Scholarlink

<p>Road accidents, rangeland, and a lack of data for herd management are some of the issues that face camel breeding in Iran. We created SARBANYAR, a web-based and mobile-integrated system for remote rangeland assessment, data recording, and camel tracking. SARBANYAR reduced the risk of accidents through SMS alerts, enabled real-time GPS monitoring, and offered a machine learning-based weight estimation tool (Partial Nonlinear Least Squares Support Vector Machine (PNLSVM), accuracy 94.9%, RMSE 18.5&#xa0;kg) in trials involving 15 herds. Using the Mann–Kendall test, analysis of soil adjusted vegetation index (SAVI) trends from 2016 to 2023 revealed no significant changes in SAVI across 15 studied herds in Yazd, South Khorasan, and Kerman provinces. It identified soil moisture, region, and grazing month as key factors influencing SAVI, while camel grazing had a comparatively minimal direct impact on SAVI. The training platform had a high user engagement rate, and deploying the trackers was affordable. SARBANYAR demonstrates how ICT can enhance camel husbandry in arid areas and provides a long-term solution for increasing output and ensuring the well-being of camels, thereby paving the way for future research and development.</p>

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

A novel ICT-based system for camel husbandry for online monitoring, phenotyping and rangeland assessment

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月23日

查看全文
  • Morteza Bitaraf Sani,
  • Yousef Hasheminejhad,
  • Nader Asadzadeh,
  • Omid Karimi,
  • Mahdi Khojastehkey,
  • Mohammad Abolghasemi,
  • Mohammad Vahid Kimiaeitalab,
  • Mohammad Hossein Banabazi

摘要

Road accidents, rangeland, and a lack of data for herd management are some of the issues that face camel breeding in Iran. We created SARBANYAR, a web-based and mobile-integrated system for remote rangeland assessment, data recording, and camel tracking. SARBANYAR reduced the risk of accidents through SMS alerts, enabled real-time GPS monitoring, and offered a machine learning-based weight estimation tool (Partial Nonlinear Least Squares Support Vector Machine (PNLSVM), accuracy 94.9%, RMSE 18.5 kg) in trials involving 15 herds. Using the Mann–Kendall test, analysis of soil adjusted vegetation index (SAVI) trends from 2016 to 2023 revealed no significant changes in SAVI across 15 studied herds in Yazd, South Khorasan, and Kerman provinces. It identified soil moisture, region, and grazing month as key factors influencing SAVI, while camel grazing had a comparatively minimal direct impact on SAVI. The training platform had a high user engagement rate, and deploying the trackers was affordable. SARBANYAR demonstrates how ICT can enhance camel husbandry in arid areas and provides a long-term solution for increasing output and ensuring the well-being of camels, thereby paving the way for future research and development.