فهرست مطالب farnaz hoseini

Face recognition is a pattern recognition process that is specifically performed on faces. Face recognition has many applications in identifying credit cards, security systems, and other cases. Creating a face recognition system with high accuracy is a big challenge that has been the focus of various researchers in recent years. The feature extraction process and classification are two important issues in diagnosis systems that can play a significant role in increasing the accuracy of diagnosis. Considering this issue, in this study, taking into account the combined features and optimizing the cuckoo algorithm, a method to improve the accuracy of face recognition is proposed. In the presented method, seven features are extracted from the images in the database, and then by obtaining the feature vector, the steps related to feature selection are performed using the cuckoo algorithm. The proposed method has been implemented with MATLAB software and compared with other methods. The evaluation results show that the proposed method was able to perform the detection on the images of ORL and FDBB databases with 93.00% and 95.12% accuracy, respectively. The result obtained for this evaluation criterion has a higher value than other compared methods.

Breast cancer is the most common cancer among women, particularly among women over 50 years old. Recent studies have proven that if breast cancer is diagnosed in the early stages of the formation of cancerous tissues, the chance of survival increases significantly and the costs of controlling the disease are greatly reduced. Therefore, the main solution is early detection of breast cancer. Until now, various research has been presented to diagnose breast cancer, but due to the selection of ineffective features and also the lack of using a suitable analytical method on the features, they could not achieve sufficient accuracy. In this study, LSD analysis and extraction of effective features by KNN classifier are used for automatic detection of breast cancer. The purpose of presenting the proposed method is to increase the accuracy of diagnosis for normal and non-normal classes. The proposed method was implemented in MATLAB environment and on the MIAS mammography image bank. The results obtained from the implementation output demonstrated the detection of breast cancer with 92% accuracy. The obtained results were compared with other methods, which shows the better performance of the proposed method in terms of accuracy criteria.

The knapsack problem is known as a NP-hard problem. The knapsack or rucksack problem consists of determining, given a set of items, each of which has a cost and a value, the number of items included in a collection such that the total cost is less than a given cost and the total value is as large as possible. There is a dynamic programming solution for this problem called the 0-1 knapsack. The 0-1 knapsack problem restricts the number of individual items to zero or one. The shuffled frog-leaping algorithm (SFLA) has long been considered a meta-heuristic algorithm that derives from how frog groups search for food. SFLA can improve computing performance by letting all frogs participate in memetic evolution and access an excellent ability for global search by adding the self-variation behavior to the frog. This study represents an efficient solution for the 0-1 knapsack problem using SFLA. Regarding the parallel nature of most meta-heuristic algorithms, they can be successfully used for speedup. Since it is time-consuming to test all the cases when the problems become larger, Compute Unified Device Architecture (CUDA) is used to implement the solution in parallel. The results of simulating the 0-1 knapsack problem using SFLA on the CUDA platform show that the execution time for a parallel solution decreases as the population of frogs increases. For the 0-1 Knapsack problem, it is 252 times faster than the sequential solution.

Image segmentation is one of the most common steps in digital image processing. The area many image segmentation algorithms (e.g., thresholding, edge detection, and region growing) employed for classifying a digital image into different segments. In this connection, finding a suitable algorithm for medical image segmentation is a challenging task due to mainly the noise, low contrast, and steep light variations of medical images. Due to the inherently parallel nature of image segmentation algorithms, they suit well for implementation on a Graphics Processing Unit (GPU). The main goal of this paper is to improve the performance of fuzzy c-means clustering through the parallel implementation of this algorithm. Although fuzzy c-means clustering is an important iterative clustering algorithm, it is computationally intensive and uses the same data between the iterations. The center of the clusters changes in each iteration, which requires a considerable amount of time for large data sets. The parallel fuzzy c-means clustering is implemented by applying pipeline parallelism on GPU. The experimental results show that the performance is improved up to 23.35x. Next, the watershed algorithm is applied to the final segmentation. In this paper using parallel fuzzy c-means clustering and computations we have attained competing results with other papers. The implementation results on the BRATS2015 show that the accuracy of diagnosis in Dice Similarity Coefficient metric 97/33% is obtained. This improvement is achieved using enhancing edges and reducing noises in images.

According to world health organization, breast cancer is one of the most deadly cancers occurred in women. Therefore accurate diagnosis and prediction is important to decrease the high death rate. The aim of this paper is twofold. First, improving breast cancer detection accuracy using Modified Fuzzy Logic (MFL) then improving the performance of MFL algorithm using GPU platform. The experimental results show that the accuracy of the breast cancer detection using MFL is higher than other techniques. In addition, by exploiting loop-level parallelism and pipeline parallel communication pattern in MFL algorithm, its performance is improved up to 19.17x for different image sizes.