机器翻译译文质量估计综述

机器翻译译文质量估计(Quality Estimation,QE)是指在不需要人工参考译文的条件下,估计机器翻译系统产生的译文的质量,对机器翻译研究和应用具有很重要的价值。机器翻译译文质量估计经过最近几年的发展,取得了丰富的研究成果。该文首先介绍了机器翻译译文质量估计的背景与意义;然后详细介绍了句子级QE、单词级QE、文档级QE的具体任务目标、评价指标等内容,进一步概括了QE方法发展的三个阶段: 基于特征工程和机器学习的QE方法阶段,基于深度学习的QE方法阶段,融入预训练模型的QE方法阶段,并介绍了每一阶段中的代表性研究工作;最后分析了目前的研究现状及不足,并对未来QE方法的研究及发展方向进行了展望。     

Parameter study for dimensioning of a PV optimized hydrogen supply plant

Green hydrogen produced from intermittent renewable energy sources is a key component on the way to a carbon neutral planet. In order to achieve the most sustainable, efficient and cost-effective solutions, it is necessary to match the dimensioning of the renewable energy source, the capacity of the hydrogen production and the size of the hydrogen storage to the hydrogen demand of the application.For optimized dimensioning of a PV powered hydrogen production system, fulfilling a specific hydrogen demand, a detailed plant simulation model has been developed. In this study the model was used to conduct a parameter study to optimize a plant that should serve 5 hydrogen fuel cell buses with a daily hydrogen demand of 90 kg overall with photovoltaics (PV) as renewable energy source. Furthermore, the influence of the parameters PV system size, electrolyser capacity and hydrogen storage size on the hydrogen production costs and other key indicators is investigated. The plant primarily uses the PV produced energy but can also use grid energy for production.The results show that the most cost-efficient design primarily depends on the grid electricity price that is available to supplement the PV system if necessary. Higher grid electricity prices make it economically sensible to invest into higher hydrogen production and storage capacity. For a grid electricity price of 200 €/MWh the most cost-efficient design was found to be a plant with a 2000 kWp PV system, an electrolyser with 360 kW capacity and a hydrogen storage of 575 kg.     

Prediction of fish quality level with machine learning

In this study, sea bream, sea bass, anchovy and trout were captured and recorded using a digital camera during refrigerated storage for 7 days. In addition, their total viable counts (TVC) were determined on a daily basis. Based on the TVC, each fish was classified as ‘fresh’ when it was <5 log cfu per g, and as ‘not fresh’ when it was >7 log cfu per g. They were uploaded on a web-based machine learning software called Teachable Machine (TM), which was trained about the pupils and heads of the fish. In addition, images of each species from different angles were uploaded to the software in order to ensure the recognition of fish species by TM. The data of the study indicated that the TM was able to distinguish fish species with high accuracy rates and achieved over 86% success in estimating the freshness of the fish species tested.     

Simulation of interaction between high-temperature process and heat emission from electricity system in summer

During the hot summer season, using electricity systems increases the local anthropogenic heat emission, further increasing the temperature. Regarding anthropogenic heat sources, electric energy consumption, heat generation, indoor and outdoor heat transfer, and exchange in buildings play a critical role in the change in the urban thermal environment. Therefore, the Weather Research and Forecasting (WRF) Model was applied in this study to investigate the heat generation from an indoor electricity system and its influence on the outdoor thermal environment. Through the building effect parameterization (BEP) of a multistorey urban canopy scheme, a building energy model (BEM) to increase the influence of indoor air conditioning on the electricity consumption system was proposed. In other words, the BEP+BEM urban canopy parameterization scheme was set. High temperatures and a summer heat wave were simulated as the background weather. The results show that using the BEP+BEM parameterization scheme of indoor and outdoor energy exchange in the WRF model can better simulate the air temperature near the surface layer on a sunny summer. During the day, the turning on the air conditioning and other electrical systems have no obvious effect on the air temperature near the surface layer in the city, whereas at night, the air temperature generally increases by 0.6 ℃, especially in densely populated areas, with a maximum temperature rise of approximately 1.2 ℃ from 22:00 to 23:00. When the indoor air conditioning target temperature is adjusted to 25–27 ℃, the total energy release of the air conditioning system is reduced by 12.66%, and the temperature drops the most from 13:00 to 16:00, with an average of approximately 1 ℃. Further, the denser the building is, the greater the temperature drop.     

Powder sintering and gel casting methods in making glass foam using waste glass: A review on parameters,performance, and challenges

The application of insulation materials in buildings and energy storage facilities is gaining global attention to reduce energy consumption, heat loss, and CO₂ emissions. Given the high insulation performance, glass foam is gaining popularity replacing combustible, high energy-consuming, and costly conventional insulation materials. The industrial process of glass foam manufacturing is an energy-consuming and non-ecofriendly process which requires the annealing of glass around its melting temperature. Therefore, researchers have developed powder sintering and gel casting methods to sinter glass foam mix at a temperature slightly above its glass transition point. However, research findings on these two methods are scattered because of the different parameters being used by researchers. The properties and performances of glass foam depend on the processing parameters, especially on the materials design and sintering conditions. Therefore, this study aimed to provide a comprehensive review on the key parameters for material selection and sintering of glass foams and provide necessary guidelines for the best practice and a direction for future research. Moreover, this review covers the current strategies and challenges associated with the powder sintering and gel casting methods including their sustainability and environmental performance.     

Pattern design and optimization of yarn-dyed plaid fabric using isolation niche genetic algorithm and rough set theory

Under the circumstance of perceptual consumption, it is still challenging to grasp consumer's emotions and demands due to the large search space, diversified preferences, and easy fatigue of consumers. To reduce user fatigue and enlarge search space, a novel method was presented to design and optimize the pattern of yarn-dyed plaid fabric using the isolation niche genetic algorithm and rough set theory. Each pattern was encoded as a chromosome based on the real number code. The population was initialized and evolved using INGA to maintain the diversity. The rough set theory was adopted as the fitness function of isolation niche genetic algorithm to extract the consumer's demands. After multiple evolutions, a large set of practical patterns of the yarn-dyed plaid fabric are obtained. Experiments were carried out by 24 testers of different ages and genders. The results prove that the proposed method based on the isolation niche genetic algorithm and rough set theory is feasible and effective, supplying references to the designer.     

雪菊精油对希氏肠球菌产酪胺及相关基因表达的影响

探讨不同质量浓度雪菊精油对希氏肠球菌（Enterococcus hirae）N47产酪胺的影响机制。利用反转录实时定量聚合酶链式反应分析E. hirae在雪菊精油作用下酪氨酸脱羧途径相关基因的表达情况；利用高效液相色谱法检测不同质量浓度雪菊精油对E. hirae产酪胺的影响。并将E. hirae接入到含不同质量浓度雪菊精油的熏马肠中发酵，评估香肠pH值、菌落总数和酪胺积累量。结果表明：在E. hirae纯培养体系和熏马肠体系中，雪菊精油通过抑制微生物的生长和酪氨酸脱羧途径中tyr DC、tyr P基因的表达，降低酪胺的积累量（P＜0.05）。当雪菊精油添加量为1/2最小抑菌浓度（minimal inhibitory concentration，MIC）和MIC时，熏马肠中酪胺的含量分别为78.52 mg/kg和45.83 mg/kg，较对照组分别减少了64.72%和79.41%。     

基于乙酰胆碱酯酶和氧化应激研究海胆酮对阿尔茨海默症的作用机制

海胆酮是一种酮式类胡萝卜素，主要从海胆及藻类等海洋生物中提取。本文研究海胆酮对乙酰胆碱酯酶（acetylcholinesterase，AChE）的抑制作用，应用酶动力学、荧光光谱、圆二色光谱和分子对接技术研究海胆酮对AChE的抑制机理，并用淀粉样β蛋白片段25～35（amyloid beta-peptide 25-35，Aβ25-35）诱导大鼠肾上腺嗜铬细胞瘤细胞（PC12细胞）建立阿尔茨海默症（Alzheimer’s disease，AD）模型，研究海胆酮对AD细胞模型氧化应激损伤的作用。结果表明，海胆酮有很强的AChE抑制活性，其半抑制质量浓度为（16.29±0.97）μg/mL，抑制常数Ki为3.82 μg/mL，表现为竞争性抑制；海胆酮可诱导AChE二级结构改变，更容易与AChE活性中心氨基酸Ser200、His440、Trp84和Tyr121结合，阻碍底物碘代硫代乙酰胆碱（acetylthiocholine iodide，ATCI）与酶结合，从而引起酶活力降低。海胆酮能有效抑制Aβ25-35诱导PC12细胞的AChE活力，降低丙二醛含量，增加超氧化物歧化酶、过氧化氢酶和谷胱甘肽过氧化物酶活力，减轻Aβ25-35诱导的PC12细胞氧化应激损伤。本研究基于AChE和氧化应激阐明了海胆酮对AD的潜在作用机制，为海胆酮在功能食品、生物医药等领域的应用提供了数据支持和理论根据。     

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.     

基于改进SOA-VMD的磁声发射信号去噪算法

磁声发射（MAE）是铁磁性材料磁化过程中产生的声发射信号，在构件应力检测和微观损伤检测中有着广泛的应用。针对MAE信号非稳态、复杂性、衰减性等特点，提出海鸥算法结合变分模态分解（SOA-VMD）的去噪方法，为克服海鸥算法求解过程中易陷入局部最优解问题，利用柯西变异算子产生随机迭代过程，使改进算法即柯西变异海欧算法（CVSOA）跳出早熟收敛。采用以幅值谱熵为适应度函数，优化VMD算法中分解模态个数K和二次惩戒因子α两个参数，将含噪声的MAE信号进行VMD分解重构。经仿真信号和实际检测信号分析表明，改进后的CVSOA-VMD算法全局寻优能力和去噪性能优于传统的SOA-VMD算法，降噪后的MAE信号特征值对于不同应力下均方根、偏斜度特征值的重复性更好，可靠性更高。