Classification of Toxic Plants on Leaf Patterns Using Gray Level Co-Occurrence Matrix (GLCM) with Neural Network Method

IF 2.5 3区社会学 Q2 DEVELOPMENT STUDIES

European Journal of Development Research Pub Date : 2022-05-31 DOI:10.28926/jdr.v6i1.202

Mohammad Faishol Zuhri, S. Maharani, Affandy Affandy, Aris Nurhindarto, Abdul Syukur, M. Soeleman

{"title":"Classification of Toxic Plants on Leaf Patterns Using Gray Level Co-Occurrence Matrix (GLCM) with Neural Network Method","authors":"Mohammad Faishol Zuhri, S. Maharani, Affandy Affandy, Aris Nurhindarto, Abdul Syukur, M. Soeleman","doi":"10.28926/jdr.v6i1.202","DOIUrl":null,"url":null,"abstract":"Poisonous plants are plants that must be avoided and not consumed by humans, because the presence of poisonous plants is also often found in the surrounding environment without realizing it. Because of the lack of knowledge to classify poisonous plant species, it will be more difficult to find out. With the help of a computer system, it will be easier to identify the types of poisonous plants. There are 3 types of poisonous plants that will be used in this study, namely cassava, jatropha, and amethyst. There are also 3 types of non-toxic plants with almost the same morphology as a comparison, namely cassava, figs, and eggplant. In this study, researchers tried to classify poisonous plant species using leaf pattern features that would be extracted using shape features and Gray Level Co-occurrence Matrix (GLCM). The value taken from the shape feature is the values of area, width, diameter, perimeter, slender, and round. While the value of contrast, entropy, correlation, energy, and homogeneity for Gray Level Co-occurrence Matrix (GLCM) attributes. To classify data using Neural Network with RapidMiner application. From this study, it is known that from 300 total datasets used, the highest accuracy is 96.13% using the Neural Network method. With an AUC value of 0.986 and is included in the very good category. ","PeriodicalId":47650,"journal":{"name":"European Journal of Development Research","volume":"16 1","pages":""},"PeriodicalIF":2.5000,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Development Research","FirstCategoryId":"90","ListUrlMain":"https://doi.org/10.28926/jdr.v6i1.202","RegionNum":3,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"DEVELOPMENT STUDIES","Score":null,"Total":0}

引用次数: 0

Abstract

Poisonous plants are plants that must be avoided and not consumed by humans, because the presence of poisonous plants is also often found in the surrounding environment without realizing it. Because of the lack of knowledge to classify poisonous plant species, it will be more difficult to find out. With the help of a computer system, it will be easier to identify the types of poisonous plants. There are 3 types of poisonous plants that will be used in this study, namely cassava, jatropha, and amethyst. There are also 3 types of non-toxic plants with almost the same morphology as a comparison, namely cassava, figs, and eggplant. In this study, researchers tried to classify poisonous plant species using leaf pattern features that would be extracted using shape features and Gray Level Co-occurrence Matrix (GLCM). The value taken from the shape feature is the values of area, width, diameter, perimeter, slender, and round. While the value of contrast, entropy, correlation, energy, and homogeneity for Gray Level Co-occurrence Matrix (GLCM) attributes. To classify data using Neural Network with RapidMiner application. From this study, it is known that from 300 total datasets used, the highest accuracy is 96.13% using the Neural Network method. With an AUC value of 0.986 and is included in the very good category.

查看原文本刊更多论文

基于灰度共生矩阵(GLCM)和神经网络的有毒植物叶型分类

有毒植物是人类必须避免和不能食用的植物，因为有毒植物的存在也经常在周围环境中被发现而没有意识到。由于缺乏对有毒植物物种进行分类的知识，找出它们将更加困难。在计算机系统的帮助下，识别有毒植物的种类会更容易。本研究将使用三种有毒植物，分别是木薯、麻风树和紫水晶。还有三种形态几乎相同的无毒植物作为对照，即木薯、无花果和茄子。在这项研究中，研究人员试图利用叶片图案特征对有毒植物进行分类，这些特征将通过形状特征和灰度共生矩阵(GLCM)提取。从形状特征中取的值是面积、宽度、直径、周长、细长和圆形的值。而灰度共生矩阵(GLCM)属性的对比度值、熵值、相关性、能量和均匀性。利用RapidMiner应用神经网络对数据进行分类。从本研究可知，在使用的300个数据集中，使用神经网络方法的准确率最高为96.13%。AUC值为0.986，属于非常好的一类。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

European Journal of Development Research DEVELOPMENT STUDIES-

CiteScore

5.70

自引率

4.00%

发文量

期刊介绍： The European Journal of Development Research (EJDR) redefines and modernises what international development is, recognising the many schools of thought on what human development constitutes. It encourages debate between competing approaches to understanding global development and international social development. The journal is multidisciplinary and welcomes papers that are rooted in any mixture of fields including (but not limited to): development studies, international studies, social policy, sociology, politics, economics, anthropology, education, sustainability, business and management. EJDR explicitly links with development studies, being hosted by European Association of Development Institutes (EADI) and its various initiatives. As a double-blind peer-reviewed academic journal, we particularly welcome submissions that improve our conceptual understanding of international development processes, or submissions that propose policy and developmental tools by analysing empirical evidence, whether qualitative, quantitative, mixed methods or anecdotal (data use in the journal ranges broadly from narratives and transcripts, through ethnographic and mixed data, to quantitative and survey data). The research methods used in the journal''s articles make explicit the importance of empirical data and the critical interpretation of findings. Authors can use a mixture of theory and data analysis to expand the possibilities for global development. Submissions must be well-grounded in theory and must also indicate how their findings are relevant to development practitioners in the field and/or policy makers. The journal encourages papers which embody the highest quality standards, and which use an innovative approach. We urge authors who contemplate submitting their work to the EJDR to respond to research already published in this journal, as well as complementary journals and books. We take special efforts to include global voices, and notably voices from the global South. Queries about potential submissions to EJDR can be directed to the Editors. EJDR understands development to be an ongoing process that affects all communities, societies, states and regions: We therefore do not have a geographical bias, but wherever possible prospective authors should seek to highlight how their study has relevance to researchers and practitioners studying development in different environments. Although many of the papers we publish examine the challenges for developing countries, we recognize that there are important lessons to be derived from the experiences of regions in the developed world. The EJDR is print-published 6 times a year, in a mix of regular and special theme issues; accepted papers are published on an ongoing basis online. We accept submissions in English and French.