Despite the availability of radiology devices in some health care centers, thorax diseases are considered as one of the most common health problems, especially in rural areas. By exploiting the power of the Internet of things and specific platforms to analyze a large volume of medical data, the health of a patient could be improved earlier. In this paper, the proposed model is based on pre-trained ResNet-50 for diagnosing thorax diseases. Chest x-ray images are cropped to extract the rib cage part from the chest radiographs. ResNet-50 was re-train on Chest x-ray14 dataset where a chest radiograph images are inserted into the model to determine if the person is healthy or not. In the case of an unhealthy patient, the model can classify the disease into one of the fourteen chest diseases. The results show the ability of ResNet-50 in achieving impressive performance in classifying thorax diseases.

No abstract

In recent years, radiography systems have become more used in medical fields, where they are used for diagnosing many diseases. The size of the radiographs differs, as well as the size of the body parts for each patient. So many researchers crop the radiographs manually to facilitate the diagnosis and make it more reliable. Currently, the trend toward deep learning was commended where the deep learning proved its effectiveness in many fields, especially in the medical field, in which it achieves good results in diagnosing the most types of diseases. Deep learning performance increases significantly when the training process is focused on the region of interest. In this paper, segmentation is implemented by used deep learning model on the thoracic region of the radiograph in order to be cropped later. The proposed model provided automatic cropping of the radiographs where a semantic segmentation network is provided by Vgg19 model. A comparison is done with semantic segmentation network provided by Vgg16. The segmentation based on Vgg19 model outperforms Vgg16 model in cropping Chest x-ray images dataset automatically and quickly.

The proliferation of Internet of Things (IoT) markets in the last decade introduces new challenges for network traffic analysis, and processing packet flows to identify IoT devices. This type of device suffers from scarcity, making them vulnerable to spoofing operations. In such circumstances, the device can be recognized by identifying its fingerprint. In this paper, a novel idea to elicit Device FingerPrint (DFP) is presented by extracting 30 features from the collected traffic packets of 19 IoT devices during setup and startup operations. Raspberry Pi 3 Model B+ is configured as an access point to collect and analyze the traffic of seven networked IoT devices using Wireshark Network Protocol Analyzer. Moreover, the rest of IoT devices traffic is taken from the publicly available network traffic dataset. Each IoT device's feature extraction process starts from getting Extensible Authentication Protocol over LAN (EAPOL) protocol, continuing with the other flowed protocols until the first session of Transmission Control Protocol (TCP) related to that device is closed. Depending on some produced variation of device traffic features, 20 fingerprints for each device are created. The probability theorem of Gaussian Naive Bayes (GNB) supervised machine learning is utilized to identify fingerprints of individual known devices and isolate the unknown ones. The performance evaluation for the proposed technique was calculated based on two measures, F1-score and identification accuracy. The average F1 score was around 0.99, while the overall identification accuracy rate was 98.35%.

No abstract