A prudential feature extraction technique is proposed in this study for breast tumor early detection. A small size UWB planar antenna with a gain and directivity of 6.09 dB and 8.15 dBi respectively, has also been proposed for smooth wave propagation through the breast model. A system is developed by integrating a small size UWB biomedical antenna and feature extraction technique for artificial neural network (ANN) for early tumor detection. Tumor's size detection accuracy of the system has been investigated experimentally by applying radar based microwave imaging technique. Forward scattering signals (received by the receiving antenna) are considered for four characteristic features, maximum, minimum, average and standard deviation values (Voltage/meter) for pattern recognition and tumor signature investigation. The range of malignant tumor sizes used in this study is 1 mm to 9 mm in diameter. The proposed system is able to detect tumor existence and size with ∼100% and ∼99% accuracy respectively within reasonable time delay, showing its superiority.

No abstract

No abstract

The possibility that an unauthorised agent is able to infer a users' hidden information (an attribute's value) is known as attribute inference risk. It is one of the privacy issues for Facebook users in recent times. An existing technique [1] provides privacy by suppressing users attribute values from their profile. However, suppression of an attribute sometimes is not enough to secure a users' confidential information. In this paper, we experimentally demonstrate that (after taking necessary steps on attribute values) a user's sensitive information can still be inferred through his/her friendship information. We evaluated our approach experimentally on two datasets. We propose 3LP, a new three layers protection technique, to provide privacy protection to users of on-line social networks.

No abstract