Research Interests:
In this paper, a new classification method is presented which uses clustering techniques to augment the performance of K-Nearest Neighbor algorithm. This new method is called Nearest Cluster approach, NC. In this algorithm the neighbor... more
In this paper, a new classification method is presented which uses clustering techniques to augment the performance of K-Nearest Neighbor algorithm. This new method is called Nearest Cluster approach, NC. In this algorithm the neighbor samples are automatically determined using clustering techniques. After partitioning the train set, the labels of cluster centers are determined. For specifying the class label of a new test sample, the class label of the nearest cluster prototype is used. Computationally, the NC method is faster than KNN, K 2 times. Also the clustering techniques lead to find the best number of neighbors based on the nature of feature space. The proposed method is evaluated on two standard data sets, SAHeart and Monk. Experimental results show the excellent improvement both in accuracy and time complexity in comparison with the KNN method.
Research Interests:
In this paper, unsharp mask is used to boost the quality of recovered watermark in correlation based watermarking. This filter is applied before take the correlation in the middle of recovery algorithm. This filter augments the... more
In this paper, unsharp mask is used to boost the quality of recovered watermark in
correlation based watermarking. This filter is applied before take the correlation in the
middle of recovery algorithm. This filter augments the distinction between the watermark
and the host image. Thus the recovery algorithm could extract the watermark more
precisely. Efficiency of proposed filter is shown by testing it on a typical the correlation
based watermarking in spatial domain method. Several attacks are done to prove the
performance of proposed method.
correlation based watermarking. This filter is applied before take the correlation in the
middle of recovery algorithm. This filter augments the distinction between the watermark
and the host image. Thus the recovery algorithm could extract the watermark more
precisely. Efficiency of proposed filter is shown by testing it on a typical the correlation
based watermarking in spatial domain method. Several attacks are done to prove the
performance of proposed method.
Research Interests:
In this paper, the usage of multi-agent systems for the management, control and optimize transportation system performance is shown. Artificial intelligence approaches in the development of intelligent agent-based systems is effective in... more
In this paper, the usage of multi-agent systems for the management, control and optimize transportation system performance is shown. Artificial intelligence approaches in the development of intelligent agent-based systems is effective in solving complex problems in the transportation system. The successful transfer of research results to practical systems is crucial for intelligent agents and multi-agent systems. Our work reveals that the transportation system based on the intelligent agent can reduce costs, time and environmental pollution.
Research Interests:
Cloud computing is a distributed architecture that has shared resources, software, and information is provided to computers and other devices on a scalable platform and demand. Availability of the cloud services is one of the key security... more
Cloud computing is a distributed architecture that has shared resources, software, and information is provided to computers and other devices on a scalable platform and demand. Availability of the cloud services is one of the key security issues in it. Distributed Denial of Service (DDoS) is an attack that threats the availability of the cloud services. In this paper, effect of the DDoS attack on the cloud is investigated. Therefore, a model for attack based on the DDoS is designed, and then we simulate a cloud system on the experimental environment. Experiments show that the cloud system is vulnerable to this attack. In order to confronting this attack, several solutions are proposed in this paper. We suggest load balancing and honeypots beside the intrusion detection systems (IDS) is used to defend from the attack.
Research Interests:
Discrimination between watermark and host image is one of primary problems in DCT-based watermarking algorithms, especially when attack occurred on watermarked image. In this paper, a new pre-processing approach is presented to improve... more
Discrimination between watermark and host image is one of primary problems in DCT-based watermarking algorithms, especially when attack occurred on watermarked image. In this paper, a new pre-processing approach is presented to improve watermark extracting performance of DCT-based watermarking schemes. This method is based on adding noise magnifying and enhancement operations as beginning steps to watermark extraction procedure. First, the watermark information is treated as noise for the watermarked image in its spatial domain. Then, the noise is magnified before detection. Next, enhancement operations are done by applying combination of two filter; sharpening and Laplacian of Gaussian, respectively. To show effectiveness of proposed method, a typical DCT method is used and proposed pre-processing package is added to this method. Experimental results show that extraction performance of DCT-based watermarking algorithm is improved by applying our pre-processing scheme before watermark extraction procedure.
Research Interests:
In image processing Pre-processing is used for preparing or improving performance of operations. In order to improve performance of extraction algorithms in DCT based watermarking method, a new pre-filtering method is proposed in this... more
In image processing Pre-processing is used for preparing or improving performance of operations. In order to improve performance of extraction algorithms in DCT based watermarking method, a new pre-filtering method is proposed in this paper. Enhancement filters are applied to the watermarked image as Pre-filtering before running watermark extraction algorithms in DCT based method. These filters are based of mixture of two filters: Unsharp and Laplacian of Gaussian (LoG). Distinction of watermarked part and unwatermarked part is increased by these filters; thus, the watermark information could be extracted with more accuracy. To show the effectiveness of the proposed method, different types of attacks are applied on typical DCT based algorithms. Experimental results show that extracted watermark has better quality than previous method.