基于ER Rule的多分类器汽车评论情感分类研究

该文针对汽车评论语料的情感二分类问题,提出一种基于证据推理规则的多分类器融合的情感分类方法。在情感特征构建方面,通过实验对比不同特征模型对分类结果的影响,并改进传统的TFIDF权重计算方法。同时,在此基础上使用ER Rule融合不同分类器进行文本情感极性分析,并考虑各分类器的权重和可靠度。最后,爬取汽车网站上的评论数据对上述方法进行测试,并用公开的中文酒店评论语料数据进行了验证,结果表明该方法能够有效集成不同分类器的优点,与传统机器学习分类算法相比,其结果在Recall,F1值和Accuracy三个指标上得到了提高,与目前流行的深度学习算法和集成学习算法相比,其结果总体占优。

Research on Agricultural Ontology and Fusion Rules Based Knowledge Fusion Framework

Currently, knowledge-based sharing and service system has been a hot issue and knowledge fusion, especially for implicit knowledge discovery, becomes the core of knowledge processing and optimization in the system. In the research, a knowledge fusion framework based on agricultural ontology and fusion rules was pro- posed, including knowledge extraction, clearing and annotation modules based on a- gricultural ontology, fusion rule construction, choosing and evaluation modules based on agricultural ontology and knowledge fusion module for users＇ demands. Finally, the significance of the framework to system of agricultural knowledge services was proved with the help of a case.

New method for detection fusion of MAC based on DCM and NP rule

The problem of distributed detection fusion using multiple sensors for remote underwater target detection is studied. Considering that multiple access channel （MAC） schemes are able to offer high efficiency in bandwidth usage and consume less energy than the parallel access channel （PAC）, the MAC scheme is introduced into the underwater target detection field. The model of underwater distributed detection fusion based on MAC schemes is established. A new method for detection fusion of MAC based on deflection coefficient maximization （DCM） and Neyman-Pearson （NP） rule is proposed. Under the power constraint of local sensors, this paper uses the DCM theory to derive the optimal weight coefficients and offsets. The closed-form expressions of detection probability and false alarm probability for fusion systems are obtained. The optimal detection performance of fusion systems is analyzed and deeply researched. Both the theory analysis and simulation experiments indicate that the proposed method could improve the detection performance and decrease the error probability effectively under power constraints of local sensors and low signal to noise ratio.

Optimal decision fusion given sensor rules

When all the rules of sensor decision are known, the optimal distributeddecision fusion, which relies only on the joint conditional probability densities, can be derivedfor very general decision systems. They include those systems with interdependent sensorobservations and any network structure. It is also valid for m-ary Bayesian decision problems andbinary problems under the Neyman-Pearson criterion. Local decision rules of a sensor withcommunication from other sensors that are optimal for the sensor itself are also presented, whichtake the form of a generalized likelihood ratio test. Numerical examples are given to reveal someinteresting phenomena that communication between sensors can improve performance of a senordecision, but cannot guarantee to improve the global fusion performance when sensor rules were givenbefore fusing.

基于复合特征规则库的多源POI融合方法

多源POI融合是指将不同来源的POI数据集成为一个统一、准确且全面的数据库。POI数据作为国家地理信息公共服务平台(天地图)的重要数据资源之一,如何有效融合其他多种POI数据源,使天地图POI数据现势性、准确性及丰富性不断提高,是天地图建设的关键技术之一。当前有关POI数据融合方法的研究在测绘、地理信息系统及大数据和人工智能领域都受到了广泛关注,并取得了一定进展。但由于POI文本类属性的复杂性与多样性,在实际工程应用时如何有效判断POI的属性相似度仍面临挑战。针对天地图POI数据快速更新的迫切需要,以及当前多源POI数据融合方法存在的不足,本文提出一种基于复合特征规则库的多源POI融合方法,为天地图的数据更新与母库建设提供技术支撑。

基于模糊数学的多源异构数据融合模型

针对多源异构型数据来源复杂、结构特殊,导致其融合难度较大的问题,为提升数据融合效率与准确性,提出一种基于模糊数学的多源异构数据融合模型.首先,利用联邦加权平均融合策略,整合从各传感器传输至数据级融合层中的元数据,得到数据级融合结果;其次,结合主成分分析法与典型相关分析法,提取出由网络本体语言统一后数据的特征,完成特征级数据融合;再次,根据模糊数学理论建立、更新模糊规则库,通过决策融合算法,得到决策级融合结果;最后,将上述不同层级的数据融合结果结合建立数据融合模型,得到最终的数据融合结果.实验结果表明,该方法的最大协方差值和绝对误差值不超过0.15,最短融合时间仅为12.6 ms.该方法的融合精度和稳定性较好,时效性与抗扰性均具有显著的优越性.

元宇宙与新质生产力的法治化融合:机理、风险与进路

党的二十届三中全会强调了健全因地制宜发展新质生产力体制机制的重要意义,这无疑为元宇宙产业的进步提供了坚实的政策支持。元宇宙与新质生产力具有深度耦合与相互塑造之关联,前者通过集成数字技术、场景应用赋能、推动产业变革,成为新质生产力的重要样态。然而,当前元宇宙的发展与落地,面临着个体权益保护、社会经济稳定、国家政治维护等方面风险,制约了其赋能效应的发挥。鉴此,亟需以习近平总书记关于新质生产力的重要论述为指导,基于元宇宙的技术特性,构建与其相适配的法治秩序,即明确伦理规范原则,贯彻全流程管控理念;建立精细化兼具灵活性的监管体系;夯实基础技术,推进包容审慎监管,以赋能新质生产力发展。

基于多跳分簇算法的异构融合通信网络节点负载均衡方法

针对网络节点负载不均衡、节点能量消耗较大、网络吞吐量较低的问题,提出基于多跳分簇算法的异构融合通信网络节点负载均衡方法。依据异构融合通信网络实时(RT)和非实时(NRT)业务的服务质量满意度,应用效用函数结合三角模融合算子,将重载网络通信业务转移至轻载网络,实现异构融合通信网络业务负载均衡;运用多跳分簇路由算法,依据节点位置和其所剩能量选取簇头,通过减少网络边缘的簇头数量,节省网络能量消耗,通过簇头节点剩余能量和链路权值大小选取下一路由,构建簇间路由通信机制,实现异构融合通信网络节点负载均衡。在实验验证方面,在5.5×15^(3)个周期时,存货节点为0,吞吐量最高可达到13.5×15^(4)bit,出色地完成异构融合通信网络节点负载均衡,合理选取簇头节点,减少节点能量的消耗,提升节点生存周期和网络吞吐量。

基于改进证据理论的冲突证据融合方法

为解决证据理论中Dempster组合规则融合高度冲突证据效果不佳的问题,提出一种同时考虑证据重要性与可靠性的综合权重生成方法和基于加权复数基本概率分配函数的证据融合方法。以提高证据融合结果的收敛性能和诊断精度为目标,建立相应的优化证据融合模型。实验结果表明,所提方法能够有效识别并处理证据冲突,克服证据加权融合过程中剩余信度被完全抛弃的问题,获得更好的融合结果和更快的收敛速度,提高诊断精度。

基于视觉传达技术的激光图像多级融合方法研究

设计了基于视觉传达技术的激光图像多级融合方法,以获得突出的视觉传达效果。首先采用改进单尺度Retinex算法提取原始激光图的反射图像,并通过高斯-拉普拉斯算法的重构获得的多尺度彩色图像,实现原始激光图像的增强,然后采用深度堆叠卷积神经网络对获得高、低频图像,并依据最大局部方差融高频图像,根据匹配度与阈值的对比融合低频图像,最后实验结果表明:堆叠CNN数量为4时,融合后的激光图像视觉传达效果最优,该方法增强后的激光图像局部细节信息丰富、色彩饱满度好,融合图像的图像最大灰度值频率仅为0.015。

基于卷积神经网络的红外与可见光图像融合方法

针对当前红外与可见光图像融合方法存在融合效果差、效率低等问题,为了获得更优的红外与可见光图像融合结果,提出了基于卷积神经网络的红外与可见光图像融合方法。首先收集待融合红外与可见光图像,采用Retinex算法对图像进行增强操作,提升图像亮度和细节信息,然后采用卷积神经网络提取图像融合特征,并设计红外与可见光图像融合规则,根据规则得到图像融合结果,最后应用多个数据集进行红外与可见光图像融合性能测试实验,结果表明,卷积神经网络的图像融合后整体视觉效果好,重要细节信息丰富,熵和平均梯度的值超过了6,融合时间低于1 s,整体性能优于其它红外与可见光图像对比融合方法。

知识辅助的空中目标综合识别

现代战场环境日益复杂,随着空中机载装备技术的升级,海量多源异构传感器数据不可避免地出现信息不一致、不完备问题.传统面向机载多源传感器量测数据的融合处理方法忽略传感特征间的相关性,单依赖物理传感器的数据驱动形成封闭识别系统.考虑到专家认知、领域参数、属性规则等知识能以专家经验、规则约束等辅助认知形式在目标综合识别的模型构建、推理识别等环节起到指导作用,本文提出一种知识辅助的空中目标类型综合识别方法,利用上述知识,首先构建典型空中目标特征军事作战知识图谱,提取关键特征参数、识别规则阈值等建立目标辨识框架关联关系模型;然后在特征级识别、决策级识别层分别构建数据基本信任指派与证据冲突可信度;此外,针对证据出现高冲突情况制定时域融合规则,引入历史数据重构调整数据时序融合权重因子;最后在静态推理与动态融合下分层实现异构多源传感器的置信类型综合识别.本文在典型空中目标类型识别任务下识别准确率优于现有算法,验证了所提方法的有效性.

基于层内和层间融合注意力的家族恶意域名检测

针对当前家族恶意域名检测方法在新出现或新变种恶意域名的检测方面仍存在精度低、漏报高等问题,提出一种基于层内和层间融合注意力的家族恶意域名检测的新方法。首先,利用深度自编码网络将域名集逐层编码压缩到空间特征中,并借助自注意力机制强化域名字符串中关键字符的表达能力;其次,利用交叉注意力建立双分支网络输入端的关联,促进分支间深层信息的交流;最后,计算待测域名映射特征与交互特征集之间的相似度对比。实验证明所设计方法的准确率为98.21%,该方法对保障网络安全、预防新型域名入侵攻击具有重要的现实意义。

Multimodal Medical Image Fusion in Non-Subsampled Contourlet Transform Domain

Multimodal medical image fusion is a powerful tool for diagnosing diseases in medical field. The main objective is to capture the relevant information from input images into a single output image, which plays an important role in clinical applications. In this paper, an image fusion technique for the fusion of multimodal medical images is proposed based on Non-Subsampled Contourlet Transform. The proposed technique uses the Non-Subsampled Contourlet Transform (NSCT) to decompose the images into lowpass and highpass subbands. The lowpass and highpass subbands are fused by using mean based and variance based fusion rules. The reconstructed image is obtained by taking Inverse Non-Subsampled Contourlet Transform (INSCT) on fused subbands. The experimental results on six pairs of medical images are compared in terms of entropy, mean, standard deviation, QAB/F as performance parameters. It reveals that the proposed image fusion technique outperforms the existing image fusion techniques in terms of quantitative and qualitative outcomes of the images. The percentage improvement in entropy is 0% - 40%, mean is 3% - 42%, standard deviation is 1% - 42%, QAB/Fis 0.4% - 48% in proposed method comparing to conventional methods for six pairs of medical images.

Target recognition based on modified combination rule

Evidence theory is widely used in the field of target recognition. The invalidation problem of this theory when dealing with highly conflict evidences is a research hotspot. Several alternatives of the combination rule are analyzed and compared. A new combination approach is proposed. Calculate the reliabilities of evidence sources using existing evidences. Construct reliabilities judge matrixes and get the weights of each evidence source. Weight average all inputted evidences. Combine processed evidences with D-S combination rule repeatedly to identify a target. The application in multi-sensor target reeognition as well as the comparison with typical alternatives all validated that this approach can dispose highly conflict evidences efficiently and get reasonable reeognition results rapidly.

Scheme of Cooperative Spectrum Sensing Based on Adaptive Decision Fusion Algorithm

Spectrum sensing is one of the core technologies for cognitive radios （CR）, where reliable detection of the signals of primary users （PUs） is precondition for implementing the CR systems. A cooperative spectrum sensing scheme based on an adaptive decision fusion algorithm for spectrum sensing in CR is proposed in this paper. This scheme can estimate the PU prior probability and the miss detection and false alarm probabilities of various secondary users （SU）, and make the local decision with the Chair-Varshney rule so that the decisions fusion can be done for the global decision. Simulation results show that the false alarm and miss detection probabilities resulted from the proposed algorithm are significantly lower than those of the single SU, and the performance of the scheme outperforms that of the cooperative detection by using the conventional decision fusion algorithms.

Knowledge Fusion and Synchronization over Ubiquitous Ontology Mapping

With the rapid development and popularization of web services, the available information types and structure are becoming more and more complex and challenging. Actually web services involve the need for dynamic integration and transparent knowledge integration, in light of the urgent information changing track. Under this situation, the traditional search engine and information integration cannot finish this challenge, thereby bringing the opportunity for knowledge fusion and synchronization. This paper proposes a multi-matching strategy ontology mapping method for web information, i.e., ubiquitous ontology mapping method (U-Mapping), which can be viewed as a base collection of information on multiple ontologies made to appear anytime and everywhere. This approach is usually built independently by different information providers, avoiding the grammatical and semantic conflict. Finally, the ontology case information can be utilized under the consolidation of the U-Mapping, concerning language technology and machine learning methods.

New Algorithm for CBR-RBR Fusion with Robust Thresholds

The case-based reasoning（CBR） and rule-based reasoning（RBR） fusion systems include a diverse range of fusion methods and their tasks are characterized by interleaving combination of the reasoning procedures. Existing approaches cannot clarify the complex relationships between data from the knowledge sources nor uniformly represent the heterogeneous case and rule knowledge in one fusion space. As a result, existing approaches fail to solve system fragility due to knowledge uncertainty and reasoning unreliability. For the purpose of addressing the difficulties, a novel algorithm for CBR-RBR fusion with robust thresholds（CRFRT） is proposed. Heterogeneous case and rule knowledge are uniformly represented in one defined fusion unitary space. The robust thresholds have been achieved to distinguish the complex relationships between meta-knowledge in the fusion space and to enhance system capacity of knowledge identification. Furthermore, fusion reasoning strategies are constructed for CRFRT and its procedure based on which robust solution of the fusion reasoning problem is obtained. Finally, CRFRT is validated by benchmark problems in machine learning. Compared with other CBR and RBR approaches, the reasoning efficiency and accuracy are increased by 5% and 2.2% respectively. The variations of system accuracy are decreased by 2% to 3.8%. The above results show that the CRFRT algorithm boosts the system＇s effectiveness and robustness. The proposed CRFRT can solve the fragility of complex intelligence decision system and give quality performance for fault diagnosis.

Multimodal Medical Image Fusion Methods Based on Improved Discrete Wavelet Transform

Objective This paper proposed a novel algorithm of discrete wavelet transform(DWT) which is used for multimodal medical image fusion. Methods The source medical images are initially transformed by DWT followed by fusing low and high frequency sub-images. Then, the "coefficient absolute value" that can provide clear and detail parts is adapted to fuse high-frequency coefficients, where as the "region energy ratio" which can efficiently preserve most information of source images is employed to fuse low-frequency coefficients. Finally, the fused image is reconstructed by inverse wavelet transform. Results Visually and quantitatively experimental results indicate that the proposed fusion method is superior to traditional wavelet transform and the existing fusion methods. Conclusion The proposed method is a feasible approach for multimodal medical image fusion which can obtain more efficient and accurate fusions results even in the noise environment.

基于关联规则挖掘的多学科知识融合研究——以新冠肺炎研究领域为例

[目的/意义]挖掘高强度关联学科,揭示多学科知识融合规律,有助于更好地把握和推动多学科知识融合。[方法/过程]从Web of Science核心集获取新冠肺炎主题论文,采用Apriori算法挖掘参考文献所属学科的频繁项集和强关联规则,揭示知识融合特征。以一项强关联规则为例,结合关键词聚类分析,识别该学科组合在知识融合后形成的热门主题。[结果/结论]新冠肺炎研究的知识来源非常广泛,跨学科知识融合十分普遍,关联规则挖掘提供了一种识别和预测强关联学科组合及其知识融合趋势的新方案。