Blind quality assessment for screen content images via convolutional neural network

With the wide propagation of cloud and mobile computing, screen content images (SCIs) have become more indispensable in our daily lives. Compared to natural scene images (NSIs), SCIs possess many particular characteristics, like mixed contents, extremely sharp edges, and text graphics. Consequently, more challenges occur in the feature extraction, which is used to reflect the distortion, during the quality assessment of SCIs. Recently, some convolutional neural network (CNN) models have been designed by automatically learning feature to evaluate the quality. In this paper, we develop a novel blind quality assessment method for SCIs via the CNN. First, compared with existing CNN-based methods, the proposed method avoids the disadvantage of training with image patches, and it is the pioneering attempt that takes the entire image as inputs. Second, instead of the image gray value, the original image is decomposed into two portions, i.e., the predicted and unpredicted portions, according to the internal generative mechanism (IGM) theory as the input of CNN. Through the CNN, all features of the image are learned automatically from beginning to end, and the network finally outputs the predicted score. Since existing SCI database is too small, to fully train the network, we collected 30000 SCIs and employed a high-accuracy full-reference quality assessment metric of SCI to compute scores as the training labels. Experimental results on SIQAD database demonstrate that the proposed method is comparable to reference-based SCI quality assessment metrics and is superior to the state-of-the-art NSI quality assessment metrics.     

Convolutional neural network: Deep learning-based classification of building quality problems

The rapid development of the construction industry in China has introduced unprecedented quality-related problems in the country’s building industry. In response to this issue, the government has established various complaint channels to report quality problems. Therefore, building quality complaints (BQCs) need to be classified and solved by respective agencies or departments rapidly for avoiding adverse impact on the safety, health, and well-being of people. However, the current process of classifying BQCs is labor intensive, time consuming, and error prone. An automatic complaint classification is required to improve the effectiveness and efficiency of complaint handling, but studies on this issue are limited. Prevailing text classification research in construction has focused on utilizing conventional shallow machine learning. By contrast, this study explores a novel convolutional neural network (CNN)-based approach that incorporates a deep-learning method to automatically classify the short texts contained within BQCs. The presented approach enables capturing the semantic features in BQC texts and automatic classification of the BQCs into predefined categories. After the model optimization, tests are conducted to examine the practical application of the text classification approach compared with Bayes-based and support vector machine classifiers. Results indicate that the developed CNN-based approach performs well in the Chinese BQC classification with limited manual intervention and few complicated feature engineering.     

镍基高温合金液相扩散焊接头组织及性能

镍基高温合金GH4413在高温下具有较为优异的高温持久强度和抗蠕变性能，在航空发动机和各种工业燃气轮机中得到广泛应用。以BNi 2作为填充合金材料使用液相扩散焊对GH4413合金进行了连接，研究了在焊接温度分别为1 030和1 080 ℃、保温时间分别为30和60 min等不同焊接参数下GH4413镍基高温合金的接头微观组织、成分分布和显微硬度。扫描电镜(SEM)以及能谱分析结果表明，当焊接温度为1 080 ℃、保温时间为60 min 时，钎缝组织中形成了性能良好的固溶体，且随着焊接温度的升高和保温时间的延长，钎缝的宽度增加，钎料元素向母材中的扩散深度逐渐增加，在母材近缝区形成了金属间化合物。     

Effect of permanent magnet stirring on internal quality of steel

Permanent magnet stirring (PMS) featuring low power dissipation and high-intensity magnetic field was investigated as a means of decreasing internal solidification defects. In this study, the magnetic Taylor number (Ta) was used to quantify the melt ?ow. Initial research of PMS involved a laboratory study of the solidification of Sn–20 wt-% Pb alloy. An industrial plant trial with continuously cast tire cord steel confirmed that PMS, in accord with the laboratory findings, produced an improvement in central cavities in the cast product. Moreover, it was established that PMS is an alternative method for reducing carbon macrosegregation in tire cord steel billets with different section sizes. It was also found that PMS (Ta?=?8.97?×?10⁷) was more effective for improving central carbon macrosegregation of tire cord steel than electromagnetic stirring (Ta?=?6.33?×?10⁷) due to the larger Ta related to the driven-flow intensity of the residual melt.     

Effects of pineapple pomace fibre on physicochemical properties of composite flour and dough,and consumer acceptance of fibre‐enriched wheat bread

Pineapple pomace fibre (PF, containing 70.2% total dietary fibre) can be added to increase dietary fibre of wheat bread. This study was performed to evaluate effects of PF added at 0, 5 or 10% (wheat flour‐basis) on physicochemical properties of the composite flour (wheat flour as the control, CPF‐5 and CPF‐10, respectively) and its dough, to evaluate consumer acceptance of CPF breads and to identify factors affecting willingness to purchase of CPF breads. Incorporating PF affected rheological and pasting properties of CPF. Water‐ and oil‐holding capacity of CPF increased (P < 0.05) as PF levels increased. Bread made with CPF‐5 was more acceptable than that with CPF‐10; however, it was not significantly different from the control, having similar specific volume and texture, but having about three times higher total dietary fibre than the control (4.4% vs. 1.5%). Product label and health benefit information potentially affected consumers' willingness to purchase of fibre‐enriched bread.     

VEGF and FGF2 Improve Revascularization,Survival, and Oocyte Quality of Cryopreserved,Subcutaneously-Transplanted Mouse Ovarian Tissues

This study was conducted to investigate the effect of the vascular endothelial growth factor (VEGF) and fibroblast growth factor 2 (FGF2) on revascularization, survival, and oocyte quality of cryopreserved, subcutaneously-transplanted mouse ovarian tissue. Autologous subcutaneous transplantation of vitrified-thawed mouse ovarian tissues treated with (experimental group) or without (control group) VEGF and FGF2 was performed. After transplantation to the inguinal region for two or three weeks, graft survival, angiogenesis, follicle development, and oocyte quality were examined after gonadotropin administration. VEGF coupled with FGF2 (VEGF/FGF2) promoted revascularization and significantly increased the survival rate of subcutaneously-transplanted cryopreserved ovarian tissues compared with untreated controls. The two growth factors did not show long-term effects on the ovarian grafts. In contrast to the untreated ovarian grafts, active folliculogenesis was revealed as the number of follicles at various stages and of mature oocytes in antral follicles after gonadotropin administration were remarkably higher in the VEGF/FGF2-treated groups. Although the fertilization rate was similar between the VEGF/FGF2 and control groups, the oocyte quality was much better in the VEGF/FGF2-treated grafts as demonstrated by the higher ratio of blastocyst development. Introducing angiogenic factors, such as VEGF and FGF2, may be a promising strategy to improve revascularization, survival, and oocyte quality of cryopreserved, subcutaneously-transplanted mouse ovarian tissue.     

A wavelet-based autoregressive fuzzy model for forecasting algal blooms

This paper proposes fuzzy models for forecasting the complex behavior of algal blooms. The models are developed through the integration of autoregressive models, the Takagi-Sugeno fuzzy model, and discrete wavelet transform algorithms. The premise parts of the proposed models are determined using the subtractive clustering technique and the consequent parts are optimized using weighted least squares. To train and validate the proposed fuzzy models, a large number of data sets were collected from Daecheong reservoir in Geum River in the Republic of Korea. The data include both water quality and hydrological variables. Total nitrogen, total phosphorous, dissolved oxygen, chemical oxygen demand, biochemical oxygen demand, pH, air temperature, water temperature and outflow water were evaluated as input signals while chlorophyll-a was used as an output. It is demonstrated from the simulation that the proposed fuzzy models are effective in forecasting algal blooms.     

A Bayesian network incorporating observation error to predict phosphorus and chlorophyll a in Saginaw Bay

Empirical relationships between lake chlorophyll a and total phosphorus concentrations are widely used to develop predictive models. These models are often estimated using sample averages as implicit surrogates for unknown lake-wide means, a practice than can result in biased parameter estimation and inaccurate predictive uncertainty. We develop a Bayesian network model based on empirical chlorophyll-phosphorus relationships for Saginaw Bay, an embayment on Lake Huron. The model treats the means as unknown parameters, and includes structure to accommodate the observation error associated with estimating those means. Compared with results from an analogous simple model using sample averages, the observation error model has a lower predictive uncertainty and predicts lower chlorophyll and phosphorus concentrations under contemporary lake conditions. These models will be useful to guide pending decision-making pursuant to the 2012 Great Lakes Water Quality Agreement.     

Study of the impact of a new hurdle technology composed of electro‐activated solution and low heat treatment on the canned pea and corn quality and microbial safety

The objective of this work was to evaluate the quality of sterilised canned pea and corn in electro‐activated brine solutions at moderate temperatures. The lowest change in vitamin C was associated with the lowest heat treatment, while the short treatment time resulted in significant changes in texture and colour of vegetables. Best texture profile was obtained with the acid electro‐activated brine solution for pea and corn. The neutral electro‐activated brine solution resulted in a less firm texture for pea and corn. The green colour and brightness of canned pea were higher when neutral solution was used (a* = ?8.4 ± 0.3) than for the acidic one (a* = ?3.7 ± 0.6). The yellowness of corn was better with the neutral electro‐activated brine solution (b* = 36.32 ± 1.24) than with the acidic one (b* = 28.44 ± 2.39). Thirty‐three percent decrease of energy consumption was obtained using the electro‐activation technology.     

浅谈谱质心对弹拨乐单音悦耳度的影响

探讨了民族弹拨乐器声学特性的客观参数中,衡量能量分布的谱质心参数与主观听觉悦耳度之间的联系.挑选了一些常见的民族弹拨乐器的单音进行音质主观评价,利用多元统计分析方法将整理的主观评价数据与谱质心的客观参数进行拟合,较全面地了解谱质心对民族弹拨乐单音悦耳度的影响.对民族乐器客观分析研究做了初期探究基础,为专家学者广泛研究民族乐器声学领域提供参考.