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。     

Creating awareness on bullying and cyberbullying among young people: Validating the effectiveness and design of the serious game Conectado

Serious games have proven to be educational tools with numerous positive effects, capable of promoting learning, changing behavior, or improving training and skills development, among other effects. Serious games can also be applied to address and prevent social problems. This study describes the experiments and analyses we have carried out to test the effectiveness of Conectado, a serious game created to prevent bullying and cyberbullying in schools by increasing awareness of the problem in players. We have used the results from these experiments to answer different research questions regarding the game’s acceptance and effectiveness, validating several characteristics of the game design. We have also studied the influence of players’ characteristics on the effect of the game, as well as the relationship between the in-game behaviors of players and their degree of awareness. We have verified a positive effect of the game in terms of an increase of awareness regarding bullying and cyberbullying for all target users, and have provided further insight into how this increase is related to different players’ characteristics and behaviors.     

多模式对连接权矩阵的一种神经网络学习算法

该文提出多模式对连接权矩阵的一种神经网络学习算法,并给出了严格的理论证明。该算法能够将多个模糊模式对可靠地编码存储到尽可能少的连接权矩阵中,从而大大地减少存储空间,而且容易实现,并举例验证了它的有效性。     

一种新型基于环上带误差学习问题的认证密钥交换方案

利用格上判定带误差学习问题(Ring-DLWE)困难假设,该文基于Peikert的调和技术构造认证密钥交换方案。在标准模型下,该方案是CK模型中可证明安全的,并达到弱前向安全性(wPFS)。与现有的基于LWE的密钥交换方案相比,该方案使用平衡的密钥提取函数,因而保护共享会话密钥,同时因其基于格中困难问题,所以能抵抗量子攻击。     

基于隐变量贝叶斯模型的稀疏信号恢复

该文基于贝叶斯分析的视角,揭示了一类算法,包括使用隐变量模型的稀疏贝叶斯学习(SBL),正则化FOCUSS算法以及Log-Sum算法之间的内在关联。分析显示,作为隐变量贝叶斯模型的一种,稀疏贝叶斯学习使用第2类最大似然(Type II ML)在隐变量空间进行运算,可以视作一种更为广义和灵活的方法,并且为不适定反问题的稀疏求解提供了改进的途径。较之于目前基于第1类最大似然(Type I ML)的稀疏方法,仿真实验证实了稀疏贝叶斯学习的优越性能。     

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。     

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。     

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.     

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。     

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。