Structural and functional explorations on bio-soft matter such as micelles,vesicles,nanoparticles,aggregates or polymers derived from traditional Chinese medicine(TCM)has emerged as a new topic in the field of TCM.The...Structural and functional explorations on bio-soft matter such as micelles,vesicles,nanoparticles,aggregates or polymers derived from traditional Chinese medicine(TCM)has emerged as a new topic in the field of TCM.The discovery of such cross-scaled bio-soft matter may provide a unique perspective for unraveling the new effective material basis of TCM as well as developing innovative medicine and biomaterials.Despite the rapid rise of TCM-derived bio-soft matter,their hierarchical structure and assembly mechanism must be unambiguously probed for a further in-depth understanding of their pharmacological activity.In this review,the current emerged TCM-derived bio-soft matter assembled from either small molecules or macromolecules is introduced,and particularly the unambiguous elucidation of their hierarchical structure and assembly mechanism with combined electron microscopic and spectroscopic techniques is depicted.The pros and cons of each technique are also discussed.The future challenges and perspective of TCM-derived bio-soft matter are outlined,particularly the requirement for their precise in situ structural determination is highlighted.展开更多
[Objectives]This study was conducted to investigate the differences of photosynthetic physiological characteristics of different varieties(strains),which will provide a theoretical basis for high photosynthesis effici...[Objectives]This study was conducted to investigate the differences of photosynthetic physiological characteristics of different varieties(strains),which will provide a theoretical basis for high photosynthesis efficiency breeding and application in Chinese chestnut.[Methods]Six Chinese chestnut varieties of Castanea mollissima‘Yanbao’,C.mollissima‘Yanqiu’,C.mollissima‘Yanchang’,C.mollissima‘Yanjia’,C.mollissima‘Qianxi 37’,and C.mollissima‘Hybrid 22’were used as the materials.Using the portable photosynthesis system Li-6400,we measured the photosynthetic characteristics and diurnal variation of leaf samples of six different chestnut varieties or strains.We fitted the light response curves and photosynthetic parameters using the leaf floating model.Additionally,we determined the chlorophyll content in the leaves using a UV-visible spectrophotometer.[Results]Among the six chestnut varieties or strains,‘Yanqiu’exhibited a significantly higher photosynthetic light saturation point(P LSP)compared to other five varieties,and‘Hybrid 22’ranked second,indicating that these two varieties had the strongest adaptation to high light intensity.The photosynthetic light compensation point(P LCP)of‘Yanchang’was significantly higher than other five varieties,and"Qianxi 37"ranked second,indicating that these two varieties had the strongest adaptation to low light intensity.Additionally,they exhibited higher chlorophyll content and maintained good photosynthetic characteristics even in shaded environments with weak light stress.Varieties‘Yanbao’and‘Yanjia’showed higher P LSP and lower P LCP,indicating that these two varieties have a wider range of adaptation to light intensity.They were capable of efficiently utilizing light across a broader spectrum of intensities.‘Yanqiu’had the highest maximum net photosynthetic rate(P n,max)and the lowest dark respiration rate(R d),along with the highest chlorophyll content.It indicated that‘Yanqiu’has strong photosynthetic capacity and organic matter accumulation ability.It also had the highest P LSP,enabling it to fully utilize the high light environment of the Yanshan Mountains and possessed high light efficiency characteristics.The P n,max of‘Yanqiu’was significantly higher than other varieties.‘Hybrid 22’and‘Yanbao’also exhibited significantly higher P n,max compared with‘Yanjia’and‘Qianxi 37’.‘Yanchang’had the lowest P n,max.The order of P n,max among the six chestnut varieties or strains was as follows:‘Yanqiu’>‘Hybrid 22’>‘Yanbao’>‘Yanjia’>‘Qianxi 37’>‘Yanchang’.[Conclusions]展开更多
The expanding role of the Chinese language in international communications has become increasingly prominent as China’s comprehensive national power continues to grow,leading to a significant rise in the number of Ch...The expanding role of the Chinese language in international communications has become increasingly prominent as China’s comprehensive national power continues to grow,leading to a significant rise in the number of Chinese language learners.Since online teaching is not limited by time and space,its application is widespread.For beginners in the Chinese language,the Chinese characters are both a priority and a challenge.The“Chinese Character Classification,”also known as the“Six Writings,”is the earliest systematic theory of Chinese character structures,and teaching Chinese characters in categories based on the“Chinese Character Classification”is a method that fits the cognition of beginners.In order to teach Chinese characters in a targeted approach,based on the collection and analysis of the common errors of Chinese characters among beginners,(1)this paper proposes that(a)the intuitive method can be applied to teach pictographic characters,indicative characters,and associative compound characters in online teaching;(b)the inductive-deductive method of“basic characters to new characters”can be applied for the teaching of pictophonetic characters and associative compound characters;(c)the learning of character patterns should be approached in a whole-part-whole process,while importance should be attached to the suggestion of the frequency effect with a view to facilitating the online learning of Chinese characters for beginners.The aim of this paper is to provide some practical implications for the online teaching of Chinese characters to foreigners.展开更多
Chestnut is a high nutritional value food that has been widely used as a tonic in traditional Chinese medicine.As an emerging functional food ingredient,Chinese chestnuts are rich in a range of bioactive nutrients suc...Chestnut is a high nutritional value food that has been widely used as a tonic in traditional Chinese medicine.As an emerging functional food ingredient,Chinese chestnuts are rich in a range of bioactive nutrients such as starch,dietary fiber,fat,protein,trace metal element and vitamins A,B,C,D and other nutrients.In our study,Chinese chestnut powder(CCP)were added into bread formulation at 2%-6%levels(based on flour weight)to produce fresh bread with enhanced anti-staling characteristics and starch digestion inhibitory ability.The texture properties,retrogradation enthalpy,water distribution,and estimated glycemic index(eGI)of wheat bread containing CCP as a functional additive were also investigated.The results showed that incorporation of CCP apparently affected bread texture,resulting in increased hardness,as well as decreased the specific volume of wheat bread.These influences were generally proportional to the amount of CCP used.It was found that adding too much CCP resulted in a dark red color,showing increased significantly higher total color difference(ΔE)and L values.Conversely,addition of CCP significantly reduced starch digestion rate and digestion extent in bread,and the reduction degree was positively related to the amount of CCP applied.The greatest reduction in eGI value from 79.40(control)to 75.02(6%CPP bread)was observed.Meanwhile,the content of resistant starch of 6%CPP bread was about 1.36 times higher than that of control bread.CCP also reduced crumb water loss and drove the water shift from the bound to the mobile state after stored for 7 days.The retrogradation enthalpy analyses further confirmed that CCP inhibited starch retrogradation and recrystallization.These results suggested that Chinese chestnut powder could be incorporated into fresh bread to provide health functions,such as lowering potential glycaemic response and improving anti-staling characteristics of bread.展开更多
Wheat allergy has become a serious health threat worldwide and its prevalence has increased alarmingly in the past few years.Factors such as food matrix and food processing may alter the structure of wheat proteins,an...Wheat allergy has become a serious health threat worldwide and its prevalence has increased alarmingly in the past few years.Factors such as food matrix and food processing may alter the structure of wheat proteins,and hence affect its allergenic properties.However,few reports have focused on the influence of Chinese traditional starter fermentation on wheat allergy.In this study,5 starters from different regions of China were used for fermentation,and protein characteristics were monitored by sodium dodecyl sulfate polyacrylamide gel electropheresis,and immunoreactivity analyzed by immunoassay with allergenic serum was obtained from New Zealand white rabbits.The allergenicity of steamed and baked matrices was also evaluated.The results showed that the allergenicity of wheat dough was basically increased at the beginning and then decreased during fermentation,but specific trends depend on different starters.With the progress of fermentation,especially as pH value decreased to 3.0-4.0,the allergenicity decreased significantly.Baking and steaming can reduce the allergenicity of wheat matrix,but fermentation is not a key factor affecting the allergenic activity of proteins.Our results can provide a theoretical basis for controlling wheat allergenicity in food proces sing or producing hypoallergenic food.展开更多
In recent years, more and more foreigners begin to learn Chinese characters, but they often make typos when using Chinese. The fundamental reason is that they mainly learn Chinese characters from the glyph and pronunc...In recent years, more and more foreigners begin to learn Chinese characters, but they often make typos when using Chinese. The fundamental reason is that they mainly learn Chinese characters from the glyph and pronunciation, but do not master the semantics of Chinese characters. If they can understand the meaning of Chinese characters and form knowledge groups of the characters with relevant meanings, it can effectively improve learning efficiency. We achieve this goal by building a Chinese character semantic knowledge graph (CCSKG). In the process of building the knowledge graph, the semantic computing capacity of HowNet was utilized, and 104,187 associated edges were finally established for 6752 Chinese characters. Thanks to the development of deep learning, OpenHowNet releases the core data of HowNet and provides useful APIs for calculating the similarity between two words based on sememes. Therefore our method combines the advantages of data-driven and knowledge-driven. The proposed method treats Chinese sentences as subgraphs of the CCSKG and uses graph algorithms to correct Chinese typos and achieve good results. The experimental results show that compared with keras-bert and pycorrector + ernie, our method reduces the false acceptance rate by 38.28% and improves the recall rate by 40.91% in the field of learning Chinese as a foreign language. The CCSKG can help to promote Chinese overseas communication and international education.展开更多
This research is based on the framework of social constructivism,utilizing the principle of Human Universals as a methodology to compare the similarities and differences between the ideation and formation methods of C...This research is based on the framework of social constructivism,utilizing the principle of Human Universals as a methodology to compare the similarities and differences between the ideation and formation methods of Chinese characters and English alphabets.Through comparative analysis of the ideation of English letters(pictogramme)and the origin of Chinese characters,known as the"Six Categories Theory,"we discover their alignment in terms of social,traditional,and cultural aspects.This suggests that different ethnic groups share common features in terms of life experience,learning cognitive development,and thinking habits.This study also finds that the origins of English letters and Chinese characters share similar linguistic features in their methods of constructing letters/characters,such as pictographic,ideographic,and semantic characteristics.Exploring these commonalities contributes to promoting learning and communication between Chinese and English characters.Additionally,by focusing on socio-cultural aspects,traditional customs,and cognitive learning,this study aims to break away from the traditional linguistic research approach that solely focuses on language differences.This provides a broader perspective and richer dimensions for Chinese and English language learning,facilitating the development of cross-linguistic and cross-cultural communication.展开更多
Medical institution preparations play an important role in the development of hospitals,being one of the main forms of traditional Chinese medicine clinical characteristic medication,as well as an important carrier fo...Medical institution preparations play an important role in the development of hospitals,being one of the main forms of traditional Chinese medicine clinical characteristic medication,as well as an important carrier for the inheritance and innovation of traditional Chinese medicine.In recent years,the research and development of traditional Chinese medicine preparations has become a hot spot in the research and development of preparations by medical institutions.Traditional Chinese medicine preparations prepared by traditional processes and their entrusted preparation matters have changed from the current licensing management to filing management.The registration model of traditional Chinese medicine preparations has undergone significant changes,emphasizing more on real data and evaluation results from the objective world,respecting traditional medication experience,and emphasizing the inheritance and innovative development of traditional technological experience.In the process of following teachers in the inheritance project of traditional Chinese medicine,we combined the inheritance of traditional Chinese medicine characteristic technology with the research and development practice of traditional Chinese medicine preparations in medical institutions,and focused on the analysis and discussion of technical problems such as prescription screening,dosage form selection,process route design and clinical observation of traditional Chinese medicine preparations,hoping to provide reference for scholars in the same field of traditional Chinese medicine.展开更多
2018 witnessed some unprecedently strict regulations on national media content production and distribution by the Chinese National Radio and Television Administration(NRTA).On its annual recommended lists of excellent...2018 witnessed some unprecedently strict regulations on national media content production and distribution by the Chinese National Radio and Television Administration(NRTA).On its annual recommended lists of excellent national TV series,there is a noticeable increase in historical series in line with core socialist values.Since late 2019,there has been a strict home-quarantine policy amid the COVID-19 pandemic.Accompanied by the newly introduced three-child birth policy in the context of the country’s low fertility rate and significant ageing,a re-emphasis on traditional Confucian ideologies incented by the Chinese authorities emerged:the primary identity of women being an understanding wife and loving mother.Furthermore,thus,a manifestation of such enforced patriarchal ideologies and cultural values is visible in the country’s strictly regulated media content.This study sets off from a corpus of national recommended TV lists to investigate the myth of women’s fates in amid-pandemic Chinese TV series that are appraised and supported by authorities to explore how their identities are constructed and potentially abused under patriarchal media production.展开更多
China,under the guidance of Xi Jinping Thought on Diplomacy,is making all-round efforts to pursue major-country diplomacy with Chinese characteristics and has achieved a series of historical achievements.Major-country...China,under the guidance of Xi Jinping Thought on Diplomacy,is making all-round efforts to pursue major-country diplomacy with Chinese characteristics and has achieved a series of historical achievements.Major-country diplomacy with Chinese characteristics significantly diverges from conventional Western major-country diplomacy.It is characterized by a vision that prioritizes national rejuvenation,aims to advance human civilizations,emphasizes the establishment of a new type of international relations,and strives for the building of a human community with a shared future.展开更多
This paper focuses on examining the relevant policies concerning Chinese language education within Iran’s foreign language education policy framework from the perspective of its historical context.By analyzing the ch...This paper focuses on examining the relevant policies concerning Chinese language education within Iran’s foreign language education policy framework from the perspective of its historical context.By analyzing the characteristics of Iran’s foreign language policy and the current situation of Chinese language teaching in Iran,this paper studies the future development of international Chinese language education in Iran.展开更多
6G is envisioned as the next generation of wireless communication technology,promising unprecedented data speeds,ultra-low Latency,and ubiquitous Connectivity.In tandem with these advancements,blockchain technology is...6G is envisioned as the next generation of wireless communication technology,promising unprecedented data speeds,ultra-low Latency,and ubiquitous Connectivity.In tandem with these advancements,blockchain technology is leveraged to enhance computer vision applications’security,trustworthiness,and transparency.With the widespread use of mobile devices equipped with cameras,the ability to capture and recognize Chinese characters in natural scenes has become increasingly important.Blockchain can facilitate privacy-preserving mechanisms in applications where privacy is paramount,such as facial recognition or personal healthcare monitoring.Users can control their visual data and grant or revoke access as needed.Recognizing Chinese characters from images can provide convenience in various aspects of people’s lives.However,traditional Chinese character text recognition methods often need higher accuracy,leading to recognition failures or incorrect character identification.In contrast,computer vision technologies have significantly improved image recognition accuracy.This paper proposed a Secure end-to-end recognition system(SE2ERS)for Chinese characters in natural scenes based on convolutional neural networks(CNN)using 6G technology.The proposed SE2ERS model uses the Weighted Hyperbolic Curve Cryptograph(WHCC)of the secure data transmission in the 6G network with the blockchain model.The data transmission within the computer vision system,with a 6G gradient directional histogram(GDH),is employed for character estimation.With the deployment of WHCC and GDH in the constructed SE2ERS model,secure communication is achieved for the data transmission with the 6G network.The proposed SE2ERS compares the performance of traditional Chinese text recognition methods and data transmission environment with 6G communication.Experimental results demonstrate that SE2ERS achieves an average recognition accuracy of 88%for simple Chinese characters,compared to 81.2%with traditional methods.For complex Chinese characters,the average recognition accuracy improves to 84.4%with our system,compared to 72.8%with traditional methods.Additionally,deploying the WHCC model improves data security with the increased data encryption rate complexity of∼12&higher than the traditional techniques.展开更多
Chinese cabbage(Brassica rapa ssp. pekinensis) has a long cultivation history and is one of the vegetable crops with the largest cultivation area in China. However, salt stress severely damages photosynthesis and horm...Chinese cabbage(Brassica rapa ssp. pekinensis) has a long cultivation history and is one of the vegetable crops with the largest cultivation area in China. However, salt stress severely damages photosynthesis and hormone metabolism, nutritional balances, and results in ion toxicity in plants. To better understand the mechanisms of salt-induced growth inhibition in Chinese cabbage, RNA-seq and physiological index determination were conducted to explore the impacts of salt stress on carbon cycle metabolism and photosynthesis in Chinese cabbage. Here, we found that the number of thylakoids and grana lamellae and the content of starch granules and chlorophyll in the leaves of Chinese cabbage under salt stress showed a time-dependent response, first increasing and then decreasing. Chinese cabbage increased the transcript levels of genes related to the photosynthetic apparatus and carbon metabolism under salt stress, probably in an attempt to alleviate damage to the photosynthetic system and enhance CO_(2) fixation and energy metabolism. The transcription of genes related to starch and sucrose synthesis and degradation were also enhanced;this might have been an attempt to maintain intracellular osmotic pressure by increasing soluble sugar concentrations. Soluble sugars could also be used as potential reactive oxygen species(ROS) scavengers, in concert with peroxidase(POD)enzymes, to eliminate ROS that accumulate during metabolic processes. Our study characterizes the synergistic response network of carbon metabolism and photosynthesis under salt stress.展开更多
This paper discusses the inheritance and application of Chinese character reverse contrast typeface style.It begins by analyzing the visual features of Western reverse contrast typeface styles,with a focus on Caslon I...This paper discusses the inheritance and application of Chinese character reverse contrast typeface style.It begins by analyzing the visual features of Western reverse contrast typeface styles,with a focus on Caslon Italian and French Clarendon,providing a Western perspective reference for subsequent Chinese character reverse contrast typeface style designs.The paper then traces the origins of the Chinese reverse contrast style,from the calligraphy style"Lacquer Script"to the earliest printing type"フワンテール形",exploring the historical background and cultural significance of the Chinese reverse contrast style.In the methodology section of Chinese character reverse contrast typeface style design,the discussion is conducted from two dimensions:inheritance and application.In terms of inheritance,through an in-depth analysis of"Lacquer Script"and"フワンテール形"typeface style,the paper summarizes three basic theories for modern Chinese character reverse contrast typeface style design.In the application section,it examines in detail the two most influential recent typeface styles,"Ribaasu"and"Basic Artistic",outlining three directions of application:extreme horizontal stroke variations,exaggerated contrast,and diverse decorative strokes,showcasing new directions and possibilities for Chinese character reverse contrast typeface style design.This paper not only reviews the developmental history of the Chinese character reverse contrast typeface style but also analyzes the design methodology of Chinese character reverse contrast typeface style through specific case studies.展开更多
Cities hold a critical responsibility for achieving the Sustainable Development Goals(SDGs)due to their high population density,extensive resource consumption,and significant economic contributions.To examine the pres...Cities hold a critical responsibility for achieving the Sustainable Development Goals(SDGs)due to their high population density,extensive resource consumption,and significant economic contributions.To examine the present state of understandings regarding urban sustainability(SDG 11:Sustainable Cities and Communities)within Chinese research communities,this study collected 15950 papers from 1994 to 2022 on the 12 indicators of SDG 11,from the China National Knowledge Infrastructure(CNKI),a hub of Chinese academic papers,that directly relate to policymaking.Significant research topics on SDG 11 were identified for each indicator using bibliometrics analysis approaches.The high-frequency keywords and clusters of keywords over the last three decades reveal that existing studies primarily concentrated on the physical aspects,such as transportation and environment,while there is a lack of consideration of societal aspects.This indicates a limited and biased understanding of the urban sustainability within the Chinese academic community.Hence,it is crucial to prioritize the societal aspects in order to develop a research agenda that further advances urban sustainability.展开更多
Handwritten character recognition is considered challenging compared with machine-printed characters due to the different human writing styles.Arabic is morphologically rich,and its characters have a high similarity.T...Handwritten character recognition is considered challenging compared with machine-printed characters due to the different human writing styles.Arabic is morphologically rich,and its characters have a high similarity.The Arabic language includes 28 characters.Each character has up to four shapes according to its location in the word(at the beginning,middle,end,and isolated).This paper proposed 12 CNN architectures for recognizing handwritten Arabic characters.The proposed architectures were derived from the popular CNN architectures,such as VGG,ResNet,and Inception,to make them applicable to recognizing character-size images.The experimental results on three well-known datasets showed that the proposed architectures significantly enhanced the recognition rate compared to the baseline models.The experiments showed that data augmentation improved the models’accuracies on all tested datasets.The proposed model outperformed most of the existing approaches.The best achieved results were 93.05%,98.30%,and 96.88%on the HIJJA,AHCD,and AIA9K datasets.展开更多
Non-equilibrium solidification structures of Cu55Ni45 and Cu55Ni43Co2 alloys were prepared by the molten glass purification cycle superheating method.The variation of the recalescence phenomenon with the degree of und...Non-equilibrium solidification structures of Cu55Ni45 and Cu55Ni43Co2 alloys were prepared by the molten glass purification cycle superheating method.The variation of the recalescence phenomenon with the degree of undercooling in the rapid solidification process was investigated using an infrared thermometer.The addition of the Co element affected the evolution of the recalescence phenomenon in Cu-Ni alloys.The images of the solid-liquid interface migration during the rapid solidification of supercooled melts were captured by using a high-speed camera.The solidification rate of Cu-Ni alloys,with the addition of Co elements,was explored.Finally,the grain refinement structure with low supercooling was characterised using electron backscatter diffraction(EBSD).The effect of Co on the microstructural evolution during nonequilibrium solidification of Cu-Ni alloys under conditions of small supercooling is investigated by comparing the microstructures of Cu55Ni45 and Cu55Ni43Co2 alloys.The experimental results show that the addition of a small amount of Co weakens the recalescence behaviour of the Cu55Ni45 alloy and significantly reduces the thermal strain in the rapid solidification phase.In the rapid solidification phase,the thermal strain is greatly reduced,and there is a significant increase in the characteristic undercooling degree.Furthermore,the addition of Co and the reduction of Cu not only result in a lower solidification rate of the alloy,but also contribute to the homogenisation of the grain size.展开更多
In order to reduce the waste of resources and environmental pollution caused by excessive application of chemical fertilizers, improve the utilization rate of fertilizers, and promote the large-scale and high-quality ...In order to reduce the waste of resources and environmental pollution caused by excessive application of chemical fertilizers, improve the utilization rate of fertilizers, and promote the large-scale and high-quality development of the Chinese rose industry. In this experiment, corn stover biochar, phosphoric acid modified biochar and organic fertilizer were used as test materials, and the effects of mixed application of modified biochar and organic fertilizer on the growth and development of Chinese rose as well as soil physicochemical properties were investigated by using the method of pot planting test. The results showed that modified biochar with organic fertilizer had the most significant effect on the enhancement of soil pH, organic matter content and soil carbon-to-nitrogen ratio. After 120 d of planting, modified biochar with organic fertilizer had the most significant effect on the enhancement of plant height and crown width of Chinese rose;both organic fertilizer and modified biochar with organic fertilizer significantly increased the chlorophyll content of Chinese rose. The number of flowers and the number of branches were the highest in the modified biochar with organic fertilizer treatment. In conclusion, the application of modified biochar with organic fertilizer can better improve the soil pH, and increase the soil organic matter content and carbon-to-nitrogen ratio to change the biological traits of Chinese rose. The results of this study provide a theoretical basis for the reduction of chemical fertilizers and the resource utilization of agricultural wastes and guarantee the sustainable development of the cut flower industry.展开更多
Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detec...Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detection and recognition.In the detection stage,an improved Differentiable Binarization Network(DBNet)framework is introduced to detect Yi characters,in which the Omni-dimensional Dynamic Convolution(ODConv)is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features,thereby improving the accuracy of Yi character detection.Then,the feature pyramid network fusion module is used to further extract Yi character image features,improving target recognition at different scales.Further,the previously generated feature map is passed through a head network to produce two maps:a probability map and an adaptive threshold map of the same size as the original map.These maps are then subjected to a differentiable binarization process,resulting in an approximate binarization map.This map helps to identify the boundaries of the text boxes.Finally,the text detection box is generated after the post-processing stage.In the recognition stage,an improved lightweight MobileNetV3 framework is used to recognize the detect character regions,where the original Squeeze-and-Excitation(SE)block is replaced by the efficient Shuffle Attention(SA)that integrates spatial and channel attention,improving the accuracy of Yi characters recognition.Meanwhile,the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model,so that the model can better understand the contextual information and improve the accuracy of text recognition.The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters,with detection and recognition accuracy rates of 97.5%and 96.8%,respectively.And also,we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms.In these comparisons,the proposed model achieves better detection and recognition results with a certain reliability.展开更多
Aspect-Based Sentiment Analysis(ABSA)is a fundamental area of research in Natural Language Processing(NLP).Within ABSA,Aspect Sentiment Quad Prediction(ASQP)aims to accurately identify sentiment quadruplets in target ...Aspect-Based Sentiment Analysis(ABSA)is a fundamental area of research in Natural Language Processing(NLP).Within ABSA,Aspect Sentiment Quad Prediction(ASQP)aims to accurately identify sentiment quadruplets in target sentences,including aspect terms,aspect categories,corresponding opinion terms,and sentiment polarity.However,most existing research has focused on English datasets.Consequently,while ASQP has seen significant progress in English,the Chinese ASQP task has remained relatively stagnant.Drawing inspiration from methods applied to English ASQP,we propose Chinese generation templates and employ prompt-based instruction learning to enhance the model’s understanding of the task,ultimately improving ASQP performance in the Chinese context.Ultimately,under the same pre-training model configuration,our approach achieved a 5.79%improvement in the F1 score compared to the previously leading method.Furthermore,when utilizing a larger model with reduced training parameters,the F1 score demonstrated an 8.14%enhancement.Additionally,we suggest a novel evaluation metric based on the characteristics of generative models,better-reflecting model generalization.Experimental results validate the effectiveness of our approach.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.:82374033,21901067)Ministry of Science and Technology of China(Grant No.:2023YFC3504100)Starting Grant from the Ministry of Human Resource and Social Security of China(Quan Li).
文摘Structural and functional explorations on bio-soft matter such as micelles,vesicles,nanoparticles,aggregates or polymers derived from traditional Chinese medicine(TCM)has emerged as a new topic in the field of TCM.The discovery of such cross-scaled bio-soft matter may provide a unique perspective for unraveling the new effective material basis of TCM as well as developing innovative medicine and biomaterials.Despite the rapid rise of TCM-derived bio-soft matter,their hierarchical structure and assembly mechanism must be unambiguously probed for a further in-depth understanding of their pharmacological activity.In this review,the current emerged TCM-derived bio-soft matter assembled from either small molecules or macromolecules is introduced,and particularly the unambiguous elucidation of their hierarchical structure and assembly mechanism with combined electron microscopic and spectroscopic techniques is depicted.The pros and cons of each technique are also discussed.The future challenges and perspective of TCM-derived bio-soft matter are outlined,particularly the requirement for their precise in situ structural determination is highlighted.
基金Supported by National Key R&D Program of China (2022YFD2200400)Doctoral Started Fund of Hebei Normal University of Science and Technology (2023YB026)Hebei Qinglong Chinese Chestnut Technological Yard.
文摘[Objectives]This study was conducted to investigate the differences of photosynthetic physiological characteristics of different varieties(strains),which will provide a theoretical basis for high photosynthesis efficiency breeding and application in Chinese chestnut.[Methods]Six Chinese chestnut varieties of Castanea mollissima‘Yanbao’,C.mollissima‘Yanqiu’,C.mollissima‘Yanchang’,C.mollissima‘Yanjia’,C.mollissima‘Qianxi 37’,and C.mollissima‘Hybrid 22’were used as the materials.Using the portable photosynthesis system Li-6400,we measured the photosynthetic characteristics and diurnal variation of leaf samples of six different chestnut varieties or strains.We fitted the light response curves and photosynthetic parameters using the leaf floating model.Additionally,we determined the chlorophyll content in the leaves using a UV-visible spectrophotometer.[Results]Among the six chestnut varieties or strains,‘Yanqiu’exhibited a significantly higher photosynthetic light saturation point(P LSP)compared to other five varieties,and‘Hybrid 22’ranked second,indicating that these two varieties had the strongest adaptation to high light intensity.The photosynthetic light compensation point(P LCP)of‘Yanchang’was significantly higher than other five varieties,and"Qianxi 37"ranked second,indicating that these two varieties had the strongest adaptation to low light intensity.Additionally,they exhibited higher chlorophyll content and maintained good photosynthetic characteristics even in shaded environments with weak light stress.Varieties‘Yanbao’and‘Yanjia’showed higher P LSP and lower P LCP,indicating that these two varieties have a wider range of adaptation to light intensity.They were capable of efficiently utilizing light across a broader spectrum of intensities.‘Yanqiu’had the highest maximum net photosynthetic rate(P n,max)and the lowest dark respiration rate(R d),along with the highest chlorophyll content.It indicated that‘Yanqiu’has strong photosynthetic capacity and organic matter accumulation ability.It also had the highest P LSP,enabling it to fully utilize the high light environment of the Yanshan Mountains and possessed high light efficiency characteristics.The P n,max of‘Yanqiu’was significantly higher than other varieties.‘Hybrid 22’and‘Yanbao’also exhibited significantly higher P n,max compared with‘Yanjia’and‘Qianxi 37’.‘Yanchang’had the lowest P n,max.The order of P n,max among the six chestnut varieties or strains was as follows:‘Yanqiu’>‘Hybrid 22’>‘Yanbao’>‘Yanjia’>‘Qianxi 37’>‘Yanchang’.[Conclusions]
基金an outcome of the project of Sichuan University,“A Preliminary Study on Online Chinese Character Teaching Strategies for Teaching Chinese as a Foreign Language During the COVID-19 Pandemic,”Project No.2022 Self-Research-Overseas 008。
文摘The expanding role of the Chinese language in international communications has become increasingly prominent as China’s comprehensive national power continues to grow,leading to a significant rise in the number of Chinese language learners.Since online teaching is not limited by time and space,its application is widespread.For beginners in the Chinese language,the Chinese characters are both a priority and a challenge.The“Chinese Character Classification,”also known as the“Six Writings,”is the earliest systematic theory of Chinese character structures,and teaching Chinese characters in categories based on the“Chinese Character Classification”is a method that fits the cognition of beginners.In order to teach Chinese characters in a targeted approach,based on the collection and analysis of the common errors of Chinese characters among beginners,(1)this paper proposes that(a)the intuitive method can be applied to teach pictographic characters,indicative characters,and associative compound characters in online teaching;(b)the inductive-deductive method of“basic characters to new characters”can be applied for the teaching of pictophonetic characters and associative compound characters;(c)the learning of character patterns should be approached in a whole-part-whole process,while importance should be attached to the suggestion of the frequency effect with a view to facilitating the online learning of Chinese characters for beginners.The aim of this paper is to provide some practical implications for the online teaching of Chinese characters to foreigners.
基金This research has been financially supported by National Key R&D Program of China(2019YFD1002300)Open Project Program of Grain,Oil and Food Engineering Technology Research Center of the State Grain and Reserves Administration/Key Laboratory of Henan Province,Henan University of Technology(GO202216)+1 种基金Doctor Foundation of Henan University of Technology(2019BS057)Cultivation Programme for Young Backbone Teachers in Henan University of Technology for financial support(21420187).
文摘Chestnut is a high nutritional value food that has been widely used as a tonic in traditional Chinese medicine.As an emerging functional food ingredient,Chinese chestnuts are rich in a range of bioactive nutrients such as starch,dietary fiber,fat,protein,trace metal element and vitamins A,B,C,D and other nutrients.In our study,Chinese chestnut powder(CCP)were added into bread formulation at 2%-6%levels(based on flour weight)to produce fresh bread with enhanced anti-staling characteristics and starch digestion inhibitory ability.The texture properties,retrogradation enthalpy,water distribution,and estimated glycemic index(eGI)of wheat bread containing CCP as a functional additive were also investigated.The results showed that incorporation of CCP apparently affected bread texture,resulting in increased hardness,as well as decreased the specific volume of wheat bread.These influences were generally proportional to the amount of CCP used.It was found that adding too much CCP resulted in a dark red color,showing increased significantly higher total color difference(ΔE)and L values.Conversely,addition of CCP significantly reduced starch digestion rate and digestion extent in bread,and the reduction degree was positively related to the amount of CCP applied.The greatest reduction in eGI value from 79.40(control)to 75.02(6%CPP bread)was observed.Meanwhile,the content of resistant starch of 6%CPP bread was about 1.36 times higher than that of control bread.CCP also reduced crumb water loss and drove the water shift from the bound to the mobile state after stored for 7 days.The retrogradation enthalpy analyses further confirmed that CCP inhibited starch retrogradation and recrystallization.These results suggested that Chinese chestnut powder could be incorporated into fresh bread to provide health functions,such as lowering potential glycaemic response and improving anti-staling characteristics of bread.
基金supported by the National Natural Science Foundation of China(31872904)。
文摘Wheat allergy has become a serious health threat worldwide and its prevalence has increased alarmingly in the past few years.Factors such as food matrix and food processing may alter the structure of wheat proteins,and hence affect its allergenic properties.However,few reports have focused on the influence of Chinese traditional starter fermentation on wheat allergy.In this study,5 starters from different regions of China were used for fermentation,and protein characteristics were monitored by sodium dodecyl sulfate polyacrylamide gel electropheresis,and immunoreactivity analyzed by immunoassay with allergenic serum was obtained from New Zealand white rabbits.The allergenicity of steamed and baked matrices was also evaluated.The results showed that the allergenicity of wheat dough was basically increased at the beginning and then decreased during fermentation,but specific trends depend on different starters.With the progress of fermentation,especially as pH value decreased to 3.0-4.0,the allergenicity decreased significantly.Baking and steaming can reduce the allergenicity of wheat matrix,but fermentation is not a key factor affecting the allergenic activity of proteins.Our results can provide a theoretical basis for controlling wheat allergenicity in food proces sing or producing hypoallergenic food.
文摘In recent years, more and more foreigners begin to learn Chinese characters, but they often make typos when using Chinese. The fundamental reason is that they mainly learn Chinese characters from the glyph and pronunciation, but do not master the semantics of Chinese characters. If they can understand the meaning of Chinese characters and form knowledge groups of the characters with relevant meanings, it can effectively improve learning efficiency. We achieve this goal by building a Chinese character semantic knowledge graph (CCSKG). In the process of building the knowledge graph, the semantic computing capacity of HowNet was utilized, and 104,187 associated edges were finally established for 6752 Chinese characters. Thanks to the development of deep learning, OpenHowNet releases the core data of HowNet and provides useful APIs for calculating the similarity between two words based on sememes. Therefore our method combines the advantages of data-driven and knowledge-driven. The proposed method treats Chinese sentences as subgraphs of the CCSKG and uses graph algorithms to correct Chinese typos and achieve good results. The experimental results show that compared with keras-bert and pycorrector + ernie, our method reduces the false acceptance rate by 38.28% and improves the recall rate by 40.91% in the field of learning Chinese as a foreign language. The CCSKG can help to promote Chinese overseas communication and international education.
文摘This research is based on the framework of social constructivism,utilizing the principle of Human Universals as a methodology to compare the similarities and differences between the ideation and formation methods of Chinese characters and English alphabets.Through comparative analysis of the ideation of English letters(pictogramme)and the origin of Chinese characters,known as the"Six Categories Theory,"we discover their alignment in terms of social,traditional,and cultural aspects.This suggests that different ethnic groups share common features in terms of life experience,learning cognitive development,and thinking habits.This study also finds that the origins of English letters and Chinese characters share similar linguistic features in their methods of constructing letters/characters,such as pictographic,ideographic,and semantic characteristics.Exploring these commonalities contributes to promoting learning and communication between Chinese and English characters.Additionally,by focusing on socio-cultural aspects,traditional customs,and cognitive learning,this study aims to break away from the traditional linguistic research approach that solely focuses on language differences.This provides a broader perspective and richer dimensions for Chinese and English language learning,facilitating the development of cross-linguistic and cross-cultural communication.
基金Supported by The Third Batch of Traditional Chinese Medicine Famous Doctors Inheritance Implementation Project in Guizhou Province in 2021(QZYYH[2021]106).
文摘Medical institution preparations play an important role in the development of hospitals,being one of the main forms of traditional Chinese medicine clinical characteristic medication,as well as an important carrier for the inheritance and innovation of traditional Chinese medicine.In recent years,the research and development of traditional Chinese medicine preparations has become a hot spot in the research and development of preparations by medical institutions.Traditional Chinese medicine preparations prepared by traditional processes and their entrusted preparation matters have changed from the current licensing management to filing management.The registration model of traditional Chinese medicine preparations has undergone significant changes,emphasizing more on real data and evaluation results from the objective world,respecting traditional medication experience,and emphasizing the inheritance and innovative development of traditional technological experience.In the process of following teachers in the inheritance project of traditional Chinese medicine,we combined the inheritance of traditional Chinese medicine characteristic technology with the research and development practice of traditional Chinese medicine preparations in medical institutions,and focused on the analysis and discussion of technical problems such as prescription screening,dosage form selection,process route design and clinical observation of traditional Chinese medicine preparations,hoping to provide reference for scholars in the same field of traditional Chinese medicine.
文摘2018 witnessed some unprecedently strict regulations on national media content production and distribution by the Chinese National Radio and Television Administration(NRTA).On its annual recommended lists of excellent national TV series,there is a noticeable increase in historical series in line with core socialist values.Since late 2019,there has been a strict home-quarantine policy amid the COVID-19 pandemic.Accompanied by the newly introduced three-child birth policy in the context of the country’s low fertility rate and significant ageing,a re-emphasis on traditional Confucian ideologies incented by the Chinese authorities emerged:the primary identity of women being an understanding wife and loving mother.Furthermore,thus,a manifestation of such enforced patriarchal ideologies and cultural values is visible in the country’s strictly regulated media content.This study sets off from a corpus of national recommended TV lists to investigate the myth of women’s fates in amid-pandemic Chinese TV series that are appraised and supported by authorities to explore how their identities are constructed and potentially abused under patriarchal media production.
基金This paper is a phased achievement of the subject“Research on Inter-civilizational Exchanges in the Context of Building a human community with a shared future”(21CKS049),a project of the National Social Science Foundation of China。
文摘China,under the guidance of Xi Jinping Thought on Diplomacy,is making all-round efforts to pursue major-country diplomacy with Chinese characteristics and has achieved a series of historical achievements.Major-country diplomacy with Chinese characteristics significantly diverges from conventional Western major-country diplomacy.It is characterized by a vision that prioritizes national rejuvenation,aims to advance human civilizations,emphasizes the establishment of a new type of international relations,and strives for the building of a human community with a shared future.
基金International Chinese Language Teaching Practice Innovation Project,Center for Language Education and Cooperation,2022:“A Study of‘New Heights’in International Chinese Language Education with a Case Study of a Junior Chinese Language Class for Iranian College Teachers”(YHJXCX22-118)。
文摘This paper focuses on examining the relevant policies concerning Chinese language education within Iran’s foreign language education policy framework from the perspective of its historical context.By analyzing the characteristics of Iran’s foreign language policy and the current situation of Chinese language teaching in Iran,this paper studies the future development of international Chinese language education in Iran.
基金supported by the Inner Mongolia Natural Science Fund Project(2019MS06013)Ordos Science and Technology Plan Project(2022YY041)Hunan Enterprise Science and Technology Commissioner Program(2021GK5042).
文摘6G is envisioned as the next generation of wireless communication technology,promising unprecedented data speeds,ultra-low Latency,and ubiquitous Connectivity.In tandem with these advancements,blockchain technology is leveraged to enhance computer vision applications’security,trustworthiness,and transparency.With the widespread use of mobile devices equipped with cameras,the ability to capture and recognize Chinese characters in natural scenes has become increasingly important.Blockchain can facilitate privacy-preserving mechanisms in applications where privacy is paramount,such as facial recognition or personal healthcare monitoring.Users can control their visual data and grant or revoke access as needed.Recognizing Chinese characters from images can provide convenience in various aspects of people’s lives.However,traditional Chinese character text recognition methods often need higher accuracy,leading to recognition failures or incorrect character identification.In contrast,computer vision technologies have significantly improved image recognition accuracy.This paper proposed a Secure end-to-end recognition system(SE2ERS)for Chinese characters in natural scenes based on convolutional neural networks(CNN)using 6G technology.The proposed SE2ERS model uses the Weighted Hyperbolic Curve Cryptograph(WHCC)of the secure data transmission in the 6G network with the blockchain model.The data transmission within the computer vision system,with a 6G gradient directional histogram(GDH),is employed for character estimation.With the deployment of WHCC and GDH in the constructed SE2ERS model,secure communication is achieved for the data transmission with the 6G network.The proposed SE2ERS compares the performance of traditional Chinese text recognition methods and data transmission environment with 6G communication.Experimental results demonstrate that SE2ERS achieves an average recognition accuracy of 88%for simple Chinese characters,compared to 81.2%with traditional methods.For complex Chinese characters,the average recognition accuracy improves to 84.4%with our system,compared to 72.8%with traditional methods.Additionally,deploying the WHCC model improves data security with the increased data encryption rate complexity of∼12&higher than the traditional techniques.
基金financially supported by the Natural Science Foundation of Hebei Province-Innovation Group Research Project(Grant No.C2020204111)the National Natural Science Foundation of China(Grant No.31930098)+3 种基金the Science Fund for Distinguished Young Scholars of Hebei Province(Grant No.C2021204049)the Hebei Province Outstanding Youth Fund(Grant No.BJ2021024)the Hebei Provincial Key Research Projects(21326344D)Hebei International Joint Research Base of Modern Agricultural Biotechnology.
文摘Chinese cabbage(Brassica rapa ssp. pekinensis) has a long cultivation history and is one of the vegetable crops with the largest cultivation area in China. However, salt stress severely damages photosynthesis and hormone metabolism, nutritional balances, and results in ion toxicity in plants. To better understand the mechanisms of salt-induced growth inhibition in Chinese cabbage, RNA-seq and physiological index determination were conducted to explore the impacts of salt stress on carbon cycle metabolism and photosynthesis in Chinese cabbage. Here, we found that the number of thylakoids and grana lamellae and the content of starch granules and chlorophyll in the leaves of Chinese cabbage under salt stress showed a time-dependent response, first increasing and then decreasing. Chinese cabbage increased the transcript levels of genes related to the photosynthetic apparatus and carbon metabolism under salt stress, probably in an attempt to alleviate damage to the photosynthetic system and enhance CO_(2) fixation and energy metabolism. The transcription of genes related to starch and sucrose synthesis and degradation were also enhanced;this might have been an attempt to maintain intracellular osmotic pressure by increasing soluble sugar concentrations. Soluble sugars could also be used as potential reactive oxygen species(ROS) scavengers, in concert with peroxidase(POD)enzymes, to eliminate ROS that accumulate during metabolic processes. Our study characterizes the synergistic response network of carbon metabolism and photosynthesis under salt stress.
文摘This paper discusses the inheritance and application of Chinese character reverse contrast typeface style.It begins by analyzing the visual features of Western reverse contrast typeface styles,with a focus on Caslon Italian and French Clarendon,providing a Western perspective reference for subsequent Chinese character reverse contrast typeface style designs.The paper then traces the origins of the Chinese reverse contrast style,from the calligraphy style"Lacquer Script"to the earliest printing type"フワンテール形",exploring the historical background and cultural significance of the Chinese reverse contrast style.In the methodology section of Chinese character reverse contrast typeface style design,the discussion is conducted from two dimensions:inheritance and application.In terms of inheritance,through an in-depth analysis of"Lacquer Script"and"フワンテール形"typeface style,the paper summarizes three basic theories for modern Chinese character reverse contrast typeface style design.In the application section,it examines in detail the two most influential recent typeface styles,"Ribaasu"and"Basic Artistic",outlining three directions of application:extreme horizontal stroke variations,exaggerated contrast,and diverse decorative strokes,showcasing new directions and possibilities for Chinese character reverse contrast typeface style design.This paper not only reviews the developmental history of the Chinese character reverse contrast typeface style but also analyzes the design methodology of Chinese character reverse contrast typeface style through specific case studies.
基金National Natural Science Foundation of China(No.42171449)。
文摘Cities hold a critical responsibility for achieving the Sustainable Development Goals(SDGs)due to their high population density,extensive resource consumption,and significant economic contributions.To examine the present state of understandings regarding urban sustainability(SDG 11:Sustainable Cities and Communities)within Chinese research communities,this study collected 15950 papers from 1994 to 2022 on the 12 indicators of SDG 11,from the China National Knowledge Infrastructure(CNKI),a hub of Chinese academic papers,that directly relate to policymaking.Significant research topics on SDG 11 were identified for each indicator using bibliometrics analysis approaches.The high-frequency keywords and clusters of keywords over the last three decades reveal that existing studies primarily concentrated on the physical aspects,such as transportation and environment,while there is a lack of consideration of societal aspects.This indicates a limited and biased understanding of the urban sustainability within the Chinese academic community.Hence,it is crucial to prioritize the societal aspects in order to develop a research agenda that further advances urban sustainability.
文摘Handwritten character recognition is considered challenging compared with machine-printed characters due to the different human writing styles.Arabic is morphologically rich,and its characters have a high similarity.The Arabic language includes 28 characters.Each character has up to four shapes according to its location in the word(at the beginning,middle,end,and isolated).This paper proposed 12 CNN architectures for recognizing handwritten Arabic characters.The proposed architectures were derived from the popular CNN architectures,such as VGG,ResNet,and Inception,to make them applicable to recognizing character-size images.The experimental results on three well-known datasets showed that the proposed architectures significantly enhanced the recognition rate compared to the baseline models.The experiments showed that data augmentation improved the models’accuracies on all tested datasets.The proposed model outperformed most of the existing approaches.The best achieved results were 93.05%,98.30%,and 96.88%on the HIJJA,AHCD,and AIA9K datasets.
文摘Non-equilibrium solidification structures of Cu55Ni45 and Cu55Ni43Co2 alloys were prepared by the molten glass purification cycle superheating method.The variation of the recalescence phenomenon with the degree of undercooling in the rapid solidification process was investigated using an infrared thermometer.The addition of the Co element affected the evolution of the recalescence phenomenon in Cu-Ni alloys.The images of the solid-liquid interface migration during the rapid solidification of supercooled melts were captured by using a high-speed camera.The solidification rate of Cu-Ni alloys,with the addition of Co elements,was explored.Finally,the grain refinement structure with low supercooling was characterised using electron backscatter diffraction(EBSD).The effect of Co on the microstructural evolution during nonequilibrium solidification of Cu-Ni alloys under conditions of small supercooling is investigated by comparing the microstructures of Cu55Ni45 and Cu55Ni43Co2 alloys.The experimental results show that the addition of a small amount of Co weakens the recalescence behaviour of the Cu55Ni45 alloy and significantly reduces the thermal strain in the rapid solidification phase.In the rapid solidification phase,the thermal strain is greatly reduced,and there is a significant increase in the characteristic undercooling degree.Furthermore,the addition of Co and the reduction of Cu not only result in a lower solidification rate of the alloy,but also contribute to the homogenisation of the grain size.
文摘In order to reduce the waste of resources and environmental pollution caused by excessive application of chemical fertilizers, improve the utilization rate of fertilizers, and promote the large-scale and high-quality development of the Chinese rose industry. In this experiment, corn stover biochar, phosphoric acid modified biochar and organic fertilizer were used as test materials, and the effects of mixed application of modified biochar and organic fertilizer on the growth and development of Chinese rose as well as soil physicochemical properties were investigated by using the method of pot planting test. The results showed that modified biochar with organic fertilizer had the most significant effect on the enhancement of soil pH, organic matter content and soil carbon-to-nitrogen ratio. After 120 d of planting, modified biochar with organic fertilizer had the most significant effect on the enhancement of plant height and crown width of Chinese rose;both organic fertilizer and modified biochar with organic fertilizer significantly increased the chlorophyll content of Chinese rose. The number of flowers and the number of branches were the highest in the modified biochar with organic fertilizer treatment. In conclusion, the application of modified biochar with organic fertilizer can better improve the soil pH, and increase the soil organic matter content and carbon-to-nitrogen ratio to change the biological traits of Chinese rose. The results of this study provide a theoretical basis for the reduction of chemical fertilizers and the resource utilization of agricultural wastes and guarantee the sustainable development of the cut flower industry.
基金The work was supported by the National Natural Science Foundation of China(61972062,62306060)the Basic Research Project of Liaoning Province(2023JH2/101300191)+1 种基金the Liaoning Doctoral Research Start-Up Fund Project(2023-BS-078)the Dalian Academy of Social Sciences(2023dlsky028).
文摘Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detection and recognition.In the detection stage,an improved Differentiable Binarization Network(DBNet)framework is introduced to detect Yi characters,in which the Omni-dimensional Dynamic Convolution(ODConv)is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features,thereby improving the accuracy of Yi character detection.Then,the feature pyramid network fusion module is used to further extract Yi character image features,improving target recognition at different scales.Further,the previously generated feature map is passed through a head network to produce two maps:a probability map and an adaptive threshold map of the same size as the original map.These maps are then subjected to a differentiable binarization process,resulting in an approximate binarization map.This map helps to identify the boundaries of the text boxes.Finally,the text detection box is generated after the post-processing stage.In the recognition stage,an improved lightweight MobileNetV3 framework is used to recognize the detect character regions,where the original Squeeze-and-Excitation(SE)block is replaced by the efficient Shuffle Attention(SA)that integrates spatial and channel attention,improving the accuracy of Yi characters recognition.Meanwhile,the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model,so that the model can better understand the contextual information and improve the accuracy of text recognition.The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters,with detection and recognition accuracy rates of 97.5%and 96.8%,respectively.And also,we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms.In these comparisons,the proposed model achieves better detection and recognition results with a certain reliability.
基金supported by the National Key Research and Development Program(Nos.2021YFF0901705,2021YFF0901700)the State Key Laboratory of Media Convergence and Communication,Communication University of China+1 种基金the Fundamental Research Funds for the Central Universitiesthe High-Quality and Cutting-Edge Disciplines Construction Project for Universities in Beijing(Internet Information,Communication University of China).
文摘Aspect-Based Sentiment Analysis(ABSA)is a fundamental area of research in Natural Language Processing(NLP).Within ABSA,Aspect Sentiment Quad Prediction(ASQP)aims to accurately identify sentiment quadruplets in target sentences,including aspect terms,aspect categories,corresponding opinion terms,and sentiment polarity.However,most existing research has focused on English datasets.Consequently,while ASQP has seen significant progress in English,the Chinese ASQP task has remained relatively stagnant.Drawing inspiration from methods applied to English ASQP,we propose Chinese generation templates and employ prompt-based instruction learning to enhance the model’s understanding of the task,ultimately improving ASQP performance in the Chinese context.Ultimately,under the same pre-training model configuration,our approach achieved a 5.79%improvement in the F1 score compared to the previously leading method.Furthermore,when utilizing a larger model with reduced training parameters,the F1 score demonstrated an 8.14%enhancement.Additionally,we suggest a novel evaluation metric based on the characteristics of generative models,better-reflecting model generalization.Experimental results validate the effectiveness of our approach.