The ability of eye-tracking metrics to classify and predict the perceived driving workload

Traffic safety is directly related to the mental and physical condition of the driver. Performing regular secondary tasks while driving is an additional activity that dissipates attention and adds to the drivers' workload. Identifying driver fatigue and workload based on gaze behavior is one way to ensure a safe driving experience. The purpose of this paper is to classify and predict driving perceived workload using a set of eye-tracking metrics (gaze fixation, duration, pointing, and pupil diameter). The ability of eye-tracking metrics to predict driving workload has been investigated. As a result, frustration, performance, and temporal load showed a correlation with gaze metrics. Gaze point, duration, fixation, and pupil diameter significantly influence driving workload.Relevance to industry: Results will supply the specialists in eye-tracking/sensor technologies and traffic safety with new knowledge to improve the design of the driving performance and safety monitoring systems and efficiency of the driving process.     

Intelligent tool wear monitoring based on parallel residual and stacked bidirectional long short-term memory network

Effective tool wear monitoring (TWM) is essential for accurately assessing the degree of tool wear and for timely preventive maintenance. Existing data-driven monitoring methods mainly rely on complex feature engineering, which reduces the monitoring efficiency. This paper proposes a novel TWM model based on a parallel residual and stacked bidirectional long short-term memory (PRes–SBiLSTM) network. First, a parallel residual network (PResNet) is used to extract the multi-scale local features of sensor signals adaptively. Subsequently, a stacked bidirectional long short-term memory (SBiLSTM) network is used to obtain the time-series features related to the tool wear characteristics. Finally, the predicted tool wear value is outputted through a fully connected network. A smoothing correction method is applied to improve the prediction accuracy. The proposed model is experimentally verified to have a high prediction accuracy without sacrificing its generalization ability. A TWM system framework based on the PRes–SBiLSTM network is proposed, which has a certain reference value for TWM in actual industrial environments.     

Thermodynamic calculation of S−Sb system and Cu−S−Sb system

Sb₂S₃ and CuSbS₂ have been proposed as alternative earth-abundant absorber materials for thin-film solar cells. However, no thermodynamic study of the S−Sb binary system and the Cu−S−Sb ternary system were investigated. In this paper, The S−Sb system and the Cu−S−Sb system are calculated utilizing the so-called CALPHAD (CALculation of PHAse Diagrams) technique. Using TEM-EDS and XRD, Cu_0.9Sb₁S₂ is experimentally confirmed at the Cu₁Sb₁S₂ and Sb₂S₃ two-phases region in the isothermal section at 673 K of the Cu−S−Sb ternary system. Given the asymmetric shape and miscibility gap of the liquidus in the S−Sb phase diagram, the associate solution model for the liquid phase is adopted. The solution phases (liquid, bcc, fcc) are treated with the Redlich–Kister equation. The compounds S₃Sb₂, Cu₃SbS₃, Cu₁₂Sb₄S₁₃, CuSbS₂, and Cu₃SbS₄ are described as a stoichiometric compound. A set of self-consistent thermodynamic parameters of the S−Sb binary system and the Cu−S−Sb ternary system are obtained. The calculated results are in good agreement with the experimental data. This study provides a set of reliable thermodynamic parameters to the Cu−Sb−S thermodynamic database, and a cost-effective tool to design material synthesis experiments and manufacturing processes.     

Adoption of human metabolic processes as Data Quality Based Models

The Journal of Supercomputing - The buildup of huge data within business intelligence is essential because such data includes complete conceptual and technological stack in addition to raw and...     

Intelligent monitor for typhoon in IoT system of smart city

The Journal of Supercomputing - Accidents often occur in the earth—typhoons, floods, earthquakes, traffic accidents and so on. Whether these accidents can be timely and effectively responded...     

FHUQI-Miner: Fast high utility quantitative itemset mining

Applied Intelligence - High utility itemset mining is a popular pattern mining task, which aims at revealing all sets of items that yield a high profit in a transaction database. Although this task...     

Software defect prediction model based on LASSO–SVM

Neural Computing and Applications - A software defect report is a bug in the software system that developers and users submit to the software defect library during software development and...     

Investigation of multiple heterogeneous relationships using a q-rung orthopair fuzzy multi-criteria decision algorithm

Neural Computing and Applications - Q-rung orthopair fuzzy (q-ROF) set is one of the powerful tools for handling the uncertain multi-criteria decision-making (MCDM) problems, various MCDM methods...     

An improved generative adversarial network for translating clothes from the human body to tiled image

Neural Computing and Applications - Nowadays, purchasing the products similar to the styles of stars’ products has become a new trend in e-commerce platforms. Clothing transaction constitutes...     

采空区自然发火监测系统的设计

针对现有的采空区自然发火监测方式成本高、易出现故障、维护困难且有线传输方式不可靠的问题,采用无线射频技术和CAN总线技术设计了一种采空区自然发火监测系统,详细介绍了系统的整体架构,主要硬件部分的设计,以及无线通信频率、探头工作时序、无线接收分站工作流程、无线路由控制协议等关键技术的实现等。测试结果表明,该系统组网快速,当两探头间距小于150 m时能够对各监测节点处的温度数据进行实时采集及可靠传输,工作寿命达90 d。