Using support vector machine with a hybrid feature selection method to the stock trend prediction

In this paper, we developed a prediction model based on support vector machine (SVM) with a hybrid feature selection method to predict the trend of stock markets. This proposed hybrid feature selection method, named F-score and Supported Sequential Forward Search (F_SSFS), combines the advantages of filter methods and wrapper methods to select the optimal feature subset from original feature set. To evaluate the prediction accuracy of this SVM-based model combined with F_SSFS, we compare its performance with back-propagation neural network (BPNN) along with three commonly used feature selection methods including Information gain, Symmetrical uncertainty, and Correlation-based feature selection via paired t-test. The grid-search technique using 5-fold cross-validation is used to find out the best parameter value of kernel function of SVM. In this study, we show that SVM outperforms BPN to the problem of stock trend prediction. In addition, our experimental results show that the proposed SVM-based model combined with F_SSFS has the highest level of accuracies and generalization performance in comparison with the other three feature selection methods. With these results, we claim that SVM combined with F_SSFS can serve as a promising addition to the existing stock trend prediction methods.     

A heuristic approach to discovering user correlations from organized social stream data

Multimedia Tools and Applications - Recently, with the widespread popularity of SNS (Social Network Service), such as Twitter, Facebook, people are increasingly accustomed to sharing feeling,...     

Social recommendation based on trust and influence in SNS environments

The development of social media provides convenience to people’s lives. People’s social relationship and influence on each other is an important factor in a variety of social activities. It is obviously important for the recommendation, while social relationship and user influence are rarely taken into account in traditional recommendation algorithms. In this paper, we propose a new approach to personalized recommendation on social media in order to make use of such a kind of information, and introduce and define a set of new measures to evaluate trust and influence based on users’ social relationship and rating information. We develop a social recommendation algorithm based on modeling of users’ social trust and influence combined with collaborative filtering. The optimal linear relation between them will be reached by the proposed method, because the importance of users’ social trust and influence varies with the data. Our experimental results show that the proposed algorithm outperforms traditional recommendation in terms of recommendation accuracy and stability.

     

Extremely localized interaction in a market model

The model of self-organized criticality (SOC) is a useful tool to understand the complexity of natural systems in the form of the artificial life and the artificial market. However, SOC remains the question what guarantees the criticality even though the natural systems seem to keep itself in the critical state. In this paper, we focus on the locality of interaction in zero-intelligence plus (ZIP) model. The extremely localized interaction changes the behavior of the ZIP model from equilibrium to intermittency. Although the original ZIP model falls into unstable with some noise, extremely localized interaction model archives robust intermittency against the noise parameter. Further, the statistical property of intermittent behavior shows the power-law nature.     

Fabrication of micro-gelatin fiber utilizing coacervation method

Biotechnology has drastically been advanced by the development of iPS and ES cells, which are representative forms induced pluripotent stem cells. In the micro/nano bio field, the development of cells and Taylor-made medicine for a potential treatment of incurable diseases has been a center of attention. The melting point of gelatin is between 25 and 33 °C, and the sol–gel transition occurs in low temperature. This makes the deformation of this useful biomaterial easy. The examples of gelatin fiber applications are suture threads, blood vessel prosthesis, cell-growth-based materials, filter materials, and many others. Because the cell size differs depending on the species and applications, it is essential to fabricate gelatin fibers of different diameters. In this paper, we have developed a fabrication method for gelatin fibers the coacervation method. We fabricated narrow gelatin fibers having a diameter over 10 μm.     

Fundamental characteristics of printed gelatin utilizing micro 3D printer

Gelatin is useful for biofabrication, because it can be used for cell scaffolds and it has unique properties. Therefore, we attempted to fabricate biodevices of gelatin utilizing micro 3D printer which is able to print with high precision. However, it has been difficult to fabricate 3D structure of gelatin utilizing 3D printer, because a printed gelatin droplet on the metal plate electrode would spread before solidification. To clear this problem, we developed a new experimental set-up with a peltier device that can control temperature of the impact point. At an impact point temperature of 80 °C, the spreading of printed gelatin droplets was prevented. Therefore, we were able to print a ball gelatin. In addition, we were able to print a narrower gelatin line than at an impact point temperature of 20 °C.     

Paraconsistent Computation Tree Logic

It is known that paraconsistent logical systems are more appropriate for inconsistency-tolerant and uncertainty reasoning than other types of logical systems. In this paper, a paraconsistent computation tree logic, PCTL, is obtained by adding paraconsistent negation to the standard computation tree logic CTL. PCTL can be used to appropriately formalize inconsistency-tolerant temporal reasoning. A theorem for embedding PCTL into CTL is proved. The validity, satisfiability, and model-checking problems of PCTL are shown to be decidable. The embedding and decidability results indicate that we can reuse the existing CTL-based algorithms for validity, satisfiability, and model-checking. An illustrative example of medical reasoning involving the use of PCTL is presented.     

Learning type PID control system using input dependence reinforcement scheme

PID control has widely used in the field of process control and a lot of methods have been used to design PID parameters. When the characteristic values of a controlled object are changed due to a change over the years or disturbance, the skilled operators observe the feature of the controlled responses and adjust the PID parameters using their knowledge and know-how, and a lot of labors are required to do it. In this research, we design a learning type PID control system using the stochastic automaton with learning function, namely learning automaton, which can autonomously adjust the control parameters updating the state transition probability using relative amount of controlled error. We show the effectiveness of the proposed learning type PID control system by simulations. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Simulation of postoperative 3D facial morphology using a physics-based head model

We propose a prototype of a facial surgery simulation system for surgical planning and the prediction of facial deformation. We use a physics-based human head model. Our head model has a 3D hierarchical structure that consists of soft tissue and the skull, constructed from the exact 3D CT patient data. Anatomic points measured on X-ray images from both frontal and side views are used to fire the model to the patient's head. The purposes of this research is to analyze the relationship between changes of mandibular position and facial morphology after orthognathic surgery, and to simulate the exact postoperative 3D facial shape. In the experiment, we used our model to predict the facial shape after surgery for patients with mandibular prognathism. Comparing the simulation results and the actual facial images after the surgery shows that the proposed method is practical.     

Autonomic control of heart rate during physical exercise and fractal dimension of heart rate variability

The objectives of the present study were to investigate autonomic nervous system influence on heart rate during physical exercise and to examine the relationship between the fractal component in heart rate variability (HRV) and the system's response. Ten subjects performed incremental exercise on a cycle ergometer, consisting of a 5-min warm-up period followed by a ramp protocol, with work rate increasing at a rate of 2.0 W/min until exhaustion. During exercise, alveolar gas exchange, plasma norepinephrine (NE) and epinephrine (E) responses, and beat-to-beat HRV were monitored. HRV data were analyzed by "coarse-graining spectral analysis" (Y. Yamamoto and R. L. Hughson. J. Appl. Physiol. 71: 1143-1150, 1991) to break down their total power (Pt) into harmonic and nonharmonic (fractal) components. The harmonic component was further divided into low-frequency (0.0-0.15 Hz) and high-frequency (0.15-0.8 Hz) components, from which low-frequency and high-frequency power (Pl and Ph, respectively) were calculated. Parasympathetic (PNS) and sympathetic (SNS) nervous system activity indicators were evaluated by Ph/Pt and Pl/Ph, respectively. From the fractal component, the fractal dimension (DF) and the spectral exponent (beta) were calculated. The PNS indicator decreased significantly (P < 0.05) when exercise intensity exceeded 50% of peak oxygen uptake (VO2 peak). Conversely, the SNS indicator initially increased at 50-60% VO2peak (P < 0.05) and further increased significantly (P < 0.05) at > 60% VO2peak when there were also more pronounced increases in NE and E.(ABSTRACT TRUNCATED AT 250 WORDS)