Sharif Digital Repository

Additive manufacturing (AM) has gained significant attention in recent years as a novel approach to fabricate three-dimensional parts. Its advantages, including high speed, low-cost production for small-scale batches, and greater design freedom, have made it a competitive alternative to traditional manufacturing methods. However, the application of AM for components subjected to fretting fatigue requires careful evaluation. Fretting fatigue is a major cause of failure in turbines, particularly at the contact interface between turbine blade roots and disk. In this study, the influence of AM and post-processing treatments on the fretting fatigue life of Ti-6Al-4V alloy was investigated. Five... 

One of the most important problems in machine learning is investigating the performance of the learning algorithms, and especially deep neural networks, on adversarial examples, which are generated by imperceptibly perturbing input images, so that cause the model make a wrong prediction. Not only this line of research is important for making deep neural networks dependable, but also can help with understanding the fundamental limitations of deep neural networks, and the nature of their operation, which can in turn provide researchers with valuable insights into artificial intelligence. In this research work, we have tried to approach the topic with a mainly theoretical mindset. The method we... 

Existing face forgery detection methods mainly focus on certain features of images, such as features related to image noise, local textures or frequency statistics of images for forgery detection. This makes the extracted representations and the final decision depend on the data in the database and makes it difficult to detect forgery with unknown manipulation methods. Solving this challenge, which is called the generalization challenge in artificial intelligence literature, has become the main goal of researchers in this field. In this thesis, the focus is on extracting effective features for success in forgery detection and preventing the performance of the forgery detection network from... 

Free access to large-scale public datasets, together with the rapid advancement of deep learning techniques and networks, particularly generative models, has led to the production of forged content whose distinction from authentic content has become impossible for humans and many classical forgery detection methods. The well-known term deepfake refers to a deep learning–based technique capable of generating forged images and videos by manipulating their content. A common example of deepfake forgery is identity manipulation in images and videos through facial alteration. In this research, three main objectives related to deepfake methods are considered. First, deepfake generation techniques... 

In recent years, deep learning has experienced rapid and remarkable advancements, demonstrating exceptional performance in various applications such as computer vision, natural language processing, and autonomous vehicles. These models are continually evolving and expanding, yet they harbor inherent vulnerabilities that prevent complete trust in their reliability. One of the most critical issues is their susceptibility to adversarial attacks, where a clean image is subtly manipulated to create an adversarial example. Adversarial examples, generated by adding imperceptible perturbations to input data, can easily mislead deep learning models into making highly confident yet incorrect... 

Wind energy technologies guarantee low pollution and operational costs. Using a DFIG and a fractionally rated power electronics converter gives variable speed operation with a low cost drive train. As energy policy organizations have allocated a considerable quota of wind energy generation to offshore wind farms, the absence of slip rings and brushes in the brushless DFIG (BDFIG) is an advantage for offshore wind turbines where maintenance is vital and expensive. With increasing wind power penetration in power systems, grid code requirements are an important consideration for the ride-through capability of wind farms through voltage dips, particularly for multi- MW wind turbine generators.... 

This study explores hysteresis in cardiac electrical and mechanical responses to heart rate changes. Specifically, the focus is on the RT interval (as a surrogate for QT) and the systolic interval (S1S2), extracted from ECG and PCG signals, respectively. Long Short-Term Memory (LSTM) models were trained to capture the dynamic relationship between RR intervals and each of these modalities. To evaluate temporal memory, synthetic step-like RR inputs were used, and the corresponding delays in model outputs were analyzed. The results showed clear hysteresis in both RT and S1S2 intervals, with delays increasing at higher workloads (i.e., shorter RR), indicating slower cardiovascular adaptation... 

Deep learning is one of the most powerful branches of machine learning, demonstrating exceptional performance in tasks such as image and speech recognition with the help of neural networks. However, deep learning networks are highly vulnerable to small and intentional changes in input data, known as adversarial perturbations. These perturbations, despite having a significant impact on the model's output, are usually imperceptible to humans and can pose serious security challenges in sensitive areas such as autonomous vehicles and medical diagnostics. To counter these perturbations, extensive research has been conducted, most of which has utilized a single deep learning network to create a...