Earticle

The nodes of Wireless Sensor Networks (WSNs) are deployed in hostile environments faces the security problem of eavesdropping and capturing by an adversary. To achieve the security of this resource constraint device is a challenging task. This paper proposed a secured key management scheme for hierarchical WSNs that distributed the keys within a cluster efficiently and update the pre-deployed keys to mitigate the node compromised attack. We use one way hash function and random variable that broadcasted to update the pre-deployed keys.

Removal of shadow from Video Object Planes (VOPs) will assist in surveillance applications for comprehensive detection of activities. We have proposed a method for removal of shadows from the VOP. Also noise removal is done using existing methods from the VOP. To authenticate the surveillance VOP, digital watermarking is used. We have proposed digital watermarking using localized Biorthogonal wavelets for VOP. Super-resolved VOP is generated using multi-frame method. Edge model based super resolution method is used to get the better results. Also the effect of digital watermarking is studied for the super-resolved VOP. A number of test cases have been proposed and found out a best method for video surveillance application. Our proposed super resolution (SR) method gives better results than bilinear and bi-cubic methods.

Temporal amount of land movement is one of the important input parameter in a study of landslide detection and prediction. Automatic approach in monitoring this movement is needed to replace conventional ground surveying technique which is time consuming. An elastic image registration and change-unchanged conditional statements procedure appropriate for historical analysis of the land movement in landslide area is presented herein. Four deformation operators were used during the registration process. The similarity between two images was measured by a similarity function which takes into consideration the value of mutual information, geometric deformation and maximum overlapping area between the two images. Landslide areas were detected using the amount of pixel movement during a registration process. Two stages of four change-unchanged conditional statements had been developed to monitor landslides of future years. These conditional statements made used of the sequence of detected change images as the input parameter. It was shown that the size of pixel movement can be used to detect changes in landslide areas. The more sequences of changed images were used, the more information about the history of the area can be gathered.

Various technologies have been explored for distance learning in recent times. Such include correspondence, instructional television, instruction radio, and recently web-based systems. These methods of instructional delivery in distance learning were found to be non-effective. Also contributing to these problems is lack of enough experts in various fields of specialization in Nigeria. In this research paper, A framework of multimedia computer network system for teaching and learning to aid expert instructors in their bid to reach wide audience is proposed. This involves the cable and wireless network design, the communication protocols and the transmission media. The implementation of the framework is done using streaming technology of RealNetworks systems. A website is designed using hypertext markup language (HTML ) for easy access to the online lectures at the remote sites. A prototype is developed in FUTA community with a view to determining the effectiveness of the system.

In speaker Identification systems both parametric and nonparametric probability modeling is used. The Gaussian model is the basic parametric model that is used and this model is the basis of other sophisticated and it can be performed in a completely text independent situation. However, it sounds efficient to speaker identification application, but it results long time processing in practice. In this paper, we propose a decision function by using vector quantization (VQ) techniques to decrease the training model for GMM in order to reduce the processing time. In our proposed modeling, we take the superiority of VQ, which is simplicity computation to distinguish between male and female speaker. Then, GMM is applied into the subgroup of speaker to get the accuracy rates. Experimental result shows that our hybrid VQ/GMM method always yielded better improvements in accuracy and bring reduce in time processing. All the experiments have been done in both direct recording speech and mobile phone speech signals.