An Improved Method for Load Taxonomy Using Sample Shifting Technique and Signature Analysis

This paper illustrates an improved method of classification of electrical appliances, particularly for domestic loads, to construct load taxonomy on the basis of their signature analysis. Each electrical load is characterized by its own distinct signature and hence load signature analysis is useful in monitoring the health of the equipment, power quality, in determining individual energy usage etc. type of services. On the other hand, load taxonomy classifies these loads in several clusters on the basis of some features extracted from their signatures. In traditional methods of construction of load taxonomy, different signature patterns based on power metrics, V-I trajectories, Eigen vectors, etc. In this proposed method, with the adoption of sample shifting technique the required number of feature extraction is reduced to a lower value to find out various signature patterns than those are required in traditional load taxonomies. Moreover, a better taxonomy, having well separated groups of loads is achieved with lower number of extracted features.     

Effect of distances between lens and sample surface on laser-induced breakdown spectroscopy with spatial confinement

Spatial confinement can significantly enhance the spectral intensity of laser-induced plasma in air.It is attributed to the compression of plasma plume by the reflected shockwave.In addition,optical emission spectroscopy of laser-induced plasma can also be affected by the distance between lens and sample surface.In order to obtain the optimized spectral intensity,the distance must be considered.In this work,spatially confined laser-induced silicon plasma by using a Nd:YAG nanosecond laser at different distances between lens and sample surface was investigated.The laser energies were 12 mJ,16 mJ,20 mJ,and 24 mJ.All experiments were carried out in an atmospheric environment.The results indicated that the intensity of Si (I) 390.55 nm line firstly rose and then dropped with the increase of lens-to-sample distance.Moreover,the spectral peak intensity with spatial confinement was higher than that without spatial confinement.The enhancement ratio was approximately 2 when laser energy was 24 mJ.     

基于t分布的电子装备测试样本选取方法

测试样本选取是装备测试工作的一项重要内容,理想的测试样本是在高置信度的前提下用尽量少的测试次数得到的,要同时兼顾质量和效率。为此,针对电子装备测试的特殊性,运用数理统计的方法,从理论上对样本数量进行了探讨,得到了相应的计算方法,并举例验证该方法有一定的理论价值。     

基于对抗学习的强PUF安全结构研究

针对强物理不可复制函数（PUF，physical unclonable function）面临的机器学习建模威胁，基于对抗学习理论建立了强PUF的对抗机器学习模型，在模型框架下，通过对梯度下降算法训练过程的分析，明确了延迟向量权重与模型预测准确率之间的潜在联系，设计了一种基于延迟向量权重的对抗样本生成策略。该策略与传统的组合策略相比，将逻辑回归等算法的预测准确率降低了5.4%~9.5%，低至51.4%。结合资源占用量要求，设计了新策略对应的电路结构，并利用对称设计和复杂策略等方法对其进行安全加固，形成了ALPUF（adversarial learning PUF）安全结构。ALPUF不仅将机器学习建模的预测准确率降低至随机预测水平，而且能够抵御混合攻击和暴力破解。与其他 PUF结构的对比表明，ALPUF在资源占用量和安全性上均具有明显优势。     

Directly fast detection of digoxin in the serum sample by the synthetic receptor sensor

A novel biosensor (the synthetic receptor sensor) employing the molecular imprinted technology for the digoxin analysis is investigated. The molecularly imprinted polymer (MIP) modified electrode can specifically bind to the analyte in the sample without sample pretreatment. The digoxin analyzed by the MIP sensor was carried out in 1 mM K₃Fe(CN)₆ solution with the cyclic voltammetry. In the system, the K₃Fe(CN)₆³⁻/Fe₂(CN)₆⁴⁻ redox couple was taking place. When the solution contains the digoxin, the MIP on the electrode will bind the digoxin. Further the redox system is interrupted and the peak current is decreased according to the digoxin concentration increasing. Digoxin is a glycosylated steroid-like drug. It is important for the heart disease treatment. However, since the digoxin toxic level is low, the drug remains in the blood sample must be monitored frequently. The device possesses many advantages, such as high specific recognition properties, good chemical and mechanical stability, simplicity and low cost of preparation, sensitive and label free determination. The reproducibility is good (CV < 5). The linear relationship between the digoxin concentration and the current is 1.28–128 nM, and a detection limit of 1.28 nM is achieved. The detection time is less than 5 min.     

焦炉煤气原位整体式干法样气处理系统研究与实践

焦炉煤气样气处理系统是在线分析样气处理系统的技术制高点之一,焦炉煤气中的焦油、萘等有害污染物的处理非常困难,至今都未能完全解决。本研究提出的焦炉煤气原位整体式干法样气处理系统,能够很好适应焦炉煤气含尘量高,焦油和萘污染严重的特殊样气条件,具有体积小、免维护、零排放和响应快速的优点。采用该样气处理系统组合构建的焦炉煤气干法防爆氧分析系统已进入工程应用考核阶段。本设计的原位处理和原位分析,由于是干法样气处理技术,能够实现氧含量的高准确度在线分析,对安全生产有特殊的重要意义。     

小样产品试织时常见问题处理的探讨

本文结合多年的实践经验，针对纺织专业学生使用江阴通源生产的SGA598型半自动织样机设计试织时，出现的松紧边、锁边问题、张力控制等常见问题进行了探讨。     

Variational Feature Representation-based Classification for face recognition with single sample per person

The single sample per person (SSPP) problem is of great importance for real-world face recognition systems. In SSPP scenario, there is always a large gap between a normal sample enrolled in the gallery set and the non-ideal probe sample. It is a crucial step for face recognition with SSPP to bridge the gap between the ideal and non-ideal samples. For this purpose, we propose a Variational Feature Representation-based Classification (VFRC) method, which employs the linear regression model to fit the variational information of a non-ideal probe sample with respect to an ideal gallery sample. Thus, a corresponding normal feature, which reserve the identity information of the probe sample, is obtained. A combination of the normal feature and the probe sample is used, which makes VFRC method more robust and effective for SSPP scenario. The experimental results show that VFRC method possesses higher recognition rate than other related face recognition methods.     

基于改进SSD的高效目标检测方法

为改善一阶段目标检测算法检测精度较差的缺陷，提出一种基于SSD的高效多目标定位检测算法FSD。该算法主要从两个方面对一阶段目标检测算法进行改进：设计了一个更高效的密集残差网络，即R-DenseNet，通过采用一种更窄的密集网络结构形式，在保持特征提取容量的同时降低了计算复杂度，从而提高了算法的检测和收敛性能；改进了损失函数，通过抑制易分样本在损失函数中的权重，提高算法的鲁棒性，改善了目标检测中样本失衡的现象。采用Tensorflow深度学习框架部署网络，并在搭载Nvidia Titan X的Ubuntu上开展实验，实验表明FSD在COCO和PASCAL VOC这两个目标检测数据集上上都取得了最高的检测精度，其中FSD300D的检测精度相比SSD300有3.7%提升，检测相率比SSD有10.87%提升。