Analysis and Design of High Performance Deep Learning Algorithm: Convolutional Neural Networks

Many languages identification (LID) systems rely on language models that use machine learning (ML) approaches, LID systems utilize rather long recording periods to achieve satisfactory accuracy. This study aims to extract enough information from short recording intervals in order to successfully classify the spoken languages under test. The classification process is based on frames of (2-18) seconds where most of the previous LID systems were based on much longer time frames (from 3 seconds to 2 minutes). This research defined and implemented many low-level features using MFCC (Mel-frequency cepstral coefficients), containing speech files in five languages (English. French, German, Italian, Spanish), from voxforge.org an open-source corpus that consists of user-submitted audio clips in various languages, is the source of data used in this paper. A CNN (convolutional Neural Networks) algorithm applied in this paper for classification and the result was perfect, binary language classiﬁcation had an accuracy of 100%, and five languages classiﬁcation with six languages had an accuracy of 99.8%.

Download Full-text

Using Slit-Lamp Images for Deep Learning-Based Identification of Bacterial and Fungal Keratitis: Model Development and Validation with Different Convolutional Neural Networks

Diagnostics ◽

10.3390/diagnostics11071246 ◽

2021 ◽

Vol 11 (7) ◽

pp. 1246

Author(s):

Ning Hung ◽

Andy Kuan-Yu Shih ◽

Chihung Lin ◽

Ming-Tse Kuo ◽

Yih-Shiou Hwang ◽

...

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Diagnostic Accuracy ◽

Convolutional Neural Networks ◽

Learning Algorithm ◽

Model Performance ◽

Fungal Keratitis ◽

Classification Model ◽

Slit Lamp ◽

Deep Learning Algorithm

In this study, we aimed to develop a deep learning model for identifying bacterial keratitis (BK) and fungal keratitis (FK) by using slit-lamp images. We retrospectively collected slit-lamp images of patients with culture-proven microbial keratitis between 1 January 2010 and 31 December 2019 from two medical centers in Taiwan. We constructed a deep learning algorithm consisting of a segmentation model for cropping cornea images and a classification model that applies different convolutional neural networks (CNNs) to differentiate between FK and BK. The CNNs included DenseNet121, DenseNet161, DenseNet169, DenseNet201, EfficientNetB3, InceptionV3, ResNet101, and ResNet50. The model performance was evaluated and presented as the area under the curve (AUC) of the receiver operating characteristic curves. A gradient-weighted class activation mapping technique was used to plot the heat map of the model. By using 1330 images from 580 patients, the deep learning algorithm achieved the highest average accuracy of 80.0%. Using different CNNs, the diagnostic accuracy for BK ranged from 79.6% to 95.9%, and that for FK ranged from 26.3% to 65.8%. The CNN of DenseNet161 showed the best model performance, with an AUC of 0.85 for both BK and FK. The heat maps revealed that the model was able to identify the corneal infiltrations. The model showed a better diagnostic accuracy than the previously reported diagnostic performance of both general ophthalmologists and corneal specialists.

Download Full-text

Assessment of the Degree of Building Damage Caused by Disaster Using Convolutional Neural Networks in Combination with Ordinal Regression

Remote Sensing ◽

10.3390/rs11232858 ◽

2019 ◽

Vol 11 (23) ◽

pp. 2858 ◽

Cited By ~ 6

Author(s):

Tianyu Ci ◽

Zhen Liu ◽

Ying Wang

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Learning Algorithm ◽

Network Models ◽

Building Damage ◽

Ordinal Regression ◽

Aerial Images ◽

Deep Learning Algorithm ◽

Ordinal Regression Model

We propose a new convolutional neural networks method in combination with ordinal regression aiming at assessing the degree of building damage caused by earthquakes with aerial imagery. The ordinal regression model and a deep learning algorithm are incorporated to make full use of the information to improve the accuracy of the assessment. A new loss function was introduced in this paper to combine convolutional neural networks and ordinal regression. Assessing the level of damage to buildings can be considered as equivalent to predicting the ordered labels of buildings to be assessed. In the existing research, the problem has usually been simplified as a problem of pure classification to be further studied and discussed, which ignores the ordinal relationship between different levels of damage, resulting in a waste of information. Data accumulated throughout history are used to build network models for assessing the level of damage, and models for assessing levels of damage to buildings based on deep learning are described in detail, including model construction, implementation methods, and the selection of hyperparameters, and verification is conducted by experiments. When categorizing the damage to buildings into four types, we apply the method proposed in this paper to aerial images acquired from the 2014 Ludian earthquake and achieve an overall accuracy of 77.39%; when categorizing damage to buildings into two types, the overall accuracy of the model is 93.95%, exceeding such values in similar types of theories and methods.

Download Full-text

A Study on the Application of Deep Learning Algorithm and Computer Neural Networks in Automatic Generation According to User Style

10.1109/iccasit53235.2021.9633546 ◽

2021 ◽

Author(s):

Junyi Li

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Learning Algorithm ◽

Automatic Generation ◽

Deep Learning Algorithm

Download Full-text

MS2CNN: predicting MS/MS spectrum based on protein sequence using deep convolutional neural networks

BMC Genomics ◽

10.1186/s12864-019-6297-6 ◽

2019 ◽

Vol 20 (S9) ◽

Cited By ~ 1

Author(s):

Yang-Ming Lin ◽

Ching-Tai Chen ◽

Jia-Ming Chang

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Large Scale ◽

Learning Algorithm ◽

Pearson Correlation ◽

Tandem Mass ◽

Spectral Library ◽

Deep Convolutional Neural Networks ◽

Library Search

Abstract Background Tandem mass spectrometry allows biologists to identify and quantify protein samples in the form of digested peptide sequences. When performing peptide identification, spectral library search is more sensitive than traditional database search but is limited to peptides that have been previously identified. An accurate tandem mass spectrum prediction tool is thus crucial in expanding the peptide space and increasing the coverage of spectral library search. Results We propose MS2CNN, a non-linear regression model based on deep convolutional neural networks, a deep learning algorithm. The features for our model are amino acid composition, predicted secondary structure, and physical-chemical features such as isoelectric point, aromaticity, helicity, hydrophobicity, and basicity. MS2CNN was trained with five-fold cross validation on a three-way data split on the large-scale human HCD MS2 dataset of Orbitrap LC-MS/MS downloaded from the National Institute of Standards and Technology. It was then evaluated on a publicly available independent test dataset of human HeLa cell lysate from LC-MS experiments. On average, our model shows better cosine similarity and Pearson correlation coefficient (0.690 and 0.632) than MS2PIP (0.647 and 0.601) and is comparable with pDeep (0.692 and 0.642). Notably, for the more complex MS2 spectra of 3+ peptides, MS2PIP is significantly better than both MS2PIP and pDeep. Conclusions We showed that MS2CNN outperforms MS2PIP for 2+ and 3+ peptides and pDeep for 3+ peptides. This implies that MS2CNN, the proposed convolutional neural network model, generates highly accurate MS2 spectra for LC-MS/MS experiments using Orbitrap machines, which can be of great help in protein and peptide identifications. The results suggest that incorporating more data for deep learning model may improve performance.

Download Full-text

Effective Deep Learning Based Architecture for Pedestrian Detection from Digital Images

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.b4225.029320 ◽

2020 ◽

Vol 9 (3) ◽

pp. 1498-1508

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Object Detection ◽

Learning Algorithm ◽

Pedestrian Detection ◽

Single Shot ◽

Deep Learning Algorithm ◽

Learning Techniques ◽

Rgb Images ◽

Deep Convolution Network

This paper is to present an efficient and fast deep learning algorithm based on neural networks for object detection and pedestrian detection. The technique, called MobileNet Single Shot Detector, is an extension to Convolution Neural Networks. This technique is based on depth-wise distinguishable convolutions in order to build a lightweighted deep convolution network. A single filter is applied to each input and outputs are combined by using pointwise convolution. Single Shot Multibox Detector is a feed forward convolution network that is combined with MobileNets to give efficient and accurate results. MobileNets combined with SSD and Multibox Technique makes it much faster than SSD alone can work. The accuracy for this technique is calculated over colored (RGB images) and also on infrared images and its results are compared with the results of shallow machine learning based feature extraction plus classification technique viz. HOG plus SVM technique. The comparison of performance between proposed deep learning and shallow learning techniques has been conducted over benchmark dataset and validation testing over own dataset in order measure efficiency of both algorithms and find an effective algorithm that can work with speed and accurately to be applied for object detection in real world pedestrian detection application.

Download Full-text

Coalescent-based species delimitation meets deep learning: Insights from a highly fragmented cactus system

10.1101/2020.12.23.424219 ◽

2020 ◽

Author(s):

Manolo F. Perez ◽

Isabel A. S. Bonatelli ◽

Monique Romeiro-Brito ◽

Fernando F. Franco ◽

Nigel P. Taylor ◽

...

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Species Delimitation ◽

Approximate Bayesian Computation ◽

Learning Algorithm ◽

Bayesian Computation ◽

Cryptic Diversity ◽

Test Species ◽

Approximate Bayesian

AbstractDelimiting species boundaries is a major goal in evolutionary biology. An increasing body of literature has focused on the challenges of investigating cryptic diversity within complex evolutionary scenarios of speciation, including gene flow and demographic fluctuations. New methods based on model selection, such as approximate Bayesian computation, approximate likelihood, and machine learning approaches, are promising tools arising in this field. Here, we introduce a framework for species delimitation using the multispecies coalescent model coupled with a deep learning algorithm based on convolutional neural networks (CNNs). We compared this strategy with a similar ABC approach. We applied both methods to test species boundary hypotheses based on current and previous taxonomic delimitations as well as genetic data (sequences from 41 loci) in Pilosocereus aurisetus, a cactus species with a sky-island distribution and taxonomic uncertainty. To validate our proposed method, we also applied the same strategy on sequence data from widely accepted species from the genus Drosophila. The results show that our CNN approach has high capacity to distinguish among the simulated species delimitation scenarios, with higher accuracy than the ABC procedure. For Pilosocereus, the delimitation hypothesis based on a splitter taxonomic arrangement without migration showed the highest probability in both CNN and ABC approaches. The splits observed within P. aurisetus agree with previous taxonomic conjectures considering more taxonomic entities within currently accepted species. Our results highlight the cryptic diversity within P. aurisetus and show that CNNs are a promising approach for distinguishing divergent and complex evolutionary histories, even outperforming the accuracy of other model-based approaches such as ABC. Keywords: Species delimitation, fragmented systems, recent diversification, deep learning, Convolutional Neural Networks, Approximate Bayesian Computation

Download Full-text

Construction of Innovation and Entrepreneurship Platform Based on Deep Learning Algorithm

Scientific Programming ◽

10.1155/2021/1833979 ◽

2021 ◽

Vol 2021 ◽

pp. 1-7

Author(s):

Jian Li ◽

Yongyan Zhao

Keyword(s):

Machine Learning ◽

College Students ◽

Neural Networks ◽

Deep Learning ◽

National Economy ◽

Learning Algorithm ◽

Learning Algorithms ◽

Computing Power ◽

Deep Learning Algorithm ◽

Innovation And Entrepreneurship

As the national economy has entered a stage of rapid development, the national economy and social development have also ushered in the “14th Five-Year Plan,” and the country has also issued support policies to encourage and guide college students to start their own businesses. Therefore, the establishment of an innovation and entrepreneurship platform has a significant impact on China’s economy. This gives college students great support and help in starting a business. The theory of deep learning algorithms originated from the development of artificial neural networks and is another important field of machine learning. As the computing power of computers has been greatly improved, especially the computing power of GPU can quickly train deep neural networks, deep learning algorithms have become an important research direction. The deep learning algorithm is a nonlinear network structure and a standard modeling method in the field of machine learning. After modeling various templates, they can be identified and implemented. This article uses a combination of theoretical research and empirical research, based on the views and research content of some scholars in recent years, and introduces the basic framework and research content of this article. Then, deep learning algorithms are used to analyze the experimental data. Data analysis is performed, and relevant concepts of deep learning algorithms are combined. This article focuses on exploring the construction of an IAE (innovation and entrepreneurship) education platform and making full use of the role of deep learning algorithms to realize the construction of innovation and entrepreneurship platforms. Traditional methods need to extract features through manual design, then perform feature classification, and finally realize the function of recognition. The deep learning algorithm has strong data image processing capabilities and can quickly process large-scale data. Research data show that 49.5% of college students and 35.2% of undergraduates expressed their interest in entrepreneurship. Entrepreneurship is a good choice to relieve employment pressure.

Download Full-text

Hybrid Deep Learning Based on a Heterogeneous Network Profile for Functional Annotations of Plasmodium falciparum Genes

International Journal of Molecular Sciences ◽

10.3390/ijms221810019 ◽

2021 ◽

Vol 22 (18) ◽

pp. 10019

Author(s):

Apichat Suratanee ◽

Kitiporn Plaimas

Keyword(s):

Plasmodium Falciparum ◽

Deep Learning ◽

Unknown Function ◽

Heterogeneous Network ◽

High Performance ◽

Striated Muscle ◽

Learning Algorithm ◽

Enrichment Analysis ◽

Biomedical Science ◽

Deep Learning Algorithm

Functional annotation of unknown function genes reveals unidentified functions that can enhance our understanding of complex genome communications. A common approach for inferring gene function involves the ortholog-based method. However, genetic data alone are often not enough to provide information for function annotation. Thus, integrating other sources of data can potentially increase the possibility of retrieving annotations. Network-based methods are efficient techniques for exploring interactions among genes and can be used for functional inference. In this study, we present an analysis framework for inferring the functions of Plasmodium falciparum genes based on connection profiles in a heterogeneous network between human and Plasmodium falciparum proteins. These profiles were fed into a hybrid deep learning algorithm to predict the orthologs of unknown function genes. The results show high performance of the model’s predictions, with an AUC of 0.89. One hundred and twenty-one predicted pairs with high prediction scores were selected for inferring the functions using statistical enrichment analysis. Using this method, PF3D7_1248700 and PF3D7_0401800 were found to be involved with muscle contraction and striated muscle tissue development, while PF3D7_1303800 and PF3D7_1201000 were found to be related to protein dephosphorylation. In conclusion, combining a heterogeneous network and a hybrid deep learning technique can allow us to identify unknown gene functions of malaria parasites. This approach is generalized and can be applied to other diseases that enhance the field of biomedical science.

Download Full-text