Performance Validation of Neural Network Based 13C NMR Prediction Using a Publicly Available Data Source

2008 ◽  
Vol 48 (3) ◽  
pp. 550-555 ◽  
Author(s):  
K. A. Blinov ◽  
Y. D. Smurnyy ◽  
M. E. Elyashberg ◽  
T. S. Churanova ◽  
M. Kvasha ◽  
...  
Keyword(s):  
Neural Network ◽  
13C Nmr ◽  
Data Source ◽  
Performance Validation ◽  
Nmr Prediction

scholarly journals Cancer-Net SCa: Tailored Deep Neural Network Designs for Detection of Skin Cancer from Dermoscopy Images

2021 ◽  
Author(s):  
James Ren Hou Lee ◽  
Maya Pavlova ◽  
Mahmoud Famouri ◽  
Alexander Wong
Keyword(s):  
Neural Network ◽  
Skin Cancer ◽  
Open Source ◽  
Cancer Detection ◽  
Deep Neural Network ◽  
Well Being ◽  
Citizen Data ◽  
Performance Validation ◽  
Skin Cancer Detection ◽  
Improved Accuracy

Abstract Background: Skin cancer continues to be the most frequently diagnosed form of cancer in the U.S., with not only significant effects on health and well-being but also significant economic costs associated with treatment. A crucial step to the treatment and management of skin cancer is effective early detection with key screening approaches such as dermoscopy examinations, leading to stronger recovery prognoses. Motivated by the advances of deep learning and inspired by the open source initiatives in the research community, in this study we introduce Cancer-Net SCa, a suite of deep neural network designs tailored for the detection of skin cancer from dermoscopy images that is open source and available to the general public. To the best of the authors' knowledge, Cancer-Net SCa comprises the first machine-driven design of deep neural network architectures tailored specifically for skin cancer detection, one of which leverages attention condensers for an efficient self-attention design.Results: We investigate and audit the behaviour of Cancer-Net SCa in a responsible and transparent manner through explainability-driven performance validation. All the proposed designs achieved improved accuracy when compared to the ResNet-50 architecture while also achieving significantly reduced architectural and computational complexity. In addition, when evaluating the decision making process of the networks, it can be seen that diagnostically relevant critical factors are leveraged rather than irrelevant visual indicators and imaging artifacts. Conclusion: The proposed Cancer-Net SCa designs achieve strong skin cancer detection performance on the International Skin Imaging Collaboration (ISIC) dataset, while providing a strong balance between computation and architectural efficiency and accuracy. While Cancer-Net SCa is not a production-ready screening solution, the hope is that the release of Cancer-Net SCa in open source, open access form will encourage researchers, clinicians, and citizen data scientists alike to leverage and build upon them.

Artificial neural network simulation of 13C NMR shifts for methyl substituted cyclohexanes

1994 ◽  
Vol 24 (2) ◽  
pp. 129-135 ◽  
Author(s):  
A. Panaye ◽  
J.P. Doucet ◽  
B.T. Fan ◽  
E. Feuilleaubois ◽  
S.Rahali El Azzouzi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
13C Nmr ◽  
Network Simulation ◽  
Neural Network Simulation ◽  
Artificial Neural

Data source combination for tourism demand forecasting

2019 ◽  
Vol 26 (7) ◽  
pp. 1248-1265 ◽  
Author(s):  
Mingming Hu ◽  
Haiyan Song
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Search Engine ◽  
Demand Forecasting ◽  
Data Models ◽  
Time Series Models ◽  
Tourism Demand ◽  
Forecasting Performance ◽  
Data Source ◽  
Causal Variables

Search engine data are of considerable interest to researchers for their utility in predicting human behaviour. Recently, search engine data have also been used to predict tourism demand (TD). Models developed based on such data generate more accurate forecasts of TD than pure time-series models. The aim of this article is to examine whether combining causal variables with search engine data can further improve the forecasting performance of search engine data models. Based on an artificial neural network framework, 168 observations during 2005–2018 for short-haul travel from Hong Kong to Macau are involved in the test, and the empirical results suggest that search engine data models with causal variables outperform models without causal variables and other benchmark models.

scholarly journals Applying statistical analysis for assessing the reliability of input data to improve the quality of short-term load forecasting for a Ho Chi Minh City distribution network

2020 ◽  
Vol 2 (4) ◽  
pp. 223-239
Author(s):  
Phúc Duy Lê ◽  
Dương Minh Bùi ◽  
Duy Anh Phạm ◽  
Hoan Thanh Nguyễn ◽  
Hoài Đức Bành ◽  
...  
Keyword(s):  
Neural Network ◽  
Input Data ◽  
Distribution Network ◽  
Load Forecasting ◽  
Ho Chi Minh City ◽  
Data Filtering ◽  
Short Term ◽  
Filtering Method ◽  
Short Term Load Forecasting ◽  
Data Source

Short-term load forecasting has an extremely important role in the design, operation and planning of power system, especially on a power grid of Ho Chi Minh City (HCMC) - an active city has the highest power demand in Vietnam. Through the data survey, the load power in the HCMC area changes suddenly so that it causes disturbances in the load data. Accordingly, the reliability assessment of the load data will be essential in the processing stage of data-filtering before implementing load forecasting models. This study introduces a novel statistical data-filtering method that takes into account the reliability of the input-data source by analyzing many different confidence levels. Results of the proposed data-filtering method will be compared to previous data -iltering methods (such as Kalman, DBSCAN, Wavelet Transform and SSA filtering methods). The data source used in this study was collected from more than 50 substations uisng the SCADA system in Ho Chi Minh City's distribution network and was put into a neural network prediction model - ANN (Artificial Neural Network) and a ARIMA model (Autoregressive Integrated Moving Average), to demonstrate the effectiveness of the proposed data-filtering method. Numerical results derived from ANN and ARIMA predictive models show the effectiveness of the proposed data-filtering method, particularly, when the reliability of real data from the Ho Chi Minh city distribution network is determined at the 95% level, the forecasting results of ANN and ARIMA models using the proposed data-filtering method are obviously better than that without filtering method or using other data-filtering methods.

scholarly journals DEEP LEARNING (CNN) MODEL FOR COVID-19 DETECTION FROM CHEST XRAY IMAGES

2021 ◽  
Vol 6 (4) ◽  
Author(s):  
Ahmed Mohamed ◽  
Ahmed Abdelhady
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Early Stage ◽  
Open Data ◽  
Disease Outbreak ◽  
Imaging Features ◽  
X Ray ◽  
X Ray Imaging ◽  
Chest X Ray ◽  
Data Source

The Coronavirus disease outbreak result in many people to have severe respira- tory problems and it was recognized as a global health threat. Since the virus is targeting the lungs in the human body initially, chest x-ray imaging features were considered to be useful for the detection of the infection in the early stage. In this study, the chest x-ray data of 130 infected patients from an open data source that referenced Cohen J. Morrison P. Dao L., 2020 was used to build a CNN( Convolutional Neural-Network) model for the early detection of the disease. The model was trained with both infected and not-infected peoples’ chest x-ray images with 100 epochs which led to 0.98 accuracy finally. In order to use this model as a professional diagnosis element, it is highly recommended it be improved with more images and the model can be restructured to get a better accuracy.

Diagnostics of a Small Jet Engine-Neural Networks Approach

2005 ◽  
Author(s):  
M. Ghoreyshi ◽  
P. Pilidis ◽  
K. W. Ramsden
Keyword(s):  
Neural Network ◽  
Design Procedure ◽  
Performance Model ◽  
Training Data ◽  
Data Generation ◽  
Simulation Code ◽  
Jet Engine ◽  
Parameters Selection ◽  
Outdoor Test ◽  
Performance Validation

This paper presents the design procedure and application of a nested neural network for diagnostics of a small jet engine. Such a diagnostics technique is based on the performance analysis while the performance model was developed with TURBOMATCH, the Cranfield University’s gas turbine simulation code. To validate this model, an outdoor test was conducted to run the small engine. Areas examined in this paper are performance validation of the engine, neural network design, training data generation, and networks training procedures. The assumptions, measured parameters selection and the results obtained are presented and discussed. The results obtained show the good prospects for the use of NNs for detection of existing faults, isolation of faults and quantification of fault levels.

Sign in / Sign up

Export Citation Format

Share Document