東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Hidden Markov Model Based Machine Le...

Blumenthal, Julie S.

Linked to FindBook

Google Book

Amazon

博客來

Hidden Markov Model Based Machine Learning for Plant Stress Type and Level Detection.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Hidden Markov Model Based Machine Learning for Plant Stress Type and Level Detection./
Author:	Blumenthal, Julie S.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	145 p.
Notes:	Source: Dissertations Abstracts International, Volume: 81-09, Section: B.
Contained By:	Dissertations Abstracts International81-09B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27665997
ISBN:	9781392731536

Hidden Markov Model Based Machine Learning for Plant Stress Type and Level Detection.
Blumenthal, Julie S.

Hidden Markov Model Based Machine Learning for Plant Stress Type and Level Detection. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 145 p.

Source: Dissertations Abstracts International, Volume: 81-09, Section: B.

Thesis (Ph.D.)--University of Massachusetts Lowell, 2020.

This item must not be sold to any third party vendors.

Chlorophyll fluorescence (ChlF), being an integral part of the photosynthetic process, has long been known to be a useful tool to detect plant stress. Early and accurate plant stress detection is imperative in enabling timely and appropriate intervention. One of the major limitations of prior work for ChIF-based plant classification is that, in general, only a few key inflection points of a localized section of a chlorophyll fluorescence signal are used to calculate single index values. These values yield very limited insight into stress level or stress type.In this thesis, we propose two new methods for clustering or classifying plant stress based upon the use of Hidden Markov Models (HMMs) using global (versus local) ChlF time-varying signal data acquired via video imaging. The first is an unsupervised method for plant stress clustering. The second is a supervised method for plant stress classification. To the best of our knowledge this is the first use of HMMs in the field of plant stress detection.We first introduce and present the proposed unsupervised learning method. We cluster the time-varying-intensity-signal data using unsupervised learning via HMMs. We show how in some scenarios plant stress classification is improved by the selection of a low-pass filtered plant's entire chlorophyll fluorescence signal profile, (as a global feature selection), the rate-of-change-in-time of the plant ChlF intensity time-varying profile, (as another global feature selection) and data quantization. We show that HMMs allow more variability in classifying data than other raw data distance-based metrics. We explore the ergodic and Bakis models for HMM state transition matrix initialization. In addition we propose a new method for initialization of the HMM state transition matrix, denoted as "the state information based initial probability assignment" (SIPA) method and compare it to the heuristic initial probability assignment (HIPA) method. We show how using the Bayesian information criterion (BIC) as a performance metric allows good state number choice. We use silhouette values as an additional performance metric. We present a method to automatically determine the number of existing classes in the data set. Note this is in contrast to existing unsupervised learning methods, where the number of existing classes in the data sets is, in general, guessed a priori, and often incorrectly.We then introduce and present a new method for plant stress classification of both stress level and stress type that uses supervised learning, via HMMs, to build accurate class profiles using the same data and features as described above. We show how creating increased-state supervised models can in particular, better classify specific stressor types as well as achieve more granularity in stressor level classification. We compare the performance of neural networks (NNs) to our supervised HMM method in classifying our data (using the same features). We show that due to our good feature selection, NNs can also perform fairly well in plant stress classification. We show the value of stochastically based HMMs over NNs, in better classifying new data signatures that have wide variance in shape from the signatures used to create the HMM profiles or train the NNs. Experimental results are presented to show the value and potential of the proposed unsupervised and supervised methods to enable more accurate and specific classification of plant stressor types and stressor levels.

ISBN: 9781392731536Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Chlorophyll fluorescence measurement

Hidden Markov Model Based Machine Learning for Plant Stress Type and Level Detection.
LDR:04771nmm a2200397 4500 001 2275149
005 20201202130421.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9781392731536
035 $a (MiAaPQ)AAI27665997
035 $a AAI27665997
040 $a MiAaPQ $c MiAaPQ
100 1 $a Blumenthal, Julie S. $3 3553387
245 1 0 $a Hidden Markov Model Based Machine Learning for Plant Stress Type and Level Detection.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 145 p.
500 $a Source: Dissertations Abstracts International, Volume: 81-09, Section: B.
500 $a Advisor: Megherbi, Dalila.
502 $a Thesis (Ph.D.)--University of Massachusetts Lowell, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Chlorophyll fluorescence (ChlF), being an integral part of the photosynthetic process, has long been known to be a useful tool to detect plant stress. Early and accurate plant stress detection is imperative in enabling timely and appropriate intervention. One of the major limitations of prior work for ChIF-based plant classification is that, in general, only a few key inflection points of a localized section of a chlorophyll fluorescence signal are used to calculate single index values. These values yield very limited insight into stress level or stress type.In this thesis, we propose two new methods for clustering or classifying plant stress based upon the use of Hidden Markov Models (HMMs) using global (versus local) ChlF time-varying signal data acquired via video imaging. The first is an unsupervised method for plant stress clustering. The second is a supervised method for plant stress classification. To the best of our knowledge this is the first use of HMMs in the field of plant stress detection.We first introduce and present the proposed unsupervised learning method. We cluster the time-varying-intensity-signal data using unsupervised learning via HMMs. We show how in some scenarios plant stress classification is improved by the selection of a low-pass filtered plant's entire chlorophyll fluorescence signal profile, (as a global feature selection), the rate-of-change-in-time of the plant ChlF intensity time-varying profile, (as another global feature selection) and data quantization. We show that HMMs allow more variability in classifying data than other raw data distance-based metrics. We explore the ergodic and Bakis models for HMM state transition matrix initialization. In addition we propose a new method for initialization of the HMM state transition matrix, denoted as "the state information based initial probability assignment" (SIPA) method and compare it to the heuristic initial probability assignment (HIPA) method. We show how using the Bayesian information criterion (BIC) as a performance metric allows good state number choice. We use silhouette values as an additional performance metric. We present a method to automatically determine the number of existing classes in the data set. Note this is in contrast to existing unsupervised learning methods, where the number of existing classes in the data sets is, in general, guessed a priori, and often incorrectly.We then introduce and present a new method for plant stress classification of both stress level and stress type that uses supervised learning, via HMMs, to build accurate class profiles using the same data and features as described above. We show how creating increased-state supervised models can in particular, better classify specific stressor types as well as achieve more granularity in stressor level classification. We compare the performance of neural networks (NNs) to our supervised HMM method in classifying our data (using the same features). We show that due to our good feature selection, NNs can also perform fairly well in plant stress classification. We show the value of stochastically based HMMs over NNs, in better classifying new data signatures that have wide variance in shape from the signatures used to create the HMM profiles or train the NNs. Experimental results are presented to show the value and potential of the proposed unsupervised and supervised methods to enable more accurate and specific classification of plant stressor types and stressor levels.
590 $a School code: 0111.
650 4 $a Computer science. $3 523869
650 4 $a Computer engineering. $3 621879
650 4 $a Agricultural engineering. $3 3168406
650 4 $a Artificial intelligence. $3 516317
653 $a Chlorophyll fluorescence measurement
653 $a Hidden Markov models
653 $a OJIP/PSMT transient
653 $a Plant stress
653 $a Supervised learning
653 $a Unsupervised learning
690 $a 0984
690 $a 0464
690 $a 0539
690 $a 0800
710 2 $a University of Massachusetts Lowell. $b Computer Science. $3 3434885
773 0 $t Dissertations Abstracts International $g 81-09B.
790 $a 0111
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27665997