Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting

Stock market prediction is regarded as a challenging task in financial time-series forecasting. The central idea to successful stock market prediction is achieving best results using minimum required input data and the least complex stock market model. To achieve these purposes this article presents an integrated approach based on genetic fuzzy systems (GFS) and artificial neural networks (ANN) for constructing a stock price forecasting expert system. At first, we use stepwise regression analysis (SRA) to determine factors which have most influence on stock prices. At the next stage we divide our raw data into k clusters by means of self-organizing map (SOM) neural networks. Finally, all clusters will be fed into independent GFS models with the ability of rule base extraction and data base tuning. We evaluate capability of the proposed approach by applying it on stock price data gathered from IT and Airlines sectors, and compare the outcomes with previous stock price forecasting methods using mean absolute percentage error (MAPE). Results show that the proposed approach outperforms all previous methods, so it can be considered as a suitable tool for stock price forecasting problems.     

Solving a bi-criteria permutation flow-shop problem using shuffled frog-leaping algorithm

Flow shop problems as a typical manufacturing challenge have gained wide attention in academic fields. In this paper, we consider a bi-criteria permutation flow shop scheduling problem, where the weighted mean completion time and the weighted mean tardiness are to be minimized simultaneously. Due to the complexity of the problem, it is very difficult to obtain optimum solution for this kind of problems by means of traditional approaches. Therefore, a new multi-objective shuffled frog-leaping algorithm (MOSFLA) is introduced for the first time to search locally Pareto-optimal frontier for the given problem. To prove the efficiency of the proposed algorithm, various test problems are solved and the reliability of the proposed algorithm, based on some comparison metrics, is compared with three distinguished multi-objective genetic algorithms, i.e. PS-NC GA, NSGA-II, and SPEA-II. The computational results show that the proposed MOSFLA performs better than the above genetic algorithms, especially for the large-sized problems.     

New wireless connection between user and VE using speech processing

This paper presents a novel speak-to-VR virtual-reality peripheral network (VRPN) server based on speech processing. The server uses a microphone array as a speech source and streams the results of the process through a Wi-Fi network. The proposed VRPN server provides a handy, portable and wireless human machine interface that can facilitate interaction in a variety interfaces and application domains including HMD- and CAVE-based virtual reality systems, flight and driving simulators and many others. The VRPN server is based on a speech processing software development kits and VRPN library in C++. Speak-to-VR VRPN works well even in the presence of background noise or the voices of other users in the vicinity. The speech processing algorithm is not sensitive to the user’s accent because it is trained while it is operating. Speech recognition parameters are trained by hidden Markov model in real time. The advantages and disadvantages of the speak-to-VR server are studied under different configurations. Then, the efficiency and the precision of the speak-to-VR server for a real application are validated via a formal user study with ten participants. Two experimental test setups are implemented on a CAVE system by using either Kinect Xbox or array microphone as input device. Each participant is asked to navigate in a virtual environment and manipulate an object. The experimental data analysis shows promising results and motivates additional research opportunities.     

Modeling metallurgical responses of coal Tri-Flo separators by a novel BNN:a "Conscious-Lab" development

Tri-flo cyclone,as a dense-medium separation device,is one of the most typical environmentally friendly industrial techniques in the coal washery plants.Surpris...     

Effects of preweaning total plane of milk intake and weaning age on intake,growth performance,and blood metabolites of dairy calves

The objective of this study was to evaluate the effects of preweaning total plane of milk intake and weaning age on intake, growth performance, and blood metabolites of dairy calves. A total of 48 Holstein calves (40 ± 1.6 kg of body weight) were used in a 2 × 2 factorial arrangement with the factors of weaning age (d 60 vs. 75) and the total plane of milk intake (medium vs. high) during the preweaning period. Calves were assigned to 1 of 4 treatments: (1) calves fed medium plane of milk (MPM) intake and weaned on d 60 of age (MPM-60d, 4 L/d of milk from d 3 to 10, 6 L/d of milk from d 11 to 55, and 3 L/d of milk from d 56 to 60 of age; total milk intake = 317 L), (2) calves fed MPM intake and weaned on d 75 of age (MPM-75d, 4 L/d of milk from d 3 to 10 and 4.5 L/d of milk from d 11 to 70 of age followed by feeding 2.25 L/d of milk from d 71 to 75 of age; total milk intake = 313 L), (3) calves fed high plane of milk (HPM) intake and weaned on d 60 of age (HPM-60d, 4 L/d of milk from d 3 to 10, 6 L/d of milk from d 11 to 20, and 8.5 L/d of milk from d 21 to 55 followed by feeding 4.25 L/d of milk from d 56 to 60 of age; total milk intake = ～411 L); and (4) calves fed HPM intake and weaned on d 75 (HPM-75d, 4 L/d of milk from d 3 to 10, and 6 L/d of milk from d 11 to 70 of age followed by feeding 3 L/d of milk from d 71 to 75 of age; total milk intake = 407 L) with no milk refusals. All of the calves were monitored up to d 90 of age. Regardless of weaning age, starter feed intake and dry matter intake (% of body weight) were lower in calves fed HPM compared with those receiving MPM. A tendency for the plane of milk intake × weaning age interaction was observed for metabolizable energy intake with the highest value was recorded with the HPM-75d calves. The lowest efficiency of metabolizable energy intake and average feed efficiency was observed in HPM-60d calves throughout the experimental period as compared with the other groups. An interaction was found between the total plane of milk intake and weaning age regarding effects on total average daily gain, average daily gain/metabolizable energy intake, feed efficiency, final body weight, and plasma β-hydroxybutyrate levels with the highest values measured in HPM-75d calves. Weaning on d 75 versus d 60 improved wither height and hip width, which tended to increase body length at the end of the trial. The results suggest that calves fed high amounts of milk during their preweaning period benefit from extending the time of weaning from 60 to 75 d of age based on average daily gain, feed efficiency, and final body weight.     

Study of Adsorption/Desorption Effect of 2-Mercaptobenzothiazole as Sweet Corrosion Inhibitor on API-5L X60 Steel

Protection of Metals and Physical Chemistry of Surfaces - In this study, the inhibitive performance of 2-mercaptobenzothiazole (2MBT) and 2-aminobenzothiazole (2ABT) were investigated on API-5L X60...     

Effect of chemical environments on palladium phthalocyanine thin film sensors for humidity analysis

Chemiresistors based on palladium phthalocyanine (PdPc) thin films were investigated as humidity sensors. The samples were thermally evaporated onto gold electrodes with a thickness about 100 nm. Optical and electrical characteristics of PdPc thin films were investigated by scanning electron microscopy (SEM), X-ray diffraction (XRD), and electrical measurements. The SEM image demonstrates PdPc (30–60 nm) nanosized particles, and XRD pattern shows that thin films are in α-phase at room temperature. Electrical measurements also confirm that PdPc exhibit semiconducting and photoconducting behaviors, and thermal activation energies of thin films were calculated. After that, the sensitivity and reversibility of devices were investigated on exposure to 20–90% RH in various chemical environments at 293 and 323 K. The response time (35–45 s) and recovery time (75–105 s) of sensors were measured at 293 K with respect to different chemical environments. At last, the stability of devices versus different RH% and chemical environments were tested. The sensors show very good stability on exposure to RH for a period of 2 months but their stability has been reduced in ethanol, acetone, and ammonia environments.     

Interfacial Reactions Between BaAl2Si2O8 and Molten Al Alloy at 850°C

A corrosion cup test was undertaken using BaAl₂Si₂O₈ and Al4.1Zn3.2Mg alloy, heated in air for 150 h at 850°C. Electron probe microanalysis, X‐ray diffraction, and scanning electron microscopy coupled with energy dispersive spectroscopy were used to identify the mineralogical and microstructural changes at the interfaces. The microstructural results revealed three microstructural areas: (1) Spinel layer with large numbers of Al alloy channels; (2) interfacial area with mainly alumina, spinel, and BaAl₂Si₂O₈; and (3) interdiffusion zone chemically close to barium hexaaluminate. The principal observations are:

相似文献