estimation

摘要： In the past few years,significant progress has been made in modeling and state estimation for industrial processes to improve control performance,reliable monitoring,quick and accurate fault detection,diagnosis,high product quality,fule and resource consumption,etc.However,with the fast development of information technology,numerous essential issues are faced in modeling and state estimation,which generates the new need for novel modeling and or state estimation methodologies and in-depth studies of them.Therefore,this special issue is dedicated to innovative modeling and state estimation from applicability,computational efficiency,and effectiveness.

摘要： Various time-frequency(T-F)masks are being applied to sound source localization tasks.Moreover,deep learning has dramatically advanced T-F mask estimation.However,existing masks are usually designed for speech separation tasks and are suitable only for single-channel signals.A novel complex-valued T-F mask is proposed that reserves the head-related transfer function(HRTF),customized for binaural sound source localization.In addition,because the convolutional neural network that is exploited to estimate the proposed mask takes binaural spectral information as the input and output,accurate binaural cues can be preserved.Compared with conventional T-F masks that emphasize single speech source–dominated T-F units,HRTFreserved masks eliminate the speech component while keeping the direct propagation path.Thus,the estimated HRTF is capable of extracting more reliable localization features for the final direction of arrival estimation.Hence,binaural sound source localization guided by the proposed T-F mask is robust under noisy and reverberant acoustic environments.The experimental results demonstrate that the new T-F mask is superior to conventional T-F masks and lead to the better performance of sound source localization in adverse environments.

摘要： Sentiment word embedding has been extensively studied and used in sentiment analysis tasks.However,most existing models have failed to differentiate high-frequency and low-frequency words.Accordingly,the sentiment information of low-frequency words is insufficiently captured,thus resulting in inaccurate sentiment word embedding and degradation of overall performance of sentiment analysis.A Bayesian estimation-based sentiment word embedding(BESWE)model,which aims to precisely extract the sentiment information of low-frequency words,has been proposed.In the model,a Bayesian estimator is constructed based on the co-occurrence probabilities and sentiment proba-bilities of words,and a novel loss function is defined for sentiment word embedding learning.The experimental results based on the sentiment lexicons and Movie Review dataset show that BESWE outperforms many state-of-the-art methods,for example,C&W,CBOW,GloVe,SE-HyRank and DLJT1,in sentiment analysis tasks,which demonstrate that Bayesian estimation can effectively capture the sentiment information of low-frequency words and integrate the sentiment information into the word embedding through the loss function.In addition,replacing the embedding of low-frequency words in the state-of-the-art methods with BESWE can significantly improve the performance of those methods in sentiment analysis tasks.

摘要： Dear editor,This letter investigates the recursive state estimation(RSE)problem for a class of coupled output complex networks via the dynamic event-triggered communication mechanism(DETCM)and innovation constraints(ICs).Firstly,a DETCM is employed to regulate the transmission sequences.Then,in order to improve the reliability of network communication,a saturation function is introduced to constrain the measurement outliers.A new RSE method is provided such that,for all output coupling,DETCM and ICs,an upper bound of state estimation error covariance(SEEC)is presented in a recursive form,whose trace can be minimized via parameterizing the state estimator gain matrix(SEGM).Moreover,the theoretical analysis is given to guarantee that the error dynamic is uniformly bounded.Finally,a simulation example is illustrated to show the effectiveness of the proposed RSE method.

摘要： Dear Editor,In this letter,the recursive fault estimation issue is considered for nonlinear time-varying systems subject to the effects induced by energy harvesting sensors and uniform quantization.Based on the energy harvesting mechanism and stochastic distribution of the absorbed energy,the real-time occurrence probability of missing measurements is calculated recursively.This research intends to develop a recursive estimator for the considered nonlinear time-varying system with energy harvesting sensors,such that,under uniform quantization effects,the state and fault can be jointly estimated.By adopting the induction approach,an upper bound is firstly calculated for the estimation error covariances(EECs)of the state and fault.Then,the value of the time-varying estimator parameter is computed through minimizing such calculated upper bound.In the end,an illustrative example is presented to verify the availability of the developed fault estimation method.

摘要： Dear Editor,This letter is concerned with self-supervised monocular depth estimation.To estimate uncertainty simultaneously,we propose a simple yet effective strategy to learn the uncertainty for self-supervised monocular depth estimation with the discrete strategy that explicitly associates the prediction and the uncertainty to train the networks.Furthermore,we propose the uncertainty-guided feature fusion module to fully utilize the uncertainty information.Codes will be available at https://github.com/zhyever/Monocular-Depth-Estimation-Toolbox.Self-supervised monocular depth estimation methods turn into promising alternative trade-offs in both the training cost and the inference performance.However,compound losses that couple the depth and the pose lead to a dilemma of uncertainty calculation that is crucial for critical safety systems.To solve this issue,we propose a simple yet effective strategy to learn the uncertainty for self-supervised monocular depth estimation using the discrete bins that explicitly associate the prediction and the uncertainty to train the networks.This strategy is more pluggable without any additional changes to self-supervised training losses and improves model performance.Secondly,to further exert the uncertainty information,we propose the uncertainty-guided feature fusion module to refine the depth estimation.

摘要： For complex orebodies in which the valuable metal is carried by several minerals that respond differently to the concentration process, an ore block model should not be characterized solely with elemental assays, as this information is not sufficient to anticipate the mill performances. Data from an iron ore concentrator is used to demonstrate the idea. A method is then proposed to estimate the mineral contents of ore samples from elemental assays. The method can readily be extended to combine the estimation of the mineral contents in the feed of the mill with an estimation of the recovery of these minerals into the products of the concentrator. These mineral recoveries can subsequently be incorporated into a block model to predict the concentrator response to the processing of an ore block.

摘要： The rapid development of 5G mobile communication and portable traffic detection technologies enhances highway transportation systems in detail and at a vehicle level. Besides the advantage of no disturbance to the regular traffic operation, these ubiquitous sensing technologies have the potential for unprecedented data collection at any temporal and spatial position. While as a typical distributed parameter system, the freeway traffic dynamics are determined by the current system states and the boundary traffic demand-supply. Using the three-step extended Kalman filtering, this paper simultaneously estimates the real-time traffic state and the boundary flux of freeway traffic with the distributed speed detector networks organized at any location of interest. In order to assess the effectiveness of the proposed approach, a freeway segment from Interstate 80 East (I-80E) in Alameda, Emeryville, and Northern California is selected. Experimental results show that the proposed method has the potential of using only speed detecting data to monitor the state of urban freeway transportation systems without access to the traditional measurement data, such as the boundary flows.

摘要： 为了提高夜间疲劳驾驶检测的准确率,在现有低光增强算法Zero-DCE(Zero-Reference Deep Curve Estimation)的基础上,提出改进Zero-DCE的低光增强算法。首先,引入上下采样结构,减少噪声影响。同时,引入注意力门控机制,提高网络对图像中人脸区域的敏感性,有效提高网络的检测率。然后,针对噪声相关问题,提出改进的核选择模块。进一步,使用MobileNet的深度可分离卷积替换Zero-DCE的标准卷积,提高网络的检测速度。最后,通过人脸关键点检测网络和分类网络,判断驾驶员的疲劳状态。实验表明,在夜间环境下,相比现有的疲劳驾驶检测算法,文中算法在人脸检测的准确率和眼睛状态的识别率上都有所提升,取得较令人满意的检测效果。

摘要： Dear editor,Traffic jams have become an important issue in urban networks, particularly for arterial roads [1]. The need for more efficient traffic control techniques has become critical. One good solution is the so-called intelligent vehicleinfrastructure cooperation systems (i-VICS), which assumes autonomous vehicles in the traffic flow (i.e., a mixed traffic flow). The aim of i-VICS is to achieve cooperative vehicle intersection control, i.e., to enable cooperation between vehicles and traffic signals, for safe and efficient intersection operations.