An intelligent stock trading system using comprehensive features

The aim of this study is to predict automatic trading decisions in stock markets. Comprehensive features (CF) for predicting future trend are very difficult to generate in a complex environment, especially in stock markets. According to related work, the relevant stock information can help investors formulate objects that may result in better profits. With this in mind, we present a framework of an intelligent stock trading system using comprehensive features (ISTSCF) to predict future stock trading decisions. The ISTSCF consists of stock information extraction, prediction model learning and stock trading decision. We apply three different methods to generate comprehensive features, including sentiment analysis (SA) that provides sensitive market events from stock news articles for sentiment indices (SI), technical analysis (TA) that yields effective trading rules based on trading information on the stock exchange for technical indices (TI), as well as the trend-based segmentation method (TBSM) that raises trading decisions from stock price for trading signals (TS). Experiments on the Taiwan stock market show that the results of employing comprehensive features are significantly better than traditional methods using numeric features alone (without textual sentiment features).     

The effect of different lattice sites substitution on photoluminescence characteristics of Eu2+/Ce3+ doped M5(ZO4)3X

The empirical formula of Van Uitert is applied to calculating the emission wavelengths of haloapatite and silicon apatite phosphors doped with Eu²⁺/Ce³⁺. The relationship between emission wavelengths and occupied lattice sites of Eu²⁺/Ce³⁺ is discussed in haloapatite crystal. For phosphors of haloapatite and silicon apatite doped with Eu²⁺, the emission bands of the long-wave region are interpreted reasonably. Phosphors Sr₅(PO₄)₂SiO₄ doped with Eu²⁺/Ce³⁺ are synthesized by high temperature solid state reaction under two different atmospheres, the spectral characteristics of Eu²⁺/Ce³⁺ occupying different lattice sites are studied. The luminescent materials Sr₅(PO₄)₂SiO₄ doped with Eu²⁺/Ce³⁺ are promising blue-green phosphors for application in white-LEDs.     

部分传输序列的遗传模拟退火搜索方法

在正交频分复用(OFDM)系统中,基于遗传算法的部分传输序列(GA-PTS)技术有效地降低了 PTS 的计算复杂度,但在 改进峰值-平均功率比(PAPR)性能方面却并不理想。 为此,提出在遗传算法中嵌入模拟退火(SA)算子从而构造一种混合的遗 传模拟退火(GSA)算法,并把它应用于对 PTS 的最优相位因子进行搜索。 首先,通过对 PTS 相位因子编码形成染色体,采用随 机元素组成的染色体作为遗传算法的初始群体,并评估每个染色体的适应度值。 然后,根据适应度值选择染色体,建立染色体 的变异规则和交叉规则,对群体进行迭代进化。 最后,群体中的染色体利用退火温度进行更新,从而产生出新的下一代种群。 仿真结果说明,与 GA-PTS 方案相比,该方法不仅能降低计算负担,而且能够有效地降低 OFDM 系统 PAPR 值。     

启发式联合PCD快速降噪算法

基于稀疏冗余表示,并行坐标下降(PCD)是最优秀的降噪算法之一.然而在音频信号处理中,当分割的帧数很大时,PCD的计算负担加重,造成运行时间剧增.该文基于联合稀疏表示(JSR)和同时稀疏近似(SSA),建立一种新的时域框架,并提出了一种启发式联合PCD算法(Joint-PCD).在该框架中,每个音频帧作为一个列向量生成...     

E-commerce personalized recommendation analysis by deeply-learned clustering

With the development of Internet, personalized recommendation has played an important role in human modern lives. Since the number of users’ data is always large-scale, traditional algorithms cannot effectively cope with e-commerce personalized recommendation tasks. This paper proposes an e-commerce product personalized recommendation system based on learning clustering representation. Traditional kNN method has limitation in selecting adjacent object set. Thus, we introduce neighbor factor and time function and leverage dynamic selection model to select the adjacent object set. We combine RNN as well as attention mechanism to design the e-commerce product recommendation system. Comprehensive experimental results have shown the effectiveness of our proposed method.     

Automatically annotating a five-billion-word corpus of Japanese blogs for sentiment and affect analysis

This paper presents our research on automatic annotation of a five-billion-word corpus of Japanese blogs with information on affect and sentiment. We first perform a study in emotion blog corpora to discover that there has been no large scale emotion corpus available for the Japanese language. We choose the largest blog corpus for the language and annotate it with the use of two systems for affect analysis: ML-Ask for word- and sentence-level affect analysis and CAO for detailed analysis of emoticons. The annotated information includes affective features like sentence subjectivity (emotive/non-emotive) or emotion classes (joy, sadness, etc.), useful in affect analysis. The annotations are also generalized on a two-dimensional model of affect to obtain information on sentence valence (positive/negative), useful in sentiment analysis. The annotations are evaluated in several ways. Firstly, on a test set of a thousand sentences extracted randomly and evaluated by over forty respondents. Secondly, the statistics of annotations are compared to other existing emotion blog corpora. Finally, the corpus is applied in several tasks, such as generation of emotion object ontology or retrieval of emotional and moral consequences of actions.     

具有相似性传播的K-均值欠定盲分离算法

对于稀疏信源的欠定盲分离问题,混合矩阵的估计是至关重要的。为了提高估计性能,提出一种组合的聚类分析算法。首先,利用短时傅里叶变换把时域中的观测信号转变成频域中的稀疏信号,并通过数据的归一化把稀疏信号在频域的线性聚类转变成致密聚类。然后,利用相似性传播AP聚类方法搜索每个观测数据的邻域自动形成数据族的数量和相对应的关键数据。最后,以AP聚类的结果作为K-均值算法的初始值,对每类(族)数据的聚类中心进一步修正。仿真结果表明,组合聚类法能有效地提高混合矩阵的估计精度。把AP聚类和K-均值算法相结合的另一个优势是,能够克服经典K-均值算法需要事先知道信源数量和对数据的初始划分非常敏感的缺陷。     

Underdetermined mixing matrix estimation based on joint density-based clustering algorithms

Multimedia Tools and Applications - In underdetermined blind source separation (UBSS), the estimation of the mixing matrix is crucial because it directly affects the performance of UBSS. To improve...     

K-Means算法最优聚类数量的确定

K-均值(K-means)聚类算法是学术与工业领域的经典算法。然而,它却具有两个明显缺陷:1) 需要预先知道聚类的数量;2) 对算法的随机初始化非常敏感。为了解决这两个问题,首先归纳了K-均值算法的基本步骤,并对聚类有效性进行了分析;然后以数据样本点的欧几里德距离为基础,定义了以聚类数量k为自变量的类间质心距离之和以及类内距离之和,由此构造了聚类有效性评价函数;最后根据经验规则,在聚类数量的可能范围内通过求解聚类有效性评价函数的最小值以确定数据集的最优聚类数量。对UCI的3个数据集Iris、Seeds和Wine的仿真结果说明,提出的聚类有效性评价函数不仅能够准确地反映数据的真实聚类结构,还能有效地抑制算法对随机初始化的敏感性,通过对K-均值算法的多次运行,其结果也验证了聚类有效性评价函数的鲁棒性。