Bridging the gap between reduced training time and maintained operational demands

To forecast time series data, two methodological frameworks of statistical and computational intelligence modelling are considered. The statistical methodological approach is based on the theory of invertible ARIMA (Auto-Regressive Integrated Moving Average) models with Maximum Likelihood (ML) estimating method. As a competitive tool to statistical forecasting models, we use the popular classic neural network (NN) of perceptron type. To train NN, the Back-Propagation (BP) algorithm and heuristics like genetic and micro-genetic algorithm (GA and MGA) are implemented on the large data set. A comparative analysis of selected learning methods is performed and evaluated. From performed experiments we find that the optimal population size will likely be 20 with the lowest training time from all NN trained by the evolutionary algorithms, while the prediction accuracy level is lesser, but still acceptable by managers.

Download Full-text

SVM-based global vision system of sports competition and action recognition

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189224 ◽

2020 ◽

pp. 1-12

Author(s):

Changxin Sun ◽

Di Ma

Keyword(s):

Target Recognition ◽

Vision System ◽

Task Assignment ◽

Recognition Algorithm ◽

Control Factor ◽

Training Time ◽

Adaboost Algorithm ◽

Advantages And Disadvantages ◽

Time Control ◽

Correlation Degree

In the research of intelligent sports vision systems, the stability and accuracy of vision system target recognition, the reasonable effectiveness of task assignment, and the advantages and disadvantages of path planning are the key factors for the vision system to successfully perform tasks. Aiming at the problem of target recognition errors caused by uneven brightness and mutations in sports competition, a dynamic template mechanism is proposed. In the target recognition algorithm, the correlation degree of data feature changes is fully considered, and the time control factor is introduced when using SVM for classification,At the same time, this study uses an unsupervised clustering method to design a classification strategy to achieve rapid target discrimination when the environmental brightness changes, which improves the accuracy of recognition. In addition, the Adaboost algorithm is selected as the machine learning method, and the algorithm is optimized from the aspects of fast feature selection and double threshold decision, which effectively improves the training time of the classifier. Finally, for complex human poses and partially occluded human targets, this paper proposes to express the entire human body through multiple parts. The experimental results show that this method can be used to detect sports players with multiple poses and partial occlusions in complex backgrounds and provides an effective technical means for detecting sports competition action characteristics in complex backgrounds.

Download Full-text

On-line testing as a new method of student knowledge evaluation

Reports of Vinnytsia National Medical University ◽

10.31393/reports-vnmedical-2018-22(2)-25 ◽

2018 ◽

Vol 22 (2) ◽

pp. 353-356

Author(s):

V.P. Kovalchuk ◽

I.M. Kovalenko ◽

S.V. Kovalenko ◽

V.M. Burkot ◽

V.O. Kovalenko

Keyword(s):

Information Technologies ◽

English Language ◽

Educational Process ◽

Personality Testing ◽

Online Testing ◽

Training Time ◽

Internet Resources ◽

New Information ◽

On Line ◽

Use Of The Internet

Innovations change the world in all spheres of life, and education is not an exception. Modern requirements of time put us new challenges that require the use of new information technologies at all stages of the educational process in higher education institutions, in particular the use of the Internet. In addition, it has been noted that Internet resources increase motivation and contribute to the formation of a fully developed personality. Testing and evaluating students' knowledge and abilities is an integral part of the credit-module system. One of the forms of evaluation of the initial level of knowledge, consolidation and improvement of assimilation of information is testing. It should be noted that in a number of countries, testing has shifted traditional forms of control — oral and written exams and interviews. However, in Ukraine, educators remain adherents of a combination of testing and classical analysis of material. It allows the most efficient distribution of the training time of a practical class, 100% control of the knowledge and the effectiveness of mastering the material of all the students of the academic group. Technical progress stimulates the search for new variants and possibilities of testing, its various variations. One of the options that can help solve this problem was a smartphone. In order to facilitate the work of the teacher at the Department of Microbiology, an online testing system with the use of smartphones was introduced. Online testing is conducted among students with Ukrainian and English language training. With the Google Forms platform, the teacher creates a form which contains the student's records and tests. Students directly from the teacher get a link to fill out an online form directly at the lesson. For testing, a database containing standard KROK-1 licensed test tasks is used. The form can contain any number of test tasks that are in arbitrary order, as well as a changed order of distractors, which makes it impossible to write off. At the same time, all students are in the same conditions: all write one option. After submitting the form, the student receives a notification that his response is recorded. Re-linking is not possible. In turn, the teacher receives a message on the result of the test in the table — the ratio of correct answers to the total number of questions, as well as options for their answers. First and foremost, questions are displayed on which students gave the largest number of incorrect answers. This allows the topic to be considered in the process of discussion of the most difficult tasks from the students perspective, and in the future it will allow more efficiently to create forms for on-line tests and to focus on these issues.

Download Full-text

Evaluation of Mixed Deep Neural Networks for Reverberant Speech Enhancement

Biomimetics ◽

10.3390/biomimetics5010001 ◽

2019 ◽

Vol 5 (1) ◽

pp. 1 ◽

Cited By ~ 1

Author(s):

Michelle Gutiérrez-Muñoz ◽

Astryd González-Salazar ◽

Marvin Coto-Jiménez

Keyword(s):

Neural Networks ◽

Short Term Memory ◽

Computational Cost ◽

Real Life ◽

Fixed Number ◽

Training Procedure ◽

Statistical Validation ◽

Significant Drop ◽

Training Time ◽

Important Solution

Speech signals are degraded in real-life environments, as a product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in those systems is reverberation, produced by sound wave reflections that travel from the source to the microphone in multiple directions. To enhance signals in such adverse conditions, several deep learning-based methods have been proposed and proven to be effective. Recently, recurrent neural networks, especially those with long short-term memory (LSTM), have presented surprising results in tasks related to time-dependent processing of signals, such as speech. One of the most challenging aspects of LSTM networks is the high computational cost of the training procedure, which has limited extended experimentation in several cases. In this work, we present a proposal to evaluate the hybrid models of neural networks to learn different reverberation conditions without any previous information. The results show that some combinations of LSTM and perceptron layers produce good results in comparison to those from pure LSTM networks, given a fixed number of layers. The evaluation was made based on quality measurements of the signal’s spectrum, the training time of the networks, and statistical validation of results. In total, 120 artificial neural networks of eight different types were trained and compared. The results help to affirm the fact that hybrid networks represent an important solution for speech signal enhancement, given that reduction in training time is on the order of 30%, in processes that can normally take several days or weeks, depending on the amount of data. The results also present advantages in efficiency, but without a significant drop in quality.

Download Full-text

An image denoising method based on BP neural network optimized by improved whale optimization algorithm

EURASIP Journal on Wireless Communications and Networking ◽

10.1186/s13638-021-02013-2 ◽

2021 ◽

Vol 2021 (1) ◽

Author(s):

Chunzhi Wang ◽

Min Li ◽

Ruoxi Wang ◽

Han Yu ◽

Shuping Wang

Keyword(s):

Neural Network ◽

Image Denoising ◽

Optimization Algorithm ◽

Bp Neural Network ◽

Weight Coefficient ◽

Whale Optimization Algorithm ◽

Denoising Method ◽

Training Time ◽

Whale Optimization ◽

City Construction

AbstractAs an important part of smart city construction, traffic image denoising has been studied widely. Image denoising technique can enhance the performance of segmentation and recognition model and improve the accuracy of segmentation and recognition results. However, due to the different types of noise and the degree of noise pollution, the traditional image denoising methods generally have some problems, such as blurred edges and details, loss of image information. This paper presents an image denoising method based on BP neural network optimized by improved whale optimization algorithm. Firstly, the nonlinear convergence factor and adaptive weight coefficient are introduced into the algorithm to improve the optimization ability and convergence characteristics of the standard whale optimization algorithm. Then, the improved whale optimization algorithm is used to optimize the initial weight and threshold value of BP neural network to overcome the dependence in the construction process, and shorten the training time of the neural network. Finally, the optimized BP neural network is applied to benchmark image denoising and traffic image denoising. The experimental results show that compared with the traditional denoising methods such as Median filtering, Neighborhood average filtering and Wiener filtering, the proposed method has better performance in peak signal-to-noise ratio.

Download Full-text

CNN Training Using 3D Virtual Models for Assisted Assembly with Mixed Reality and Collaborative Robots

Applied Sciences ◽

10.3390/app11094269 ◽

2021 ◽

Vol 11 (9) ◽

pp. 4269

Author(s):

Kamil Židek ◽

Ján Piteľ ◽

Michal Balog ◽

Alexander Hošovský ◽

Vratislav Hladký ◽

...

Keyword(s):

Mixed Reality ◽

Current Trend ◽

Robot Vision ◽

Processing Unit ◽

Single Shot ◽

Vision Systems ◽

Collaborative Robots ◽

Training Time ◽

Position And Orientation ◽

Collaborative Robot

The assisted assembly of customized products supported by collaborative robots combined with mixed reality devices is the current trend in the Industry 4.0 concept. This article introduces an experimental work cell with the implementation of the assisted assembly process for customized cam switches as a case study. The research is aimed to design a methodology for this complex task with full digitalization and transformation data to digital twin models from all vision systems. Recognition of position and orientation of assembled parts during manual assembly are marked and checked by convolutional neural network (CNN) model. Training of CNN was based on a new approach using virtual training samples with single shot detection and instance segmentation. The trained CNN model was transferred to an embedded artificial processing unit with a high-resolution camera sensor. The embedded device redistributes data with parts detected position and orientation into mixed reality devices and collaborative robot. This approach to assisted assembly using mixed reality, collaborative robot, vision systems, and CNN models can significantly decrease assembly and training time in real production.

Download Full-text

Nodule Detection with Convolutional Neural Network Using Apache Spark and GPU Frameworks

Applied Sciences ◽

10.3390/app11062838 ◽

2021 ◽

Vol 11 (6) ◽

pp. 2838

Author(s):

Nikitha Johnsirani Venkatesan ◽

Dong Ryeol Shin ◽

Choon Sung Nam

Keyword(s):

Neural Network ◽

Radiation Dose ◽

Convolutional Neural Network ◽

Model Performance ◽

Performance Comparison ◽

Apache Spark ◽

Training Time ◽

Learning Framework ◽

Proposed Model

In the pharmaceutical field, early detection of lung nodules is indispensable for increasing patient survival. We can enhance the quality of the medical images by intensifying the radiation dose. High radiation dose provokes cancer, which forces experts to use limited radiation. Using abrupt radiation generates noise in CT scans. We propose an optimal Convolutional Neural Network model in which Gaussian noise is removed for better classification and increased training accuracy. Experimental demonstration on the LUNA16 dataset of size 160 GB shows that our proposed method exhibit superior results. Classification accuracy, specificity, sensitivity, Precision, Recall, F1 measurement, and area under the ROC curve (AUC) of the model performance are taken as evaluation metrics. We conducted a performance comparison of our proposed model on numerous platforms, like Apache Spark, GPU, and CPU, to depreciate the training time without compromising the accuracy percentage. Our results show that Apache Spark, integrated with a deep learning framework, is suitable for parallel training computation with high accuracy.

Download Full-text

Failed Surgery for Patellar Tendinopathy in Athletes: Midterm Results of Further Surgical Management

Orthopaedic Journal of Sports Medicine ◽

10.1177/2325967121994550 ◽

2021 ◽

Vol 9 (3) ◽

pp. 232596712199455

Author(s):

Nicola Maffulli ◽

Francesco Oliva ◽

Gayle D. Maffulli ◽

Filippo Migliorini

Keyword(s):

Surgical Management ◽

Revision Surgery ◽

Case Series ◽

Sports Participation ◽

Patellar Tendinopathy ◽

Symptom Duration ◽

Level Of Evidence ◽

Training Time ◽

The Mean

Background: Tendon injuries are commonly seen in sports medicine practice. Many elite players involved in high-impact activities develop patellar tendinopathy (PT) symptoms. Of them, a small percentage will develop refractory PT and need to undergo surgery. In some of these patients, surgery does not resolve these symptoms. Purpose: To report the clinical results in a cohort of athletes who underwent further surgery after failure of primary surgery for PT. Study Design: Case series; Level of evidence, 4. Methods: A total of 22 athletes who had undergone revision surgery for failed surgical management of PT were enrolled in the present study. Symptom severity was assessed through the Victorian Institute of Sport Assessment Scale for Patellar Tendinopathy (VISA-P) upon admission and at the final follow-up. Time to return to training, time to return to competition, and complications were also recorded. Results: The mean age of the athletes was 25.4 years, and the mean symptom duration from the index intervention was 15.3 months. At a mean follow-up of 30.0 ± 4.9 months, the VISA-P score improved 27.8 points ( P < .0001). The patients returned to training within a mean of 9.2 months. Fifteen patients (68.2%) returned to competition within a mean of 11.6 months. Of these 15 patients, a further 2 had decreased their performance, and 2 more had abandoned sports participation by the final follow-up. The overall rate of complications was 18.2%. One patient (4.5%) had a further revision procedure. Conclusion: Revision surgery was feasible and effective in patients in whom PT symptoms persisted after previous surgery for PT, achieving a statistically significant and clinically relevant improvement of the VISA-P score as well as an acceptable rate of return to sport at a follow-up of 30 months.

Download Full-text

Improved SinGAN Integrated with an Attentional Mechanism for Remote Sensing Image Classification

Remote Sensing ◽

10.3390/rs13091713 ◽

2021 ◽

Vol 13 (9) ◽

pp. 1713

Author(s):

Songwei Gu ◽

Rui Zhang ◽

Hongxia Luo ◽

Mengyao Li ◽

Huamei Feng ◽

...

Keyword(s):

Remote Sensing ◽

Real Life ◽

Attention Mechanism ◽

Training Data ◽

Generative Adversarial Networks ◽

Natural Image ◽

Remote Sensing Images ◽

Training Time ◽

Adversarial Networks ◽

Remote Sensing Image Classification

Deep learning is an important research method in the remote sensing field. However, samples of remote sensing images are relatively few in real life, and those with markers are scarce. Many neural networks represented by Generative Adversarial Networks (GANs) can learn from real samples to generate pseudosamples, rather than traditional methods that often require more time and man-power to obtain samples. However, the generated pseudosamples often have poor realism and cannot be reliably used as the basis for various analyses and applications in the field of remote sensing. To address the abovementioned problems, a pseudolabeled sample generation method is proposed in this work and applied to scene classification of remote sensing images. The improved unconditional generative model that can be learned from a single natural image (Improved SinGAN) with an attention mechanism can effectively generate enough pseudolabeled samples from a single remote sensing scene image sample. Pseudosamples generated by the improved SinGAN model have stronger realism and relatively less training time, and the extracted features are easily recognized in the classification network. The improved SinGAN can better identify sub-jects from images with complex ground scenes compared with the original network. This mechanism solves the problem of geographic errors of generated pseudosamples. This study incorporated the generated pseudosamples into training data for the classification experiment. The result showed that the SinGAN model with the integration of the attention mechanism can better guarantee feature extraction of the training data. Thus, the quality of the generated samples is improved and the classification accuracy and stability of the classification network are also enhanced.

Download Full-text