Query-focused multi-document text summarization using fuzzy inference

The present paper proposes a fuzzy inference system for query-focused multi-document text summarization (MTS). The overall scheme is based on Mamdani Inferencing scheme which helps in designing Fuzzy Rule base for inferencing about the decision variable from a set of antecedent variables. The antecedent variables chosen for the task are from linguistic and positional heuristics, and similarity of the documents with the user-defined query. The decision variable is the rank of the sentences as decided by the rules. The final summary is generated by solving an Integer Linear Programming problem. For abstraction coreference resolution is applied on the input sentences in the pre-processing step. Although designed on the basis of a small set of antecedent variables the results are very promising.

Fuzzy-based Adaptive Framework for Module Advising Expert System

In the enrolment process, selecting the right module and lecturer is very important for students. The wrong choice may put them in a situation where they may fail the module. This could lead to a more complicated situation, such as receiving an academic warning, being de-graded, as well as withdrawn from the program or the university. However, module advising is time-consuming and requires knowledge of the university legislation, program requirements, modules available, lecturers, modules, and the student's case. Therefore, the creation of effective and efficient systems and tools to support the process is highly needed. This paper discusses the development of a fuzzy-based framework for the expert recommender system for module advising. The proposed framework builds three main spaces which are: student-space (SS), module-space (MS), and lecturer-space (LS). These spaces are used to estimate the risk level associated with each student, module, and lecturer. The framework then associates each abnormal student case in the students’ grade history with the estimated risk level in the SS, MS, and LS involved in that particular case. The fuzzy-based association-rule learning is then used to extract the dominant rules that classify the consequent situation for each eligible module if it is to be taken by the student for a specific semester. The proposed framework was developed and tested using real-life university data which included student enrollment records and student grade records. A five-fold cross-validation process was used for testing and validating the classifying accuracy of the fuzzy rule base. The fuzzy rule base achieved a 92% accuracy level in classifying the risk level for enrolling on a specific module for a specific student case. However, the average classifying accuracy achieved was 89.2% which is acceptable for this problem domain as it involves human behavior modeling and decision making.

Prediction of Health Risk Potential Using Fuzzy Rule Base System for Indoor Work Environmental Condition in Dyeing and Printing House

The physical work environment in any industry is dynamic and unpredictable. It highly influencing to the health, comfort and well being of the occupants. Work environmental condition can be evaluated by measuring four basic comfort parameters, which include thermal comfort, acoustic comfort, visual comfort and air change inside the working area. These parameters are the major contributing factors to the health of workers. Usage of heat and water in the different processes of textile dyeing and printing industry make the work environment hot and humid. Due to high thermal stress a wide range of disease and complications has been observed from mild disorder to heatstroke. Also, the high level of noise and the poor lighting condition has been impacting on the stress, absenteeism, turnover, production and output quality in the industry. Improper ventilation in the working area will affect the dispersion and dilution of the pollutants generated due to the processes. The parameters considered for evaluating comfort levels include wet bulb globe temperature index, illumination, noise and air changes in this study. Fuzzy rule base system approach had been used to predict worker’s health risk associated due to the impact of the work environment condition. The modeling process has been carried out with the help of MATLAB (R2014a) fuzzy tool box. Triangular membership function had been used for the input parameters. Linguistic variables were finalized by the expert opinion. Total 144 fuzzy rules had been developed based on the linguistic variable. Output obtain is in the terms of crisp value [0,1] is divided into four linguistic term low, moderate, high and very high. The study reveals that work environment condition in the textile dyeing and printing mills at various sections of the industry fall in the category of a high and very high risk condition because of prevailing poor work environmental condition at various locations. Thus, the workers working in these sections having very high potential to get the diseases related to a hot and humid environment.