Many people around the world are affected by pulmonary disease as well as asthma, pneumonia, lung cancer, and tuberculosis. All of these conditions have one thing in common: airway obstruction. Lung illnesses are a wo...
详细信息
Many people around the world are affected by pulmonary disease as well as asthma, pneumonia, lung cancer, and tuberculosis. All of these conditions have one thing in common: airway obstruction. Lung illnesses are a worldwide issue in which chronic obstructive pulmonary disease, pneumonia, asthma, tuberculosis, and fibrosis are few of the most common. An accurate diagnosis of a lung problem is essential, and it has been pursued by many researchers using image processing and machine learning models. Multiple deeplearning methods are used to predict lung disease;these include convolutional neuralnetworks, vanilla neuralnetworks, visual geometry group-based neuralnetworks, and the capsule network. Medical data are scarce, so diagnosing pulmonary diseases using chest x-ray pictures from datasets with less than 1000 samples is considered to address the problem. Three deeplearning multiple neuralnetworks (DLMNNs) were generated using the chicken swarm optimization (CSO) approach, for which transfer learning was applied to evaluate the performance of each. First, we created an algorithm for segmenting CXR images, and then we compared it with other classification systems. Our results were compared with those of other methods using publicly available data from the Shenzhen and Montgomery lung datasets. However, our technique has a lower number of trainable parameters compared with the best-performing models trained on the Montgomery dataset. The DLMNN-CSO virtually matched the best performance on the Shenzhen dataset, although it was computationally less expensive than the other models. DLMNN-CSO's validation loss was 0.4, whereas the validation loss for CNN, VDSNet, VGG, and DBN was 0.9, 0.8, 0.6, and 0.5, respectively.
The Internet of Things (IoT) is a global system of "smart devices " which senses and connects with their environment and communicates with users as well as other systems. Air Pollution (AP) is one of the mos...
详细信息
The Internet of Things (IoT) is a global system of "smart devices " which senses and connects with their environment and communicates with users as well as other systems. Air Pollution (AP) is one of the most significant global issues. Prevailing AP systems have low accuracy and require laboratory-based analysis. Therefore, improved prediction systems are needed. To overcome such problems, this paper proposes an IoT based efficient APprediction system utilizing the deep learning modified neural network (DLMNN) classifier. Initially, the faulty node detection is done in the sensor nodes using the H-ANFIS algorithm. Here, ANFIS is hybridized with the K-Medoid algorithm. After that, the features are extracted from the sensed data and the unnecessary features are reduced by using the MPCA algorithm. Next, based on the reduced features, the data are balanced by using Entropy-HOA. Then, the balanced sensed data are pre-processed using replacing of missing attributes and HDFS. Next, the pre-processed data are tested with an AP prediction system employing the DLMNN classifier, where the Pity Beetle Algorithm (PBA) is used for weight optimization. Then, the predicted result is stored in the cloud server. Finally, the stored data is visualized. Experimental results have proved that the proposed system gives a better result than the existing systems.
暂无评论