Multi-Modal Medical Image Fusion Based on Improved Parameter Adaptive PCNN and Latent Low-Rank Representation

Multimodal medical image fusion can help physicians provide more accurate treatment plans for patients, as unimodal images provide limited valid information. To address the insufficient ability of traditional medical image fusion solutions to protect image details and significant information, a new multimodality medical image fusion method(NSST-PAPCNNLatLRR) is proposed in this paper. Firstly, the high and low-frequency sub-band coefficients are obtained by decomposing the source image using NSST. Then, the latent low-rank representation algorithm is used to process the low-frequency sub-band coefficients;An improved PAPCNN algorithm is also proposed for the fusion of high-frequency sub-band coefficients. The improved PAPCNN model was based on the automatic setting of the parameters, and the optimal method was configured for the time decay factor αe. The experimental results show that, in comparison with the five mainstream fusion algorithms, the new algorithm has significantly improved the visual effect over the comparison algorithm,enhanced the ability to characterize important information in images, and further improved the ability to protect the detailed information;the new algorithm has achieved at least four firsts in six objective indexes.

Multimodal Medical Image Fusion Based on Parameter Adaptive PCNN and Latent Low-rank Representation

Medical image fusion has been developed as an efficient assistive technology in various clinical applications such as medical diagnosis and treatment planning.Aiming at the problem of insufficient protection of image contour and detail information by traditional image fusion methods,a new multimodal medical image fusion method is proposed.This method first uses non-subsampled shearlet transform to decompose the source image to obtain high and low frequency subband coefficients,then uses the latent low rank representation algorithm to fuse the low frequency subband coefficients,and applies the improved PAPCNN algorithm to fuse the high frequency subband coefficients.Finally,based on the automatic setting of parameters,the optimization method configuration of the time decay factorαe is carried out.The experimental results show that the proposed method solves the problems of difficult parameter setting and insufficient detail protection ability in traditional PCNN algorithm fusion images,and at the same time,it has achieved great improvement in visual quality and objective evaluation indicators.

Product Knowledge Representation and Integration Technology in Web-based Collaborative Design

Because of the complexity of modern product design,the web-based collaborative product design aroused considerable attention of manufacturers in the last few years with the development of Internet technology. But it is still hardly achievable due to the difficulty to share product knowledge from different designers and systems. In this paper,we firstly create an ontology-based product model,which consists of PPR (Product,Process and Resource) concept models and PPR characteristic models,to describe product knowledge. Afterwards,how to represent the model in XML is discussed in detail. Then the mechanism of product knowledge collection and integration from different application systems based on interface agents is introduced. At last,a web-based open-architecture product knowledge integrating and sharing prototype system AD-HUB is developed. An example is also given and it shows that the theory discussed in this paper is efficient to represent and integrate product knowledge in web-based collaborative design processes.

Face Recognition Algorithm Fusing Monogenic Binary Coding and Collaborative Representation

Monogenic binary coding （MBC） have been known to be effective for local feature extraction, while sparse or collaborative representation based classification （CRC） has shown interesting results in robust face recognition. In this paper, a novel face recognition algorithm of fusing MBC and CRC named M-CRC is proposed; in which the dimensionality problem is resolved by projection matrix. The proposed algorithm is evaluated on benchmark face databases, including AR, PolyU-NIR and CAS-PEAL. The results indicate a significant increase in the performance when compared with state-of-the-art face recognition methods.

Integrating absolute distances in collaborative representation for robust image classification

Conventional sparse representation based classification （SRC） represents a test sample with the coefficient solved by each training sample in all classes. As a special version and improvement to SRC, collaborative representation based classification （CRC） obtains representation with the contribution from all training samples and produces more promising results on facial image classification. In the solutions of representation coefficients, CRC considers original value of contributions from all samples. However, one prevalent practice in such kind of distance-based methods is to consider only absolute value of the distance rather than both positive and negative values. In this paper, we propose an novel method to improve collaborative representation based classification, which integrates an absolute distance vector into the residuals solved by collaborative representation. And we named it AbsCRC. The key step in AbsCRC method is to use factors a and b as weight to combine CRC residuals rescrc with absolute distance vector disabs and generate a new dviaetion r = a·rescrc b.disabs, which is in turn used to perform classification. Because the two residuals have opposite effect in classification, the method uses a subtraction operation to perform fusion. We conducted extensive experiments to evaluate our method for image classification with different instantiations. The experimental results indicated that it produced a more promising result of classification on both facial and non-facial images than original CRC method.

Low-Rank and Sparse Representation with Adaptive Neighborhood Regularization for Hyperspectral Image Classification

Low-Rank and Sparse Representation(LRSR)method has gained popularity in Hyperspectral Image(HSI)processing.However,existing LRSR models rarely exploited spectral-spatial classification of HSI.In this paper,we proposed a novel Low-Rank and Sparse Representation with Adaptive Neighborhood Regularization(LRSR-ANR)method for HSI classification.In the proposed method,we first represent the hyperspectral data via LRSR since it combines both sparsity and low-rankness to maintain global and local data structures simultaneously.The LRSR is optimized by using a mixed Gauss-Seidel and Jacobian Alternating Direction Method of Multipliers(M-ADMM),which converges faster than ADMM.Then to incorporate the spatial information,an ANR scheme is designed by combining Euclidean and Cosine distance metrics to reduce the mixed pixels within a neighborhood.Lastly,the predicted labels are determined by jointly considering the homogeneous pixels in the classification rule of the minimum reconstruction error.Experimental results based on three popular hyperspectral images demonstrate that the proposed method outperforms other related methods in terms of classification accuracy and generalization performance.

Extraction method of typical IEQ spatial distributions based on low-rank sparse representation and multi-step clustering

Indoor environment quality(IEQ)is one of the most concerned building performances during the operation stage.The non-uniform spatial distribution of various IEQ parameters in large-scale public buildings has been demonstrated to be an essential factor affecting occupant comfort and building energy consumption.Currently,IEQ sensors have been widely employed in buildings to monitor thermal,visual,acoustic and air quality.However,there is a lack of effective methods for exploring the typical spatial distribution of indoor environmental quality parameters,which is crucial for assessing and controlling non-uniform indoor environments.In this study,a novel clustering method for extracting IEQ spatial distribution patterns is proposed.Firstly,representation vectors reflecting IEQ distributions in the concerned space are generated based on the low-rank sparse representation.Secondly,a multi-step clustering method,which addressed the problems of the“curse of dimensionality”,is designed to obtain typical IEQ distribution patterns of the entire indoor space.The proposed method was applied to the analysis of indoor thermal environment in Beijing Daxing international airport terminal.As a result,four typical temperature spatial distribution patterns of the terminal were extracted from a four-month monitoring,which had been validated for their good representativeness.These typical patterns revealed typical environmental issues in the terminal,such as long-term localized overheating and temperature increases due to a sudden influx of people.The extracted typical IEQ spatial distribution patterns could assist building operators in effectively assessing the uneven distribution of IEQ space under current environmental conditions,facilitating targeted environmental improvements,optimization of thermal comfort levels,and application of energy-saving measures.

Weighted Sparse Image Classification Based on Low Rank Representation

The conventional sparse representation-based image classification usually codes the samples independently,which will ignore the correlation information existed in the data.Hence,if we can explore the correlation information hidden in the data,the classification result will be improved significantly.To this end,in this paper,a novel weighted supervised spare coding method is proposed to address the image classification problem.The proposed method firstly explores the structural information sufficiently hidden in the data based on the low rank representation.And then,it introduced the extracted structural information to a novel weighted sparse representation model to code the samples in a supervised way.Experimental results show that the proposed method is superiority to many conventional image classification methods.

Knowledge Graph Representation Reasoning for Recommendation System

In view of the low interpretability of existing collaborative filtering recommendation algorithms and the difficulty of extracting information from content-based recommendation algorithms,we propose an efficient KGRS model.KGRS first obtains reasoning paths of knowledge graph and embeds the entities of paths into vectors based on knowledge representation learning TransD algorithm,then uses LSTM and soft attention mechanism to capture the semantic of each path reasoning,then uses convolution operation and pooling operation to distinguish the importance of different paths reasoning.Finally,through the full connection layer and sigmoid function to get the prediction ratings,and the items are sorted according to the prediction ratings to get the user’s recommendation list.KGRS is tested on the movielens-100k dataset.Compared with the related representative algorithm,including the state-of-the-art interpretable recommendation models RKGE and RippleNet,the experimental results show that KGRS has good recommendation interpretation and higher recommendation accuracy.

Studying Design and Use of Healthcare Technologies in Interaction: The Social Learning Perspective in a Dutch Quality Improvement Collaborative Program

Designing technologies is a process that relies on multiple interactions between design and use contexts. These interactions are essential to the development and establishment of technologies. This article seeks to understand the attempts of healthcare organisations to integrate use contexts into the design of healthcare technologies following insights of the theoretical approaches of social learning and user representations. We present a multiple case study of three healthcare technologies involved in improving elderly care practice. These cases were part of a Dutch quality improvement collaborative program, which urged that development of these technologies was not “just” development, but should occur in close collaboration with other parts of the collaborative program, which were more focused on implementation. These cases illustrate different ways to develop technologies in interaction with use contexts and users. Despite the infrastructure of the collaborative program, interactions were not without problems. We conclude by arguing that interactions between design and use are not naturally occurring phenomena, but must be actively organised in order to create effects.

任务协作表示增强的要素及关系联合抽取模型

对文本中诸如实体与关系、事件及其论元等要素及其特定关系的联合抽取是自然语言处理的一项关键任务.现有研究大多采用统一编码或参数共享的方式隐性处理任务间的交互,缺乏对任务之间特定关系的显式建模,从而限制模型充分利用任务间的关联信息并影响任务间的有效协同.为此,提出了一种基于任务协作表示增强的要素及关系联合抽取模型(Task-Collaboration Representation Enhanced model for joint extraction of elements and relationships,TCRE).该模型旨在从多个阶段处理任务间的特定关系,帮助子任务进行更细致的调节和优化,促进整体性能的提升.在三个关系抽取和一个事件抽取数据集上进行实验,TCRE在实体识别和关系提取任务上平均性能分别提高0.57%和0.77%,在触发词识别和论元角色分类任务上分别提高0.7%和1.4%.此外,TCRE还显示出在缓解“跷跷板现象”方面的作用.

MCM-ICE:联合独立编码和协同编码的多模态分类模型

多模态数据处理是一个重要的研究领域,它可以通过结合文本、图像等多种信息来提高模型性能.然而,由于不同模态之间的异构性以及信息融合的挑战,设计有效的多模态分类模型仍然是一个具有挑战性的问题.本文提出了一种新的多模态分类模型——MCM-ICE,它通过联合独立编码和协同编码策略来解决特征表示和特征融合的挑战.MCM-ICE在Fashion-Gen和Hateful Memes Challenge两个数据集上进行了实验,结果表明该模型在这两项任务中均优于现有的最先进方法.本文还探究了协同编码模块Transformer输出层的不同向量选取对结果的影响,结果表明选取[CLS]向量和去除[CLS]的向量的平均池化向量可以获得最佳结果.消融研究和探索性分析支持了MCM-ICE模型在处理多模态分类任务方面的有效性.

多机协同自主任务规划系统研究综述

针对多机协同自主任务规划显著提升无人机任务感知效能、提高任务执行能力的现状,对其关键技术进行阐述,主要包括知识表示、通感一体化、任务调度及航迹规划等技术。针对知识表示技术,阐述基于任务环境上下文感知的知识库构建方法,进而对多域融合知识图谱构建、动态知识图谱更新与共享方法进行分析总结;针对通感一体化技术,分析了环境适变、灵活可扩的多机协同通感一体化架构,进而揭示多机协同通感一体化理论能限,阐述面向任务差异性需求的资源共享方法;针对任务调度及航迹规划技术,阐述资源适配的多机协同自主任务调度方案,并对基于动力学模型的航迹控制策略及不完美环境下的鲁棒控制机制进行分析总结。

多任务联合学习的图卷积神经网络推荐

基于图神经网络的协同过滤推荐可以更有效地挖掘用户项目之间的交互信息,但其性能依然受到数据稀疏和表征学习质量不高问题的影响,因此提出一种多任务联合学习的图卷积神经网络推荐(multi-task joint learning for graph convolutional neural network recommendations,MTJL-GCN)模型。利用图神经网络在用户-项目交互图上所聚集到的同质结构信息与初始嵌入信息形成结构邻居关系,设计节点邻居关系的对比学习辅助任务来缓解数据稀疏问题;向节点的原始表征添加随机的统一噪声进行表征级数据增强,构建节点表征关系的对比学习辅助任务,并提出直接优化对齐性和均匀性两个属性的学习目标来提高表征学习质量;将图协同过滤推荐任务与对比学习辅助任务和直接优化学习目标进行联合训练,从而提升推荐性能。在Amazon-books和Yelp2018两个公开数据集上进行实验,该模型在Recall@k和NDCG@k两个推荐性能指标上的表现均优于基线模型,证明了MTJL-GCN模型的有效性。

基于保真度加权判别协同竞争表示的鲁棒图像分类

为了深度挖掘类别之间的信息,提升方法鲁棒性和准确度,提出一种基于加权判别式协同竞争表示的鲁棒图像分类方法。该文将所有类之间的判别和竞争协作表示集成到统一模型中;在模型中引入两个判别约束和加权类别表示系数的约束,进一步提升类别对表征的贡献率;引入一种具有保真度的鲁棒算法,有效提升对噪声的鲁棒性。对6组图像数据集进行实验验证,结果证明提出的方法具有更高的分类精度与鲁棒性。

双层协同结构改进的高光谱异常检测算法

在高光谱目标检测领域,基于协同表示的算法展现出优异的性能,但其一直存在异常点对背景字典的污染问题,这一定程度上影响了算法的检测性能。本文提出了一种改进的协同表示高光谱异常检测算法,设计了双层协同表示结构,首先利用第一层协同表示算法将大部分异常点检出,并用其邻域进行背景纯化,剔除已检出的异常点对背景字典的污染,然后用纯化的背景字典来预测背景,进而在第二层采用协同表示进行异常检测。仿真试验表明,通过简单的双层协同表示结构可以有效地减轻异常点对背景污染的问题。该算法的检测性能相对基础的协同表示算法有显著的提升,与现有的算法对比,具有相对较好的检测效果。

基于样本内外协同表示和自适应融合的多模态学习方法

多模态机器学习是一种新的人工智能范式,结合各种模态和智能处理算法以实现更高的性能.多模态表示和多模态融合是多模态机器学习的2个关键任务.目前,多模态表示方法很少考虑样本间的协同,导致特征表示缺乏鲁棒性,大部分多模态特征融合方法对噪声数据敏感.因此,在多模态表示方面,为了充分学习模态内和模态间的交互,提升特征表示的鲁棒性,提出一种基于样本内和样本间多模态协同的表示方法.首先,分别基于预训练的BERT,Wav2vec 2.0,Faster R-CNN提取文本特征、语音特征和视觉特征;其次,针对多模态数据的互补性和一致性,构建模态特定和模态共用2类编码器,分别学习模态特有和共享2种特征表示;然后,利用中心矩差异和正交性构建样本内协同损失函数,采用对比学习构建样本间协同损失函数;最后,基于样本内协同误差、样本间协同误差和样本重构误差设计表示学习函数.在多模态融合方面,针对每种模态可能在不同时刻表现出不同作用类型和不同级别的噪声,设计一种基于注意力机制和门控神经网络的自适应的多模态特征融合方法.在多模态意图识别数据集MIntRec和情感数据集CMU-MOSI,CMU-MOSEI上的实验结果表明,该多模态学习方法在多个评价指标上优于基线方法.

融合结构邻居和语义邻居的解耦图对比学习推荐模型

基于GCN的协同过滤模型在推荐领域取得了较好的效果,但现有的图协同过滤学习方法通常不区分用户和项目的交互关系,不易挖掘用户行为的潜在意图.因此,提出了一种融合结构邻居和语义邻居的解耦图对比学习推荐模型.首先,将用户和项目嵌入投影到独立空间进行意图解耦;其次,在图传播阶段,依据用户和项目的意图特征挖掘其潜在语义邻居,根据意图相似性对结构邻居和语义邻居进行解耦表征学习,生成用户和项目的完整高阶表示.在对比学习阶段,对节点进行随机扰动并生成对比视图,构建结构和语义的对比学习任务;最后,根据多任务策略,对监督任务和对比学习任务进行联合优化.在真实数据集Yelp2018和Amazon-Book上的实验表明,提出的模型相比最优基准模型NCL在两个数据集上的Recall@20指标提高了7.54%、5.65%,NDCG@20指标提高了8.57%、6.28%.

Representation learning: serial-autoencoder for personalized recommendation

Nowadays,the personalized recommendation has become a research hotspot for addressing information overload.Despite this,generating effective recommendations from sparse data remains a challenge.Recently,auxiliary information has been widely used to address data sparsity,but most models using auxiliary information are linear and have limited expressiveness.Due to the advantages of feature extraction and no-label requirements,autoencoder-based methods have become quite popular.However,most existing autoencoder-based methods discard the reconstruction of auxiliary information,which poses huge challenges for better representation learning and model scalability.To address these problems,we propose Serial-Autoencoder for Personalized Recommendation(SAPR),which aims to reduce the loss of critical information and enhance the learning of feature representations.Specifically,we first combine the original rating matrix and item attribute features and feed them into the first autoencoder for generating a higher-level representation of the input.Second,we use a second autoencoder to enhance the reconstruction of the data representation of the prediciton rating matrix.The output rating information is used for recommendation prediction.Extensive experiments on the MovieTweetings and MovieLens datasets have verified the effectiveness of SAPR compared to state-of-the-art models.

基于人机协作迭代分析的网络协议逆向方法

协议逆向分析在网络安全领域具有重要意义,现有方法主要依靠计算机进行自动化推断,并未考虑人的经验知识干预条件下可能带来的信息增益,存在准确性较低的问题。鉴于此,提出了一种基于人机协作迭代分析的网络协议逆向方法,该方法基于人机协作协议逆向分析框架,利用XML将人的经验知识进行知识表征,通过迭代式修正阶段性分析结果,克服了因缺乏知识辅助而导致的协议词法、语法及状态机推断准确率较低的问题。以典型工控协议数据样本为例进行了实验和对比分析,结果表明了该方法的有效性和可行性。