结合句法依存信息的方面级情感分类

引入句法依存信息到原方面术语,提出一种新的方面术语表示方法,利用Glove词向量表示单词以及单词与单词之间的依存关系,构造出包含句法依存信息的依存关系邻接矩阵和依存关系表示矩阵,利用图卷积神经网络和多头注意力机制将句法依存信息融入到方面术语中,使得方面术语表达与上下文结构高度相关。将改进后的方面词术语表示替换到现有模型后,模型泛化能力得到有效提升。对比试验和分析结果表明:该方法具有有效性和泛化性。     

Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

Thermal properties of hierarchical YSZ and LZO ceramic microspheres with multi-scaled voids investigated by using theoretical,experimental and simulation methods

Heat transfer within ceramic feedstock powders is still unclear, which impedes optimization of the thermal and mechanical properties of the thermal sprayed coatings. The microspheres (yttria-stabilized zirconia YSZ and lanthanum zirconate LZO) were prepared via the electro-spraying assisted phase inversion method (ESP). The thermal properties of the two ESP microspheres and a commercial hollow spherical powder (HOSP) were investigated by using theoretical, experimental, and simulation methods. Thermal conductivity of the single microsphere was estimated via a novel nest model that was derived from the Maxwell-Eucken 1 and the EMT model. Thermal conductivity of a single YSZ/LZO-ESP microsphere prepared at 1100–1200 °C was within 0.36–0.75 W/m K, which was ～ 20 % lower than that of a single YSZ-HOSP microsphere with a similar porosity. Heat flux simulation showed that high tortuosity around the multi-scaled voids of the ESP microsphere led to a more efficient decrease in thermal conductivity compared with total porosity.     

CT/MR-compatible physical human-robotized needle interactions: From modeling to percutaneous steering

In recent years a number of robotic steering systems have been proposed that are geared towards improving interventional radiology procedures such as tumor ablation and biopsy. These solutions have introduced new safety challenges in the physical human–robot interaction domain. This study presents a new 3D robotized needle steering algorithm compatible with CT and MR-imaging guidance. The steering algorithm is featured with an adaptive self-correction mechanism that works as a failure contingency tool that could be adapted online at each insertion step. The developed pHRI solution was designed to be compatible to ferro-magnetic issues and a reduced workspace inside the scanner bore. As far as we know, this is the first approach designed to steer rigid needles free of force sensors and which meets the challenges that prevail in our context. Our proposed approach helps overcome safety issues regarding the physical interaction between robotized needles and patients. Validation testing highlighted the feasibility of the new needle steering algorithm, while its accuracy revealed the potential of the approach under the proposed scope of application.     

No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion

This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa.     

Steering feel improvement by mathematical modeling of the Electric Power Steering system

Currently, the Electric Power Steering (EPS) system is an essential component of the vehicle because it provides assistive steering torque to the driver. To ensure a faster steering response, the position of the EPS in some vehicles is moved closer to the tire rather than the steering wheel. The steering torque, which is provided by the EPS in the steering system, mainly affects the driver’s feel while steering. Therefore, the driver often feels uncomfortable owing to such positioning of the EPS in the steering system. In particular, the nonlinearity of the Universal Joint (UJ), which is one of parts of the steering system, can be felt at the steering wheel side.In this paper, we proposed an algorithm based on the mathematical model of the steering torque in the steering system to improve the steering feel. The mathematical model is structured using parameters that can be obtained from the information of the steering system. Moreover, the formulation of the steering torque consists of the two parts, namely the deformation part, which describes the propagation inside the steering system, and the friction part that describes the inherent friction in the UJ.Simulation and experiments were conducted to verify the proposed mathematical model with similar conditions to the real tire load during the steering motion. Furthermore, to improve the driver’s feel during steering, a torque compensation algorithm is proposed and verified through experiments.     

Influence of tetraploid wheat (Triticum dicoccum) on low glycaemic index pizza base processing and its starch digestibility

The present study aimed to utilise Dicoccum wheat (DW), barley (BF) and soya flour (SF) in the development of low in vitro starch digestibility (IVSD) and estimated glycaemic index (EGI) PB. The BF and SF are mixed (1:1) (BFSF) and used to replace DW at 25%, 50% and 75% level and compared with 100% DW. The quality characteristics (rheological, physical, textural and chemical), IVSD and EGI of PB were determined. The incorporation of BFSF to DW increased the farinograph water absorption capacity (58.1%–64.2%) and mixing tolerance index (21-68 FU), and decreased the dough development time (4.3–2.8 min) and amylograph pasting properties, respectively. Further, the thickness, shear force and redness were decreased and lightness and yellowness increased. Based on the physico-sensory studies, 50% of BFSF along with emulsifier’s incorporation was optimum without affecting any sensory parameters and this PB had decreased IVSD (31) and EGI (54) when compared to the control 37 and 63, respectively.     

Steerable Microinvasive Probes for Localized Drug Delivery to Deep Tissue

Enhanced understanding of neuropathologies has created a need for more advanced tools. Current neural implants result in extensive glial scarring and are not able to highly localize drug delivery due to their size. Smaller implants reduce surgical trauma and improve spatial resolution, but such a reduction requires improvements in device design to enable accurate and chronic implantation in subcortical structures. Flexible needle steering techniques offer improved control over implant placement, but often require complex closed‐loop control for accurate implantation. This study reports the development of steerable microinvasive neural implants (S‐MINIs) constructed from borosilicate capillaries (OD = 60 µm, ID = 20 µm) that do not require closed‐loop guidance or guide tubes. S‐MINIs reduce glial scarring 3.5‐fold compared to prior implants. Bevel steered needles are utilized for open‐loop targeting of deep‐brain structures. This study demonstrates a sinusoidal relationship between implant bevel angle and the trajectory radius of curvature both in vitro and ex vivo. This relationship allows for bevel‐tipped capillaries to be steered to a target with an average error of 0.23 mm ± 0.19 without closed‐loop control. Polished microcapillaries present a new microinvasive tool for chronic, predictable targeting of pathophysiological structures without the need for closed‐loop feedback and complex imaging.     

基于孪生支持向量回归机的转炉炼钢终点预测

为了提高转炉炼钢的终点命中率，建立了一种新的转炉终点预测模型，实现了对转炉终点碳质量分数和温度的准确预测。模型采用K最近邻孪生支持向量机(KNNWTSVR)算法，将权重矩阵引入到目标函数中，并利用鲸群优化算法进行求解，提高了传统算法的性能；然后基于某炼钢厂260 t转炉的实际生产数据，建立了转炉炼钢终点预测模型。结果表明，预测模型的终点碳质量分数(误差±0.005%)和温度(误差±15 ℃)的终点单命中率分别为94%和88%，双命中率达到84%。与其他两种现有的建模方法相比，本模型取得了最优的预测效果。该方法满足转炉炼钢实际生产的需求，也可适用于钢铁冶金其他领域的数学建模。