SYSTEM OF AUTOMATIC SEGMENTATION OF PAUSES IN PHONOGRAMS ON THE BASIS OF NEURON NETWORKS OF THE DEEP LEARNING

2021 ◽  
Vol 1 ◽  
pp. 91-97
Author(s):  
Viktor I. Soloviev ◽  
◽  
Oleg V. Rybalsky ◽  
Vadim V. Zhuravel ◽  
◽  
...  
Keyword(s):  
Deep Learning ◽  
High Efficiency ◽  
Automatic Segmentation ◽  
Neuron Networks ◽  
Automatic Mode ◽  
Primary Base ◽  
Efficiency Of Selection ◽  
Language Context ◽  
Speech Information ◽  
Selection Of

The use of neuron networks of the deep learning for the construction of tool for realization of examinations of materials and apparatus of the digital audio recording allows to solve the «frigging» problem of such examination — problem of exposure of tracks of editing in digital phonograms. These networks provide high probability of exposure of such tracks in the pauses of speech information writtenin on a phonogram. Before man-hunting of tracks of editing in the investigated phonogram it is necessary to distinguish pauses (to perform its segmentation), and tool built on the basis of neuron networks of the deep learning, requires its work to be done in automatic mode. The basic requirement of automatic segmentation is high efficiency of selection of pauses in the conditions of permanent change of level of noises in phonograms. It is determined by probability of errors of І and ІІ kinds. It is offered on the basis of neuron networks of the deep learning to create CAS of segmentation of phonograms, possessing high efficiency of selection of pauses in speech information. Thus the system must be independent of level of noises in every concrete pause, and also language, context and announcer, whose speech is fixed in a phonogram. It is suggested to examine pauses as one of the types of voice information, which characteristics differ from characteristics of speech information fixed in a phonogram. For educating of such network it was required to create the primary base of these sounds and pauses. On its basis three arrays of the data, intended for learning, testing and determination of the crooked errors of І and ІІ kinds, are created. After learning and testing the system passed verification on the real phonograms. As a result taking into account some features of speech on the neuron networks of deep learning there has been built the system providing effective segmentation of pauses in phonograms in the automatics mode. The obtained results suit examination that is conformed by given curves over of errors of І and ІІ kinds.

Molecular Characterization of Parental Lines and Validation of Snp Markers for Disease Resistance in Common Bean

2021 ◽  
Author(s):  
Lucas Matias Gomes-Messias ◽  
Rosana Pereira Vianello ◽  
Joney Pereira Monteiro-Júnior ◽  
Luana Alves Rodrigues ◽  
Ana Paula Simplício Mota ◽  
...  
Keyword(s):  
Disease Resistance ◽  
Common Bean ◽  
Molecular Characterization ◽  
High Efficiency ◽  
Snp Markers ◽  
Molecular Tools ◽  
Breeding Programs ◽  
Efficiency Of Selection ◽  
Selection Of

Abstract The implementation of molecular tools that help the early selection of genotypes carrying target alleles increases efficiency and reduces the time and costs of breeding programs. The present study aimed the molecular characterization and validation of SNPs targeting disease resistance alleles for assisted selection. A total of 376 common bean lines with contrasting responses for anthracnose and angular leaf spot resistance were used, as well as 149 F2 plants from the cross between BRS Cometa x SEL 1308 (carrying the Anthracnose resistance gene Co-42). Seven of the ten SNP markers evaluated showed potential for assisted breeding: snpPV0025 (Phg-2), snpPV0027 (Phg-5), snpPV0079 (Phg-5), snpPV0046 (Co-u), snpPV0068 (Co-42), snpPV0070 (Co-42) and snpP8282v3-817 (Co-42). Markers snpPV0070 and snpP8282v3-817 showed high efficiency of selection (99.7 and 99.8%, respectively). These markers exhibit great potential to assist in the selection at different stages of the breeding program and may be readily incorporated into marker-assisted selection.

Combination of ribosome and phage display for fast selection of high affinity VHH antibody fragments

2019 ◽  
pp. 27-33
Author(s):  
YuE Kravchenko ◽  
SV Ivanov ◽  
DS Kravchenko ◽  
EI Frolova ◽  
SP Chumakov
Keyword(s):  
Phage Display ◽  
Selection Procedure ◽  
Free System ◽  
Phage Displays ◽  
High Affinity ◽  
Binding Domains ◽  
A Cell ◽  
Vhh Antibodies ◽  
Efficiency Of Selection ◽  
Selection Of

Selection of antibodies using phage display involves the preliminary cloning of the repertoire of sequences encoding antigen-binding domains into phagemid, which is considered the bottleneck of the method, limiting the resulting diversity of libraries and leading to the loss of poorly represented variants before the start of the selection procedure. Selection in cell-free conditions using a ribosomal display is devoid from this drawback, however is highly sensitive to PCR artifacts and the RNase contamination. The aim of the study was to test the efficiency of a combination of both methods, including pre-selection in a cell-free system to enrich the source library, followed by cloning and final selection using phage display. This approach may eliminate the shortcomings of each method and increase the efficiency of selection. For selection, alpaca VHH antibody sequences suitable for building an immune library were used due to the lack of VL domains. Analysis of immune libraries from the genes of the VH3, VHH3 and VH4 families showed that the VHH antibodies share in the VH3 and VH4 gene groups is insignificant, and selection from the combined library is less effective than from the VHH3 family of sequences. We found that the combination of ribosomal and phage displays leads to a higher enrichment of high-affinity fragments and avoids the loss of the original diversity during cloning. The combined method allowed us to obtain a greater number of different high-affinity sequences, and all the tested VHH fragments were able to specifically recognize the target, including the total protein extracts of cell cultures.

MODERN CONDITION AND PROSPECTS OF DEVELOPMENT OF THE UKRAINIAN WHITEHEAD BREED

2016 ◽  
Vol 52 ◽  
pp. 194-202
Author(s):  
S. L. Voitenko ◽  
L. V. Vishnevsky
Keyword(s):  
Milk Yield ◽  
Milk Fat ◽  
Objective Assessment ◽  
Live Weight ◽  
Fat Content ◽  
Early Age ◽  
Average Value ◽  
The Future ◽  
Efficiency Of Selection ◽  
Selection Of

The article shows the state of Ukrainian Whiteheaded cattle, which includes distribution of cattle, the number of animals belonging to respective bloodlines, evaluation of young animals with live weight in the process of growing and milk production of cows during the first lactation. It reflects the historic development of the breed when it was colonism whiteheaded cattle, which turned into the original breed, undergone a significant expansion in livestock and increase of productivity, decreased in the number, was as basis for creation of Ukrainian Black-and-White dairy breed and now bred only in one breeding farm. Visual estimation of animal exterior showed good development of cows and calves and their belonging to the dairy type. In the vast majority the cows of the herd have a black suit, a white head with " glasses" around the eyes, white belly, udder, lower legs and brush of the tail. The youngsters aren’t consolidated by the exterior, and among them there are animals which are not typical for Ukrainian Whiteheaded breed. The young animals have some lag in live weight behind the breed standard [12] to 7 months’ age with exceeding of this trait in certain periods quite significantly in the future. It was established that selection of heifers on live weight will be effective at the early age (1-5 months), given the coefficient of variation of live weight – 22,63-30,21% and will not have a significant influence in the future. Milk yields of first-calf heifers vary considerably depending on the origin. The milk yield of first-calf heifers in the herd was 4238,5 kg on average, the heifers belonging to Mart 171 and Ozon 417 bloodlines had the best milk performance – 4483,1 and 4254,9 kg accordingly. The most aligned milk yield during the first lactation was in the cows belonging to Ozon 417 bloodline, the limits of the trait are 4128,5-4327,4 kg with the average value by the line 4254,9 kg. In contrast, the first-calf heifers of Ryezvyi 33 bloodline with average milk yield 4048,9 kg had limits of the trait 2199,3-4736,1 kg. Even greater range in cows’ milk yield during the first lactation R= 4939 kg (limits 1687 – 6626 kg) is characterized for the herd in general, it shows, on the one hand, the possibility of qualitative improvement of cows’ productivity due to selection on the investigated trait and lack of selection in the herd on the other hand. It was established that daughters of bull Chardash belonging to Ryezvyi 33 bloodline produced 4736,1 kg of milk for 305 days of the first lactation with fat content 3,6%, whereas Zlak’s descendants of the same line were characterized by the lowest milk yield for the first completed lactation – 2199,3 kg with fat content 3,7% and the average value by the line – 4048,9 kg of milk, fat content 3,6%. Similar variability of first-calf heifers’ milk yields, depending on the origin, is typical for other bloodlines of Ukrainian Whiteheaded breed. To increase milk productivity of Ukrainian Whiteheaded cows is recommended to repeat successful combinations of parental forms, and to preserve the breed – to carry out an objective assessment of animals by a range of traits, given the efficiency of selection of heifers on live weight at early age.

Deep Learning in Disease Diagnosis: Models and Datasets

2020 ◽  
Vol 15 ◽  
Author(s):  
Deeksha Saxena ◽  
Mohammed Haris Siddiqui ◽  
Rajnish Kumar
Keyword(s):  
Biological Sciences ◽  
Machine Learning ◽  
Deep Learning ◽  
Disease Diagnosis ◽  
Learning Models ◽  
Data Types ◽  
Related Data ◽  
Abstract Level ◽  
Experimental Validations ◽  
Selection Of

Background: Deep learning (DL) is an Artificial neural network-driven framework with multiple levels of representation for which non-linear modules combined in such a way that the levels of representation can be enhanced from lower to a much abstract level. Though DL is used widely in almost every field, it has largely brought a breakthrough in biological sciences as it is used in disease diagnosis and clinical trials. DL can be clubbed with machine learning, but at times both are used individually as well. DL seems to be a better platform than machine learning as the former does not require an intermediate feature extraction and works well with larger datasets. DL is one of the most discussed fields among the scientists and researchers these days for diagnosing and solving various biological problems. However, deep learning models need some improvisation and experimental validations to be more productive. Objective: To review the available DL models and datasets that are used in disease diagnosis. Methods: Available DL models and their applications in disease diagnosis were reviewed discussed and tabulated. Types of datasets and some of the popular disease related data sources for DL were highlighted. Results: We have analyzed the frequently used DL methods, data types and discussed some of the recent deep learning models used for solving different biological problems. Conclusion: The review presents useful insights about DL methods, data types, selection of DL models for the disease diagnosis.

scholarly journals A deep learning method for automatic segmentation of the bony orbit in MRI and CT images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jared Hamwood ◽  
Beat Schmutz ◽  
Michael J. Collins ◽  
Mark C. Allenby ◽  
David Alonso-Caneiro
Keyword(s):  
Deep Learning ◽  
Human Performance ◽  
Automatic Segmentation ◽  
Ct Images ◽  
Human Observer ◽  
In Series ◽  
Magnetic Resonance Imaging Mri ◽  
High Degree ◽  
Orbital Region ◽  
Ct And Mri

AbstractThis paper proposes a fully automatic method to segment the inner boundary of the bony orbit in two different image modalities: magnetic resonance imaging (MRI) and computed tomography (CT). The method, based on a deep learning architecture, uses two fully convolutional neural networks in series followed by a graph-search method to generate a boundary for the orbit. When compared to human performance for segmentation of both CT and MRI data, the proposed method achieves high Dice coefficients on both orbit and background, with scores of 0.813 and 0.975 in CT images and 0.930 and 0.995 in MRI images, showing a high degree of agreement with a manual segmentation by a human expert. Given the volumetric characteristics of these imaging modalities and the complexity and time-consuming nature of the segmentation of the orbital region in the human skull, it is often impractical to manually segment these images. Thus, the proposed method provides a valid clinical and research tool that performs similarly to the human observer.

scholarly journals Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Ling-Ping Cen ◽  
Jie Ji ◽  
Jian-Wei Lin ◽  
Si-Tong Ju ◽  
Hong-Jie Lin ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Efficiency ◽  
Characteristic Curve ◽  
Weighted Average ◽  
Age Related Macular Degeneration ◽  
Learning Platform ◽  
Age Related ◽  
Public Data ◽  
Primary Test ◽  
Retinal Fundus

AbstractRetinal fundus diseases can lead to irreversible visual impairment without timely diagnoses and appropriate treatments. Single disease-based deep learning algorithms had been developed for the detection of diabetic retinopathy, age-related macular degeneration, and glaucoma. Here, we developed a deep learning platform (DLP) capable of detecting multiple common referable fundus diseases and conditions (39 classes) by using 249,620 fundus images marked with 275,543 labels from heterogenous sources. Our DLP achieved a frequency-weighted average F1 score of 0.923, sensitivity of 0.978, specificity of 0.996 and area under the receiver operating characteristic curve (AUC) of 0.9984 for multi-label classification in the primary test dataset and reached the average level of retina specialists. External multihospital test, public data test and tele-reading application also showed high efficiency for multiple retinal diseases and conditions detection. These results indicate that our DLP can be applied for retinal fundus disease triage, especially in remote areas around the world.

scholarly journals Automatic Segmentation of Choroid Layer Using Deep Learning on Spectral Domain Optical Coherence Tomography

2021 ◽  
Vol 11 (12) ◽  
pp. 5488
Author(s):  
Wei Ping Hsia ◽  
Siu Lun Tse ◽  
Chia Jen Chang ◽  
Yu Len Huang
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Choroidal Thickness ◽  
Automatic Segmentation ◽  
Average Error ◽  
Good Prediction ◽  
Optical Coherence ◽  
Learning Method ◽  
Subfoveal Choroidal Thickness ◽  
Fully Connected

The purpose of this article is to evaluate the accuracy of the optical coherence tomography (OCT) measurement of choroidal thickness in healthy eyes using a deep-learning method with the Mask R-CNN model. Thirty EDI-OCT of thirty patients were enrolled. A mask region-based convolutional neural network (Mask R-CNN) model composed of deep residual network (ResNet) and feature pyramid networks (FPNs) with standard convolution and fully connected heads for mask and box prediction, respectively, was used to automatically depict the choroid layer. The average choroidal thickness and subfoveal choroidal thickness were measured. The results of this study showed that ResNet 50 layers deep (R50) model and ResNet 101 layers deep (R101). R101 U R50 (OR model) demonstrated the best accuracy with an average error of 4.85 pixels and 4.86 pixels, respectively. The R101 ∩ R50 (AND model) took the least time with an average execution time of 4.6 s. Mask-RCNN models showed a good prediction rate of choroidal layer with accuracy rates of 90% and 89.9% for average choroidal thickness and average subfoveal choroidal thickness, respectively. In conclusion, the deep-learning method using the Mask-RCNN model provides a faster and accurate measurement of choroidal thickness. Comparing with manual delineation, it provides better effectiveness, which is feasible for clinical application and larger scale of research on choroid.

Sign in / Sign up

Export Citation Format

Share Document