Forecasting directional movement of Forex data using LSTM with technical and macroeconomic indicators

Forex(foreign exchange)is a special financial market that entails both high risks and high profit opportunities for traders.It is also a very simple market since traders can profit by just predicting the direction of the exchange rate between two currencies.However,incorrect predictions in Forex may cause much higher losses than in other typical financial markets.The direction prediction requirement makes the problem quite different from other typical time-series forecasting problems.In this work,we used a popular deep learning tool called“long short-term memory”(LSTM),which has been shown to be very effective in many time-series forecasting problems,to make direction predictions in Forex.We utilized two different data sets—namely,macroeconomic data and technical indicator data—since in the financial world,fundamental and technical analysis are two main techniques,and they use those two data sets,respectively.Our proposed hybrid model,which combines two separate LSTMs corresponding to these two data sets,was found to be quite successful in experiments using real data.

Modern tectonic stress field in the Chinese mainland inverted from focal mechanism solutions

The inversion of modern tectonic stress field in China is made by regions on the basis of focal mechanism data inthe period of 1920-1996. Results of the inversion show that the maximum principal compressive stress σ1 axisstrikes nearly north-south direction in the Tibet Plateau and western Chin4 east-west direction in North China Incentral China, its strikes show a radiate pattern, i.e., north-north east in north part, east-west in central part andnorth-north west in south part. The σ1 axes are often perpendicular to the minimum principal stress σ3 axes, exceptwestern China where the σ1 axes are oblique to the σ3 axes with an acute angle. R is defined by (σ2-σ1)/(σ3-σ1),has the higher values (0.60-0.90) in north part of central China and quickly changes into the lower values(0. 10-0.30) in the Tibet Plateau. Both of the observed and inverted fault planes have strikes varying with locations.Combining stress directions and R value, the stress configuration is divided into 7 groups. Most of the groups showstrike-slip faulting with intermediate R values, which occupies North China and the eastern part of China as well asinner Tibet Plateau. A few of them show reverse faulting with higher R values within western pod of China and thenorth edge of the Tibet Plateau. Normal faulting occurred on the south edge of the Tibet Plateau with smaller Rval nes.

Multi-functional Hollow Structures for Intelligent Drug Delivery

Multi-fountional hollow structures have emerged as promising platforms for intelligent drug delivery due to their unique properties,such as high loading capacities and programmed drug release.In particular,hollow multishell structures(HoMSs)with multilevel shell and space can regulate the molecular-level interaction between drugs and materials,so as to achieve the temporal-spatial order and sequential release of drugs.The anisotropic hollow structures can control the drug diffusion process by inducing the macroscopic interface flow through autonomous movement,realizing the targeted drug transport and release.In this paper,a key focus will be HoMSs with their temporal-ordered architectures and anisotropic hollow carriers with directional movement.Their synthesis mechanisms,structure-property relationships,smartly programmed drug delivery and biomedical applications will be discussed,providing insights into designing next-generation intelligent drug carriers.