CNN with Multiple Inputs for Automatic Glaucoma Assessment Using Fundus Images

In the area of ophthalmology, glaucoma affects an increasing number of people. It is a major cause of blindness. Early detection avoids severe ocular complications such as glaucoma, cystoid macular edema, or diabetic proliferative retinopathy. Intelligent artificial intelligence has been confirmed beneficial for glaucoma assessment. In this paper, we describe an approach to automate glaucoma diagnosis using funds images. The setup of the proposed framework is in order: The Bi-dimensional Empirical Mode Decomposition (BEMD) algorithm is applied to decompose the Regions of Interest (ROI) to components (BIMFs+residue). CNN architecture VGG19 is implemented to extract features from decomposed BEMD components. Then, we fuse the features of the same ROI in a bag of features. These last very long; therefore, Principal Component Analysis (PCA) are used to reduce features dimensions. The bags of features obtained are the input parameters of the implemented classifier based on the Support Vector Machine (SVM). To train the built models, we have used two public datasets, which are ACRIMA and REFUGE. For testing our models, we have used a part of ACRIMA and REFUGE plus four other public datasets, which are RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF. The overall precision of 98.31%, 98.61%, 96.43%, 96.67%, 95.24%, and 98.60% is obtained on ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, by using the model trained on REFUGE. Again an accuracy of 98.92%, 99.06%, 98.27%, 97.10%, 96.97%, and 96.36% is obtained in the ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, using the model training on ACRIMA. The experimental results obtained from different datasets demonstrate the efficiency and robustness of the proposed approach. A comparison with some recent previous work in the literature has shown a significant advancement in our proposal.

Sleep Apnea Classification Algorithm Development Using a Machine-Learning Framework and Bag-of-Features Derived from Electrocardiogram Spectrograms

Background: Heart rate variability (HRV) and electrocardiogram (ECG)-derived respiration (EDR) have been used to detect sleep apnea (SA) for decades. The present study proposes an SA-detection algorithm using a machine-learning framework and bag-of-features (BoF) derived from an ECG spectrogram. Methods: This study was verified using overnight ECG recordings from 83 subjects with an average apnea–hypopnea index (AHI) 29.63 (/h) derived from the Physionet Apnea-ECG and National Cheng Kung University Hospital Sleep Center database. The study used signal preprocessing to filter noise and artifacts, ECG time–frequency transformation using continuous wavelet transform (CWT), BoF feature generation, machine-learning classification using support vector machine (SVM), ensemble learning (EL), k-nearest neighbor (KNN) classification, and cross-validation. The time length of the spectrogram was set as 10 and 60 s to examine the required minimum spectrogram window time length to achieve satisfactory accuracy. Specific frequency bands of 0.1–50, 8–50, 0.8–10, and 0–0.8 Hz were also extracted to generate the BoF to determine the band frequency best suited for SA detection. Results: The five-fold cross-validation accuracy using the BoF derived from the ECG spectrogram with 10 and 60 s time windows were 90.5% and 91.4% for the 0.1–50 Hz and 8–50 Hz frequency bands, respectively. Conclusion: An SA-detection algorithm utilizing BoF and a machine-learning framework was successfully developed in this study with satisfactory classification accuracy and high temporal resolution.

Machine Learning Microservice for Identification of Accident Predecessors

Drilling accidents prediction is the important task in well construction. Drilling support software allows observing the drilling parameters for multiple wells at the same time and artificial intelligence helps detecting the drilling accident predecessor ahead the emergency situation. We present machine learning (ML) algorithm for prediction of such accidents as stuck, mud loss, fluid show, washout, break of drill string and shale collar. The model for forecasting the drilling accidents is based on the "Bag-of-features" approach, which implies the use of distributions of the directly recorded data as the main features. Bag-of-features implies the labeling of small parts of data by the particular symbol, named codeword. Building histograms of symbols for the data segment, one could use the histogram as an input for the machine learning algorithm. Fragments of real-time mud log data were used to create the model. We define more than 1000 drilling accident predecessors for more than 60 real accidents and about 2500 normal drilling cases as a training set for ML model. The developed model analyzes real-time mud log data and calculates the probability of accident. The result is presented as a probability curve for each type of accident; if the critical probability value is exceeded, the user is notified of the risk of an accident. The Bag-of-features model shows high performance by validation both on historical data and in real time. The prediction quality does not vary field to field and could be used in different fields without additional training of the ML model. The software utilizing the ML model has microservice architecture and is integrated with the WITSML data server. It is capable of real-time accidents forecasting without human intervention. As a result, the system notifies the user in all cases when the situation in the well becomes similar to the pre-accident one, and the engineer has enough time to take the necessary actions to prevent an accident.

Appending Global to Local features for Skin Lesion Classification on Dermoscpic Images

Skin cancer is the deadliest diseases compared with all other kinds of cancer. In this paper various pre- and post-treatments are proposed for improving automated melanoma diagnosis of dermoscopy images. At first pre-processing have done to exclude unwanted parts, a new triple-A segmentation proposes to extract lesion according to their histogram patterns. Lastly, suggest appending process with testing many factors for superior detection decision. This paper offers a novel approach with testing different detection rules: first system used fuzzy rules based on a different features, a second test has been done by modeled local colours with bag-of-features classifier. Then proposed adding lesion shape on two previous systems as their global form in the first one, while distributing it and appending with local colour patches in the second system. For each case, different features; various colour models, and many other parameters are examined to decide which settings are more discriminating. Evaluates performance of each method has carried out on (ISIC2019 Challenge) dermoscopic database. The novel processes with their a specific parameters are rising the classification accuracy to 98.26%.

Bag of Features (BoF) Based Deep Learning Framework for Bleached Corals Detection

Coral reefs are the sub-aqueous calcium carbonate structures collected by the invertebrates known as corals. The charm and beauty of coral reefs attract tourists, and they play a vital role in preserving biodiversity, ceasing coastal erosion, and promoting business trade. However, they are declining because of over-exploitation, damaging fishery, marine pollution, and global climate changes. Also, coral reefs help treat human immune-deficiency virus (HIV), heart disease, and coastal erosion. The corals of Australia’s great barrier reef have started bleaching due to the ocean acidification, and global warming, which is an alarming threat to the earth’s ecosystem. Many techniques have been developed to address such issues. However, each method has a limitation due to the low resolution of images, diverse weather conditions, etc. In this paper, we propose a bag of features (BoF) based approach that can detect and localize the bleached corals before the safety measures are applied. The dataset contains images of bleached and unbleached corals, and various kernels are used to support the vector machine so that extracted features can be classified. The accuracy of handcrafted descriptors and deep convolutional neural networks is analyzed and provided in detail with comparison to the current method. Various handcrafted descriptors like local binary pattern, a histogram of an oriented gradient, locally encoded transform feature histogram, gray level co-occurrence matrix, and completed joint scale local binary pattern are used for feature extraction. Specific deep convolutional neural networks such as AlexNet, GoogLeNet, VGG-19, ResNet-50, Inception v3, and CoralNet are being used for feature extraction. From experimental analysis and results, the proposed technique outperforms in comparison to the current state-of-the-art methods. The proposed technique achieves 99.08% accuracy with a classification error of 0.92%. A novel bleached coral positioning algorithm is also proposed to locate bleached corals in the coral reef images.

CNN with Multiple Input for automatic glaucoma assessment using Fundus Images

In the area of ophthalmology, glaucoma affects an increasing number of people. It is a major cause of blindness. Early detection avoids severe ocular complications such as glaucoma, cystoid macular edema, or diabetic proliferative retinopathy. Intelligent artificial has been confirmed beneficial for glaucoma assessment. In this paper, we describe an approach to automate glaucoma diagnosis using funds images. The setup of the proposed framework is, in order: The Bi-dimensional Empirical Mode Decomposition (BEMD) algorithm is applied to decompose the Regions of Interest (ROI) to components (BIMFs + residue). CNN architecture VGG19 is implemented to extract features from decomposed BEMD components. Then, we fuse the features of the same ROI in a bag of features. These last are very long; therefore, Principal Component Analyses (PCA) are used to reduce features dimensions. Obtained bags of features are the input parameters of the implemented classifier based on the Support Vector Machine (SVM). To train the built models, we have used two public datasets, which are ACRIMA and REFUGE. For testing our models, we have used a part of ACRIMA and REFUGE plus four other public datasets, which are RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF. The overall accuracy of 98.31%, 98.61%, 96.43%, 96.67%, 95.24%, and 98.60% are obtained on ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, by using the model trained on REFUGE. Against an accuracy of 98.92%, 99.06%, 98.27%, 97.10%, 96.97%, and 96.36% are obtained on ACRIMA, REFUGE, RIM-ONE, ORIGA-light, Drishti-GS1, and sjchoi86-HRF datasets, respectively, using the model training on ACRIMA. Obtained experimental results from different datasets demonstrate the efficiency and robustness of the proposed approach. A comparison with some recent previous work in the literature has shown a significant advancement in our proposal.

Evaluation of image partitioning strategies for preserving spatial information of cross-sectional micrographs in automated wood recognition of Fagaceae

Although wood cross sections contain spatiotemporal information regarding tree growth, computer vision-based wood identification studies have traditionally favored disordered image representations that do not take such information into account. This paper describes image partitioning strategies that preserve the spatial information of wood cross-sectional images. Three partitioning strategies are designed, namely grid partitioning based on spatial pyramid matching and its variants, radial and tangential partitioning, and their recognition performance is evaluated for the Fagaceae micrograph dataset. The grid and radial partitioning strategies achieve better recognition performance than the bag-of-features model that constitutes their underlying framework. Radial partitioning, which is a strategy for preserving spatial information from pith to bark, further improves the performance, especially for radial-porous species. The Pearson correlation and autocorrelation coefficients produced from radially partitioned sub-images have the potential to be used as auxiliaries in the construction of multi-feature datasets. The contribution of image partitioning strategies is found to be limited to species recognition and is unremarkable at the genus level.

Improved bag-of-features using grey relational analysis for classification of histology images

An efficient classification method to categorize histopathological images is a challenging research problem. In this paper, an improved bag-of-features approach is presented as an efficient image classification method. In bag-of-features, a large number of keypoints are extracted from histopathological images that increases the computational cost of the codebook construction step. Therefore, to select the a relevant subset of keypoints, a new keypoints selection method is introduced in the bag-of-features method. To validate the performance of the proposed method, an extensive experimental analysis is conducted on two standard histopathological image datasets, namely ADL and Blue histology datasets. The proposed keypoint selection method reduces the extracted high dimensional features by 95% and 68% from the ADL and Blue histology datasets respectively with less computational time. Moreover, the enhanced bag-of-features method increases classification accuracy by from other considered classification methods.