Realizing the potential of empowerment: the impact of a feedback intervention on the performance of complex technology

An empowerment initiative involving enhanced fault-management responsibility for operators of complex technology had not led to expected increases in performance, and investigations suggested that this was due to a lack of appropriate feedback. Thus, a feedback intervention was designed to provide specific, timely feedback on operator-correctable faults. It was hypothesized that the intervention would increase operator self-reliance in operating complex technology and promote system performance. Moreover, given the feedback was continuous from the point of intervention, it was predicted that gains would increase over time. Time series analysis of data on engineer call-outs (self-reliance) and machine utilization (performance) showed clear positive effects of the feedback intervention, with call-outs also showing progressive improvement. Selfreport data showed no change over time in motivation, but an increase in knowledge dissemination and a reduction in the likelihood of making expensive mistakes. There were no detrimental effects on operator well being. Implications for theory and practice in the management of complex technology are discussed.     

DFD-SS: Document Forgery Detection using Spectral – Spatial Features for Hyperspectral Images

In the present era of machines and edge-cutting technologies, still document frauds persist. They are done intuitively by using almost identical inks, that it becomes challenging to detect them—this demands an approach that efficiently investigates the document and leaves it intact. Hyperspectral imaging is one such a type of approach that captures the images from hundreds to thousands of spectral bands and analyzes the images through their spectral and spatial features, which is not possible by conventional imaging. Deep learning is an edge-cutting technology known for solving critical problems in various domains. Utilizing supervised learning imposes constraints on its usage in real scenarios, as the inks used in forgery are not known prior. Therefore, it is beneficial to use unsupervised learning. An unsupervised feature extraction through a Convolutional Autoencoder (CAE) followed by Logistic Regression (LR) for classification is proposed (CAE-LR). Feature extraction is evolved around spectral bands, spatial patches, and spectral-spatial patches. We inspected the impact of spectral, spatial, and spectral-spatial features by mixing inks in equal and unequal proportion using CAE-LR on the UWA writing ink hyperspectral images dataset for blue and black inks. Hyperspectral images are captured at multiple correlated spectral bands, resulting in information redundancy handled by restoring certain principal components. The proposed approach is compared with eight state-of-art approaches used by the researchers. The results depicted that by using the combination of spectral and spatial patches, the classification accuracy enhanced by 4.85% for black inks and 0.13% for blue inks compared to state-of-art results. In the present scenario, the primary area concern is to identify and detect the almost similar inks used in document forgery, are efficiently managed by the proposed approach.     

基于宽度学习的注塑产品质量预测方法

在注塑成型工业中,产品质量自动监测一直是注塑工业智能化发展的核心问题。高品质和大规模的产品质量数据采集成本高昂,导致数据样本量少、不同类别样本数据不平衡,为注塑产品质量预测提出了更高的挑战。为此,该文提出一种基于宽度学习方法的注塑产品质量预测模型,以产品的3维尺寸为预测目标,在普通的宽度学习系统(BLS)中加入最小p范数来改进得到模型p范数宽度学习系统(pN-BLS),解决小样本和不平衡数据的问题,提高模型对离群点的检测性能。在第4届工业大数据竞赛任务2《注塑成型工艺的虚拟量测和调机优化》数据集中,将192个参数特征与预测目标进行相关分析,提取相关性高的基础特征17个,衍生特征4个和调机参数2个作为模型的输入。将16600条数据平均分为训练集和测试集各8300条,与支持向量机 (SVM)、最近邻算法 (KNN)、多层感知机 (MLP)和BLS进行对比实验,实验结果显示pN-BLS具有更快速和更准确的预测效果。在实际缺陷检测应用中,pN-BLS能更准确地预测异常数据,具有更高的鲁棒性。     

无蜂窝大规模MIMO中基于深度强化学习的无人机辅助通信与资源调度

无蜂窝大规模多入多出(MIMO)网络中分布式接入点(AP)同时服务多个用户,可以实现较大区域内虚拟MIMO的大容量传输;而无人机辅助通信能够为该目标区域热点或边缘用户提供覆盖增强。为了降低反馈链路负载,并有效提升无人机辅助通信的频谱利用率,该文研究了基于AP功率分配、无人机服务区选择和接入用户选择的联合调度;首先将AP功率分配和无人机服务区选择问题联合建模为双动作马尔可夫决策过程 (DAMDP),提出了基于Q-learning和卷积神经网络(CNN)的深度强化学习(DRL)算法;然后将用户调度构造为一个0-1优化问题,并分解成子问题来求解。仿真结果表明,该文提出的基于DRL的资源调度方案与现有方案相比,可以有效提升无蜂窝大规模MIMO网络中频谱利用率。     

运营商网络中基于深度强化学习的服务功能链迁移机制

为改善运营商网络提供的移动服务体验,该文研究服务功能链(SFC)的在线迁移问题。首先基于马尔可夫决策过程(MDP)对服务功能链中的多个虚拟网络功能(VNF)在运营商网络中的驻留位置迁移进行模型化分析。通过将强化学习和深度神经网络相结合提出一种基于双深度Q网络(double DQN)的服务功能链迁移机制,该迁移方法能在连续时间下进行服务功能链的在线迁移决策并避免求解过程中的过度估计。实验结果表明,该文所提出的策略相比于固定部署算法和贪心算法在端到端时延和网络系统收益等方面优势明显,有助于运营商改善服务体验和资源的使用效率。     

An automated patient monitoring using discrete‐time wireless sensor networks

In recent years, Internet of Things (IoT) devices are used for remote health monitoring. For remotely monitoring a patient, only the health information at different time points are not sufficient; predicted values of biomarkers (for some future time points) are also important. In this article, we propose a powerful statistical model for an efficient dynamic patient monitoring using wireless sensor nodes through Bayesian Learning (BL). We consider the setting where a set of correlated biomarkers are measured from a patient through wireless sensors, but the sensors only report the ordinal outcomes (say, good, fair, high, or very high) to the sink based on some prefixed thresholds. The challenge is to use the ordinal outcomes for monitoring and predicting the health status of the patient under consideration. We propose a linear mixed model where interbiomarker correlations and intrabiomarker dependence are modeled simultaneously. The estimated and the predicted values of the biomarkers are transferred over the internet so that health care providers and the family members of the patient can remotely monitor the patient. Extensive simulation studies are performed to assess practical usefulness of our proposed joint model, and the performance of the proposed joint model is compared to that of some other traditional models used in the literature.     

基于列表译码方法在查询访问模型下含错学习问题的分析

Regev在2005年提出了含错学习问题(LWE),这个问题与随机线性码的译码问题密切相关,并且在密码学特别是后量子密码学中应用广泛。原始的含错学习问题是在随机访问模型下提出的,有证据证明该问题的困难性。许多研究者注意到的一个事实是当攻击者可以选择样本时,该问题是容易的。但是目前据作者所知并没有一个完整的求解算法。该文分析了查询访问模型下的带有错误学习问题,给出了完整的求解算法。分析采用的工具是将该问题联系到隐藏数问题,然后应用傅里叶学习算法进行列表译码。     

一种融合噪声网络的深度强化学习通信干扰资源分配算法

针对传统干扰资源分配算法在处理非线性组合优化问题时需要较完备的先验信息,同时决策维度小,无法满足现代通信对抗要求的问题,该文提出一种融合噪声网络的深度强化学习通信干扰资源分配算法(FNNDRL)。借鉴噪声网络的思想,该算法设计了孪生噪声评估网络,在避免Q值高估的基础上,通过提升评估网络的随机性,保证了训练过程的探索性;基于概率熵的物理意义,设计了基于策略分布熵改进的策略网络损失函数,在最大化累计奖励的同时最大化策略分布熵,避免策略优化过程中收敛到局部最优。仿真结果表明,该算法在解决干扰资源分配问题时优于所对比的平均分配和强化学习方法,同时算法稳定性较高,对高维决策空间适应性强。     

手写汉字的四角识别方案

手写汉字的本质特征的抽取是提高识别率的关键，而识别规则的生成又依赖于大量样本的归纳学习，手写汉字的四角方案就是针对这两个问题设计并实现的。实验结果证明了该方法的可行性和优越性。     

基于深度卷积神经网络和多核学习的遥感图像分类方法

为解决传统遥感图像分类方法特征提取过程复杂、特征表现力不强等问题,该文提出一种基于深度卷积神经网络和多核学习的高分辨率遥感图像分类方法。首先基于深度卷积神经网络对遥感图像数据集进行训练,学习得到两个全连接层的输出将作为遥感图像的两种高层特征;然后采用多核学习理论训练适合这两种高层特征的核函数,并将它们映射到高维空间,实现两种高层特征在高维空间的自适应融合;最后在多核融合特征的基础上,设计一种基于多核学习-支持向量机的遥感图像分类器,对遥感图像进行精确分类。实验结果表明,与目前已有的基于深度学习的遥感图像分类方法相比,该算法在分类准确率、误分类率和Kappa系数等性能指标上均有所提升,在实验测试集上3个指标分别达到了96.43%, 3.57%和96.25%,取得了令人满意的结果。