A nonlinear multi-classification knowledge-based kernel machine

This paper presents a knowledge-based nonlinear kernel classification model for multi-category discrimination of sets or objects with prior knowledge. A kernel function is employed to find a nonlinear classifier capable of discriminating future points into an appropriate class. The prior knowledge is in the form of multiple polyhedral sets belonging to one or more categories or classes, and it is introduced as additional constraints into the formulation of the regularized nonlinear kernel least squares multi-class support vector machine model. The resulting formulation leads to a linear system of equations that can be solved using matrix methods or iterative methods. This work extends previous work (Oladunni et al. in ICCS 2006, Lecture notes in Computer Science, Part I, LNCS, vol 3991. Springer, Berlin, pp 188–195, 2006) that incorporated similar prior knowledge into a regularized linear least squares multi-class model. To evaluate the model, data and prior knowledge from the two-phase flow regimes in pipes were used to train and test the proposed formulation.     

Combination of phosphatidylinositol 3-kinases pathway inhibitor and photodynamic therapy in endothelial and tumor cells

Tumor recurrence due to incomplete eradication of tumor cells is a major problem facing current cancer therapies. To overcome this problem, it is necessary to enhance cell killing and/or prevent cell regrowth after treatment. Because phosphatidylinositol 3-kinases (PI3K) pathway plays an important role in stimulating cell survival and growth, we studied the feasibility of using a PI3K pathway inhibitor NVP-BEZ235 (BEZ235) to enhance the effectiveness of vascular-targeted photodynamic therapy (vPDT) with verteporfin. We found that BEZ235 or PDT alone significantly inhibited cell growth in both SVEC endothelial and PC-3 prostate cancer cells, although SVEC cells appeared to be more responsive than PC-3 cells. Autophagy was detected after both BEZ235 and verteporfin-PDT in both cell lines. Autophagy appeared to protect cells from PDT-induced cell death because inhibition of autophagy increased cell death. Autophagic flux assay revealed that PDT actually decreased autophagic flux especially at a high dose of verteporfin. Combination of BEZ235 and PDT caused greater inhibition of PI3K signaling pathway, leading to enhanced cell growth inhibition in both cell lines. SVEC cells exhibited a higher sensitivity towards such a combination than PC-3 cells. Our data indicated that BEZ235 in combination with PDT provides a promising approach of enhancing therapeutic response.     

Linear classification tikhonov regularization knowledge-based support vector machine for tornado forecasting

A knowledge-based linear Tihkonov regularization classification model for tornado discrimination is presented. Twenty-three attributes, based on the National Severe Storms Laboratory’s Mesoscale Detection Algorithm, are used as prior knowledge. Threshold values for these attributes are employed to discriminate the data into two classes (tornado, non-tornado). The Weather Surveillance Radar 1998 Doppler is used as a source of data streaming every 6 min. The combination of data and prior knowledge is used in the development of a least squares problem that can be solved using matrix or iterative methods. Advantages of this formulation include explicit expressions for the classification weights of the classifier and its ability to incorporate and handle prior knowledge directly to the classifiers. Comparison of the present approach to that of Fung et al. [in Proceedings neural information processing systems (NIPS 2002), Vancouver, BC, December 10–12, 2002], over a suite of forecast evaluation indices, demonstrates that the Tikhonov regularization model is superior for discriminating tornadic from non-tornadic storms.     

A regularized pairwise multi-classification knowledge-based machine and applications

This paper presents a novel knowledge-based linear classification model for multi-category discrimination of sets or objects with prior knowledge. The prior knowledge is in the form of multiple polyhedral sets belonging to one or more categories or classes and it is introduced as additional constraints into the formulation of the Tikhonov linear least squares multi-class support vector machine model. The resulting formulation leads to a least squares problem that can be solved using matrix methods or iterative methods. Investigations include the development of a linear knowledge-based classification model extended to the case of multi-categorical discrimination and expressed as a single unconstrained optimization problem. Advantages of this formulation include explicit expressions for the classification weights of the classifier(s) and its ability to incorporate and handle prior knowledge directly to the classifiers. In addition it can provide fast solutions to the optimal classification weights for multi-categorical separation without the use of specialized solver-software. To evaluate the model, data and prior knowledge from the Wisconsin breast cancer prognosis and two-phase flow regimes in pipes were used to train and test the proposed formulation.     

Low Viscosity Poly(trimethylene carbonate) for Localized Drug Delivery: Rheological Properties and in vivo Degradation

The purpose of this study is to examine the potential of low‐molecular‐weight poly(trimethylene carbonate) for localized delivery for acid‐sensitive drugs. Poly(trimethylene carbonate) of various molecular weights is prepared by ring‐opening polymerization initiated by octan‐1‐ol and co‐initiated/catalyzed by tin 2‐ethylhexanoate. The resultant polymers are amorphous with low glass transition temperatures and viscosities at 37 °C that permit their injection through an G 1.5″ needle. Their biocompatibility and the influence of the molecular weight on the rate of degradation are assessed in vivo through subcutaneous implantation in rats over 40 weeks. The polymers are well tolerated in vivo, and degrade in a fashion dependent on their initial molecular weight. For very low initial molecular weight (620 Da) and for high initial molecular weight (2 400 Da), polymer mass loss is a result of dissolution of the soluble low molecular chains from the bulk. This is contrasted by the results obtained for an intermediate initial molecular weight (1 600 Da), for which polymer mass loss is a result of both dissolution and enzymatic hydrolysis or oxidation as a result of reactive species secreted by activated macrophages at the implant surface.