Search

Fatigue driving always endangers road traffic safety and is one of the main causes of traffic accidents. How to effectively monitor and determine the fatigue driving state, so as to realize the fatigue early warning, has become a hot spot of scientific research. The traditional detection methods are mostly based on a certain human physiological parameters, through the monitoring of the physiological parameters changes, to complete the determination of the fatigue state. Compared with the traditional detection methods, the fatigue detection method based on computer vision has the advantages of accurate and reliable detection results, detection not relying on wearable devices, and good human-computer interaction experience. However, in the specific algorithm application scenarios, there are often interference from environmental factors such as partial occlusion of the inspected image, low image resolution, complex illumination of the detection environment, and unstable acquisition equipment. In the face of many challenges, how to effectively improve the detection accuracy of fatigue state, and the algorithm has the practical application space, still needs to be explored. The traditional fatigue detection method based on facial information often detects and analyzes a certain subordination. Due to the detection of individual differences and the fuzzy definition of fatigue state, the algorithm has the problems of high recognition error rate and poor robustness. Moreover, the single attribute model separates the potential integration and exclusion relationship between facial attributes. At the same time, the huge model size and complex model structure also limit the actual implementation of the algorithm. In view of these urgent problems, this paper first proposes the fusion model of face detection and head posture analysis based on the multi-task convolutional neural network (MTCNN). The model uses the architecture strategy of multi-task cascade to complete the complete facial posture analysis task while completing the facial detection task. Secondly, based on the lightweight convolutional neural network (SqueezeNet) of the network cascade, the facial key point detection network is designed to obtain the 72-point key point coordinates of the face. For the obtained facial attribute information, extract fatigue features and propose a fatigue determination method of multimodal fusion. Finally, combined with the research results, the construction of the online fatigue detection and early warning system platform was completed.

Under the two-carbon target, the road of green development in China has reached a new height. This paper is based on the SBM-GML model of 2001-2019 the Yellow River basin nine provinces of agricultural green total factor productivity, combined with the number of Beijing university Digital Inclusive Financial index, from the perspective of time series, space to explore the Digital Inclusive Financial and the relationship between agricultural green low carbon development, for the Yellow River city Green High Quality Development.

This paper explores the cultivation paths of innovation ecosystems in the digital age by constructing a theoretical framework consisting of innovators, elements of innovation, platforms and digital governance. Four cities in China, Shenzhen, Hangzhou, Xuzhou and Weifang, were selected for in-depth case studies. Findings revealed that: (1) regions with ‘head enterprises’ and a strong industrial base achieve a competitive advantage via the synergy of digital industrialisation and industrial digitalisation; (2) digital technology pioneer regions can adopt digital industrialisation; (3) regions with a strong industrial base and traditional manufacturing industries can prioritise industrial digitalisation and (4) manufacturing regions with a large number of small and mid-size enterprises (SMEs) who can combine industrial digitalisation and digital value. This study provides theoretical and practical value for the cultivation of regional innovation ecosystems.

Five-day biochemical oxygen demand (BOD5) is a vital wastewater contamination strength indicator. The process of measuring BOD5 is to measure the mass of molecular oxygen consumed in 1 L of water at 20 °C over a 5-day incubation period. It is a time-consuming process and often too late for water management agencies to make a timely reaction if the result of measurement shows a water body is seriously polluted. Biosensors can simplify the process of BOD5 measurement; however, the measurement results often deviate significantly from the measured BOD5 values. The main aim of this research is to identify a machine learning model, which could predict BOD5 value from historical data and make it easier to detect water pollution in advance and timely adopt treatment measures. Three machine learning techniques, linear regression, support vector regression (SVR) and multi-layer perceptron (MLP) and two optimization processes have been studied in this research. Four main steps, preprocessing (one-time only), model training, model evaluation (testing) and analysis have been implemented in the experiments. With three feature selection strategies, the results of the experiment showed that SVR with genetic algorithm (GA) optimizer achieved the best performance with R2 of 0.694 and the lowest MAE of 0.109.

PurposeThe purpose of this work is to investigate the effect of filament composition with different specifications on the thermal comfort properties of bi-layer knitted fabrics.Design/methodology/approachIn this paper eight bi-layer knitted fabrics with the same knitting structure but different filament compositions were prepared, and the thermal-wet comfort properties of these fabrics were examined. According to experimental data, the effect of filament composition on the thermal comfort properties of fabric was analyzed.FindingsThe increasing difference of hydrophilicity between inner and outer layers resulted in the enhancement of moisture management properties. Better thermal-physiology performance was exhibited by fabrics made up of finer and circular section fibers. Excellent thermal transfer, drying performance and one-way water transport capacity benefited the improvement of dynamic cooling effect of fabrics.Originality/valueThis work provides a useful and effective method for the development of bi-layer knitted fabric applied for sports and summer clothing.

Remaining useful life (RUL) prediction of rolling bearings is of paramount importance to various industrial applications. Recently, intelligent data-driven RUL prediction methods have achieved fruitful results. However, the existing methods heavily rely on the quality and quantity of the available data. For some critical bearings in industrial scenarios, the real run-to-failure data are insufficient, which impair the applicability of data-based methods for industrial practices. To address these issues, this article proposes a novel dynamic model-assisted RUL prediction approach for rolling bearing, in which sufficient simulation data are applied as the training data to solve the problem caused by insufficient real data. More specifically, a dynamic rolling bearing model is introduced for simulating the degradation process of physical structures. Then, a multilayer cross-domain transformer network is developed to implement RUL prediction and adapt the learned prediction knowledge from simulation to the actual measurements. Furthermore, a mutual information loss is utilized to preserve the generalized prediction knowledge of the measured data. The proposed approach can achieve a high RUL prediction accuracy with only limited measured data, which tackles the drawbacks of the existing data-driven methods. The experimental results of the rolling bearing degradation datasets demonstrate the effectiveness and superiority of the proposed RUL prediction approach.

Traffic lights optimization is one of the principal components to lessen the traffic flow and travel time in an urban area. The present article seeks to introduce a novel procedure to design the traffic lights in a city using evolutionary-based optimization algorithms in combination with an ontology-based driving behavior simulation framework. Accordingly, an ontology-based knowledge base is introduced to provide a machine-understandable knowledge of roads and intersections, traffic rules, and driving behaviors. Then, a simulation environment is developed to inspect car behavior in real time. To optimize the traffic lights, a sine-based equation was defined for each traffic light, and the total travel time of the vehicles was considered as the cost function in the optimization algorithm. The optimization was performed with 5, 10, 15, 20, 25, and 30 vehicles in the urban areas. Based on the results, in contrast to uncontrolled intersections without traffic lights, optimized traffic lights can significantly contribute to total travel time-saving. To conclude, due to an escalation in the number of vehicles, the significance of optimized traffic lights has encountered an increase, and unoptimized traffic lights could increase total travel time even more than a city deprived of any traffic light.

Failure mode and effect analysis (FMEA) is a widely used reliability management technology to evaluate the risk of potential failures in a system, product, or service. Nevertheless, the normal risk priority number (RPN) method has been extensively criticized for many deficiencies in practical applications. To overcome the drawbacks of traditional FMEA, plenty of methods have been suggested in previous studies. But majority of them evaluated the risk factors of each failure mode directly and cannot take group and individual risk attitudes into account. In this article, we put forward a new FMEA approach integrating probabilistic linguistic preference relations (PLPRs) and gained and lost dominance score (GLDS) method. The PLPRs are adopted to describe the risk evaluations of experts by pairwise comparison of failure modes. An extended GLDS method is introduced to derive the risk ranking of failure modes considering both group and individual risk attitudes. Moreover, a two-step optimization model is proposed to determine the weights of risk factors when their weighing information is unknown. Finally, a load-haul-dumper machine risk analysis case is presented to demonstrate the proposed FMEA. It is shown that the approach being proposed in this study provides a practical and effective way for risk evaluation in FMEA.

Self-esteem, generally refers to an evaluation made and usually held by individuals, which is one of the important factors affecting individual mental health. Nowadays, society pays more and more attention to college students' mental health. As an important index, self-esteem is of great significance to promote college students' psychological development and improve their self-esteem. Some researchers have pointed out that an individual's self-esteem level is affected by the family environment in which he grew up. As a system, the total body function of the family has a great influence on the level of individual self-esteem. In recent years, more and more researchers have found that there are certain limitations in the research paradigm of examining one or some family factors alone, so they turn to the family as a system, put forward the concept of family function, and investigate the influence of family as a system on individuals. This review selects the special group of college students as the research object, focuses on the impact of family factors on College Students' self-esteem, and discusses the relationship between College Students' self-esteem and family factors such as family background and family relations.

PurposeIn the past two decades, manufacturing has witnessed significant transformations alongside ecological challenges. Meanwhile, industrial 4.0 digital technologies have accelerated industrialisation with potentials of innovation in the context of circular economy. However, current concepts and models are fragmented and impractical. This paper aims to develop a holistic view integrating the three bodies of knowledge – industrialisation, ecologicalisation and digitalisation (IED) – in order to achieve sustainable development.Design/methodology/approachCritical literature review is conducted across three bodies of knowledge. Key themes are summarised with the identification of research gaps. A theoretical framework is synthesised and developed aiming to achieve synergy from IED with the modules, integration architecture, mechanism and dynamic paths.FindingsFirst, the authors review and develop three conceptual models of ecologicalised industrialisation (IE3), industrial system digitalisation (D1) and digital technology industrialisation (D2) separately. Second, the authors propose a theoretical framework seeking to synthesise the above three conceptual models together to form the IED. Third, the authors design a process orientated abductive approach to improve and validate the IED framework.Originality/valueThis study contributes to the limited literature addressing the linkage of IED by integration different perspectives to develop theory in a novel way. Practically, it provides important tools for organisations to consider resource cascading in combination with digitalisation during the industrial system design.

Two-dimensional (2D) materials including graphene, transition metal dichalcogenides, black phosphorus, MXenes, and semimetals have attracted extensive and widespread interest over the past years for their many intriguing properties and phenomena, underlying physics, and great potential for applications. The vast library of 2D materials and their heterostructures provides a diverse range of electrical, photonic, mechanical, and chemical properties with boundless opportunities for photonics and plasmonic devices. The infrared (IR) regime, with wavelengths across 0.78 μm to 1000 μm, has particular technological significance in industrial, military, commercial, and medical settings while facing challenges especially in the limit of materials. Here, we present a comprehensive review of the varied approaches taken to leverage the properties of the 2D materials for IR applications in photodetection and sensing, light emission and modulation, surface plasmon and phonon polaritons, non-linear optics, and Smith-Purcell radiation, among others. The strategies examined include the growth and processing of 2D materials, the use of various 2D materials like semiconductors, semimetals, Weyl-semimetals and 2D heterostructures or mixed-dimensional hybrid structures, and the engineering of light-matter interactions through nanophotonics, metasurfaces, and 2D polaritons. Finally, we give an outlook on the challenges in realizing high-performance and ambient-stable devices and the prospects for future research and large-scale commercial applications. Agency for Science, Technology and Research (A*STAR) National Research Foundation (NRF) This work is partially supported by the National Research Foundation, Singapore, under its CRP program (NRF-CRP26- 2021-0004) and A*STAR AME IRG (A20E5c0084). Z.L. acknowledges the support from PHC Merlion Program 2020. L.W. gratefully acknowledges the Start-Up Research Grant from the Singapore University of Technology and Design via Grant No. SRG SMT 2021 169, and National Research Foundation Singapore via Grant Nos. NRF2021-QEP2-02-P03 and NRF2021-QEP2-03-P09. Y.L. acknowledges the support from A*STAR Career Development Fund - Seed Projects (C222812008). M.Z. acknowledges the support from A*STAR Career Development Fund (C210812027).

Methylation of histone H3 lysine-79 (H3K79) is an epigenetic mark for gene regulation in development, cellular differentiation, and disease progression. However, how this histone mark is translated into downstream effects remains poorly understood owing to a lack of knowledge about its readers. We developed a nucleosome-based photoaffinity probe to capture proteins that recognize H3K79 dimethylation (H3K79me2) in a nucleosomal context. In combination with a quantitative proteomics approach, this probe identified menin as a H3K79me2 reader. A cryo–electron microscopy structure of menin bound to an H3K79me2 nucleosome revealed that menin engages with the nucleosome using its fingers and palm domains and recognizes the methylation mark through a π-cation interaction. In cells, menin is selectively associated with H3K79me2 on chromatin, particularly in gene bodies.

Deep semantic matching aims at discriminating the relationship between documents based on deep neural networks. In recent years, it becomes increasingly popular to organize documents with a graph structure, then leverage both the intrinsic document features and the extrinsic neighbor features to derive discrimination. Most of the existing works mainly care about how to utilize the presented neighbors, whereas limited effort is made to filter appropriate neighbors. We argue that the neighbor features could be highly noisy and partially useful. Thus, a lack of effective neighbor selection will not only incur a great deal of unnecessary computation cost but also restrict the matching accuracy severely. In this work, we propose a novel framework, C ascaded D eep S emantic M atching ( CDSM ), for accurate and efficient semantic matching on textual graphs. CDSM is highlighted for its two-stage workflow. In the first stage, a lightweight CNN-based ad-hod neighbor selector is deployed to filter useful neighbors for the matching task with a small computation cost. We design both one-step and multi-step selection methods. In the second stage, a high-capacity graph-based matching network is employed to compute fine-grained relevance scores based on the well-selected neighbors. It is worth noting that CDSM is a generic framework which accommodates most of the mainstream graph-based semantic matching networks. The major challenge is how the selector can learn to discriminate the neighbors’ usefulness which has no explicit labels. To cope with this problem, we design a weak-supervision strategy for optimization, where we train the graph-based matching network at first and then the ad-hoc neighbor selector is learned on top of the annotations from the matching network. We conduct extensive experiments with three large-scale datasets, showing that CDSM notably improves the semantic matching accuracy and efficiency thanks to the selection of high-quality neighbors. The source code is released at https://github.com/jingjyyao/CDSM.

Power forecasting has a guiding effect on power-aware scheduling strategies to reduce unnecessary power consumption in data centers. Many metrics related to power consumption can be collected in physical servers, such as the status of CPU, memory, and other components. However, most existing methods empirically exploit a small number of metrics to forecast power consumption. To this end, this article uses feature selection based on causality to explore the metrics that strongly influence the power consumption of different tasks. Moreover, we propose a tensor-based dual-stage attention LSTM to forecast the non-linear and non-periodic power consumption. In the proposed model, a multi-way delay embedding transform is utilized to convert the time series into tensors along the temporal direction. The LSTM combines with the tensor technique and the attention mechanism to capture the temporal pattern effectively. In addition, we adopt the cost-sensitive loss function to optimize the specific power forecasting problem in data centers. The experimental results demonstrate that our method can achieve up to 1.4% to 4.3% forecasting accuracy improvement compared with the state-of-the-art models.

Potassium offers the benefits of plentiful supplies, widespread availability, and inexpensive cost. Potassium-ion batteries (KIBs) are thought to be one of the best energy storage technologies to take the place of lithium-ion batteries in the future since potassium has a low electrode potential and rapid ion transport kinetics in the electrochemical system. As opposed to lithium-ion batteries, potassium-ion battery research is still in its early stages, and the system has issues with low capacity, inferior rate performance, and short cycle life. As a result, creating safe, dependable, and high-performance charge-discharge potassium-ion batteries still presents several difficulties. One of the main elements promoting the development of potassium-ion batteries is the development of anode materials for these batteries. At present, there are various methods for constructing potassium-ion battery anode materials, including hydrothermal method, solid phase reaction, electrospinning method, etc. The advancement of electrospinning and the creation of potassium-ion battery anode materials based on electrospinning are the main topics of this review article. This report also anticipates the direction of research and development for high-performance, low-cost anode materials.