Search

Skin cancer is measured as one of the fatal types of cancer diseases in humans, among numerous kinds of malignancy. Current diagnostic classifications are lacking in finding an effective treatment. The effective and early stage treatment of skin disease can increase the survival rate of patients. Substantial investigative work has been developed to improve computer aided diagnosis system to detect cancer at early stage. However, early detection of skin cancer still requires better accuracy through experiment on digital skin lesion images as a multiclass classification, rather than using biopsy methods. This paper presents an intelligent framework to detect and classify four types of skin cancer. Before classification, noise removal from skin lesion is performed by gaussian filter. Textural and colour features are extracted from skin lesion to detect and classify cancer into four types. Support vector Machine is trained to classify Melanoma, Nevus, Basal and Squamous skin cancer types. Extensive experiments are performed on standard benchmark skin cancer images dataset with an improvement in accuracy of 92.41% after comparison with the well-known methods.

Nodes in a multi-hop wireless network rely on each other to maintain network connectivity. A primary design objective of these networks is to eliminate or minimize the unavailability of network at some point. However, the movement of nodes creates service disruption and delay as path failure detection and re-establishment consume considerable amount of time. Existing solutions for link classification and prediction operate on discrete values resulting in performance degradation. This problem can best be modelled using fuzzy logic. This work presents a new fuzzy logic based link status classification mechanism for the use with multipath routing protocols in multi-hop wireless networks. The new Enhanced Adhoc On-demand Multipath Distance Vector (eAOMDV) uses fuzzy logic to classify the link status as active, about-to-break or broken. On the basis of fuzzy input parameters RSSI, velocity, distance and bit error rate, the fuzzy based classification mechanism predicts in advance that a particular link, on the active path between the sender and receiver, is about-to-break and helps the reactive multipath routing protocol to start the rerouting operation, thus minimizing the service disruption time, route discovery frequency, end-to-end delay and the packet loss.