首页> 外文期刊>Current Science: A Fortnightly Journal of Research >Identification of Indian butterflies and moths with deep convolutional neural networks
【24h】

Identification of Indian butterflies and moths with deep convolutional neural networks

机译:鉴定深卷积神经网络的印度蝴蝶和飞蛾

获取原文
获取原文并翻译 | 示例
           

摘要

This paper reports our efforts to use artificial intelligence based on deep convolutional neural network (CNN) as a tool to identify Indian butterflies and moths. We compiled a dataset of over 170,000 images for 800 Indian butterfly species and 500 Indian moth species from diverse sources. We adopted the EfficientNet-B6 architecture for our CNN model, with about 44 million learnable parameters. We trained an ensemble of 5 such models on different subsets of the images in our data, employing artificial image augmentation techniques and transfer learning. This ensemble achieved a balanced top-1 accuracy of 86.5%, top-3 accuracy of 94.7%, and top-5 accuracy of 96.4% on the 1300 species, and a mean F-1 score of 0.867. Thus, our efforts demonstrate artificial intelligence can be effectively used for identifying these biological species that would substantially enhance the work efficiency of field level biologists in several spheres of investigations.
机译:本文报道了我们努力,基于深度卷积神经网络(CNN)作为识别印度蝴蝶和飞蛾的工具。 我们编制了800多种图像的数据集,可获得来自不同来源的500种印度蝴蝶种和500种印度蛾类。 我们为我们的CNN模型采用了高效的网络B6架构,具有约4400万个可读的参数。 我们在我们的数据中培训了5种这些模型的各种模型,在我们的数据中,采用人工映像增强技术和转移学习。 该集合达到了86.5%的平衡前1个精度,高度为94.7%,最高5种精度为1300种96.4%,平均f-1分数为0.867。 因此,我们的努力展示了人工智能,可以有效地用于识别这些生物物种,这将大大提高现场水平生物学家在几个调查领域的工作效率。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号