The Sunn [Eurygaster spp. (Hemiptera: Scutelleridae)] damage in wheat and the effect of seed amount used on yield by fuzzy logic method

Sunn pest (Eurygaster spp.) is a highly harmful insect species for Wheatgrass. Especially with the emphasis it makes in herbal products, it causes the wheat to lose both its bread and pasta qualities. This study presents an example of a model that approximates the wheat yield in the irrigated field in Batman province according to the criteria selected through fuzzy logic. In the modelling, firstly the parameters affecting the wheat yield were determined and input and output variables were defined. In the next step, the membership functions are determined by doing the blurring process. The triangular membership function has been selected for the membership function. Later, fuzzy rule base was determined and fuzzy rules were formed. In the next step, the fuzzy inference mechanism was created. For the rinsing process, the "weight average" method was used. In the study, fuzzy logic toolbox was used in Matlab and the results obtained were seen to be useful in determining wheat yield per decare.

Devising a technology for managing outsourcing IT-projects with the application of fuzzy logic

An outsourcing IT project management model has been developed. The proposed model features taking into account the specifics of project management processes at outsourcing IT companies in terms of the uncertainty of the external and internal environment of their operation. The model is based on the stage-gate project management framework with fuzzy logic tools. The proposed modification of the fuzzy inference mechanism makes it possible to refuse to save the intermediate results which reduce the load on the database and create the possibility of using semantic networks. The technology of expert consultations was demonstrated by the example of decision-making regarding the assessment of the current status of the IT projects accepted by the outsourcing company for development. Dynamic nature and cyclical management of the portfolio of IT projects involves constant monitoring of the results of implementation with an appropriate regular portfolio reforming. The model was developed to improve the efficiency of the software development sub-process and minimize the negative consequences of financial dependence on the customer. The application software developed on the basis of the model of management of outsourcing IT projects and modification of the fuzzy inference mechanism has found practical application and was implemented in the computational practice of HYS Enterprise B.V. outsourcing IT company. Testing of the program shell has shown positive results in the course of solving the tasks peculiar to concrete stages of IT project management. The proposed structure and composition of the fuzzy knowledgebase of the expert shell are quite typical in terms of IT outsourcing problems. It is expedient to use the developed model at outsourcing IT companies in the process of project portfolio management

Artificial Neural Network based COVID-19 Suspected Area Identification

This paper deals with the symptoms based COVID-19 suspected area identification using an artificial neural network by which a country or region can be divided into red, yellow, and green zone representing the highly infected area, moderate infected area, and controlled or low infected area, respectively. At first, an online survey of twenty (20) patients was conducted based on the nine (09) major symptoms of COVID-19. Then, a model based on the fuzzy logic system was designed consisting of COVID-19 symptoms identification, fuzzification, rule evaluation, fuzzy inference mechanism, etc. for getting the data sets to be trained in neural networks. For different combinations of 09 symptoms, different rules were generated and evaluated for possible recommendations. Based on different rules, three possible outputs representing high infection probability, medium infection probability, and low infection probability were obtained using the Mamdani inference mechanism. These outputs were termed as red, yellow, and green zone separated by the crisp value of +1, 0, -1, respectively, and considered as target data to be trained in neural networks.

A Fuzzy Logic Based Synonym Resolution Approach for Automated Information Retrieval

Precise semantic similarity measurement between words is vital from the viewpoint of many automated applications in the areas of word sense disambiguation, machine translation, information retrieval and data clustering, etc. Rapid growth of the automated resources and their diversified novel applications has further reinforced this requirement. However, accurate measurement of semantic similarity is a daunting task due to inherent ambiguities of the natural language, spread of web documents across various domains, localities and dialects. All these issues render to the inadequacy of the manually maintained semantic similarity resources (i.e. dictionaries). This article uses context sets of the words under consideration in multiple corpora to compute semantic similarity and provides credible and verifiable semantic similarity results directly usable for automated applications in the intelligent manner using fuzzy inference mechanism. It can also be used to strengthen the existing lexical resources by augmenting the context set and properly defined extent of semantic similarity.

Analysis of Pedagogy of Teacher's Capability to Transform Knowledge Into Practice Using Fuzzy Logic

Current literature and common practices suggest that there is no consistent method available to analyze the performance of teachers. Due to its inherent vagueness and uncertainty, this article analyzes the effectiveness of a teacher depending upon various factors using fuzzy logic. It explains various parameters influencing professional, interpersonal and personal behavior of teachers. Secondly, a fuzzy inference mechanism is developed to decide the possible quality of teachers. The article concludes by observing that the proposed fuzzy logic based system is consistent with that judged by the experts and can be used to predict the possible quality of teachers.

Developing a neuro–fuzzy system to classify drainage sub-basins according to erosion processes on the Island of Lefkas, Greece

In this paper we attempt to classify drainage sub-basins according to their erosion risk. We have adopted a multistep procedure to face this problem. The input variables were introduced into a GIS – platform. These variables were the vulnerability of the surface rocks to erosion, topographic variations, vegetation cover, land use and drainage basin characteristics. We constructed a fuzzy inference mechanism to pre-process the input variables. Next we used neural–network technology to process the input variables. The system was trained to ‘learn’ and classify the input data. The output of this procedure was a classification of the sub-drainage basins related to their risk of erosion. This neuro–fuzzy system was applied to the island of Lefkas (Greece).

A Fuzzy Logic Based Synonym Resolution Approach for Automated Information Retrieval

Precise semantic similarity measurement between words is vital from the viewpoint of many automated applications in the areas of word sense disambiguation, machine translation, information retrieval and data clustering, etc. Rapid growth of the automated resources and their diversified novel applications has further reinforced this requirement. However, accurate measurement of semantic similarity is a daunting task due to inherent ambiguities of the natural language, spread of web documents across various domains, localities and dialects. All these issues render to the inadequacy of the manually maintained semantic similarity resources (i.e. dictionaries). This article uses context sets of the words under consideration in multiple corpora to compute semantic similarity and provides credible and verifiable semantic similarity results directly usable for automated applications in the intelligent manner using fuzzy inference mechanism. It can also be used to strengthen the existing lexical resources by augmenting the context set and properly defined extent of semantic similarity.