BioTuCSoN: biochemical extension of TuCSoN to support self-organising coordination

Starting from pervasive computing paradigm, we want to face the new system's requirements, concerning, mainly, self-organisation, situatedness and adaptivity, through the definition and execution of nature-inspired patterns. They are extracted by the study of dynamics in biological systems and we consider for their implementation the biochemical tuple spaces model. In particular, the aim of the thesis is to design and realize a first biochemical extension of TuCSoN (technology based on tuple spaces model) and, then, to verify its capabilities by means of a proper case study, that deals with local self-organisation and competition of services in an open and highly-dynamic environment.

Nootropia : a user profiling model based on a self-organising term network

Artificial Immune Systems are well suited to the problem of using a profile representation of an individual’s or a group’s interests to evaluate documents. Nootropia is a user profiling model that exhibits similarities to models of the immune system that have been developed in the context of autopoietic theory. It uses a self-organising term network that can represent a user’s multiple interests and can adapt to both short-term variations and substantial changes in them. This allows Nootropia to drift, constantly following changes in the user’s multiple interests, and, thus, to become structurally coupled to the user.

Self-organising zooms for decentralised redundancy management in visual sensor networks

When visual sensor networks are composed of cameras which can adjust the zoom factor of their own lens, one must determine the optimal zoom levels for the cameras, for a given task. This gives rise to an important trade-off between the overlap of the different cameras’ fields of view, providing redundancy, and image quality. In an object tracking task, having multiple cameras observe the same area allows for quicker recovery, when a camera fails. In contrast having narrow zooms allow for a higher pixel count on regions of interest, leading to increased tracking confidence. In this paper we propose an approach for the self-organisation of redundancy in a distributed visual sensor network, based on decentralised multi-objective online learning using only local information to approximate the global state. We explore the impact of different zoom levels on these trade-offs, when tasking omnidirectional cameras, having perfect 360-degree view, with keeping track of a varying number of moving objects. We further show how employing decentralised reinforcement learning enables zoom configurations to be achieved dynamically at runtime according to an operator’s preference for maximising either the proportion of objects tracked, confidence associated with tracking, or redundancy in expectation of camera failure. We show that explicitly taking account of the level of overlap, even based only on local knowledge, improves resilience when cameras fail. Our results illustrate the trade-off between maintaining high confidence and object coverage, and maintaining redundancy, in anticipation of future failure. Our approach provides a fully tunable decentralised method for the self-organisation of redundancy in a changing environment, according to an operator’s preferences.

Multimodal semantic-associative collateral labelling and indexing of still images

A novel framework for multimodal semantic-associative collateral image labelling, aiming at associating image regions with textual keywords, is described. Both the primary image and collateral textual modalities are exploited in a cooperative and complementary fashion. The collateral content and context based knowledge is used to bias the mapping from the low-level region-based visual primitives to the high-level visual concepts defined in a visual vocabulary. We introduce the notion of collateral context, which is represented as a co-occurrence matrix, of the visual keywords, A collaborative mapping scheme is devised using statistical methods like Gaussian distribution or Euclidean distance together with collateral content and context-driven inference mechanism. Finally, we use Self Organising Maps to examine the classification and retrieval effectiveness of the proposed high-level image feature vector model which is constructed based on the image labelling results.

Bayesian classification of catchments using spatial data: a first step to improved modelling of catchment effects on stream ecological condition

A major challenge facing freshwater ecologists and managers is the development of models that link stream ecological condition to catchment scale effects, such as land use. Previous attempts to make such models have followed two general approaches. The bottom-up approach employs mechanistic models, which can quickly become too complex to be useful. The top-down approach employs empirical models derived from large data sets, and has often suffered from large amounts of unexplained variation in stream condition.

We believe that the lack of success of both modelling approaches may be at least partly explained by scientists considering too wide a breadth of catchment type. Thus, we believe that by stratifying large sets of catchments into groups of similar types prior to modelling, both types of models may be improved. This paper describes preliminary work using a Bayesian classification software package, ‘Autoclass’ (Cheeseman and Stutz 1996) to create classes of catchments within the Murray Darling Basin based on physiographic data.

Autoclass uses a model-based classification method that employs finite mixture modelling and trades off model fit versus complexity, leading to a parsimonious solution. The software provides information on the posterior probability that the classification is ‘correct’ and also probabilities for alternative classifications. The importance of each attribute in defining the individual classes is calculated and presented, assisting description of the classes. Each case is ‘assigned’ to a class based on membership probability, but the probability of membership of other classes is also provided. This feature deals very well with cases that do not fit neatly into a larger class. Lastly, Autoclass requires the user to specify the measurement error of continuous variables.

Catchments were derived from the Australian digital elevation model. Physiographic data werederived from national spatial data sets. There was very little information on measurement errors for the spatial data, and so a conservative error of 5% of data range was adopted for all continuous attributes. The incorporation of uncertainty into spatial data sets remains a research challenge.

The results of the classification were very encouraging. The software found nine classes of catchments in the Murray Darling Basin. The classes grouped together geographically, and followed altitude and latitude gradients, despite the fact that these variables were not included in the classification. Descriptions of the classes reveal very different physiographic environments, ranging from dry and flat catchments (i.e. lowlands), through to wet and hilly catchments (i.e. mountainous areas). Rainfall and slope were two important discriminators between classes. These two attributes, in particular, will affect the ways in which the stream interacts with the catchment, and can thus be expected to modify the effects of land use change on ecological condition. Thus, realistic models of the effects of land use change on streams would differ between the different types of catchments, and sound management practices will differ.

A small number of catchments were assigned to their primary class with relatively low probability. These catchments lie on the boundaries of groups of catchments, with the second most likely class being an adjacent group. The locations of these ‘uncertain’ catchments show that the Bayesian classification dealt well with cases that do not fit neatly into larger classes.

Although the results are intuitive, we cannot yet assess whether the classifications described in this paper would assist the modelling of catchment scale effects on stream ecological condition. It is most likely that catchment classification and modelling will be an iterative process, where the needs of the model are used to guide classification, and the results of classifications used to suggest further refinements to models.

Representation of 2D objects with a topology preserving network

Comunicación presentada en el 2nd International Workshop on Pattern Recognition in Information Systems, Alicante, April, 2002.

Spatial and Temporal Variability of Dissolved Organic Matter Quantity and Composition in an Oilgotrophic Subtropical Coastal Wetland

Dissolved organic matter (DOM) is an essential component of the carbon cycle and a critical driver in controlling variety of biogeochemical and ecological processes in wetlands. The quality of this DOM as it relates to composition and reactivity is directly related to its sources and may vary on temporal and spatial scales. However, large scale, long-term studies of DOM dynamics in wetlands are still scarce in the literature. Here we present a multi-year DOM characterization study for monthly surface water samples collected at 14 sampling stations along two transects within the greater Everglades, a subtropical, oligotrophic, coastal freshwater wetland-mangrove-estuarine ecosystem. In an attempt to assess quantitative and qualitative variations of DOM on both spatial and temporal scales, we determined dissolved organic carbon (DOC) values and DOM optical properties, respectively. DOM quality was assessed using, excitation emission matrix (EEM) fluorescence coupled with parallel factor analysis (PARAFAC). Variations of the PARAFAC components abundance and composition were clearly observed on spatial and seasonal scales. Dry versus wet season DOC concentrations were affected by dry-down and re-wetting processes in the freshwater marshes, while DOM compositional features were controlled by soil and higher plant versus periphyton sources respectively. Peat-soil based freshwater marsh sites could be clearly differentiated from marl-soil based sites based on EEM–PARAFAC data. Freshwater marsh DOM was enriched in higher plant and soil-derived humic-like compounds, compared to estuarine sites which were more controlled by algae- and microbial-derived inputs. DOM from fringe mangrove sites could be differentiated between tidally influenced sites and sites exposed to long inundation periods. As such coastal estuarine sites were significantly controlled by hydrology, while DOM dynamics in Florida Bay were seasonally driven by both primary productivity and hydrology. This study exemplifies the application of long term optical properties monitoring as an effective technique to investigate DOM dynamics in aquatic ecosystems. The work presented here also serves as a pre-restoration condition dataset for DOM in the context of the Comprehensive Everglades Restoration Plan (CERP).

Fast 2D/3D object representation with growing neural gas

This work presents the design of a real-time system to model visual objects with the use of self-organising networks. The architecture of the system addresses multiple computer vision tasks such as image segmentation, optimal parameter estimation and object representation. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. We present experimental results for hands and faces, and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product. The proposed method is easily extensible to 3D objects, as it offers similar features for efficient mesh reconstruction.

Profiling of carotenoids and antioxidant capacity of microalgae from subtropical coastal and brackish waters

Carotenoids are associated with various health benefits, such as prevention of age-related macular degeneration, cataract, certain cancers, rheumatoid arthritis, muscular dystrophy and cardiovascular problems. As microalgae contain considerable amounts of carotenoids, there is a need to find species with high carotenoid content. Out of hundreds of Australian isolates, twelve microalgal species were screened for carotenoid profiles, carotenoid productivity, and in vitro antioxidant capacity (total phenolic content (TPC) and ORAC). The top four carotenoid producers at 4.68-6.88 mg/g dry weight (DW) were Dunaliella salina, Tetraselmis suecica, Isochrysis galbana, and Pavlova salina. TPC was low, with D. salina possessing the highest TPC (1.54 mg Gallic Acid Equivalents/g DW) and ORAC (577 μmol Trolox Equivalents/g DW). Results indicate that T. suecica, D. salina, P. salina and I. galbana could be further developed for commercial carotenoid production.

Benthic responses to organic matter variation in a subtropical coastal area off SE Brazil

Organic matter quality, expressed as the proportion of chlorophyll a (Chl a) to degraded organic material (i.e. phaeopigments), is known to influence the structure of benthic associations and plays an important role in the functioning of the ecosystem. This study investigates the vertical distribution of microbial biomass, meiofauna and macrofauna with respect to organic matter variation in Ubatuba, Brazil, a southeastern, subtropical coastal area. On three occasions, samples were collected in exposed and sheltered stations, at high and low hydrodynamic conditions. We hypothesize that benthic assemblages will have high meio- and macrofaunal densities and high microbial biomass at the sediment surface at the sheltered site, and lower and vertically homogeneous microbial biomass and densities of meio- and macrofauna are expected at the exposed site. The accumulation of fresh organic matter at the sediment surface was observed at both stations over the three sampling dates, which contributed to the higher densities of meiofauna in the first layers of the sediment column. Macrofauna followed the same trend only at the exposed station, but changes in the number of species, biodiversity and feeding groups were registered for both stations. Microbial biomass increased at the sheltered station over the three sampling dates, whereas at the exposed station, microbial biomass was nearly constant. Physical exposure did not influence organic matter loading at the sites and therefore did not affect overall structure of benthic assemblages, which negates our original hypothesis. Most of the benthic system components reacted to organic matter quality and quantity, but relationships between different-sized organisms (i.e. competition and/or predation) may explain the unchanged microbial profiles at the exposed site and homogeneous vertical distribution of macrofauna at the sheltered site. In conclusion, the high quality of organic matter was a crucial factor in sustaining and regulating the benthic system, but coupled results showed that interactions between micro-, meio- and macrofauna can be highly complex.

Estuarine and oceanic influences on copepod abundance and production of a subtropical coastal area

We investigated the influence of nutrient-rich oceanic waters in comparison to the estuarine outflow from Santos Bay (SE Brazil) on copepod abundance and production on the adjacent inner shelf. Zooplankton samples were collected with a Multinet in spring 2005 and in summer 2006. Copepod biomass was derived from length-weight regressions, and growth rates were estimated from empirical models. Altogether, 58 copepod taxa were identified. The highest abundances were due to small-sized organisms including nauplii, oncaeids and copepodids of paracalanids and clausocalanids. Biomass and secondary production mirrored copepod abundance, with Temora copepodids accompanying the above-mentioned taxa as major contributors. The contribution of naupliar biomass and production was low (2.2 and 3.8% of the total, respectively). The influence of the Santos Bay outflow was observed only in spring, when Coastal Water (CW) dominated at the study site; whereas in summer the inner shelf was occupied by CW in the surface layer and the oceanic South Atlantic Central Water (SACW) in the bottom layer. The SACW intrusion had more of an influence for the increase in copepod production than the Santos Bay plume. The distribution and dynamics of the oceanic water masses seemed to be the most important influence on copepod diversity and production at this subtropical site.