scholarly journals Automatic and Reliable Leaf Disease Detection Using Deep Learning Techniques

2021 ◽  
Vol 3 (2) ◽  
pp. 294-312
Author(s):  
Muhammad E. H. Chowdhury ◽  
Tawsifur Rahman ◽  
Amith Khandakar ◽  
Mohamed Arselene Ayari ◽  
Aftab Ullah Khan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Binary Classification ◽  
Experimental Studies ◽  
Plant Diseases ◽  
Superior Performance ◽  
World Population ◽  
Comparative Performance ◽  
Learning Techniques ◽  
Segmented Images ◽  
Segmentation Models

Plants are a major source of food for the world population. Plant diseases contribute to production loss, which can be tackled with continuous monitoring. Manual plant disease monitoring is both laborious and error-prone. Early detection of plant diseases using computer vision and artificial intelligence (AI) can help to reduce the adverse effects of diseases and also overcome the shortcomings of continuous human monitoring. In this work, we propose the use of a deep learning architecture based on a recent convolutional neural network called EfficientNet on 18,161 plain and segmented tomato leaf images to classify tomato diseases. The performance of two segmentation models i.e., U-net and Modified U-net, for the segmentation of leaves is reported. The comparative performance of the models for binary classification (healthy and unhealthy leaves), six-class classification (healthy and various groups of diseased leaves), and ten-class classification (healthy and various types of unhealthy leaves) are also reported. The modified U-net segmentation model showed accuracy, IoU, and Dice score of 98.66%, 98.5%, and 98.73%, respectively, for the segmentation of leaf images. EfficientNet-B7 showed superior performance for the binary classification and six-class classification using segmented images with an accuracy of 99.95% and 99.12%, respectively. Finally, EfficientNet-B4 achieved an accuracy of 99.89% for ten-class classification using segmented images. It can be concluded that all the architectures performed better in classifying the diseases when trained with deeper networks on segmented images. The performance of each of the experimental studies reported in this work outperforms the existing literature.

scholarly journals Tomato Leaf Diseases Detection Using Deep Learning Technique

2021 ◽  
Author(s):  
Muhammad E.H. Chowdhury ◽  
Tawsifur Rahman ◽  
Amith Khandakar ◽  
Nabil Ibtehaz ◽  
Aftab Ullah Khan ◽  
...  
Keyword(s):  
Binary Classification ◽  
Experimental Studies ◽  
Tomato Leaf ◽  
Plant Diseases ◽  
Superior Performance ◽  
Disease Monitoring ◽  
World Population ◽  
Network Architectures ◽  
Comparative Performance ◽  
Human Monitoring

Plants are a major source of food for the world population. Plant diseases contribute to production loss, which can be tackled with continuous monitoring. Manual plant disease monitoring is both laborious and error-prone. Early detection of plant diseases using computer vision and artificial intelligence (AI) can help to reduce the adverse effects of diseases and also helps to overcome the shortcomings of continuous human monitoring. In this study, we have extensively studied the performance of the different state-of-the-art convolutional neural networks (CNNs) classification network architectures i.e. ResNet18, MobileNet, DenseNet201, and InceptionV3 on 18,162 plain tomato leaf images to classify tomato diseases. The comparative performance of the models for the binary classification (healthy and unhealthy leaves), six-class classification (healthy and various groups of diseased leaves), and ten-class classification (healthy and various types of unhealthy leaves) are also reported. InceptionV3 showed superior performance for the binary classification using plain leaf images with an accuracy of 99.2%. DenseNet201 also outperform for six-class classification with an accuracy of 97.99%. Finally, DenseNet201 achieved an accuracy of 98.05% for ten-class classification. It can be concluded that deep architectures performed better at classifying the diseases for the three experiments. The performance of each of the experimental studies reported in this work outperforms the existing literature.

scholarly journals Deep Learning for Laryngopharyngeal Reflux Diagnosis

2021 ◽  
Vol 11 (11) ◽  
pp. 4753
Author(s):  
Gen Ye ◽  
Chen Du ◽  
Tong Lin ◽  
Yan Yan ◽  
Jack Jiang
Keyword(s):  
Deep Learning ◽  
Speech Processing ◽  
Data Augmentation ◽  
Laryngopharyngeal Reflux ◽  
Ph Monitoring ◽  
Binary Classification ◽  
Classification Problem ◽  
Learning Approaches ◽  
Learning Techniques ◽  
Auc Value

(1) Background: Deep learning has become ubiquitous due to its impressive performance in various domains, such as varied as computer vision, natural language and speech processing, and game-playing. In this work, we investigated the performance of recent deep learning approaches on the laryngopharyngeal reflux (LPR) diagnosis task. (2) Methods: Our dataset is composed of 114 subjects with 37 pH-positive cases and 77 control cases. In contrast to prior work based on either reflux finding score (RFS) or pH monitoring, we directly take laryngoscope images as inputs to neural networks, as laryngoscopy is the most common and simple diagnostic method. The diagnosis task is formulated as a binary classification problem. We first tested a powerful backbone network that incorporates residual modules, attention mechanism and data augmentation. Furthermore, recent methods in transfer learning and few-shot learning were investigated. (3) Results: On our dataset, the performance is the best test classification accuracy is 73.4%, while the best AUC value is 76.2%. (4) Conclusions: This study demonstrates that deep learning techniques can be applied to classify LPR images automatically. Although the number of pH-positive images used for training is limited, deep network can still be capable of learning discriminant features with the advantage of technique.

scholarly journals Trends in Computer-Aided Diagnosis Using Deep Learning Techniques: A Review of Recent Studies on Algorithm Development

2017 ◽  
Author(s):  
Bosede Iyiade Edwards ◽  
Nosiba Hisham Osman Khougali ◽  
Adrian David Cheok
Keyword(s):  
Deep Learning ◽  
Human Subjects ◽  
Binary Classification ◽  
Computer Aided Diagnosis ◽  
Network Architectures ◽  
Learning Approaches ◽  
Learning Techniques ◽  
Computer Aided ◽  
Multi Class Classification ◽  
Aided Diagnosis

With recent focus on deep neural network architectures for development of algorithms for computer-aided diagnosis (CAD), we provide a review of studies within the last 3 years (2015-2017) reported in selected top journals and conferences. 29 studies that met our inclusion criteria were reviewed to identify trends in this field and to inform future development. Studies have focused mostly on cancer-related diseases within internal medicine while diseases within gender-/age-focused fields like gynaecology/pediatrics have not received much focus. All reviewed studies employed image datasets, mostly sourced from publicly available databases (55.2%) and few based on data from human subjects (31%) and non-medical datasets (13.8%), while CNN architecture was employed in most (70%) of the studies. Confirmation of the effect of data manipulation on quality of output and adoption of multi-class rather than binary classification also require more focus. Future studies should leverage collaborations with medical experts to aid future with actual clinical testing with reporting based on some generally applicable index to enable comparison. Our next steps on plans for CAD development for osteoarthritis (OA), with plans to consider multi-class classification and comparison across deep learning approaches and unsupervised architectures were also highlighted.

scholarly journals DeepMQ: A Deep Learning Approach Based Myelin Quantification in Microscopic Fluorescence Images

2018 ◽  
Author(s):  
Sibel Çimen ◽  
Abdulkerim Çapar ◽  
Dursun Ali Ekinci ◽  
Umut Engin Ayten ◽  
Bilal Ersen Kerman ◽  
...  
Keyword(s):  
Image Analysis ◽  
Feature Extraction ◽  
Deep Learning ◽  
Neurological Diseases ◽  
Binary Classification ◽  
Signal Transmission ◽  
Machine Learning Techniques ◽  
Neuronal Communication ◽  
Learning Classifier ◽  
Learning Techniques

AbstractOligodendrocytes wrap around the axons and form the myelin. Myelin facilitates rapid neural signal transmission. Any damage to myelin disrupts neuronal communication leading to neurological diseases such as multiple sclerosis (MS). There is no cure for MS. This is, in part, due to lack of an efficient method for myelin quantification during drug screening. In this study, an image analysis based myelin sheath detection method, DeepMQ, is developed. The method consists of a feature extraction step followed by a deep learning based binary classification module. The images, which were acquired on a confocal microscope contain three channels and multiple z-sections. Each channel represents either oligodendroyctes, neurons, or nuclei. During feature extraction, 26-neighbours of each voxel is mapped onto a 2D feature image. This image is, then, fed to the deep learning classifier, in order to detect myelin. Results indicate that 93.38% accuracy is achieved in a set of fluorescence microscope images of mouse stem cell-derived oligodendroyctes and neurons. To the best of authors’ knowledge, this is the first study utilizing image analysis along with machine learning techniques to quantify myelination.

scholarly journals A Hybrid Approach to Cognition in Radars

2018 ◽  
Vol 68 (2) ◽  
pp. 183 ◽  
Author(s):  
M. Justin Sagayaraj ◽  
Jithesh V. ◽  
J.B. Singh ◽  
Dange Roshani ◽  
K.G. Srinivasa
Keyword(s):  
Deep Learning ◽  
Cognitive Architecture ◽  
Hybrid Approach ◽  
Experimental Studies ◽  
Vital Role ◽  
Cognitive Architectures ◽  
Radar Systems ◽  
Learning Techniques ◽  
Time Calculation ◽  
High Resolution Radar

In many engineering domains, cognition is emerging to play vital role. Cognition will play crucial role in radar engineering as well for the development of next generation radars. In this paper, a cognitive architecture for radars is introduced, based on hybrid cognitive architectures. The paper proposes deep learning applications for integrated target classification based on high-resolution radar range profile measurements and target revisit time calculation as case studies. The proposed architecture is based on the artificial cognitive systems concepts and provides a basis for addressing cognition in radars, which is inadequately explored for radar systems. Initial experimental studies on the applicability of deep learning techniques under this approach provided promising results.

scholarly journals Detection of Disease in Maize Plant Using Deep Learning

2021 ◽  
Vol 36 (2) ◽  
pp. 82-88
Author(s):  
Dr.B. Rama Subba Reddy ◽  
Dr.G. Bindu Madhavi ◽  
C.H. Sri Lakshmi ◽  
Dr.K. Venkata Nagendra ◽  
Dr.R. Sridevi
Keyword(s):  
Deep Learning ◽  
Food Production ◽  
Automated Detection ◽  
Plant Diseases ◽  
Maize Plant ◽  
Small Scale ◽  
Traditional Farming ◽  
Cercospora Leaf Spot ◽  
Detection Model ◽  
Learning Techniques

Agriculture is vital to the Indian economy as over 17 percent of total GDP and employs more than 60 percent of the population relies on agriculture. This research focuses on plant diseases as they create a major threat to food production as well as for small-scale farmer’s livelihood. Expert workers are employed in traditional farming to visually evaluate row by row to identify plant diseases, which is a time-consuming, labor-intensive activity that is potentially error-prone because it is done by humans. The aim of this research is to develop an automated detection model that uses a combination of image processing and deep learning techniques (Faster R-CNN+ResNet50) to analyze real-time images and detect and classify the three common maize plant diseases: Common Rust, Cercospora Leaf Spot, and Northern Leaf Blight. The proposed system achieved 91% accuracy and successfully detects three maize diseases.

scholarly journals Detection of Bone Metastases on Bone Scans through Image Classification with Contrastive Learning

2021 ◽  
Vol 11 (12) ◽  
pp. 1248
Author(s):  
Te-Chun Hsieh ◽  
Chiung-Wei Liao ◽  
Yung-Chi Lai ◽  
Kin-Man Law ◽  
Pak-Ki Chan ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Bone Metastases ◽  
Binary Classification ◽  
Characteristic Curve ◽  
Convolutional Networks ◽  
Learning Techniques ◽  
Bone Scans ◽  
Improving Patient Care ◽  
Physician Workload

Patients with bone metastases have poor prognoses. A bone scan is a commonly applied diagnostic tool for this condition. However, its accuracy is limited by the nonspecific character of radiopharmaceutical accumulation, which indicates all-cause bone remodeling. The current study evaluated deep learning techniques to improve the efficacy of bone metastasis detection on bone scans, retrospectively examining 19,041 patients aged 22 to 92 years who underwent bone scans between May 2011 and December 2019. We developed several functional imaging binary classification deep learning algorithms suitable for bone scans. The presence or absence of bone metastases as a reference standard was determined through a review of image reports by nuclear medicine physicians. Classification was conducted with convolutional neural network-based (CNN-based), residual neural network (ResNet), and densely connected convolutional networks (DenseNet) models, with and without contrastive learning. Each set of bone scans contained anterior and posterior images with resolutions of 1024 × 256 pixels. A total of 37,427 image sets were analyzed. The overall performance of all models improved with contrastive learning. The accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve, and negative predictive value (NPV) for the optimal model were 0.961, 0.878, 0.599, 0.712, 0.92 and 0.965, respectively. In particular, the high NPV may help physicians safely exclude bone metastases, decreasing physician workload, and improving patient care.

scholarly journals Designing Audio Equalization Filters by Deep Neural Networks

2020 ◽  
Vol 10 (7) ◽  
pp. 2483 ◽  
Author(s):  
Giovanni Pepe ◽  
Leonardo Gabrielli ◽  
Stefano Squartini ◽  
Luca Cattani
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Frequency Response ◽  
Superior Performance ◽  
Linear Filters ◽  
Audio Quality ◽  
Learning Techniques ◽  
Convolutional Autoencoder ◽  
Active Research

Audio equalization is an active research topic aiming at improving the audio quality of a loudspeaker system by correcting the overall frequency response using linear filters. The estimation of their coefficients is not an easy task, especially in binaural and multipoint scenarios, due to the contribution of multiple impulse responses to each listening point. This paper presents a deep learning approach for tuning filter coefficients employing three different neural networks architectures—the Multilayer Perceptron, the Convolutional Neural Network, and the Convolutional Autoencoder. Suitable loss functions are proposed for each architecture, and are formulated in terms of spectral Euclidean distance. The experiments were conducted in the automotive scenario, considering several loudspeakers and microphones. The obtained results show that deep learning techniques give superior performance compared to baseline methods, achieving almost flat magnitude frequency response.

scholarly journals Twitter Sentiment Analysis using Deep Learning

2020 ◽  
Vol 9 (7) ◽  
pp. 1040-1044
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
Customer Service ◽  
Fast Food ◽  
Short Term Memory ◽  
Binary Classification ◽  
Product Reviews ◽  
Learning Techniques ◽  
Fast Food Restaurants ◽  
Sentiment Detection

The whole world is changing rapidly with current innovations, using the Internet, has become a fundamental requirement in people's lives. Nowadays, a massive amount of data made by social networks based on daily user activities. Gathering and analyzing people's opinions are crucial for business applications when they are extracted and analyzed accurately. This data helps the corporations to improve product quality and provide better customer service. But manually analyzing opinions is an impossible task because the content is unorganized. For this reason, we applied sentiment analysis that is the process of extracting and analyzing the unorganized data automatically. The primary steps to perform sentiment analysis include data collection, pre-processing, word embedding, sentiment detection, and classification using deep learning techniques. This work focused on the binary classification of sentiments for three product reviews of fast-food restaurants. Twitter is chosen as the source of data to perform analysis. All tweets were collected automatically by using Tweepy. The experimented dataset divided into half of the positive and half of the negative tweets. In this paper, three deep learning techniques implemented, which are Convolutional Neural Network (CNN), Bi-Directional Long Short-Term Memory (Bi-LSTM), and CNN-Bi-LSTM, The performance of each of them measured and compared in terms of accuracy, precision, recall, and F1 score Finally, Bi-LSTM scored the highest performance in all metrics compared to the two other techniques.

Sign in / Sign up

Export Citation Format

Share Document