Handwritten Annotation Spotting in Printed Documents Using Top-Down Visual Saliency Models

In this article, we address the problem of localizing text and symbolic annotations on the scanned image of a printed document. Previous approaches have considered the task of annotation extraction as binary classification into printed and handwritten text. In this work, we further subcategorize the annotations as underlines, encirclements, inline text, and marginal text. We have collected a new dataset of 300 documents constituting all classes of annotations marked around or in-between printed text. Using the dataset as a benchmark, we report the results of two saliency formulations—CRF Saliency and Discriminant Saliency, for predicting salient patches, which can correspond to different types of annotations. We also compare our work with recent semantic segmentation techniques using deep models. Our analysis shows that Discriminant Saliency can be considered as the preferred approach for fast localization of patches containing different types of annotations. The saliency models were learned on a small dataset, but still, give comparable performance to the deep networks for pixel-level semantic segmentation. We show that saliency-based methods give better outcomes with limited annotated data compared to more sophisticated segmentation techniques that require a large training set to learn the model.

Automatic text summarization of konkani texts using pre-trained word embeddings and deep learning

<span lang="EN-US">Automatic text summarization has gained immense popularity in research. Previously, several methods have been explored for obtaining effective text summarization outcomes. However, most of the work pertains to the most popular languages spoken in the world. Through this paper, we explore the area of extractive automatic text summarization using deep learning approach and apply it to Konkani language, which is a low-resource language as there are limited resources, such as data, tools, speakers and/or experts in Konkani. In the proposed technique, Facebook’s fastText <br /> pre-trained word embeddings are used to get a vector representation for sentences. Thereafter, deep multi-layer perceptron technique is employed, as a supervised binary classification task for auto-generating summaries using the feature vectors. Using pre-trained fastText word embeddings eliminated the requirement of a large training set and reduced training time. The system generated summaries were evaluated against the ‘gold-standard’ human generated summaries with recall-oriented understudy for gisting evaluation (ROUGE) toolkit. The results thus obtained showed that performance of the proposed system matched closely to the performance of the human annotators in generating summaries.</span>

Binary Classification of COVID-19 CT Images Using CNN

COVID-19 pandemic has hit the world with such a force that the world's leading economies are finding it challenging to come out of it. Countries with the best medical facilities are even cannot handle the increasing number of cases and fatalities. This disease causes significant damage to the lungs and respiratory system of humans, leading to their death. Computed tomography (CT) images of the respiratory system are analyzed in the proposed work to classify the infected people with non-infected people. Deep learning binary classification algorithms have been applied, which have shown an accuracy of 86.9% on 746 CT images of chest having COVID-19 related symptoms.

Binary classification of rainfall time-series using machine learning algorithms

Summer monsoon rainfall contributes more than 75% of the annual rainfall in India. For the state of Maharashtra, India, this is more than 80% for almost all regions of the state. The high variability of rainfall during this period necessitates the classification of rainy and non-rainy days. While there are various approaches to rainfall classification, this paper proposes rainfall classification based on weather variables. This paper explores the use of support vector machine (SVM) and artificial neural network (ANN) algorithms for the binary classification of summer monsoon rainfall using common weather variables such as relative humidity, temperature, pressure. The daily data, for the summer monsoon months, for nineteen years, was collected for the Shivajinagar station of Pune in the state of Maharashtra, India. Classification accuracy of 82.1 and 82.8%, respectively, was achieved with SVM and ANN algorithms, for an imbalanced dataset. While performance parameters such as misclassification rate, F1 score indicate that better results were achieved with ANN, model parameter selection for SVM was less involved than ANN. Domain adaptation technique was used for rainfall classification at the other two stations of Maharashtra with the network trained for the Shivajinagar station. Satisfactory results for these two stations were obtained only after changing the training method for SVM and ANN.

Toxic Comment Classification Based on Bidirectional Gated Recurrent Unit and Convolutional Neural Network

For English toxic comment classification, this paper presents the model that combines Bi-GRU and CNN optimized by global average pooling (BG-GCNN) based on the bidirectional gated recurrent unit (Bi-GRU) and global pooling optimized convolution neural network (CNN) . The model treats each type of toxic comment as a binary classification. First, Bi-GRU is used to extract the time-series features of the comment and then the dimensionality is reduced through global pooling optimized convolution neural network. Finally, the classification result is output by Sigmoid function. Comparative experiments show the BG-GCNN model has a better classification effect than Text-CNN, LSTM, Bi-GRU, and other models. The Macro-F1 value of the toxic comment dataset on the Kaggle competition platform is 0.62. The F1 values of the three toxic label classification results (toxic, obscene, and insult label) are 0.81, 0.84, and 0.74, respectively, which are the highest values in the comparative experiment.

Quality analysis for reliable complex multiclass neuroscience signal classification via electroencephalography

PurposeThe aim of this paper is to explore the brain–computer interface (BCI) as a methodology for generating awareness and increasing reliable use cases of the same so that an individual's quality of life can be enhanced via neuroscience and neural networks, and risk evaluation of certain experiments of BCI can be conducted in a proactive manner.Design/methodology/approachThis paper puts forward an efficient approach for an existing BCI device, which can enhance the performance of an electroencephalography (EEG) signal classifier in a composite multiclass problem and investigates the effects of sampling rate on feature extraction and multiple channels on the accuracy of a complex multiclass EEG signal. A one-dimensional convolutional neural network architecture is used to further classify and improve the quality of the EEG signals, and other algorithms are applied to test their variability. The paper further also dwells upon the combination of internet of things multimedia technology to be integrated with a customized design BCI network based on a conventionally used system known as the message query telemetry transport.FindingsAt the end of our implementation stage, 98% accuracy was achieved in a binary classification problem of classifying digit and non-digit stimuli, and 36% accuracy was observed in the classification of signals resulting from stimuli of digits 0 to 9.Originality/valueBCI, also known as the neural-control interface, is a device that helps a user reliably interact with a computer using only his/her brain activity, which is measured usually via EEG. An EEG machine is a quality device used for observing the neural activity and electric signals generated in certain parts of the human brain, which in turn can help us in studying the different core components of the human brain and how it functions to improve the quality of human life in general.

Automatic freezing-tolerant rapeseed material recognition using UAV images and deep learning

Background Freezing injury is a devastating yet common damage that occurs to winter rapeseed during the overwintering period which directly reduces the yield and causes heavy economic loss. Thus, it is an important and urgent task for crop breeders to find the freezing-tolerant rapeseed materials in the process of breeding. Existing large-scale freezing-tolerant rapeseed material recognition methods mainly rely on the field investigation conducted by the agricultural experts using some professional equipments. These methods are time-consuming, inefficient and laborious. In addition, the accuracy of these traditional methods depends heavily on the knowledge and experience of the experts. Methods To solve these problems of existing methods, we propose a low-cost freezing-tolerant rapeseed material recognition approach using deep learning and unmanned aerial vehicle (UAV) images captured by a consumer UAV. We formulate the problem of freezing-tolerant material recognition as a binary classification problem, which can be solved well using deep learning. The proposed method can automatically and efficiently recognize the freezing-tolerant rapeseed materials from a large number of crop candidates. To train the deep learning network, we first manually construct the real dataset using the UAV images of rapeseed materials captured by the DJI Phantom 4 Pro V2.0. Then, five classic deep learning networks (AlexNet, VGGNet16, ResNet18, ResNet50 and GoogLeNet) are selected to perform the freezing-tolerant rapeseed material recognition. Result and conclusion The accuracy of the five deep learning networks used in our work is all over 92%. Especially, ResNet50 provides the best accuracy (93.33$$\%$$ % ) in this task. In addition, we also compare deep learning networks with traditional machine learning methods. The comparison results show that the deep learning-based methods significantly outperform the traditional machine learning-based methods in our task. The experimental results show that it is feasible to recognize the freezing-tolerant rapeseed using UAV images and deep learning.

Leveraging Multi-Task Learning to Cope With Poor and Missing Labels of Mammograms

In breast cancer screening, binary classification of mammograms is a common task aiming to determine whether a case is malignant or benign. A Computer-Aided Diagnosis (CADx) system based on a trainable classifier requires clean data and labels coming from a confirmed diagnosis. Unfortunately, such labels are not easy to obtain in clinical practice, since the histopathological reports of biopsy may not be available alongside mammograms, while normal cases may not have an explicit follow-up confirmation. Such ambiguities result either in reducing the number of samples eligible for training or in a label uncertainty that may decrease the performances. In this work, we maximize the number of samples for training relying on multi-task learning. We design a deep-neural-network-based classifier yielding multiple outputs in one forward pass. The predicted classes include binary malignancy, cancer probability estimation, breast density, and image laterality. Since few samples have all classes available and confirmed, we propose to introduce the uncertainty related to the classes as a per-sample weight during training. Such weighting prevents updating the network's parameters when training on uncertain or missing labels. We evaluate our approach on the public INBreast and private datasets, showing statistically significant improvements compared to baseline and independent state-of-the-art approaches. Moreover, we use mammograms from Susan G. Komen Tissue Bank for fine-tuning, further demonstrating the ability to improve the performances in our multi-task learning setup from raw clinical data. We achieved the binary classification performance of AUC = 80.46 on our private dataset and AUC = 85.23 on the INBreast dataset.

A Study on 3D Deep Learning-Based Automatic Diagnosis of Nasal Fractures

This paper reported a study on the 3-dimensional deep-learning-based automatic diagnosis of nasal fractures. (1) Background: The nasal bone is the most protuberant feature of the face; therefore, it is highly vulnerable to facial trauma and its fractures are known as the most common facial fractures worldwide. In addition, its adhesion causes rapid deformation, so a clear diagnosis is needed early after fracture onset. (2) Methods: The collected computed tomography images were reconstructed to isotropic voxel data including the whole region of the nasal bone, which are represented in a fixed cubic volume. The configured 3-dimensional input data were then automatically classified by the deep learning of residual neural networks (3D-ResNet34 and ResNet50) with the spatial context information using a single network, whose performance was evaluated by 5-fold cross-validation. (3) Results: The classification of nasal fractures with simple 3D-ResNet34 and ResNet50 networks achieved areas under the receiver operating characteristic curve of 94.5% and 93.4% for binary classification, respectively, both indicating unprecedented high performance in the task. (4) Conclusions: In this paper, it is presented the possibility of automatic nasal bone fracture diagnosis using a 3-dimensional Resnet-based single classification network and it will improve the diagnostic environment with future research.

Negative mpMRI Rules Out Extra-Prostatic Extension in Prostate Cancer Before Robot-Assisted Radical Prostatectomy

The accuracy of multi-parametric MRI (mpMRI) in pre-operative staging of prostate cancer (PCa) remains controversial. Objective: To evaluate the ability of mpMRI to accurately predict PCa extra-prostatic extension (EPE) on a side-specific basis using a risk-stratified 5-point Likert scale. This study also aimed to assess the influence of mpMRI scan quality on diagnostic accuracy. Patients and Methods: We included 124 men who underwent robot-assisted RP (RARP) as part of the NeuroSAFE PROOF study at our centre. Three radiologists retrospectively reviewed mpMRI blinded to RP pathology and assigned a Likert score (1-5) for EPE on each side of the prostate. Each scan was also ascribed a Prostate Imaging Quality (PI-QUAL) score for assessing the quality of the mpMRI scan, where 1 represents poorest and 5 represents best diagnostic quality. Outcome measurements and statistical analyses: Diagnostic performance is presented for binary classification of EPE including 95% confidence intervals and area under the receiver operating characteristic curve (AUC). Results: A total of 231 lobes from 121 men (mean age 56.9 years) were evaluated. 39 men (32.2%), or 43 lobes (18.6%) had EPE. Likert score &ge;3 had sensitivity (SE), specificity (SP), NPV, PPV of 90.4%, 52.3%, 96%, 29.9%, respectively, and AUC was 0.82 (95% CI: 0.77-0.86). AUC was 0.63 (95% CI: 0.37-0.9), 0.77 (0.71-0.84) and 0.92 (0.88-0.96) for biparametric scans, PI-QUAL 1-3 and PI-QUAL 4-5 scans, respectively. Conclusions: MRI can be used effectively by genitourinary radiologists to rule out EPE and help inform surgical planning for men undergoing RARP. EPE prediction was more reliable when the MRI scan was a) multi-parametric and b) of a higher image quality according to the PI-QUAL scoring system.