Machine Learning Based Classification Models in Smart Farming

Adhitya, Yudhi

WEKO3

lat lon distance

[[sub_check.contents]]

[[sub_radio.contents]]

Field does not validate

[[sub_attr.contents]]　

インデックスツリー

アイテム

スマート農業における機械学習に基づく分類モデル

https://doi.org/10.18997/0002000039

名前 / ファイル	ライセンス	アクション
jou_k_385.pdf (1.7 MB)

アイテムタイプ

学位論文 = Thesis or Dissertation(1)

公開日

2023-08-07

資源タイプ

資源タイプ識別子

http://purl.org/coar/resource_type/c_db06

資源タイプ

doctoral thesis

タイトル

Machine Learning Based Classification Models in Smart Farming

言語

タイトル

スマート農業における機械学習に基づく分類モデル

言語

eng

著者

Adhitya, Yudhi

抄録

内容記述タイプ

Abstract

内容記述

The development of information systems and technology, referred to as Machine Learning, has numerous applications across various industries. One application is within Smart Farming, an agricultural concept based on precision agriculture. The application utilizes platforms connected to technological automation devices. Big data management, Machine Learning, Artificial Intelligence (AI), and the Internet of Things (IoT) facilitate data processing for optimizing the quality and quantity of production to maximize farming methods, agriculture technologies, and human resources. Data obtained from farming locations will be beneficial if presented in the proper format at the appropriate time. The direction for Machine Learning (ML) implementation techniques that operate on simple IoT devices and accomplish simple processing on-site, which enable information to flow to and from remote and agricultural farming sites, has become a fundamental requirement.
This dissertation proposes two approaches to implementing Machine Learning (ML) techniques within IoT communication schemes for practical, increased precision, solving real-world problems, improving farming operating efficiency, and providing robust solutions. With consideration of energy-efficient, the number of the evaluated dataset, time calculation, and computational performance.
The first approach is implementing a feature classification framework focusing on the isolated groups of objects for agricultural products. On digital images of cocoa beans as a farmed product, we have demonstrated a method of textural feature research. In terms of feature extraction, the method contrasts the Gray Level Co-occurrence Matrix (GLCM) cooccurrence matrix features with the Convolutional Neural Network (CNN) method. Moreover, we used a series of classifiers for complete assessment and classifications in order to produce an appropriate performance evaluation. According to our findings, adopting GLCM texture feature extraction instead of CNN feature extraction from the conclusive classification can generate more reliable results.
The second approach is motion analysis. We investigate the validation and simulation dataset to determine whether accidents occur to farmers. We evaluate a quaternion representing 3D rotation as an input feature on farmers’ working positions. Moreover, it is analyzed employing an algorithm inspired by the biological model called Hierarchical Temporal Memory (HTM) classifier. We combine the data collected with previous data and train machine learning models to identify patterns to predict farmers’ conditions in the remote working environment. Employing a managing time-series dataset constrained that applied in the real-world accelerometer and gyroscope dataset performs well in practice in terms of accuracy.
Our findings from implementing a smart farming scheme incorporating simple classifier application and motion analysis within agricultural areas are promising solutions as an integrated approach, efficient, cost-effective, and fast-deployment technologies which improve accessibility. The computational framework and statistical result from the classifier application verify that our proposed classifier application method is feasible and effective in resolving the problem constraint in an acceptable dataset and deployed in the actual remote farming environment for the optimal solution. It also helped facilitate the usage of modern IoT technologies among farmers. It also encouraged communication among intermediary organizations working remotely and in agriculture, providing sustainable, reliable, and affordable connectivity. Furthermore, increasing the food supply chain’s security opens up new opportunities for the communities and improves farmer quality of life.

内容記述タイプ

TableOfContents

内容記述

備考

内容記述タイプ

Other

内容記述

九州工業大学博士学位論文学位記番号：情工博甲第385号学位授与年月日：令和5年6月30日

キーワード

主題Scheme

Other

主題

Machine Learning

キーワード

主題Scheme

Other

主題

Classification Models

キーワード

主題Scheme

Other

主題

Feature Classification

キーワード

主題Scheme

Other

主題

Temporal Classification

キーワード

主題Scheme

Other

主題

IoT Schemes

キーワード

主題Scheme

Other

主題

Smart Farming

学位授与番号

甲第385号

学位名

博士（情報工学）

学位授与年月日

2023-06-30

学位授与機関

学位授与機関識別子Scheme

kakenhi

学位授与機関識別子

17104

学位授与機関名

九州工業大学

学位授与年度

内容記述タイプ

Other

内容記述

令和5年度

出版タイプ

VoR

出版タイプResource

http://purl.org/coar/version/c_970fb48d4fbd8a85

アクセス権

open access

アクセス権URI

http://purl.org/coar/access_right/c_abf2

ID登録

10.18997/0002000039

ID登録タイプ

JaLC

戻る

views

See details

	Views

Versions

Ver.1

2023-08-07 05:59:19.752361

Show All versions

Cite as

Other

エクスポート

OAI-PMH

JPCOAR 2.0
JPCOAR 1.0
DublinCore
DDI

Other Formats

インデックスリンク

インデックスツリー

アイテム

スマート農業における機械学習に基づく分類モデル

× Adhitya, Yudhi

Versions

Share

Cite as

Other

エクスポート

コミュニティ

メニューを最小化

インデックスリンク

インデックスツリー

アイテム

スマート農業における機械学習に基づく分類モデル

× Adhitya, Yudhi

Versions

Share

Cite as

Other

エクスポート

コミュニティ