基于Word2vec和粒子群的链路预测算法

链路预测中普遍存在两大问题:特征提取困难和类别数据不平衡.本文借鉴文本处理中的深度学习特征提取算法和优化问题中的粒子群算法, 提出一种基于词向量的粒子群优化算法(Word2vec-PSO).该方法首先通过随机游走产生网络序列后, 利用Word2vec算法对节点序列特征提取.然后在有监督的条件下, 利用粒子群算法对提取好的特征进行筛选, 并确定重采样的参数来解决类别数据不平衡问题, 并分析了不同链路预测算法的计算复杂性.最后将本文的算法与基于相似性、基于深度学习、基于不平衡数据的3类链路预测算法, 在4个不同的时序网络中进行实证对比研究.结果表明, 本文提出的链路预测算法预测精度较高, 算法更加稳定且具有普适性.     

基于深度无监督学习的多小区蜂窝网资源分配方法

针对多小区蜂窝网络资源分配所要求的低能耗、高速率和低延时问题,提出一种基于深度无监督学习的多小区蜂窝网络资源分配方法.首先,构建基于无监督学习的深度功率控制神经网络,通过约束处理输出优化的信道功率控制方案以最大化能量效率的期望;然后,构建基于无监督学习的深度信道分配神经网络,通过约束处理输出优化的信道分配方案,并联合前期训练好的深度功率控制神经网络拟合输出优化的信道功率,进一步优化能量效率的期望.仿真结果表明,所提出的方法在保证低计算时延的同时可获得优于其他算法的能量效率和传输速率.     

基于深度剥离的三维打印模型朝向优化算法

为了提高三维打印产品表面质量且有效节省材料,提出一种面向熔融挤压式三维打印机的模型朝向优化算法.该算法基于深度剥离技术,以打印朝向为自变量构建模型悬空面积及其支撑结构体积的双目标优化函数;利用模式搜索方法设计一个两步走的优化方案来确定最优的打印朝向.实验结果表明,利用深度剥离技术能够较为准确、高效地检测出打印模型悬空区域,并计算出相应的悬空面积和支撑体积;设计的优化方案也能够根据双目标的权重比确定一个较优的打印朝向,不但减少了支撑结构与模型表面的接触范围,还能降低支撑结构的体积.文中算法在提高模型表面质量以及减少支撑结构的材料消耗两方面具有优势.     

基于大数据和深度学习的全社会月用电总量预测

为解决经典方法预测全社会用电总量预测数值精度较低、模型结构参数过于复杂等技术难题,本文提出将电力大数据和人工智能领域深度学习算法相结合的研究方法。采用计算机建立具有阶层结构的深度神经网络,根据仿生学原理引入线性整流函数解决梯度消失及神经网络收敛速度减慢问题,采用梯度下降来进行优化模型,同时通过引入指数衰减法由神经网络模型自动设定学习率以提高模型预测精度并降低迭代次数。从数量场的梯度原理并结合泰勒公式,推导出梯度下降法背后数学原理。为解决过拟合问题引入早停算法以提高模型训练速度及泛化能力。最后深度学习算法预测数值与经典线性回归算法预测数值相比较,深度学习算法在对全社会月用电总量的预测精准度、稳定性指标上明显优于线性回归算法,深度神经网络模型对未来全社会电力需求的预测数值具有高度的可信性。     

基于大数据的分布式光伏接入配电网影响分析与功率预测研究

为提高分布式光伏发电功率预测的精度,满足电网调度和规划的高精度要求,本文利用光伏运行、电能量采集、电网调度等业务系统的海量数据,利用大数据分析方法研究大量分布式光伏接入对配电网负荷特性的影响,并提出基于气象相似日和粒子群算法优化BP神经网络的光伏电站功率预测方法。通过分析光伏发电功率随天气类型、温度、光照强度等气象因素变化规律,运用模糊聚类算法计算确定待预测日的气象相似日序列,选取气象相似日历史数据作为BP神经网络预测模型的输入变量,并采用粒子群算法方法优化BP神经网络的初始值,最终输出分布式光伏各时段发电功率的预测值。实验结果表明该方法可有效提高光伏电站功率预测模型的收敛能力和学习能力,具有较高的预测精度。     

用于求解旅行商问题的深度智慧型蚁群优化算法

启发式算法是求解组合优化问题求解的重要手段,其主要特征是能够以可接受的计算代价找到足够好的可行解.然而,设计良好的用于求解组合优化问题的启发式算法需要大量的专业领域知识以及大量的试错工作,且人工设计的启发式算法不能够保证在不同问题集上均具有一致性表现.另一方面,深度学习方法能够通过学习自动设计启发式规则,然而深度学习方法通常缺少在解空间内搜索的能力.为克服以上问题,提出了一种基于蚁群优化和深度强化学习的混合启发式算法框架.在该框架中,蚁群算法能够利用深度强化学习提取的启发式信息,而深度强化学习方法的解空间搜索性能也由于蚁群算法的加入而获得提高.采用经典的TSPLIB中的算例对该算法求解旅行商问题的效能进行了计算验证,结果表明采用深度学习方法能够极大地提升蚁群算法的计算表现,并降低其计算代价.     

基于Toy模型蛋白质折叠预测的多种群微粒群优化算法研究

基于Toy模型的蛋白质折叠结构预测问题是一个典型的NP问题.提出了多种群微粒群优化算法用于计算蛋白质能量最小值.该算法采用了一种新的算法结构,在该结构中,每一代的种群被分为精英子种群、开采子种群和勘探子种群三部分,通过改善种群的局部开采能力和全局勘探能力来提高算法的性能.分别采用Fibonacci蛋白质测试序列和真实蛋白质序列进行了折叠结构预测的仿真实验.实验结果表明该算法能够更精确地进行蛋白质折叠结构预测,为生物科学研究提供了一条有效途径.     

基于混沌优化的非线性预测控制器

针对非线性系统的控制问题,本文将神经网络辨识、混沌优化和预测控制思想有机结合,提出了一种新型非线性预测控制器.该控制器以神经网络作为预测模型,混沌优化算法作为滚动优化策略,避免了非线性预测控制中复杂的梯度计算和矩阵求逆问题.另外在训练神经网络过程中,采用了带混沌机制的自适应学习率的BP算法,以提高神经网络的收敛能力和收敛速度.仿真研究说明了该非线性预测控制器的有效性及实时性.     

应用深度学习加速石墨烯导电剂的研发

石墨烯作为电极材料的导电剂能极大改善锂电池的性能,传统的制备方法只能依赖过往的经验合理地推测材料的合成和加工流程。本文基于深度学习的方法训练实验中的数据集,通过K折交叉验证对比实验,选择优化算法及调节超参数,实现测试数据集电阻率的预测,构建了材料电学性能和工艺参数之间的关系。结果表明,深度学习模型能根据不同的工艺参数预测材料的电学性能,运用深度学习的方法可以加速石墨烯导电剂的研发,为石墨烯导电剂的产业化推广提供指导。     

基于改进的DeepESN软测量建模方法及应用

针对硫回收装置中硫化氢和二氧化硫浓度的实时监控预测问题,提出一种基于改进的深度回声状态网络(DeepESN)软测量建模方法,给出了其离线学习算法.改进的DeepESN网络能够通过多层回声状态网络的结构,可以对具有强非线性特性的化工过程进行有效的深度学习和预测.离线学习算法在求输出权值时加入了岭回归算法,有效地提高了网络学习的稳定性.将该方法在同等条件下与现有的软测量建模方法进行了比较,基于改进的DeepESN软测量建模方法具有更好的学习能力、更高的学习效率和预测精度.     

Deep learning driven real time topology optimisation based on initial stress learning

Topology optimisation can facilitate engineers in proposing efficient and novel conceptual design schemes, but the traditional FEM based optimization demands significant computing power and makes the real time optimization impossible. Based on the convolutional neural network (CNN) method, a new deep learning approximate algorithm for real time topology optimisation is proposed. The algorithm learns from the initial stress (LIS), which is defined as the major principal stress matrix obtained from finite element analysis in the first iteration of classical topology optimisation. The initial major principal stress matrix of the structure is used to replace the load cases and boundary conditions of the structure as independent variables, which can produce topological prediction results with high accuracy based on a relatively small number of samples. Compared with the traditional topology optimisation method, the new method can produce a similar result in real time without repeated iterations. A classic short cantilever problem was used as an example, and the optimized topology of the cantilever structure is predicted successfully by the established approximate algorithm. By comparing the prediction results to the structural optimisation results obtained by the classical topology optimisation method, it is discovered that the two results are highly approximate, which verifies the validity of the established algorithm. Furthermore, a new algorithm evaluation method is proposed to evaluate the effects of using different methods to select samples on the prediction performance of the optimized topology, and the results were promising and concluded in the end.     

Deep Metallogenic prediction model construction of the Xiongcun no. II orebody based on the DNN algorithm

With the continuous mining and gradual reduction of shallow deposits, deep prospecting has become a new global prospecting trend. In addition, with the development of artificial intelligence, deep learning provides a favorable means for geological big data analysis. This paper, researches the No. II Orebody of the Xiongcun deposit. First, based on previous research results and metallogenic regularity, prospecting information, namely, lithology, Au-Ag-Cu chemical elements and wall rock alteration is extracted, and the block model is established by combining the Kriging interpolation structure. Second, the datasets are divided into dataset I and dataset II according to “randomness” and “depth”. Third, deep prospecting prediction models based on deep neural networks (DNN) and the convolutional neural networks (CNN) is constructed, and the model parameters are optimized. Finally, the models are applied to the deep prediction of the Xiongcun No. II Orebody. The results show that the accuracy rate and recall rate of the prediction model based on the DNN algorithm are 96.15% and 89.23%, respectively, and the AUC is 96.39%, which are higher values than those of the CNN algorithm, indicating that the performance of the prediction model based on the DNN algorithm is better. The accuracy of prediction model based on dataset I is higher than that of dataset II. The accuracy of deep metallogenic prediction based on the DNN algorithm is approximately 89%, that based on the CNN is approximately 87%, and that based on prospecting information method is approximately 61.27%. The prediction results of the DNN algorithm are relatively consistent in the spatial location and scale of the orebody. Therefore, based on the work done in this paper, it is feasible to use a deep learning method to carry out deep mineral prediction.

     

Prediction of software vulnerability based deep symbiotic genetic algorithms: Phenotyping of dominant-features

The detection of software vulnerabilities is considered a vital problem in the software security area for a long time. Nowadays, it is challenging to manage software security due to its increased complexity and diversity. So, vulnerability detection applications play a significant part in software development and maintenance. The ability of the forecasting techniques in vulnerability detection is still weak. Thus, one of the efficient defining features methods that have been used to determine the software vulnerabilities is the metaheuristic optimization methods. This paper proposes a novel software vulnerability prediction model based on using a deep learning method and SYMbiotic Genetic algorithm. We are first to apply Diploid Genetic algorithms with deep learning networks on software vulnerability prediction to the best of our knowledge. In this proposed method, a deep SYMbiotic-based genetic algorithm model (DNN-SYMbiotic GAs) is used by learning the phenotyping of dominant-features for software vulnerability prediction problems. The proposed method aimed at increasing the detection abilities of vulnerability patterns with vulnerable components in the software. Comprehensive experiments are conducted on several benchmark datasets; these datasets are taken from Drupal, Moodle, and PHPMyAdmin projects. The obtained results revealed that the proposed method (DNN-SYMbiotic GAs) enhanced vulnerability prediction, which reflects improving software quality prediction.

     

基于BOA-ELM的混凝土抗压强度预测研究

为控制控制混凝土生产成本,在混凝土拌和期限制抗压强度不足的缺陷构建产出,可以有效降低原料的浪费,是节能降耗的关键方法之一。针对混凝土抗压强度的传统测量方法严重滞后的问题,提出了基于贝叶斯优化极限学习机(BOA-ELM)的混凝土抗压强度预测方法。首先,分析了混凝土拌和过程中对抗压强度预测值实时获得的需求。以各物料的用量为分析基础,28天标准养护后混凝土抗压强度值为预测目标,设计了基于极限学习机的强度预测模型。其次,为进一步提高模型的稳定性以及准确行,提出基于贝叶斯优化的极限学习机模型,根据模型超参数的分布特征,以高斯过程作为超参的先验分布,预测误差最小化作为目标,寻找最优的模型超参。最后,在实际施工产生的C50标号混凝土数据集上测试文中模型,并对比分析了其他预测模型和寻优算法。结果表明,结合了贝叶斯优化的极限学习机预测模型相较于经典算法具有更高的预测准确性和模型训练的高效性。     

基于深度学习的步态识别算法优化研究

基于深度学习的神经网络,对步态识别算法进行了优化研究。利用粒子群优化BP神经网络阈值、权值,在神经网络中代入优化后的初始值进行训练,避免陷入局部最优。通过Vicon MX系统对角度特征值进行采集,利用基于粒子群优化BP神经网络进行识别,验证其识别步态的可行性;筛选出传感器系统特征值,在对其优化改进时选取粒子群优化BP神经网络。与传统神经网络法、粒子群优化法相比,基于粒子群优化BP神经网络法的识别方式,识别时间短且识别率高。     

PCA和PSO-ELM在高炉铁水硅含量中的预测仿真

炉温的实时预测技术对高炉运转具有重要意义。在高炉炼铁过程中,通常以铁水硅含量来表征高炉热状态。针对硅含量预测效率和精度不足的问题,提出主成分分析和粒子群改进的极限学习机相结合的方法对高炉铁水硅含量进行预测。由于影响铁水硅含量的因素众多,且各因素之间相互影响,通过主成分分析对影响硅含量的输入变量进行降维处理。利用粒子群算法来优化极限学习机的权值和阈值,并以均方根误差作为适应度函数建立预测模型。将提取出的主成分作为模型输入,铁水硅含量作为模型输出。最后比较了极限学习机算法和粒子群改进的极限学习机,实验结果表明改进后的预测模型提高了硅含量预测的准确度,上述方法可为高炉的生产操作提供参考。     

脑卒中多分类预后预测的深度集成优化方法

诊疗前预测急性缺血性脑卒中（AIS）的预后分级,有利于揭示预后转归水平并指导治疗策略,提升方法的预测性能是实现精准医疗的重要指导。利用临床和影像组学的融合特征实施脑卒中的多分类预测,并提出了一种基于融合特征的深度集成优化方法（IABC-DEL）模型,其特征选择方法为Embedded嵌入法和卡方检验,数据不平衡处理方式为Borderline-SMOTE算法,利用Stacking构建深度集成优化模型,基学习器包括深度神经网络（DNN）、长短期记忆网络（LSTM）和门控循环单元（GRU）,优化方法为改良人工蜂群算法（IABC）。研究结果表明,深度集成优化方法的预后预测性能优于经典方法和既往研究,Macro-F1 score为87.88%,Macro-AUC为96.27%,ACC为88.02%。因此,基于深度集成优化学习的急性缺血性脑卒中预后模型可对临床诊治和预后康复提供指导意义,并为研究预测提供新的建模思路。     

Shape-based object extraction in high-resolution remote-sensing images using deep Boltzmann machine

In this article, we proposed a novel method based on deep learning shape priors for object extraction in high-resolution (HR) remote-sensing images. Specifically, the deep Boltzmann machines (DBMs) are applied to model the shape priors via the unsupervised training process, which qualify for the advantages of deep learning method, especially the powerful feature learning and modelling ability. The deep shape model is integrated into a new energy function to eliminate the influence of disturbing background. The energy function combines image appearance information and region information. A new region term in the function is proposed to eliminate the influence of object shadow. The process of object extraction is achieved by minimizing the energy function with an iterative optimization algorithm and the Split Bregman method is applied to derive a global solution during the minimization process. Quantitative and qualitative experiments are conducted on the aircraft data set acquired by QuickBird with 60 cm resolution and the results demonstrate the effectiveness of the proposed method.     

势能曲面变平法的改进及其在三维非格点模型中的应用

根据蛋白质的氨基酸序列预测其空间结构可以归纳为一个多极值的全局优化问题,缺少一种有效的全局寻优方法是阻碍这一难题解决的一个关键。势能曲面变平(ELP)法是一种启发式的全局优化算法,是一种推广的蒙特卡罗(MC)法,已被成功地应用于蛋白质结构预测问题。本文在ELP法的基础上,提出改进的势能曲面变平(ELP )算法。将ELP 算法应用于三维非格点的蛋白质AB模型,预测和发现蛋白质结构,数值实验表明ELP 算法是一种预测蛋白质结构的有效算法,计算结果优于ELP和MC算法。