With increasing population there is equally higher risk of laosing precious life due to natural calamities like Earthquakes, Floods, landslides etc. every year. We can minimize this risk by sensing the changes in advance and providing advance information with the help of exploding technologies. Internet of Things (IoT) is one such promising technology which has gained attention of researchers due to seamless connectivity between people and object. IoT represents a system where sensors are attached to objects via internet and thus provides real time data monitoring. The sensed data coming from IoT systems are not streamed properly. These data can be analyzed effectively by another promising technology called Deep Learning (DL) that can predict the likely possibility of a disaster threat. With the available information sensed using IoT devices incorporated withDeep Learning(DL) technique, we can predict the occurrence of a disaster looming in and thus minimizing the risk of losing life.

Health experts are increasingly taking advantage of the benefits of most modern technologies, thus generating a scalable improvement in the area of health care. Because of this, there is a paradigm shift from manual monitoring towards more accurate virtual monitoring with minimum percentage of error. Advances in artificial intelligence (AI) led to exciting solutions with high accuracy for medical imaging technology and is a key method for enhancing future applications. Detection of brain tumor is a very difficult task in medical field. Detection of brain tumor manually is time consuming and requires large number of mri images for cancer diagnosis. So, there is a need for automatic brain tumor detection from Brain MR images. Deep learning methods can achieve this task. Different deep learning networks can be used for the detection of brain tumors. The proposed method comprises of a classification network which classifies the input MR images into 2 classes: on with tumor and the second without tumor. In this work, detection of brain tumor is done via classification by retraining the classifier using the technique known as transfer learning. The obtained result shows that our method outperforms the existing methods.