考虑多样化需求的诊疗设备维护和患者调度联合优化研究

针对诊疗设备维护和住院患者候诊难以有效协调的问题,建立了联合优化模型。首先,假设设备具有离散的劣化状态,将设备的劣化过程建模为连续时间马尔可夫链;其次,考虑到患者对诊疗设备的不同功能频率需求,以及不同劣化状态对患者治疗时间、费用的影响,以患者就诊顺序、检查策略、修复策略为决策变量建立了设备维护和患者调度模型;最后,采用改进后的非支配排序遗传算法对多目标问题进行了求解。实验结果验证了设备维护与患者调度联合优化模型的有效性。改进后的算法提高了整体和局部的搜索能力,且具有鲁棒性。     

带平衡约束矩形布局优化问题的深度强化学习算法

带平衡约束的矩形布局问题源于卫星舱设备布局设计,属于组合优化问题。深度强化学习利用奖赏机制,通过数据训练实现高性能决策优化。针对布局优化问题,提出一种基于深度强化学习的新算法DAR及其扩展算法IDAR。DAR用指针网络输出定位顺序,再利用定位机制给出布局结果,算法的时间复杂度是O（n³）;IDAR算法在DAR的基础上引入迭代机制,算法时间复杂度是O（n⁴）,但能给出更好的结果。测试表明DAR算法具有较好的学习能力,用小型布局问题进行求解训练所获得的模型,能有效应用在大型问题上。在两个大规模典型算例的对照实验中,提出算法分别超出和接近目前最优解,具有时间和质量上的优势。     

卷积融合文本和异质信息网络的学术论文推荐算法

针对交互数据稀疏和推荐多样性问题,基于卷积协同过滤推荐框架提出卷积融合文本和异质信息网络的学术论文推荐算法（WN-APR）。首先学习不同语义下用户和论文的多样化特征,缓解数据稀疏问题;然后基于外积设计不同语义特征相互增强的方式融合它们,并使用三维卷积神经网络代替二维卷积神经网络充分挖掘不同特征对性能的影响;最后改进贝叶斯个性化排序损失函数增强推荐多样性。在CiteuLike-a、CiteuLike-t数据集上的实验结果表明,相比于基线模型,WN-APR在准确率和多样性的四个指标上都有所提升。     

LPNet: A DNN based latency prediction technique for application mapping in Network-on-Chip design

Analytical models used for latency estimation of Network-on-Chip (NoC) are not producing reliable accuracy. This makes these analytical models difficult to use in optimization of design space exploration. In this paper, we propose a learning based model using deep neural network (DNN) for latency predictions. Input features for DNN model are collected from analytical model as well as from Booksim simulator. Then this DNN model has been adopted in mapping optimization loop for predicting the best mapping of given application and NoC parameters combination. Our simulations show that using the proposed DNN model, prediction error is less than 12% for both synthetic and application specific traffic. More than 108 times speedup could be achieved using DPSO with DNN model compared to DPSO using Booksim simulator.     

Bayesian network based general correspondence retrieval method for depth sensing with single-shot structured light

This study reinvestigated one of the most fundamental problems in structure light depth sensing field: correspondence retrieval of features between patterns and images. We formulate the global optimum correspondence retrieval by maximizing a conditional probability of correspondence given observed features, which is depicted by a Bayesian network. Different from traditional “code-only” based correspondence retrieval methods, the proposed Bayesian network based method exploits the positional correlations of correspondences of neighboring features, namely, the correspondences of poorly detected features are estimated with the aid of the correspondences of well detected features. The method performs especially well on challenging scenes with rich depth variations, abrupt depth changes, edges, etc. Experiments show that the proposed method increase the correspondence accuracy by about 40% on challenging scenes, compared with traditional “code-only” based correspondence retrieval methods.     

Analysis of oceanaut operating performance using an integrated Bayesian network aided by the fuzzy logic theory

Because the oceanaut plays a significant role in safety and capability during manned deep-diving scientific tasks, preventing oceanaut performance decline is of paramount importance. However, the factors responsible for oceanaut performance are almost entirely unexplored. To address the preceding issues, a quantitative method of fuzzy integrated Bayesian network (FIBN) was modeled within the limits of oceanaut operating procedures. To quantify the probabilities of the influencing factors, the probability of each node in the FIBN was calculated using integrated expert judgement, fuzzy logic theory, and Bayesian network. By considering a total of 28 factors related to oceanaut performance in the “Jiaolong” manned submersible, this study found that difficult sampling, long sampling times, cabin equipment failure, oceanaut physical decline, and declining decision-making ability are important factors that affect oceanaut performance. The FIBN proposed in our study fused the qualitative and quantitative methods and can be developed into a versatile tool for analysis of comprehensive systems that contain both static and dynamic factors.Relevance to industryThe results provide a powerful basis for the design of manned submersible and assignment of tasks to oceanauts, while the fuzzy integrated Bayesian network (FIBN) method proposed can be effectively applied to various quantitative assessment fields which direct researchers to deal with analysis problems of complex systems.     

Authority updating: An expert authority evaluation algorithm considering post‐evaluation and power indices in social networks

In group assessment, the focus is on finding high‐authority experts to improve the reliability of assessment results. In this study, we propose an authority updating algorithm while considering the power and judgement reliability of an expert on the basis of social networks and post‐evaluations. A network power index is established and used to reflect the power of an expert while considering social networks. The measurement of the judgement reliability of an expert considers the post‐evaluation of the objects selected by experts, thereby more scientifically reflecting the reliability of experts. The analysis shows the following: although the social‐network structure influences the authority of experts, the influence weakens when the assessment group is a highly or even fully connected group; the network effect may increase the authority of some experts and reduce that of others, and it will weaken as the network connectivity increases; moreover, the judgement reliability and authority of an expert while considering post‐evaluation can encourage him/her to make fair assessments and strive to reduce his/her motivation and cognitive biases.     

CoGCN: Combining co‐attention with graph convolutional network for entity linking with knowledge graphs

Entity linking is a fundamental task in natural language processing. The task of entity linking with knowledge graphs aims at linking mentions in text to their correct entities in a knowledge graph like DBpedia or YAGO2. Most of existing methods rely on hand‐designed features to model the contexts of mentions and entities, which are sparse and hard to calibrate. In this paper, we present a neural model that first combines co‐attention mechanism with graph convolutional network for entity linking with knowledge graphs, which extracts features of mentions and entities from their contexts automatically. Specifically, given the context of a mention and one of its candidate entities' context, we introduce the co‐attention mechanism to learn the relatedness between the mention context and the candidate entity context, and build the mention representation in consideration of such relatedness. Moreover, we propose a context‐aware graph convolutional network for entity representation, which takes both the graph structure of the candidate entity and its relatedness with the mention context into consideration. Experimental results show that our model consistently outperforms the baseline methods on five widely used datasets.     

Stock Price Forecasting: An Echo State Network Approach

Forecasting stock prices using deep learning models suffers from problems such as low accuracy, slow convergence, and complex network structures. This study developed an echo state network (ESN) model to mitigate such problems. We compared our ESN with a long short-term memory (LSTM) network by forecasting the stock data of Kweichow Moutai, a leading enterprise in China’s liquor industry. By analyzing data for 120, 240, and 300 days, we generated forecast data for the next 40, 80, and 100 days, respectively, using both ESN and LSTM. In terms of accuracy, ESN had the unique advantage of capturing nonlinear data. Mean absolute error (MAE) was used to present the accuracy results. The MAEs of the data forecast by ESN were 0.024, 0.024, and 0.025, which were, respectively, 0.065, 0.007, and 0.009 less than those of LSTM. In terms of convergence, ESN has a reservoir state-space structure, which makes it perform faster than other models. Root-mean-square error (RMSE) was used to present the convergence time. In our experiment, the RMSEs of ESN were 0.22, 0.27, and 0.26, which were, respectively, 0.08, 0.01, and 0.12 less than those of LSTM. In terms of network structure, ESN consists only of input, reservoir, and output spaces, making it a much simpler model than the others. The proposed ESN was found to be an effective model that, compared to others, converges faster, forecasts more accurately, and builds time-series analyses more easily.     

Layout Optimization for Greenhouse WSN Based on Path Loss Analysis

When wireless sensor networks (WSN) are deployed in the vegetable greenhouse with dynamic connectivity and interference environment, it is necessary to increase the node transmit power to ensure the communication quality, which leads to serious network interference. To offset the negative impact, the transmit power of other nodes must also be increased. The result is that the network becomes worse and worse, and node energy is wasted a lot. Taking into account the irregular connection range in the cucumber greenhouse WSN, we measured the transmission characteristics of wireless signals under the 2.4 Ghz operating frequency. For improving network layout in the greenhouse, a semi-empirical prediction model of signal loss is then studied based on the measured data. Compared with other models, the average relative error of this semi-empirical signal loss model is only 2.3%. Finally, by combining the improved network topology algorithm and tabu search, this paper studies a greenhouse WSN layout that can reduce path loss, save energy, and ensure communication quality. Given the limitation of node-degree constraint in traditional network layout algorithms, the improved algorithm applies the forwarding constraint to balance network energy consumption and constructs asymmetric network communication links. Experimental results show that this research can realize the energy consumption optimization of WSN layout in the greenhouse.