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.     

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。     

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.     

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。     

A new linearly constrained minimum variance beamformer for reconstructing EEG sparse sources

Brain source imaging based on EEG aims to reconstruct the neural activities producing the scalp potentials. This includes solving the forward and inverse problems. The aim of the inverse problem is to estimate the activity of the brain sources based on the measured data and leadfield matrix computed in the forward step. Spatial filtering, also known as beamforming, is an inverse method that reconstructs the time course of the source at a particular location by weighting and linearly combining the sensor data. In this paper, we considered a temporal assumption related to the time course of the source, namely sparsity, in the Linearly Constrained Minimum Variance (LCMV) beamformer. This assumption sounds reasonable since not all brain sources are active all the time such as epileptic spikes and also some experimental protocols such as electrical stimulations of a peripheral nerve can be sparse in time. Developing the sparse beamformer is done by incorporating L1-norm regularization of the beamformer output in the relevant cost function while obtaining the filter weights. We called this new beamformer SParse LCMV (SP-LCMV). We compared the performance of the SP-LCMV with that of LCMV for both superficial and deep sources with different amplitudes using synthetic EEG signals. Also, we compared them in localization and reconstruction of sources underlying electric median nerve stimulation. Results show that the proposed sparse beamformer can enhance reconstruction of sparse sources especially in the case of sources with high amplitude spikes.     

基于k-shell的复杂网络最短路径近似算法

复杂网络最短路径经典算法的处理效率较低，不适用于大规模复杂网络，而现有近似算法通用性有限，且计算准确率不理想，不能满足规模日益扩大的复杂网络中的最短路径计算需求。针对于此，提出基于[k]-shell的复杂网络最短路径近似算法。算法利用节点的[k]-shell值进行网络划分并引导搜索路径，利用超点聚合处理[k]-shell子网来降低路径搜索中节点和连边的规模，通过在路径搜索过程使用双向搜索树方法提高算法的计算效率和准确率。实验结果表明，算法通用性较好，在现实与仿真大规模复杂网络中均具有较高的计算效率和准确率。