J. Gabriel Aviña-Cervantes

New prioritized value iteration for Markov decision processes

The problem of solving large Markov decision processes accurately and quickly is challenging. Since the computational effort incurred is considerable, current research focuses on finding superior acceleration techniques. For instance, the convergence properties of current solution methods depend, to a great extent, on the order of backup operations. On one hand, algorithms such as topological sorting are able to find good orderings but their overhead is usually high. On the other hand, shortest path methods, such as Dijkstra’s algorithm which is based on priority queues, have been applied successfully to the solution of deterministic shortest-path Markov decision processes. Here, we propose an improved value iteration algorithm based on Dijkstra’s algorithm for solving shortest path Markov decision processes. The experimental results on a stochastic shortest-path problem show the feasibility of our approach.

Applying balancing techniques in traffic sign recognition

Traffic Sign Recognition systems aim to determine the meaning of traffic signs in highways for real-world applications such astraffic sign inventory or driver assistance systems. Traffic sign datasets are inherently imbalanced, i.e. some traffic signs appearmore frequently than others. One serious consequence of this imbalance is the low recognition rates of minority classes (classeswith fewer training cases). In this paper, we propose a new method for improving traffic sign recognition of minority classes, byapplying balancing algorithms. As a result, our proposed method improves minority class recognition rates up to 28% comparedto traditional methods.

Design of Microelectronic Cooling Systems Using a Thermodynamic Optimization Strategy Based on Cuckoo Search

This paper proposes a conceptual design strategy for an optimal cooling system, typically used in several microelectronic devices. The methodology was implemented using the entropy generation minimization (EGM) criterion, powered by the cuckoo search (CS) algorithm. EGM-CS methodology was addressed to design rectangular microchannel heat sinks, utilizing high thermal conductive graphite as build material and a water-based colloid as coolant. This strategy was implemented under different hydrodynamic conditions, where it showed strong capability to achieve optimal designs with flowing nanofluids in either laminar or turbulent regimes. In addition, two types of nanoparticles were considered, i.e., Al and TiO2, with several values of volume fraction, as a passive mechanism for enhancing overall system performance. It was corroborated that all considered flowing colloids in laminar regime improve the thermal efficiency of the system. Moreover, an additional enhancement of this performance was observed with smaller nanoparticle concentrations (e.g., 0.01 wt/wt%), which also reduces the side effects due to nanoclustering. Furthermore, fluids with titanium dioxide nanoparticles showed slightly better thermal performance enhancement compared to aluminum particles.

Design of an Optimal Heat Sink for Microelectronic Devices Using Entropy Generation Minimization

The present article describes the design of an optimum rectangular microchannel heat sink typically used in microelectronics heat transfer management. We use the entropy generation minimization criterion to model the heat transfer process, and the spiral algorithm to solve it. For the scenarios we considered, optimum heat sinks using environmentally friendly ammonia (azane) performed about 17% better than those using air. Moreover, we observed that the thermal resistance related to the working fluid represents about 52 ± 16% of the total equivalent thermal resistance, whilst the thermal resistance related to convection phenomena only represents about 12 ± 6%.

Shadows attenuation for robust object recognition

Shadows are useful for synthetic images in order to increase extrinsically reality in image generation. However, in natural images, object recognition and segmentation are often negatively affected by cast shadows. Since shadows are a physical phenomena observed in most natural scenes, we propose a fast and reliable procedure to detect and attenuate shadows effects based on color/brightness density. Detected shadows are attenuated by modifying locally brightness and color that have the same color/brightness density. Some color artifacts (false colors on shadows) produced by the acquisition devices have been detected and discussed, and it has been noticed that they may affect some of the classical shadow removal methods. Finally, some experimental results of the proposed shadow attenuation method in real images are presented and evaluated.