With nearly 30,000 cases reported annually all over the island, Dengue fever has become a major health hazard in Sri Lanka over the past few years. This research attempts to develop an Artificial Neural Network (ANN) to predict Dengue outbreaks. The study investigates the effects of weather variables and previous Dengue cases on the current Dengue cases. The weather variables, Average Temperature, Average Relative Humidity, Rainy Days per Week, Total Rainfall and the Previous Cases are identified with a time lag as input parameters to the ANN. The parameters and the specific time lags are defined by a correlation analysis between each individual variable with current Dengue cases. The ANN developed as an outcome of this research is capable of predicting Dengue outbreaks in Kandy district in Sri Lanka with fairly good accuracy. General Terms Artificial Neural Networks, Predicting Dengue Outbreaks
This paper presents a robust and secure watermarking technique for digital image. To implement the technique, Discrete Wavelet Transform (DWT) is applied on cover image. Further on Low-Low (LL) sub-band of DWT, Discrete Cosine Transform (DCT) is applied which is followed by Singular Value Decomposition (SVD). To introduce the secure watermarking, watermark is secured using Arnold Transformation and embedded in the cover image. Parameters such as Peak Signal to Noise Ratio (PSNR) and Normalized Correlation (NC) are used for checking the reliability of the proposed technique. Different attacks like noise, filtering, rotation, cropping, flipping, and compression are applied on watermarked image to check the robustness of the proposed approach.
Cloud Computing became an optimal solution for business customers to maintain and promote their business needs to clients via cloud services like IaaS, SaaS, and PaaS. On-Demand and pay-per-use scale up methodologies attracted organizations for cloud adoption and migration. Due to the increased demand for cloud services from users, Efficient Resource Management in cloud computing become an important task. In order to achieve resource multiplexing in cloud computing, recent researches were introduced dynamic resource allocation through virtual machines. Existing dynamic approaches followed un-evenness procedures to allocate the available resources based on current workload of systems. Unexpected demand for huge amount of resources in future may cause allocation failure or system hang problem. In this paper we present a new systematic approach to predict the future resource demands of cloud from past usage. This approach analyzes the resource allocation logs of virtual server, SLA agreements and follows the resource prediction algorithm to estimate future needs to avoid allocation failure problem in cloud resource management. Experimental results are supporting our strategy is more scalable and reliable than existing approaches.
In late 1950s, two mathematicians discovered a network with complex topology by random graph theory. Complex networks have received great attention in past few decades. Many studies have been done on complex networks and many are still in progress. Complex Networks are the networks which can be seen in real as well as in technological systems. They have nodes and these nodes are connected by various links. They are called complex networks because of the underlying complex architecture and complex topology. In this paper, our goal is to study the complex networks and various basic terms related to complex networks like mutual behavior between real-networks and complex networks, average path length, clustering coefficient, degree distribution. Designing and analyzing the behavior and dynamics of a complex networked system are also discussed. Hence, A complex networked system can helps us in: understanding the efficiency of new security approaches for computer networks, improving the design of computer networks to make it more robust and resilience against errors and failures occurred in system, understanding how population will respond to introduction of new nodes in system, detecting subtle vulnerabilities, and also detecting catastrophic failures in power grid.
This paper describes an efficient technique of locating and extracting license plate and recognizing each segmented character. The proposed model can be subdivided into four partsDigitization of image, Edge Detection, Separation of characters and Template Matching. In this work, we propose a method which is based on morphological operations where different Structuring Elements (SE) are used to maximally eliminate non-plate region and enhance plate region. Character segmentation is done using Connected Component Analysis. Correlation based template matching technique is used for recognition of characters. This system is implemented using MATLAB7. 4. 0. The proposed system is mainly applicable to Indian License Plates.