The face plays an essential role in identifying people and showing their emotions in society. The human ability to recognize faces is remarkable. But face recognition is a fundamental problem in many computer programs. Due to the inherent complexities of the face and the many changes in its features, different algorithms for face recognition have been introduced in the last 20 years. Face recognition methods that are based on the structure of the face are unsupervised methods that produce good results compared to the linear changes that occur in the image. In this article, the Gabor algorithm, which is the origin of face recognition algorithms, has been described. Over the past decade, most of the research in the area of pattern classification has emphasized the use of the Gabor filter bank for extracting features. Because the Gabor algorithm has shortcomings, researchers have introduced a new method that is a combination of Gabor and PCA. After the introduction of the Gabor method, more complete and accurate algorithms have been introduced, such as Boosting algorithms, which we have briefly explained in this article. Also, here are the results of the comparison made by the researchers between Boosting and Gabor algorithms. The results show that Boosting-based algorithms have performed better compared to Gabor-based algorithms.

Face recognition methods are computational algorithms that follow aim to identify a person's image according to the bank of images they have of different people. So far, various methods have been proposed for face recognition, which can generally be divided into two categories based on face structure and based on facial features. Based on this, many algorithms have been introduced and used for face recognition. Genetic algorithm has been one of the successful algorithms for face recognition. In this article, we first briefly explained the genetic algorithm and then used the combination of neural network and genetic algorithm to select and classify facial features The presented method has been evaluated using individual features and combined features of the face region. Composite features perform better than face region features in experimental tests. Also, a comprehensive comparison with other facial recognition techniques available in the FERET database is included in this paper. The proposed method has produced a classification accuracy of 94%, which is a significant improvement and the best classification accuracy among the results established in other studies.

Bone marrow is a spongy tissue that contains stem cells that are found inside some bones, including the hip and femur. Bone marrow cancer is a type of cancer that is caused by stem cells that make up the blood cells in the bone marrow. Sometimes these cells grow too fast or abnormally, which is called bone marrow cancer. Bone tissue cells are mainly composed of osteoblasts and osteoclasts. Osteoblast cells constantly build new bone throughout the life of each bone, and other cells called osteoclasts constantly absorb pieces of bone, so the bone is constantly being renewed. In this paper, mathematical models of tumors, the effect of the body on the drug, and the drug on the body are introduced, and then the appropriate dose of the drug to reduce tumor density is calculated using the model predictive control (MPC) algorithm. To obtain an adaptive MPC strategy, the extended least squares (ELS) method developed to learn the parameters of the tumor growth model is used. Finally, the simulation in MATLAB, assuming the model is correct, shows that the tumor is gone, and the bone mass improves over a period of time. The results demonstrate that the proposed method is effective for the treatment of bone marrow cancer.

Face recognition has attracted tremendous attention during the last three decades because it is considered a simple pattern recognition and image analysis method. Also, many facial recognition patterns have been introduced and used over the years. The SVM algorithm has been one of the successful models in this field. In this article, we have introduced the special faces first. In the following, we have fully explained the SVM method and its subsets, including linear and non-linear support vector machines. Suggestions for improving the recognition percentage of a person's identity check system by applying the SVM method on the face image using special faces are presented. For this test, 10 face images of 40 people (400 face images in total) have been selected from the ORL database. In this way, by choosing the optimal parameter C, determining the most suitable training samples, comparing more accurately with training images and using the distance with the closest training sample instead of the average distance, the proposed method has been implemented and tested on the famous ORL database. The obtained results are FAR=0.23% and FRR=0.48%, which shows the very high accuracy of the operation following the application of the above suggestions.

No abstract