Search

BackgroundPopulus simonii, a notable native tree species in northern China, demonstrates impressive resistance to stress, broad adaptability, and exceptional hybridization potential. DOF family is a class of specific transcription factors that only exist in plants, widely participating in plant growth and development, and also playing an important role in abiotic stress response. To date, there have been no reported studies on the DOF gene family in P. simonii, and the expression levels of this gene family in different tissues of poplar, as well as its expression patterns under cold, heat, and other stress conditions, remain unclear.MethodsIn this study, DOF gene family were identified from the P. simonii genome, and various bioinformatics data on the DOF gene family, gene structure, gene distribution, promoters and regulatory networks were analyzed. Quantitative real time PCR technology was used to verify the expression patterns of the DOF gene family in different poplar tissues.ResultsThis research initially pinpointed 41 PSDOF genes in P. simonii genome. The chromosomal localization results revealed that the PSDOF genes is unevenly distributed among 19 chromosomes, with the highest number of genes located on chromosomes 4, 5, and 11. A phylogenetic tree was constructed based on the homology between Arabidopsis thaliana and P. simonii, dividing the 41 PSDOF genes into seven subgroups. The expression patterns of PSDOF genes indicated that specific genes are consistently upregulated in various tissues and under different stress conditions, suggesting their pivotal involvement in both plant development and response to stress. Notably, PSDOF35 and PSDOF28 serve as pivotal hubs in the interaction network, playing a unique role in coordinating with other genes within the family.ConclusionThe analysis enhances our comprehension of the functions of the DOF gene family in tissue development and stress responses within P. simonii. These findings provide a foundation for future exploration into the biological roles of DOF gene family.

Summary: This study aims to comprehensively review a recently emerging multidisciplinary area related to the application of deep learning methods in cryptocurrency research. We first review popular deep learning models employed in multiple financial application scenarios, including convolutional neural networks, recurrent neural networks, deep belief networks, and deep reinforcement learning. We also give an overview of cryptocurrencies by outlining the cryptocurrency history and discussing primary representative currencies. Based on the reviewed deep learning methods and cryptocurrencies, we conduct a literature review on deep learning methods in cryptocurrency research across various modeling tasks, including price prediction, portfolio construction, bubble analysis, abnormal trading, trading regulations and initial coin offering in cryptocurrency. Moreover, we discuss and evaluate the reviewed studies from perspectives of modeling approaches, empirical data, experiment results and specific innovations. Finally, we conclude this literature review by informing future research directions and foci for deep learning in cryptocurrency.

With the development of computer technology, especially the development of artificial intelligence, big data technology and blockchain technology, the transaction mode of traditional economic society and financial market has been changed.Quantitative trading is an important emerging trading mode in the contemporary financial market.To meet the social demand for quantitative trading talents, it is particularly important to explore a reasonable course system of AI and quantitative trading.Firstly, the recent development of quantitative trading and the application of AI in quantitative trading were analyzed.Then, the current situations and problems of the quantitative trading course were summarized.Finally, according to the problems, the suggestions on the course design for AI and quantitative trading were put forward in four aspects, which included teaching content system, teaching practice simulation platform, teacher training, and multi-channel practice platform.

The cone is a crucial component of the whole life cycle of gymnosperm and an organ for sexual reproduction of gymnosperms. In Pinus koraiensis, the quantity and development process of male and female cones directly influence seed production, which in turn influences the tree’s economic value. There are, however, due to the lack of genetic information and genomic data, the morphological development and molecular mechanism of female and male cones of P. koraiensis have not been analyzed. Long-term phenological observations were used in this study to document the main process of the growth of both male and female cones. Transcriptome sequencing and endogenous hormone levels at three critical developmental stages were then analyzed to identify the regulatory networks that control these stages of cones development. The most significant plant hormones influencing male and female cones growth were discovered to be gibberellin and brassinosteroids, according to measurements of endogenous hormone content. Additionally, transcriptome sequencing allowed the identification of 71,097 and 31,195 DEGs in male and female cones. The synthesis and control of plant hormones during cones growth were discovered via enrichment analysis of key enrichment pathways. FT and other flowering-related genes were discovered in the coexpression network of flower growth development, which contributed to the growth development of male and female cones of P. koraiensis. The findings of this work offer a cutting-edge foundation for understanding reproductive biology and the molecular mechanisms that control the growth development of male and female cones in P. koraiensis.

Tilia amurensis is a significant ornamental and economically-important tree species, known for its fragrant flowers, which are a source of high-quality honey production. However, the regulatory mechanisms involved in aroma formation during flower development in T. amurensis remains limited. The current study revealed the detection of plant hormones at every assessed stage of flower development. Among them, auxin and brassinosteroid contents significantly increased at stage 3, potentially regulating crucial functions during T. amurensis flower development. Moreover, the study examined the levels and change patterns of secondary metabolites and employed a combination of transcriptomics and metabolomics to comprehensively assess essential structural genes implicated in the biosynthesis pathways of terpenoid and phenylpropanoid. A comprehensive set of 89,526 differentially expressed genes (DEGs) was uncovered, including candidate structural genes ACAT, HDS, TPS, 4CL, CAD, and CCOAMT, which are specifically involved in the biosynthesis of terpenoids and phenylpropanoids. Maslinic acid, 2α,3α-dihydroxyursolic acid, and betulinic acid were accumulated in the terpenoid biosynthesis pathway. In contrast, metabolites with differential accumulation, such as phenylalanine, coniferyl alcohol, and cinnamic acid, were specifically enriched in the phenylpropanoid biosynthesis pathway. The C2H2, MYB, and NAC transcription factor families are crucially associated with the terpenoid and phenylpropanoid biosynthesis pathways. Two transcription factors, C2H2-17 and MYB-24, exhibited strong co-expression with structural genes in two networks, and were identified as central regulatory factors. These findings establish a solid groundwork for elucidating the generation of floral fragrance and provide comprehensive genetic and metabolic information for further studies on T. amurensis.

The auxin/indole-3-acetic acid (Aux/IAA) and auxin response factor (ARF) genes are two crucial gene families in the plant auxin signaling pathway. Nonetheless, there is limited knowledge regarding the Aux/IAA and ARF gene families in Populus simonii. In this study, we first identified 33 putative PsIAAs and 35 PsARFs in the Populus simonii genome. Analysis of chromosomal location showed that the PsIAAs and PsARFs were distributed unevenly across 17 chromosomes, with the greatest abundance observed on chromosomes 2. Furthermore, based on the homology of PsIAAs and PsARFs, two phylogenetic trees were constructed, classifying 33 PsIAAs and 35 PsARFs into three subgroups each. Five pairs of PsIAA genes were identified as the outcome of tandem duplication, but no tandem repeat gene pairs were found in the PsARF family. The expression profiling of PsIAAs and PsARFs revealed that several genes exhibited upregulation in different tissues and under various stress conditions, indicating their potential key roles in plant development and stress responses. The variance in expression patterns of specific PsIAAs and PsARFs was corroborated through RT-qPCR analysis. Most importantly, we instituted that the PsIAA7 gene, functioning as a central hub, exhibits interactions with numerous Aux/IAA and ARF proteins. Furthermore, subcellular localization findings indicate that PsIAA7 functions as a protein localized within the nucleus. To conclude, the in-depth analysis provided in this study will contribute significantly to advancing our knowledge of the roles played by PsIAA and PsARF families in both the development of P. simonii tissue and its responses to stress. The insights gained will serve as a valuable asset for further inquiries into the biological functions of these gene families.

The MADS-box gene family plays a crucial role in multiple developmental processes of plants, especially in floral organ specification and the regulation of fruit development and ripening. Juglans mandshurica is a precious fruit material whose quality and yield are determined by floral organ development. The molecular mechanism of J. mandshurica female and male flower development depending on MADS-box genes remains unclear. In our study, 67 JmMADS genes were identified and unevenly distributed on 15 of 16 J. mandshurica chromosomes. These genes were divided into two types [type I (Mα, Mγ, Mδ) and type II (MIKC)]. The gene structure and motif analyses showed that most genes belonging to the same type had similar gene structures and conserved motifs. The analysis of syntenic relationships showed that MADS-box genes in J. mandshurica, J. sigillata, and J. regia exhibited the highest homology and great collinearity. Analysis of cis-acting elements showed that JmMADS gene promoter regions contained light, stress and hormone response cis-acting elements. The gene expression patterns demonstrated that 30 and 26 JmMADS genes were specifically expressed in the female and male flowers, respectively. In addition, 12 selected genes common to J. mandshurica female and male flowers were significantly upregulated at the mature stage and were used to validate the reliability of the transcriptome data using quantitative real-time PCR. This comprehensive and systematic analysis of J. mandshurica MADS-box genes lays a foundation for future studies on MADS-box gene family functions.

Light is not only a very important source of energy for the normal growth and development of plants, but also a regulator of many development and metabolic processes. The mechanism of plant growth and development under low light conditions is an important scientific question. With the promulgation of the law to stop natural forest cutting, understory regeneration is an important method for artificial forest afforestation. Here, the growth and physiological indexes of Juglans mandshurica, an important hardwood species in Northeast China, were measured under different shade treatments. In addition, transcriptome and metabolome were compared to analyze the molecular mechanism of shade tolerance in J. mandshurica. The results showed that the seedling height of the shade treatment group was significantly higher than that of the control group, and the 50% light (L50) treatment was the highest. Compared with the control group, the contents of gibberellin, abscisic acid, brassinolide, chlorophyll a, and chlorophyll b in all shade treatments were significantly higher. However, the net photosynthetic rate and water use efficiency decreased with increasing shade. Furthermore, the transcriptome identified thousands of differentially expressed genes in three samples. Using enrichment analysis, we found that most of the differentially expressed genes were enriched in photosynthesis, plant hormone signal transduction and chlorophyll synthesis pathways, and the expression levels of many genes encoding transcription factors were also changed. In addition, analysis of differentially accumulated metabolites showed that a total of 470 differential metabolites were identified, and flavonoids were the major differential metabolites of J. mandshurica under light stress. These results improved our understanding of the molecular mechanism and metabolite accumulation under light stress in J. mandshurica.

Abstract Background Class III peroxidases (POD) proteins are widely present in the plant kingdom that are involved in a broad range of physiological processes including stress responses and lignin polymerization throughout the plant life cycle. At present, POD genes have been studied in Arabidopsis, rice, poplar, maize and Chinese pear, but there are no reports on the identification and function of POD gene family in Betula pendula. Results We identified 90 nonredundant POD genes in Betula pendula. (designated BpPODs). According to phylogenetic relationships, these POD genes were classified into 12 groups. The BpPODs are distributed in different numbers on the 14 chromosomes, and some BpPODs were located sequentially in tandem on chromosomes. In addition, we analyzed the conserved domains of BpPOD proteins and found that they contain highly conserved motifs. We also investigated their expression patterns in different tissues, the results showed that some BpPODs might play an important role in xylem, leaf, root and flower. Furthermore, under low temperature conditions, some BpPODs showed different expression patterns at different times. Conclusions The research on the structure and function of the POD genes in Betula pendula plays a very important role in understanding the growth and development process and the molecular mechanism of stress resistance. These results lay the theoretical foundation for the genetic improvement of Betula pendula.

In aquaculture, the accurate recognition of fish underwater has outstanding academic value and economic benefits for scientifically guiding aquaculture production, which assists in the analysis of aquaculture programs and studies of fish behavior. However, the underwater environment is complex and affected by lighting, water quality, and the mutual obscuration of fish bodies. Therefore, underwater fish images are not very clear, which restricts the recognition accuracy of underwater targets. This paper proposes an improved YOLO-V7 model for the identification of Takifugu rubripes. Its specific implementation methods are as follows: (1) The feature extraction capability of the original network is improved by adding a sizeable convolutional kernel model into the backbone network. (2) Through ameliorating the original detection head, the information flow forms a cascade effect to effectively solve the multi-scale problems and inadequate information extraction of small targets. (3) Finally, this paper appropriately prunes the network to reduce the total computation of the model; meanwhile, it ensures the precision of the detection. The experimental results show that the detection accuracy of the improved YOLO-V7 model is better than that of the original. The average precision improved from 87.79% to 92.86% (when the intersection over union was 0.5), with an increase of 5.07%. Additionally, the amount of computation was reduced by approximately 35%. This shows that the detection precision of the proposed network model was higher than that for the original model, which can provide a reference for the intelligent aquaculture of fishes.

Acer pseudosieboldianum (Pax) Komarov is an ornamental plant with prominent potential and is naturally distributed in Northeast China. Here, we obtained a chromosome-scale genome assembly of A. pseudosieboldianum combining HiFi and Hi-C data, and the final assembled genome size was 690.24 Mb and consisted of 287 contigs, with a contig N50 value of 5.7 Mb and a BUSCO complete gene percentage of 98.4%. Genome evolution analysis showed that an ancient duplication occurred in A. pseudosieboldianum. Phylogenetic analyses revealed that Aceraceae family could be incorporated into Sapindaceae, consistent with the present Angiosperm Phylogeny Group system. We further construct a gene-to-metabolite correlation network and identified key genes and metabolites that might be involved in anthocyanin biosynthesis pathways during leaf color change. Additionally, we identified crucial teosinte branched1, cycloidea, and proliferating cell factors (TCP) transcription factors that might be involved in leaf morphology regulation of A. pseudosieboldianum, Acer yangbiense and Acer truncatum. Overall, this reference genome is a valuable resource for evolutionary history studies of A. pseudosieboldianum and lays a fundamental foundation for its molecular breeding.

How to design an effective experiment system to teach computational intelligence methods is big challenge nowadays. For the computational intelligence course, we design an aquaponics system and use the project-based teaching method. The aquaponics experiment system includes PLC, LabVIEW and OPC technology. The computational intelligence teaching project has data acquisition, sensors, and model subsystems. This project-based teaching method not only allows students to easily learn the computational intelligence methods and soft measurement, but also enhances their practical skills. Finally, we provide the teaching evaluation of the proposed teaching method.

Pinus koraiensis, Pinus sibirica, and Pinus pumila are the major five-needle pines in northeast China, with substantial economic and ecological values. The phenotypic variation, environmental adaptability and evolutionary relationships of these three five-needle pines remain largely undecided. It is therefore important to study their genetic differentiation and evolutionary history. To obtain more genetic information, the needle transcriptomes of the three five-needle pines were sequenced and assembled. To explore the relationship of sequence information and adaptation to a high mountain environment, data on needle morphological traits [needle length (NL), needle width (NW), needle thickness (NT), and fascicle width (FW)] and 19 climatic variables describing the patterns and intensity of temperature and precipitation at six natural populations were recorded. Geographic coordinates of altitude, latitude, and longitude were also obtained. The needle morphological data was combined with transcriptome information, location, and climate data, for a comparative analysis of the three five-needle pines. We found significant differences for needle traits among the populations of the three five-needle pine species. Transcriptome analysis showed that the phenotypic variation and environmental adaptation of the needles of P. koraiensis, P. sibirica, and P. pumila were related to photosynthesis, respiration, and metabolites. Analysis of orthologs from 11 Pinus species indicated a closer genetic relationship between P. koraiensis and P. sibirica compared to P. pumila. Our study lays a foundation for genetic improvement of these five-needle pines and provides insights into the adaptation and evolution of Pinus species.

The C-Repeat Binding Factor (CBF) gene family has been identified and characterized in multiple plant species, and it plays a crucial role in responding to low temperatures. Presently, only a few studies on tree species demonstrate the mechanisms and potential functions of CBFs associated with cold resistance, while our study is a novel report on the multi-aspect differences of CBFs among three tree species, compared to previous studies. In this study, genome-wide identification and analysis of the CBF gene family in Acer truncatum, Acer pseudosieboldianum, and Acer yangbiense were performed. The results revealed that 16 CBF genes (five ApseCBFs, four AcyanCBFs, and seven AtruCBFs) were unevenly distributed across the chromosomes, and most CBF genes were mapped on chromosome 2 (Chr2) and chromosome 11 (Chr11). The analysis of phylogenetic relationships, gene structure, and conserved motif showed that 16 CBF genes could be clustered into three subgroups; they all contained Motif 1 and Motif 5, and most of them only spanned one exon. The cis-acting elements analysis showed that some CBF genes might be involved in hormone and abiotic stress responsiveness. In addition, CBF genes exhibited tissue expression specificity. High expressions of ApseCBF1, ApseCBF3, AtruCBF1, AtruCBF4, AtruCBF6, AtruCBF7, and ApseCBF3, ApseCBF4, ApseCBF5 were detected on exposure to low temperature for 3 h and 24 h. Low expressions of AtruCBF2, AtruCBF6, AtruCBF7 were detected under cold stress for 24 h, and AtruCBF3 and AtruCBF5 were always down-regulated under cold conditions. Taken together, comprehensive analysis will enhance our understanding of the potential functions of the CBF genes on cold resistance, thereby providing a reference for the introduction of Acer species in our country.

Larix olgensis is a tall deciduous tree species that has many applications in the wood fiber industry. Bud mutations are somatic mutations in plants and are considered an ideal material to identify and describe the molecular mechanism of plant mutation. However, the molecular regulatory mechanisms of bud mutations in L. olgensis remain unknown. In this study, dwarfed (or stunted), short-leaved, and multi-branched mutants of L. olgensis were found and utilized to identify crucial genes and regulatory networks controlling the multiple branch structure of L. olgensis. The physiological data showed that the branch number, bud number, fresh and dry weight, tracheid length, tracheid length-width ratio, inner tracheid diameter, and epidermal cell area of mutant plants were higher than that of wild-type plants. Hormone concentration measurements found that auxin, gibberellin, and abscisic acid in the mutant leaves were higher than that in wild-type plants. Moreover, the transcriptome sequencing of all samples using the Illumina Hiseq sequencing platform. Transcriptome analysis identified, respectively, 632, 157, and 199 differentially expressed genes (DEGs) in buds, leaves, and stems between mutant plants and wild type. DEGs were found to be involved in cell division and differentiation, shoot apical meristem activity, plant hormone biosynthesis, and sugar metabolism. Furthermore, bZIP, WRKY, and AP2/ERF family transcription factors play a role in bud formation. This study provides new insights into the molecular mechanisms of L. olgensis bud and branch formation and establishes a fundamental understanding of the breeding of new varieties in L. olgensis.

Korean pine (Pinus koraiensis Sieb. et Zucc.), as the main tree species in northeast China, has important economic and ecological values. Currently, supplementary light has been widely used in plant cultivation projects. However, the studies about different supplementary light sources on the growth and development of Korean pine are few. In this study, the one with no supplementary light was used as the control, and two kinds of light sources were set up: light-emitting diode (LED) and incandescent lamp, to supplement light treatment of Korean pine. The spectrum and intensity of these two light sources were different. The results showed that the growth and physiological–biochemical indicators were significantly different under different supplementary light treatments. The biomass of supplementary light treatment was significantly lower than the control. Compared with the control, IAA and GA were lower, and JA, ABA, ZT, and ETH were higher under supplementary light conditions. Photosynthetic parameters in supplementary light conditions were significantly lower than the control. Supplemental light induces chlorophyll a, chlorophyll b, total chlorophyll, and carotenoid accumulation. From RNA-seq data, differentially expressed genes (DEGs) were observed in all the comparison groups, and there were 487 common DEGs. The expression levels of DEGs encoding transcription factors were also changed. According to GO and KEGG analysis, the plant hormone signal transduction, circadian rhythm-plant, and flavonoid biosynthesis pathways were the most enriched. These results provided a theoretical basis for the response of Korean pine to different supplementary lights.

This paper proposes a hybrid approach combining Wigner-Ville distribution (WVD) with convolutional neural network (CNN) for power quality disturbance (PQD) classification. Firstly, a WVD technique is developed to transfer a 1D voltage disturbance signal into a 2D image file, followed by a CNN model developed for the image classification. Then, the feature maps are extracted automatically from the image file and different patterns are extracted from variables on CNN. A set of synthetic signals, as well as real-world measurement data, are used to test the proposed method. The high classification accuracy of test results is achieved to confirm the effectiveness of the proposed method. Furthermore, the model is simplified and optimized by visualizing the output of convolutional layers. On this basis, one visualizing technique called the class activation map (CAM) is used to identify the location and shape of “hotspots (PQDs)”. The effect of incorrect classification of the model is analyzed with the CAM. Therefore, the proposed method is proved to have the capability of providing necessary and accurate information for PQDs, which will then be used to determine the subsequent PQ remedy actions accordingly.

Light is one of the most important environmental cues that affects plant development and regulates its behavior. Light stress directly inhibits physiological responses and plant tissue development and even induces mortality in plants. Korean pine (Pinus koraiensis) is an evergreen conifer species widely planted in northeast China that has important economic and ecological value. However, the effects of light stress on the growth and development of Korean pine are still unclear. In this study, the effects of different shading conditions on physiological indices, molecular mechanisms and metabolites of Korean pine were explored. The results showed that auxin, gibberellin and abscisic acid were significantly increased under all shading conditions compared with the control. The contents of chlorophyll a, chlorophyll b, total chlorophyll and carotenoid also increased as the shading degree increased. Moreover, a total of 8556, 3751 and 6990 differentially expressed genes (DEGs) were found between the control and HS (heavy shade), control and LS (light shade), LS vs. HS, respectively. Notably, most DEGs were assigned to pathways of phytohormone signaling, photosynthesis, carotenoid and flavonoid biosynthesis under light stress. The transcription factors MYB-related, AP2-ERF and bHLH specifically increased expression during light stress. A total of 911 metabolites were identified, and 243 differentially accumulated metabolites (DAMs) were detected, among which flavonoid biosynthesis (naringenin chalcone, dihydrokaempferol and kaempferol) metabolites were significantly different under light stress. These results will provide a theoretical basis for the response of P. koraiensis to different light stresses.

In recent years, the culture and fishing of precious marine product are heavily dependent on manual work, which is labor-intensive, high-cost and time-consuming. To address this issue, an underwater robot can be used to monitor the size of the marine products and fish the mature ones automatically. Automatic detection of marine products from underwater images is one of the most important steps in developing an underwater robot perceiving method. In the traditional detection model, the CNN based backbone suffers from the limited receptive field and hinders the modeling of long-range dependencies, due to the small kernel size. In this paper, a novel detection model FFT_YOLOX based on a modified YOLOX is proposed. Firstly, a unique FFT_Filter is presented, which is a computational efficient and conceptually simple architecture to capture global information of images. Then, a novel FFT_YOLOX model is introduced with fewer model parameters and FLOPs by replacing the standard 3 × 3 kernel in the original backbone of the YOLOX model with a FFT_Filter, for an underwater object detection vision task. Extensive experimental results demonstrate the effectiveness and generalization of the visual representation of our proposed FFT_YOLOX model.

Flowers are imperative reproductive organs and play a key role in the propagation of offspring, along with the generation of several metabolic products in flowering plants. In Juglans mandshurica, the number and development of flowers directly affect the fruit yield and subsequently its commercial value. However, owing to the lack of genetic information, there are few studies on the reproductive biology of Juglans mandshurica, and the molecular regulatory mechanisms underlying the development of female and male inflorescence remain unclear. In this study, phytohormones and transcriptomic sequencing analyses at the three stages of female and male inflorescence growth were performed to understand the regulatory functions underlying flower development. Gibberellin is the most dominant phytohormone that regulates flower development. In total, 14,579 and 7188 differentially expressed genes were identified after analyzing the development of male and female flowers, respectively, wherein, 3241 were commonly expressed. Enrichment analysis for significantly enriched pathways suggested the roles of MAPK signaling, phytohormone signal transduction, and sugar metabolism. Genes involved in floral organ transition and flowering were obtained and analyzed; these mainly belonged to the M-type MADS-box gene family. Three flowering-related genes (SOC1/AGL20, ANT, and SVP) strongly interacted with transcription factors in the co-expression network. Two key CO genes (CO3 and CO1) were identified in the photoperiod pathway. We also identified two GA20xs genes, one SVP gene, and five AGL genes (AGL8, AGL9, AGL15, AGL19, and AGL42) that contributed to flower development. The findings are expected to provide a genetic basis for the studies on the regulatory networks and reproductive biology in inflorescence development for J. mandshurica.

The NAC (NAM, ATAF and CUC) gene family plays a crucial role in the transcriptional regulation of various biological processes and has been identified and characterized in multiple plant species. However, genome-wide identification of this gene family has not been implemented in Juglans mandshurica, and specific functions of these genes in the development of fruits remain unknown. In this study, we performed genome-wide identification and functional analysis of the NAC gene family during fruit development and identified a total of 114 JmNAC genes in the J. mandshurica genome. Chromosomal location analysis revealed that JmNAC genes were unevenly distributed in 16 chromosomes; the highest numbers were found in chromosomes 2 and 4. Furthermore, according to the homologues of JmNAC genes in Arabidopsis thaliana, a phylogenetic tree was constructed, and the results demonstrated 114 JmNAC genes, which were divided into eight subgroups. Four JmNAC gene pairs were identified as the result of tandem duplicates. Tissue-specific analysis of JmNAC genes during different developmental stages revealed that 39 and 25 JmNAC genes exhibited upregulation during the mature stage in walnut exocarp and embryos, indicating that they may serve key functions in fruit development. Furthermore, 12 upregulated JmNAC genes were common in fruit ripening stage in walnut exocarp and embryos, which demonstrated that these genes were positively correlated with fruit development in J. mandshurica. This study provides new insights into the regulatory functions of JmNAC genes during fruit development in J. mandshurica, thereby improving the understanding of characteristics and evolution of the JmNAC gene family.

This paper presents a hybrid approach combining phase space reconstruction (PSR) with a convolutional neural network (CNN) for power quality disturbance (PQD) classification. Firstly, a PSR technique is developed to transform a 1D voltage disturbance signal into a 2D image file. Then, a CNN model is developed for the image classification. The feature maps are extracted automatically from the image file and different patterns are derived from variables in CNN. A set of synthetic signals, as well as operational measurements, are used to validate the proposed method. Moreover, the test results are also compared with existing methods, including empirical mode decomposition (EMD) with balanced neural tree (BNT), S-transform (ST) with neural network (NN) and decision tree (DT), hybrid ST with DT, adaptive linear neuron (ADALINE) with feedforward neural network (FFNN), and variational mode decomposition (VMD) with deep stochastic configuration network (DSCN). Based on deep learning algorithms, the proposed method is capable of providing more accurate results without any human intervention for PQDs. It also enables the planning of PQ remedy actions.

This paper proposes a novel, two-stage and hybrid approach based on variational mode decomposition (VMD) and the deep stochastic configuration network (DSCN) for power quality (PQ) disturbances detection and classification in power systems. Firstly, a VMD technique is applied to discriminate between stationary and non-stationary PQ events. Secondly, the key parameters of VMD are determined as per different types of disturbance. Three statistical features (mean, variance, and kurtosis) are extracted from the instantaneous amplitude (IA) of the decomposed modes. The DSCN model is then developed to classify PQ disturbances based on these features. The proposed approach is validated by analytical results and actual measurements. Moreover, it is also compared with existing methods including wavelet network, fuzzy and S-transform (ST), adaptive linear neuron (ADALINE) and feedforward neural network (FFNN). Test results have proved that the proposed method is capable of providing necessary and accurate information for PQ disturbances in order to plan PQ remedy actions accordingly.