Sharif Digital Repository

With the advent of the Internet of Things (IoT), e-health has become one of the main topics of research. Due to the sensitivity of patient information, patient privacy seems challenging. Nowadays, patient data is usually stored in the cloud in healthcare programs, making it difficult for users to have enough control over their data. The recent increment in announced cases of security and surveillance breaches compromising patients' privacy call into question the conventional model, in which third-parties gather and control immense amounts of patients' Healthcare data. In this work, we try to resolve the issues mentioned above by using blockchain technology. We propose a blockchain-based... 

In this thesis a comprehensive software code has been developed for analyzing dynamic behavior of rotary systems. Dynamic analysis of rotors consists of calculating critical speeds, mode shapes and vibrational response. The code is also capable to model unbalance, bend and misalignment faults. Due to the complexity of current misalignment models, a simplified model was developed. Rotor, disks and bearings were modeled and joined together to build the complete model. A novel procedure was suggested for modeling of multisectional rotors (such as, Tie-rod and Tie-bolts). Vibrational response has been calculated for each of the faults and effect of shaft and bearing parameters has been observed.... 

Nowadays, methods based on deep learning networks are the most effective artificial in­ telligence methods. Although they have achieved success in various fields (such as machine vision and object recognition), practical and experimental cases show the fragility of deep learning networks against perturbations and unwanted changes of the input pattern. All these perturbations must be in a way that the main class of the perturbed input pattern can be rec­ ognized by human, but the network makes a mistake in recognizing its correct class. This thesis seeks a more accurate evaluation by designing adversarial attacks such that the main class of the adversarial pattern is detectable by human...