ResNeXt convolution neural network topology-based deep learning model for identification and classification of Pediastrum

Pant, Gaurav; Yadav, Dhirendra Prasad; Gaur, Ashish

doi:10.1016/j.algal.2020.101932

Cited by 71 publications

(26 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The worst sub-index is the AQI for that location ( https://app.cpcbccr.com/AQI_India/ ). An increment in AQI causes acute and chronic mode health concern especially in the older age people and in children (Januszek et al 2020 ; Pant et al 2020 ). Due to the COVID-19 pandemic confinement, there is a significant reduction in the level of such toxic pollutants globally (Selvam et al 2020 ; Singh and Chauhan 2020 ).…”

Section: Origin Of Data Setmentioning

confidence: 99%

Air quality assessment among populous sites of major metropolitan cities in India during COVID-19 pandemic confinement

Pant

Alka

Garlapati

et al. 2020

Environ Sci Pollut Res

Self Cite

View full text Add to dashboard Cite

The present study aims to determine the impact of COVID-19 pandemic confinement on air quality among populous sites of four major metropolitan cities in India (Delhi, Mumbai, Kolkata, and Chennai) from January 1, 2020 to May 31, 2020 by analyzing particulate matter (PM2.5 and PM10), nitrogen dioxide (NO 2), ammonia (NH 3), sulfur dioxide (SO 2), carbon monoxide (CO), and ozone levels. The most prominent pollutant concerning air quality index (AQI) was determined by Pearson's correlation analysis and unpaired Welch's two-sample t test was carried out to measure the statistically significant reduction in average AQI for all the four sites. AQI significantly plummeted by 44%, 59%, 59%, and 6% in ITO-Delhi, Worli-Mumbai, Jadavpur-Kolkata, and Manali Village-Chennai respectively. The findings conclude a significant improvement in air quality with respect to reduction of 49-73%, 17-63%, 30-74%, and 15-58% in the mean concentration of PM2.5, PM10, NH 3 , and SO 2 respectively during the confinement for the studied locations. The p values for all of the four studied locations were found significantly less than the 5% level of significance for Welch's t test analysis. In addition, reduced AQI values were highly correlated with prominent pollutants (PM2.5 and PM10) during Pearson's correlation analysis. These positive results due to pandemic imprisonment might aid to alter the current policies and strategies of pollution control for a safe and sustainable environment.

show abstract

Section: Origin Of Data Setmentioning

confidence: 99%

Air quality assessment among populous sites of major metropolitan cities in India during COVID-19 pandemic confinement

Pant

Alka

Garlapati

et al. 2020

Environ Sci Pollut Res

Self Cite

View full text Add to dashboard Cite

show abstract

“…For comparison with already existing solutions, the networks YOLOv5 [ 37 ], Mask R-CNN [ 38 ], ResNeXt [ 39 ], VGG16 [ 40 ] were selected; they were trained on the same data sets as the network we are developing, namely: a set of data that was collected from the site “auto.ru”, “It is Train or Bus”, “UK Truck Brands Dataset”, “Vehicle Dataset”, “Open Image Dataset”, as well as the collected dataset with streets of Moscow.…”

Section: Resultsmentioning

confidence: 99%

“…For comparison with already existing solutions, the networks YO CNN [38], ResNeXt [39], VGG16 [40] were selected; they were trained sets as the network we are developing, namely: a set of data that was site "auto.ru", "It is Train or Bus", "UK Truck Brands Dataset", "Vehic Image Dataset", as well as the collected dataset with streets of Moscow Comparisons of classification quality for each class are presented best indicators for each class are highlighted in bold. It can be seen from the error matrix that the excavator is predicted extremely inaccurately, while there are no errors at all for bulldozers; this may be due to the insufficient number of examples of this class in the sample.…”

Section: Formation Of a Training Samplementioning

confidence: 99%

On the Problem of Restoring and Classifying a 3D Object in Creating a Simulator of a Realistic Urban Environment

Gorodnichev

Erokhin

Polyantseva

et al. 2022

Sensors

View full text Add to dashboard Cite

Since the 20th century, a rapid process of motorization has begun. The main goal of researchers, engineers and technology companies is to increase the safety and optimality of the movement of vehicles, as well as to reduce the environmental damage caused by the automotive industry. The difficulty of managing traffic flows is that cars are driven by a person and their behavior, even in similar situations, is different and difficult to predict. To solve this problem, ground-based unmanned vehicles are increasingly being developed and implemented; however, like any other intelligent system, it is necessary to train different road scenarios. Currently, an engineer is driving an unmanned vehicle for training and thousands of kilometers are being driven for training. Of course, this approach to training unmanned vehicles is very long, and it is impossible to reproduce all the scenarios that can be found in real operations on a real road. Based on this, we offer a simulator of a realistic urban environment which allows you to reduce the training time and allows you to generate all kinds of events. To implement such a simulator, it is necessary to develop a method that would allow recreating a realistic world in one passage with cameras (monocular) installed on board the vehicle. Based on this, the purpose of this work is to develop an intelligent vehicle recognition system using convolutional neural networks, which allows you to create mesh objects for further placement in the simulator. It is important to note that the resulting objects should be optimal in size so as not to overload the system, since a large number of road infrastructure objects are stored there. Also, neural complexity should not be excessive. In this paper, the general concept and classification of convolutional neural networks are given, which allow solving the problem of recognizing 3D objects in images. Based on the analysis, the existing neural network architectures do not solve the problems mentioned above. In this connection, the authors first of all carried out the design of the system according to the methodology of modeling business processes, and also modified and developed the architecture of the neural network, which allows classifying objects with sufficient accuracy, obtaining optimized mesh objects and reducing computational complexity. The methods proposed in this paper are used in a simulator of a realistic urban environment, which reduces the time and computational costs when training unmanned transport systems.

show abstract

“…Finally, the outputs of the three classifiers are integrated through a majority voting mechanism to obtain better classification performance. Narin et al (2021) proposed to use five types of pre-trained convolutional neural network (CNN) models (ResNet50, ResNet101, ResNet152, InceptionV3, and Inception-ResNetV2) to detect patients infected with coronavirus pneumonia based on chest X-ray. The pre-trained ResNet50 model obtained the highest classification performance.…”

Section: Introductionmentioning

confidence: 99%

“…effective than increasing depth and width, which improves the accuracy of the model without obviously increasing the order of magnitude of parameters, and also allows it to have fewer hyperparameters, which facilitates model portability. Since the introduction of ResNeXt network, it has been used by a large number of researchers(Koné and Boulmane, 2018;Pant et al, …”

mentioning

confidence: 99%

DR-IIXRN : Detection Algorithm of Diabetic Retinopathy Based on Deep Ensemble Learning and Attention Mechanism

Huang

Fan

et al. 2021

Front. Neuroinform.

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is one of the common chronic complications of diabetes and the most common blinding eye disease. If not treated in time, it might lead to visual impairment and even blindness in severe cases. Therefore, this article proposes an algorithm for detecting diabetic retinopathy based on deep ensemble learning and attention mechanism. First, image samples were preprocessed and enhanced to obtain high quality image data. Second, in order to improve the adaptability and accuracy of the detection algorithm, we constructed a holistic detection model DR-IIXRN, which consists of Inception V3, InceptionResNet V2, Xception, ResNeXt101, and NASNetLarge. For each base classifier, we modified the network model using transfer learning, fine-tuning, and attention mechanisms to improve its ability to detect DR. Finally, a weighted voting algorithm was used to determine which category (normal, mild, moderate, severe, or proliferative DR) the images belonged to. We also tuned the trained network model on the hospital data, and the real test samples in the hospital also confirmed the advantages of the algorithm in the detection of the diabetic retina. Experiments show that compared with the traditional single network model detection algorithm, the auc, accuracy, and recall rate of the proposed method are improved to 95, 92, and 92%, respectively, which proves the adaptability and correctness of the proposed method.

show abstract

ResNeXt convolution neural network topology-based deep learning model for identification and classification of Pediastrum

Cited by 71 publications

References 17 publications

Air quality assessment among populous sites of major metropolitan cities in India during COVID-19 pandemic confinement

Air quality assessment among populous sites of major metropolitan cities in India during COVID-19 pandemic confinement

On the Problem of Restoring and Classifying a 3D Object in Creating a Simulator of a Realistic Urban Environment

DR-IIXRN : Detection Algorithm of Diabetic Retinopathy Based on Deep Ensemble Learning and Attention Mechanism

Contact Info

Product

Resources

About