Genomic evaluation of dairy heifer livability

Differences in breeds and sire lines suggest the presence of a genetic component for heifer livability (HLIV). Genomic evaluation for this trait can increase profitability and improve animal health and welfare. Evaluations for HLIV were examined from 3,362,499 calf data records from heifers of all breeds born from 2009 to 2016. Data were obtained from the national cooperator database maintained by the Council on Dairy Cattle Breeding (https://www.uscdcb.com/). The total number of deaths reported was 134,753 (4.01%), which included herds with death loss between 1.5 and 25.5%. Age at death was evaluated and ranged from >2 d of age until the heifer left the herd, with a maximum of 18 mo of age. Records were not included until 3 yr after the birthdate so that live status of contemporaries could be confirmed by a calving date for those animals. Deaths observed until 2 d after birth were considered to be a stillbirth rather than a failure of HLIV. The scale used for analysis of HLIV was 0 (died) or 100 (live), and the heritability estimate was 0.7% based on sire model with restricted maximum likelihood estimation. Genomic predicted transmitting abilities for Holstein ranged from ?1.6% to +1.6% with a standard deviation of 0.5%, and genomic predicted transmitting abilities for Jersey ranged from ?0.5% to +0.5% with a standard deviation of 0.2%. The mean overall death loss was about 4%. Reliabilities of genomic predictions for young animals averaged 46% for Holsteins and 30% for Jerseys, and corresponding traditional parent average reliabilities averaged 16% and 12%, respectively. Correlations of HLIV were 0.44 with productive life, 0.18 to 0.22 with yield traits, and 0.29 with early first calving on proven Holstein bulls. The HLIV trait had a favorable genetic trend in recent years, likely because of the indirect selection associated with the correlated traits. The trait HLIV should receive 1% of emphasis on the Lifetime Net Merit index, resulting in economic progress worth $50,000/yr. By encouraging more comprehensive recording on calf mortality, the reliabilities of genetic predictions could increase significantly.     

Enthalpy- versus Entropy-Driven Molecular Recognition in the Era of Biologics

Our laboratory has recently identified two nanobodies (small antibodies produced by camelids)—Nb1 and Nb6—that bind efficiently to epithelial growth factor (EGF) and inhibit its ability to activate its receptor (EGFR). Because of the relevance of the EGF/EGFR axis as a target in oncology, these new nanobodies have promising therapeutic potential. This article, however, is focused on another feature of these nanobodies: their distinct thermodynamic signatures. Nb1 binds to EGF through an entropy-driven mechanism whereas Nb6 binds to this factor under enthalpic control. We discuss the advantages and disadvantages of each mechanism in the contexts of traditional medical chemistry (small-molecule drugs) and also of biological drugs. In this latter case, the implications in terms of selectivity are far from being clearly established and further experimental data are required. Their monomeric natures, high stability, and ease of recombinant production make nanobodies ideally suited for thermodynamic studies. Moreover, nanobodies, thanks to their simpler structures in comparison with conventional antibodies, might provide better understanding of the structural basis of the thermodynamic parameters of antigen recognition.     

Selective nonanal molecular recognition with SnO2 nanosheets for lung cancer sensor

SnO₂ nanosheets were developed to detect nonanal gas in the order of ppb which was a marker of lung cancer. The nanosheets showed higher resistance change in nonanal gas than that in carbon monoxide (CO), nitrogen dioxide (NO₂), acetone (CH₃COCH₃), hydrogen (H₂), ethanol (C₂H₆O), ammonia (NH₃), hydrogen sulfide (H₂S), formaldehyde (HCHO), acetaldehyde (CH₃CHO), or butanal (C₄H₈O). Crystal surfaces of the nanosheets would be effective for adsorption of nonanal molecules. Furthermore, it was shown that resistance changed with an increase in carbon number in aldehyde. The nanosheets had molecular selectivity for a series of aldehyde molecules. Molecular recognition of the nanosheets gave us a great advantage to detect nonanal gas which was produced by lung cancer.     

基于人体关节点数据的攻击性行为识别

针对人体攻击性行为识别问题，提出一种基于人体关节点数据的攻击性行为识别方法。首先，利用OpenPose获得单帧图像中的人体关节点数据，并通过最近邻帧特征加权法和分段多项式回归完成由人体自遮挡和环境因素所导致缺失值的补全；然后，对每个人体定义动态"安全距离"阈值，如果两人真实距离小于阈值，则构建行为特征矢量，其中包括帧间人体重心位移、人体关节旋转角角速度和发生交互时的最小攻击距离等；最后，提出改进的LightGBM算法w-LightGBM，并对攻击性行为进行识别。采用公共数据集UT-interaction对所提出的攻击性行为分类识别方法进行测试实验，准确率达到95.45%。实验结果表明，所提方法能够有效识别各种角度的攻击性行为。     

Emotion recognition at the edge with AI specific low power architectures

Nowadays Deep Learning is applied in almost every research field and helps getting amazing results in a great number of challenging tasks. The main problem is that this kind of learning and consequently Neural Networks that can be defined deep, are resource intensive. They need specialized hardware to perform computation in a reasonable time. Many tasks are mandatory to be as much real-time as possible . It is needed to optimize many components such as code, algorithms, numeric accuracy and hardware, to make them “efficient and usable”. All these optimizations can help us to produce incredibly accurate and fast learning models. The paper reports a study in this direction for the challenging face detection and emotion recognition tasks.     

Flow regime recognition in a long pipeline-riser system based on signals at the top of the riser

To identify conveniently multiphase flow regimes in subsea pipeline-risers, we study in this paper experimentally two-phase flows in a 1657 m long pipeline with an S-shaped riser to simulate field experiment, within a wide range of gas and liquid velocities. Three flow regimes, namely severe slugging, transitional flows, and stable flows, are analyzed based on three differential pressure and one pressure signals at the top of the riser; comparatively speaking, the positions of these signals in the experimental system are similar to those of the sea level signals in industrial fields, which are easy and less expensive to obtain. The obtained signals are decomposed into six scales via a multi-scale wavelet analysis, and further four statistical parameters on each scale are extracted, including mean values, standard deviations, ranges, and mean values of absolute. We compared the effects of six SVM classifiers with different kernel functions on the recognition rate of flow regimes, and it is found the recognition rates of SVM classifier with quadratic and cubic kernel functions are the highest. Further, the principal component analysis is employed to reduce the dimension of statistical parameters and it indicates that the recognition rate tends to increase with the rising number of principal components from 1 to 6, and it remains constant if the principal component number is further increased. Moreover, The results suggest that the recognition rate obtained from the pressure difference between the top of the riser and the separator peaks, and then it comes that from the pressure signal at the top of the riser, and that for the pressure difference signal at the top of the riser is the least satisfying one. As for the optimal differential pressure signals between the top of the riser and the separator, the results show that the recognition rate increases rapidly from 70.2% to 90.4% when the sample duration rising from 2.3 s to 18.6 s, and when the sample duration exceeds 74.4 s, the recognition rate exceeds 92.9% and remains unchanged.     

Image-Based Lifelogging: User Emotion Perspective

Lifelog is a digital record of an individual’s daily life. It collects, records, and archives a large amount of unstructured data; therefore, techniques are required to organize and summarize those data for easy retrieval. Lifelogging has been utilized for diverse applications including healthcare, self-tracking, and entertainment, among others. With regard to the image-based lifelogging, even though most users prefer to present photos with facial expressions that allow us to infer their emotions, there have been few studies on lifelogging techniques that focus upon users’ emotions. In this paper, we develop a system that extracts users’ own photos from their smartphones and configures their lifelogs with a focus on their emotions. We design an emotion classifier based on convolutional neural networks (CNN) to predict the users’ emotions. To train the model, we create a new dataset by collecting facial images from the CelebFaces Attributes (CelebA) dataset and labeling their facial emotion expressions, and by integrating parts of the Radboud Faces Database (RaFD). Our dataset consists of 4,715 high-resolution images. We propose Representative Emotional Data Extraction Scheme (REDES) to select representative photos based on inferring users’ emotions from their facial expressions. In addition, we develop a system that allows users to easily configure diaries for a special day and summaize their lifelogs. Our experimental results show that our method is able to effectively incorporate emotions into lifelog, allowing an enriched experience.     

基于多尺度双线性卷积神经网络的多角度下车型精细识别

针对多角度下车辆出现一定的尺度变化和形变导致很难被准确识别的问题，提出基于多尺度双线性卷积神经网络（MS-B-CNN）的车型精细识别模型。首先，对双线性卷积神经网络（B-CNN）算法进行改进，提出MS-B-CNN算法对不同卷积层的特征进行了多尺度融合，以提高特征表达能力；此外，还采用基于中心损失函数与Softmax损失函数联合学习的策略，在Softmax损失函数基础上分别对训练集每个类别在特征空间维护一个类中心，在训练过程中新增加样本时，网络会约束样本的分类中心距离，以提高多角度情况下的车型识别的能力。实验结果显示，该车型识别模型在CompCars数据集上的正确率达到了93.63%，验证了模型在多角度情况下的准确性和鲁棒性。