Early Lung Cancer Prediction Using Neural Network with Cross-validation | Asian Journal of Research in Infectious Diseases

 The name of lung cancer is lung carcinoma. It is a condition that contributes to uncontrolled cell growth in the lung tissue, which is a malignant tumour. Generally, lung cancer is caused by smoking and the use of tobacco products. Two large small-cell lung carcinomas and non-small-cell lung carcinomas are classified. Surgery, radiation therapy, chemotherapy, and targeted therapy are lung cancer therapies. Lung cancer is one of the world's most common causes of death. Early detection of this disease will assist both the medical care unit and doctors in providing patients with countermeasures. The goal of this paper is to discuss an automated method that takes feedback from influential causes of lung cancer and identifies patients with higher risks of being affected by this disease. This paper proposes a neural network classifier followed by the k-fold cross-validation technique as a predictive method. This suggested approach is later compared with another Gradient Boosting Classifier baseline classifier to justify the efficiency of the forecast. Experimental findings suggest that the study of interfering causes of lung cancer with an accuracy of 95% will effectively achieve the disease classification model.

Please see the link :- https://www.journalajrid.com/index.php/AJRID/article/view/30153

GAS TYPE DETECTION AND CONCENTRATION ESTIMATION USING THERMAL MODULATED RESISTIVE SENSOR AND NEURAL NETWORKS

In this paper, a new processing sensor data method base on neural networks and principal component analysis block is presented in order to identify the gas type and to estimate the gas concentration. Three gases in thirteen different concentrations have been examined including methanol, ethanol, and 2-propanol. For temperature modulation, the stair-case voltage was applied to the sensor heater at spans of 40s in 200s. In each of the obtained curves, at any span, transient and steady state responses were recorded. These recorded properties are analyzed using the usual methods of pattern recognition. Principal component analysis was used to increase the selectivity of the sensor and the neural network was used to recognize the type and estimate the gas concentration. In this study, we have achieved the separation of gases successfully as well as average estimation error concentration was calculated to be 0.00358%.

Please read full article : - www.ikprress.org