000			02676nam a2200193Ia 4500
003			NULRC
005			20250730145912.0
008			250730s9999 xx 000 0 und d
022			_a1908-1995
245		0	_aPhilippine Computing Journal.
260			_aPhilippines : _bComputing Society of the Philippines, _c2017
300			_a29 pages : _billustrations ; _c28 cm.
490			_vPhilippine Computing Journal, Vol. 12, No.2, August 2017
504			_aIncludes index and bibliographical references.
505			_aDiscovering Policies using Activity Models of Self Regulated Learners -- Optimal Allocation of Investment to Maximize an Insurer's Prospect Value Under Risk with Exponential Claims -- Split Bregman Iterations on Regularized L1 Total Variation Models.
520			_a[Article Title: Discovering Policies using Activity Models of SelfRegulated Learners / Jordan Aiko Deja and Rafael Cabredo, p.1-10] Abstract: Self-Initiated Learning Scenarios are environments that enable students to learn on their own without the supervision of a teacher .Self-regulated learners are students who can greatly benefit from these environments. ;[Article Title: Optimal Allocation of Investment to Maximize an Insurer's Prospect Value Under Risk with Exponential Claims / Adrian R. Llamado and Jonathan B. Mamplata, p.11-19] Abstract: This study calculates the optimal allocation of theinsurer's portfolio that maximizes the prospect theoryvalue of its gain or loss. The gain or loss is relativeto the insurer's current surplus. The surplus process follows a model formulated by Liu and Yang. Theprospect theory minimizing strategies derived in this study are compared to the ruin probability minimizingstrategy of Liu and Yang. Effects of prospect theory parameters on the investment strategy are analyzed.A simulation of the surplus process showed that using smooth normalized prospect theory (SNPT) without probability weighting is the best strategy when initialsurplus is zero, while using complete SNPT (i.e. probability weighting is included) yields the best results when the initial surplus is large. The strategies are comparedusing finite time ruin probabilities. ;[Article Title: Split Bregman Iterations on Regularized L1 Total Variation Models / Marrick C. Neri, p.20-29] Abstract: In this paper, regularized discrete versions of theL1to-tal variation based image denoising model are solved using split Bregman iterations. The methods use inexact solutions which are effective in restoring images corrupted with impulse noise.
650			_aINFORMATION TECHNOLOGY
942			_2lcc _cSER
999			_c26020 _d26020