Cotton Stand Counting from Unmanned Aerial System Imagery Using MobileNet and CenterNet Deep Learning Models

An accurate stand count is a prerequisite to determining the emergence rate, assessing seedling vigor, and facilitating site-specific management for optimal crop production. Traditional manual counting methods in stand assessment are labor intensive and time consuming for large-scale breeding programs or production field operations. This study aimed to apply two deep learning models, the MobileNet and CenterNet, to detect and count cotton plants at the seedling stage with unmanned aerial system (UAS) images. These models were trained with two datasets containing 400 and 900 images with variations in plant size and soil background brightness. The performance of these models was assessed with two testing datasets of different dimensions, testing dataset 1 with 300 by 400 pixels and testing dataset 2 with 250 by 1200 pixels. The model validation results showed that the mean average precision (mAP) and average recall (AR) were 79% and 73% for the CenterNet model, and 86% and 72% for the MobileNet model with 900 training images. The accuracy of cotton plant detection and counting was higher with testing dataset 1 for both CenterNet and MobileNet models. The results showed that the CenterNet model had a better overall performance for cotton plant detection and counting with 900 training images. The results also indicated that more training images are required when applying object detection models on images with different dimensions from training datasets. The mean absolute percentage error (MAPE), coefficient of determination (R2), and the root mean squared error (RMSE) values of the cotton plant counting were 0.07%, 0.98 and 0.37, respectively, with testing dataset 1 for the CenterNet model with 900 training images. Both MobileNet and CenterNet models have the potential to accurately and timely detect and count cotton plants based on high-resolution UAS images at the seedling stage. This study provides valuable information for selecting the right deep learning tools and the appropriate number of training images for object detection projects in agricultural applications.

Download Full-text

Parsing of Urban Facades from 3D Point Clouds Based on a Novel Multi-View Domain

Photogrammetric Engineering & Remote Sensing ◽

10.14358/pers.87.4.283 ◽

2021 ◽

Vol 87 (4) ◽

pp. 283-293

Author(s):

Wei Wang ◽

Yuan Xu ◽

Yingchao Ren ◽

Gang Wang

Keyword(s):

Deep Learning ◽

Prior Knowledge ◽

Performance Improvement ◽

Data Distribution ◽

Point Clouds ◽

Learning Models ◽

Data Set ◽

3D Point Clouds ◽

Segmentation Accuracy ◽

The Mean

Recently, performance improvement in facade parsing from 3D point clouds has been brought about by designing more complex network structures, which cost huge computing resources and do not take full advantage of prior knowledge of facade structure. Instead, from the perspective of data distribution, we construct a new hierarchical mesh multi-view data domain based on the characteristics of facade objects to achieve fusion of deep-learning models and prior knowledge, thereby significantly improving segmentation accuracy. We comprehensively evaluate the current mainstream method on the RueMonge 2014 data set and demonstrate the superiority of our method. The mean intersection-over-union index on the facade-parsing task reached 76.41%, which is 2.75% higher than the current best result. In addition, through comparative experiments, the reasons for the performance improvement of the proposed method are further analyzed.

Download Full-text

Development of U-Net Breast Density Segmentation Method for Fat-Sat MR Images Using Transfer Learning Based on Non-Fat-Sat Model

Journal of Digital Imaging ◽

10.1007/s10278-021-00472-z ◽

2021 ◽

Author(s):

Yang Zhang ◽

Siwa Chan ◽

Jeon-Hor Chen ◽

Kai-Ting Chang ◽

Chin-Yao Lin ◽

...

Keyword(s):

Deep Learning ◽

Transfer Learning ◽

Breast Tissue ◽

Ground Truth ◽

Training Dataset ◽

Breast Volume ◽

Segmentation Method ◽

Tissue Segmentation ◽

Testing Dataset ◽

The Mean

AbstractTo develop a U-net deep learning method for breast tissue segmentation on fat-sat T1-weighted (T1W) MRI using transfer learning (TL) from a model developed for non-fat-sat images. The training dataset (N = 126) was imaged on a 1.5 T MR scanner, and the independent testing dataset (N = 40) was imaged on a 3 T scanner, both using fat-sat T1W pulse sequence. Pre-contrast images acquired in the dynamic-contrast-enhanced (DCE) MRI sequence were used for analysis. All patients had unilateral cancer, and the segmentation was performed using the contralateral normal breast. The ground truth of breast and fibroglandular tissue (FGT) segmentation was generated using a template-based segmentation method with a clustering algorithm. The deep learning segmentation was performed using U-net models trained with and without TL, by using initial values of trainable parameters taken from the previous model for non-fat-sat images. The ground truth of each case was used to evaluate the segmentation performance of the U-net models by calculating the dice similarity coefficient (DSC) and the overall accuracy based on all pixels. Pearson’s correlation was used to evaluate the correlation of breast volume and FGT volume between the U-net prediction output and the ground truth. In the training dataset, the evaluation was performed using tenfold cross-validation, and the mean DSC with and without TL was 0.97 vs. 0.95 for breast and 0.86 vs. 0.80 for FGT. When the final model developed with and without TL from the training dataset was applied to the testing dataset, the mean DSC was 0.89 vs. 0.83 for breast and 0.81 vs. 0.81 for FGT, respectively. Application of TL not only improved the DSC, but also decreased the required training case number. Lastly, there was a high correlation (R2 > 0.90) for both the training and testing datasets between the U-net prediction output and ground truth for breast volume and FGT volume. U-net can be applied to perform breast tissue segmentation on fat-sat images, and TL is an efficient strategy to develop a specific model for each different dataset.

Download Full-text

Development and Evaluation of Speech Synthesis System Based on Deep Learning Models

Symmetry ◽

10.3390/sym13050819 ◽

2021 ◽

Vol 13 (5) ◽

pp. 819

Author(s):

Alakbar Valizada ◽

Sevil Jafarova ◽

Emin Sultanov ◽

Samir Rustamov

Keyword(s):

Deep Learning ◽

Speech Synthesis ◽

Online Survey ◽

Subjective Evaluation ◽

Learning Models ◽

Text To Speech ◽

Opinion Score ◽

News Website ◽

Text To Speech Synthesis ◽

The Mean

This study concentrates on the investigation, development, and evaluation of Text-to-Speech Synthesis systems based on Deep Learning models for the Azerbaijani Language. We have selected and compared state-of-the-art models-Tacotron and Deep Convolutional Text-to-Speech (DC TTS) systems to achieve the most optimal model. Both systems were trained on the 24 h speech dataset of the Azerbaijani language collected and processed from the news website. To analyze the quality and intelligibility of the speech signals produced by two systems, 34 listeners participated in an online survey containing subjective evaluation tests. The results of the study indicated that according to the Mean Opinion Score, Tacotron demonstrated better results for the In-Vocabulary words; however, DC TTS indicated a higher performance of the Out-Of-Vocabulary words synthesis.

Download Full-text

Face Recognition with CNN and Inception Deep Learning Models

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.c4476.098319 ◽

2019 ◽

Vol 8 (3) ◽

pp. 1932-1938

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Face Recognition ◽

Convolutional Neural Network ◽

Training Image ◽

Learning Models ◽

Training Images ◽

Testing Data ◽

Facial Images

In this work, deep learning methods are used to classify the facial images. ORL Database is used for the purpose of training the models and for testing. Three kinds of models are developed and their performances are measured. Convolutional Neural Networks (CNN), Convolutional Neural Network Based Inception Model with single training image per class (CNN-INC) and Convolutional Neural Network Based Inception Model with several training images per class (CNN-INC-MEAN) are developed. The ORL database has ten facial images for each person. Five images are used for training purpose and remaining 5 images are used for testing. The five images for the training are chosen randomly so that two sets of training and testing data is generated. The models are trained and tested on the two sets that are drawn from the same population. The results are presented for accuracy of face recognition

Download Full-text

Sorghum Panicle Detection and Counting Using Unmanned Aerial System Images and Deep Learning

Frontiers in Plant Science ◽

10.3389/fpls.2020.534853 ◽

2020 ◽

Vol 11 ◽

Author(s):

Zhe Lin ◽

Wenxuan Guo

Keyword(s):

Deep Learning ◽

Unmanned Aerial System ◽

Detection And Counting

Download Full-text

Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort

Scientific Reports ◽

10.1038/s41598-020-80839-4 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Kaori Ishii ◽

Ryo Asaoka ◽

Takashi Omoto ◽

Shingo Mitaki ◽

Yuri Fujino ◽

...

Keyword(s):

Deep Learning ◽

Intraocular Pressure ◽

Mean Absolute Error ◽

Absolute Error ◽

Fundus Photography ◽

Training Dataset ◽

Support Vector ◽

Testing Dataset ◽

The Mean ◽

Systemic Variables

AbstractThe purpose of the current study was to predict intraocular pressure (IOP) using color fundus photography with a deep learning (DL) model, or, systemic variables with a multivariate linear regression model (MLM), along with least absolute shrinkage and selection operator regression (LASSO), support vector machine (SVM), and Random Forest: (RF). Training dataset included 3883 examinations from 3883 eyes of 1945 subjects and testing dataset 289 examinations from 289 eyes from 146 subjects. With the training dataset, MLM was constructed to predict IOP using 35 systemic variables and 25 blood measurements. A DL model was developed to predict IOP from color fundus photographs. The prediction accuracy of each model was evaluated through the absolute error and the marginal R-squared (mR2), using the testing dataset. The mean absolute error with MLM was 2.29 mmHg, which was significantly smaller than that with DL (2.70 dB). The mR2 with MLM was 0.15, whereas that with DL was 0.0066. The mean absolute error (between 2.24 and 2.30 mmHg) and mR2 (between 0.11 and 0.15) with LASSO, SVM and RF were similar to or poorer than MLM. A DL model to predict IOP using color fundus photography proved far less accurate than MLM using systemic variables.

Download Full-text

Robust image-based risk predictions from the deep learning of lung tumors in motion

10.1101/2021.07.28.21261255 ◽

2021 ◽

Author(s):

Amishi Bajaj ◽

P. Troy Teo ◽

James Randall ◽

Bin Lou ◽

Jainil Shah ◽

...

Keyword(s):

Lung Cancer ◽

Deep Learning ◽

Free Breathing ◽

Learning Models ◽

Model Accuracy ◽

Failure Risk ◽

Object Appearance ◽

The Mean ◽

Robust Image ◽

The Impact

Deep learning (DL) models that use medical images to predict clinical outcomes are poised for clinical translation. For tumors that reside in organs that move, however, the impact of motion (i.e. degenerated object appearance or blur) on DL model accuracy remains unclear. Here we examine the impact of tumor motion on an image-based DL framework that predicts local failure risk for patients with lung cancer receiving stereotactic body radiotherapy. We show that an image-based DL risk score derived from a series of four-dimensional CT images varies in a deterministic, sinusoidal trajectory in phase with the respiratory cycle. Critically, the mean of the scores derived from time series of images and the score obtained from free breathing scans (average tumor position) were highly associated (Pearson r = 0.99). These results indicate that deep learning models of tumors in motion can be robust to fluctuations in object appearance due to movement.

Download Full-text

Multi-label topic classification for COVID-19 literature annotation using an ensemble model based on PubMedBERT

10.1101/2021.10.26.465946 ◽

2021 ◽

Author(s):

Shubo Tian ◽

Jinfeng Zhang

Keyword(s):

Deep Learning ◽

Loss Function ◽

Language Model ◽

Ensemble Model ◽

Test Results ◽

Learning Models ◽

Baseline Model ◽

Satisfactory Performance ◽

The Mean ◽

Better Than

The BioCreative VII Track 5 calls for participants to tackle the multi-label classification task for automated topic annotation of COVID-19 literature. In our participation, we evaluated several deep learning models built on PubMedBERT, a pre-trained language model, with different strategies addressing the challenges of the task. Specifically, multi-instance learning was used to deal with the large variation in the lengths of the articles, and focal loss function was used to address the imbalance in the distribution of different topics. We found that the ensemble model performed the best among all the models we have tested. Test results of our submissions showed that our approach was able to achieve satisfactory performance with an F1 score of 0.9247, which is significantly better than the baseline model (F1 score: 0.8678) and the mean of all the submissions (F1 score: 0.8931).

Download Full-text

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

10.26434/chemrxiv.12562121 ◽

2020 ◽

Author(s):

Dean Sumner ◽

Jiazhen He ◽

Amol Thakkar ◽

Ola Engkvist ◽

Esben Jannik Bjerrum

Keyword(s):

Neural Networks ◽

Pattern Recognition ◽

Deep Learning ◽

Recurrent Neural Networks ◽

Data Augmentation ◽

State Of The Art ◽

Sequence Similarity ◽

Learning Models ◽

Underlying Network

SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as attentional gain – an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.

Download Full-text

Improving the Accuracy of Protein-Ligand Binding Affinity Prediction by Deep Learning Models: Benchmark and Model

10.26434/chemrxiv.9866912 ◽

2019 ◽

Author(s):

Mohammad Rezaei ◽

Yanjun Li ◽

Xiaolin Li ◽

Chenglong Li

Keyword(s):

Deep Learning ◽

Drug Design ◽

Binding Affinity ◽

Benchmark Dataset ◽

Rational Drug Design ◽

Learning Models ◽

Structure Based Drug Design ◽

Binding Affinity Prediction ◽

Affinity Prediction ◽

Rational Drug

Introduction: The ability to discriminate among ligands binding to the same protein target in terms of their relative binding affinity lies at the heart of structure-based drug design. Any improvement in the accuracy and reliability of binding affinity prediction methods decreases the discrepancy between experimental and computational results. Objectives: The primary objectives were to find the most relevant features affecting binding affinity prediction, least use of manual feature engineering, and improving the reliability of binding affinity prediction using efficient deep learning models by tuning the model hyperparameters. Methods: The binding site of target proteins was represented as a grid box around their bound ligand. Both binary and distance-dependent occupancies were examined for how an atom affects its neighbor voxels in this grid. A combination of different features including ANOLEA, ligand elements, and Arpeggio atom types were used to represent the input. An efficient convolutional neural network (CNN) architecture, DeepAtom, was developed, trained and tested on the PDBbind v2016 dataset. Additionally an extended benchmark dataset was compiled to train and evaluate the models. Results: The best DeepAtom model showed an improved accuracy in the binding affinity prediction on PDBbind core subset (Pearson’s R=0.83) and is better than the recent state-of-the-art models in this field. In addition when the DeepAtom model was trained on our proposed benchmark dataset, it yields higher correlation compared to the baseline which confirms the value of our model. Conclusions: The promising results for the predicted binding affinities is expected to pave the way for embedding deep learning models in virtual screening and rational drug design fields.

Download Full-text