Reverse direction-based surrounder queries for mobile recommendations

This paper proposes a new spatial query called a reverse direction-based surrounder (RDBS) query, which retrieves a user who is seeing a point of interest (POI) as one of their direction-based surrounders (DBSs). According to a user, one POI can be dominated by a second POI if the POIs are directionally close and the first POI is farther from the user than the second is. Two POIs are directionally close if their included angle with respect to the user is smaller than an angular threshold ??. If a POI cannot be dominated by another POI, it is a DBS of the user. We also propose an extended query called competitor RDBS query. POIs that share the same RDBSs with another POI are defined as competitors of that POI. We design algorithms to answer the RDBS queries and competitor queries. The experimental results show that the proposed algorithms can answer the queries efficiently.     

非工程领域中的TRIZ

TRIZ是研究人类进行发明创造,解决技术问题过程中所遵循的科学原理和法则,目前已经成为国外研究者们研究的热点。为使我国各行各业的工作者了解TRIZ理论,论文对TRIZ的基本概念、组成和主要方法与工具进行了介绍,并在此基础上通过实例提出了TRIZ在非工程领域中的应用。最后对TRIZ当前研究的重点和方向进行了讨论。     

Box-Behnken设计响应面法优化黑果枸杞总黄酮纯化工艺

目的应用Box-Behnken设计响应面法优化黑果枸杞总黄酮纯化工艺条件及相关参数。方法考察6种大孔吸附树脂静态、动态吸附和解吸性能,用单因素试验分别对上样浓度、上样体积、上样pH、洗脱液浓度、洗脱液体积和洗脱流速进行考察,以黑果枸杞总黄酮纯化后含量为指标,再从6个单因素中选出对解吸附试验影响最显著的3个因素进行三因素三水平Box-Behnken设计响应面实验。结果 NKA-9型大孔树脂为纯化黑果枸杞总黄酮的最佳树脂,最佳纯化工艺条件为总黄酮提取液浓度为4mg/mL,pH为4.0,按5BV进行上样,再用3VB的80%乙醇在2mL/min流速下进行洗脱,黑果枸杞总黄酮含量可以从4.54%提高到43.19%。结论此工艺对黑果枸杞总黄酮的纯化效果较好,工艺简单且稳定性良好,适用于工业化生产。     

多值神经元函数的频谱近似

为衡量多值神经元函数与其扩展频谱之间的误差,定义了多值神经元输入函数和输出函数之间的近似误差,并给出误差的下限.通过限定下限为0,给出单个p值神经元能实现的函数应该满足的充分条件,这也是单个神经元计算能力的一个衡量指标.给出了当输入函数不满足正交条件时,多值神经网络复杂度的下限.     

基于中医网络的中心性算法研究

中医概念之间的关系极为复杂,采用传统的基于简单数据集的数据挖掘方法显得力不从心.考虑到中医数据的特点,提出了一种基于图结构的挖掘方法,将中医对象之间的复杂关系和潜在的信息提取出来.首先,通过自然语言处理从医案中抽取出的中医概念与中医本体知识库匹配得到中医的知识网络.然后将该中医网络抽象成数学表达方式--图,利用图论的算法来处理.最后,采用中心性算法来分析中医网络,找出在中医诊断网络中具有重要作用的症状.     

Three-Phase Unbalance Prediction of Electric Power Based on Hierarchical Temporal Memory

The difference in electricity and power usage time leads to an unbalanced current among the three phases in the power grid. The three-phase unbalanced is closely related to power planning and load distribution. When the unbalance occurs, the safe operation of the electrical equipment will be seriously jeopardized. This paper proposes a Hierarchical Temporal Memory (HTM)-based three-phase unbalance prediction model consisted by the encoder for binary coding, the spatial pooler for frequency pattern learning, the temporal pooler for pattern sequence learning, and the sparse distributed representations classifier for unbalance prediction. Following the feasibility of spatialtemporal streaming data analysis, we adopted this brain-liked neural network to a real-time prediction for power load. We applied the model in five cities (Tangshan, Langfang, Qinhuangdao, Chengde, Zhangjiakou) of north China. We experimented with the proposed model and Long Short-term Memory (LSTM) model and analyzed the predict results and real currents. The results show that the predictions conform to the reality; compared to LSTM, the HTM-based prediction model shows enhanced accuracy and stability. The prediction model could serve for the overload warning and the load planning to provide high-quality power grid operation.     

榅桲饮料的制作工艺研究

主要对酶解法提取榅桲果汁并配以柠檬酸、蔗糖、CMC-Na等辅料,制作风味独特、营养保健、品质稳定的榅桲果汁饮料的工艺进行研究。结果表明,果胶酶酶解浸提榅桲的最适条件为:果胶酶用量为0.30%,浸提温度为45℃,料水比为1∶4,pH 3.5,浸提时间为2 h。榅桲果汁饮料最佳配方为:榅桲浸提汁100%,蔗糖8%,柠檬酸0.10%,稳定剂CMC-Na0.05%。     

超导电荷量子比特系统中几何量子失协和稠密编码的研究

研究了由约瑟夫森大结耦合的两个超导电荷量子比特模型中的几何量子失协和稠密编码信道容量。讨论了初始平均光子数、相对相位和两电荷量子比特间振幅对几何量子失协和稠密编码信道容量的影响。结果表明,初始平均光子数、相对相位和两电荷量子比特间振幅在几何量子失协及稠密编码信道容量的动力学演化过程中扮演了一个非常重要的角色,特别有意义的是可以通过调控相对相位来提高稠密编码信道容量的值。     

An Improved End-to-End Memory Network for QA Tasks

At present, End-to-End trainable Memory Networks (MemN2N) has proven to be promising in many deep learning fields, especially on simple natural language-based reasoning question and answer (QA) tasks. However, when solving some subtasks such as basic induction, path finding or time reasoning tasks, it remains challenging because of limited ability to learn useful information between memory and query. In this paper, we propose a novel gated linear units (GLU) and local-attention based end-to-end memory networks (MemN2N-GL) motivated by the success of attention mechanism theory in the field of neural machine translation, it shows an improved possibility to develop the ability of capturing complex memory-query relations and works better on some subtasks. It is an improved end-to-end memory network for QA tasks. We demonstrate the effectiveness of these approaches on the 20 bAbI dataset which includes 20 challenging tasks, without the use of any domain knowledge. Our project is open source on github⁴.     

A Recommendation System Based on Fusing Boosting Model and DNN Model

In recent years, the models combining traditional machine learning with the deep learning are applied in many commodity recommendation practices. It has been proved better performance by the means of the neural network. Feature engineering has been the key to the success of many click rate estimation model. As we know, neural networks are able to extract high-order features automatically, and traditional linear models are able to extract low-order features. However, they are not necessarily efficient in learning all types of features. In traditional machine learning, gradient boosting decision tree is a typical representative of the tree model, which can construct new features related before and after tree. Convolutional neural networks have a better perception of local features. In this paper, we take advantage of convolutional networks to capture the local features. The features are constructed by the node leaf of gradient boosting decision tree. This paper employs the tree leaf node to mine the user behavior path features, and uses the deep model to extract the user abstract features. Based on a Kaggle competition, our model performs better in the test data than any other model.