To address the challenges of high error rates and poor generalization in current deep learning models for predicting lattice thermal conductivity (LTC), we introduce CrysGraphFormer, an innovative equivariant crystal graph...
High-speed mobile wireless communication system always goes through the doubly selective wireless fading channels, which seriously affects the performance of communication systems.In this paper, a non-coherent chirp spread spectrum (CSS ) communication method is proposed based on CORDIC algorithm and differential frequency discriminator.According to the Doppler shift caused by constant and variable speed on the CSS communication method, an inner symbol differential decider is introduced to counteract the Doppler shift in highly dynamic scenes.In the situation of 4MHz carrier frequency and bit error rate less than 10 -4 , computer simulation shows that the proposed method based on CORDIC differential discriminator has a maximum resistance of Doppler shift up to about 150 kHz, which is much larger than the coherent method's 30Hz.
Multicomponent oxides (MCOs) have attracted considerable attention due to their wide range of applications. However, the extensive search space of MCO components and the scarcity of MCO crystal structures in existing literature have promoted the use of deep machine learning methods for predicting MCO properties. Despite these advances, accurately predicting the thermal expansion of MCOs across wide temperature and composition ranges remains a complex task. An innovative attention-based deep learning model was introduced in this study. The proposed two self-attention modules have greatly improved the performance of this model, achieve a 86.88% improvement in root mean square error for thermal expansion predictions of MCOs. Additionally, the model demonstrates impressive adaptability and interpretability. Its training results can further aid in comprehending the thermal expansion coefficient variations of multicomponent oxide materials. In summary, judiciously crafted self-attention models overcome tradeoffs between performance and interpretability for materials discovery.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
