Search

In the era of big data, prediction has become a fundamental capability. Current prediction methods primarily focus on sequence elements; however, in multivariate time series forecasting, time is a critical factor that must not be overlooked. While some methods consider time, they often neglect the temporal distance between sequence elements and the predicted target time, a relationship essential for identifying patterns such as periodicity, trends, and other temporal dynamics. Moreover, the extraction of temporal features is often inadequate, and discussions on how to comprehensively leverage temporal data are limited. As a result, model performance can suffer, particularly in prediction tasks with specific time requirements. To address these challenges, we propose a new model, TE-LSTM, based on LSTM, which employs a temporal encoding method to fully extract temporal features. A temporal weighting strategy is also used to optimize the integration of temporal information, capturing the temporal relationship of each element relative to the target element, and integrating it into the LSTM. Additionally, this study examines the impact of different time granularities on the model. Using the Beijing International Airport station as the study area, we applied our method to temperature prediction. Compared to the baseline model, our model showed an improvement of 0.7552% without time granularity, 1.2047% with a time granularity of 3, and 0.0953% when addressing prediction tasks with specific time requirements. The final results demonstrate the superiority of the proposed method and highlight its effectiveness in overcoming the limitations of existing approaches. [ABSTRACT FROM AUTHOR]

Lanthanide ion (Ln3+)‐doped halide double perovskites (DPs) have evoked tremendous interest due to their unique optical properties. However, Ln3+ ions in these DPs still suffer from weak emissions due to their parity‐forbidden 4f–4f electronic transitions. Herein, the local electronic structure of Ln3+‐doped Cs2NaInCl6 DPs is unveiled. Benefiting from the localized electrons of [YbCl6]3− octahedron in Cs2NaInCl6 DPs, an efficient strategy of Cl−‐Yb3+ charge transfer sensitization is proposed to obtain intense near‐infrared (NIR) luminescence of Ln3+. NIR photoluminescence (PL) quantum yield (QY) up to 39.4% of Yb3+ in Cs2NaInCl6 is achieved, which is more than three orders of magnitude higher than that (0.1%) in the well‐established Cs2AgInCl6 via conventional self‐trapped excitons sensitization. Density functional theory calculation and Bader charge analysis indicate that the [YbCl6]3− octahedron is strongly localized in Cs2NaInCl6:Yb3+, which facilitates the Cl−‐Yb3+ charge transfer process. The Cl−‐Yb3+ charge transfer sensitization mechanism in Cs2NaInCl6:Yb3+ is further verified by temperature‐dependent steady‐state and transient PL spectra. Furthermore, efficient NIR emission of Er3+ with the NIR PLQY of 7.9% via the Cl−‐Yb3+ charge transfer sensitization is realized. These findings provide fundamental insights into the optical manipulation of Ln3+‐doped halide DPs, thus laying a foundation for the future design of efficient NIR‐emitting DPs. [ABSTRACT FROM AUTHOR]

Currently, lanthanide (Ln3+)‐doped near‐infrared (NIR)‐emitting double perovskites (DPs) suffer from low photoluminescence quantum yield (PLQY). Herein, we develop a new class of NIR‐emitting DPs based on Ln3+‐doped Cs2(Na/Ag)BiCl6. Benefiting from the Na+‐induced breakdown of local site symmetry in the Cs2AgBiCl6 DPs, effective NIR emissions of Ln3+ are realized through Bi3+ sensitization. Specifically, 7.3‐fold and 362.9‐fold enhanced NIR emissions of Yb3+ and Er3+ are achieved in Cs2Ag0.2Na0.8BiCl6 DPs relative to those in Na‐free Cs2AgBiCl6 counterparts, respectively. The optimal absolute NIR PLQYs for Yb3+ and Er3+ in Cs2Ag0.2Na0.8BiCl6 DPs are determined to be 19.0 % and 4.3 %, respectively. Raman spectroscopy and first‐principles density functional theory calculations verify the sublattice distortion in Cs2(Na/Ag)BiCl6 DPs via Na+ doping. These findings provide fundamental insights into the design of efficient NIR‐emitting Ln3+‐doped DPs for versatile optoelectronic applications. [ABSTRACT FROM AUTHOR]

Lanthanide (Ln3+)‐doped upconversion (UC) nanoprobes, which have drawn extensive attention for various bioapplications, usually suffer from small absorption cross‐sections and weak luminescence intensity of Ln3+ ions. Herein, we report the controlled synthesis of a new class of Ln3+‐doped UC nanoprobes based on CsLu2F7:Yb/Er nanocrystals (NCs), which can effectively increase the intersystem crossing (ISC) efficiency from singlet excited state to triplet excited state of IR808 up to 99.3 % through the heavy atom effect. By virtue of the efficient triplet sensitization of IR808, the optimal UC luminescence (UCL) intensity of IR808‐modified CsLu2F7:Yb/Er NCs is enhanced by 1309 times upon excitation at 808 nm. Benefiting from the intense dye‐triplet‐sensitized UCL, the nanoprobes are demonstrated for sensitive assay of extracellular and intracellular hypochlorite with an 808‐nm/980‐nm dual excited ratiometric strategy. [ABSTRACT FROM AUTHOR]

Currently, lanthanide (Ln 3+ )-doped near-infrared (NIR)-emitting double perovskites (DPs) suffer from low photoluminescence quantum yield (PLQY). Herein, we develop a new class of NIR-emitting DPs based on Ln 3+ -doped Cs 2 (Na/Ag)BiCl 6 . Benefiting from the Na + -induced breakdown of local site symmetry in the Cs 2 AgBiCl 6 DPs, effective NIR emissions of Ln 3+ are realized through Bi 3+ sensitization. Specifically, 7.3-fold and 362.9-fold enhanced NIR emissions of Yb 3+ and Er 3+ are achieved in Cs 2 Ag 0.2 Na 0.8 BiCl 6 DPs relative to those in Na-free Cs 2 AgBiCl 6 counterparts, respectively. The optimal absolute NIR PLQYs for Yb 3+ and Er 3+ in Cs 2 Ag 0.2 Na 0.8 BiCl 6 DPs are determined to be 19.0 % and 4.3 %, respectively. Raman spectroscopy and first-principles density functional theory calculations verify the sublattice distortion in Cs 2 (Na/Ag)BiCl 6 DPs via Na + doping. These findings provide fundamental insights into the design of efficient NIR-emitting Ln 3+ -doped DPs for versatile optoelectronic applications., (© 2022 Wiley-VCH GmbH.)

Lanthanide (Ln 3+ )-doped upconversion (UC) nanoprobes, which have drawn extensive attention for various bioapplications, usually suffer from small absorption cross-sections and weak luminescence intensity of Ln 3+ ions. Herein, we report the controlled synthesis of a new class of Ln 3+ -doped UC nanoprobes based on CsLu 2 F 7 :Yb/Er nanocrystals (NCs), which can effectively increase the intersystem crossing (ISC) efficiency from singlet excited state to triplet excited state of IR808 up to 99.3 % through the heavy atom effect. By virtue of the efficient triplet sensitization of IR808, the optimal UC luminescence (UCL) intensity of IR808-modified CsLu 2 F 7 :Yb/Er NCs is enhanced by 1309 times upon excitation at 808 nm. Benefiting from the intense dye-triplet-sensitized UCL, the nanoprobes are demonstrated for sensitive assay of extracellular and intracellular hypochlorite with an 808-nm/980-nm dual excited ratiometric strategy., (© 2021 Wiley-VCH GmbH.)

Emotion calibration is measured by the valence and arousal scales and the ideal center is used to directly divide valence arousal into high scores and low scores. This division method has a big classification and labeling defect, and the influence of emotion stimulation material on the subjects cannot be accurately measured. To address this problem, this paper proposes an EEG emotion recognition algorithm (DW-FBCSP: Distance Weighted Filter Bank Common Spatial Pattern) based on scale distance weighted optimization to optimize the classification according to the distance of the scores from ideal center. This method is a natural extension of CSP that optimize the user's EEG signal projection matrix. Then, the LDA classifier is used to recognize emotions using the features set which fused the selected features and the features extracted by the projection matrix. The results show that the mean correct rate of the valence and arousal achieves 81.14% and 84.45% using the DEAP dataset. The results demonstrate that our proposed method outperforms better than some other results published in recent years.