蚁群遗传算法的多目标优化

为了求解带有约束条件的多目标函数优化问题,提出基于连续空间优化的多目标蚁群遗传算法。针对多目标优化问题的特点,定义连续空间中利用信息量指导遗传搜索策略和信息更新方法,将信息量指导遗传搜索、优秀决策引入、决策集更新、改变算法终止条件等方式相结合,有效地加速了搜索的收敛速度,控制了Pareto最优决策集的数量,扩大了决策的分布范围,维持了决策的多样性。数值实验说明该算法能够快速找到一组分布广泛的Pareto最优决策。     

关于扩充转移网络的研究

随着因特网的普及,计算机整体性能已经大幅提高,信息处理量也出现爆炸式增长,在这种情况下,要求计算机对我们的母语（自然语言）理解日益迫切。自然语言理解的主流技术一直是句法--语义分析。本文研究了扩充转移网络的描述语言的语法,给出了扩充转移网络的分析算法,并通过实例解析了这种算法的特点。     

基于改进三角模糊VIKOR法的用户储能系统配置方案综合评估

针对不确定环境下用户储能系统配置方案评估决策,提出一种基于改进三角模糊多准则妥协解排序(VIKOR)法的评估模型。首先,运用扎根理论构建评估指标集,并采用灰色关联-粗糙集方法进行指标筛选,形成评估指标体系。然后,采用主、客观相结合的方法计算指标组合权重,以提高其准确性,其中主观权重由模糊层次分析(FAHP)法求得,客观赋权法由改进标准间重要性相关性(CRITIC)法求得。最后,考虑指标之间的冲突性与模糊性,运用改进三角模糊VIKOR法对配置方案评估与排序比选。通过仿真分析,验证了本文所建模型的有效性和可行性。     

Residual Feature Attentional Fusion Network for Lightweight Chest CT Image Super-Resolution

The diagnosis of COVID-19 requires chest computed tomography (CT). High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease, so it is of clinical importance to study super-resolution (SR) algorithms applied to CT images to improve the resolution of CT images. However, most of the existing SR algorithms are studied based on natural images, which are not suitable for medical images; and most of these algorithms improve the reconstruction quality by increasing the network depth, which is not suitable for machines with limited resources. To alleviate these issues, we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution (RFAFN). Specifically, we design a contextual feature extraction block (CFEB) that can extract CT image features more efficiently and accurately than ordinary residual blocks. In addition, we propose a feature-weighted cascading strategy (FWCS) based on attentional feature fusion blocks (AFFB) to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information. Finally, we suggest a global hierarchical feature fusion strategy (GHFFS), which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels. Numerous experiments show that our method performs better than most of the state-of-the-art (SOTA) methods on the COVID-19 chest CT dataset. In detail, the peak signal-to-noise ratio (PSNR) is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at SR compared to the suboptimal method, but the number of parameters and multi-adds are reduced by 22K and 0.43G, respectively. Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.     

基于最大熵模型的汉语词义消歧与标注方法

分析最大熵模型开源代码的原理和各参数的意义,采用频次和平均互信息相结合特征筛选和过滤方法,用Delphi语者编程实现汉语词义消歧的最大熵模型,运用GIS（Generalized Iterative Scaling）算法计算模型的参数。结合一些语占知识规则解决训练语料的数据稀疏问题,所实现的汉语词义消歧与标注系统,对800多个多义词进行词义标注,取得了较好的标注正确率。     

A review on cost allocation methods in collaborative transportation

Collaboration in transportation between two or more agents is becoming an important approach to find efficient solutions or plans. Efficiency can be measured in, for example, lower cost or more flexibility. An important aspect of the collaboration is to decide on how to share the benefits—for example, cost, profit, or resources. There are many sharing mechanisms or cost allocations proposed in the literature. Some are based on simple proportional rules and others are based on theoretical concepts found in game theory. We provide a survey on cost allocation methods found in the literature on collaborative transportation, including problems on planning, vehicle routing, traveling salesman, distribution, and inventory. A total of 55 scientific articles compose the main part of the survey, most of them published between 2010 and 2015. We identify more than 40 cost allocation methods used in this stream of literature. We describe the theoretical basis for the main methods as well as the cases where they are used. We also report savings from the collaborations when they are based on industrial data. Some directions for future research are discussed.     

产品评论中领域情感词典的构建

领域情感词典是情感分析最重要的基础。由于产品评论的数量巨大、领域众多,如何自动构建领域情感词典已经成为近年来的一个研究热点。该文提出了一个两阶段的领域情感词典构建算法。第一阶段,利用情感词间的点互信息和上下文约束,使用基于约束的标签传播算法构造基本情感词典;第二阶段,根据情感冲突的频率来识别领域相关情感词,并根据其上下文约束以及修饰的特征完善领域情感词典。实验结果表明,该方法在实际产品评论数据集上取得了较好的效果。
     

基于高斯词长特征的中文分词方法

中文分词是中文信息处理的基础,在语音合成、中外文翻译、中文检索、文本摘要等方面均有重要应用。在中文分词的任务中,存在的主要问题在于可用有效特征较少,分词准确率较低,如何有效的获取和使用分词特征是关键。该文从中文文本生成的过程出发,基于词长噪声的高斯分布特性,提出利用上下文的词长特征作为分词特征。实验表明,在封闭测试中,采用条件随机场模型,使用该特征对现有的实验结果有提高作用。
     

Application of fuzzy sets to manufacturing/distribution planning decisions in supply chains

In the real-world manufacturing/distribution planning decision (MDPD) integration problems in supply chains, the environmental coefficients and parameters are normally imprecise due to incomplete and/or unavailable information. This work presents a fuzzy linear programming approach based on the possibility theory. It applies this approach to solve multi-product and multi-time period MDPD problems with imprecise goals and forecast demand by considering the time value of money of related operating cost categories. The proposed approach attempts to minimize the total manufacturing and distribution costs by considering the levels of inventory, subcontracting and backordering, the available machine capacity and labor levels at each source, forecast demand and available warehouse space at each destination. This study utilizes an industrial case study to demonstrate the feasibility of applying the proposed approach to practical MDPD problems. The primary contribution of this paper is a fuzzy mathematical programming methodology for solving the MDPD integration problems in uncertain environments.     

Adoption of Open Source Software: The role of social identification

While the benefits of incorporating Open Source Software (OSS) into personal and organizational systems have been widely touted, OSS must be adopted and used by end users before these benefits can be realized. Drawing on research in information systems and sociology, this study develops and evaluates an integrated model for the acceptance of OSS. In addition to the traditional technology adoption variables the findings stress the importance of social identification as a key driver of OSS adoption. The proposed model provides a useful decision support tool for assessing and proactively designing interventions targeted at successful OSS adoption and diffusion.