Implementation of Case-Based Reasoning and Nearest Neighbor Similarity for Peanut Disease Diagnosis

Minarni,; Warman, Indra; Yuhendra,

doi:10.1088/1742-6596/1196/1/012053

Cited by 6 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We also want to integrate RustOnt as part of a case-based reasoning (CBR) system widely used in agriculture for crop management [3], traceability [73], yield estimation [74], and pest and disease protection [75][76][77]. RustOnt can improve the retrieval process of a CBR by making the input data less heterogeneous and thus more accurate, so that the search for the most similar case can be more precise according to the system requirements.…”

Section: Discussionmentioning

confidence: 99%

RustOnt: An Ontology to Explain Weather Favorable Conditions of the Coffee Rust

Suárez

Griol

Figueroa

et al. 2022

Sensors

View full text Add to dashboard Cite

Crop disease management in smart agriculture involves applying and using new technologies to reduce the impact of diseases on the quality of products. Coffee rust is a disease that factors such as poor agronomic management activities and climate conditions may favor. Therefore, it is crucial to identify the relationships between these factors and this disease to learn how to face its consequences and build intelligent systems to provide appropriate management or help farmers and experts make decisions accordingly. Nevertheless, there are no studies in the literature that propose ontologies to model these factors and coffee rust. This paper presents a new ontology called RustOnt to help experts more accurately model data, expressions, and samples related to coffee rust and apply it whilst taking into account the geographical location where the ontology is adopted. Consequently, this ontology is crucial for coffee rust monitoring and management by means of smart agriculture systems. RustOnt was successfully evaluated considering quality criteria such as clarity, consistency, modularity, and competence against a set of initial requirements for which it was built.

show abstract

Section: Discussionmentioning

confidence: 99%

RustOnt: An Ontology to Explain Weather Favorable Conditions of the Coffee Rust

Suárez

Griol

Figueroa

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…CBR ialah sebuah teknik yang digunakan sebagai pemecahan masalah atau kasus baru dengan menyesuaikan solusi masalah pada kasus sebelumnya [7][8]. Penyelesaian masalah menggunakan pendekatan CBR memiliki empat tahapan utama, tahapan tersebut dikenal dengan 4R (Retrieve, Reuse, Revise, dan Retain) [9]. Retrieve merupakan tahapan di mana kasus lama dalam basis kasus yang serupa dengan kasus baru diambil dan dibandingkan.…”

Section: Pendahuluanunclassified

“…Nilai 0 mengindikasikan kedua kasus tersebut tidak sama secara mutlak, sementara nilai 1 mengindikasikan kedua kasus sama secara mutlak [14]. Berikut adalah rumus yang digunakan [18] :…”

Section: Metode Penelitianunclassified

Case-Based Reasoning Diagnosis Penyakit Pada Tanaman Kelapa Sawit

Yuliarni,

Septiriana

2024

JURNAL MULTIMEDIA NETWORKING INFORMATICS

View full text Add to dashboard Cite

Budidaya tanaman kelapa sawit adalah salah satu komoditas pertanian utama di Indonesia, hal tersebut terjadi karena tanaman kelapa sawit memiliki nilai jual ekonomi yang cukup tinggi. Namun Budidaya tanaman kelapa sawit rentan terhadap serangan penyakit yang dapat mengancam produktivitas. Kurangnya pengetahuan para petani dalam mengelola kebun dan mengatasi masalah tersebut dapat memperparah kerusakan tanaman akibat serangan penyakit. Untuk mengatasi permasalahan tersebut pada penelitian ini akan membangun sebuah aplikasi dengan pendekatan Case-Based Reasoning (CBR) untuk mendiagnosis penyakit pada tanaman kelapa sawit dengan algoritma perhitungan nearest neighbor. CBR akan menyelesaikan permasalahan baru dengan memanfaatkan kembali pengetahuan dalam menyelesaikan permasalahan lama yang memiliki kesamaan dan telah memiliki solusi. Algoritma nearest neighbor berguna untuk menghitung similaritas atau kemiripan antar kasus baru dengan kasus lama. Data untuk penelitian melibatkan 7 jenis penyakit, 20 gejala, dan 345 kasus serangan penyakit pada tanaman kelapa sawit. Pengujian aplikasi menggunakan 25 kasus uji serta 320 basis kasus. Dari hasil pengujian aplikasi menunjukkan hasil akurasi sebesar 31,00%, dengan nilai similaritas tertinggi mencapai 0,98. Meskipun aplikasi mampu memberikan solusi yang efektif tetapi terdapat keterbatasan dalam penentuan kasus terpilih ketika memiliki nilai similaritas yang sama.

show abstract

“…Peanut (Arachis hypogaea L.) is an essential economic and oilseed crop worldwide [1], and China is the largest peanut producer [2]. Peanut soil-borne fungal diseases are one of the disastrous factors limiting peanut yield, which seriously threatens the quality of peanuts and the safety of agricultural products [3]. Peanut southern blight is a soil-borne fungal disease caused by Agroathelia rolfsii Sacc [4], substantially affecting peanut yields and prevalent in the major peanut-growing regions of China.…”

Section: Introductionmentioning

confidence: 99%

Development and Evaluation of a New Spectral Index to Detect Peanut Southern Blight Disease Using Canopy Hyperspectral Reflectance

Wen,

Liu,

et al. 2024

Horticulturae

View full text Add to dashboard Cite

Peanut southern blight is a soil-borne fungal disease caused by Agroathelia rolfsii (syn. Sclerotium rolfsii) Sacc, which seriously affects peanut yield. The disease mainly affects the stem, pod, and root of the plant, and it is difficult to detect the disease by visual interpretation. Detecting peanut southern blight using existing technology is an urgent problem that needs to be solved. To address this issue, field experiments were conducted in September 2022 to determine whether hyperspectral techniques could be used to assess the severity of peanut southern blight. In this study, we obtained 610 canopy-scale spectral data through field experiments. Firstly, 18 traditional spectral features were calculated. Then, wavelengths of 544 nm, 678 nm, and 769 nm were selected as sensitive by the Relief-F algorithm, and the NDSISB and NSISB were constructed using normalization and ratio calculation methods. Finally, Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), and ANN were used to evaluate the diagnostic ability of all spectral features to assess disease severity levels. The results showed that the NSISB had the highest association with peanut southern blight (R2 = 0.817), exceeding the other spectral features. Compared to the other three models, CatBoost demonstrated superior accuracy, with an overall accuracy (OA) and Kappa coefficient of 84.18% and 78.31%, respectively. The findings of this study can serve as a reference for estimating the severity levels of peanut southern blight using ground-based hyperspectral data.

show abstract

Implementation of Case-Based Reasoning and Nearest Neighbor Similarity for Peanut Disease Diagnosis

Cited by 6 publications

References 4 publications

RustOnt: An Ontology to Explain Weather Favorable Conditions of the Coffee Rust

RustOnt: An Ontology to Explain Weather Favorable Conditions of the Coffee Rust

Case-Based Reasoning Diagnosis Penyakit Pada Tanaman Kelapa Sawit

Development and Evaluation of a New Spectral Index to Detect Peanut Southern Blight Disease Using Canopy Hyperspectral Reflectance

Contact Info

Product

Resources

About