Search

Background: The active travel concept has gained recognition as an effective method to enhance physical activity in children's everyday mobility. Yet, there is a notable gap of quantitative evidence on its direct impacts, especially regarding physiological outcomes that can concretely demonstrate its influences on physical intensity and overall health of children. Methods: This study investigates the effects of active travel on children, focusing on trip-level physiological responses, specifically heart rate. Through a mixed survey design, we obtained a repeated-measures dataset from a cohort of 73 children (average age 13) across three Austrian secondary schools, each observed for 7 days. By applying mixed effects modelling approach, both fixed and random effects to children's heart rates were explored. Results: According to results from developed mixed linear models (maximum R2 = 0.22), it revealed a significant positive association between active travel mode(s) engagement and heightened physiological responses (Low, Medium and High active level of trip compare to None: β = 1.81, 5.01 and 8.34, t-value = 4.70, 10.29 and 21.34), indicating that increased usage of active travel modes led to elevated heart rate values. Additionally, subjective perceptions also played an important role in influencing children's physiological responses. Feelings of exhausted, anxiety, and stress contributing to a higher heart rate (β = 14.79, 16.69 and 1.99, t-value = 20.42, 5.67 and 3.0), while unhappiness was associated with a lower heart rate (β = -5.96, t-value = -14.62). Effects of social interactions were also found during the trip. The presence of adults was associated with a calming effect (β = -1.92, t-value = -5.72), whereas solo travel resulted in lower heart rate compared to travel with peers (β = -1.95, t-value = -6.59). Conclusion: Our article innovatively employs mixed survey methods and heart rate data to quantitatively demonstrate the positive association between engagement in active travel modes and heightened physiological responses in children, elucidating the intricate interplay of subjective perceptions and social interactions during trips, thus offering valuable insights into the health implications of active travel at a trip level. Future research will keep on leveraging survey and experimental methods. [ABSTRACT FROM AUTHOR]

Inconsistent lighting phenomena in digital images, such as underexposure and overexposure, pose challenges in computer vision. Many studies have developed to address these issues. However, most of these techniques cannot remedy both exposure problems simultaneously. Meanwhile, existing methods that claim to be capable of handling these cases have not yielded optimal results, especially for images with blur and noise distortions. Therefore, this study proposes a system to improve underexposed and overexposed photos, consisting of two different residual attention convolution networks with the CIELab color space as the input. The first model working on the L-channel (luminance) is responsible for recovering degraded image illumination by using residual memory block networks with self-attention layers. The next model based on dense residual attention networks aims to restore degraded image colors using ab-channels (chromatic). A properly exposed image is produced by fusing the output of these models and converting them to RGB color space. Experiments on degraded synthetic images from two public datasets and one real-life exposure dataset demonstrate that the proposed system outperforms the state-of-the-art algorithms in optimal illumination and color correction outcomes for underexposed and overexposed images. [ABSTRACT FROM AUTHOR]

The uncertainty due to road fluctuations and vision system dynamics represents a big challenge to adjusting the steering angle of autonomous vehicles (AVs). Furthermore, AVs require fast action to follow the target lane to overcome lateral deviation with minor errors. In this regard, this paper introduces a fast model predictive controller formulated based on the discrete-time Laguerre function (DTLF) to overcome the high computational burden of the traditional MPC. To improve the hybrid DTLF-MPC performance, a modern and effective dandelion optimizer (DO) strategy is used in this work, which resulted in obtaining the optimal DTLF-MPC parameters and achieving satisfactory results. Furthermore, the proposed hybrid DTLF-MPC is designed based on different algorithms in the literature to evaluate the performance of the DO. Several scenarios are discussed in this paper to confirm the effectiveness and efficiency of the proposed control strategy system against the vision system uncertainty and road fluctuations. The results emphasize that the proposed DTLF-MPC based on the DO can achieve the best damping performance for the lateral deviations with less overshoot; around 0.4533, and a settling time of around 0.01979 s compared with other algorithms. [ABSTRACT FROM AUTHOR]

The issue of adaptive fuzzy prescribed performance tracking control is considered in this article for strict-feedback stochastic uncertain nonlinear systems. A novel adaptive tracking control design approach, in which the fuzzy systems are employed to approximate the totally unknown nonlinear terms, is proposed by incorporating the technology of prescribed performance control with the method of command filtered backstepping design. The proposed adaptive state feedback controller can ensure that the output tracking error converges to a predefined arbitrarily small residual set in probability and all the signals of the closed-loop system can be bounded in probability, meanwhile, the problem of “explosion of complexity” is solved. The effectiveness of the presented method is verified by two simulation examples. [ABSTRACT FROM AUTHOR]

This article proposes a novel approach to replace the fixed projection planes existed in the previous researches to reduce motion artifacts obtained from the human face by a normal webcam for monitoring heart rate in a real-time fashion. The novel projection plane is adaptively changed with the light intensity change to eliminate the color distortion induced by motion. In this article, the state-of-the-art semantic segmentation Deeplabv3+ is implemented to segment the skin pixels from the facial region that is detected by several trackers (Boosting, MIL, TLD, Median Flow, Mosse, and CSRT) to boost the computational time compared to the conventional face detection by Haar-Like features. Image and digital signal processing techniques are also applied to eliminate possible noise for obtaining a clean pulse signal. The proposed approach is compared with other existing approaches (Green, PCA, Chrom, and POS) in multiple challenges. From the experiments conducted, the Deeplabv3+ outperforms the conventional K-means for different kinds of skin segmentation. Moreover, the proposed approach is quite robust and stable in the stationary case (with the accuracy 96%), dim-lighting environment and the long-distance up to 4-m away without zooming in camera. Besides, multiple head-movement simulations and motions of fitness are conquered by the APP approach as shown in the experiments. Thus, it can be concluded that the proposed approach is applicable to surveillance or healthcare applications. [ABSTRACT FROM AUTHOR]

This article reports this article on the problem of adaptive fuzzy output tracking control for a category of high-order nonlinear systems with input saturation, output constraint, and serious uncertainties. A high-order barrier Lyapunov function and an auxiliary Hyperbolic Tangent function is employed to deal with output constraint and input saturation, respectively. By incorporating a backstepping design technique, adaptive fuzzy control, and adding a power integrator, a novel control scheme is designed to ensure that all states in the resulting closed-loop system are bounded and the tracking error converges to a bounded compact set. Moreover, two simulations are conducted to verify the effectiveness of the design method. [ABSTRACT FROM AUTHOR]

The ongoing realization of a transition towards increased reliance on edge computing is evident. This shift not only underscores the importance of interdependence in knowledge sharing but also contributes to a reduction in adaptation and transmission time through cloud computing directly, along with decreased computational demands compared to edge-to-edge computing. A persistent challenge in knowledge transfer stems from the shift in dependence from high-performance computing systems to compact models, making the adjustment cumbersome. Even with cross-edge knowledge transfer, pre-processing remains essential to facilitate seamless adaptation—a necessity that endures despite the escalating volume of data. Consequently, the system tends to become overburdened with instance filtering instead. To address this issue, we present an optimization for small-to-small inter-edge transfer learning of a comparable size. This is achieved through a self-supervised domain-adaptive protocol, utilizing self-target curriculum-based pseudo-labeling creation, new statistical alignment, and lightweight attention. In the multi-view verification using public visual DA datasets, we demonstrate a remarkable improvement of 73.6 (+4.2 %) in Top-1 performance. Our results consistently outperform other methods, particularly when using the latent feature input technique. This advantage is most noticeable at the 10-th layer for latent feature input. Crucially, our approach incurs the modest increase in computational demands, adding just 100 K-units of parameters and MFLOPS of computational power. Furthermore, through model enhancement via acceleration and compression, we achieve significant compression—up to 6.28 times faster at FP32 and 7.18 times faster at FP16 runtimes—resulting in an increased FPS to 124.9 and 142.9, respectively. This demonstration effectively illustrates the feasibility of advancing inter-edge transfer learning with our approach. [ABSTRACT FROM AUTHOR]

SUMMARY: The 7 degrees of freedom (DOF) redundant manipulator greatly improves obstacle/singularity avoidance capability and operational flexibility. However, the inverse kinematics problem of this manipulator is very difficult to solve because it has an infinite number of solutions. This paper uses a new numerical sequence processing method with a closed-loop framework to solve the inverse kinematics of the 7-DOF redundant manipulator. Simulation and experiment show that this method has high commonality. No special structure of the robot is required, and this method has improved computational efficiency and reliability. [ABSTRACT FROM AUTHOR]

Calcium dynamics in the developing pollen of Chinese fir (Cunninghamia lanceolata) were investigated using an antimonate calcium precipitation method. After microspores were released from the tetrad, abundant calcium precipitates formed on the surface of microspores. A characteristic event during microspore development is the formation of a large vacuole which displaces the nucleus to the periphery and produces polarity, which initiates male gametophyte development. During the formation of the large vacuole, calcium precipitates moved into the large vacuole via mitochondria, suggesting that calcium abundance is related to vacuole biogenesis and formation. After microspore division, the large vacuole reorganised and calcium became concentrated in smaller vacuoles. The pollen wall of Chinese fir consists mostly of the intine, composed of polysaccharose, and the surface of the pollen grains is covered with a thin indefinite structure, the exine, which is composed of sporopollenin. The function of calcium during pollen development and the characteristics of the pollen wall of Chinese fir are discussed. [ABSTRACT FROM AUTHOR]

This paper focuses on the design of a reduced adaptive fuzzy tracking controller for a class of high-order stochastic nonstrict feedback nonlinear systems with full-state constraints. In the proposed approach, reduced fuzzy systems are used to approximate uncertain functions which involve all state variables and a high-order tan-type barrier Lyapunov function (BLF) is considered to deal with full-state constraints of the controlled system. With this BLF and a combination of the reduced fuzzy control and adding a power integrator, a novel control scheme is constructed to ensure that tracking error is within a very small range of the origin almost surely, meanwhile, the constraints on the system states are not breached almost surely during the operation. Two examples are proposed to show the effectiveness of the design scheme. [ABSTRACT FROM AUTHOR]

This paper aims to build a simple and low-cost system by using images to detect human breath in a real-time fashion to estimate the peak of the inspiratory phase of a breath so as to define a proper triggering timing for X-ray shooting. In fact, it is very difficult to detect very small breathing motion on images. In this paper, well-known techniques are employed to obtain useful features from the chest area for the Lucas–Kanade algorithm. Various levels of the Pyramidal Lucas–Kanade are then adapted to track possible small motions of those features. The proposed approach can successfully detect the inspiratory–expiratory motions and the peak time of inspiratory phase can be predicted within an acceptable interval of error time. From the experiments conducted, the breath motion can be successfully observed in two different environment situations (dim-lighting and lighting conditions). It can be found that the tracked features are quite robust and stable without losing the quantity over a long period of testing time. Thus, the proposed approach can effectively be used to define a proper triggering timing for X-ray shooting. Besides, in our experiments, even though the target is 6 m away, the breath detection is still successful. In other words, the proposed approach can also be used for surveillance or healthcare environments. [ABSTRACT FROM AUTHOR]

This paper reports our study on adaptive fuzzy tracking control for flexible-joint robots with full state constraints. In the control design, fuzzy systems are adopted to identify the totally unknown nonlinear functions and can properly avoid burdensome computations. The tan-type barrier Lyapunov functions are used to deal with state constraints so that even without state constraints, the controller is still valid. By combining the method of backstepping design with adaptive fuzzy control approaches, a novel simpler controller is successfully constructed to ensure that the output tracking errors converge to a sufficiently small neighborhood of the origin, while the constraints on the system states will not be violated during operation. Finally, comparison simulations are presented to demonstrate the effectiveness of the proposed control schemes. [ABSTRACT FROM AUTHOR]

Microsporongium development in Chinese fir (Cunninghamia lanceolata) was investigated using cytochemical methods with a special attention to the fluctuations (in amount and distribution) of polysaccharide and lipid reserves along the development of the microsporangium. Semi-thin sections of microsporangia at different developmental stages were stained with periodic acid–Schiff (PAS) reagent and Sudan Black B to detect insoluble polysaccharides and neutral lipids, respectively. In young microsporangia, microspore mother cells began to accumulate starch grains and lipids, which disappeared during microspore development. Following microspore division, the starch grains present in bicellular pollen disappeared and abundant lipid deposits were accumulated. In mature pollen, only abundant lipids accumulated as storage material. The pollen wall of C. lanceolata is predominantly composed of polysaccharidic intine, and the sporopollenin-containing exine is weakly developed and only forms a thin layer covering the intine. [ABSTRACT FROM AUTHOR]

In this paper, a backpropagating constraints-based trajectory tracking control (BCTTC) scheme is addressed for trajectory tracking of a quadrotor with complex unknowns and cascade constraints arising from constrained actuator dynamics, including saturations and dead zones. The entire quadrotor system including actuator dynamics is decomposed into five cascade subsystems connected by intermediate saturated nonlinearities. By virtue of the cascade structure, backpropagating constraints (BCs) on intermediate signals are derived from constrained actuator dynamics suffering from nonreversible rotations and nonnegative squares of rotors, and decouple subsystems with saturated connections. Combining with sliding-mode errors, BC-based virtual controls are individually designed by addressing underactuation and cascade constraints. In order to remove smoothness requirements on intermediate controls, first-order filters are employed, and thereby contributing to backstepping-like subcontrollers synthesizing in a recursive manner. Moreover, universal adaptive compensators are exclusively devised to dominate intermediate tracking residuals and complex unknowns. Eventually, the closed-loop BCTTC system stability can be ensured by the Lyapunov synthesis, and trajectory tracking errors can be made arbitrarily small. Simulation studies demonstrate the effectiveness and superiority of the proposed BCTTC scheme for a quadrotor with complex constrains and unknowns. [ABSTRACT FROM AUTHOR]

• Exploit source knowledge to self-classify a target via self-supervised adaptation. • Implement double-time EMA to enable self-supervised target debiasing. • Extend morphological data to practical use with RiceDA dataset. • Conduct benchmarks and scenario deployment for real-world rice transportation. Industrial rice agriculture has transitioned towards intelligent computing, with an increasing likelihood of incorporating unmanned decision-making systems. However, one lingering issue that persists is the continued reliance on annotations for activity description. Applying transfer learning and domain-adaptive learning to non-labeled target data with the assistance of source data can be explicitly, but depends on mitigating domain discrepancy instead of principally generating predictive. This compromise both target robustness and comprehensibility. Our aim to enable a model to rely effectively on explicit source knowledge and self-labeling to reliably self-annotate. Our proposed self-supervised domain adaptation method provides debiasing by utilizing both former and present states, which reduces inconsistency when generating imbalanced pseudo-labels and implicitly utilizes source knowledge to consistently increase target-specific knowledge. Comprehensive results show improved performance by 7.5% for public data benchmarks and a gain of 2.4% for a rice transportation scenario. Ablation studies reveal improvements of up to 8.2% in Top-1 accuracy and 2.5% in Top-5 accuracy compared to an existing debiasing method, and highlights substantial parameter and FLOPs saving of up to 4.2 and 14 times, respectively. This underscores the feasibility of our system over self-label-dependent learning. [ABSTRACT FROM AUTHOR]

Decomposed fuzzy system (DFS) is a fuzzy system with a novel structure. Due to its excellent learning performance, DFS is originally proposed for an online learning control scheme and is shown to have effective learning performance. This paper is about the use of DFS for modeling dynamic systems. Since the learning mechanism used in online learning control is not suitable for modeling tasks, a commonly used back propagation learning algorithm is adapted for the use of DFS in modeling dynamic systems. The structure of DFS is to decompose each fuzzy variable into fuzzy subsystems that are called component fuzzy systems. Owing to the independency among component fuzzy systems, the learning for those parameters is also independent among different component fuzzy systems and thus, the learning can become more efficient. From the simulation results, it is evident that the proposed DFS can have much faster convergent speed. In addition, the DFS has a smaller testing error than those of other fuzzy systems. [ABSTRACT FROM PUBLISHER]

The present work focuses on studying the relationship between the time period of a polymer solution staying in the metastable region and the resulting porous structure after phase separation of the solution. We employed the technique of FTIR microscopy to determine the composition change in the PMMA/NMP ( n -methylpyrrolidone) solution after its contact with water. By plotting the composition change on the ternary phase diagram of PMMA, NMP and water, and identifying the times that the composition path intersected with the binodal and the spinodal, we then determined the residence time of the solution in the metastable region (t m ). For each polymer solution, we identified a critical residence time (t mc ) that played a dominant role in determining the phase separation mechanism and the resulting porous structure: with t m less than t mc , the corresponding structure was bi-continuous (typical structure resulted from spinodal decomposition); with t m greater than t mc , the corresponding structure was cellular (typical structure from the mechanism of nucleation and growth). The results show that t mc depended on the polymer molecular weight and the polymer concentration in casting solution. And the dependences can be superimposed into one curve as the polymer concentration was normalized by the polymer chain entanglement concentration. With the relationship between t mc and the normalized polymer concentration and a simple model for the effective diffusivity of water in the polymer solution, we developed a model equation to estimate the positions in PMMA membranes where structure transition occurred from bi-continuous to cellular. Good agreement was obtained between the calculated transition positions and the experimentally determined ones. [ABSTRACT FROM AUTHOR]

Aiming at the carbon dioxide (CO 2) emissions from energy and material flow streams in petrochemical sites, a bi-objective optimization strategy based on retrofit improvements and total site techniques is constructed, which is referred to as the petrochemical CO 2 emission reduction comprehensive (Petro-CERC) model. The fossil fuels for heat, steam and power provision, as well as the fossil-fired power importation are condsidered to shift to biomass fuel and renewable power in utilities and process units. A waste heat up-graded utilization system is introduced and adopted to improve the efficiency of heat energy, and a green combined heat and power system based on renewable and sustainable resources is established to reconstruct the conventional utility system. Carbon capture by the organic amine solvent absorption process is also integrated into the bi-objective optimization strategy. The CO 2 emission reduction methods were applied individually to a petrochemical site in South China with an annual emission of 3.2 million tons CO 2 for the sensitivity analysis. The proposed Petro-CERC model was then performed for the optimization of the combined application of the CO 2 emission reduction methods. From the perspective of both carbon neutrality and economy, the optimal value at the trade-off point of CO 2 emission is 464 thousand tons CO 2 /year, and the cost of achieving an 85% reduction of CO 2 emission is $44.9 million. Further, the CO 2 emission reduction strategies in different petrochemical sites are coupled with four different regions on a national scale according to the matching degree of the three standards of technical feasibility, economic development status and geographical appearance. Consequently, a multi-scenario application based on the four regions is applied in this case, and the feasibility of the CO 2 emission reduction methods to achieve the near carbon neutral goal in these scenarios is evaluated. [Display omitted] • A total-site CO 2 emission bi-objective optimization framework was established. • Energy and mass flow routes for CO 2 emission reduction were both considered. • Four CO 2 emission reduction methods were compared with techno-economic analysis. • Various carbon abatement methods were integrated to optimize a petrochemical site. • Different petrochemical sites have been given different carbon abatement strategies. [ABSTRACT FROM AUTHOR]

This paper introduces a new structure of radial basis function networks (RBFNs) that can successfully model symbolic interval-valued data. In the proposed structure, to handle symbolic interval data, the Gaussian functions required in the RBFNs are modified to consider interval distance measure, and the synaptic weights of the RBFNs are replaced by linear interval regression weights. In the linear interval regression weights, the lower and upper bounds of the interval-valued data as well as the center and range of the interval-valued data are considered. In addition, in the proposed approach, two stages of learning mechanisms are proposed. In stage 1, an initial structure (i.e., the number of hidden nodes and the adjustable parameters of radial basis functions) of the proposed structure is obtained by the interval competitive agglomeration clustering algorithm. In stage 2, a gradient-descent kind of learning algorithm is applied to fine-tune the parameters of the radial basis function and the coefficients of the linear interval regression weights. Various experiments are conducted, and the average behavior of the root mean square error and the square of the correlation coefficient in the framework of a Monte Carlo experiment are considered as the performance index. The results clearly show the effectiveness of the proposed structure. [ABSTRACT FROM AUTHOR]

Abstract: A dissolutive wetting model is employed to study the dynamics of axisymmetric Bi–Sn alloy drops spreading on Bi. The liquid drop surface is assumed to be a spherical cap, while the isothermal model for solute transport with simplified hydrodynamics computes the evolution of the solid–liquid interface. Simulations are performed on a millimeter scale to model experiments. The evolution of the drop radius, the flow and solute concentration profiles near the triple junction, the contact line mobility relationship, the apparent contact angles and the shape of the dissolution boundary during spreading are investigated as functions of initial Sn concentration, model parameters and initial conditions. Good agreement is obtained when compared with the experiments for the cases where diffusion is the dominant transport mode. The shape of the solid–liquid interface is predicted better when the initial experimentally determined dissolution boundary is implemented as the starting point of the subsequent simulation. [Copyright &y& Elsevier]

Normal endothelial and epithelial cells undergo apoptosis when cell adhesion and spreading are disrupted, implying a critical role of focal adhesions in cell survival. Cten is a focal adhesion molecule of the tensin family. In contrast to other tensins, cten expression is limited to very few tissues, such as the prostate, and only in epithelial cells. Here, we have explored the potential roles of cten in apoptosis. We found cten was cleaved during apoptosis induced by staurosporine in normal prostate epithelial cells. By using recombinant caspases and site-directed mutagenesis, we have identified caspase-3 as the major protease to digest cten at the DSTD570↓S site. The biological relevance of cten-cleaved fragments was demonstrated by cells ectopically expressing these fragments. Cten fragment (residues 571–715) containing the phosphotyrosine-binding domain significantly reduced the growth rate. Detection of cleaved poly(ADP-ribose) polymerase and annexin binding in cells expressing cten (571–715) indicated that a fraction of cells underwent apoptosis. These results demonstrate that cten is a target of caspase-3 and the resultant fragments could further promote apoptosis.Oncogene (2005) 24, 4311–4314. doi:10.1038/sj.onc.1208571 Published online 4 April 2005 [ABSTRACT FROM AUTHOR]

The synthesis of a polymer-supported N-hydroxyphthalimide is described. The polystyrene-bound N-hydroxyphthalimide resin has been used to prepare complex alkoxyamines exhibiting both stereochemical and positional diversity. Methods for efficient condensation of complex alkoxyamines with aldehydes and ketones are also outlined. [Copyright &y& Elsevier]

Matrix metalloproteinase-2 ( MMP-2) can degrade extracellular matrix and basement membrane, and play an important role in the development and progression of multiple carcinomas, including oral squamous cell carcinoma (OSCC). A −1306 C→ T polymorphism in the MMP-2 promoter disrupts Sp1-binding site, and results in reduction of transcriptional activity. This study aimed to assess the association of such genotype with the risk of OSCC and oral submucous fibrosis (OSF), which is a precancerous condition that exhibits excessive collagen production and etiologically links to areca use. Genomic DNA from the blood samples of 121 OSCC cases, 58 OSF cases and 147 controls were amplified by polymerase chain reaction (PCR) and subjected to denaturing high-performance liquid chromatography (dHPLC ) analysis for genotyping. The OSCC were further classified into buccal squamous cell carcinoma (BSCC) and non-buccal squamous cell carcinoma (NBSCC), according to the site of involvement. Fisher's exact test and unconditional logistic regression models were used for statistical analysis. Subjects carrying CC genotype had nearly twofold increased risk for developing OSCC when comparing with CT or TT genotype. Subjects carrying CC genotype had more apparent risk (greater than fourfold) for developing NBSCC. However, no increase in risk for lymph node metastasis or advanced stage was identified in OSCC cases carrying such genotype. Preliminarily data suggest no significant association between subjects carrying CC genotype and the development of BSCC or OSF. This is the first paper demonstrating that functional genotype of MMP-2 promoter is a risk factor for oral carcinogenesis, particularly for the subsets occurring on non-buccal site. [ABSTRACT FROM AUTHOR]

Total syntheses of the peptide enamide natural products terpeptin and aspergillamides A and B are reported. An oxidative decarboxylation–elimination protocol is employed to construct the indolic enamide moiety. Unambiguous stereochemical assignment of (−)-terpeptin is accomplished by synthesis of all possible stereochemical analogues. Select compounds have been evaluated in cell cycle inhibitor assays which show that the natural amino acid configuration of terpeptin has the most potent inhibitory activity. [Copyright &y& Elsevier]

Proposes a novel genetic algorithm (GA) with greedy eugenics. Weapon-target assignment (WTA) problems; GA for WTA problems; Discussion on GA with eugenic mechanisms; Results of employing the proposed algorithm to solve general WTA problems.

Studies the dynamical modeling with delay feedback neural-fuzzy networks. Description of the neural-fuzzy network; Overview of used modeling approaches and additive delay feedback neural-fuzzy networks; Formation of training data and testing data.

Proposes the robust support vector, a regression approach to enhance the robust capability of support vector regression (SVR). Application of support vector machine for problem solving; Concept of robust learning; Robust property of SVR.

In recent years the grey theorem has been successfully used in many prediction applications. The proposed Markov-Fourier grey model prediction approach uses a grey model to predict roughly the next datum from a set of most recent data. Then, a Fourier series is used to fit the residual error produced by the grey model. With the Fourier series obtained, the error produced by the grey model in the next step can be estimated. Such a Fourier residual correction approach can have a good performance. However, this approach only uses the most recent data without considering those previous data. In this paper, we further propose to adopt the Markov forecasting method to act as a longterm residual correction scheme. By combining the short-term predicted value by a Fourier series and a long-term estimated error by the Markov forecasting method, our approach can predict the future more accurately. Three time series are used in our demonstration. They are a smooth functional curve, a curve for the stock market and the Mackey-Glass chaotic time series. The performance of our approach is compared with different prediction schemes, such as back-propagation neural networks and fuzzy models. All these methods are one-step-ahead forecasting. The simulation results show that our approach can predict the future more accurately and also use less computational time than other methods do. [ABSTRACT FROM AUTHOR]

Deals with a study which proposed the annealing robust backpropagation (ARBP) learning algorithm to deal with the problem of modeling under the existence of outliers. Robust learning algorithms; ARBP learning algorithm; Simulation results; Conclusion.

• The quadratic curve fitting method is indisputably the best for practical use. • Mass measurement uncertainty couldn't be the leading error source(s). • The volatile loss occurred primarily during the hold time at 50 °C. Correct sensible heat curve (virtual baseline) during phase change is a must for accurate evaluation of latent heat. In this article, the dynamically moving interface (DMI) model for any phase change material (PCM) measured with a differential scanning calorimeter (DSC) is devised not only for elucidating the complex mechanisms of transient heat transfer in the five stages from solid phase to liquid phase, but also for constructing a correct sensible heat curve during phase change. We derive all the governing relations in exact or analytic form to describe the corresponding heat currents in the five stages of transient heat transfer together with the correct sensible heat curve during phase change inside any tiny PCM sample. The error budget analysis for the expanded uncertainty of specific latent heat about the tiny indium sample is detailed after the full assessment to specific latent heats of several PCMs. [ABSTRACT FROM AUTHOR]

This study developes a flexible performance optimal control scheme via reinforcement learning strategy and event-triggered mechanism for flexible-joint robots with random noise and non-affine input. It is notable that an event-triggered optimization mechanism is developed, which meets the optimality principle and saves communication resources. Nevertheless, the existing event-triggered strategy is unable to handle non-affine input, which limits the applicability of this method. To overcome the above problems, a modified event-triggered mechanism is proposed. At the same time, the optimal solution of the system is given by an optimized control algorithm based on the improved performance index function. In the controller design, neural network is used to deal with random disturbances and uncertainties, and an adaptive law is designed to replace the identifier structure. Besides, a flexible prescribed performance function is constructed to yield multiple prescribed performance behaviors by adjusting the key parameters, while the tracking error is stayed within a prescribed boundary. Finally, the effectiveness of the proposed control scheme is further demonstrated by simulation and the experiment of the 2-link flexible-joint robot on the Quanser platform. • The proposed scheme can handle random disturbance and reduce approximation behaviors. • An improved trigger condition is designed to eliminate the impact of nonaffine input. • The controller can yield multiple constraint behaviors by adjusting key parameters. • The value function with an exponential term is meaningful at infinity. [ABSTRACT FROM AUTHOR]

In this study, an effective approach of spectral images based on environmental sound classification using Convolutional Neural Networks (CNN) with meaningful data augmentation is proposed. The feature used in this approach is the Mel spectrogram. Our approach is to define features from audio clips in the form of spectrogram images. The randomly selected CNN models used in this experiment are, a 7-layer or a 9-layer CNN learned from scratch. Also, various well-known deep learning structures with transfer learning and with a concept of freezing initial layers, training model, unfreezing the layers, again training the model with discriminative learning are considered. Three datasets, ESC-10, ESC-50, and Us8k are considered. As for the transfer learning methodology, 11 explicit pre-trained deep learning structures are used. In this study, instead of using those available data augmentation schemes for images, we proposed to have meaningful data augmentation by considering variations applied to the audio clips directly. The results show the effectiveness, robustness, and high accuracy of the proposed approach. The meaningful data augmentation can accomplish the highest accuracy with a lower error rate on all datasets by using transfer learning models. Among those used models, The ResNet-152 attained 99.04% for ESC-10 and 99.49% for Us8k datasets. DenseNet-161 gained 97.57% for ESC-50. From our understanding, they are the best-achieved results on these datasets. [ABSTRACT FROM AUTHOR]

Over the past few years, the study of environmental sound classification (ESC) has become very popular due to the intricate nature of environmental sounds. This paper reports our study on employing various acoustic features aggregation and data enhancement approaches for the effective classification of environmental sounds. The proposed data augmentation techniques are mixtures of the reinforcement, aggregation, and combination of distinct acoustics features. These features are known as spectrogram image features (SIFs) and retrieved by different audio feature extraction techniques. All audio features used in this manuscript are categorized into two groups: one with general features and the other with Mel filter bank-based acoustic features. Two novel and innovative features based on the logarithmic scale of the Mel spectrogram (Mel), Log (Log-Mel) and Log (Log (Log-Mel)) denoted as L2M and L3M are introduced in this paper. In our study, three prevailing ESC benchmark datasets, ESC-10, ESC-50, and Urbansound8k (Us8k) are used. Most of the audio clips in these datasets are not fully acquired with sound and include silence parts. Therefore, silence trimming is implemented as one of the pre-processing techniques. The training is conducted by using the transfer learning model DenseNet-161, which is further fine-tuned with individual optimal learning rates based on the discriminative learning technique. The proposed methodologies attain state-of-the-art outcomes for all used ESC datasets, i.e., 99.22% for ESC-10, 98.52% for ESC-50, and 97.98% for Us8k. This work also considers real-time audio data to evaluate the performance and efficiency of the proposed techniques. The implemented approaches also have competitive results on real-time audio data. [ABSTRACT FROM AUTHOR]

The adoption of the environmental sound classification (ESC) tasks increases very rapidly over recent years due to its broad range of applications in our daily routine life. ESC is also known as Sound Event Recognition (SER) which involves the context of recognizing the audio stream, related to various environmental sounds. Some frequent and common aspects like non-uniform distance between acoustic source and microphone, the difference in the framework, presence of numerous sounds sources in audio recordings and overlapping various sound events make this ESC problem much complex and complicated. This study is to employ deep convolutional neural networks (DCNN) with regularization and data enhancement with basic audio features that have verified to be efficient on ESC tasks. In this study, the performance of DCNN with max-pooling (Model-1) and without max-pooling (Model-2) function are examined. Three audio attribute extraction techniques, Mel spectrogram (Mel), Mel Frequency Cepstral Coefficient (MFCC) and Log-Mel, are considered for the ESC-10, ESC-50, and Urban sound (US8K) datasets. Furthermore, to avoid the risk of overfitting due to limited numbers of data, this study also introduces offline data augmentation techniques to enhance the used datasets with a combination of L2 regularization. The performance evaluation illustrates that the best accuracy attained by the proposed DCNN without max-pooling function (Model-2) and using Log-Mel audio feature extraction on those augmented datasets. For ESC-10, ESC-50 and US8K, the highest achieved accuracies are 94.94%, 89.28%, and 95.37% respectively. The experimental results show that the proposed approach can accomplish the best performance on environment sound classification problems. [ABSTRACT FROM AUTHOR]

This paper presents a novel architecture of the vision/position hybrid control for a Hexa parallel robot. The 3D vision system is combined with the Proportional-Integral-Derivative (PID) position controller to form a two-level closed-loop controller of the robot. The 3D vision system measures the pose of the end-effector after the PID control. The measurement of the 3D vision system is used as a feedback of the second closed-loop control. The 3D vision system has a simple structure using two fixed symmetric cameras at the top of the robot and four planar colored markers on the surface of the end-effector. The 3D vision system detects and reconstructs the 3D coordinates of colored markers. Based on the distance and coplanarity constraints of the colored markers, the optimization problem is modeled for the real-time adjustment, which is implemented during the operation of the robot to minimize the measurement error of the 3D vision system due to both the initial calibration of the stereo camera and the external noise affecting image processing. The bacterial foraging optimization is appropriately configured to solve the optimization problem. The experiment is performed on a specific Hexa parallel robot to assess the effectiveness and feasibility of the proposed real-time adjustment using the bacterial foraging optimization. The experimental result shows that it has high accuracy and fast computation time although the experiment is conducted on a laptop with an average hardware configuration. An experimental comparison of the performance between the proposed method and another control method is also implemented. The results show the superiority and application potential of the proposed method. [ABSTRACT FROM AUTHOR]

This article addresses an event-triggered adaptive fuzzy tracking control problem for nonlinear systems with unknown control directions. To achieve the practical tracking, fuzzy logic systems are employed to approximate unknown nonlinear function. Nussbaum functions are adopted to address the problem of the unknown control directions. The newly designed controller not only guarantees the tracking error that converges to an arbitrary small neighborhood near the zero but also reduces the communication burden from the controller to the actuator. Moreover, the feasibility of the proposed event-triggered mechanism is verified by excluding Zeno behavior. Finally, the simulation result proves the effectiveness of the designed control scheme. [ABSTRACT FROM AUTHOR]

This study considers the problem of prescribed performance adaptive asymptotic tracking control for a class of nonlinear systems with time‐varying parameters. A novel adaptive tracking control scheme is constructed by using the congelation of variables method and the backstepping method, in which the adaptive laws are designed to approximate the averages of the time‐varying parameters. The normalized function transformation is introduced to achieve the prescribed performance control; meanwhile, the issue of the explosion of complexity is avoided by using the command filtered technique. In addition, the proposed approach guarantees that all signals of the closed‐loop system are bounded and the tracking error can asymptotically converge to zero, while staying within prescribed boundaries. Finally, the effectiveness of the control strategy is shown by two simulation examples. [ABSTRACT FROM AUTHOR]

In this study, a novel adaptive neural network control scheme is proposed to resolve the tracking control problem for flexible‐joint robots with random noises. More precisely, the controlled system in this study is a multi‐input and multi‐output stochastic nonlinear system, employing the traditional backstepping design to study such a system will greatly increase the amount of calculation. To resolve this problem, the command filtered technology is applied to the adaptive neural network design framework. More importantly, with the aid of the event‐triggered strategy, the proposed control algorithm can reduce the communication burden to a certain extent. Besides, the proposed method can also ensure that the tracking error converges to a small neighborhood of the origin. Finally, the simulation example is given to verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In this article, a global finite-time active disturbance rejection control (ADRC) scheme is proposed for tracking control of redundant parallel manipulators with unknown bounded uncertainties. This approach combines an ADRC and a global finite-time control for high accuracy trajectory tracking control. Based on the nonsingular fast terminal sliding mode control, the proposed approach can remove the condition in the original ADRC that the derivative of the uncertainties is required to be bounded. The extended state observer is employed to handle the real-time estimation of the total uncertainty. It can be found that the proposed scheme not only can converge fast to the semi-global finite-time stable equilibrium but also can have superior tracking control performance. In summary, compared to existing approaches, the proposed scheme can have several advantages, such as uncertainty rejection, easy implementation, robustness, chattering-free, high precision, and no need for prior knowledge of bounded uncertainties. The simulation results validate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This study reports adaptive quantized control for a class of uncertain strict‐feedback nonlinear systems with unknown control directions. Combining backstepping technique and Lyapunov stability theory, a systematic analysis method is designed. Based on the disintegration of the hysteresis quantizer, a Nussbaum‐based scheme can be developed to get over the obstacle of the quantized input signal and unknown control directions. Moreover, the number of adaptive laws is small, thereby reducing the computational burden. Then we testify the boundedness of all signals in the closed‐loop system. Besides, the tracking error can converge to an arbitrarily small domain of origin. Finally, a simulation example is provided to verify the feasibility of the control scheme. [ABSTRACT FROM AUTHOR]

Coronary artery disease is caused primarily by vessel narrowing. Extraction of the coronary artery area from images is the preferred procedure for diagnosing coronary diseases. In this study, a U-Net-based network architecture, 3D Dense-U-Net, was adopted to perform fully automatic segmentation of the coronary artery. The network was applied to 474 coronary computed tomography (CT) angiography scans performed at Wanfang Hospital, Taiwan. Of these, 10% were used for testing. The CT scans were divided into patches of 16 original high-resolution slices. The slices were overlapped between patches to take advantage of surrounding imaging information. However, an imbalance between the foreground and background presents a challenge in smaller-object segmentation such as with coronary arteries. The network was optimized and achieved a promising result when the focal loss concept was adopted. To evaluate the accuracy of the automatic segmentation approach, the dice similarity coefficient (DSC) was calculated, and an existing clinical tool was used. The subjective ratings of three experienced radiologists were used to compare the two ratings. The results show that the proposed approach can achieve a DSC of 0.9691, which is significantly higher than other studies using a deep learning approach. In the main trunk, the results of automatic segmentation agree with those of the clinical tool; they were significantly better in some small branches. In our study, automatic segmentation tool shows high-performance detection in coronary lumen vessels, thereby providing potential power in assisting clinical diagnosis. [ABSTRACT FROM AUTHOR]

This article is concerned with the improvement of robust control methodology and its application in stabilizing a class of high-order nonlinear systems with multiple unknown time-varying sensitivities, and discusses how to use the proposed control strategy on humanoid robot manipulation. The novel design approach successfully breaks through the limitation of the neural network technique; that is, state variables must be located in some compact sets. The remarkable feature of the systems under investigation lies in the presence of measurement sensitivities and higher powers, which makes the nonlinear systems essentially different from the related works. By reductio and the introduction of a modified tuning function, an appropriate controller is constructed to render that all the state variables belong to a predetermined bounded set. Finally, an example is provided to illustrate the effectiveness of the proposed control strategy. [ABSTRACT FROM AUTHOR]

In this study, a novel method with the U-Net-based network architecture, 2D U-Net, is employed to segment the position of lung nodules, which are an early symptom of lung cancer and have a high probability of becoming a carcinoma, especially when a lung nodule is bigger than 15 mm 2 . A serious problem of considering deep learning for all medical images is imbalanced labeling between foreground and background. The lung nodule is the foreground which accounts for a lower percentage in a whole image. The evaluation function adopted in this study is dice coefficient loss, which is usually used in image segmentation tasks. The proposed pre-processing method in this study is to use complementary labeling as the input in U-Net. With this method, the labeling is swapped. The no-nodule position is labeled. And the position of the nodule becomes non-labeled. The result shows that the proposal in this study is efficient in a small quantity of data. This method, complementary labeling could be used in a small data quantity scenario. With the use of ROI segmentation model in the data pre-processing, the results of lung nodule detection can be improved a lot as shown in the experiments. [ABSTRACT FROM AUTHOR]

Pollen is the male gametophyte of higher plants. Its major function is to deliver sperm cells to the ovule to ensure successful fertilization. During this process, many interactions occur among pollen tubes and pistil cells and tissues, and calcium ion (Ca2+) dynamics mediate these interactions among cells to ensure that pollen reaches the embryo sac. Although the precise functions of Ca2+ dynamics in the cells are unknown, we can speculate about its roles on the basis of its spatial and temporal characteristics during these interactions. The results of many studies indicate that calcium is a critical element that is strongly related to pollen germination and pollen tube growth. [ABSTRACT FROM AUTHOR]

This study concentrates on the prescribed-time output feedback tracking problem for nonlinear systems with unknown control gains and quantized input. A modified observer with the first-order scale function handles the unmeasurable problem of states while achieving accurate observation in the prescribed time. A simple controller is constructed by a new function transformation in which the computation burden is greatly reduced. The resulting controller not only drives that tracking error converges to zero but also ensures that all signals in the closed-loop system are bounded. Finally, the effectiveness of the control scheme is demonstrated by a numerical simulation and a practical simulation. • The settling time of the prescribed-time control considered in this study is neither affected by the initial states nor by the design parameters. • To solve unmeasurable states, a modified state observer using only the first-order scale function is proposed. • The sector-bounded quantizer is considered to avoid the communication problem and relax the nonlinear condition of the quantizer. [ABSTRACT FROM AUTHOR]