No abstract

With the advancement of technology and the limitations of the conventional healthcare system, an improvised framework for healthcare system is needed. This paper presents another cloud based skeleton which relates key segments of any healthcare framework which are patient, doctor, symptom and disease. The paper fundamentally concentrates on how these parts are inter-related and how we can infer suitable data from them. As an implementation, it shows the basic healthcare analyser interface which takes data as input and mines the data by using some of the data mining techniques like clustering. It is convenient for government associations which point at investigating restorative issues and to enhance health conditions of India.

<abstract> <p>In the livestock industry, wireless sensor networks (WSNs) play a significant role in monitoring many fauna health statuses and behaviors. Energy preservation in WSNs is considered one of the critical, complicated tasks since the sensors are coupled to constrained resources. Therefore, the clustering approach has proved its efficacy in preserving energy in WSNs. In recent studies, various clustering approaches have been introduced that use optimization techniques to improve the network lifespan by decreasing energy depletion. Yet, they take longer to converge and choose the optimal cluster heads in the network. In addition, the energy is exhausted quickly in the network. This paper introduces a novel optimization technique, i.e., an artificial rabbits optimization algorithm-based energy efficient cluster formation (EECHS-ARO) approach in a WSN, to extend the network lifetime by minimizing the energy consumption rate. The EECHS-ARO technique balances the search process in terms of enriched exploration and exploitation while selecting the optimal cluster heads. The experimentation was carried out on a MATLAB 2021a platform with varying sensor nodes. The obtained results of EECHS-ARO are contrasted with other existing approaches via teaching–learning based optimization algorithm (TLBO), ant lion optimizer (ALO) and quasi oppositional butterfly optimization algorithm (QOBOA). The proposed EECHS-ARO enriches the network lifespan by ~15% and improves the packet delivery ratio by ~5%.</p> </abstract>

No abstract

No abstract