A Rapid and Highly Efficient Method for the Identification of Soybean Seed Varieties: Hyperspectral Images Combined with Transfer Learning

Convolutional neural network (CNN) can be used to quickly identify crop seed varieties. 1200 seeds of ten soybean varieties were selected, hyperspectral images of both the front and the back of the seeds were collected, and the reflectance of soybean was derived from the hyperspectral images. A total of 9600 images were obtained after data augmentation, and the images were divided into a training set, validation set, and test set with a 3:1:1 ratio. Pretrained models (AlexNet, ResNet18, Xception, InceptionV3, DenseNet201, and NASNetLarge) after fine-tuning were used for transfer training. The optimal CNN model for soybean seed variety identification was selected. Furthermore, the traditional machine learning models for soybean seed variety identification were established by using reflectance as input. The results show that the six models all achieved 91% accuracy in the validation set and achieved accuracy values of 90.6%, 94.5%, 95.4%, 95.6%, 96.8%, and 97.2%, respectively, in the test set. This method is better than the identification of soybean seed varieties based on hyperspectral reflectance. The experimental results support a novel method for identifying soybean seeds rapidly and accurately, and this method also provides a good reference for the identification of other crop seeds.

Download Full-text

PSSPNN: PatchShuffle Stochastic Pooling Neural Network for an Explainable Diagnosis of COVID-19 with Multiple-Way Data Augmentation

Computational and Mathematical Methods in Medicine ◽

10.1155/2021/6633755 ◽

2021 ◽

Vol 2021 ◽

pp. 1-18

Author(s):

Shui-Hua Wang ◽

Yin Zhang ◽

Xiaochun Cheng ◽

Xin Zhang ◽

Yu-Dong Zhang

Keyword(s):

Neural Network ◽

Pulmonary Tuberculosis ◽

Healthy Subjects ◽

Data Augmentation ◽

State Of The Art ◽

Accurate Diagnosis ◽

Test Set ◽

The World ◽

Stochastic Pooling ◽

Better Than

Aim. COVID-19 has caused large death tolls all over the world. Accurate diagnosis is of significant importance for early treatment. Methods. In this study, we proposed a novel PSSPNN model for classification between COVID-19, secondary pulmonary tuberculosis, community-captured pneumonia, and healthy subjects. PSSPNN entails five improvements: we first proposed the n-conv stochastic pooling module. Second, a novel stochastic pooling neural network was proposed. Third, PatchShuffle was introduced as a regularization term. Fourth, an improved multiple-way data augmentation was used. Fifth, Grad-CAM was utilized to interpret our AI model. Results. The 10 runs with random seed on the test set showed our algorithm achieved a microaveraged F1 score of 95.79%. Moreover, our method is better than nine state-of-the-art approaches. Conclusion. This proposed PSSPNN will help assist radiologists to make diagnosis more quickly and accurately on COVID-19 cases.

Download Full-text

Multi-Class Parrot Image Classification Including Subspecies with Similar Appearance

Biology ◽

10.3390/biology10111140 ◽

2021 ◽

Vol 10 (11) ◽

pp. 1140

Author(s):

Woohyuk Jang ◽

Eui Chul Lee

Keyword(s):

Deep Learning ◽

Endangered Species ◽

Image Classification ◽

Data Augmentation ◽

Training Model ◽

Test Set ◽

Plant Image ◽

Similar Appearance ◽

Parrot Species ◽

Validation Set

Owing to climate change and human indiscriminate development, the population of endangered species has been decreasing. To protect endangered species, many countries worldwide have adopted the CITES treaty to prevent the extinction of endangered plants and animals. Moreover, research has been conducted using diverse approaches, particularly deep learning-based animal and plant image recognition methods. In this paper, we propose an automated image classification method for 11 endangered parrot species included in CITES. The 11 species include subspecies that are very similar in appearance. Data images were collected from the Internet and built in cooperation with Seoul Grand Park Zoo to build an indigenous database. The dataset for deep learning training consisted of 70% training set, 15% validation set, and 15% test set. In addition, a data augmentation technique was applied to reduce the data collection limit and prevent overfitting. The performance of various backbone CNN architectures (i.e., VGGNet, ResNet, and DenseNet) were compared using the SSD model. The experiment derived the test set image performance for the training model, and the results show that the DenseNet18 had the best performance with an mAP of approximately 96.6% and an inference time of 0.38 s.

Download Full-text

PercepPan: Towards Unsupervised Pan-Sharpening Based on Perceptual Loss

Remote Sensing ◽

10.3390/rs12142318 ◽

2020 ◽

Vol 12 (14) ◽

pp. 2318 ◽

Cited By ~ 1

Author(s):

Changsheng Zhou ◽

Jiangshe Zhang ◽

Junmin Liu ◽

Chunxia Zhang ◽

Rongrong Fei ◽

...

Keyword(s):

Ground Truth ◽

Fine Tuning ◽

The Novel ◽

Multispectral Images ◽

Training Paradigm ◽

Supervised Training ◽

Random Initialization ◽

Degradation Step ◽

Novel Method ◽

Better Than

In the literature of pan-sharpening based on neural networks, high resolution multispectral images as ground-truth labels generally are unavailable. To tackle the issue, a common method is to degrade original images into a lower resolution space for supervised training under the Wald’s protocol. In this paper, we propose an unsupervised pan-sharpening framework, referred to as “perceptual pan-sharpening”. This novel method is based on auto-encoder and perceptual loss, and it does not need the degradation step for training. For performance boosting, we also suggest a novel training paradigm, called “first supervised pre-training and then unsupervised fine-tuning”, to train the unsupervised framework. Experiments on the QuickBird dataset show that the framework with different generator architectures could get comparable results with the traditional supervised counterpart, and the novel training paradigm performs better than random initialization. When generalizing to the IKONOS dataset, the unsupervised framework could still get competitive results over the supervised ones.

Download Full-text

Using Connectionist Modules for Decision Support

Methods of Information in Medicine ◽

10.1055/s-0038-1634790 ◽

1990 ◽

Vol 29 (03) ◽

pp. 167-181 ◽

Cited By ~ 6

Author(s):

G. Hripcsak

Keyword(s):

Decision Support ◽

Standard Deviation ◽

Confidence Interval ◽

Posterior Probability ◽

Back Propagation ◽

Connectionist Model ◽

Test Set ◽

The Third ◽

Independent Test ◽

Better Than

AbstractA connectionist model for decision support was constructed out of several back-propagation modules. Manifestations serve as input to the model; they may be real-valued, and the confidence in their measurement may be specified. The model produces as its output the posterior probability of disease. The model was trained on 1,000 cases taken from a simulated underlying population with three conditionally independent manifestations. The first manifestation had a linear relationship between value and posterior probability of disease, the second had a stepped relationship, and the third was normally distributed. An independent test set of 30,000 cases showed that the model was better able to estimate the posterior probability of disease (the standard deviation of residuals was 0.046, with a 95% confidence interval of 0.046-0.047) than a model constructed using logistic regression (with a standard deviation of residuals of 0.062, with a 95% confidence interval of 0.062-0.063). The model fitted the normal and stepped manifestations better than the linear one. It accommodated intermediate levels of confidence well.

Download Full-text

Deep Learning Techniques for Grape Plant Species Identification in Natural Images

Sensors ◽

10.3390/s19224850 ◽

2019 ◽

Vol 19 (22) ◽

pp. 4850 ◽

Cited By ~ 6

Author(s):

Carlos S. Pereira ◽

Raul Morais ◽

Manuel J. C. S. Reis

Keyword(s):

Transfer Learning ◽

Climatic Conditions ◽

Fine Tuning ◽

Variety Identification ◽

Test Accuracy ◽

Accuracy Score ◽

Learning Techniques ◽

Four Corners ◽

Integrated Software ◽

Grape Varieties

Frequently, the vineyards in the Douro Region present multiple grape varieties per parcel and even per row. An automatic algorithm for grape variety identification as an integrated software component was proposed that can be applied, for example, to a robotic harvesting system. However, some issues and constraints in its development were highlighted, namely, the images captured in natural environment, low volume of images, high similarity of the images among different grape varieties, leaf senescence, and significant changes on the grapevine leaf and bunch images in the harvest seasons, mainly due to adverse climatic conditions, diseases, and the presence of pesticides. In this paper, the performance of the transfer learning and fine-tuning techniques based on AlexNet architecture were evaluated when applied to the identification of grape varieties. Two natural vineyard image datasets were captured in different geographical locations and harvest seasons. To generate different datasets for training and classification, some image processing methods, including a proposed four-corners-in-one image warping algorithm, were used. The experimental results, obtained from the application of an AlexNet-based transfer learning scheme and trained on the image dataset pre-processed through the four-corners-in-one method, achieved a test accuracy score of 77.30%. Applying this classifier model, an accuracy of 89.75% on the popular Flavia leaf dataset was reached. The results obtained by the proposed approach are promising and encouraging in helping Douro wine growers in the automatic task of identifying grape varieties.

Download Full-text

A MYC-Driven Plasma Polyamine Signature for Early Detection of Ovarian Cancer

Cancers ◽

10.3390/cancers13040913 ◽

2021 ◽

Vol 13 (4) ◽

pp. 913

Author(s):

Johannes Fahrmann ◽

Ehsan Irajizad ◽

Makoto Kobayashi ◽

Jody Vykoukal ◽

Jennifer Dennison ◽

...

Keyword(s):

Ovarian Cancer ◽

Early Stage ◽

Area Under The Curve ◽

Polyamine Metabolism ◽

Healthy Controls ◽

Test Set ◽

Exact Test ◽

Oncogenic Driver ◽

Characteristic Area ◽

Validation Set

MYC is an oncogenic driver in the pathogenesis of ovarian cancer. We previously demonstrated that MYC regulates polyamine metabolism in triple-negative breast cancer (TNBC) and that a plasma polyamine signature is associated with TNBC development and progression. We hypothesized that a similar plasma polyamine signature may associate with ovarian cancer (OvCa) development. Using mass spectrometry, four polyamines were quantified in plasma from 116 OvCa cases and 143 controls (71 healthy controls + 72 subjects with benign pelvic masses) (Test Set). Findings were validated in an independent plasma set from 61 early-stage OvCa cases and 71 healthy controls (Validation Set). Complementarity of polyamines with CA125 was also evaluated. Receiver operating characteristic area under the curve (AUC) of individual polyamines for distinguishing cases from healthy controls ranged from 0.74–0.88. A polyamine signature consisting of diacetylspermine + N-(3-acetamidopropyl)pyrrolidin-2-one in combination with CA125 developed in the Test Set yielded improvement in sensitivity at >99% specificity relative to CA125 alone (73.7% vs 62.2%; McNemar exact test 2-sided P: 0.019) in the validation set and captured 30.4% of cases that were missed with CA125 alone. Our findings reveal a MYC-driven plasma polyamine signature associated with OvCa that complemented CA125 in detecting early-stage ovarian cancer.

Download Full-text

Deep Learning-Based Differentiation between Mucinous Cystic Neoplasm and Serous Cystic Neoplasm in the Pancreas Using Endoscopic Ultrasonography

Diagnostics ◽

10.3390/diagnostics11061052 ◽

2021 ◽

Vol 11 (6) ◽

pp. 1052

Author(s):

Leang Sim Nguon ◽

Kangwon Seo ◽

Jung-Hyun Lim ◽

Tae-Jun Song ◽

Sung-Hyun Cho ◽

...

Keyword(s):

Decision Making ◽

Deep Learning ◽

Network Model ◽

Endoscopic Ultrasonography ◽

Data Augmentation ◽

Clinical Information ◽

Training Data ◽

Fine Tuning ◽

Cystic Neoplasm ◽

Cystic Neoplasms

Mucinous cystic neoplasms (MCN) and serous cystic neoplasms (SCN) account for a large portion of solitary pancreatic cystic neoplasms (PCN). In this study we implemented a convolutional neural network (CNN) model using ResNet50 to differentiate between MCN and SCN. The training data were collected retrospectively from 59 MCN and 49 SCN patients from two different hospitals. Data augmentation was used to enhance the size and quality of training datasets. Fine-tuning training approaches were utilized by adopting the pre-trained model from transfer learning while training selected layers. Testing of the network was conducted by varying the endoscopic ultrasonography (EUS) image sizes and positions to evaluate the network performance for differentiation. The proposed network model achieved up to 82.75% accuracy and a 0.88 (95% CI: 0.817–0.930) area under curve (AUC) score. The performance of the implemented deep learning networks in decision-making using only EUS images is comparable to that of traditional manual decision-making using EUS images along with supporting clinical information. Gradient-weighted class activation mapping (Grad-CAM) confirmed that the network model learned the features from the cyst region accurately. This study proves the feasibility of diagnosing MCN and SCN using a deep learning network model. Further improvement using more datasets is needed.

Download Full-text

Predicting drug–target interactions Based on the Ensemble Models of Multiple Feature Pairs

International Journal of Molecular Sciences ◽

10.3390/ijms22126598 ◽

2021 ◽

Vol 22 (12) ◽

pp. 6598

Author(s):

Cheng Wang ◽

Jun Zhang ◽

Peng Chen ◽

Bing Wang

Keyword(s):

Drug Target ◽

Essential Feature ◽

Characteristic Curve ◽

Prediction Method ◽

New Drugs ◽

Good Prediction ◽

Ensemble Model ◽

Test Set ◽

Multiple Feature ◽

Validation Set

Backgroud: The prediction of drug–target interactions (DTIs) is of great significance in drug development. It is time-consuming and expensive in traditional experimental methods. Machine learning can reduce the cost of prediction and is limited by the characteristics of imbalanced datasets and problems of essential feature selection. Methods: The prediction method based on the Ensemble model of Multiple Feature Pairs (Ensemble-MFP) is introduced. Firstly, three negative sets are generated according to the Euclidean distance of three feature pairs. Then, the negative samples of the validation set/test set are randomly selected from the union set of the three negative sets in the validation set/test set. At the same time, the ensemble model with weight is optimized and applied to the test set. Results: The area under the receiver operating characteristic curve (area under ROC, AUC) in three out of four sub-datasets in gold standard datasets was more than 94.0% in the prediction of new drugs. The effectiveness of the proposed method is also shown with the comparison of state-of-the-art methods and demonstration of predicted drug–target pairs. Conclusion: The Ensemble-MFP can weigh the existing feature pairs and has a good prediction effect for general prediction on new drugs.

Download Full-text

AT2ES: Simultaneous Atmospheric Transmittance-Temperature-Emissivity Separation Using Online Upper Midwave Infrared Hyperspectral Images

Remote Sensing ◽

10.3390/rs13071249 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1249

Author(s):

Sungho Kim ◽

Jungsub Shin ◽

Sunho Kim

Keyword(s):

Air Temperature ◽

Atmospheric Correction ◽

Hyperspectral Data ◽

Hyperspectral Images ◽

Co2 Absorption ◽

Infrared Band ◽

Data Regression ◽

Midwave Infrared ◽

Novel Method ◽

Atmospheric Transmittance

This paper presents a novel method for atmospheric transmittance-temperature-emissivity separation (AT2ES) using online midwave infrared hyperspectral images. Conventionally, temperature and emissivity separation (TES) is a well-known problem in the remote sensing domain. However, previous approaches use the atmospheric correction process before TES using MODTRAN in the long wave infrared band. Simultaneous online atmospheric transmittance-temperature-emissivity separation starts with approximation of the radiative transfer equation in the upper midwave infrared band. The highest atmospheric band is used to estimate surface temperature, assuming high emissive materials. The lowest atmospheric band (CO2 absorption band) is used to estimate air temperature. Through onsite hyperspectral data regression, atmospheric transmittance is obtained from the y-intercept, and emissivity is separated using the observed radiance, the separated object temperature, the air temperature, and atmospheric transmittance. The advantage with the proposed method is from being the first attempt at simultaneous AT2ES and online separation without any prior knowledge and pre-processing. Midwave Fourier transform infrared (FTIR)-based outdoor experimental results validate the feasibility of the proposed AT2ES method.

Download Full-text

Variety Identification of Orchids Using Fourier Transform Infrared Spectroscopy Combined with Stacked Sparse Auto-Encoder

Molecules ◽

10.3390/molecules24132506 ◽

2019 ◽

Vol 24 (13) ◽

pp. 2506 ◽

Cited By ~ 1

Author(s):

Yunfeng Chen ◽

Yue Chen ◽

Xuping Feng ◽

Xufeng Yang ◽

Jinnuo Zhang ◽

...

Keyword(s):

Fourier Transform ◽

Principal Component ◽

Fourier Transform Infrared ◽

Spectroscopic Technique ◽

Variety Identification ◽

Support Vector ◽

K Nearest Neighbors ◽

Discriminant Models ◽

The Fourier Transform ◽

Better Than

The feasibility of using the fourier transform infrared (FTIR) spectroscopic technique with a stacked sparse auto-encoder (SSAE) to identify orchid varieties was studied. Spectral data of 13 orchids varieties covering the spectral range of 4000–550 cm−1 were acquired to establish discriminant models and to select optimal spectral variables. K nearest neighbors (KNN), support vector machine (SVM), and SSAE models were built using full spectra. The SSAE model performed better than the KNN and SVM models and obtained a classification accuracy 99.4% in the calibration set and 97.9% in the prediction set. Then, three algorithms, principal component analysis loading (PCA-loading), competitive adaptive reweighted sampling (CARS), and stacked sparse auto-encoder guided backward (SSAE-GB), were used to select 39, 300, and 38 optimal wavenumbers, respectively. The KNN and SVM models were built based on optimal wavenumbers. Most of the optimal wavenumbers-based models performed slightly better than the all wavenumbers-based models. The performance of the SSAE-GB was better than the other two from the perspective of the accuracy of the discriminant models and the number of optimal wavenumbers. The results of this study showed that the FTIR spectroscopic technique combined with the SSAE algorithm could be adopted in the identification of the orchid varieties.

Download Full-text