After the September 11 tragedies of 2001, scientists and law‐enforcement agencies have shown increasing concern that terrorist organizations and their “rogue” foreign government‐backers may resort to ...the use of chemical and/or biological agents against U.S. military or civilian targets. In addition to the right mix of policies, including security measures, intelligence gathering and training for medical personnel on how to recognize symptoms of biochemical warfare agents, the major success in combating terrorism lies in how best to respond to an attack using reliable analytical sensors. The public and regulatory agencies expect sensing methodologies and devices for homeland security to be very reliable. Quality data can only be generated by using analytical sensors that are validated and proven to be under strict design criteria, development and manufacturing controls. Electrochemical devices are ideally suited for obtaining the desired analytical information in a faster, simpler, and cheaper manner compared to traditional (lab‐based) assays and hence for meeting the requirements of decentralized biodefense applications. This articler presents a review of the major trends in monitoring technologies for chemical and biological warfare (CBW) agents. It focuses on research and development of sensors (particularly electrochemical ones), discusses how advances in molecular recognition might be used to design new multimission networked sensors (MULNETS) for homeland security. Decision flow‐charts for choosing particular analytical techniques for CBW agents are presented. Finally, the paths to designing sensors to meet the needs of today's measurement criteria are analyzed.
Parenchymal patterns defining the density of breast tissue are detected by advanced correlation pattern recognition in an integrated Computer-Aided Detection (CAD) and diagnosis system. Fractal ...signatures of density are modelled according to four clinical categories. A Support Vector Machine (SVM) in the primal formulation solves the multiclass problem using 'One-Versus-All' (OVA) and 'All-Versus-All' (AVA) decompositions, achieving 85% and 94% accuracy, respectively. Fully automated classification of breast density via a texture model derived from fractal dimension, dispersion, and lacunarity moves current qualitative methods forward to objective quantitative measures, amenable with the overarching vision of substantiating the role of density in epidemiological risk models of breast cancer.
Analysis of gene expression microarray datasets presents the high risk of over-fitting (spurious patterns) because of their feature-rich but case-poor nature. This paper describes our ongoing efforts ...to develop a method to combat over-fitting and determine the strongest signal in the dataset. A GA-SVM hybrid along with Gaussian noise (manual noise gain) is used to discover feature sets of minimal size that accurately classifies the cases under cross-validation. Initial results on a colorectal cancer dataset shows that the strongest signal (modest number of candidates) can be found by a binary search.
To establish radiologic imaging as a valid biomarker for assessing the response of cancer to different treatments. We study patients with metastatic colorectal carcinoma to learn whether Statistical ...Learning Theory (SLT) improves the performance of radiologists using Computer Tomography (CT) in predicting patient treatment response to therapy compared with traditional Response Evaluation Criteria in Solid Tumours (RECIST) standard. Preliminary research demonstrated that SLT algorithms can address questions and criticisms associated with both RECIST and World Health Organization (WHO) scoring methods. We add tumour heterogeneity, shape, etc., obtained from CT or MRI scans the feature vector for processing.
The need for rapid and accurate detection systems is expanding and the utilization of cross-reactive sensor arrays to detect chemical warfare agents in conjunction with novel computational techniques ...may prove to be a potential solution to this challenge. We have investigated the detection, prediction, and classification of various organophosphate (OP) nerve agent simulants using sensor arrays with a novel learning scheme known as support vector machines (SVMs). The OPs tested include parathion, malathion, dichlorvos, trichlorfon, paraoxon, and diazinon. A new data reduction software program was written in MATLAB V. 6.1 to extract steady-state and kinetic data from the sensor arrays. The program also creates training sets by mixing and randomly sorting any combination of data categories into both positive and negative cases. The resulting signals were fed into SVM software for “pairwise” and “one” vs all classification. Experimental results for this new paradigm show a significant increase in classification accuracy when compared to artificial neural networks (ANNs). Three kernels, the S2000, the polynomial, and the Gaussian radial basis function (RBF), were tested and compared to the ANN. The following measures of performance were considered in the pairwise classification: receiver operating curve (ROC) A z indices, specificities, and positive predictive values (PPVs). The ROC A z values, specifities, and PPVs increases ranged from 5% to 25%, 108% to 204%, and 13% to 54%, respectively, in all OP pairs studied when compared to the ANN baseline. Dichlorvos, trichlorfon, and paraoxon were perfectly predicted. Positive prediction for malathion was 95%.