The use of coevolution and the artificial immune system for ensemble learning

This paper presents two new approaches for constructing an ensemble of neural networks (NN) using coevolution and the artificial immune system (AIS). These approaches are extensions of the CLONal Selection Algorithm for building ENSembles (CLONENS) algorithm. An explicit diversity promotion technique was added to CLONENS and a novel coevolutionary approach to build neural ensembles is introduced, whereby two populations representing the gates and the individual NN are coevolved. The former population is responsible for defining the ensemble size and selecting the members of the ensemble. This population is evolved using the differential evolution algorithm. The latter population supplies the best individuals for building the ensemble, which is evolved by AIS. Results show that it is possible to automatically define the ensemble size being also possible to find smaller ensembles with good generalization performance on the tested benchmark regression problems. More interestingly, the use of the diversity measure during the evolutionary process did not necessarily improve generalization. In this case, diverse ensembles may be found using only implicit diversity promotion techniques.     

Efficient duration and hierarchical modeling for human activity recognition

A challenge in building pervasive and smart spaces is to learn and recognize human activities of daily living (ADLs). In this paper, we address this problem and argue that in dealing with ADLs, it is beneficial to exploit both their typical duration patterns and inherent hierarchical structures. We exploit efficient duration modeling using the novel Coxian distribution to form the Coxian hidden semi-Markov model (CxHSMM) and apply it to the problem of learning and recognizing ADLs with complex temporal dependencies. The Coxian duration model has several advantages over existing duration parameterization using multinomial or exponential family distributions, including its denseness in the space of nonnegative distributions, low number of parameters, computational efficiency and the existence of closed-form estimation solutions. Further we combine both hierarchical and duration extensions of the hidden Markov model (HMM) to form the novel switching hidden semi-Markov model (SHSMM), and empirically compare its performance with existing models. The model can learn what an occupant normally does during the day from unsegmented training data and then perform online activity classification, segmentation and abnormality detection. Experimental results show that Coxian modeling outperforms a range of baseline models for the task of activity segmentation. We also achieve a recognition accuracy competitive to the current state-of-the-art multinomial duration model, while gaining a significant reduction in computation. Furthermore, cross-validation model selection on the number of phases K in the Coxian indicates that only a small K is required to achieve the optimal performance. Finally, our models are further tested in a more challenging setting in which the tracking is often lost and the activities considerably overlap. With a small amount of labels supplied during training in a partially supervised learning mode, our models are again able to deliver reliable performance, again with a small number of phases, making our proposed framework an attractive choice for activity modeling.     

Snap-stabilization and PIF in tree networks

The contribution of this paper is threefold. First, we present the paradigm of snap-stabilization. A snap- stabilizing protocol guarantees that, starting from an arbitrary system configuration, the protocol always behaves according to its specification. So, a snap-stabilizing protocol is a time optimal self-stabilizing protocol (because it stabilizes in 0 rounds). Second, we propose a new Propagation of Information with Feedback (PIF) cycle, called Propagation of Information with Feedback and Cleaning (). We show three different implementations of this new PIF. The first one is a basic cycle which is inherently snap-stabilizing. However, the first PIF cycle can be delayed O(h ²) rounds (where h is the height of the tree) due to some undesirable local states. The second algorithm improves the worst delay of the basic algorithm from O(h ²) to 1 round. The state requirement for the above two algorithms is 3 states per processor, except for the root and leaf processors that use only 2 states. Also, they work on oriented trees. We then propose a third snap-stabilizing PIF algorithm on un-oriented tree networks. The state requirement of the third algorithm depends on the degree of the processors, and the delay is at most h rounds. Next, we analyze the maximum waiting time before a PIF cycle can be initiated whether the PIF cycle is infinitely and sequentially repeated or launch as an isolated PIF cycle. The analysis is made for both oriented and un-oriented trees. We show or conjecture that the two best of the above algorithms produce optimal waiting time. Finally, we compute the minimal number of states the processors require to implement a single PIF cycle, and show that both algorithms for oriented trees are also (in addition to being time optimal) optimal in terms of the number of states. WARNING: The concept of snap-stabilization was first introduced in [12]. The concept evolved over the last eight years. We take this evolution in consideration in this paper, which includes the early results published in [10] and [12]. In particular, infinite repetition of computation cycles is a requirement of self-stabilizing systems. This is not required in snap-stabilization because snap-stabilization ensures that the first completed computation cycle is executed according to the specification of the problem. The correctness proofs conform to this basic property.     

Petri nets with causal time for system verification

We present a new approach to the modelling of time constrained systems. It is based on untimed high-level Petri nets using the concept of causal time. With this concept, the progression of time is modelled in the system by the occurrence of a distinguished event, tick, which serves as a reference to the rest of the system. In order to validate this approach as suitable for automated verification, a case study is provided and the results obtained using a model-checker on high-level Petri nets are compared with those obtained for timed automata using prominent tools. The comparison is encouraging and shows that the causal time approach is intuitive and modular. It also potentially allows for efficient verification.     

Flexible diamond-like carbon films on rubber: Friction and the effect of viscoelastic deformation of rubber substrates

This paper focuses on the frictional behavior of flexible diamond-like carbon (DLC) film-coated hydrogenated nitrile butadiene rubber. By making use of the substantial thermal mismatch between DLC film and rubber substrate, a dense network of cracks forms in the DLC films and contributes to flexibility. The influence of the size of DLC film microsegments on the frictional performance is studied. The effect of viscoelasticity of the rubber substrate on the frictional behavior of the DLC film-coated system is scrutinized by tribo-tests and theoretical analysis. The importance of adhesive and hysteresis contributions to friction is revealed, and an overarching model is presented.     

Spatial-temporal graph neural network for traffic forecasting: An overview and open research issues

Applied Intelligence - Traffic forecasting plays an important role of modern Intelligent Transportation Systems (ITS). With the recent rapid advancement in deep learning, graph neural networks...     

The APOA5-rs662799 Polymorphism Is a Determinant of Dyslipidemia in Vietnamese Primary School Children

Apolipoprotein A-V encoded by apolipoprotein 5 (APOA5) gene plays an important role in lipid metabolism, especially in the regulation of plasma triglycerol levels. The study aimed to evaluate the association of the APOA5-rs662799 polymorphism with dyslipidemia in Vietnamese children and the potential modification of obesity-related traits (body mass index, waist circumference, hip circumference, and waist-to-hip ratio) on this association. A case–control study was conducted with a total of 154 dyslipidemia cases and 389 controls at the age of 6 to 10 recruited at 31 primary schools in Hanoi city of Vietnam. Genotype for APOA5-rs662799 polymorphism was determined by the restriction fragment length polymorphism analysis. The association of APOA5-rs662799 polymorphism with dyslipidemia adjusting for age, sex, residence, and obesity-related traits was analyzed by binary logistic regression analysis. The results showed that in comparison with T/T and T/C carriers, the C/C carriers had a higher concentration of serum TAG in cases (p =0.049). Carriers of the C allele (C/C + T/C) had higher risk for developing dyslipidemia and hypertriglyceridemia than subjects with T/T genotype (odds ratio, OR = 1.7, p =0.0062 and OR = 1.6, p = 0.026, respectively). The association remained significant after adjusting for age, gender, residence, and obesity status (OR = 1.75, p = 0.006 and OR = 1.53, p = 0.049, respectively) or other obesity-related traits. The study suggested that the APOA5-rs662799 polymorphism may be a determinant of dyslipidemia and hypertriglyceridemia in Vietnamese children, independent of obesity-related traits.     

A Novel 1,8-Naphthyridine-2-Carboxamide Derivative Attenuates Inflammatory Responses and Cell Migration in LPS-Treated BV2 Cells via the Suppression of ROS Generation and TLR4/Myd88/NF-κB Signaling Pathway

Novel 1,8-naphthyridine-2-carboxamide derivatives with various substituents (HSR2101-HSR2113) were synthesized and evaluated for their effects on the production of pro-inflammatory mediators and cell migration in lipopolysaccharide (LPS)-treated BV2 microglial cells. Among the tested compounds, HSR2104 exhibited the most potent inhibitory effects on the LPS-stimulated production of inflammatory mediators, including nitric oxide (NO), tumor necrosis factor-α, and interleukin-6. Therefore, this compound was chosen for further investigation. We found that HSR2104 attenuated levels of inducible NO synthase and cyclooxygenase 2 in LPS-treated BV2 cells. In addition, it markedly suppressed LPS-induced cell migration as well as the generation of intracellular reactive oxygen species (ROS). Moreover, HSR2104 abated the LPS-triggered nuclear translocation of nuclear factor-κB (NF-κB) through inhibition of inhibitor kappa Bα phosphorylation. Furthermore, it reduced the expressions of Toll-like receptor 4 (TLR4) and myeloid differentiation factor 88 (MyD88) in LPS-treated BV2 cells. Similar results were observed with TAK242, a specific inhibitor of TLR4, suggesting that TLR4 is an upstream regulator of NF-κB signaling in BV2 cells. Collectively, our findings demonstrate that HSR2104 exhibits anti-inflammatory and anti-migratory activities in LPS-treated BV2 cells via the suppression of ROS and TLR4/MyD88/NF-κB signaling pathway. Based on our observations, HSR2104 may have a beneficial impact on inflammatory responses and microglial cell migration involved in the pathogenesis of various neurodegenerative disorders.