快速近似计算Shapley值的归因解释方法

Shapley值归因解释方法虽然能更准确量化解释结果, 但过高的计算复杂度严重影响了该方法的实用性. 本文引入KD树重新整理待解释模型的预测数据, 通过在KD树上插入虚节点, 使之满足TreeSHAP算法的使用条件, 在此基础上提出了KDSHAP方法. 该方法解除了TreeSHAP算法仅能解释树结构模型的限制, 将该算法计算Shapley值的高效性放宽到对所有的黑盒模型的解释中, 同时保证了计算准确度. 通过实验对比分析, KDSHAP方法的可靠性, 以及在解释高维输入模型时的适用性.     

浅谈拆除爆破工程中存在的问题和对策

拆除爆破工程的广泛应用为社会主义经济建设提供了有益的帮助,充分体现了科学技术是第一生产力。但是在拆除爆破领域也存在不少问题,如设计、施工、安全防护、爆破器材管理、爆破理论研究等方面还有许多不足,这需要我们认真正视,并采取切实有效的对策加以解决。文中针对存在的问题提出了一些对策,可以为拆除爆破界的同行们借鉴。     

Convolutional Neural Network Auto Encoder Channel Estimation Algorithm in MIMO-OFDM System

Higher transmission rate is one of the technological features of prominently used wireless communication namely Multiple Input Multiple Output-Orthogonal Frequency Division Multiplexing (MIMO–OFDM). One among an effective solution for channel estimation in wireless communication system, specifically in different environments is Deep Learning (DL) method. This research greatly utilizes channel estimator on the basis of Convolutional Neural Network Auto Encoder (CNNAE) classifier for MIMO-OFDM systems. A CNNAE classifier is one among Deep Learning (DL) algorithm, in which video signal is fed as input by allotting significant learnable weights and biases in various aspects/objects for video signal and capable of differentiating from one another. Improved performances are achieved by using CNNAE based channel estimation, in which extension is done for channel selection as well as achieve enhanced performances numerically, when compared with conventional estimators in quite a lot of scenarios. Considering reduction in number of parameters involved and re-usability of weights, CNNAE based channel estimation is quite suitable and properly fits to the video signal. CNNAE classifier weights updation are done with minimized Signal to Noise Ratio (SNR), Bit Error Rate (BER) and Mean Square Error (MSE).     

Development of Phospholipids Vesicular Nanocarrier for Topical Delivery of Tea Tree Oil in Management of Atopic Dermatitis Using BALB/c Mice Model

This work aims to develop and evaluate the efficacy of tea tree oil (TTO) ethosomal cream with improved deposition in skin layers for treatment of atopic dermatitis (AD). Ethosomes of TTO are developed using phosphatidylcholine (2% and 3% w/v) and ethanol (20%, 30%, and 40% w/v). Ethosomes are evaluated for percent entrapment efficiency (%EE), vesicle size, zeta potential, and in vitro drug diffusion. Ethosomal creams with optimized ethosomal dispersion are developed and evaluated for physicochemical parameters, thermal stability, ex vivo permeation, skin retention, and in vitro cytotoxicity using HaCat skin cell lines in comparison to conventional creams of TTO. In vivo investigations of optimized creams are performed using BALB/c mice model. The %EE, vesicle size, and zeta potential for optimized ethosomes are found to be 76.19 ± 3.26%, 333.6 nm, and –35.3 mV, respectively. Ethosomal creams showed higher deposition in the epidermis and dermis. The optimized creams are non-cytotoxic to HaCat cell lines. The creams significantly reduce the inflammatory response by decreasing the clinical score and infiltration of white blood cells, eosinophils, and IgE antibodies. Overall efficacy of ethosomal cream is higher than conventional cream. In conclusion, optimized ethosomal cream of TTO shows good efficacy for treatment of AD. Practical applications : The method used for the formulation of ethosomes is simple and can be easily scaled up on the industrial level. The loading of TTO within ethosomes can increase the efficiency by enhanced drug deposition in the epidermis and might also improve its stability against oxidative degradation. Topical ethosomal cream of TTO can improve patient compliance by avoidance of adverse effects linked with corticosteroids and could be a possible complementary or alternative therapy in management of AD.     

基于SAOR的Massive MIMO系统信号检测算法

大规模多输入多输出(Massive multiple input multiple output, Massive MIMO)系统采用最小均方误差(Minimum mean square error, MMSE)接收检测方法时存在矩阵求逆复杂度高的问题，已有较多降低复杂度的研究。在降低检测算法复杂度的同时，如何提高算法收敛速度和检测性能一直是人们关注的焦点。本文将对称加速超松弛(Symmetric accelerated over-relaxation， SAOR)迭代算法应用于Massive MIMO系统信号检测中，避免了复杂的矩阵求逆计算，实现了复杂度较最小均方误差算法降低了一个数量级。仿真结果表明，基于SAOR的检测方法通过较少的迭代次数就能逼近最小均方误差（Minimum mean square error, MMSE）算法的检测性能，为Massive MIMO系统中接收信号的快速检测提供了较好的实现方法。     

皮带输送机运行过程中常见问题及处理对策

皮带输送机是煤矿井下重要的煤炭运输设备,其稳定运行关系着煤矿生产的高产高效。由于煤矿井下生产环境恶劣,皮带输送机很容易发生各种问题。因此,对皮带输送机运行过程中出现的问题进行准确分析并进行处理显得十分重要。对皮带输送机运行过程中出现的一些常见问题进行了分析,并给出了一些相应的处理对策,有助于实现煤矿生产的高产高效。     

Learning Association Rules and Tracking the Changing Concepts on Webpages: An Effective Pornographic Websites Filtering Approach

We applied the decision tree algorithm to learn association rules between webpage’s category (pornographic or normal) and the critical features. Based on these rules, we proposed an efficient method of filtering pornographic webpages with the following major advantages: 1) a weighted window-based technique was proposed to estimate for the condition of concept drift for the keywords found recently in pornographic webpages; 2) checking only contexts of webpages without scanning pictures; 3) an incremental learning mechanism was designed to incrementally update the pornographic keyword database.     

回弹检测法检测混凝土强度相关问题的探讨

本文就当前社会人们对建筑安全水平和质量要求不断提高的背景下,对回弹检测法检测混凝土强度的相关问题进行探讨,并以此推动回弹法检测混凝土强度行业标准的规范化发展进程,希望能够给从事相关行业的工作者提供帮助。     

基于DoG检测图像特征点的快速二进制描述子

针对SIFT描述子实时性差和传统二进制描述子对尺度、旋转和视角变化鲁棒性差的问题,本文通过优化采样模式和添加灰度差分不变量比较测试进行改进,提出了一种鲁棒性更高的二进制描述子。首先,设计了一种尺度关联、编号标记的采样模式;然后,旋转采样模式中各采样点到特定位置,确保描述子尺度、旋转不变性;接着,分析了采样点点对模式对描述子的影响,选择使用机器学习训练后的128对采样点对;最后,选择灰度值比较测试及梯度绝对值和比较测试构建二进制描述子。实验中采用DoG检测图像关键点,结果表明:本文提出的描述子在描述子构建和描述子匹配上比SIFT描述子分别快84%和67%;在有视角变化的图像匹配上,准确率比传统的二进制描述子高3%~5%,召回率平均要高30%以上。本文提出的特征点描述方法适用于时间要求高的图像匹配领域。