diseases should be treated on time; otherwise the patients might die if there is delay in attending to such patient or scarcity of medical practitioners’ or experts. Several attempts have been made through studies to design and built software based medical expert systems for probing and prognosis of several medical conditions using artificial and non-artificial based approaches for patients and medical facilities. This paper represents a comprehensive methodological review of existing medical expert systems used for diagnosis of various diseases based on the increasing demand of expert systems to support the human experts. The study provides a concise evaluation of the various techniques used such as rule-based, fuzzy, artificial neural networks and intelligent hybrid models. The rule-based techniques is not too efficient based on its inability to learn and require powerful search strategies for its knowledge-base; while the fuzzy or ANN models are less efficient when compared to the hybrid models that can give a more accurate results.
Keywords: AI, ANN, Expert System, Fuzzy Logic, Intelligent hybrid model, Rule-based
A Comparative Analysis of Multi-Criteria Road Network (Published)
Travel Optimization is a method to find the best route to be followed for a journey between two points. This optimization can be based on factors one considers important while traveling. The work presented deals with the design of a multi-criteria based traffic network evaluation technique, using a variety of methods to calculate the cost of the feasible set of solutions, and then to decide which path is most desirable for a given requirement domain. Subsequently, various forms of the desired results e.g. the global depths of all the nodes in a given road network are extracted and presented; and compared by implementing the different methods of cost calculation: a weight based method and a Fuzzy Logic based mechanism. Both methods used are explained and compared through a case study to show that the aims are met in a useful way. Also among the aims of this research is to work out some way of solving the multi objective optimization problem of finding the shortest path using some optimization methods for given multiple objectives. The phenomenon of multiple criterions tells about the nature of the problem where increasing one or more objectives reduce effect of the rest of the criteria or criterions, which effectively, makes the solution more complex but comes out with better results and provides more knowledge of the problem itself.
Keywords: Fuzzy Logic, Multi-Criteria Optimization, Pareto Optimization, Road Network Analysis, Travel Optimization
Metric Genetic-Fuzzy Based Customer Relationship Management Health Model (Published)
Customer Relationship Management (CRM) is a model for managing a company’s interactions with current and future customers. Most of the implemented CRM approaches are subjective in nature, in addition to the serious need to separate feelings of satisfaction or dissatisfaction with the services delivery. Metric Genetic-Fuzzy Based Customer Relationship Management Health Model (MGFBCRMHM) was initiated for these reasons. Unified Modeling Language was utilized for modeling the software system, depicting clearly the interaction between various components and the dynamic aspect of the system. The simulation results utilizing Matrix Laboratory (MATLAB) was satisfactory. This paper demonstrates the practical application of metric based soft computing techniques in the health sector in determining patient’s satisfaction.
Keywords: CRM, Fuzzy Logic, Genetic Algorithm