检索结果-南通市图书馆

Grow-light smart monitoring system leveraging lightweight deep learning for plant disease classification

Artificial Intelligence in Agriculture 2024年第2期12卷 44-56页

作者： William Macdonald yuksel asli sari Majid Pahlevani Department of Electrical&Computer Engineering Queen's UniversityKingstonON K7L 3N6Canada The Robert M.Buchan Department of Mining Queen's UniversityKingstonON K7L 3N6Canada

This work focuses on a novel lightweight machine learning approach to the task of plant disease classification,posing as a core component of a larger grow-light smart monitoring *** the extent of our knowledge,this work is the first to implement lightweight convolutional neural network architectures leveraging down-scaled versions of inception blocks,residual connections,and dense residual connections applied without pre-training to the PlantVillage *** novel contributions of this work include the proposal of a smart monitor-ing framework outline;responsible for detection and classification of ailments via the devised lightweight net-works as well as interfacing with LED grow-light fixtures to optimize environmental parameters and lighting control for the growth of plants in a greenhouse *** adaptation of dense residual connections achieved the best balance of minimizing model parameters and maximizing performance metrics with accuracy,precision,recall,and F1-scores of 96.75%,97.62%,97.59%,and 97.58%respectively,while consisting of only 228,479 model *** results are further compared against various full-scale state-of-the-art model architectures trained on the PlantVillage dataset,of which the proposed down-scaled lightweight models were capable of performing equally to,if not better than many large-scale counterparts with drastically less com-putational requirements.

关键词： Plant disease classification Smart monitoring Deep learning Residual connections Inception Dense residual connections

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A landfill based approach to surface mine design

引用

Journal of Central South University 2018年第1期25卷 159-168页

作者： yuksel asli sari Mustafa Kumral Department of Mining and Materials Engineering McGill University

Surface mining operations extract a large quantity of waste material,which is generally disposed into a dump *** waste can cause a series of environmental problems ranging from landscape deterioration to acidic water generation and water ***,mine waste management is a significant task in mining *** known,in strip mining,the overburden is not transported to waste dumps but disposed directly into adjacent strip which was mined *** concept can be adapted for mine planning of relatively horizontal deposits through a mixed integer programming(MIP)*** main idea behind this work is that,in one pit,production voids created in early year of mining are used for waste landfilling in late years of *** other words,in addition to external dumping,a landfilling option within the same pit is proposed for mine design *** problem is formulated as maximization of the net present value(NPV)of the mining project under the constraints of access,landfill waste handling,mining and processing capacities.A case study using a data set was carried out to see the performance of the proposed *** findings showed that this approach could be used in waste management incorporating a landfilling option into mine *** a result,material handling costs decrease,and environmental compliance increases due to less external waste quantity.

关键词： mine waste management landfill mine design mineral industries mine optimization

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：