Parallel Computational Intelligence-Based Multi-Camera Surveillance System

In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units). It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mobile agents in the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency. Offering relevant information to higher level systems, monitoring and making decisions in real time, it must accomplish a set of requirements, such as: time constraints, high availability, robustness, high processing speed and re-configurability. We have built a system able to represent and analyze the motion in video acquired by a multi-camera network and to process multi-source data in parallel on a multi-GPU architecture.

Impacts on particles and ozone by transport processes recorded at urban and high-altitude monitoring stations

In order to evaluate the influence of particle transport episodes on particle number concentration temporal trends at both urban and high-altitude (Aitana peak-1558 m a.s.l.) stations, a simultaneous sampling campaign from October 2011 to September 2012 was performed. The monitoring stations are located in southeastern Spain, close to the Mediterranean coast. The annual average value of particle concentration obtained in the larger accumulation mode (size range 0.25–1 μm) at the mountain site, 55.0 ± 3.0 cm− 3, was practically half that of the value obtained at the urban station (112.0 ± 4.0 cm− 3). The largest difference between both stations was recorded during December 2011 and January 2012, when particles at the mountain station registered the lowest values. It was observed that during urban stagnant episodes, particle transport from urban sites to the mountain station could take place under specific atmospheric conditions. During these transports, the major particle transfer is produced in the 0.5–2 μm size range. The minimum difference between stations was recorded in summer, particularly in July 2012, which is most likely due to several particle transport events that affected only the mountain station. The particle concentration in the coarse mode was very similar at both monitoring sites, with the biggest difference being recorded during the summer months, 0.4 ± 0.1 cm− 3 at the urban site and 0.9 ± 0.1 cm− 3 at the Aitana peak in August 2012. Saharan dust outbreaks were the main factor responsible for these values during summer time. The regional station was affected more by these outbreaks, recording values of > 4.0 cm− 3, than the urban site. This long-range particle transport from the Sahara desert also had an effect upon O3 levels measured at the mountain station. During periods affected by Saharan dust outbreaks, ozone levels underwent a significant decrease (3–17%) with respect to its mean value.

Multi-objective optimization of environmentally conscious chemical supply chains under demand uncertainty

In this work, we analyze the effect of demand uncertainty on the multi-objective optimization of chemical supply chains (SC) considering simultaneously their economic and environmental performance. To this end, we present a stochastic multi-scenario mixed-integer linear program (MILP) with the unique feature of incorporating explicitly the demand uncertainty using scenarios with given probability of occurrence. The environmental performance is quantified following life cycle assessment (LCA) principles, which are represented in the model formulation through standard algebraic equations. The capabilities of our approach are illustrated through a case study. We show that the stochastic solution improves the economic performance of the SC in comparison with the deterministic one at any level of the environmental impact.

Tuning compilations by multi-objective optimization: Application to Apache web server

Modern compilers present a great and ever increasing number of options which can modify the features and behavior of a compiled program. Many of these options are often wasted due to the required comprehensive knowledge about both the underlying architecture and the internal processes of the compiler. In this context, it is usual, not having a single design goal but a more complex set of objectives. In addition, the dependencies between different goals are difficult to be a priori inferred. This paper proposes a strategy for tuning the compilation of any given application. This is accomplished by using an automatic variation of the compilation options by means of multi-objective optimization and evolutionary computation commanded by the NSGA-II algorithm. This allows finding compilation options that simultaneously optimize different objectives. The advantages of our proposal are illustrated by means of a case study based on the well-known Apache web server. Our strategy has demonstrated an ability to find improvements up to 7.5% and up to 27% in context switches and L2 cache misses, respectively, and also discovers the most important bottlenecks involved in the application performance.

Robust solutions to multi-objective linear programs with uncertain data

In this paper we examine multi-objective linear programming problems in the face of data uncertainty both in the objective function and the constraints. First, we derive a formula for the radius of robust feasibility guaranteeing constraint feasibility for all possible scenarios within a specified uncertainty set under affine data parametrization. We then present numerically tractable optimality conditions for minmax robust weakly efficient solutions, i.e., the weakly efficient solutions of the robust counterpart. We also consider highly robust weakly efficient solutions, i.e., robust feasible solutions which are weakly efficient for any possible instance of the objective matrix within a specified uncertainty set, providing lower bounds for the radius of highly robust efficiency guaranteeing the existence of this type of solutions under affine and rank-1 objective data uncertainty. Finally, we provide numerically tractable optimality conditions for highly robust weakly efficient solutions.

Saproxylic Beetle Assemblage Selection as Determining Factor of Species Distributional Patterns: Implications for Conservation

The knowledge of the distributional patterns of saproxylic beetles is essential for conservation biology due to the relevance of this fauna in the maintenance of ecological processes and the endangerment of species. The complex community of saproxylic beetles is shaped by different assemblages that are composed of species linked by the microhabitats they use. We evaluate how different the species distribution patterns that are obtained can be, depending on the analyzed assemblage and to what extent these can affect conservation decisions. Beetles were sampled using hollow emergence and window traps in three protected areas of the Iberian Peninsula. Species richness, composition, and diversity turnover were analyzed for each sampling method and showed high variation depending on the analyzed assemblage. Beta diversity was clearly higher among forests for the assemblage captured using window traps. This method collects flying insects from different tree microhabitats and its captures are influenced by the forest structuring. Within forests, the assemblages captured by hollow emergence traps, which collect the fauna linked to tree hollows, showed the largest turnover of species, as they are influenced by the characteristics of each cavity. Moreover, the selection of the forest showing the highest species richness strongly depended on the studied assemblage. This study demonstrates that differences in the studied assemblages (group of species co-occurring in the same habitat) can also lead to significant differences in the identified patterns of species distribution and diversity turnover. This fact will be necessary to take into consideration when making decisions about conservation and management.

Seasonal differences in migration patterns of a soaring bird in relation to environmental conditions: a multi-scale approach

Many studies suggest that migratory birds are expected to travel more quickly during spring, when they are en route to the breeding grounds, in order to ensure a high-quality territory. Using data recorded by means of Global Positioning System satellite tags, we analysed at three temporal scales (hourly, daily and overall journey) seasonal differences in migratory performance of the booted eagle (Aquila pennata), a soaring raptor migrating between Europe and tropical Africa, taking into account environmental conditions such as wind, thermal uplift and day length. Unexpectedly, booted eagles showed higher travel rates (hourly speed, daily distance, overall migration speed and overall straightness) during autumn, even controlling for abiotic factors, probably thanks to higher hourly speeds, more straight routes and less non-travelling days during autumn. Tailwinds were the main environmental factor affecting daily distance. During spring, booted eagles migrated more quickly when flying over the Sahara desert. Our results raise new questions about which ecological and behavioural reasons promote such unexpected faster speeds in autumn and not during spring and how events occurring in very different regions can affect migratory performance, interacting with landscape characteristics, weather conditions and flight behaviour.