Search results

Light field images (LFIs) have gained popularity as a technology to increase the field of view (FoV) of plenoptic cameras since they can capture information about light rays with a large FoV. Wide FoV causes light field (LF) data to increase rapidly, which restricts the use of LF imaging in image processing, visual analysis and user interface. Effective LFI coding methods become of paramount importance. This paper aims to eliminate more redundancy by exploring sparsity and correlation in the angular domain of LFIs, as well as mitigate the loss of perceptual quality of LFIs caused by encoding.

This work proposes a new efficient LF coding framework. On the coding side, a new sampling scheme and a hierarchical prediction structure are used to eliminate redundancy in the LFI's angular and spatial domains. At the decoding side, high-quality dense LF is reconstructed using a view synthesis method based on the residual channel attention network (RCAN).

In three different LF datasets, our proposed coding framework not only reduces the transmitted bit rate but also maintains a higher view quality than the current more advanced methods.

(1) A new sampling scheme is designed to synthesize high-quality LFIs while better ensuring LF angular domain sparsity. (2) To further eliminate redundancy in the spatial domain, new ranking schemes and hierarchical prediction structures are designed. (3) A synthetic network based on RCAN and a novel loss function is designed to mitigate the perceptual quality loss due to the coding process.

Traffic flow prediction has always been a top priority of intelligent transportation systems. There are many mature methods for short-term traffic flow prediction. However, the existing methods are often insufficient in capturing long-term spatial-temporal dependencies. To predict long-term dependencies more accurately, in this paper, a new and more effective traffic flow prediction model is proposed.

This paper proposes a new and more effective traffic flow prediction model, named channel attention-based spatial-temporal graph neural networks. A graph convolutional network is used to extract local spatial-temporal correlations, a channel attention mechanism is used to enhance the influence of nearby spatial-temporal dependencies on decision-making and a transformer mechanism is used to capture long-term dependencies.

The proposed model is applied to two common highway datasets: METR-LA collected in Los Angeles and PEMS-BAY collected in the California Bay Area. This model outperforms the other five in terms of performance on three performance metrics a popular model.

(1) Based on the spatial-temporal synchronization graph convolution module, a spatial-temporal channel attention module is designed to increase the influence of proximity dependence on decision-making by enhancing or suppressing different channels. (2) To better capture long-term dependencies, the transformer module is introduced.

This study aims to study the distribution characteristics of antibiotic resistance in direct-eating food and analysis of Citrobacter freundii genome and pathogenicity. Residual antibiotics and antibiotic resistance genes (ARGs) in the environment severely threaten human health and the ecological environment. The diseases caused by foodborne pathogenic bacteria are increasing daily, and the enhancement of antibiotic resistance of pathogenic bacteria poses many difficulties in the treatment of disease.

In this study, six fresh fruits and vegetable samples were selected for isolation and identification of culturable bacteria and analysis of antibiotic resistance. The whole genome of Citrobacter freundii isolated from cucumber was sequenced and analyzed by Oxford Nanopore sequencing.

The results show that 270 strains of bacteria were identified in 6 samples. From 12 samples of direct food, 2 kinds of probiotics and 10 kinds of opportunistic pathogens were screened. The proportion of Citrobacter freundii screened from cucumber was significantly higher than that from other samples, and it showed resistance to a variety of antibiotics. Whole genome sequencing showed that Citrobacter freundii was composed of a circular chromosome containing signal peptides, transmembrane proteins and transporters that could induce antibiotic efflux, indicating that Citrobacter freundii had strong adaptability to the environment. The detection of genes encoding carbohydrate active enzymes is more beneficial to the growth and reproduction of Citrobacter freundii in crops. A total of 29 kinds of ARGs were detected in Citrobacter freundii, mainly conferring resistance to fluoroquinolones, aminoglycosides, carbapenem, cephalosporins and macrolides. The main mechanisms are the change in antibiotic targets and efflux pumps, the change in cell permeability and the inactivation of antibiotics and the detection of virulence factors and ARGs, further indicating the serious risk to human health.

The detection of genomic islands and prophages increases the risk of horizontal transfer of virulence factors and ARGs, which spreads the drug resistance of bacteria and pathogenic bacteria more widely.

Compared with traditional methods relying on manual teaching or system modeling, data-driven learning methods, such as deep reinforcement learning and imitation learning, show more promising potential to cope with the challenges brought by increasingly complex tasks and environments, which have become the hot research topic in the field of robot skill learning. However, the contradiction between the difficulty of collecting robot–environment interaction data and the low data efficiency causes all these methods to face a serious data dilemma, which has become one of the key issues restricting their development. Therefore, this paper aims to comprehensively sort out and analyze the cause and solutions for the data dilemma in robot skill learning.

First, this review analyzes the causes of the data dilemma based on the classification and comparison of data-driven methods for robot skill learning; Then, the existing methods used to solve the data dilemma are introduced in detail. Finally, this review discusses the remaining open challenges and promising research topics for solving the data dilemma in the future.

This review shows that simulation–reality combination, state representation learning and knowledge sharing are crucial for overcoming the data dilemma of robot skill learning.

To the best of the authors’ knowledge, there are no surveys that systematically and comprehensively sort out and analyze the data dilemma in robot skill learning in the existing literature. It is hoped that this review can be helpful to better address the data dilemma in robot skill learning in the future.

In recent years, private brands for e-commerce platforms have experienced rapid growth. However, whether these platforms developing private brands should share their demand information with others and how such information sharing affects the sales format selection of national brand manufacturers have puzzled firm managers in practice. This paper aims to investigate the information-sharing strategy for the e-commerce platform and its influence on the sales format selection in the presence of the private brand.

The authors use a game-theoretical model to examine the interaction between the information-sharing strategy and sales format selection in a supply chain consisting of a manufacturer and a platform that operates a private brand.

The equilibrium results show that when the commission rate is low, the manufacturer favors agency selling, and the platform shares demand information with the manufacturer; when the commission rate is high, the manufacturer prefers reselling, and the platform does not share the information. This preference is affected by information forecasting accuracy; as the information forecasting accuracy increases, the manufacturer prefers to adopt agency selling, and the platform tends to share the information. Interestingly, under agency selling, sharing information with the manufacturer can increase the platform’s profit from selling the private brand and achieve a win-win situation for them. Furthermore, we show that the manufacturer can inspire the platform to share the information with himself by adopting agency selling, whereas the platform sharing the information improves the probability that the manufacturer adopts agency selling. Moreover, the manufacturer may have a first-mover advantage. In particular, the manufacturer moving first increases the likelihood that the manufacturer chooses agency selling and the platform shares the information.

This paper contributes to sales format literature by exploring the effect of information sharing strategy on sales format selection in the presence of the private brand and can help manufacturers and platforms to make suitable decisions regarding information sharing and sales format selection.

Vision, audition, olfactory, tactile and taste are five important senses that human uses to interact with the real world. As facing more and more complex environments, a sensing system is essential for intelligent robots with various types of sensors. To mimic human-like abilities, sensors similar to human perception capabilities are indispensable. However, most research only concentrated on analyzing literature on single-modal sensors and their robotics application.

This study presents a systematic review of five bioinspired senses, especially considering a brief introduction of multimodal sensing applications and predicting current trends and future directions of this field, which may have continuous enlightenments.

This review shows that bioinspired sensors can enable robots to better understand the environment, and multiple sensor combinations can support the robot’s ability to behave intelligently.

The review starts with a brief survey of the biological sensing mechanisms of the five senses, which are followed by their bioinspired electronic counterparts. Their applications in the robots are then reviewed as another emphasis, covering the main application scopes of localization and navigation, objection identification, dexterous manipulation, compliant interaction and so on. Finally, the trends, difficulties and challenges of this research were discussed to help guide future research on intelligent robot sensors.

The purpose of this study is to design a wearable medical device as a human care platform and to introduce the design details, key technologies and practical implementation methods of the system.

A multi-channel data acquisition scheme based on PCI-E (rapid interconnection of peripheral components) was proposed. The flexible biosensor is integrated with the flexible data acquisition card with monitoring capability, and the embedded (device that can operate independently) chip STM32F103VET6 is used to realize the simultaneous processing of multi-channel human health parameters. The human health parameters were transferred to the upper computer LabVIEW by intelligent clothing through USB or wireless Bluetooth to complete the transmission and processing of clinical data, which facilitates the analysis of medical data.

The smart clothing provides a mobile medical cloud platform for wearable medical through cloud computing, which can continuously monitor the body's wrist movement, body temperature and perspiration for 24 h. The result shows that each channel is completely accurate to the top computer display, which can meet the expected requirements, and the wearable instant care system can be applied to healthcare.

The smart clothing in this study is based on the monitoring and diagnosis of textiles, and the electronic communication devices can cooperate and interact to form a wearable textile system that provides medical monitoring and prevention services to individuals in the fastest and most accurate way. Each channel of the system is precisely matched to the display screen of the host computer and meets the expected requirements. As a real-time human health protection platform technology, continuous monitoring of human vital signs can complete the application of human motion detection, medical health monitoring and human–computer interaction. Ultimately, such an intelligent garment will become an integral part of our everyday clothing.

In the prior literature, the motivation to adopt wearable fitness technology (WFT) has been linked with either intrinsic or extrinsic. However, how the subcategories of extrinsic motivations (identified, introjected and external) affect the consumers’ WFT adoption decision remains sparse. Furthermore, do regulatory focus (prevention vs promotion) and gender differences the effects of different motivations on WFT adoption is almost unknown in the health-care marketing literature. This study aims to fill the above-mentioned gap and to unfold the WFT adoption beyond the traditional motivation by incorporating the organismic integration theory (part of self-determined theory) and regulatory focus theory.

This study used a questionnaire-based survey. Using the “AMOS” survey, questionnaire responses of 641 respondents were analyzed and validated by using structural equation modeling. All the variables were adopted from the literature.

The results show that intrinsic, identified and external motivations have the greatest impact on consumers’ decisions, while introjected motivation was not significant directly. The moderation effects of regulatory focus are significant in such a way that prevention focus influences the introjected motivation and promotion focus affects the external motivation and WFT adoption decision. Furthermore, the findings on gender moderation suggest that women are more intrinsically motivated, and men are more externally motivated for WFT adoption.

The new insights and contributions of this study provide a better understanding of WFT adoption and help sellers develop more effective marketing strategies.

This study incorporates subcategories of extrinsic motivations to provide a deeper understanding of consumers’ behavior. Furthermore, this study applies a unique framework of organismic integration theory to consumers’ WFT adoption. It is also among very few research that investigate regulatory focus and gender impact on consumers’ WFT adoption.

A time-varying grey Fourier model (TVGFM(1,1,N)) is proposed for the simulation of variable amplitude seasonal fluctuation time series, as the performance of traditional grey models can't catch the time-varying trend well.

The proposed model couples Fourier series and linear time-varying terms as the grey action, to describe the characteristics of variable amplitude and seasonality. The truncated Fourier order N is preselected from the alternative order set by Nyquist-Shannon sampling theorem and the principle of simplicity, then the optimal Fourier order is determined by hold-out method to improve the robustness of the proposed model. Initial value correction and the multiple transformation are also studied to improve the precision.

The new model has a broader applicability range as a result of the new grey action, attaining higher fitting and forecasting accuracy. The numerical experiment of a generated monthly time series indicates the proposed model can accurately fit the variable amplitude seasonal sequence, in which the mean absolute percentage error (MAPE) is only 0.01%, and the complex simulations based on Monte-Carlo method testify the validity of the proposed model. The results of monthly electricity consumption in China's primary industry, demonstrate the proposed model catches the time-varying trend and has good performances, where MAPE_F and MAPE_T are below 5%. Moreover, the proposed TVGFM(1,1,N) model is superior to the benchmark models, grey polynomial model (GMP(1,1,N)), grey Fourier model (GFM(1,1,N)), seasonal grey model (SGM(1,1)), seasonal ARIMA model seasonal autoregressive integrated moving average model (SARIMA) and support vector regression (SVR).

The parameter estimates and forecasting of the new proposed TVGFM are studied, and the good fitting and forecasting accuracy of time-varying amplitude seasonal fluctuation series are testified by numerical simulations and a case study.

With over-the-top (OTT) streaming services rapidly transforming the media industry and saturating the market, the authors' study seeks to enrich the goal-directed behaviour model by exploring how perceived risks and descriptive norms influence OTT consumption.

Survey data from OTT subscribers were collected online to assess their risk behaviours. The 353 responses obtained were analysed with SmartPLS, validating the structural equation modelling (SEM) through structural and measurement model verification.

The authors' findings illustrate that descriptive norm, perceived behavioural control, as well as positive and negative anticipated emotion (NEM) and attitude, contribute positively to the desire to engage with OTT streaming services. Interestingly, the authors' study contradicts common assumptions, revealing that subjective norms do not significantly impact the propensity to utilise OTT services. This counterintuitive finding necessitates a reconsideration of prevalent theories and contributes to a nuanced understanding of OTT adoption determinants.

The data gathering for this study were conducted from the perspective of a single nation. Therefore, caution must be exercised when generalising this study's results.

The practical ramifications of this research are vast, providing OTT service providers and marketers with actionable insights to maximise user engagement and navigate perceived risks related to OTT service adoption and consumption.

This study's exploration of perceived risks and descriptive norms enhances the goal-directed behaviour model's breadth, facilitating a holistic comprehension of the constructs shaping OTT consumption behaviours. It would be the first attempt to combine perceptual, affective and behavioural factors and perceived risks to understand the user's predisposition to engage in OTT streaming services.