A Framework for Extractive Text Summarization based on Deep Learning Modified Neural Network Classifier

2020 ◽  
Author(s):  
BalaAnand Muthu ◽  
Sivaparthipan CB ◽  
Priyan Malarvizhi Kumar ◽  
Seifedine Nimer Kadry ◽  
Ching-Hsien Hsu ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Text Summarization ◽  
Neural Network Classifier

scholarly journals piRNN: deep learning algorithm for piRNA prediction

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e5429 ◽  
Author(s):  
Kai Wang ◽  
Joshua Hoeksema ◽  
Chun Liang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Germ Cells ◽  
Small Rna ◽  
Learning Algorithm ◽  
Structural Features ◽  
Neural Network Classifier ◽  
Deep Learning Algorithm ◽  
Non Coding Rnas ◽  
Strong Performance

Piwi-interacting RNAs (piRNAs) are the largest class of small non-coding RNAs discovered in germ cells. Identifying piRNAs from small RNA data is a challenging task due to the lack of conserved sequences and structural features of piRNAs. Many programs have been developed to identify piRNA from small RNA data. However, these programs have limitations. They either rely on extracting complicated features, or only demonstrate strong performance on transposon related piRNAs. Here we proposed a new program called piRNN for piRNA identification. For our software, we applied a convolutional neural network classifier that was trained on the datasets from four different species (Caenorhabditis elegans, Drosophila melanogaster, rat and human). A matrix of k-mer frequency values was used to represent each sequence. piRNN has great usability and shows better performance in comparison with other programs. It is freely available at https://github.com/bioinfolabmu/piRNN.

scholarly journals Generative Model of Brain Microbleeds for MRI Detection of Vascular Marker of Neurodegenerative Diseases

2021 ◽  
Vol 15 ◽  
Author(s):  
Saba Momeni ◽  
Amir Fazlollahi ◽  
Leo Lebrat ◽  
Paul Yates ◽  
Christopher Rowe ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
State Of The Art ◽  
Three Dimensional ◽  
Ground Truth ◽  
Imaging Features ◽  
Neural Network Classifier ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
High Diversity

Cerebral microbleeds (CMB) are increasingly present with aging and can reveal vascular pathologies associated with neurodegeneration. Deep learning-based classifiers can detect and quantify CMB from MRI, such as susceptibility imaging, but are challenging to train because of the limited availability of ground truth and many confounding imaging features, such as vessels or infarcts. In this study, we present a novel generative adversarial network (GAN) that has been trained to generate three-dimensional lesions, conditioned by volume and location. This allows one to investigate CMB characteristics and create large training datasets for deep learning-based detectors. We demonstrate the benefit of this approach by achieving state-of-the-art CMB detection of real CMB using a convolutional neural network classifier trained on synthetic CMB. Moreover, we showed that our proposed 3D lesion GAN model can be applied on unseen dataset, with different MRI parameters and diseases, to generate synthetic lesions with high diversity and without needing laboriously marked ground truth.

scholarly journals Deep Learning Assisted Cognitive Diagnosis for the D-Riska Application

2021 ◽  
Author(s):  
Cristian Cuerda ◽  
Alejandro Zornoza ◽  
Ricardo Tesoriero ◽  
Jose A. Gallud ◽  
Dulce Romero-Ayuso
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Brain Injury ◽  
Diagnostic Tests ◽  
Acquired Brain Injury ◽  
Cognitive Diagnosis ◽  
Neural Network Classifier ◽  
Proposed Model ◽  
Final Score

Abstract In this article, we expose a system developed that extends the Acquired Brain Injury (ABI) diagnostic application known as D-Riska with an artificial intelligence module that supports the diagnosis of ABI enabling therapists to evaluate patients in an assisted way. The application is in charge of collecting the data of the diagnostic tests of the patients, and due to a multi-class. Convolutional Neural Network classifier (CNN), it is capable of making predictions that facilitate the diagnosis and the final score obtained in the test by the patient. To find out the best solution to this problem, different classifiers are used to compare the performance of the proposed model based on various classification metrics. The proposed CNN classifier makes predictions with 93 \% of Accuracy, 94 \% of Precision, 91 \%, of Recall and 92\% of F1-Score.

scholarly journals Identification of Low Population States in Cryo-EM Using Deep Learning

2021 ◽  
Author(s):  
Alec Fraser ◽  
Nikolai S Prokhorov ◽  
John M Miller ◽  
Ekaterina S Knyazhanskaya ◽  
Petr G Leiman
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Three Dimensional ◽  
Atomic Resolution ◽  
Neural Network Classifier ◽  
Automate Data ◽  
Bacterial Host ◽  
Learning Classifier ◽  
Human Effort ◽  
Automate Data Collection

Cryo-EM has made extraordinary headway towards becoming a semi-automated, high-throughput structure determination technique. In the general workflow, high-to-medium population states are grouped into two- and three-dimensional classes, from which structures can be obtained with near-atomic resolution and subsequently analyzed to interpret function. However, low population states, which are also functionally important, are often discarded. Here, we describe a technique whereby low population states can be efficiently identified with minimal human effort via a deep convolutional neural network classifier. We use this deep learning classifier to describe a transient, low population state of bacteriophage A511 in the midst of infecting its bacterial host. This method can be used to further automate data collection and identify other functionally important low population states.

scholarly journals Deep learning assisted cognitive diagnosis for the D-Riska application

2021 ◽  
Author(s):  
Cristian Cuerda ◽  
Alejandro Zornoza ◽  
Jose A. Gallud ◽  
Ricardo Tesoriero ◽  
Dulce Romero Ayuso
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Brain Injury ◽  
Diagnostic Tests ◽  
Acquired Brain Injury ◽  
Cognitive Diagnosis ◽  
Neural Network Classifier ◽  
Proposed Model ◽  
Final Score

AbstractIn this article, we expose a system developed that extends the Acquired Brain Injury (ABI) diagnostic application known as D-Riska with an artificial intelligence module that supports the diagnosis of ABI enabling therapists to evaluate patients in an assisted way. The application is in charge of collecting the data of the diagnostic tests of the patients, and due to a multi-class Convolutional Neural Network classifier (CNN), it is capable of making predictions that facilitate the diagnosis and the final score obtained in the test by the patient. To find out the best solution to this problem, different classifiers are used to compare the performance of the proposed model based on various classification metrics. The proposed CNN classifier makes predictions with 93 % of Accuracy, 94 % of Precision, 91 %, of Recall and 92% of F1-Score.

scholarly journals Classification and Specific Primer Design for Accurate Detection of SARS-CoV-2 Using Deep Learning

2020 ◽  
Author(s):  
Alejandro Lopez-Rincon ◽  
Alberto Tonda ◽  
Lucero Mendoza-Maldonado ◽  
Daphne G.J.C. Mulders ◽  
Richard Molenkamp ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Diagnostic Methods ◽  
Neural Network Classifier ◽  
Explainable Artificial Intelligence ◽  
Primer Sets ◽  
Virus Strains

ABSTRACTIn this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier is first trained on 553 sequences from available repositories, separating the genome of different virus strains from the Coronavirus family with considerable accuracy. The network’s behavior is then analyzed, to discover sequences used by the model to identify SARS-CoV-2, ultimately uncovering sequences exclusive to it. The discovered sequences are first validated on samples from other repositories, and proven able to separate SARS-CoV-2 from different virus strains with near-perfect accuracy. Next, one of the sequences is selected to generate a primer set, and tested against other state-of-the-art primer sets on existing datasets, obtaining competitive results. Finally, the primer is synthesized and tested on patient samples (n=6 previously tested positive), delivering a sensibility similar to routine diagnostic methods, and 100% specificity. In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier is first trained on 553 sequences from NGDC, separating the genome of different virus strains from the Coronavirus family with accuracy 98.73%. The network’s behavior is then analyzed, to discover sequences used by the model to identify SARS-CoV-2, ultimately uncovering sequences exclusive to it. The discovered sequences are validated on samples from NCBI and GISAID, and proven able to separate SARS-CoV-2 from different virus strains with near-perfect accuracy. Next, one of the sequences is selected to generate a primer set, and tested against other state-of-the-art primer sets, obtaining competitive results. Finally, the primer is synthesized and tested on patient samples (n=6 previously tested positive), delivering a sensibility similar to routine diagnostic methods, and 100% specificity. The proposed methodology has a substantial added value over existing methods, as it is able to both identify promising primer sets for a virus from a limited amount of data, and deliver effective results in a minimal amount of time. Considering the possibility of future pandemics, these characteristics are invaluable to promptly create specific detection methods for diagnostics.

Sign in / Sign up

Export Citation Format

Share Document