Improving the Method of Short-term Forecasting of Electric Load in Distribution Networks using Wavelet transform combined with Ridgelet Neural Network Optimized by Self-adapted Kho-Kho Optimization Algorithm.

This paper proposes a new method for short-term electric load forecasting using a Ridgelet Neural Network (RNN) combined with a wavelet transform and optimized by a Self-Adapted (SA) Kho-Kho algorithm (SAKhoKho). The aim of this method is to improve the accuracy and reliability of electric load forecasting, which is essential for the planning and operation of competitive electrical networks. The proposed method uses the Wavelet Transform (WT) to decompose the load data into different frequency components and applies the RNN to each component separately. The RNN is, then, optimized by the SAKhoKho algorithm, which is an improved version of the KhoKho algorithm that can adapt the search parameters dynamically. The proposed method is trained and tested on the Zone Preliminary Billing Data from the PJM regulatory area, which is updated every two weeks based on the Intercontinental Exchange (ICE) figures. The proposed method is compared with six other cutting-edge methods from the literature, including SVM/SA, hybrid, ARIMA, MLP/PSO, CNN, and RNN/KhoKho/WT. The results show that the proposed method achieves the lowest Mean Absolute Error (MAE) of 7.7704 and Root Mean Square Error (RMSE) of 17.4132 among all the methods, indicating its superior performance. The proposed method can capture the temporal dependencies in the load data and optimize the RNN's weights to minimize the error function. The proposed method is a promising technique for electric load forecasting, as it can provide accurate and reliable predictions for the next hour based on the previous 24 h of data.

Knowledge graph embedding by fusing multimodal content via cross-modal learning.

Knowledge graph embedding aims to learn representation vectors for the entities and relations. Most of the existing approaches learn the representation from the structural information in the triples, which neglects the content related to the entity and relation. Though there are some approaches proposed to exploit the related multimodal content to improve knowledge graph embedding, such as the text description and images associated with the entities, they are not effective to address the heterogeneity and cross-modal correlation constraint of different types of content and network structure. In this paper, we propose a multi-modal content fusion model (MMCF) for knowledge graph embedding. To effectively fuse the heterogenous data for knowledge graph embedding, such as text description, related images and structural information, a cross-modal correlation learning component is proposed. It first learns the intra-modal and inter-modal correlation to fuse the multimodal content of each entity, and then they are fused with the structure features by a gating network. Meanwhile, to enhance the features of relation, the features of the associated head entity and tail entity are fused to learn relation embedding. To effectively evaluate the proposed model, we compare it with other baselines in three datasets, i.e., FB-IMG, WN18RR and FB15k-237. Experiment result of link prediction demonstrates that our model outperforms the state-of-the-art in most of the metrics significantly, implying the superiority of the proposed method.

Overexpression of ClRAP2.4 in Chrysanthemum enhances tolerance to cold stress.

The apetala/ethylene responsive factor (AP2/ERF) family is one of the largest plant-specific transcription factors and plays a vital role in plant development and response to stress. The apetala 2.4 (RAP2.4) gene is a member of the AP2/ERF family. In this study, ClRAP2.4 cDNA fragment with 768bp open reading frame was cloned and the resistance of ClRAP2.4 overexpression to low temperature was investigated to understand whether RAP2.4 is involved in low-temperature stress in chrysanthemum (Chrysamthemum lavandulifolium ). Phylogenetic analysis showed that ClRAP2.4 belonged to the DREB subfamily and was most closely related to AT1G22190. ClRAP2.4 was localised in cell nucleus and promotes transcriptional activation in yeast. In addition, ClRAP2.4 was transformed by using the Agrobacterium -mediated leaf disc method, and four overexpression lines (OX-1, OX-2, OX-7, and OX-8) were obtained. The activities of superoxide dismutase and peroxidase, and proline content in leaves in the four overexpression line were higher than those in the wild type (WT), whereas the electrical conductivity and malondialdehyde content were decreased, indicating that the tolerance of plants with ClRAP2.4 overexpression to cold stress was increased. RNA-Seq showed 390 differentially expressed genes (DEGs) between the transgenic and WT plants(229 upregulated, 161 downregulated). The number of ABRE , LTR , and DRE cis -elements in the promoters of DEGs were 175, 106, and 46, respectively. The relative expression levels of ClCOR , ClFe/MnSOD , ClPOD , ClNCL , ClPLK , ClFAD , and ClPRP in the transgenic plants were higher than those in WT plants at low temperatures. These data suggest that ClRAP2.4 may increase chrysanthemum tolerance to cold stress.

Efficient extraction, excellent activity, and microencapsulation of flavonoids from Moringa oleifera leaves extracted by deep eutectic solvent.

A deep eutectic solvent (choline chloride (ChCl)-urea) was chosen to extract flavonoids from Moringa oleifera leaves (FMOL), the condition of extraction was tailor-made, under the optimal extraction conditions (material-to-liquid ratio of 1:60 g/mL, extraction time of 80 min, extraction temperature of 80 °C), the highest extraction efficiency reached 63.2 ± 0.3 mg R/g DW, and nine flavonoids were identified. Then, the biological activities including antioxidant activities, antibacterial activities, and anti-tumor activities were systematically studied. FMOL was superior to positive drugs in terms of antioxidant activity. As to DPPH investigation, the IC50 of FMOL and Vc were 64.1 ± 0.7 and 176.1 ± 2.0 µg/mL; for the ABTS, the IC50 of FMOL and Vc were 9.5 ± 0.3 and 38.2 ± 1.2 µg/mL, the FRAP value of FMOL and Vc were 15.5 ± 0.6 and 10.2 ± 0.4 mg TE/g, and ORAC value of FMOL and Vc were 4687.2 ± 102.8 and 3881.6 ± 98.6 µmol TE/g. The bacteriostatic (MICs were ≤ 1.25 mg/mL) activities of FMOL were much better than propyl p-hydroxybenzoate. Meanwhile, FMOL had comparable inhibitory activity with genistein on tumor cells, IC50 was 307.8 µg/mL, and could effectively induce apoptosis in HCT116. Microcapsules were prepared with xylose-modified soybean protein isolate and gelatin as wall materials; after that, the intestinal release of modified FMOL microcapsules was 86 times of free FMOL. Therefore, this study confirmed that FMOL extracted with ChCl/urea has rich bioactive components, and microencapsulated FMOL has potential application in food industry. Supplementary Information: The online version contains supplementary material available at 10.1007/s13399-023-03877-8.