Artificial neural networks for classifying the time series sensor data generated by medical detection dogs

Withington, Lucy; Vera, David Díaz Pardo de; Guest, Claire; Mancini, Clara; Piwek, Paul

doi:10.1016/j.eswa.2021.115564

Cited by 17 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks (ANNs) can simulate biological neurons and work by imitating the information transmission mode of biological neurons [ 22 – 27 ]. The structure of biological neurons is shown in Figure 2 .…”

Section: Construction Of the Obesity Monitoring Model Based On Sa Algorithmmentioning

confidence: 99%

[Retracted] Obesity Mass Monitoring in Medical Big Data Based on High‐Order Simulated Annealing Neural Network Algorithm

Ren

Zhao

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the rapid development of information technology, hospital informatization has become the general trend. In this context, disease monitoring based on medical big data has been proposed and has aroused widespread concern. In order to overcome the shortcomings of the BP neural network, such as slow convergence speed and easy to fall into local extremum, simulated annealing algorithm is used to optimize the BP neural network and high-order simulated annealing neural network algorithm is constructed. After screening the potential target indicators using the random forest algorithm, based on medical big data, the experiment uses high-order simulated annealing neural network algorithm to establish the obesity monitoring model to realize obesity monitoring and prevention. The results show that the training times of the SA-BP neural network are 1480 times lower than those of the BP neural network, and the mean square error of the SA-BP neural network is 3.43 times lower than that of the BP neural network. The MAE of the SA-BP neural network is 1.81 times lower than that of the BP neural network, and the average output error of the obesity monitoring model is about 2.35 at each temperature. After training, the average accuracy of the obesity monitoring model was 98.7%. The above results show that the obesity monitoring model based on medical big data can effectively complete the monitoring of obesity and has a certain contribution to the diagnosis, treatment, and early warning of obesity.

show abstract

Section: Construction Of the Obesity Monitoring Model Based On Sa Algorithmmentioning

confidence: 99%

[Retracted] Obesity Mass Monitoring in Medical Big Data Based on High‐Order Simulated Annealing Neural Network Algorithm

Ren

Zhao

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Thus, the concept of DL is used in the classification of Otitis disease. Artificial neural network (ANN) is a popular method in the concept of DL and is used in solving problems by doing learning in the network [19]. ANN gives results by presenting a fairly high level of accuracy [20].…”

Section: Introductionmentioning

confidence: 99%

Optimization deep learning with rough set approach model classification Otitis

Arief Wisky,

Ade Putra

2023

IJEECS

View full text Add to dashboard Cite

<span>Otitis is a disease that occurs in the middle ear in the form of inflammation. This research aims to develop an analysis model for the classification of Otitis disease based on knowledge patterns based on symptoms and type of disease. The analysis methods used include the performance of the certainty factor (CF), rough set (RS), artificial neural network (ANN), and decision tree (DT) methods. CF and RS performance can be used to generate classification rule patterns. These rule patterns become new knowledge in the classification analysis process using the concept of deep learning (DL). DL analysis with ANN and DT performance can work optimally in exploring and discovering hidden knowledge. Based on the results of performance testing, the combination of CF and RS in preprocessing can present a classification pattern of 106 rules. The output of DL analysis results is proven to produce precise and accurate classification results with an accuracy of 89%. Based on these results, the analytical model developed was proven to be effective in classifying Otitis disease. Not only that, this research is also able to contribute to updating the knowledge-based system in the classification process.</span>

show abstract

Canine Detection of Cancer in Humans: Expectations Versus Reality

Jezierski,

Dzięcioł

2023

Chemical Signals in Vertebrates 15

View full text Add to dashboard Cite

Artificial neural networks for classifying the time series sensor data generated by medical detection dogs

Cited by 17 publications

References 27 publications

[Retracted] Obesity Mass Monitoring in Medical Big Data Based on High‐Order Simulated Annealing Neural Network Algorithm

[Retracted] Obesity Mass Monitoring in Medical Big Data Based on High‐Order Simulated Annealing Neural Network Algorithm

Optimization deep learning with rough set approach model classification Otitis

Canine Detection of Cancer in Humans: Expectations Versus Reality

Contact Info

Product

Resources

About