Toward designing a secure biosurveillance cloud

Biosurveillance is very complex, and it complements traditional public health surveillance to provide both early warning of infectious disease events and leads to situational awareness as well as to signaling any potential threat for using biological agents as weapons of mass destruction. Biosurveillance requires close cooperation and rapid information-sharing among many healthcare partners including primary care units and the biosurveillance hubs. Achieving improvements in this direction has become a bipartisan top priority for governments and institutions. Currently there are many national and international centers envisioned as clouds for intelligence on biological threats, however security obstacles have hindered their progress. This article investigates the requirements for a biosurveillance secure cloud. The investigation identifies the major security components needed to build a trusted environment for cloud based biosurveillance system through the integration of the public health enterprise private cloud with public clouds based on the Distributed OSGi framework along with a distributed authentication service. The trusted environment allows biosurveillance to be conducted over primary care private clouds including patient information from the electronic medical records.     

Residual U-Network for Breast Tumor Segmentation from Magnetic Resonance Images

Breast cancer positions as the most well-known threat and the main source of malignant growth-related morbidity and mortality throughout the world. It is apical of all new cancer incidences analyzed among females. Two features substantially influence the classification accuracy of malignancy and benignity in automated cancer diagnostics. These are the precision of tumor segmentation and appropriateness of extracted attributes required for the diagnosis. In this research, the authors have proposed a ResU-Net (Residual U-Network) model for breast tumor segmentation. The proposed methodology renders augmented, and precise identification of tumor regions and produces accurate breast tumor segmentation in contrast-enhanced MR images. Furthermore, the proposed framework also encompasses the residual network technique, which subsequently enhances the performance and displays the improved training process. Over and above, the performance of ResU-Net has experimentally been analyzed with conventional U-Net, FCN8, FCN32. Algorithm performance is evaluated in the form of dice coefficient and MIoU (Mean Intersection of Union), accuracy, loss, sensitivity, specificity, F1score. Experimental results show that ResU-Net achieved validation accuracy & dice coefficient value of 73.22% & 85.32% respectively on the Rider Breast MRI dataset and outperformed as compared to the other algorithms used in experimentation.     

Multi-hop in Clustering with Mobility Protocol to Save the Energy Utilization in Wireless Sensor Networks

Wireless Personal Communications - Wireless sensor networks (WSNs) gain popularity owing to their capability to access remote areas hard to be reached. Given that, the energy consumption with...     

Cell-graph coloring for cancerous tissue modelling and classification

In traditional cancer diagnosis process, pathologists manually examine biopsies to make diagnostic assessments. The assessments are largely based on visual interpretation of cell morphology and tissue distribution, lacking of quantitative measures. Therefore, they are subject to considerable inter-observer variability. To circumvent this problem, numerous studies aim at quantifying the characteristics of cancerous cells and tissues that distinguish them from their counterparts. Such quantification facilitates to design automated systems that operate on quantitative measures, and in turn, to reduce the inter-observer variability. There is a computational model available that relies solely on the topological features of cancerous cells in a tumor. Despite their complex dynamic nature, the self-organizing clusters of cancerous cells exhibit distinctive graph properties that distinguish the cancerous tissue from non-cancerous tissues; e.g. from a healthy tissue or an inflamed tissue. It is difficult to distinguish a cancerous tissue sample visually from an inflamed one. It is possible to construct a graph of the cells (cell graph) based on the location of the cells in the low-magnification image of a tissue sample surgically removed from a human patient. Assuming the cells present in a sample as the vertices of the cell graphs and the edges connecting those vertices/cells we can construct the cell graphs. There is a possibility of implementing the technique of using cell graphs to detect cancerous sample biopsies using some simple or a little bit complex computational techniques. Here possibly a new way is going to be introduced in this field, which is an application of graph coloring using the cell graphs to classify the normal, cancerous and inflamed sample biopsies. This work intends to automate the solution to the problem of identifying cancerous sample biopsies applying customized graph Coloring method solving by Genetic Algorithm on the cell graphs.     

Deciding optimal entropic thresholds to calibrate the detection mechanism for variable rate DDoS attacks in ISP domain: honeypot based approach

High bandwidth DDoS attacks consume more resources and have direct impact at ISP level in contrast to low rate DDoS attacks which lead to graceful degradation of network and are mostly undetectable. Although an array of detection schemes have been proposed, current requirement is a real time DDoS detection mechanism that adapts itself to varying network conditions to give minimum false alarms. DDoS attacks that disturb the distribution of traffic features in ISP domain are reflected by entropic variations on in stream samples. We propose honeypot detection for attack traffic having statistically similar distribution features as legitimate traffic. Next we propose to calibrate the detection mechanism for minimum false alarm rate by varying tolerance factor in real time. Simulations are carried out in ns-2 at different attack strengths. We also report our experimental results over MIT Lincoln lab dataset and its subset KDD 99 dataset. Results show that the proposed approach is comparable to previously reported approaches with an advantage of variable rate attack detection with minimum false positives and negatives.