Neural Network based Plant Identification using Leaf Characteristics Fusion

Sumathi, C. S.; Kumar, A. V. Senthil

doi:10.5120/15499-4141

Cited by 9 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pada penelitian-penelitian sebelumnya kebanyakan menggunkan daun untuk mengetahui/mengenali suatu jenis tanaman [6] [7]. Fitur-fiur yang ada pada daun seperti fitur tekstur, fitur bentuk ataupun fitur yang lain sangat bermanfaat untuk mengidendifikasi jenis daun [8] [9]. Salah satu dari fitur tekstur yakni fitur tekstur gray level co-occurrence matric (GLCM) .…”

Section: Pendahuluanunclassified

Perbandingan Algoritma K-Nearest Neighbor Untuk Klasifikasi Jenis Mangga Menggunakan Berdasarkan Fitur Gray Level Co-Occurrence Matric dan Fitur Warna

Rizal¹,

Nadiyah²

2022

COREAI

View full text Add to dashboard Cite

Indonesia merupakan negara dengan sumber daya manusia serta sumber daya alam yang memiliki pontesial untuk dapat membangun industri buah nusantra, serta mata pencaharian sebagian besar penduduk indonesia yakni petani. Produksi pertanian diantaranya padi, jagung dan lain-lain [1][2]. Budidaya tanaman kebun jenis buah-buahan di indonesiaa seperti alpukat, nanas, kelengkeng, pisang, mangga dan lain-lain. Sebagian besar penduduk indonesia sangat gemar menanam pohon mangga di halaman rimah atau kebun mereka. Akan tetapi dari kegemaran mereka menanam pohon mangga tidak jarang masyarakat tertipu dengan jenis mangga yang ditanam. Oleh sebab itu dibutuhkan suatu model atau metode untuk dapat mengklasifikasikan jenis mangga serta untuk mengetahui jenis mangga tersebut dapat dilihat dari ciri yang ada seperti bentuk tekstur dan warna. Terdapat beberapa metode yang telah diusulkan serta telah dikerjakan utnuk mengklasifikasikan jenis mangga, akan tetapi hasil rata-rata akurasi yang diperoleh kurang dari 80%. Dalam penelitian ini mengusulkan pendekatan menggunakan k-nearest neighbor dengan optimasi algoritma genetika serta menggunakan fitur gray level co-occurrence matrix dan fitur warna daun mangga jumlah dataset yang digunakan sebanyak 800 daun citra. Penggunaan algoritma genetika untuk optimasi berhasil meningkatkan nilai akurasi pada metode k-nearest neighbor. Akurasi tertinggi terdapat pada nilai k=3 yakni 93.50%. Sedangkan metode k-nearest neighbor tanpa menggunakan optimasi memperoleh akurasi sebesar 93.00% dengan nilai k=1.

show abstract

Section: Pendahuluanunclassified

Perbandingan Algoritma K-Nearest Neighbor Untuk Klasifikasi Jenis Mangga Menggunakan Berdasarkan Fitur Gray Level Co-Occurrence Matric dan Fitur Warna

Rizal¹,

Nadiyah²

2022

COREAI

View full text Add to dashboard Cite

show abstract

“…The BP neural network model is the activation function model of linear weight (19). The learning process is divided into two parts, including forward propagation process and backward propagation process, as shown in Figure 3.…”

Section: Bp Neural Network Modelmentioning

confidence: 99%

An Empirical Study on the Equity Performance of China's Health Insurance Companies During the COVID-19 Pandemic—Based on Cases of Dominant Listed Companies

Xie

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

The health insurance industry in China is undergoing great shocks and profound impacts induced by the worldwide COVID-19 pandemic. Taking for instance the three dominant listed companies, namely, China Life Insurance, Ping An Insurance, and Pacific Insurance, this paper investigates the equity performances of China's health insurance companies during the pandemic. We firstly construct a stock price forecasting methodology using the autoregressive integrated moving average, back propagation neural network, and long short-term memory (LSTM) neural network models. We then empirically study the stock price performances of the three listed companies and find out that the LSTM model does better than the other two based on the criteria of mean absolute error and mean square error. Finally, the above-mentioned models are used to predict the stock price performances of the three companies.

show abstract

“…Both sampling and capturing of leaves is very convenient and also inexpensive. This captured leaf image may be easily moved to a computer and all its necessary features can be extracted automatically by means of techniques of image processing [3].…”

Section: Introductionmentioning

confidence: 99%

Hybrid Group Search Optimizer for Plant Leaf Classification

Ravishankkar¹,

santhosh²,

Amudhavalli³

2019

IJITEE

View full text Add to dashboard Cite

The analysis of Big Data is a data mining discipline in which large quantity of unstructured data is analysed which can be challenging to store and also to retrieve efficiently. The classification of plants is based on the identification of leaf that has a very broad application in both agriculture and medicine. In this work, a method which is computerized is used to recognize a plant leaf based on images is proposed. The proposed method extracts features from the image and these are used for classifying the plant leaf. The process of deciding on the subset for all relevant features to be used in the construction of a system is known as feature selection. The Group Search Optimizer (GSO) is a nature-inspired algorithm that possesses all the qualities used effectively to solve feature selection tasks. In this work, there is a GSO-based algorithm of feature selection along with fuzzy logic and the classifier of a Neural Network (NN) is proposed. The results of the experiment prove the proposed method (GSO-NN) was able to achieve a better level of performance compared to the other methods.

show abstract

Neural Network based Plant Identification using Leaf Characteristics Fusion

Cited by 9 publications

References 11 publications

Perbandingan Algoritma K-Nearest Neighbor Untuk Klasifikasi Jenis Mangga Menggunakan Berdasarkan Fitur Gray Level Co-Occurrence Matric dan Fitur Warna

Perbandingan Algoritma K-Nearest Neighbor Untuk Klasifikasi Jenis Mangga Menggunakan Berdasarkan Fitur Gray Level Co-Occurrence Matric dan Fitur Warna

An Empirical Study on the Equity Performance of China's Health Insurance Companies During the COVID-19 Pandemic—Based on Cases of Dominant Listed Companies

Hybrid Group Search Optimizer for Plant Leaf Classification

Contact Info

Product

Resources

About