Multi-Objective Optimization and Analysis Model of Sintering Process Based on BP Neural Network

A multi-objective optimization and analysis model of the sintering process based on BP neural network is presented. Genetic algorithms are combined to simplify the BP neural network, which can reduce the learning time and increase the forecasting accuracy of the network model. This model has been experimented in the sintering process, and the production cost, the energy consumption, the quality （revolving intensity）, and the output are considered at the same time. Moreover, the relation between some factors and the multi-objectives has been analyzed, and the results are consistent with the process. Different objectives are emphasized at different practical periods, and this can provide a theoretical basis for the manager.

Using Object Detection Network for Malware Detection and Identification in Network Traffic Packets

In recent years,the number of exposed vulnerabilities has grown rapidly and more and more attacks occurred to intrude on the target computers using these vulnerabilities such as different malware.Malware detection has attracted more attention and still faces severe challenges.As malware detection based traditional machine learning relies on exports’experience to design efficient features to distinguish different malware,it causes bottleneck on feature engineer and is also time-consuming to find efficient features.Due to its promising ability in automatically proposing and selecting significant features,deep learning has gradually become a research hotspot.In this paper,aiming to detect the malicious payload and identify their categories with high accuracy,we proposed a packet-based malicious payload detection and identification algorithm based on object detection deep learning network.A dataset of malicious payload on code execution vulnerability has been constructed under the Metasploit framework and used to evaluate the performance of the proposed malware detection and identification algorithm.The experimental results demonstrated that the proposed object detection network can efficiently find and identify malicious payloads with high accuracy.

Smart Body Sensor Object Networking

This paper discusses smart body sensor objects （BSOs）, including their networking and internetworking. Smartness can be incorpo-rated into BSOs by embedding virtualization, predictive analytics, and proactive computing and communications capabilities. A few use cases including the relevant privacy and protocol requirements are also presented. General usage and deployment eti-quette along with the relevant regulatory implications are then discussed.

Multi-scale object detection by top-down and bottom-up feature pyramid network

While moving ahead with the object detection technology, especially deep neural networks, many related tasks, such as medical application and industrial automation, have achieved great success. However, the detection of objects with multiple aspect ratios and scales is still a key problem. This paper proposes a top-down and bottom-up feature pyramid network(TDBU-FPN),which combines multi-scale feature representation and anchor generation at multiple aspect ratios. First, in order to build the multi-scale feature map, this paper puts a number of fully convolutional layers after the backbone. Second, to link neighboring feature maps, top-down and bottom-up flows are adopted to introduce context information via top-down flow and supplement suboriginal information via bottom-up flow. The top-down flow refers to the deconvolution procedure, and the bottom-up flow refers to the pooling procedure. Third, the problem of adapting different object aspect ratios is tackled via many anchor shapes with different aspect ratios on each multi-scale feature map. The proposed method is evaluated on the pattern analysis, statistical modeling and computational learning visual object classes(PASCAL VOC)dataset and reaches an accuracy of 79%, which exhibits a 1.8% improvement with a detection speed of 23 fps.

Real-time object segmentation based on convolutional neural network with saliency optimization for picking

This paper concerns the problem of object segmentation in real-time for picking system. A region proposal method inspired by human glance based on the convolutional neural network is proposed to select promising regions, allowing more processing is reserved only for these regions. The speed of object segmentation is significantly improved by the region proposal method.By the combination of the region proposal method based on the convolutional neural network and superpixel method, the category and location information can be used to segment objects and image redundancy is significantly reduced. The processing time is reduced considerably by this to achieve the real time. Experiments show that the proposed method can segment the interested target object in real time on an ordinary laptop.

Overview of Object Detection Algorithms Using Convolutional Neural Networks

In today’s world, computer vision technology has become a very important direction in the field of Internet applications. As one of the basic problems of computer vision, object detection has become the basis of many vision tasks. Whether we need to realize the interaction between images and text or recognize fine categories, it provides reliable information. This article reviews the development of object detection networks. Starting from RCNN, we introduce object detection based on candidate regions, including Fast R-CNN, Faster R-CNN, etc.;and then start to introduce single-shot networks including YOLO, SSD, and Retina Net, etc. Detectors are the most excellent methods at present. By reviewing the current research status of object detection networks, it provides suggestions for the further development trend and research of object detection.

Modelling and Multi-Objective Optimal Control of Batch Processes Using Recurrent Neuro-fuzzy Networks

In this paper, the modelling and multi-objective optimal control of batch processes, using a recurrent neuro-fuzzy network, are presented. The recurrent neuro-fuzzy network, forms a ＂global＂ nonlinear long-range prediction model through the fuzzy conjunction of a number of ＂local＂ linear dynamic models. Network output is fed back to network input through one or more time delay units, which ensure that predictions from the recurrent neuro-fuzzy network are long-range. In building a recurrent neural network model, process knowledge is used initially to partition the processes non-linear characteristics into several local operating regions, and to aid in the initialisation of corresponding network weights. Process operational data is then used to train the network. Membership functions of the local regimes are identified, and local models are discovered via network training. Based on a recurrent neuro-fuzzy network model, a multi-objective optimal control policy can be obtained. The proposed technique is applied to a fed-batch reactor.

QoE Assessment of Fairness between Players in Networked Virtual 3D Objects Identification Game Using Haptic, Olfactory, and Auditory Senses

In this paper, we carry out QoE (Quality of Experience) assessment to investigate influences of olfactory and auditory senses on fairness for a networked virtual 3D object identification game with haptics. In the game, two players try to identify objects which are placed in a shared 3D virtual space. In the assessment, we carry out the game in four cases. Smells and sounds are presented in the first case, only sounds are done in the second case, and only smells are done in the third case. In the last case, we present neither smell nor sound. As a result, we demonstrate that the fairness deteriorates more largely as the difference in conditions between two users becomes larger.

3D Object Recognition by Classification Using Neural Networks

In this Paper, a classification method based on neural networks is presented for recognition of 3D objects. Indeed, the objective of this paper is to classify an object query against objects in a database, which leads to recognition of the former. 3D objects of this database are transformations of other objects by one element of the overall transformation. The set of transformations considered in this work is the general affine group.

Initial Object Segmentation for Video Object Plane Generation Using Cellular Neural Networks

MPEG 4 is a basic tool for interactivity and manipulation of video sequences. Video object segmentation is a key issue in defining the content of any video sequence, which is often divided into two steps: initial object segmentation and object tracking. In this paper, an initial object segmentation method for video object plane(VOP) generation using color information is proposed. Based on 3 by 3 linear templates, a cellular neural network (CNN) is used to implemented object segmentation. The Experimental results are presented to verify the efficiency and robustness of this approach.

基于SuperMap Objects的校园地下管网信息查询系统的实现

校园地下管网管理是校园后勤管理工作的重要组成部分,本文在介绍了校园地下管网管理的现状和存在问题的基础上,分析了校园管网系统要解决的问题及其研究意义。详细叙述了校园管网系统采用的管网数据组织方式和整体设计方案,包括数据库设计和系统功能设计等,并提出了系统一些主要功能的实现方法。以吉林建筑工程学院校园为例,利用SuperMap Objects进行二次开发实现对管网的查询、统计、图表打印输出,绘制纵、横断面图、爆管分析,缓冲分析、管线分析等功能,从而大大提高了校园管网管理工作的效率和质量。

基于特征融合和模板更新的孪生网络跟踪算法

针对现有孪生网络跟踪算法仅使用主干网络最后一层的特征进行相似度匹配,以及缺少有效模板更新策略的问题,提出基于多尺度特征融合和自适应模板更新的孪生网络跟踪算法。首先,结合深度过参数化卷积设计非填充单元,提取更深层的前景特征和语义背景;然后,设计新的全局-局部特征融合模块,充分聚合浅、中层特征的全局和局部信息,捕获丰富的浅层外观特征和中层过渡特征;最后,采用自适应模板更新机制在线更新模板。为验证算法的有效性,在公开数据集上对所提算法进行详尽评估,实验结果显示,所提算法在OTB2015和VOT2018数据集上的精确度分别达到0.878和0.588,GOT10K数据集上平均重叠率达到0.526,优于其他主流算法。

基于SuperMap Objects的等高线自动绘制方法的研究与实现

等高线是地形图中最常用的标识之一,在计算机地图制图中关于等高线自动生成问题占有很重要位置。为此,在分析等高线自动生成的方法后,利用SuperMap Objects平台对三角网的创建、等高线的自动绘制和优化功能进行开发,并通过导入外业采样点数据集对该方法进行了验证。

一种基于Subject-Action-Object三元组的知识基因提取方法

以专利引证网络为载体,从知识基因稳定性、遗传性以及变异性等基本特征出发,提出一种基于subject-action-object三元组的知识基因提取方法.应用连接度算法分析专利引证关系,挖掘引证专利和被引专利之间继承和发展的知识流,建立知识进化轨迹;利用文本语法分析技术,从专利权利要求书中提取subject-action-object三元组;基于语义词库WordNet进行语义加工,计算语义相似度,合并同义的subject-action-object三元组,绘制知识基因图谱.从美国专利数据库中采集了5 073项1975—1999年授权的数据挖掘领域的相关专利,分析了专利的地区分布情况和年度分布情况.从NBER(National Bureau of Economic Research)的专利数据集中查询得到专利引证关系,利用网络分析软件Pajek构建专利引证网络,作为实验数据样本,对所提出的知识基因提取方法进行验证.实验结果表明:所提取的subject-action-object三元组具备了知识基因稳定性、遗传性和变异性等特征,可以作为知识基因的一种表现形式.

强化学习和矩阵补全引导的多目标试卷生成

针对现有的试卷生成技术存在过多关注生成试卷的难易程度,而忽略了其他相关目标,例如质量、分数分布和技能覆盖范围的问题,提出一种强化学习和矩阵补全引导的多目标试卷生成方法,以优化试卷生成领域的特定目标。首先,运用深度知识追踪方法对学生之间的交互信息和响应日志进行建模以获取学生群体的技能熟练程度;其次,运用矩阵分解和矩阵补全方法对学生未做的习题进行得分预测;最后,基于多目标试卷生成策略,为提升Q网络的更新效率,设计一个Exam Q-Network函数逼近器以自动地选择合适的问题集来更新试卷组成。实验结果表明,相较于DEGA(Diseased-Enhanced Genetic Algorithm)、SSA-GA(Sparrow Search Algorithm-Genetic Algorithm)等模型,在试卷难度、合理性、准确性这3个指标上验证了所提模型在解决试卷生成场景的多重困境方面上效果显著。

深度学习驱动下的目标检测研究进展综述

近年来,深度学习在GPU高性能计算能力的加持下得到了迅速推广,并在安防、医疗、工业等领域实现了广泛应用。目标检测模型的性能也在稳步提高,从传统的目标检测方法逐渐过渡到基于卷积神经网络(CNN)深度学习的进一步应用,极大地节省了人力物力。通过参考大量文献,按照两阶段脉络梳理了目标检测的发展历程以及近年深度学习在目标检测领域内的研究进展,对比了在不同数据集上模型网络的性能,总结不同方法的优势与不足,并对领域内重要数据集作了归纳,还对目标检测算法的落地效果做了总结,特别是生活与科技中的实际应用(无人驾驶、医学图像、遥感等)。最后,还对深度学习驱动下目标检测在未来研究上的机遇和挑战作了展望。

等级型城市群应急物资储备库网络优化模型——以京津冀城市群为例

构建具有等级性、多目标特征的应急物资储备库网络,对于城市群应急物资储备库的良性互动和城市群应急物资储备库网络的协同发展具有重要现实意义。结合城市群实际情况,对传统的等级设施选址模型加以改进,以实现城市群内受灾点民众接受应急物资配置总满意度最大、应急物资储备库之间总关联度最高和应急物资储备建设与储存成本最小为目标,构建了适用于城市群应急物资储备库网络优化的等级型设施选址模型。针对所构建模型的等级性、多目标特点,对传统两阶段启发式算法进行拓展,设计了三阶段启发式算法加以求解。以京津冀城市群为例进行实证,优化结果表明:所构建模型稳健性较强,所设计算法能实现对模型的有效求解。京津冀城市群内应设立北京市、天津市、石家庄市等6个区域级应急物资储备库,且进一步形成由区域级、市级、县(市、区)级3个等级构成的应急物资储备库网络协作区。

基于关联交互和双边注意力的稀疏目标检测器

稀疏目标检测器Sparse R-CNN算法缺少对目标间关系的建模,导致网络对全局特征信息的利用较差,使检测效果不佳。为解决上述问题,提出关联交互模块,通过融合可学习的参数和与图像数据相关的目标间关联特征数据,增强目标之间的关联性;提出双边注意力机制,通过融合实例交互注意力信息和物体与物体间的关联注意力信息,增强对全局特征的交互。基于PASCAL VOC和MS COCO数据集的实验结果表明,该方法能够有效提升检测精度,整体性能优于原方法。

基于行波全频带特征的配电网故障行波波头标定方法

针对配电网行波波头标定方法易受噪声、波头畸变影响的问题,提出一种基于行波全频带特征的配电网故障行波波头标定方法。首先,根据行波高频段分量包含奇异点特征、行波中低频段分量不受噪声干扰的特点,提出利用行波全频带分量特征来标定行波,并分析了不同工况下利用行波全频带分量特征标定波头的优势。然后,设计并搭建基于目标检测模型的卷积神经网络(convolutional neural network,CNN),以行波全频带分量作为特征输入量,利用一维卷积核提取行波信号的波头特征。最后,结合特征金字塔网络与路径聚合网络结构,融合行波波头高中低频带特征,实现行波到达时刻的准确标定。与传统方法相比,所提方法在短线路、强噪声情况下具有较强的适应性,并且在微弱故障行波场景下也能够实现波头标定,具有良好的现场应用效果。