scholarly journals Self-Learning Network-based segmentation for real-time brain M.R. images through HARIS

2021 ◽  
Vol 7 ◽  
pp. e654
Author(s):  
Parvathaneni Naga Srinivasu ◽  
Valentina Emilia Balas
Keyword(s):  
Learning Strategies ◽  
Matthews Correlation Coefficient ◽  
Similarity Index ◽  
Training Model ◽  
Initial Assessment ◽  
Jaccard Similarity ◽  
Learning Network ◽  
Proposed Model ◽  
Sensitivity Specificity ◽  
Self Learning

In recent years in medical imaging technology, the advancement for medical diagnosis, the initial assessment of the ailment, and the abnormality have become challenging for radiologists. Magnetic resonance imaging is one such predominant technology used extensively for the initial evaluation of ailments. The primary goal is to mechanizean approach that can accurately assess the damaged region of the human brain throughan automated segmentation process that requires minimal training and can learn by itself from the previous experimental outcomes. It is computationally more efficient than other supervised learning strategies such as CNN deep learning models. As a result, the process of investigation and statistical analysis of the abnormality would be made much more comfortable and convenient. The proposed approach’s performance seems to be much better compared to its counterparts, with an accuracy of 77% with minimal training of the model. Furthermore, the performance of the proposed training model is evaluated through various performance evaluation metrics like sensitivity, specificity, the Jaccard Similarity Index, and the Matthews correlation coefficient, where the proposed model is productive with minimal training.

scholarly journals Enhancer for ovarian cyst segmentation using adaptive thresholding technique

2020 ◽  
Vol 13 (39) ◽  
pp. 4142-4150
Author(s):  
S Sheela
Keyword(s):  
Ovarian Cyst ◽  
Matthews Correlation Coefficient ◽  
Similarity Index ◽  
Adaptive Thresholding ◽  
Ultrasound Images ◽  
Jaccard Similarity ◽  
Segmented Image ◽  
Pixel Value ◽  
Sensitivity Specificity

Objective: To achieve the accurate segmentation of ovarian cyst from the ultrasound images. Method: Ovarian cyst ultrasound images are taken from ultrasound images.com and sonoworld.com. The cysts are segmented using adaptive thresholding technique. The segmented image (binary image) is divided into sub blocks and then number of binary transition in each block is calculated. Based on the number of transition, the pixel values are replaced by 0 or the same pixel value is maintained. In order to measure the performance of the proposed enhancer various measures like Accuracy (ACC), Dice Coefficient (DC), Jaccard Similarity Index (JSI), Matthews correlation coefficient (MCC), Sensitivity, Specificity and Precision are measured. Findings: In order to analyse the performance of the enhancer with adaptive thresholding technique, 100 ultrasound ovarian cyst images are taken. The enhancer produced better result than the existing adaptive thresholding technique. Novelty/Application: The proposed enhancer enriches the quality of the ovarian cyst segmentation.

Automated white corpuscles nucleus segmentation using deep neural network from microscopic blood smear

2021 ◽  
pp. 1-14
Author(s):  
Indrajeet Kumar ◽  
Chandradeep Bhatt ◽  
Vrince Vimal ◽  
Shamimul Qamar
Keyword(s):  
Neural Network ◽  
Similarity Index ◽  
Proposed Model ◽  
Deep Convolution Neural Network ◽  
Clinical Purpose ◽  
Complete Set ◽  
Testing Accuracy ◽  
Network Weight ◽  
Sensitivity Specificity ◽  
Nucleus Segmentation

The white corpuscles nucleus segmentation from microscopic blood images is major steps to diagnose blood-related diseases. The perfect and speedy segmentation system assists the hematologists to identify the diseases and take appropriate decision for better treatment. Therefore, fully automated white corpuscles nucleus segmentation model using deep convolution neural network, is proposed in the present study. The proposed model uses the combination of ‘binary_cross_entropy’ and ‘adam’ for maintaining learning rate in each network weight. To validate the potential and capability of the above proposed solution, ALL-IDB2 dataset is used. The complete set of images is partitioned into training and testing set and tedious experimentations have been performed. The best performing model is selected and the obtained training and testing accuracy of best performing model is reported as 98.69 % and 99.02 %, respectively. The staging analysis of proposed model is evaluated using sensitivity, specificity, Jaccard index, dice coefficient, accuracy and structure similarity index. The capability of proposed model is compared with performance of the region-based contour and fuzzy-based level-set method for same set of images and concluded that proposed model method is more accurate and effective for clinical purpose.

scholarly journals 4mCPred-CNN—Prediction of DNA N4-Methylcytosine in the Mouse Genome Using a Convolutional Neural Network

Genes ◽  
2021 ◽  
Vol 12 (2) ◽  
pp. 296
Author(s):  
Zeeshan Abbas ◽  
Hilal Tayara ◽  
Kil To Chong
Keyword(s):  
Mouse Genome ◽  
Matthews Correlation Coefficient ◽  
Biological Functions ◽  
Independent Dataset ◽  
Validation Test ◽  
Single Feature ◽  
Proposed Model ◽  
Dna Modifications ◽  
Feature Encoding ◽  
Feature Encoding Scheme

Among DNA modifications, N4-methylcytosine (4mC) is one of the most significant ones, and it is linked to the development of cell proliferation and gene expression. To know different its biological functions, the accurate detection of 4mC sites is required. Although we have several techniques for the prediction of 4mC sites in different genomes based on both machine learning (ML) and convolutional neural networks (CNNs), there is no CNN-based tool for the identification of 4mC sites in the mouse genome. In this article, a CNN-based model named 4mCPred-CNN was developed to classify 4mC locations in the mouse genome. Until now, we had only two ML-based models for this purpose; they utilized several feature encoding schemes, and thus still had a lot of space available to improve the prediction accuracy. Utilizing only a single feature encoding scheme—one-hot encoding—we outperformed both of the previous ML-based techniques. In a ten-fold validation test, the proposed model, 4mCPred-CNN, achieved an accuracy of 85.71% and Matthews correlation coefficient (MCC) of 0.717. On an independent dataset, the achieved accuracy was 87.50% with an MCC value of 0.750. The attained results exhibit that the proposed model can be of great use for researchers in the fields of biology and bioinformatics.

scholarly journals Content Dependent Representation Selection Model for Systems Based on MPEG DASH

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1843
Author(s):  
Jelena Vlaović ◽  
Snježana Rimac-Drlje ◽  
Drago Žagar
Keyword(s):  
Mathematical Model ◽  
Spatial Information ◽  
Relevant Literature ◽  
Video Quality ◽  
Similarity Index ◽  
Video Encoding ◽  
Adaptation Algorithm ◽  
Subjective Testing ◽  
Proposed Model ◽  
The Mathematical Model

A standard called MPEG Dynamic Adaptive Streaming over HTTP (MPEG DASH) ensures the interoperability between different streaming services and the highest possible video quality in changing network conditions. The solutions described in the available literature that focus on video segmentation are mostly proprietary, use a high amount of computational power, lack the methodology, model notation, information needed for reproduction, or do not consider the spatial and temporal activity of video sequences. This paper presents a new model for selecting optimal parameters and number of representations for video encoding and segmentation, based on a measure of the spatial and temporal activity of the video content. The model was developed for the H.264 encoder, using Structural Similarity Index Measure (SSIM) objective metrics as well as Spatial Information (SI) and Temporal Information (TI) as measures of video spatial and temporal activity. The methodology that we used to develop the mathematical model is also presented in detail so that it can be applied to adapt the mathematical model to another type of an encoder or a set of encoding parameters. The efficiency of the segmentation made by the proposed model was tested using the Basic Adaptation algorithm (BAA) and Segment Aware Rate Adaptation (SARA) algorithm as well as two different network scenarios. In comparison to the segmentation available in the relevant literature, the segmentation based on the proposed model obtains better SSIM values in 92% of cases and subjective testing showed that it achieves better results in 83.3% of cases.

Application of Internet of Things intelligent image-positioning studio classroom in English teaching

2021 ◽  
pp. 1-11
Author(s):  
Jie Chen ◽  
Yukun Chen ◽  
Jiaxin Lin
Keyword(s):  
Internet Of Things ◽  
Language Learning ◽  
Learning Strategies ◽  
English Teaching ◽  
Classroom Activities ◽  
Post Test ◽  
Studio Classroom ◽  
And Control ◽  
Self Learning ◽  
Intelligent Positioning

The purpose is to minimize color overflow and color patch generation in intelligent images and promote the application of the Internet of Things (IoT) intelligent image-positioning studio classroom in English teaching. Here, the Convolutional Neural Network (CNN) algorithm is introduced to extract and classify features for intelligent images. Then, the extracted features can position images in real-time. Afterward, the performance of the CNN algorithm is verified through training. Subsequently, two classes in senior high school are selected for experiments, and the influences of IoT intelligent image-positioning studio classroom on students’ performance in the experimental class and control class are analyzed and compared. The results show that the introduction of the CNN algorithm can optimize the intelligent image, accelerate the image classification, reduce color overflow, brighten edge color, and reduce color patches, facilitating intelligent image editing and dissemination. The feasibility analysis proves the effectiveness of the IoT intelligent image-positioning studio classroom, which is in line with students’ language learning rules and interests and can involve students in classroom activities and encourage self-learning. Meanwhile, interaction and cooperation can help students master learning strategies efficiently. The experimental class taught with the IoT intelligent positioning studio has made significant progress in academic performance, especially, in the post-test. In short, the CNN algorithm can promote IoT technologies and is feasible in English teaching.

scholarly journals Genetic structure and gene flow of Eugenia dysenterica natural populations

2005 ◽  
Vol 40 (10) ◽  
pp. 975-980 ◽  
Author(s):  
Maria Imaculada Zucchi ◽  
José Baldin Pinheiro ◽  
Lázaro José Chaves ◽  
Alexandre Siqueira Guedes Coelho ◽  
Mansuêmia Alves Couto ◽  
...  
Keyword(s):  
Gene Flow ◽  
Genetic Variability ◽  
Pearson Correlation ◽  
Natural Populations ◽  
Similarity Index ◽  
Genetic Distances ◽  
Strong Positive Correlation ◽  
Randomly Amplified Polymorphic Dna ◽  
Jaccard Similarity ◽  
Eugenia Dysenterica

This study was carried out to assess the genetic variability of ten "cagaita" tree (Eugenia dysenterica) populations in Southeastern Goiás. Fifty-four randomly amplified polymorphic DNA (RAPD) loci were used to characterize the population genetic variability, using the analysis of molecular variance (AMOVA). A phiST value of 0.2703 was obtained, showing that 27.03% and 72.97% of the genetic variability is present among and within populations, respectively. The Pearson correlation coefficient (r) among the genetic distances matrix (1 - Jaccard similarity index) and the geographic distances were estimated, and a strong positive correlation was detected. Results suggest that these populations are differentiating through a stochastic process, with restricted and geographic distribution dependent gene flow.

scholarly journals Distilling Deep Structural Facial Relationships for FAU Intensity Estimation

2021 ◽  
Author(s):  
Yingruo Fan ◽  
Jacqueline CK Lam ◽  
Victor On Kwok Li
Keyword(s):  
Structural Characteristics ◽  
Model Performance ◽  
Training Model ◽  
Model Parameters ◽  
Intensity Estimation ◽  
Structural Relationships ◽  
Proposed Model ◽  
Comparable Performance ◽  
Knowledge Distillation ◽  
The Difference

<div> <div> <div> <p>Facial emotions are expressed through a combination of facial muscle movements, namely, the Facial Action Units (FAUs). FAU intensity estimation aims to estimate the intensity of a set of structurally dependent FAUs. Contrary to the existing works that focus on improving FAU intensity estimation, this study investigates how knowledge distillation (KD) incorporated into a training model can improve FAU intensity estimation efficiency while achieving the same level of performance. Given the intrinsic structural characteristics of FAU, it is desirable to distill deep structural relationships, namely, DSR-FAU, using heatmap regression. Our methodology is as follows: First, a feature map-level distillation loss was applied to ensure that the student network and the teacher network share similar feature distributions. Second, the region-wise and channel-wise relationship distillation loss functions were introduced to penalize the difference in structural relationships. Specifically, the region-wise relationship can be represented by the structural correlations across the facial features, whereas the channel-wise relationship is represented by the implicit FAU co-occurrence dependencies. Third, we compared the model performance of DSR-FAU with the state-of-the-art models, based on two benchmarking datasets. Our proposed model achieves comparable performance with other baseline models, though requiring a lower number of model parameters and lower computation complexities. </p> </div> </div> </div>

An abundance- and morphology-based similarity index

Paleobiology ◽  
2021 ◽  
pp. 1-18
Author(s):  
Daniel G. Dick ◽  
Marc Laflamme
Keyword(s):  
River Flow ◽  
Similarity Index ◽  
Ecological Gradients ◽  
Jaccard Similarity ◽  
Real World Data ◽  
Large Component ◽  
Morphological Gradient ◽  
Random Samples ◽  
Similarity Indices ◽  
General Method

Abstract Classic similarity indices measure community resemblance in terms of incidence (the number of shared species) and abundance (the extent to which the shared species are an equivalently large component of the ecosystem). Here we describe a general method for increasing the amount of information contained in the output of these indices and describe a new “soft” ecological similarity measure (here called “soft Chao-Jaccard similarity”). The new measure quantifies community resemblance in terms of shared species, while accounting for intraspecific variation in abundance and morphology between samples. We demonstrate how our proposed measure can reconstruct short ecological gradients using random samples of taxa, recognizing patterns that are completely missed by classic measures of similarity. To demonstrate the utility of our new index, we reconstruct a morphological gradient driven by river flow velocity using random samples drawn from simulated and real-world data. Results suggest that the new index can be used to recognize complex short ecological gradients in settings where only information about specimens is available. We include open-source R code for calculating the proposed index.

An Attempt to Estimate the Noises in Homeopathic Pathogenetic Trials by Employing the Jaccard Similarity Index and Noise Index

Homeopathy ◽  
2021 ◽  
Author(s):  
Kurian Poruthukaren
Keyword(s):  
Placebo Group ◽  
Hepatitis C ◽  
Intervention Group ◽  
Similarity Index ◽  
Signs And Symptoms ◽  
Piper Methysticum ◽  
Common Elements ◽  
Jaccard Similarity ◽  
Noise Index ◽  
Trial Drug

Abstract Background The critical task of researchers conducting double-blinded, randomized, placebo-controlled homeopathic pathogenetic trials is to segregate the signals from the noises. The noises are signs and symptoms due to factors other than the trial drug; signals are signs and symptoms due to the trial drug. Unfortunately, the existing tools (criteria for a causal association of symptoms only with the tested medicine, qualitative pathogenetic index, quantitative pathogenetic index, pathogenic index) have limitations in analyzing the symptoms of the placebo group as a comparator, resulting in inadequate segregation of the noises. Hence, the Jaccard similarity index and the Noise index are proposed for analyzing the symptoms of the placebo group as a comparator. Methods The Jaccard similarity index is the ratio of the number of common elements among the placebo and intervention groups to the aggregated number of elements in these groups. The Noise index is the ratio of common elements among the placebo and intervention group to the total elements of the intervention group. Homeopathic pathogenetic trials of Plumbum metallicum, Piper methysticum and Hepatitis C nosode were selected for experimenting with the computation of the Jaccard similarity index and the Noise index. Results Jaccard similarity index calculations show that 8% of Plumbum metallicum's elements, 10.7% of Piper methysticum's elements, and 19.3% of Hepatitis C nosode's elements were similar to the placebo group when elements of both the groups (intervention and placebo) were aggregated. Noise index calculations show that 10.7% of Plumbum metallicum's elements, 13.9% of Piper methysticum's elements and 25.7% of Hepatitis C nosode's elements were similar to those of the placebo group. Conclusion The Jaccard similarity index and the Noise index might be considered an additional approach for analyzing the symptoms of the placebo group as a comparator, resulting in better noise segregation in homeopathic pathogenetic trials.

scholarly journals Multi-Person Pose Estimation using an Orientation and Occlusion Aware Deep Learning Network

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1593 ◽  
Author(s):  
Yanlei Gu ◽  
Huiyang Zhang ◽  
Shunsuke Kamijo
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Body Orientation ◽  
Learning Approaches ◽  
The Public ◽  
Learning Network ◽  
Proposed Model ◽  
Body Boundary ◽  
Public Dataset ◽  
Deep Learning Network

Image based human behavior and activity understanding has been a hot topic in the field of computer vision and multimedia. As an important part, skeleton estimation, which is also called pose estimation, has attracted lots of interests. For pose estimation, most of the deep learning approaches mainly focus on the joint feature. However, the joint feature is not sufficient, especially when the image includes multi-person and the pose is occluded or not fully visible. This paper proposes a novel multi-task framework for the multi-person pose estimation. The proposed framework is developed based on Mask Region-based Convolutional Neural Networks (R-CNN) and extended to integrate the joint feature, body boundary, body orientation and occlusion condition together. In order to further improve the performance of the multi-person pose estimation, this paper proposes to organize the different information in serial multi-task models instead of the widely used parallel multi-task network. The proposed models are trained on the public dataset Common Objects in Context (COCO), which is further augmented by ground truths of body orientation and mutual-occlusion mask. Experiments demonstrate the performance of the proposed method for multi-person pose estimation and body orientation estimation. The proposed method can detect 84.6% of the Percentage of Correct Keypoints (PCK) and has an 83.7% Correct Detection Rate (CDR). Comparisons further illustrate the proposed model can reduce the over-detection compared with other methods.

Sign in / Sign up

Export Citation Format

Share Document