Scholarlink

This paper presents a novel swarm-based algorithm for the intelligent manoeuvring of robots within poultry farms, aiming to enhance livestock well-being monitoring for smart livestock-rearing practices. The existing practices in environmental monitoring include the use of ceiling-mounted sensors. This has shown an inaccuracy in data due to the difference in biomarker data at ceiling and ground levels. The proposed algorithm utilizes the principles of the Firefly algorithm to produce a viable navigation system for the robot swarm. The fitness function of the algorithm is determined using sensor values received from MQ-135, MQ-137, and DHT-11 sensors for carbon dioxide, ammonia, temperature, and humidity. Further scope for this system is also discussed within the conclusion of this paper. Experimental analysis was conducted to deduce the optimal parameters for defining the fitness function for the swarm algorithm. The proposed system successfully maps and monitors the environment within a simulated setting, demonstrating its effectiveness in addressing the challenges of traditional environmental monitoring techniques.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

On the Analysis of Swarm Robotics in Sensor-Based Environmental Monitoring for Sustainable Poultry Farming

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Karen Jane Dsouza,
  • Senthil Arumugam Muthukumaraswamy,
  • Girish Balasubramanian

摘要

This paper presents a novel swarm-based algorithm for the intelligent manoeuvring of robots within poultry farms, aiming to enhance livestock well-being monitoring for smart livestock-rearing practices. The existing practices in environmental monitoring include the use of ceiling-mounted sensors. This has shown an inaccuracy in data due to the difference in biomarker data at ceiling and ground levels. The proposed algorithm utilizes the principles of the Firefly algorithm to produce a viable navigation system for the robot swarm. The fitness function of the algorithm is determined using sensor values received from MQ-135, MQ-137, and DHT-11 sensors for carbon dioxide, ammonia, temperature, and humidity. Further scope for this system is also discussed within the conclusion of this paper. Experimental analysis was conducted to deduce the optimal parameters for defining the fitness function for the swarm algorithm. The proposed system successfully maps and monitors the environment within a simulated setting, demonstrating its effectiveness in addressing the challenges of traditional environmental monitoring techniques.