مهدی نوشیار

Photogrammetric analysis of facial soft tissue plays an important role in facial plastic surgeries. In many countries, planning for facial plastic surgery is done based on the defined facial metric standards for the same society. Few research works have been conducted in the field of facial cephalometric criteria of the Iranian race. The main goal of this study is to determine the average values of facial profile view metrics of people referred to Imam Reza Hospital (Ardabil).

First, in a period of 3 months, facial profile view images of the referred patients including 30 males and 30 females were provided. Then, the angular criteria of the profile view were measured by selecting 11 facial anatomical landmarks applicable for Rhinoplasty and Mentoplasty surgeries in the MATLAB software.

The results showed that among the facial profile view metrics, the Nasofrontal, Nose Tip and Mentolabial angles are close to the criteria of the Turkish, Nepalese and Brazilian races, respectively. The Facial Convexity Including Nose (FCIN) metric is close to the Brazilian and Nepalese races, and also, Facial Convexity Excluding Nose (FCEN) is close to the Bangladesh and Brazilian races.

In this study, cephalometric analysis of facial soft tissue was done by measuring the facial profile view metrics to help facial plastic surgeons. Considering the difference in facial metrics of Iranians with other races, the criteria measured in this study can be interesting for surgeons in planning of facial cosmetic surgeries, especially Rhinoplasty and Mentoplasty.

Identifying and diagnosing Alzheimer's disease in brain tissue is one of the serious challenges in diagnosis in the field of medical image processing. Currently, MRI is the most common way to diagnose Alzheimer's disease, and failure to correctly identify the tissue involved in it can lead to incorrect diagnosis as healthy brain tissue. Deep learning algorithm as a process of detecting features related to damaged tissue and extracting useful information. In this research, we decided to use the convolutional neural network in the processing of medical images so that we can perform the diagnosis with better accuracy than the previous works.

Using a convolutional neural network, the features of MRI images have been extracted. Alzheimer's images have been analyzed using Matlab2023a software and the intended outputs have been obtained.

Brain Alzheimer's images have been analyzed after pre-processing and entering the deep neural network, and in the output of the proposed algorithm, the identification accuracy and identification speed of the algorithm with the improvement of cloud parameters was higher compared to other common methods, which was 96% accuracy. presented in identification.

The purpose of using deep learning is to make image data with large dimensions and a large number into a conceptual form for machines. It is expected that in the future feature extraction will be done more accurately and more details will be available to machine vision systems to recognize objects in the image.

Today, heart disease is one of the main causes of morbidity and mortality. Since the initial and early diagnosis of this disease is very important and vital and the usual methods used in the medical industry need to spend a lot of time and money to diagnose this disease, accurate prediction of this disease has become a challenge. According to the huge amount of hospital data, which is added to its volume every day, the importance of data mining, which is one of the important techniques for discovering knowledge and hidden patterns, is increasing. Many studies have been done based on data mining to predict heart disease; according to their solution, each one pursues goals such as increasing speed, increasing accuracy, reducing the volume of calculations, and error coefficient. This research aims to increase the reliability and accuracy of heart disease diagnosis using the feature selection technique by meta-heuristic algorithms to extract useful features and to reduce the computational burden, and we use machine-learning algorithms to evaluate the proposed method. The results indicate that the proposed system can diagnose individuals with cardiovascular disease with relatively high levels of accuracy and precision. By improving the efficiency and accuracy of heart disease diagnosis, this research may contribute to better patient outcomes and reduced healthcare costs.

Facial skin segmentation plays an important role in applications such as identification, facial expression analysis, facial animation, and skin disease analysis. Clustering is one of the most common methods for image segmentation. In this paper, a new hybrid method based on Quantum Particle Swarm Optimization and Grey Wolf Optimization is presented to optimize the performance of the K-Means clustering. By Combination of two algorithms, the exploitation performance of the QPSO algorithm is improved by the exploration capability of the GWO algorithm. To measure the similarity, four distance criteria including Euclidean, Minkowski,  Mahalanobis, and City-Block distances have been used to optimize the K-Means algorithm. The proposed method has a better performance in segmentation and convergence speed compared to other meta-heuristic algorithms such as Genetic Algorithm, GWO, PSO, QPSO, Bat Optimization, Crow Search Algorithm. The experimental results show that Minkowski distance has a better performance in calculating similarity and optimization of K-Means algorithm. Based on the obtained results, the proposed method ensures the achievement of the optimal solution and prevents the problem from falling to a local minimum.

This paper deals with the dynamic economic and emission dispatch during a day as an important challenge in engineering. On the other hand, renewable energy provides an undeniable contribution to the energy supply. Therefore, to create an efficient model, the probability wind energy models have been proposed. In principle, this problem has several limitations and to bring it to reality, practical and nonlinear constraints such as power balance, ramp rate, prohibited zone, non-smooth cost function, and production constraints have been considered. Since these functions i.e. emission, cost, and wind models are conflicting in nature, to solve this problem, a multi-objective virus colony search algorithm (VCS) based on Pareto theory has been proposed. To improve the performance of the virus colony search algorithm, the chaos theory has been employed that eliminates the weakness of the standard algorithm, ie the speed of convergence and increased number of iterations of the algorithm to achieve the optimal solution. Chaos theory refers to the nature of complex systems with unpredictable behavior. Using the stochastic properties of chaos system, Chaos theory can improve the quality of population distribution in search space and enhance algorithm convergence function. The fuzzy decision function is also used to select the best solution from the set of solutions. The proposed model and method are applied to different systems and in some cases are compared with other methods in the articles. The results show an improvement in the performance of the proposed algorithm. The results also show that the presence of renewable resources has reduced production costs and thus increased network security.

Glaucoma is the most common cause of blindness in some countries. In the meantime, the field of retinal image processing has been proposed in order to provide automatic systems for disease diagnosis. Among the methods of medical image processing, image segmentation is a process of identification and change in the display of an image. The objective of this study was to use the segmentation method and compare it with previous algorithms so as to be able to diagnose retinal optic disc more accurately.

In the present analytical study, using the image segmentation method, each pixel was assigned a label in such a way that pixels with the same label had similar characteristics. The optic disc segmentation was performed. Using MATLAB software, retinal images of patients with glaucoma were entered into the program and an ideal output was obtained.

The quantitative analysis of the obtained results showed a high accuracy (85%) for the proposed method for the segmentation of the retinal optic disc; thus, the results can be used to efficiently diagnose a person with glaucoma.

The purpose of segmenting an image is to make raw data more usable for subsequent statistical processing. It is expected that in the future, feature extraction be more accurate, and more details be available to machine vision systems to identify objects in the images.

Given that the price signal in the electricity market is highly volatile or otherwise uncertain, short-term forecasting is significantly affected. Since time-series methods cannot estimate such nonlinear models appropriately with high accuracy, we need to provide an efficient model. For this reason, in this paper, a new hybrid algorithm for day-ahead electricity price forecasting is proposed. In order to achieve this model, we first divide the forecasting problem into three main layers: preprocessor, training, and regulator. In the first layer, we use the curvelet transform to reduce possible noise in the price signal. Then, using the extended data selection model based on increasing correlation and decreasing redundancy, we eliminate the unnecessary data and reduce the volume of computation significantly. Then the regularized data is entered into the learning layer which is a developed Extreme Learning Machine (ELM) to obtain and extract the best pattern from the input data. Since adjusting the control parameters of the proposed ELM can maximize its ability to derive a nonlinear pattern from the price signal, a new developed Virus Colony Search (VCS) method based on the time-varying coefficients theory is proposed in the last layer. The proposed algorithm is a novel optimization method based on the function of viruses to destroy host cells and penetrate the best ones into a cell for replication. The proposed method is applied to existing real electricity markets and the results are compared based on prediction error rates and error-based criteria. The obtained results show the appropriate and acceptable performance of the proposed forecasting method.

The identification of factors influencing the incidence of breast cancer bears great importance. The wide range of symptoms of the disease makes the diagnosis difficult for doctors. Preventing breast cancer could be achieved via a knowledge of the factors affecting the incidence of the disease. The purpose of this paper was to identify variables related to dietary habits, cultural factors, and laboratory results that could contribute to the effective prediction of breast cancer. For this purpose, an optimal model based on genetic bee colony (GBC) algorithm was developed to increase machine learning accuracy. In this study, patient information was collected from the database of Mortaaz subspecialty hospital in Yazd. Medical records of 711 breast cancer patients were screened for 63 variables. Patients had been followed up for at least two years. Variables most affecting the incidence of breast cancer were identified using the GBC algorithm and backup vector machine. Among diet- and culture-related factors, smoking and hookah use, physical inactivity, nighttime employment, and being single and cultural factors related to breast cancer were selected. Also, based on the proposed model, factors such as comparing the results of previous and current mammograms, the duration of taking contraceptive pills, hysterectomy, hormone replacement therapy, nipple retraction and pain, type of discharge, and detecting a mass in mammograms were effective in detecting the disease. No significant relationship was found between breast cancer and factors such as using the microwave in the kitchen, or the type of rice or oil consumed. Using dietary habits and cultural factors in the prediction of breast cancer, the proposed model has the least error rate and the most accuracy compared with other models such as fuzzy and neural networks.

Awareness of cancer increases the probability of neurotic disorders and stress in the patient. Also, stress increases the risk of myocardial infarction. The present study aimed to determine the probability of a heart attack in cancer patients based on the GBC algorithm. In this study, data were collected from the database of Shahid Sadoughi subspecialty hospital in Yazd. The medical records of 1679 patients with heart attack were studied, of which 81 ones belonged to patients with cancer. In the process of selecting features by the proposed model, if cancer is identified as an effective feature, then the relationship between cancer and cardiac infarction will be meaningful. Using the proposed model, the cancer feature was selected to predict the probability of heart attack, which indicated a significant relationship between these two characteristics in patients who were vulnerable to cardiac disease. The predictive accuracy of the proposed model was 0.91 By choosing the cancer feature, the proposed model compared to other models has the least error rate and the most accuracy in predicting myocardial infarction. Naive bias method has maximum error rate and minimum accuracy. The simulation results indicate that in patients who are vulnerable to cardiac disease, after being diagnosed with cancer during the early months, heart attack is possible.

Supply of energy with minimum production cost as view of consumer's payment is the most important challenge in recent researches. In other words, power supply during a day (24h) in the least costs, while satisfy the power system constraints is main aim of this paper. Since the dynamic economic dispatch (DED) had inherent nonlinearity therefore it makes a quite complexity inherent for the mathematical methods to solve it as view of computational burden. In this regard, we models dynamic economic load dispatch during a day with available constrains such as valve point effect, power system bound, ramp-rate constraints and etc and propose a new Modified Harmony Search Algorithm (MHSA) to solve it. In the proposed algorithm employ Chaos theory and local/global operators to improve search ability of original harmony search algorithm. At last, the proposed method assesses on available standard test systems compare to other existing methods. The results of the proposed method show acceptable performance in solving of nonlinear problem such as dynamic economic dispatch (DED). Also, the obtained results of the improved harmony search algorithm from test function show acceptable improvement in local search and global parts.

Impulsive Noise is one of the degrading factors in digital image quality. In this paper, an innovative and hybrid method for noise reduction is proposed. The proposed algorithm has two stages: detection of the noise and removing of it in the frequency domain. Another innovation of the paper is introducing of a measure of quality assessment of the degraded image. The results show the improving of the quality in comparison with the state of the art related works is achieved and this method outperforms them about 2dB in PSNR measure.

This paper proposes a statistical method for content-aware image shrinking. This method divides image into equal quads by an initial uniform grid and computes an important factor for each of quads guided by importance map. The importance map is generated automatically using a novel combination of image edge density and Harel saliency measurement. The method then computes scaling factor for each of quads by using of statistical measures such as the mean and the variance of quads importance factors. To preserve the important areas as far as possible and to destroy the unimportant areas more, this method uses statistical functions to give the larger value to important quads. To prevent bending of straight horizontal lines, in the vertical direction, the algorithm equally resizes quads that are placed in the same row. Also, to prevent bending of straight vertical lines, the algorithm equally squeezes and stretches quads that are placed in the same column. Experimental results of different types of images show that our method can achieve better objective and subjective quality with preserving prominent objects.

In a DoS attack can be regarded as an attempt of attackers to prevent legal users from gaining a normal network service. The TCP connection management protocol sets a position for a classic DoS attack, namely, the SYN flood attack. In this attack some sources send a large number of TCP SYN segments, without completing the third handshake step to quickly exhaust connection resources of the under attack system. This paper models the under attack server by using the queuing theory in which attack requests are recognized based on their long service time. Then it proposes a framework in which the defense issue is formulated as an optimization problem and employs combination of the particle swarm optimization (PSO) algorithm and proposed filter for reduction degradation caused by impulsive noise to optimally solve this problem. The goal is to direct the server to an optimum defense point by dynamically setting of two TCP parameters, namely, maximum number of connections and maximum duration of a half-open connection. The simulation results show that the proposed defense strategy improves the performance of the under attack system in terms of rejection probability of connection requests and efficient consumption of buffer space.

Accurate load forecasting becomes more and more important for all market participants in competitive electricity markets، which can maximize producers’ profits and consumers’ utilities، respectively. The optimal profit is determined by applying a perfect price forecast. A load forecast with a less prediction errors، yields maximum profits for market players. The numerical electricity load forecasting is high in forecasting errors of various approaches. However، electricity load is a complex signal due to its nonlinearity، non-stationary، and time variant behavior. In spite of much research in this area، more accurate and robust price forecast methods are still required. In this paper، a new hybrid forecast technique based on feature selection technique، Artificial Neural Network (ANN) and Artificial Bee Colony (ABC) model is proposed for load forecasting. The feature selection method is an improved version of the mutual information (MI) technique. The superiority of this proposed method is examined by using the data acquired from New England market. Empirical results show that this proposed method performs better than some of the other price forecast techniques.