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。     

Visually deficient working conditions and reduced work performance in office workers: Is it mediated by visual discomfort?

IntroductionThe main purpose of this cross-sectional study was to investigate whether visual discomfort acts as a mediating factor between perceived visual ergonomic working conditions and self-rated visual performance among office workers who carry out administrative tasks and computer-based work at the Swedish Tax Agency.MethodsA questionnaire was sent to 94 office workers addressing: 1) perceived visual quality of the visual display units; 2) prevalence of eye symptoms; and 3) self-rated visual performance. Eighty-six persons (54 women (63%), 31 men (36%), and 1 of unspecified sex) answered the questionnaire. Multiple regression analysis investigated the association between visual ergonomic working conditions and visual performance, both with and without visual discomfort as a mediator.ResultsThe group mean of the Indexed survey questions indicated a reasonably good quality of visual ergonomic working conditions, a relative absence of eye symptoms, and acceptable self-rated visual performance. Results from multiple regression analysis showed a significant association between perceived visual ergonomic working conditions and self-rated visual performance (r² = 0.30, β = 0.327, p < 0.01). When visual discomfort was used as a mediator, the association between perceived visual ergonomic working conditions and self-rated visual performance remained the same (r² = 0.32, β = 0.315, p < 0.01).DiscussionIt was remarkable to discover that self-rated visual performance was independent of visual discomfort. Possible explanations include exposure factors not included in the current study, such as dry air and sensory irritation in the eyes, psychosocial stress, time spent performing near work activities, or time exposed to visually deficient working conditions.Relevance to industryThe strong connection between satisfaction with visual ergonomic working conditions and productivity in this study has implications for workplace profitability and staff satisfaction. If productivity is enhanced by better visual ergonomic working conditions, then managers of workplaces may be able to improve work outcomes by optimizing the physical work environment.     

Antenna selection for MIMO system based on pattern recognition

This paper proposes a novel Multiple-Input Multiple-Output (MIMO) transmission scheme based on Pattern Recognition (PR), which is termed as the PR aided Transmission Antenna Selection MIMO (PR-TAS aided MIMO). As the conventional TAS algorithms need to search all possible legitimate antenna subsets, they may impose some redundant calculations. In order to avoid this problem, we employ some pattern recognition methods to carry out the TAS algorithm in this paper. To be specific, two PR algorithms, namely the K-Nearest Neighbor (KNN) algorithm and the Support Vector Machine (SVM) algorithm, are introduced and redesigned to obtain a TAS with lower complexity but higher efficiency. Moreover, in order to improve the performance of the SVM, we propose a new feature extraction of channel matrix for the TAS. Our simulation results show that the proposed KNN and SVM based PR-TAS algorithms are capable of striking a flexible tradeoff between the complexity and the Bit Error Rate (BER), and the new feature can effectively improve the BER performance compared with the conventional feature extraction method.     

基于深度学习的四旋翼无人机单目视觉避障方法

针对无人机避障问题，提出一种基于深度学习的四旋翼无人机单目视觉避障方法。首先通过目标检测框选出目标在图像中的位置，并通过计算目标选框上下边距的长度，以此来估量出障碍物到无人机之间的距离；然后通过协同计算机判断是否执行避障动作；最后使用基于Pixhawk搭建的飞行实验平台进行实验。实验结果表明，该方法可用于无人机低速飞行条件下避障。该方法所用到的传感器只有一块单目摄像头，而且相对于传统的主动式传感器避障方法，所占用无人机的体积大幅减小。该方法鲁棒性较好，能够准确识别不同姿态的人，实现对人避障。     

面向智能客服的句子相似度计算方法

针对金融领域中智能客服的句子相似度计算方法进行了研究。利用基于词性的分词纠正模型减少中文歧义词、金融相关词汇的分词错误；通过词向量方法和循环神经网络分别提取词语级和句子级的语义特征，并且得到句子向量；用融合层计算出句子向量间的差异特征；对差异特征进行降维和归一化得到句子相似度计算结果。实验结果表明，该方法具有较高的准确率和[F1]值。     

基于支持向量机的RSA电磁旁路分析方法

针对在旁路分析过程中由于噪声的影响，不能直接观察出RSA的加密过程这一问题，提出结合支持向量机的旁路分析方法，从分类的角度对RSA二进制模幂运算中的平方、乘法操作进行识别，根据密钥与操作的相关性，推断出RSA二进制密钥序列。基于此，对移动设备PCM-9589F凌动主板进行了RSA电磁旁路分析研究，使用串口通信技术实现了对目标设备CPU的旁路电磁信号的采集，并采用基于边界的单类支持向量机的方法，以分类的正确率为70%为阈值，实现了对RSA二进制模幂运算中平方、乘法操作的识别，提取了OpenSSL加密库中1?024位RSA加密算法的二进制密钥序列。相比于传统的简单分析方法，克服了因旁路信号质量低而无法破解密钥的难题。     

优化特征提取的互动式人脸活体检测研究

针对人脸识别系统中出现的通过照片或视频“欺诈”解锁问题，提出一种活体检测方法，通过随机指令判断被检测对象是否为真人。利用HOG特征和随机森林算法对摄像头采集的图像进行人脸检测，预测脸部68个特征点位置，把68个特征点位置和脸部位置的相对位置归一化后作为姿态的特征，提取的姿态特征与SVM分类器相结合，训练出分类效果较好的头部姿态估计分类器。通过多次实验，对特征提取方法进行优化，进一步提高检测准确率。最后，使用随机互动式命令序列对被检测人发出指令，实现活体检测。该方法对头部姿态估计具有较高的鲁棒性，并且可以有效地防范照片和视频认证攻击。     

基于多视图立体视觉的沙堆三维尺寸测量研究

利用从运动中恢复结构方法(SFM),提出了一种基于多视图立体视觉的沙堆三维重建及三维尺寸测量方法。首先根据SFM方法的求解不稳定特点,结合光束平差法对SFM求解过程进行分析及优化;其次针对SFM重建结果为稀疏点云的问题,利用基于面片的稠密重建算法重新生成稠密的三维点云,再利用泊松算法对密集点云进行三维曲面重建;最后获得模型的三维尺寸信息。对某建筑工地的沙堆进行了三维尺寸的测量实验,实验结果验证了该方法的有效及可行性,提高了重建能力及精度,同时考虑了目标实际测量误差与重建误差,能够满足实际智能测量的应用需求。     

一种图像校正的偏振光罗盘系统的研究

导航传感器在探险、应急、精确制导武器、船舶、航空器导航和定位系统中起着关键作用。针对偏振光罗盘在倾斜状态下误差较大的问题,提出了一种利用加速度计和陀螺仪对偏振光罗盘进行图像校正的方法,设计了一种基于陀螺仪校正的偏振光罗盘系统。首先利用加速度计和陀螺仪计算得到载体姿态角,对偏振光图像数据进行图像校正,采用Stokes矢量法解算大气偏振模式分布,进而提取导航特征点,最后对特征点进行拟合解算出航向角信息。并且进行了静态和动态测试实验,实验结果表明,该算法能够有效的对偏振光罗盘姿态变化引起的误差进行补偿,可以将偏振光罗盘的航向角测量误差控制在1.86°之内,平均误差为0.09°。