The prediction of stock price movement direction is significant in financial circles and academic. Stock price contains complex, incomplete, and fuzzy information which makes it an extremely difficult task to predict its development trend. Predicting and analysing financial data is a nonlinear, time-dependent problem. With rapid development in machine learning and deep learning, this task can be performed more effectively by a purposely designed network. This paper aims to improve prediction accuracy and minimizing forecasting error loss through deep learning architecture by using Generative Adversarial Networks. It was proposed a generic model consisting of Phase-space Reconstruction (PSR) method for reconstructing price series and Generative Adversarial Network (GAN) which is a combination of two neural networks which are Long Short-Term Memory (LSTM) as Generative model and Convolutional Neural Network (CNN) as Discriminative model for adversarial training to forecast the stock market. LSTM will generate new instances based on historical basic indicators information and then CNN will estimate whether the data is predicted by LSTM or is real. It was found that the Generative Adversarial Network (GAN) has performed well on the enhanced root mean square error to LSTM, as it was 4.35% more accurate in predicting the direction and reduced processing time and RMSE by 78 s and 0.029, respectively. This study provides a better result in the accuracy of the stock index. It seems that the proposed system concentrates on minimizing the root mean square error and processing time and improving the direction prediction accuracy, and provides a better result in the accuracy of the stock index.
Irrigated agriculture is an important strategic sector in arid and semi-arid regions. Given the large spatial coverage of irrigated areas, operational tools based on satellite remote sensing can contribute to their optimal management. The aim of this study was to evaluate the potential of two spectral indices, calculated from SPOT-5 high-resolution visible (HRV) data, to retrieve the surface water content values (from bare soil to completely covered soil) over wheat fields and detect irrigation supplies in an irrigated area. These indices are the normalized difference water index (NDWI) and the moisture stress index (MSI), covering the main growth stages of wheat. These indices were compared to corresponding in situ measurements of soil moisture and vegetation water content in 30 wheat fields in an irrigated area of Morocco, during the 2012–2013 and 2013–2014 cropping seasons. NDWI and MSI were highly correlated with in situ measurements at both the beginning of the growing season (sowing) and at full vegetation cover (grain filling). From sowing to grain filling, the best correlation (R2 = 0.86; p < 0.01) was found for the relationship between NDWI values and observed soil moisture values. These results were validated using a k-fold cross-validation methodology; they indicated that NDWI can be used to estimate and map surface water content changes at the main crop growth stages (from sowing to grain filling). NDWI is an operative index for monitoring irrigation, such as detecting irrigation supplies and mitigating wheat water stress at field and regional levels in semi-arid areas. 相似文献
The motion of a drop along a fibre is studied to formulate a method by which adhesives could be distributed within fibre bundles. The drops had to be located at the cross-points of fibres to provide strength and flexibility to the mat. Among the various methods of application, described in detail, only the solution method gave satisfactory results. An empirical relationship was derived to estimate the mass of the adhesives retained by the fibres. 相似文献
Training sequence is used in multiple antenna systems to estimate channel state information and mitigate channel distortion between transmitter and receiver. However, the training sequence or pilot must be limited to a certain size in order to reduce the impact of overhead loss due to limited channel coherence length in mobile users. In this paper, we proposed to use training size optimization in cell-free massive MIMO system. In addition, we proposed and compared the performance of different training size optimization algorithms, namely exhaustive search optimization, bisection optimization and min–max optimization, with each method has different level of calculation complexities. The results showed that in general, all of the 3 training length optimization methods improved the downlink rate compared to the conventional pilot length method. We also showed that the training optimization methods are more effective when the coherence length is small or the number of users is very large. In the case of large number of users or small coherence length, the exhaustive search has the best median downlink rate, followed closely by min–max optimum and finally the bisection method. Even though the exhaustive search optimization has the best downlink rate, we showed that the proposed reduce optimization complexity methods has significantly less calculation complexity. In addition, the median downlink rate performance of min–max optimization method is only slightly less than that of the exhaustive search method for various number of users and coherence length.
In this paper, we propose a learning assessment method based on the analysis of learner’s behavioural style. This method was first applied for wheel-chair driving tasks because it is simple and risk-free, but unusual for users. Seven classic performance indicators based on joystick control were used to characterise the users’ driving style. We assumed that the learning effectiveness of the users can be evaluated by comparing their driving style with the reference ones, which could be extracted from experienced users. The evaluation was carried out for six novice users and eight experienced users. The users were asked to carry out several typical driving tasks for seven trials at first. The fuzzy C-means clustering method was used with the data of the experienced users to obtain the reference driving styles. Next, an evaluation was performed for novice users by comparing their driving styles with the reference ones. The results showed that, for all of the experienced users, their driving styles could be classified into two reference types. In addition, there was no significant difference in their driving styles from one trial to another, even for a user with disabilities, which means that their driving style was stable. On the other hand, novice users had switching behaviours during the learning phase; however, after eight additional trials, each novice user’s driving style converged to one of the two identified reference types, meaning that the novice users could achieve a stable performance after learning, which was also validated by an expert therapist. 相似文献
International Journal of Control, Automation and Systems - The main research topic of this paper is to apply the sliding mode based soft actuation to smooth transition between position, force, and... 相似文献
Wireless Personal Communications - The early diagnosis and the accurate separation of COVID-19 from non-COVID-19 cases based on pulmonary diffuse airspace opacities is one of the challenges facing... 相似文献