Modeling a Diet Planner for Livestock Using Fuzzy Logic Approach and Ontology Model

Abstract

Abstract. As a known fact, the basic ontology is not sufficient to handle the vague data to derive a good semantic service, as the modelled ontology has the set of entities with the defined relationship. To overcome this, the fuzzy logic is used to handle the uncertain data, to improvise the performance. This paper proposes the fuzzy type ontology with the knowledge representation in the process of diet planner for the livestock. As the nutrition requirement varies for cow with the age, BMI, and health, the diet for each type of cow differs, in respect to the food served on each day, the fuzzy technique is used to decide the amount of food needs to be served for the livestock. This papers shows the effective way to drawn the perfect diet plan for the livestock.

Towards a balanced nutrition system using fuzzy logic in livestock

“…The input variable, Health, is divided into "Unhealthy", "Health" and "Veryhealthy". Similarly, the Weight is divided into "Underweight", "Normal" and "Overweight" as shown in Table 1, referred from our work [12].…”

“…Using Mamdani inference method in the MATLAB fuzzy logic system, the simulated results are obtained for the before mentioned rule are shown in the figure 3, which is referred from our work [12]. In this simulation, the weight is 1300 lbs with the CowStage, that represents the age of the cow, 4 years, the health percentage is 0.4, and the PregnantPhase is 54, resulting in the output of 4.02 indicating "Normal".…”

“…In this simulation, the weight is 1300 lbs with the CowStage, that represents the age of the cow, 4 years, the health percentage is 0.4, and the PregnantPhase is 54, resulting in the output of 4.02 indicating "Normal". [12] If the nutrition requirement is Low, the amount of food given is reduced with respect to the TDN of the food. Let us consider the food given to the cow to be Hay.…”

Interval Type-2 Fuzzy Application for Diet Journaling

“…(Safitri & Abadi, 2015) aims to help consumers buy more nutritious noodles, and similarly (Nakandala & Lau, 2013) aims to help shoppers get as much nutrient density as they can afford by evaluating foods with a fuzzy expert system, scoring each food on whether or not to purchase. It is found in (Sivamani, Kim, Shin, Park, & Cho, 2016) that fuzzy inference can help plan more cost-effective livestock diets, tailored to the attributes of each individual cow.…”