A method for outlier detection based on cluster analysis and visual expert criteria

Outlier detection is an important problem occurring in a wide range of areas. Outliers are the outcome of fraudulent behaviour, mechanical faults, human error, or simply natural deviations. Many data mining applications perform outlier detection, often as a preliminary step in order to filter out outliers and build more representative models. In this paper, we propose an outlier detection method based on a clustering process. The aim behind the proposal outlined in this paper is to overcome the specificity of many existing outlier detection techniques that fail to take into account the inherent dispersion of domain objects. The outlier detection method is based on four criteria designed to represent how human beings (experts in each domain) visually identify outliers within a set of objects after analysing the clusters. This has an advantage over other clustering-based outlier detection techniques that are founded on a purely numerical analysis of clusters. Our proposal has been evaluated, with satisfactory results, on data (particularly time series) from two different domains: stabilometry, a branch of medicine studying balance-related functions in human beings and electroencephalography (EEG), a neurological exploration used to diagnose nervous system disorders. To validate the proposed method, we studied method outlier detection and efficiency in terms of runtime. The results of regression analyses confirm that our proposal is useful for detecting outlier data in different domains, with a false positive rate of less than 2% and a reliability greater than 99%.     

Culture-based artefacts to inform ICT design: foundations and practice

AI & SOCIETY - Cultural aspects frame our perception of the world and direct the many different ways people interact with things in it. For this reason, these aspects should be considered when...     

The effects of self-awareness on body movement indicators of the intention to deceive

A study was conducted to investigate the body movements of participants waiting to be interviewed in one of two conditions: preparing to answer questions truthfully or preparing to lie. The effects of increased self-awareness were also investigated, with half of the participants facing a mirror; the other half facing a blank wall. Analysis of covertly obtained video footage showed a significant interaction for the duration of hand/arm movements between deception level and self-awareness. Without a mirror, participants expecting to lie spent less time moving their hands than those expecting to tell the truth; the opposite was seen in the presence of a mirror. Participants expecting to lie also had higher levels of anxiety and thought that they were left waiting for less time than those expecting to tell the truth. These findings led to the identification of further research areas with the potential to support deception detection in security applications.     

Domain-specific discrete event modelling and simulation using graph transformation

Graph transformation is being increasingly used to express the semantics of domain-specific visual languages since its graphical nature makes rules intuitive. However, many application domains require an explicit handling of time to accurately represent the behaviour of a real system and to obtain useful simulation metrics to measure throughputs, utilization times and average delays. Inspired by the vast knowledge and experience accumulated by the discrete event simulation community, we propose a novel way of adding explicit time to graph transformation rules. In particular, we take the event scheduling discrete simulation world view and provide rules with the ability to schedule the occurrence of other rules in the future. Hence, our work combines standard, efficient techniques for discrete event simulation (based on the handling of a future event set) and the intuitive, visual nature of graph transformation. Moreover, we show how our formalism can be used to give semantics to other timed approaches and provide an implementation on top of the rewriting logic system Maude.     

Assimilation of traumatic experiences and physical-health outcomes: Cautions for the Pennebaker paradigm.

This study reports an application of the assimilation model, a theory of psychotherapeutic change, to an analogue study in which 43 students were asked to write for 20 minutes a day for 4 days ("Pennebaker paradigm") about a traumatic experience. Contrary to expectations based on previous research, participants who showed the greatest change in assimilation level and achieved the highest levels of assimilation during the study subsequently had more health-center visits than participants whose assimilation was less. Qualitative exploratory work suggested that there may be negative consequences of exposing traumatic experiences in the absence of supportive therapy to contain and fully integrate the experiences. A more measured approach to the benefits of brief exposition of traumatic experiences may be warranted. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Selective deposits of versican in the extracellular matrix of restenotic lesions from human peripheral arteries

Although a large percentage of the volume of human restenotic arterial lesions is occupied by extracellular matrix (ECM), the composition and organization of this ECM are not well characterized. In this study, restenotic segments taken from 30 human peripheral arteries by directional atherectomy at times ranging from 13 days to 36 months after angioplasty were analyzed for specific patterns of ECM composition and organization by light and electron microscopic histochemistry and immunohistochemistry. Histochemical analysis revealed the presence of distinct zones, enriched either in proteoglycans or fibrillar collagen. Most sections contained these regions juxtaposed to each other. The frequency of these two distinct ECMs did not change as a function of time after angioplasty. The collagen-rich zone usually contained elongated smooth muscle cells spaced close together except in regions resembling fibrous plaques. The proteoglycan-rich ECM contained both elongated and stellate-shaped smooth muscle cells randomly arranged and separated by wide distances. This region resembled the loose-connective-tissue-containing myxoid region typical of restenotic lesions. Immunohistochemical analysis of these regions revealed that the proteoglycan-containing zone stained intensely for versican, a large interstitial chondroitin sulfate proteoglycan, whereas the collagen-containing areas were mostly negative for versican but positive for type I collagen. The versican-positive regions also immunostained for biglycan, a small leucine-rich dermatan sulfate proteoglycan, and sparsely for elastin. However, both of these ECM molecules were present in the versican-negative type I collagen-positive regions of the lesions. These results suggest that the development of restenotic lesions involves localized deposits of specific ECM molecules that may play a role in the asymmetric renarrowing of this tissue after angioplasty.     

Guest editorial for the theme section on modeling language engineering

Software and Systems Modeling -     

Precursor system of liquid crystalline phase containing propolis microparticles for the treatment of periodontal disease: development and characterization

Precursor systems of liquid crystalline phase were prepared using the surfactant PPG-5-Ceteth-20, isopropyl myristate, and water; gelatin microparticles containing propolis were then added into these systems. Homogeneity of dispersion, the in-system microparticle morphology, and sedimentation behavior of each formulation were evaluated. The rheological and mechanical properties (hardness, compressibility, and adhesiveness), the work of syringing, and the propolis release profile were also evaluated. All the formulations exhibited pseudoplastic flow and thixotropy, and they displayed storage modulus, loss modulus, dynamic viscosity, and loss tangent that depended on temperature, frequency, and composition. Mechanical properties varied significantly among the formulations being affected by changes in the composition and temperature. Raising the concentration of surfactant and adding propolis microparticles significantly decreased the work of syringing. The drug release was non-Fickian (anomalous) and there was no significant difference between the tested systems in the times required for 10%, 30%, and 50% release of the initial drug loading.     

A survey of ellagitannin content in raspberry and blackberry cultivars grown in Trentino (Italy)

This study describes the first application of a new procedure for acid hydrolysis of Rubus ellagitannins in methanol, which allows quantification of all the major reaction products (ellagic acid, methyl-sanguisorboate, methyl gallate and an unknown ellagic acid derivative) and estimation of the mean degree of polymerization (mDP) of Rubus ellagitannins. The ellagitannins of 21 raspberry and 15 blackberry cultivars produced in Trentino, Italy during 2005 were extracted and characterised. The total content of ellagitannins was shown to vary by a factor of 2 among raspberry cultivars and by a factor of 4 among blackberry cultivars.     

Fractional channel reservation in mobile communication systems

A fractional channel reservation scheme is proposed. In conventional channel reservation schemes, the number of channels reserved for handoff calls has always been an integer. The proposed fractional channel reservation algorithm can be used to finely control the communication service quality. By varying the number of reserved channels for handoff calls by fractions of one