Computer aided agriculture development for crop disease detection by segmentation and classification using deep learning architectures

Raj, Nirmal; Perumal, Senthil K.; Singla, Sanjay; Sharma, Girish Kumar; Qamar, Shamimul; Chakkaravarthy, A. Prabhu

doi:10.1016/j.compeleceng.2022.108357

Cited by 18 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies on crop disease diagnosis have focused primarily on a single modality, such as images or environmental data. To improve accuracy, they have worked on refining model architectures [34][35][36], collecting new data to simulate real-world conditions [12,13], or compressing models for real-time detection [37][38][39]. Recently, with the advancement of IoT technologies like low-power sensors and remote-sensing, it has become easier to acquire various multimodal data.…”

Section: Discussionmentioning

confidence: 99%

A Deep Learning-Based Crop Disease Diagnosis Method Using Multimodal Mixup Augmentation

Lee,

Park,

Yang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

With the widespread adoption of smart farms and continuous advancements in IoT (Internet of Things) technology, acquiring diverse additional data has become increasingly convenient. Consequently, studies relevant to deep learning models that leverage multimodal data for crop disease diagnosis and associated data augmentation methods are significantly growing. We propose a comprehensive deep learning model that predicts crop type, detects disease presence, and assesses disease severity at the same time. We utilize multimodal data comprising crop images and environmental variables such as temperature, humidity, and dew points. We confirmed that the results of diagnosing crop diseases using multimodal data improved 2.58%p performance compared to using crop images only. We also propose a multimodal-based mixup augmentation method capable of utilizing both image and environmental data. In this study, multimodal data refer to data from multiple sources, and multimodal mixup is a data augmentation technique that combines multimodal data for training. This expands the conventional mixup technique that was originally applied solely to image data. Our multimodal mixup augmentation method showcases a performance improvement of 1.33%p compared to the original mixup method.

show abstract

Section: Discussionmentioning

confidence: 99%

A Deep Learning-Based Crop Disease Diagnosis Method Using Multimodal Mixup Augmentation

Lee,

Park,

Yang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The changes brought about by the lacto-fermentation process in the zucchini product can be analyzed with different measurements and observations. However, the increasing use of computerized systems in agriculture reduces the number of manual or human-sourced solutions (Raj et al, 2022). In this context, automating the solution of existing When the results of the study were examined, the effect of lactofermentation was strongly distinguished by different machine learning methods using texture features obtained from different color channels.…”

Section: Discussionmentioning

confidence: 99%

The effect of lacto‐fermentation over time on the changes in zucchini flesh quality assessed using machine learning models based on image textures

Ropelewska,

Sabanci,

Aslan

2023

J Food Process Engineering

View full text Add to dashboard Cite

Lacto‐fermented foods may have health benefits. Therefore, the consumption of lacto‐fermented fruit and vegetables is important. The objective of this study was to assess the effect of lacto‐fermentation on zucchini flesh after 1 week and 3 months. The zucchini slices were classified using models built based on image textures using different machine learning algorithms. The developed models were characterized by overall accuracies of up to 99.33% for a combined set of textures selected from images in color channels R, G, B, L, a, b, X, Y, and Z (IBk algorithm). Only fresh zucchini slices were correctly classified with an accuracy of 100% and Precision, F‐Measure, Matthews Correlation Coefficient (MCC), Receiver Operating Characteristic (ROC) Area, and Precision‐Recall (PRC) Area of 1.000 for selected models. The greater changes in the zucchini flesh structure were observed after the first week of lacto‐fermentation compared to the fresh slices than between samples lacto‐fermented for 1 week and 3 months.Practical ApplicationsThe obtained results confirmed that the developed procedure combining image analysis and machine learning can be used for the quality assessment of the lacto‐fermented zucchini and the detection of the optimal period to obtain desired changes. The determination of changes in product quality as a result of lengthening the lacto‐fermentation time can be useful for detecting the optimal period of the process.

show abstract

“…Built-in sensor-based system gathers the surrounding information (e.g., speed, accelerations, component visual integrity, etc.) still there are various challenges to acquiring efficient and accurate pedestrian detection because pedestrian images undergo low-level visual descriptors, variation in intraclass, non-constraint illumination, occlusions, different scale, illumination, variable appearance clothing, and complex background is unreliable due to mismatched posed or camera viewpoint.More of the studies have focused on deep learning algorithms, convolution networks(CNN) (Szarvas et al, 2005), Deep active contour convolutional neural network (DACCNN) (Raj et al, 2022) region convolution networks (RCNN) (Dong and Wang, 2016), Faster Region-based Convolutional Neural networks (F-RCNN) (Zhang et al, 2016) we have added an extra effort to check the neighborhood pixel of every single pixel through the sliding window technique. Our aim to maintain the speed limit without detoriating the image pixel.…”

Section: Literature Reviewmentioning

confidence: 99%

Wireless Sensor Network Based Real-Time Pedestrian Detection and Classification for Intelligent Transportation System

Kumar

Sharma

Kumar

2023

Int. j. math. eng. manag. sci.

View full text Add to dashboard Cite

Pedestrian safety has become a critical consideration in developing society especially road traffic, an intelligent transportation need of the hour is the solution left. India tops the world with 11% of global road accidents. With this data, we have moved in the direction of computer vision applications for efficient and accurate pedestrian detection for intelligent transportation systems (ITS). The important application of this research is robot development, traffic management and control, unmanned vehicle driving (UVD), intelligent monitoring and surveillance system, and automatic pedestrian detection system. Much research has focused on pedestrian detection, but sustainable solution-driven research must still be required to overcome road accidents. We have proposed a wireless sensor network-based pedestrian detection system that classifies the real-time set of pedestrian activity and samples the reciprocally received signal strength (RSS) from the sensor node. We applied a histogram of oriented gradient (HOG) descriptor algorithm K-nearest neighbor, decision tree and linear support vector machine to measure the performance and prediction of the target. Also, these algorithms have performed a comparative analysis under different aspects. The linear support vector machine algorithm was trained with 481 samples. The performance achieves the accuracy of 98.90%and has accomplished superior results with a maximum precision of 0.99, recall of 0.98, and F-score of 0.95 with 2% error rate. The model’s prediction indicates that it can be used in the intelligent transportation system. Finally, the limitation and the challenges discussed to provide an outlook for future research direction to perform effective pedestrian detection.

show abstract

Computer aided agriculture development for crop disease detection by segmentation and classification using deep learning architectures

Cited by 18 publications

References 9 publications

A Deep Learning-Based Crop Disease Diagnosis Method Using Multimodal Mixup Augmentation

A Deep Learning-Based Crop Disease Diagnosis Method Using Multimodal Mixup Augmentation

The effect of lacto‐fermentation over time on the changes in zucchini flesh quality assessed using machine learning models based on image textures

Wireless Sensor Network Based Real-Time Pedestrian Detection and Classification for Intelligent Transportation System

Contact Info

Product

Resources

About