Quasi Algorithm Based Model for Intelligent Zoonotic Livestock Disease Diagnosis

Weaknesses in veterinary surveillance systems have been highlighted during recent outbreaks of infectious diseases such as Rift Valley fever and Highly Pathogenic Avian Influenza. Conventional passive surveillance has proven largely ineffective due to poor capacity and compliance, and many countries are not able to sustain active surveillance activities. As the result, public veterinary services and the commercial livestock sector are unable to detect and respond in a timely fashion to outbreaks of new disease threats, nor to manage successfully the control of trans-boundary diseases, many of which remain endemic. This situation not only compromises the development of livestock trade, but also creates a continuing threat to human public health since the majority of emerging infectious diseases are zoonotic, shared by animals and humans. Strategies are needed to ensure that surveillance systems can meet the challenges posed by emerging infectious diseases, while recognizing the context of resource limitations. Tools and incentives that encourage the full participation of both public and private actors are therefore critical. Among the many machine learning methods the learning component will be implemented on the premise of the Algorithm Quasi. The algorithm is designed to generate generalization or induction from very complex problems, where data would be separated and general rules would be created from the separation. This study will establish the introduction of an intelligent system that will be used in diagnosis of zoonotic diseases among livestock