Use of Neural Network Model to Examine Post-Operative Infections Following Orthognathic Surgeries in the United States

Our endocrine system is not only complex, but is also enormously sensitive to the imbalances caused by the environmental stressors, extreme weather situation, and other geographical factors. The endocrine disruptions are associated with the bone diseases. Osteoporosis is a bone disorder that occurs when bone mineral density and bone mass decrease. It affects women and men of all races and ethnic groups, causing bone weakness and the risk of fractures. Environmental stresses are referred to physical, chemical, and biological factors that can impact species productivity. This research aims to examine the impact of environmental stresses on bone diseases like osteoporosis and low bone mass (LBM) in the United States (US). For this purpose, we use an artificial neural network model to evaluate the correlation between the data. A multilayer neural network model is constructed using the Levenberg–Marquardt training algorithm, and its performance is evaluated by mean absolute error and coefficient of correlation. The data of osteoporosis and LBM cases in the US are divided into three groups, including gender group, age group, and race/ethnicity group. Each group shows a positive correlation with environmental stresses and thus the endocrinology.

Download Full-text

Effect of frost on plants, leaves, and forecast of frost events using convolutional neural networks

International Journal of Distributed Sensor Networks ◽

10.1177/15501477211053777 ◽

2021 ◽

Vol 17 (10) ◽

pp. 155014772110537

Author(s):

Sobia Wassan ◽

Chen Xi ◽

NZ Jhanjhi ◽

Laiqa Binte-Imran

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Model ◽

Neural Network Model ◽

The United States ◽

Plant Structure ◽

Weather Extremes ◽

Model Framework ◽

Data Set ◽

Frost Event

Climate change brings many changes in a physical environment like plants and leaves. The flowers and plants get affected by natural climate and local weather extremes. However, the projected increase in the frost event causes sensitivity in plant reproduction and plant structure vegetation. The timing of growing and reproduction might be an essential tactic by which plant life can avoid frost. Flowers are more sensitive to hoarfrost than leaves but more sensitive to frost in most cases. In most cases, frost affects the size of the plant, its growth, and the production of seeds. In this article, we examined that how frost affects plants and flowers? How it affects the roots and prevents the growth of plants, vegetables, and fruits? Furthermore, we predicted how the frost will grow and how we should take early precautions to protect our crops? We presented the convolutional neural network model framework and used the conv1d algorithm to evaluate one-dimensional data for frost event prediction. Then, as part of our model contribution, we preprocessed the data set. The results were comparable to four weather stations in the United States. The results showed that our convolutional neural network model configuration is reliable.

Download Full-text

An Artificial Neural Network Model to Reduce False Alarms in Satellite Precipitation Products Using MODIS and CloudSat Observations

Journal of Hydrometeorology ◽

10.1175/jhm-d-12-0172.1 ◽

2013 ◽

Vol 14 (6) ◽

pp. 1872-1883 ◽

Cited By ~ 24

Author(s):

Nasrin Nasrollahi ◽

Kuolin Hsu ◽

Soroosh Sorooshian

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Network Model ◽

Neural Network Model ◽

Artificial Neural Network Model ◽

The United States ◽

Training Dataset ◽

Detection Accuracy ◽

Satellite Precipitation ◽

Artificial Neural

Abstract The Moderate Resolution Imaging Spectroradiometer (MODIS) instrument aboard the NASA Earth Observing System (EOS) Aqua and Terra platform with 36 spectral bands provides valuable information about cloud microphysical characteristics and therefore precipitation retrievals. Additionally, CloudSat, selected as a NASA Earth Sciences Systems Pathfinder satellite mission, is equipped with a 94-GHz radar that can detect the occurrence of surface rainfall. The CloudSat radar flies in formation with Aqua with only an average of 60 s delay. The availability of surface rain presence based on CloudSat together with the multispectral capabilities of MODIS makes it possible to create a training dataset to distinguish false rain areas based on their radiances in satellite precipitation products [e.g., Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)]. The brightness temperatures of six MODIS water vapor and infrared channels are used in this study along with surface rain information from CloudSat to train an artificial neural network model for no-rain recognition. The results suggest a significant improvement in detecting nonprecipitating regions and reducing false identification of precipitation. Also, the results of the case studies of precipitation events during the summer and winter of 2007 over the United States show an accuracy of 77% no-rain identification and 93% detection accuracy, respectively.

Download Full-text