Stock price prediction is of great significance but faces numerous challenges. In this study, a hybrid CNN-LSTM model was utilized. The stock data were processed and feature engineering was conducted. The model architecture and training strategies were expounded. Experimental results demonstrated that this model outperformed traditional methods and benchmark models on the test set, featuring strong capabilities in feature extraction and handling long-term dependencies. Key roles of data preprocessing, hyperparameter adjustment, and model fusion were also summarized, providing valuable references for stock price prediction.

Apigenin (API) possesses excellent antitumor properties, but its limited water solubility and low bioavailability restrict its therapeutic impact. Thus, a suitable delivery systems is needed to overcome these limitations and improve the therapeutic efficiency. Poly (lactic-co-glycolic acid) (PLGA) is a copolymer extensively utilized in drug delivery. Hyaluronic acid (HA) is a major extracellular matrix and can specifically bind with CD44 on colon cancer cells. Chitosan (CS) can serve as an intermediate binding with HA and PLGA. Herein, we aimed to perpare receptor-selective HA-coated PLGA nanoparticles (NPs) for colon cancer with high expression of CD44. Firstly, API was encapsulated in PLGA to obtain PLGA-API-NPs, which were then sequentially combined with CS and HA to form HA-coated PLGA NPs. HA coated PLGA NPs had a stronger sustained-release capability. Cellular uptake of HA coated PLGA NPs was enhanced in HT-29 cells with high expression of CD44. HA-PLGA-DiR-NPs can target specificity towards the HT-29 ectopic tumor model. Overall, HA coated PLGA NPs was an effectively drug deliver platform for API in treatment of colon cancer with high expression of CD44.

This study systematically investigates the effects of different anode work function metals (Ti/Au and Ni/Au) on the transport and temperature characteristics of β-Ga2O3 based Schottky barrier diodes (SBD), junction barrier Schottky diodes (JBSD), and P-N diodes (PND), utilizing Sentaurus TCAD simulation software for mechanistic analysis. From the perspective of transport characteristics, it is observed that the SBD exhibits a lower turn-on voltage and a higher current density. Notably, the turn-on voltage (Von) of the Ti/Au anode SBD is merely 0.2 V, marking the lowest recorded value in the existing literature. Furthermore, our study reveals that the turn-on voltages of the two types of PNDs are nearly identical, confirming that the contact between the anode metals and NiOx is ohmic contact, and the contact between Ni/Au and NiOx exhibits a lower contact resistance. The Von, current density, and variation rate of the JBSD lie between those of the SBD and PND. In terms of temperature characteristics, all diodes can work at 200 °C, with both current density and Von showing a decreasing trend as the temperature increases. Among them, the PND with a Ni/Au anode exhibits the best thermal stability, with reductions in Von and current density of 8.20% and 25.31%, respectively, while the SBD with a Ti/Au anode shows the poorest performance, with reductions of 98.56% and 30.97%. Finally, the reverse breakdown (BV) characteristics of all six devices are tested. The average BV for the PND with Ti/Au and Ni/Au anodes reach 1575 V and 1550 V, respectively. Moreover, although the Von of the JBSD decreases to 0.24 V, its average BV is approximately 220 V. This study demonstrates that β-Ga2O3 based power diodes continue to exhibit excellent characteristics and application prospects in terms of low turn-on voltage.