aboozar zandvakili | Shahid Bahonar University of Kerman (original) (raw)

Papers by aboozar zandvakili

Evolving systems, Jun 29, 2024

Multimedia tools and applications, Apr 22, 2024

Neural computing & applications, Jul 1, 2024

Social Network Analysis and Mining, Feb 7, 2022

Rumor is an important form of social interaction. Therefore, spreading harmful rumors can have a ... more Rumor is an important form of social interaction. Therefore, spreading harmful rumors can have a negative impact on the health of the society. People's communication in the society plays an important role in spreading rumors, and whether or not it is spread depends on the person's level of trust in the rumor. Thus, one of the most important factors in a person's trust (or distrust) of a rumor is the number of neighbors who believe the rumor and spread it (and vice versa, the number of neighbors who do not believe the rumor and react to it). In this paper, we present this case in the form of linguistic variables and the use of fuzzy logic. In this paper, we propose an epidemic model of rumor dissemination in online social networks in which in addition to existing (susceptible–infected–recovered) modes, the rumor delay mechanism (exposed) is also added a counter attack mechanism (counterattack). The proposed model is presented as: susceptible–exposed–infected–counterattack–vaccinated–recovered–susceptible considering that the network and exposed node are constructed fuzzy. Using numerical simulations, we verify the performance of model in a SFN and a real network topology (Facebook). The simulation results of the proposed model show that compared to the SIRS and SEIRS models, the emission rate is lower, and the pollution is eliminated earlier.

International Journal of Computer Mathematics, Jan 7, 2022

International Symposium on Algorithms and Computation, Jun 1, 2021

Task scheduling in cloud computing plays an essential role for service provider to enhance its qu... more Task scheduling in cloud computing plays an essential role for service provider to enhance its quality of service. Grasshopper Optimization Algorithm (GOA) is an evolutionary computation technique developed by emulating the swarming behavior of grasshoppers while searching for food. GOA is easy to implement but it cannot make full utilization of every iteration, and there is a risk of falling into the local optimal. This paper proposes a suitable approach for adjusting the comfort zone parameter based on the fuzzy signatures called signature GOA (SGOA) to balance exploration and exploitation. Then, we propose task scheduling based on SGOA by considering different objectives such as completion time, delay, and the load balancing on the machines. Finally,

A dispersed computing standard that assists the users is cloud computing. In this model, users pa... more A dispersed computing standard that assists the users is cloud computing. In this model, users pay as much as use. Cloud servers try to achieve high performance, and one of the main factors is optimal scheduling. Several metaheuristic techniques are used to solve the scheduling problem, which is an NP-hard problem. In this paper, for task scheduling in the cloud, we use Particle Swarm Optimization (PSO), Firefly Algorithm (FA), Bat Algorithm (BA), and Grasshopper Optimization Algorithm (GOA), which are swarm-based algorithms. All of these algorithms have one or more parameters that can be updated adaptively. We update these parameters using Chaos and compare their performance. The experimental results indicate that the improved GOA can optimize task scheduling problem by effective utilization of available resources.

DOAJ (DOAJ: Directory of Open Access Journals), Jul 1, 2019

This paper presents a new method for encryption of color images based on a combination of chaotic... more This paper presents a new method for encryption of color images based on a combination of chaotic systems, which make the image encryption more efficient and robust. The proposed algorithm generates three series of data ranged between 0 and 255 using a chaotic Chen system. Another Chen system is then started with different initial values, which are converted to three series of numbers from 0 to 10. The red, green, and blue values are combined with the three values for the first Chen system to encrypt pixel 1 of the image, while the values for the second Chen system are used to distort the combination order of the values for the first Chen system with the pixels of the image. The process is repeated until all pixels of the image are encrypted. The innovative aspect of this method is in combination with the two chaotic systems, which make the encryption process more complicated. The tests performed on the standard images (USC datasets) indicate the effectiveness and robustness of the proposed encryption method.

International Journal of Computer Mathematics

Drought is one of the most important natural hazards that in spite of low human casualties cause ... more Drought is one of the most important natural hazards that in spite of low human casualties cause enormous social and economic losses. Climate scientists have proposed several indexes in order to drought monitoring such as: SPI, PDSI, PN, RDI, EPI, ... that each of these criteria based on the using weather variables and different methods and calculation has designed for an specific area and has own corresponding problems, for this reason and because of the nature of the fuzzy systems that have provided the right tool for using imprecise and qualitative data in the vague and uncertain world, we have proposed the method upon which, the parameters influencing on drought (number of rainy days, rainfall, temperature, moisture, wind speed) have been considered together and the SPI method has been modeled by using the fuzzy inference system. The designed system models the desired output with acceptable accuracy.

Skin detection has different applications in computer vision and image processing. In this paper,... more Skin detection has different applications in computer vision and image processing. In this paper, relying on statistical methods, the issue of skin detection is investigated and given that the discussion is about color images, the precession in choosing the correct color space is an inevitable issue. HSV color space is used in this paper. Some images are used to build the data set and three features are extracted from the images and the fourth feature determines the skin and non-skin class. Another important issue is the use of an appropriate model for detecting skin regions in the image. Three groups of classification methods have been reviewed and compared. The three categories are based on normal distribution such as linear, nonlinear, and high order polynomials methods. Estimating the errors of categories are as follows. Group 1: 0.1594. Group 2: 0.00025 and group 3: 0.0776. As can be seen, non-linear methods have the best performance.

Cloud computing provides a shared pool of resources in a distributed environment. It supports the... more Cloud computing provides a shared pool of resources in a distributed environment. It supports the features of utility-based computing. Task scheduling is a largely studied research topic in cloud computing, which targets utilizing cloud resources for tasks by considering the objectives specified in QoS. Optimal task scheduling is an NP-hard problem, which is time-consuming to solve with precise methods and depends on many factors such as completion time, latency, cost, energy consumption, throughput, and load balance on the machines. Therefore, using meta-heuristic algorithms is a good selection. This paper uses the Pathfinder optimization Algorithm (PFA) for the task scheduling problem; but when the dimension of a problem is extremely increased, the performance of this algorithm decreases. In the last iterations, fluctuation rate (A) and vibration vector (ε) converg to 0, and finding a new solution is impossible. We used fuzzy logic to overcome this shortcoming and named the new algorithm Fuzzy-PFA (FPFA). In this paper, makespan, energy consumption, throughput, tardiness, and degree of imbalance are considered as objective functions. Our goal is to minimize the makespan, energy consumption, tardiness, and degree of imbalance while maximizing throughput. Finally, different algorithms such as Firefly Algorithm (FA), Bat Algorithm (BA), Particle Swarm Optimization (PSO), and PFA are used for comparison. The experimental results indicate that the proposed scheduling algorithm can improve up to 34.2%, 16.2%, 15.9%, and 3.5% the objective function in comparison with FA, BA, PSO, and PFA, respectively.

Task scheduling is one of the fundamental issues that attract the attention of lots of researcher... more Task scheduling is one of the fundamental issues that attract the attention of lots of researchers to enhance cloud performance and consumer satisfaction. Task scheduling is an NP (non-deterministic polynomial)hard problem that is challenging due to the several conflicting objectives of users and service providers. Therefore, meta-heuristic algorithms are the more preferred option for solving scheduling problems in a reasonable time. Although many task scheduling algorithms are proposed, existing strategies mainly focus on minimizing makespan or energy consumption while ignoring other performance factors. In this paper, we propose a new task scheduling algorithm based on the Discrete Pathfinder Algorithm (DPFA) that is inspired by the collective movement of the animal group and mimics the guidance hierarchy of swarms to find hunt. The proposed scheduler considers five objectives (i.e., makespan, energy consumption, throughput, tardiness, and resource utilization) as cost functions. Finally, different algorithms such as Firefly Algorithm (FA), Particle Swarm Optimization (PSO), Grasshopper Optimization Algorithm (GOA), and Bat Algorithm (BA), are used for comparison. The experimental results indicate that the proposed scheduling algorithm with FA, BA, PSO, and GOA improved up to 9.16%, 38.44%, 3.59%, and 3.44%, respectively. Moreover, the results show dramatic improvements in terms of resource utilization, throughput, and energy consumption.

Most structures of neural networks used for engineering applications are static networks (forward... more Most structures of neural networks used for engineering applications are static networks (forward). These networks have some neurons that respond instantly to inputs. The lack of feedback in static neural networks ensures that they are conditionally stable. Ignoring the time delays that affect the dynamics of the system is the most important limitation of these networks. Time delays are intrinsic properties of biological neurons. Along with the improvement of static neural networks, dynamic neural networks were presented with the idea of address-taking content memory in the issues related to pattern recognition In this research, a bidirectional associative memory network and Hopfield network which are dynamic neural networks were used to detect the Persian numeric characters. Both networks have been tested with noise data and had similar results in noise removal. With the parameter that has been defined in this study, bi-directional associative memory networks and Hopfield networks ...

Due to the extensive use of color images, the image segmentation is of utmost importance. Medicin... more Due to the extensive use of color images, the image segmentation is of utmost importance. Medicine, sites content diagnosis, skin detection in images, filtering unethical sites and etc. are the functions of this technique. Time of performing segmentation algorithms is very important in real applications. Using an algorithm that has done the color image segmentation with best quality but has not a high execution time is virtually impossible in many applications (time-sensitive). One method of color image segmentation is an algorithm that uses fuzzy color classification to do the segmentation process in HSL space. This algorithm is of high quality. Color image segmentation using fuzzy classification, is a classification method based on the pixels. In this paper, for segmentation of color images, a fuzzy inference system is designed based on expert knowledge that has provided satisfactory results due to the image.