Sharif Digital Repository

The precise positioning of magnetic catheters is critical for a range of medical procedures, ensuring efficacy while minimizing potential complications. This research delves into the position control of a magnetic catheter influenced by an external permanent magnet. Due to the intricate and complex equations describing the plant's behavior, a neural network approach was deemed suitable for modeling. Using a 5 degree of freedom manipulator carrying an external permanent magnet, data was gathered from real-world positionings, tracking the coordination of the magnetic catheter's end. These data points served to train the neural network, subsequently allowing for an effective simulation of the... 

A Brain-Computer Interface (BCI) is a communication system that does not need any peripheral muscular activity. The huge goal of BCI is to translate brain activity into a command for a computer. One of the most important topics in the brain-computer interface is motor imagery (MI), which shows the reconstruction of subjects. The electrical activities of the brain are measured as electroencephalogram (EEG). EEG signals behave as low to noise ratio also show the dynamic behaviors.In the present work, a novel approach has been employed which is based on feature extraction with discretion wavelet transform (DWT), support vector machine (SVM), Artificial Neural Network (ANN) and Convolutional... 

In the recent years, development of new technologies in the field of cognitive science has made a huge effect on the people social life style. Facial expression imitation with applications in the design of human robot interaction (HRI) systems is an active area of research. In this study, we propose an approach using a humanoid social robot, The Alice, for real-time imitation of human facial expression. The facial keypoints of the user are extracted by using the Kinect sensor together with manipulated SDK 2.0 codes. Kinect output array are collected for each expression, then the training dataset is created with these output arrays. An accurate Artificial neural network (ANN), which has a... 

Nowadays, industrial companies deal with a wide range of serious problems in the field of power transmission maintenance and also fault detection. A large amount of money and time is spent on these issues in order to solve them; consequently, there is an essential need for this subject. In this thesis, in order to tackle those major issues which were referred above, an artificial neural network is trained with only one hidden layer. Also, a suitable database for training an efficient neural network is needed. Thus, a one-stage gearbox system with appropriate degrees of freedom is used to set up referred database. In this system, a crack is imposed to a tooth of spur gear with different sizes... 

In recent years, Rheological behavior and heat transfer of nanofluid studies have been increasing considerably and results show significant progress in this area. In this study we analyze the laboratory examination of the influence of parameters of volume fraction and temperature on thermal conductivity coefficient, dynamic viscosity of new and useful nanofluid carbon nanotube in engine oil. Most of fluid comparing to solid has lower thermal conductivity coefficient therefore solid particles increase thermal conductivity coefficient. On the other hand by adding particles, the dynamic viscosity of nanofluid also increases. Since nanoparticles have high volume ratio to surface (SSA) they have... 

Lack of force feedback during minimally invasive procedures is one of the downsides of such interventions and might result to excessive damage to surrounding tissues. The goal of the present research is to introduce a vision-based approach to estimate contact forces on soft tissues. In this approach, a model was developed in which, image of deformation of a sample soft tissue, under the jaws of laparoscopic gripper, is the input and the output is the gripper force. In this work, a FEM of soft tissue in contact with jaws of a laparoscopic tool is developed. . In the model, the effects of friction between the tool and tissue is considered which was not included in the previous studies. After... 

The investigation of the behavior of structures subjected to various kinds of loadings is of considerable importance. In this research, an attempt was made to analyze behavior of beams that a load is moving on them.Most of the existing relevant works in this field are dealt with examination of elastic beams with constant section, while in most cases beams with variable sections are used in order to have the optimum structure and appropriate stress distribution and to maximize strength to weight or cost ratio. While construct analysis is very advantageous, it is very difficult due to the complexities arising from the variable sections. But this design is so advantageous that it dominates... 

Pump operating problems may be either hydraulic or mechanical and there is interdependence between the failure diagnoses of these two categories. Consequently, a correct diagnosis of a pump failure needs to consider many symptoms including hydraulic or mechanical causes. Nonlinear, time-varying behavior, and imprecise measurement information of the systems makes it difficult to deal with pump failures with precise mathematical equations, while human operators with the aid of their practical experience can handle these complex situations, with only a set of imprecise linguistic if-then rules and imprecise system states, but this procedure is time consuming and needs the knowledge of human... 

An event must be modeled in a way that either reflects a comprehensive perspective for the event or acts in an especial part of that event, roperly. The main aim of this thesis is to control. Therefore the models will be accepted whenever the suggested mathematical models can move towards controller final target, desirably.This thesis proposes a linear mathematical model, five nonlinear models and a simple model based upon Convolution, Fuzzy Regression and Neural Networks techniques for Acquired Immune Deficiency Syndrome (AIDS), respectively. The proposed models were achieved through studying 300 HIV+ Patients who were under Highly Active Antiretroviral Therapy (HAART) approach in Iranian... 

Tool Condition Monitoring (TCM) is a vital demand of advanced manufacturing in order to develop automated unmanned production. Tool condition has an essential influence on machined surface quality and dimension of manufactured parts. Continuing machining operation with a worn or damaged tool will result in damages to workpiece and even the machine tool itself. This problem becomes more important in supplementary machining processes like drilling in which the workpiece is usually at the final stages of production and any damage to workpiece at this stage is irreparable and results in high production losses. In this thesis, sound and vibrations signals are analyzed for drill wear detection.... 

The objective of this project is to consider the various methods employed in processing the EMG signal to control an artificial hand. The current presented methods of EMG processing do not benefit from the fact that sequential movements are closely correlated. Using this time correlation we are going to improve the correctness of the prediction of movements. To find the application of this project in commercial artificial hand we focus on one DOF hand for a high level of accuracy. Using this processing method combined with an artificial hand having Geometric Adaptability may present an acceptable product for commercial use.

 

This thesis describes different neural networks models and an approximation based neural network controller for autonomous underwater vehicles (AUVs). The online multilayer perceptron neural networks (OMLPNN) have been designed to perform modeling of AUVs of which the dynamics are highly nonlinear and time varying. The online recurrent multilayer perceptron neural networks (ORMLPNN) have been additionally designed to generate a memory to pervious states and increase the performance of the modeling. The designed OMLPNN and ORMLPNN with the use of backpropagation learning algorithm have advantages and robustness to model the highly nonlinear functions. The proposed neural networks architecture... 

Wound healing is a complex biological process dependent on multiple variables: tissue oxygenation, wound size, contamination, etc. Many of these factors depend on multiple factors themselves. Mechanisms for some interactions between these factors are still unknown. In this resarch we try to simulate and control wound healing process with focusing on remodeling phase by neural networks as an intelligence technique. For these purposes some materials like mathematical modeling, finite elements method, and effect of external forces on the scar tissue are used here  

Mobile robots are increasingly being used to perform tasks in unknown environments. The potential of robots to undertake such tasks lies in their ability to intelligently and efficiently locate and interact with objects in their environment. My research focuses on developing algorithms to navigate mobile robots in a partially known environment observed by an overhead camera. The environment consists of stationary and dynamic obstacles and a moving target. The aim of the robot is to select avoidance maneuvers to avoid the dynamic obstacles while approaching the target. The core of the navigation algorithm is based on the velocity obstacle avoidance method and the guidance-based tracking... 

Neuron models are the elementary units, which determine the performance of an Artificial Spiking Neural Network (ASNN) as they are known to be a particular class of machine learning methods. The ASNNs that are inspired by the features of biological neurons and organizational structure of biological nervous system as the third generation of Artificial Neural Networks (ANN). This thesis concentrates on study of biologically plausible neuron; based on Fuzzy approach and tries to develop fuzzy state of Leaky Integrate and Fire (LIF) model, in order to resemble closely the neuron-electrical dynamics for ASNN in most efficient way. In this study, the Fuzzy methods including TAKAGI-SUGENO-KANG... 

Cardiovascular diseases (CVDs) have ranked first cause of deaths globally. In 2016, about 17.7 million people died from CVDs representing 31% of all world deaths. So, early intelligent detection of cardiovascular disease could help to save many lives in worldwide. There are several methods to analyze heart activity and to detect any abnormalities including Electrocardiogram, Stress test, Echocardiography, cardiac catheterization and coronary angiography.Among all methods, Electrocardiogram (ECG) is the most common and convenient type where it measures heart electrical activity and records it as a series of pulses. Analyzing these pulses would provide useful information about normal and... 

Cerebrovascular Attack has been ranked the second or third of top 10 death causes in Taiwan. It has caused about 13,000 deaths every year since 1986. Once Cerebrovascular Attack (CVA) occurs, it not only leads to the huge cost of medical care, but even death. All developed countries in the world put CVA prevention and treatment in high priority. However, it is necessary to build a detective model to enhance the accurate diagnosis of CVA. From this detective model, CVA classification rules were extracted and used to improve the diagnosis and detection of CVA. This study acquired 2449 valid samples from this CVA prevention and treatment program, and adopted three classification algorithms,... 

Weed management is the important issue in agriculture. Using herbicides is one of the strategies to control weed. But using huge amount of herbicides are destructive for environment. Smart spraying system is an impressive solution for this problem. This system detects weeds and sprays just them instead of spraying overall field. In this thesis a new method for plant detection is presented by using Lab color space. We determine the type of plants (broadleaf/grass) to spray specific herbicides onto specific type of plant. One feature of grass plants (the parallel edges of leaf) is used to detect grass plants. A convolutional neural network with four layers and fuzzy logic are used to separate... 

Human brain is one the most efficient biological neural network that is capable of performing most complicated tasks in very short time. Visual system as a part of the brain can process the visual records from the environment and perform very useful processes on them. The information provided from visual system processes play important roles in human intelligence. In this thesis we introduce and investigate one of the well-known theories about visual system called gestalt theories. These theories tried to define how a biological neural network can perform such results. Gestalt theorists developed rules of perception to explain their ideas including Law of Pragnanz, Similarity, Closure,... 

A survey on the methods of detecting a human body inside surrounding captured images of a machine, optimizing one of these methods and finding an injured person in a captured picture is our target. Using neural networks for better detection and making RBFN network, make it possible to use high altitude captured pictures with lower resolution and light changes. Modifying RBFN to MRBFN network for an optimized processing with effect of living signs seems to be an applicable approach. These methods can extended from detecting an injured person in a captured picture, to analyze the medical images like detecting a special pattern in MRI picture. Of course it’s a start for many future...