An evaluation of dimension reduction techniques for one-class classification

Dimension reduction (DR) is important in the processing of data in domains such as multimedia or bioinformatics because such data can be of very high dimension. Dimension reduction in a supervised learning context is a well posed problem in that there is a clear objective of discovering a reduced representation of the data where the classes are well separated. By contrast DR in an unsupervised context is ill posed in that the overall objective is less clear. Nevertheless successful unsupervised DR techniques such as principal component analysis (PCA) exist—PCA has the pragmatic objective of transforming the data into a reduced number of dimensions that still captures most of the variation in the data. While one-class classification falls somewhere between the supervised and unsupervised learning categories, supervised DR techniques appear not to be applicable at all for one-class classification because of the absence of a second class label in the training data. In this paper we evaluate the use of a number of up-to-date unsupervised DR techniques for one-class classification and we show that techniques based on cluster coherence and locality preservation are effective.     

Barriers and drivers for non-shoppers in B2C e-commerce: A latent class exploratory analysis

The barriers and drivers of e-shopping, as well as segmentation and behavior of e-shoppers, have been long studied in the last two decades, but the behavior of non-shoppers in business-to-consumer (B2C) e-commerce is still an open field for research which has seldom been dealt with. Our exploratory study has as its main objective the classification of non-shoppers in B2C e-commerce based on the barriers which keep deterring them from purchasing on the Internet and the drivers which might lead them to engage in e-shopping. In order to achieve this goal, data was gathered from 1499 Spanish respondents from a nationwide household panel survey. The responses were analyzed using a latent class analysis (LCA) approach and the results show four different types of non-shoppers based on the barriers for online shopping, while six different groups were identified based on the drivers to start shopping on the Internet. Implications for research and practice from the findings of the study are discussed in the final section.     

Multi-agent location system in wireless networks

In this paper we propose a flexible Multi-Agent Architecture together with a methodology for indoor location which allows us to locate any mobile station (MS) such as a Laptop, Smartphone, Tablet or a robotic system in an indoor environment using wireless technology. Our technology is complementary to the GPS location finder as it allows us to locate a mobile system in a specific room on a specific floor using the Wi-Fi networks.The idea is that any MS will have an agent known at a Fuzzy Location Software Agent (FLSA) with a minimum capacity processing at its disposal which collects the power received at different Access Points distributed around the floor and establish its location on a plan of the floor of the building. In order to do so it will have to communicate with the Fuzzy Location Manager Software Agent (FLMSA). The FLMSAs are local agents that form part of the management infrastructure of the Wi-Fi network of the Organization.The FLMSA implements a location estimation methodology divided into three phases (measurement, calibration and estimation) for locating mobile stations (MS). Our solution is a fingerprint-based positioning system that overcomes the problem of the relative effect of doors and walls on signal strength and is independent of the network device manufacturer.In the measurement phase, our system collects received signal strength indicator (RSSI) measurements from multiple access points. In the calibration phase, our system uses these measurements in a normalization process to create a radio map, a database of RSS patterns. Unlike traditional radio map-based methods, our methodology normalizes RSS measurements collected at different locations on a floor. In the third phase, we use Fuzzy Controllers to locate an MS on the plan of the floor of a building.Experimental results demonstrate the accuracy of the proposed method. From these results it is clear that the system is highly likely to be able to locate an MS in a room or adjacent room.     

Enhanced magnetic field sensitivity of spin-dependent transport in cluster-assembled metallic nanostructures

The emerging field of spintronics explores the many possibilities offered by the prospect of using the spin of the electrons for fast, nanosized electronic devices. The effect of magnetization acting on a current is the essence of giant or tunnel magnetoresistance. Although such spintronics effects already find technological applications, much of the underlying physics remains to be explored. The aim of this article is to demonstrate the importance of spin mixing in metallic nanostructures. Here we show that magnetic clusters embedded in a metallic matrix exhibit a giant magnetic response of more than 500% at low temperature, using a recently developed thermoelectric measurement. This method eliminates the dominating resistivity component of the magnetic response and thus reveals an intrinsic spin-dependent process: the conduction-electron spin precession about the exchange field as the electron crosses the clusters, giving rise to a spin-mixing mechanism with strong field dependence. This effect appears sensibly only in the smallest clusters, that is, at the level of less than 100 atoms per cluster.     

Highly Hydrophilic and Lipophilic Derivatives of Bile Salts

Lipophilicity of 15 derivatives of sodium cholate, defined by the octan-1-ol/water partition coefficient (log P), has been theoretically determined by the Virtual log P method. These derivatives bear highly hydrophobic or highly hydrophilic substituents at the C3 position of the steroid nucleus, being linked to it through an amide bond. The difference between the maximum value of log P and the minimum one is enlarged to 3.5. The partition coefficient and the critical micelle concentration (cmc) are tightly related by a double-logarithm relationship (VirtuallogP=−(1.00±0.09)log(cmcmM)+(2.79±0.09)), meaning that the Gibbs free energies for the transfer of a bile anion from water to either a micelle or to octan-1-ol differ by a constant. The equation also means that cmc can be used as a measurement of lipophilicity. The demicellization of the aggregates formed by three derivatives of sodium cholate bearing bulky hydrophobic substituents has been studied by surface tension and isothermal titration calorimetry. Aggregation numbers, enthalpies, free energies, entropies, and heat capacities, ΔC_P,demic, were obtained. ΔC_P,demic, being positive, means that the interior of the aggregates is hydrophobic.     

Rancidity development during the chilled storage of farmed Coho salmon (Oncorhynchus kisutch)

Coho salmon (Oncorhynchus kisutch) is a fatty fish species whose farming production has greatly increased in recent years. Lipid damage produced during Coho salmon chilled storage was studied for up to 24 d. Lipid hydrolysis (free fatty acids, FFA) and oxidation (conjugated dienes; peroxide value, PV; thiobarbituric acid index, TBA‐i; fluorescent compounds formation, FR; browning development) were determined and compared to lipid composition (polyene index, PI; astaxanthin, AX) changes and sensory assessment (rancid odour development) results. Most lipid damage indices developed slowly during storage; thus, values obtained for FFA, PV, TBA‐i and FR were in all cases under 1.5 g/100 g, 4.0 meq oxygen/kg lipid, 0.40 mg malondialdehyde/kg muscle and 0.40, respectively. Odour assessment showed a significant (p <0.05) rancidity development at day 10, when compared to starting fish material; then, non‐acceptable values were obtained at days 19 and 24. The PI analysis showed not many differences during the storage time, with the lowest mean value at day 19. AX analysis indicated a relatively high content in the white muscle, which was maintained till the end of the experiment. A low oxidation development is concluded for Coho salmon lipids when compared to other fatty fish species under the same chilling conditions. AX was found to contribute to the oxidation stability of Coho salmon lipids, due to its free radical scavenger properties.     

Modélisation de la cinétique de biodégradation de phénol par granules aérobies

This work describes a model of the biodegradation of phenol carried out by aerobic granules. These granules were obtained by culturing an activated sludge supernatant in a sequencing batch reactor fed with a synthetic waste water and subsequently, by acclimation to phenol (100 mg/L). The kinetics of phenol biodegradation by the aerobic granules was investigated over a wide range of initial phenol concentrations (40–1112 mg/L) in shake‐flask cultures. A Haldane‐type model was adjusted to the experimental results, which depicts successfully the phenol biodegradation profiles in the entire range of initial concentrations studied by using only one set of parameters. It is our view that the proposed model could contribute to the knowledge about the ability of aerobic granular systems to biodegrade toxic, inhibitory compounds such as phenol.