An effective identification of crop diseases using faster region based convolutional neural network and expert systems

Chandana, P.; Ghantasala, G. S. Pradeep; Jeny, J. Rethna Virgil; Sekaran, Kaushik; Deepika, N.; Nam, Yunyoung; Kadry, Seifedine

doi:10.11591/ijece.v10i6.pp6531-6540

Cited by 25 publications

(20 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensor devices are used to monitor the control and read the information to monitor the environments of planting. The sensors that are commonly used in agriculture consisted of temperature sensor [26], [28], [29] water level sensor [23]- [26], [28], [29], humidity sensor [26], [29], soil moisture sensors [29], light sensor, [26], [29] and pressure sensor [21], [26], [29]. The sensor devices are related with hardware control devices which are a part in physical layer.…”

Section: Sensor Devicesmentioning

confidence: 99%

See 1 more Smart Citation

An internet of things secosystem for planting of coriander (Coriandrum sativum L.)

Tangwannawit

Saengkrajang

2021

IJECE

View full text Add to dashboard Cite

The internet of things (IoT) is a network of physical devices and is becoming a major area of innovation for computer-based systems. Agriculture is one of the areas which could be improved by utilizing this technology ranging from farming techniques to production efficiency. The objective of this research is to design an IoT to monitor local vegetable (Coriander; Coriandrum sativum L.) growth via sensors (light, humidity, temperature, water level) and combine with an automated watering system. This would provide planters with the ability to monitor field conditions from anywhere at any time. In this research, a group of local vegetables including coriander, cilantro, and dill weed were experimented. The prototype system consists of several smart sensors to accurately monitor the mentioned vegetable growth from seedling stage to a fully grown plant which will ensure the highest production levels from any field environment. Three different types coriander were measured under these parameters: height, trunk width, and leaf width. The result showed that IoT ecosystem for planting different types of coriander could produce effective and efficient plant growth and ready for harvest with a shorter time than conventional method.

show abstract

Section: Sensor Devicesmentioning

confidence: 99%

“…The representation of information from these devices is done by using web browser [21]- [22], [28] or mobile application [23], [26], [28], [29]. The web application is responsible for supporting a responsive design.…”

Section: The Representation Of Informationmentioning

confidence: 99%

An internet of things secosystem for planting of coriander (Coriandrum sativum L.)

Tangwannawit

Saengkrajang

2021

IJECE

View full text Add to dashboard Cite

show abstract

“…In [44], Deep Residual Neural Network-based algorithm is used for detecting multiple plant diseases which achieved a balanced accuracy of 0.87 under challenging testing. In [45], faster region-based convolutional neural network is used to classify images within images within 0.2 seconds. In [46], a Convolutional Neural Network based approach is proposed for mapping crop types.…”

Section: Related Workmentioning

confidence: 99%

Assessing the Impact of Segmentation on Wheat Stripe Rust Disease Classification Using Computer Vision and Deep Learning

Bukhari

Mumtaz²,

Inayat

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Wheat is a staple crop that is grown across the world due to its substantial contribution to human nutrition. Its significance is evident as it provides almost 20% of calories and protein required for daily human consumption. However, wheat yield is affected by rust disease that can reduce 30% of wheat production which is a serious threat to food security. In order to minimize the loss, it is crucial to identify precisely and localize the wheat rust disease and its infection types. For this purpose, several classification and segmentation techniques are used which are based on machine/deep learning models. This paper provides a realistic analysis and evaluation of various segmentation techniques including Watershed, Grab Cut, and U2-Net. These techniques are applied to the wheat stripe rust data to generate multiple datasets such as Watershed segmented data, GrabCut segmented data, and U2-Net segmented data. Subsequently, a pretrained deep learning model, ResNet-18 is applied to these datasets to assess the impact of segmentation on classification accuracy. The highest classification accuracy (96.196%) is achieved on the dataset segmented by U2-Net. This research collates several state-of-the-art segmentation techniques in terms of correctness and their direct impact on classification accuracy which gives a pragmatic analysis for researchers to choose optimal segmentation technique. The research primarily focuses on the direct impact of segmentation on classification accuracy of wheat stripe rust, which has not been given sufficient focus in earlier researches.

show abstract

“…There are three main detectors: Faster Region-Based Convolutional Neural Network (Faster R-CNN), Region-Based Fully Convolutional Network (R-FCN), and Single-Shot Multi-Shot Box Detector (SSD). The system can effectively identify different types of diseases with the ability to handle complex scenarios from the plant's area (Hari et al, 2019;Chandana et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Application of Artificial Intelligence in Modern Ecology for Detecting Plant Pests and Animal Diseases

Sara

Maharani

Amin³

et al. 2021

ijqrm

View full text Add to dashboard Cite

Climate change could lead to an increase in diseases in plants and animals. Plant pathogens have caused devastating production losses, such as in tropical countries. The development of algorithms that match the accuracy of plant and animal disease detection in predicting the toxicity of substances has continued through a massive database. Data and information from 10,000 substances from more than 800,000 animal tests have been carried out to generate the algorithms. Plant and animal disease detection using artificial intelligent in the modern ecological era is important and needed. Diseases in animals are still found in several Ruminant-Slaughterhouses. The purpose of the study is to identify the leverage attributes for using of Artificial Intelligent (AI) in detecting plant pests and animal diseases. The use of Multidimensional Scaling (MDS) produces a leverage attribute for the use of AI in detecting plant pests and animal diseases. The results showed that leverage attributes found were: Prediction of the presence of proteins structures produced by pathogens with a Root Mean Square (RMS) value of 4.5123; and Plant and Animal Disease Data will be opened with an RMS value of 4.2555. The findings of this study in the real world are to produce the development of smart agricultural applications in detecting plant pests and animal diseases as an early warning system. In addition, the application is also useful for eco-tourism managers who have a natural close relationship with plants and animals, so that ecological security in the modern ecological era, can be better maintained.

show abstract

An effective identification of crop diseases using faster region based convolutional neural network and expert systems

Cited by 25 publications

References 19 publications

An internet of things secosystem for planting of coriander (<i>Coriandrum sativum</i> L.)

An internet of things secosystem for planting of coriander (<i>Coriandrum sativum</i> L.)

Assessing the Impact of Segmentation on Wheat Stripe Rust Disease Classification Using Computer Vision and Deep Learning

Application of Artificial Intelligence in Modern Ecology for Detecting Plant Pests and Animal Diseases

Contact Info

Product

Resources

About