Sharif Digital Repository

In the complicated industrial world interactions between human and machine always result in the higher human risk. Moreover, human may act differently in same situations on the basis of iner conflict, complexity or diverse motivations. Therefore, investigating human reliability is really more complicated than reliability of some mechanic parts of the system.within this study, human reliability factors have been intensively explored and based on Mamdani Fuzzy Inference and PROMETHEE these factors ranked for numerical example. Using this method, one may benefit its dynamic adaptivity and also its ability to contain eperts knowlegde within the Fuzzy Role Base. Furhtermore, Validity of the... 

Human tracking is one of the most important research topics in computer vision with application in surveillance, crowd analysis, human motion and behavior analysis, and human-computer interaction. Availability of a large number of cameras has caused the need of designing automatic tracking methods. One of the most important challenges in automatic tracking is the occlusion of objects. Several methods have been proposed in the literature to solve this problem. One of the most popular and powerful methods is based on the usage of multiple views of the same scene in a cooperative manner between cameras. The most important challenge in using multiple cameras is the complexity of the tracker in... 

Human tracking is an essential step in many computer vision-based applications. As single view tracking may not be sufficiently robust and accurate, tracking based on multiple cameras has been widely considered in recent years. This thesis presents a distributed human tracking method in a smart camera network and introduces a particle filter design based on Histogram of Oriented Gradients (HOG) and color histogram. The proposed adaptive motion model also estimates the target speed from the history of its latest displacement and improves the robustness of the tracker by decreasing the probability of missing targets. In addition, a distributed data fusion method is proposed which fuses the... 

Recognizing human actions is an important and challenging topic in computer vision, which has important applications such as video surveillance and Indexing. From a computational perspective, actions can be defined as three-dimensional patterns, in space and in time which can be modeled using several representations. Action representations differ in visual information used in spatial dimensions (e.g., shape or appearance) and the representation of dynamics in time. The goal of this thesis is to develop new techniques and improve current results in action categorization. As such, using a general structure, three methods are proposed. In this structure, local spatio-temporal features are... 

Suspension systems play a significant role in vehicles. They are responsible for providing ride comfort to the passengers and maintain car handling. Vibrations induced by the road can cause harmful effects on human body and this reveals the importance of designing and controlling the suspension system. Semi-active control is a reliable and safe method that has attracted a great deal of attention in the suppressing the car vibration. MR damper is a sample of semi-active control method. In most of the studies that have been done in literature the human body model has not been considered in designing the control strategy. In this study, a complete model of suspension system integrated with the... 

Simultaneous development of technology and social networks and universal access to them caused to produce and distribute huge volume of videos that recognition of their content without use of machine vision is very hard. This thesis examine some video classification algorithms to improve them. The algorithm that is used to improve is based on one of local descriptor algorithms. At first with using STIP tools, the local interest point found by Harris3d and describe by HOG/HOF. Then by using Bag of Features, all local descriptors in a video produce a descriptor per videos. Bag of Features divide the domain of all local descriptors from all videos to K cluster and produce a vector per video... 

While the science–religion debate on human creation has been widely explored in the Muslim world، Iranian Muslim opinions have been missed in the mainstream literature. To see whether they follow the lead of the majority of Muslim thinkers or not، here is an overview of the Qur’anic Perspective of Iranian Muslim Scholars. After reviewing the previously categorized approaches of Muslims encountering evolution mentioned in the literature، this thesis will survey the Qur’anic verses related to the biological creation of man with the “scientific-lexical” method of all possible states. Afterward، the views of the most-cited Iranian scholars، such as Saḥābī، Ṭabāṭabā’ī، Muṭahharī، and Jawādī، will... 

Innovations in laser, microwaves, and similar technologies have significantly advanced thermal treatments for diseases or even injuries concerning skin tissue. For a thorough understanding in the underlying mechanisms of bioheat transfer behavior of skin,a1D unsteady non-dimensional hyperbolic model of heat transfer through this tissue with metabolic heat generation which is subject to specific boundary conditions, is solved numerically using the finite difference method. A thermal shock is generated at the base of the tissue, which moves forward with a finite speed. A Numerical solution for a simple one-layer skin tissue is obtained. Then, the effects of various parameters, time step,... 

Natural intuitive human-robot interaction depends on how responsive a social robot can be to environmental information. Speaker localization is a prominent ability for communication and socialization that allows the robot to react to a speaker by turning its head towards it. In this paper, we have designed and implemented a robotic head, “Ava”, which turns toward the speaker in noisy environments. Ava is able to detect and enhance a speech activity and estimate the azimuth direction and vertical level of a speaker. The speech segments which are differentiated by a Speech Activity Detection system are processed to reduce noise levels. Then, by extracting the binaural features of two signals... 

The goal of this research is to elucidate the mechanism of Cell recognition in molecularly imprinted polymers (MIPs) using already utilized techniques. Our approach employs a more flexible non-covalent imprinting method which starts from a readily available polymer and utilizes an aqueous environment for both MIP synthesis and testing. Cell MIPs against MG-63 cell were synthesized. The synthesis procedure was optimized to obtain better binding characteristics to the targeted cell. Adsorption of target cell onto imprinted Alginate Spheres was facilitated by these macromolecular fingerprints as revealed by various microscopical examinations The imprinted Spheres showed high selectivity toward... 

In recent years, dialogue generation systems as a branch of natural language text generation have made significant progress. These systems enable human-machine conversations and based on their application, they’re divided into two categories: the goal-oriented, and the open-domain dialogue systems. A goal-oriented dialogue is based on a specific goal, such as the hotel reservation or the product recommendation, while there is no specific topic or goal in the open-domain conversations. This wide coverage of topics in open-domain systems causes some occasional contradictions between utterances. Therefore, preserving dialogue consistency has become a challenge in open-domain dialogue systems.... 

Falling is a prevalent event among elderly people, which sometimes leads to their death. Automatic detection of fall can significantly reduce the resulting damages.Fallings can be detected using various modalities, among which we choose RGB videos captured by CCTV cameras because of its advantages. Due to the great advances in deep learning-based image/video classification methods, we focused on using these methods for fall detection. One of the main challenges in using deep learning methods is lack of enough training data. Unlike other activities, there are not enough falling samples available which is due to its unconscious nature. Moreover, simulating falling by actors can endanger their... 

In software testing, it is often desirable to find test inputs that exercise specific program features. Good testing means uncovering as many faults as possible with a potent set of tests. Thus, a test series that has the potential to uncover many faults is better than one that can only uncover a few. To find these inputs by hand is extremely time-consuming, especially when the software is complex. Therefore, many attempts have been made to automate the process. There are three major methods to generate software test data: Random test data generation, Symbolic test data generation and Dynamic test data generation. Dynamic test data generation, such as those using genetic algorithms, is... 

Human action recognition is nowadays within the most active computer vision research areas. The problem of action recognition is challenging due to the large intra-class variations, noise and high dimension of video data. Recent development of affordable depth sensors leads to new opportunities in this field by providing depth data. Literature of vision based human action recognition can be divided into two main groups of handcrafted and deep learning based approaches. In the first approach, a supervised spatio-temporal kernel descriptor (SSTKDes) is proposed from RGB-depth videos. To enhance the discriminative ability of the descriptor, extracted primary kernel-based features are... 

Human Activity Recognition (HAR) has had tremendous improvements in the field of elderly monitoring and telerehabilitation. An anchor point for HAR systems in telerehabilitation is supervising rehabilitative excercises. For Parkinson’s disease (PD) patients, a group of rehabilitative activities, known as Lee Silverman Voice Treatment-BIG, or LSVT-BIG, have shown to be effective in improving motor performance. Similar to any rehabilitative measure, delivering these activities requires the supervision of an expert or clinician, so that the patient receives proper feedbacks. HAR systems can replace human experts. They can recognize activities and provide the user with proper feedback. HAR... 

Nowadays exoskeltons are developed because of improvements carried out in mechatronic technologies, to use in applications such as human rehabilitation and power augmentation. By reason of interaction between exoskeleton robot and human, an appropriate control strategy should be considered to implement regulated interaction force between them. As an example there are situations that a person wants to carry heavy load with this robot without suffering from weight of the load, so control of robot movements is of great importance. The aim of this thesis is dedicated to develop and implement a control strategy achieving minimum ineraction force in a 2 degree of freedom lower limb exoskeleton.... 

Exoskeleton robot is so useful because of the interaction with them and human and are used in rehabilitation and augmentation applications. These robots can be either passively or actively actuated. Human and robot interaction is an important issue involved with these robots. In this thesis, the interaction force reduction is considered leading to the transparency of a lower limb exoskeleton during switch between swing and stance phasees of walking. Achieving this goal, a robust Lyapunov based motion control method has been developed. The desired reference signals for motion control are generated using a direct force control approach. Robot accelerations are estimated by an observer to be... 

The statistics show that around 5% of the world's population suffers from deafness. For these people, the most comprehensive way of communicating with the world around them is using sign language. These facts will clarify the need for review in design practices, especially in designing user interfaces, in order to make technology usable for people with disabilities. The present study wants to design a sign language-based user interface for the RASA robot. The goal is to enable the robot to interact with deaf users. In the first step, a cognitive architecture developed, to enable the robot to interact by sign language in specific working conditions. The second step was the implementation of a... 

From the creation of the first robots, researchers have been fascinated by the possibility of interaction between a robot and its environment, by the possibility of robots interacting with each other and with humans. The common, underlying assumption is that humans prefer to interact with machines in the same way that they interact with other people. In this work, an assistant robot is developed based on a commercial platform, known as Alice R-50 (with the Iranian name of Mina). Alice is designed specifically for human-robot social interaction and has been used widely for studies on developmental and social robotics. It is used to improve and encourage the development of communication and... 

Natural sciences have philosophical and ideological fundamentals. "The attitude towards human", is one of these philosophic or metaphysical fundamentals of science so that scientists and researchers, attentive or not, take it as a basis for their scientific activities. In the other hand, "the science" also affects "The attitude towards human", and different scientific theories caused various attitudes towards human to take shape. "Renaissance" is one of the most important and sophisticated historical periods of the west`s history, and the changes in this period are among the main basics of entering the modern age. In this thesis, first of all some issues about the fundamentals of the science...