In this paper, a new approximation to off-line signature verification is proposed based on two-class classifiers using an
expert decisions ensemble. Different methods to extract sets of local and a global features from the target sample are detailed.
Also a normalization by confidence voting method is used in order to decrease the final equal error rate (EER). Each set of
features is processed by a single expert, and on the other approach proposed, the decisions of the individual classifiers
are combined using weighted votes. Experimental results are given using a subcorpus of the large MCYT signature database for
random and skilled forgeries. The results show that the weighted combination outperforms the individual classifiers significantly.
The best EER obtained were 6.3 % in the case of skilled forgeries and 2.31 % in the case of random forgeries. 相似文献
Fuzzy rule-based classification systems (FRBCSs) are known due to their ability to treat with low quality data and obtain
good results in these scenarios. However, their application in problems with missing data are uncommon while in real-life
data, information is frequently incomplete in data mining, caused by the presence of missing values in attributes. Several
schemes have been studied to overcome the drawbacks produced by missing values in data mining tasks; one of the most well
known is based on preprocessing, formerly known as imputation. In this work, we focus on FRBCSs considering 14 different approaches
to missing attribute values treatment that are presented and analyzed. The analysis involves three different methods, in which
we distinguish between Mamdani and TSK models. From the obtained results, the convenience of using imputation methods for
FRBCSs with missing values is stated. The analysis suggests that each type behaves differently while the use of determined
missing values imputation methods could improve the accuracy obtained for these methods. Thus, the use of particular imputation
methods conditioned to the type of FRBCSs is required. 相似文献
Model-based testing is focused on testing techniques which rely on the use of models. The diversity of systems and software to be tested implies the need for research on a variety of models and methods for test automation. We briefly review this research area and introduce several papers selected from the 22nd International Conference on Testing Software and Systems (ICTSS). 相似文献
Vehicular sensor networks are an emerging network paradigm, suitable for various applications in vehicular environment making use of vehicles’ sensors as data sources and Inter-Vehicle Communication systems for the transmissions. We present a solution, based on vehicular sensor networks, for gathering data from a certain geographic area while satisfying with a specific delay bound. The method leverages the time interval during which the query is active in order to make the gathering process efficient, properly alternating data muling and multi-hop forwarding strategies like in delay-bounded routing protocols. Simulations show that our proposed solution succeeds in performing efficient data gathering outperforming other solutions. 相似文献
In finite labelled transition systems the problems of deciding strong bisimilarity, observation equivalence and observation congruence areP-complete under many—oneNC-reducibility. As a consequence, algorithms for automated analysis of finite state systems based on bisimulation seem to be inherently sequential in the following sense: the design of anNC algorithm to solve any of these problems will require an algorithmic breakthrough, which is exceedingly hard to achieve. 相似文献
Ca2+ signaling has been involved in controling critical cellular functions such as activation of proteases, cell death, and cell cycle control. The endoplasmatic reticulum plays a significant role in Ca2+ storage inside the cell, but mitochondria have long been recognized as a fundamental Ca2+ pool. Protozoan parasites such as Plasmodium falciparum, Toxoplasma gondii, and Trypanosoma cruzi display a Ca2+ signaling toolkit with similarities to higher eukaryotes, including the participation of mitochondria in Ca2+-dependent signaling events. This review summarizes the most recent knowledge in mitochondrial Ca2+ signaling in protozoan parasites, focusing on the mechanism involved in mitochondrial Ca2+ uptake by pathogenic protists. 相似文献
Electrocaloric (EC) refrigeration, is accepted as an auspicious method to develop eco-friendly cooling devices. Here, the investigations on the EC response and energy storage performance of heterovalent-doped Ba(Sn, Ti)O3 relaxor ferroelectrics are carried out. Doping of aliovalent Mn or Nb elements into Ti site would regulate both the EC and energy storage behaviors. An enhanced EC temperature change up to 1.31 K, and a maximal recoverable energy storage density of 0.24 J cm??3 with the efficiency as high as 87.11?%, can be observed under 70 kV cm??1 in 0.5?% acceptor-doped Ba(Sn, Ti)O3 ceramics. It is found that the local internal stress, the local charge fluctuation, and the oxygen deficiencies would benefit the electrical behaviors of this system. These results would shed light on the effect of the heterovalent substitution on the electrical properties of lead-free BaTiO3 system and provide a novel and simple route to further improve the EC response and energy storage performance.
Visceral adipose tissue (VAT) metabolic profiling harbors the potential to disentangle molecular changes underlying obesity-related dysglycemia. In this study, the VAT exometabolome of subjects with obesity and different glycemic statuses are analyzed. The subjects (n = 19) are divided into groups according to body mass index and glycemic status: subjects with obesity and euglycemia (Ob+NGT, n = 5), subjects with obesity and pre-diabetes (Ob+Pre-T2D, n = 5), subjects with obesity and type 2 diabetes under metformin treatment (Ob+T2D, n = 5) and subjects without obesity and with euglycemia (Non-Ob, n = 4), used as controls. VATs are incubated in culture media and extracellular metabolite content is determined by proton nuclear magnetic resonance (1H-NMR). Glucose consumption is not different between the groups. Pyruvate and pyroglutamate consumption are significantly lower in all groups of subjects with obesity compared to Non-Ob, and significantly lower in Ob+Pre-T2D as compared to Ob+NGT. In contrast, isoleucine consumption is significantly higher in all groups of subjects with obesity, particularly in Ob+Pre-T2D, compared to Non-Ob. Acetate production is also significantly lower in Ob+Pre-T2D compared to Non-Ob. In sum, the VAT metabolic fingerprint is associated with pre-diabetes and characterized by higher isoleucine consumption, accompanied by lower acetate production and pyruvate and pyroglutamate consumption. We propose that glucose metabolism follows different fates within the VAT, depending on the individuals’ health status. 相似文献