In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shippi...In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.展开更多
In the process of building a new power system dominated by new energy sources,power storage is a key supporting technology that ensures the safe and stable operation of the power grid,enables the flexible regulation o...In the process of building a new power system dominated by new energy sources,power storage is a key supporting technology that ensures the safe and stable operation of the power grid,enables the flexible regulation of the system,and raises the level of new energy consumption.It is also key to achieving carbon peak and neutrality as well as energy transformation.展开更多
Due to the availability of a huge number of electronic text documents from a variety of sources representing unstructured and semi-structured information,the document classication task becomes an interesting area for ...Due to the availability of a huge number of electronic text documents from a variety of sources representing unstructured and semi-structured information,the document classication task becomes an interesting area for controlling data behavior.This paper presents a document classication multimodal for categorizing textual semi-structured and unstructured documents.The multimodal implements several individual deep learning models such as Deep Neural Networks(DNN),Recurrent Convolutional Neural Networks(RCNN)and Bidirectional-LSTM(Bi-LSTM).The Stacked Ensemble based meta-model technique is used to combine the results of the individual classiers to produce better results,compared to those reached by any of the above mentioned models individually.A series of textual preprocessing steps are executed to normalize the input corpus followed by text vectorization techniques.These techniques include using Term Frequency Inverse Term Frequency(TFIDF)or Continuous Bag of Word(CBOW)to convert text data into the corresponding suitable numeric form acceptable to be manipulated by deep learning models.Moreover,this proposed model is validated using a dataset collected from several spaces with a huge number of documents in every class.In addition,the experimental results prove that the proposed model has achieved effective performance.Besides,upon investigating the PDF Documents classication,the proposed model has achieved accuracy up to 0.9045 and 0.959 for the TFIDF and CBOW features,respectively.Moreover,concerning the JSON Documents classication,the proposed model has achieved accuracy up to 0.914 and 0.956 for the TFIDF and CBOW features,respectively.Furthermore,as for the XML Documents classication,the proposed model has achieved accuracy values up to 0.92 and 0.959 for the TFIDF and CBOW features,respectively.展开更多
With the widespread use of Chinese globally, the number of Chinese learners has been increasing, leading to various grammatical errors among beginners. Additionally, as domestic efforts to develop industrial informati...With the widespread use of Chinese globally, the number of Chinese learners has been increasing, leading to various grammatical errors among beginners. Additionally, as domestic efforts to develop industrial information grow, electronic documents have also proliferated. When dealing with numerous electronic documents and texts written by Chinese beginners, manually written texts often contain hidden grammatical errors, posing a significant challenge to traditional manual proofreading. Correcting these grammatical errors is crucial to ensure fluency and readability. However, certain special types of text grammar or logical errors can have a huge impact, and manually proofreading a large number of texts individually is clearly impractical. Consequently, research on text error correction techniques has garnered significant attention in recent years. The advent and advancement of deep learning have paved the way for sequence-to-sequence learning methods to be extensively applied to the task of text error correction. This paper presents a comprehensive analysis of Chinese text grammar error correction technology, elaborates on its current research status, discusses existing problems, proposes preliminary solutions, and conducts experiments using judicial documents as an example. The aim is to provide a feasible research approach for Chinese text error correction technology.展开更多
With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers ...With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers has become particularly urgent.Currently,detection methods based on document structure and behavioral features encounter challenges in feature engineering,these methods not only have limited accuracy,but also consume large resources,and usually can only detect documents in specific formats,which lacks versatility and adaptability.To address such problems,this paper proposes a novel malicious document detection method-visualizing documents as GGE images(Grayscale,Grayscale matrix,Entropy).The GGE method visualizes the original byte sequence of the malicious document as a grayscale image,the information entropy sequence of the document as an entropy image,and at the same time,the grayscale level co-occurrence matrix and the texture and spatial information stored in it are converted into grayscale matrix image,and fuses the three types of images to get the GGE color image.The Convolutional Block Attention Module-EfficientNet-B0(CBAM-EfficientNet-B0)model is then used for classification,combining transfer learning and applying the pre-trained model on the ImageNet dataset to the feature extraction process of GGE images.As shown in the experimental results,the GGE method has superior performance compared with other methods,which is suitable for detecting malicious documents in different formats,and achieves an accuracy of 99.44%and 97.39%on Portable Document Format(PDF)and office datasets,respectively,and consumes less time during the detection process,which can be effectively applied to the task of detecting malicious documents in real-time.展开更多
Objective: To investigate the content related to epidemic diseases in the silk documents unearthed from the Qin and Han Dynasties in China.Specifically, it aims to analyze the use of special excipients in the treatmen...Objective: To investigate the content related to epidemic diseases in the silk documents unearthed from the Qin and Han Dynasties in China.Specifically, it aims to analyze the use of special excipients in the treatment of these diseases.Methods: This study conducted extensive research and verification on the bamboo and silk documents. They systematically collected, sorted out, and studied the methods of treating epidemic diseases during the Qin and Han Dynasties. This involved analyzing the use of excipients as well as understanding the ancient doctors' aseptic awareness and recognition of medicinal properties.Results: The study revealed that ancient doctors in the Qin and Han Dynasties frequently used special excipients in the treatment of epidemic diseases. They demonstrated a certain level of aseptic awareness and could accurately identify the medicinal properties of these excipients.The treatment activities were carried out based on the etiology and pathology of the diseases.Conclusions: Collecting, sorting out, and studying the treatment methods of epidemic diseases in the Qin and Han Dynasties have certain reference value for the prevention and control of epidemic diseases in both traditional Chinese medicine(TCM) and modern clinical treatment.展开更多
This video series is the first experimental psychology documentary made in China.It focuses on analyzing professional theories to raise people’s general understanding of basic psychology.By combining innovative audio...This video series is the first experimental psychology documentary made in China.It focuses on analyzing professional theories to raise people’s general understanding of basic psychology.By combining innovative audiovisual narrative with psychological experiments,it zooms in on real human nature through discussing social hotspots from the perspectives of social psychology,cognitive psychology,and personality psychology,in order to help people find answers for their current psychological difficulties.展开更多
This critical review looks at the assessment of the application of artificial intelligence in handling legal documents with specific reference to medical negligence cases with a view of identifying its transformative ...This critical review looks at the assessment of the application of artificial intelligence in handling legal documents with specific reference to medical negligence cases with a view of identifying its transformative potentialities, issues and ethical concerns. The review consolidates findings that show the impact of AI in improving the efficiency, accuracy and justice delivery in the legal profession. The studies show increased efficiency in speed of document review and enhancement of the accuracy of the reviewed documents, with time efficiency estimates of 60% reduction of time. However, the review also outlines some of the problems that continue to characterize AI, such as data quality problems, biased algorithms and the problem of the opaque decision-making system. This paper assesses ethical issues related to patient autonomy, justice and non-malignant suffering, with particular focus on patient privacy and fair process, and on potential unfairness to patients. This paper’s review of AI innovations finds that regulations lag behind AI developments, leading to unsettled issues regarding legal responsibility for AI and user control over AI-generated results and findings in legal proceedings. Some of the future avenues that are presented in the study are the future of XAI for legal purposes, utilizing federated learning for resolving privacy issues, and the need to foster adaptive regulation. Finally, the review advocates for Legal Subject Matter Experts to collaborate with legal informatics experts, ethicists, and policy makers to develop the best solutions to implement AI in medical negligence claims. It reasons that there is great potential for AI to have a deep impact on the practice of law but when done, it must do so in a way that respects justice and on the Rights of Individuals.展开更多
What Are You Up To Today?Chief Director:Wu Zijuan Length:12 Episodes Producer:bilibili Broadcasting Platform:bilibili Produced by China’s YouTube-like video sharing platform bilibili,the film is a series of short doc...What Are You Up To Today?Chief Director:Wu Zijuan Length:12 Episodes Producer:bilibili Broadcasting Platform:bilibili Produced by China’s YouTube-like video sharing platform bilibili,the film is a series of short documentaries presenting people's daily life in different jobs.It follows 12 individuals in their respective jobs and trades that keep society functioning.By focusing on their daily lives,the documentary films capture the hustle and bustle of the days that make up a hopeful life.展开更多
This paper highlights the critical role of medical device design and development documents within the quality system,including their compliance with regulatory standards,their function as a traceable record,their supp...This paper highlights the critical role of medical device design and development documents within the quality system,including their compliance with regulatory standards,their function as a traceable record,their support for all stages,and their use in risk and change management.It also covers document template creation,review record association,information management,adverse event traceability,and the reconciliation of differences in international declarations.展开更多
Most semi-structured data are of certain structure regularity. Having beenstored as structured data in relational database (RDB), they can be effectively managed by databasemanagement system (DBMS). Some semi-structur...Most semi-structured data are of certain structure regularity. Having beenstored as structured data in relational database (RDB), they can be effectively managed by databasemanagement system (DBMS). Some semi-structured data are difficult to transform due to theirirregular structures. We design an efficient algorithm and data structure for ensuring losslesstransformation. We bring forward an approach of schema extraction through data mining, in whichdifferent kinds of elements are transformed respectively and lossless mapping from semi-structureddata to structured data can be achieved.展开更多
Purpose:Detection of research fields or topics and understanding the dynamics help the scientific community in their decisions regarding the establishment of scientific fields.This also helps in having a better collab...Purpose:Detection of research fields or topics and understanding the dynamics help the scientific community in their decisions regarding the establishment of scientific fields.This also helps in having a better collaboration with governments and businesses.This study aims to investigate the development of research fields over time,translating it into a topic detection problem.Design/methodology/approach:To achieve the objectives,we propose a modified deep clustering method to detect research trends from the abstracts and titles of academic documents.Document embedding approaches are utilized to transform documents into vector-based representations.The proposed method is evaluated by comparing it with a combination of different embedding and clustering approaches and the classical topic modeling algorithms(i.e.LDA)against a benchmark dataset.A case study is also conducted exploring the evolution of Artificial Intelligence(AI)detecting the research topics or sub-fields in related AI publications.Findings:Evaluating the performance of the proposed method using clustering performance indicators reflects that our proposed method outperforms similar approaches against the benchmark dataset.Using the proposed method,we also show how the topics have evolved in the period of the recent 30 years,taking advantage of a keyword extraction method for cluster tagging and labeling,demonstrating the context of the topics.Research limitations:We noticed that it is not possible to generalize one solution for all downstream tasks.Hence,it is required to fine-tune or optimize the solutions for each task and even datasets.In addition,interpretation of cluster labels can be subjective and vary based on the readers’opinions.It is also very difficult to evaluate the labeling techniques,rendering the explanation of the clusters further limited.Practical implications:As demonstrated in the case study,we show that in a real-world example,how the proposed method would enable the researchers and reviewers of the academic research to detect,summarize,analyze,and visualize research topics from decades of academic documents.This helps the scientific community and all related organizations in fast and effective analysis of the fields,by establishing and explaining the topics.Originality/value:In this study,we introduce a modified and tuned deep embedding clustering coupled with Doc2Vec representations for topic extraction.We also use a concept extraction method as a labeling approach in this study.The effectiveness of the method has been evaluated in a case study of AI publications,where we analyze the AI topics during the past three decades.展开更多
The major problem of the most current approaches of information models lies in that individual words provide unreliable evidence about the content of the texts. When the document is short, e.g. only the abstract is av...The major problem of the most current approaches of information models lies in that individual words provide unreliable evidence about the content of the texts. When the document is short, e.g. only the abstract is available, the word-use variability problem will have substantial impact on the Information Retrieval （IR） performance. To solve the problem, a new technology to short document retrieval named Reference Document Model （RDM） is put forward in this letter. RDM gets the statistical semantic of the query/document by pseudo feedback both for the query and document from reference documents. The contributions of this model are three-fold： （1） Pseudo feedback both for the query and the document; （2） Building the query model and the document model from reference documents; （3） Flexible indexing units, which can be ally linguistic elements such as documents, paragraphs, sentences, n-grams, term or character. For short document retrieval, RDM achieves significant improvements over the classical probabilistic models on the task of ad hoc retrieval on Text REtrieval Conference （TREC） test sets. Results also show that the shorter the document, the better the RDM performance.展开更多
There exist a large number of composed documents in universities in the teaching process. Most of them are required to check the similarity for validation. A kind of similarity computation system is constructed for co...There exist a large number of composed documents in universities in the teaching process. Most of them are required to check the similarity for validation. A kind of similarity computation system is constructed for composed documents with images and text information. Firstly, each document is split and outputs two parts as images and text information. Then, these documents are compared by computing the similarities of images and text contents independently. Through Hadoop system, the text contents are easily and quickly separated. Experimental results show that the proposed system is efficient and practical.展开更多
This paper examines automatic recognition and extraction of tables from a large collection of het-erogeneous documents. The heterogeneous documents are initially pre-processed and converted to HTML codes, after which ...This paper examines automatic recognition and extraction of tables from a large collection of het-erogeneous documents. The heterogeneous documents are initially pre-processed and converted to HTML codes, after which an algorithm recognises the table portion of the documents. Hidden Markov Model (HMM) is then applied to the HTML code in order to extract the tables. The model was trained and tested with five hundred and twenty six self-generated tables (three hundred and twenty-one (321) tables for training and two hundred and five (205) tables for testing). Viterbi algorithm was implemented for the testing part. The system was evaluated in terms of accuracy, precision, recall and f-measure. The overall evaluation results show 88.8% accuracy, 96.8% precision, 91.7% recall and 88.8% F-measure revealing that the method is good at solving the problem of table extraction.展开更多
Deacidification and self-cleaning are important for the preservation of paper documents.In this study,nano-CaCO_(3) was used as a deacidification agent and stabilized by nanocellulose(CNC)and hydroxypropyl methylcellu...Deacidification and self-cleaning are important for the preservation of paper documents.In this study,nano-CaCO_(3) was used as a deacidification agent and stabilized by nanocellulose(CNC)and hydroxypropyl methylcellulose(HPMC)to form a uniform dispersion.Followed by polydimethylsiloxane(PDMS)treatment and chemical vapor deposition(CVD)of methyltrimethoxysilane(MTMS),a hydrophobic coating was constructed for self-cleaning purposes.The pH value of the treated paper was approximately 8.20,and the static contact angle was as high as 152.29°.Compared to the untreated paper,the tensile strength of the treated paper increased by 12.6%.This treatment method endows the paper with a good deacidification effect and self-cleaning property,which are beneficial for its long-term preservation.展开更多
The issue of document management has been raised for a long time, especially with the appearance of office automation in the 1980s, which led to dematerialization and Electronic Document Management (EDM). In the same ...The issue of document management has been raised for a long time, especially with the appearance of office automation in the 1980s, which led to dematerialization and Electronic Document Management (EDM). In the same period, workflow management has experienced significant development, but has become more focused on the industry. However, it seems to us that document workflows have not had the same interest for the scientific community. But nowadays, the emergence and supremacy of the Internet in electronic exchanges are leading to a massive dematerialization of documents;which requires a conceptual reconsideration of the organizational framework for the processing of said documents in both public and private administrations. This problem seems open to us and deserves the interest of the scientific community. Indeed, EDM has mainly focused on the storage (referencing) and circulation of documents (traceability). It paid little attention to the overall behavior of the system in processing documents. The purpose of our researches is to model document processing systems. In the previous works, we proposed a general model and its specialization in the case of small documents (any document processed by a single person at a time during its processing life cycle), which represent 70% of documents processed by administrations, according to our study. In this contribution, we extend the model for processing small documents to the case where they are managed in a system comprising document classes organized in subclasses;which is the case for most administrations. We have thus observed that this model is a Markovian <i>M<sup>L×K</sup>/M<sup>L×K</sup>/</i>1 queues network. We have analyzed the constraints of this model and deduced certain characteristics and metrics. <span style="white-space:normal;"><i></i></span><i>In fine<span style="white-space:normal;"></span></i>, the ultimate objective of our work is to design a document workflow management system, integrating a component of global behavior prediction.展开更多
While XML web services become recognized as a solution to business-to-business transactions, there are many problems that should be solved. For example, it is not easy to manipulate business documents of existing stan...While XML web services become recognized as a solution to business-to-business transactions, there are many problems that should be solved. For example, it is not easy to manipulate business documents of existing standards such as RosettaNet and UN/EDIFACT EDI, traditionally regarded as an important resource for managing B2B relationships. As a starting point for the complete implementation of B2B web services, this paper deals with how to support B2B business documents in XML web services. In the first phase, basic requirements for driving XML web services by business documents are introduced. As a solution, this paper presents how to express B2B business documents in WSDL, a core standard for XML web services. This kind of approach facilitates the reuse of existing business documents and enhances interoperability between implemented web services. Furthermore, it suggests how to link with other conceptual modeling frameworks such as ebXML/UMM, built on a rich heritage of electronic business experience.展开更多
The Internet of Medical Things(IoMT)will come to be of great importance in the mediation of medical disputes,as it is emerging as the core of intelligent medical treatment.First,IoMT can track the entire medical treat...The Internet of Medical Things(IoMT)will come to be of great importance in the mediation of medical disputes,as it is emerging as the core of intelligent medical treatment.First,IoMT can track the entire medical treatment process in order to provide detailed trace data in medical dispute resolution.Second,IoMT can infiltrate the ongoing treatment and provide timely intelligent decision support to medical staff.This information includes recommendation of similar historical cases,guidance for medical treatment,alerting of hired dispute profiteers etc.The multi-label classification of medical dispute documents(MDDs)plays an important role as a front-end process for intelligent decision support,especially in the recommendation of similar historical cases.However,MDDs usually appear as long texts containing a large amount of redundant information,and there is a serious distribution imbalance in the dataset,which directly leads to weaker classification performance.Accordingly,in this paper,a multi-label classification method based on key sentence extraction is proposed for MDDs.The method is divided into two parts.First,the attention-based hierarchical bi-directional long short-term memory(BiLSTM)model is used to extract key sentences from documents;second,random comprehensive sampling Bagging(RCS-Bagging),which is an ensemble multi-label classification model,is employed to classify MDDs based on key sentence sets.The use of this approach greatly improves the classification performance.Experiments show that the performance of the two models proposed in this paper is remarkably better than that of the baseline methods.展开更多
Engineers often need to look for the right pieces of information by sifting through long engineering documents, It is a very tiring and time-consuming job. To address this issue, researchers are increasingly devoting ...Engineers often need to look for the right pieces of information by sifting through long engineering documents, It is a very tiring and time-consuming job. To address this issue, researchers are increasingly devoting their attention to new ways to help information users, including engineers, to access and retrieve document content. The research reported in this paper explores how to use the key technologies of document decomposition （study of document structure）, document mark-up （with EXtensible Mark- up Language （XML）, HyperText Mark-up Language （HTML）, and Scalable Vector Graphics （SVG））, and a facetted classification mechanism. Document content extraction is implemented via computer programming （with Java）. An Engineering Document Content Management System （EDCMS） developed in this research demonstrates that as information providers we can make document content in a more accessible manner for information users including engineers.The main features of the EDCMS system are： 1） EDCMS is a system that enables users, especially engineers, to access and retrieve information at content rather than document level. In other words, it provides the right pieces of information that answer specific questions so that engineers don＇t need to waste time sifting through the whole document to obtain the required piece of information. 2） Users can use the EDCMS via both the data and metadata of a document to access engineering document content. 3） Users can use the EDCMS to access and retrieve content objects, i.e. text, images and graphics （including engineering drawings） via multiple views and at different granularities based on decomposition schemes. Experiments with the EDCMS have been conducted on semi-structured documents, a textbook of CADCAM, and a set of project posters in the Engineering Design domain. Experimental results show that the system provides information users with a powerful solution to access document content.展开更多
文摘In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.
文摘In the process of building a new power system dominated by new energy sources,power storage is a key supporting technology that ensures the safe and stable operation of the power grid,enables the flexible regulation of the system,and raises the level of new energy consumption.It is also key to achieving carbon peak and neutrality as well as energy transformation.
文摘Due to the availability of a huge number of electronic text documents from a variety of sources representing unstructured and semi-structured information,the document classication task becomes an interesting area for controlling data behavior.This paper presents a document classication multimodal for categorizing textual semi-structured and unstructured documents.The multimodal implements several individual deep learning models such as Deep Neural Networks(DNN),Recurrent Convolutional Neural Networks(RCNN)and Bidirectional-LSTM(Bi-LSTM).The Stacked Ensemble based meta-model technique is used to combine the results of the individual classiers to produce better results,compared to those reached by any of the above mentioned models individually.A series of textual preprocessing steps are executed to normalize the input corpus followed by text vectorization techniques.These techniques include using Term Frequency Inverse Term Frequency(TFIDF)or Continuous Bag of Word(CBOW)to convert text data into the corresponding suitable numeric form acceptable to be manipulated by deep learning models.Moreover,this proposed model is validated using a dataset collected from several spaces with a huge number of documents in every class.In addition,the experimental results prove that the proposed model has achieved effective performance.Besides,upon investigating the PDF Documents classication,the proposed model has achieved accuracy up to 0.9045 and 0.959 for the TFIDF and CBOW features,respectively.Moreover,concerning the JSON Documents classication,the proposed model has achieved accuracy up to 0.914 and 0.956 for the TFIDF and CBOW features,respectively.Furthermore,as for the XML Documents classication,the proposed model has achieved accuracy values up to 0.92 and 0.959 for the TFIDF and CBOW features,respectively.
文摘With the widespread use of Chinese globally, the number of Chinese learners has been increasing, leading to various grammatical errors among beginners. Additionally, as domestic efforts to develop industrial information grow, electronic documents have also proliferated. When dealing with numerous electronic documents and texts written by Chinese beginners, manually written texts often contain hidden grammatical errors, posing a significant challenge to traditional manual proofreading. Correcting these grammatical errors is crucial to ensure fluency and readability. However, certain special types of text grammar or logical errors can have a huge impact, and manually proofreading a large number of texts individually is clearly impractical. Consequently, research on text error correction techniques has garnered significant attention in recent years. The advent and advancement of deep learning have paved the way for sequence-to-sequence learning methods to be extensively applied to the task of text error correction. This paper presents a comprehensive analysis of Chinese text grammar error correction technology, elaborates on its current research status, discusses existing problems, proposes preliminary solutions, and conducts experiments using judicial documents as an example. The aim is to provide a feasible research approach for Chinese text error correction technology.
基金supported by the Natural Science Foundation of Henan Province(Grant No.242300420297)awarded to Yi Sun.
文摘With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers has become particularly urgent.Currently,detection methods based on document structure and behavioral features encounter challenges in feature engineering,these methods not only have limited accuracy,but also consume large resources,and usually can only detect documents in specific formats,which lacks versatility and adaptability.To address such problems,this paper proposes a novel malicious document detection method-visualizing documents as GGE images(Grayscale,Grayscale matrix,Entropy).The GGE method visualizes the original byte sequence of the malicious document as a grayscale image,the information entropy sequence of the document as an entropy image,and at the same time,the grayscale level co-occurrence matrix and the texture and spatial information stored in it are converted into grayscale matrix image,and fuses the three types of images to get the GGE color image.The Convolutional Block Attention Module-EfficientNet-B0(CBAM-EfficientNet-B0)model is then used for classification,combining transfer learning and applying the pre-trained model on the ImageNet dataset to the feature extraction process of GGE images.As shown in the experimental results,the GGE method has superior performance compared with other methods,which is suitable for detecting malicious documents in different formats,and achieves an accuracy of 99.44%and 97.39%on Portable Document Format(PDF)and office datasets,respectively,and consumes less time during the detection process,which can be effectively applied to the task of detecting malicious documents in real-time.
基金supported by Sichuan Province Social Science Key Research Base:China Unearthed Medical Literature and Cultural Relics Research Center (Extended)(CTWX 2305)。
文摘Objective: To investigate the content related to epidemic diseases in the silk documents unearthed from the Qin and Han Dynasties in China.Specifically, it aims to analyze the use of special excipients in the treatment of these diseases.Methods: This study conducted extensive research and verification on the bamboo and silk documents. They systematically collected, sorted out, and studied the methods of treating epidemic diseases during the Qin and Han Dynasties. This involved analyzing the use of excipients as well as understanding the ancient doctors' aseptic awareness and recognition of medicinal properties.Results: The study revealed that ancient doctors in the Qin and Han Dynasties frequently used special excipients in the treatment of epidemic diseases. They demonstrated a certain level of aseptic awareness and could accurately identify the medicinal properties of these excipients.The treatment activities were carried out based on the etiology and pathology of the diseases.Conclusions: Collecting, sorting out, and studying the treatment methods of epidemic diseases in the Qin and Han Dynasties have certain reference value for the prevention and control of epidemic diseases in both traditional Chinese medicine(TCM) and modern clinical treatment.
文摘This video series is the first experimental psychology documentary made in China.It focuses on analyzing professional theories to raise people’s general understanding of basic psychology.By combining innovative audiovisual narrative with psychological experiments,it zooms in on real human nature through discussing social hotspots from the perspectives of social psychology,cognitive psychology,and personality psychology,in order to help people find answers for their current psychological difficulties.
文摘This critical review looks at the assessment of the application of artificial intelligence in handling legal documents with specific reference to medical negligence cases with a view of identifying its transformative potentialities, issues and ethical concerns. The review consolidates findings that show the impact of AI in improving the efficiency, accuracy and justice delivery in the legal profession. The studies show increased efficiency in speed of document review and enhancement of the accuracy of the reviewed documents, with time efficiency estimates of 60% reduction of time. However, the review also outlines some of the problems that continue to characterize AI, such as data quality problems, biased algorithms and the problem of the opaque decision-making system. This paper assesses ethical issues related to patient autonomy, justice and non-malignant suffering, with particular focus on patient privacy and fair process, and on potential unfairness to patients. This paper’s review of AI innovations finds that regulations lag behind AI developments, leading to unsettled issues regarding legal responsibility for AI and user control over AI-generated results and findings in legal proceedings. Some of the future avenues that are presented in the study are the future of XAI for legal purposes, utilizing federated learning for resolving privacy issues, and the need to foster adaptive regulation. Finally, the review advocates for Legal Subject Matter Experts to collaborate with legal informatics experts, ethicists, and policy makers to develop the best solutions to implement AI in medical negligence claims. It reasons that there is great potential for AI to have a deep impact on the practice of law but when done, it must do so in a way that respects justice and on the Rights of Individuals.
文摘What Are You Up To Today?Chief Director:Wu Zijuan Length:12 Episodes Producer:bilibili Broadcasting Platform:bilibili Produced by China’s YouTube-like video sharing platform bilibili,the film is a series of short documentaries presenting people's daily life in different jobs.It follows 12 individuals in their respective jobs and trades that keep society functioning.By focusing on their daily lives,the documentary films capture the hustle and bustle of the days that make up a hopeful life.
文摘This paper highlights the critical role of medical device design and development documents within the quality system,including their compliance with regulatory standards,their function as a traceable record,their support for all stages,and their use in risk and change management.It also covers document template creation,review record association,information management,adverse event traceability,and the reconciliation of differences in international declarations.
文摘Most semi-structured data are of certain structure regularity. Having beenstored as structured data in relational database (RDB), they can be effectively managed by databasemanagement system (DBMS). Some semi-structured data are difficult to transform due to theirirregular structures. We design an efficient algorithm and data structure for ensuring losslesstransformation. We bring forward an approach of schema extraction through data mining, in whichdifferent kinds of elements are transformed respectively and lossless mapping from semi-structureddata to structured data can be achieved.
文摘Purpose:Detection of research fields or topics and understanding the dynamics help the scientific community in their decisions regarding the establishment of scientific fields.This also helps in having a better collaboration with governments and businesses.This study aims to investigate the development of research fields over time,translating it into a topic detection problem.Design/methodology/approach:To achieve the objectives,we propose a modified deep clustering method to detect research trends from the abstracts and titles of academic documents.Document embedding approaches are utilized to transform documents into vector-based representations.The proposed method is evaluated by comparing it with a combination of different embedding and clustering approaches and the classical topic modeling algorithms(i.e.LDA)against a benchmark dataset.A case study is also conducted exploring the evolution of Artificial Intelligence(AI)detecting the research topics or sub-fields in related AI publications.Findings:Evaluating the performance of the proposed method using clustering performance indicators reflects that our proposed method outperforms similar approaches against the benchmark dataset.Using the proposed method,we also show how the topics have evolved in the period of the recent 30 years,taking advantage of a keyword extraction method for cluster tagging and labeling,demonstrating the context of the topics.Research limitations:We noticed that it is not possible to generalize one solution for all downstream tasks.Hence,it is required to fine-tune or optimize the solutions for each task and even datasets.In addition,interpretation of cluster labels can be subjective and vary based on the readers’opinions.It is also very difficult to evaluate the labeling techniques,rendering the explanation of the clusters further limited.Practical implications:As demonstrated in the case study,we show that in a real-world example,how the proposed method would enable the researchers and reviewers of the academic research to detect,summarize,analyze,and visualize research topics from decades of academic documents.This helps the scientific community and all related organizations in fast and effective analysis of the fields,by establishing and explaining the topics.Originality/value:In this study,we introduce a modified and tuned deep embedding clustering coupled with Doc2Vec representations for topic extraction.We also use a concept extraction method as a labeling approach in this study.The effectiveness of the method has been evaluated in a case study of AI publications,where we analyze the AI topics during the past three decades.
基金Supported by the Funds of Heilongjiang Outstanding Young Teacher (1151G037).
文摘The major problem of the most current approaches of information models lies in that individual words provide unreliable evidence about the content of the texts. When the document is short, e.g. only the abstract is available, the word-use variability problem will have substantial impact on the Information Retrieval （IR） performance. To solve the problem, a new technology to short document retrieval named Reference Document Model （RDM） is put forward in this letter. RDM gets the statistical semantic of the query/document by pseudo feedback both for the query and document from reference documents. The contributions of this model are three-fold： （1） Pseudo feedback both for the query and the document; （2） Building the query model and the document model from reference documents; （3） Flexible indexing units, which can be ally linguistic elements such as documents, paragraphs, sentences, n-grams, term or character. For short document retrieval, RDM achieves significant improvements over the classical probabilistic models on the task of ad hoc retrieval on Text REtrieval Conference （TREC） test sets. Results also show that the shorter the document, the better the RDM performance.
文摘There exist a large number of composed documents in universities in the teaching process. Most of them are required to check the similarity for validation. A kind of similarity computation system is constructed for composed documents with images and text information. Firstly, each document is split and outputs two parts as images and text information. Then, these documents are compared by computing the similarities of images and text contents independently. Through Hadoop system, the text contents are easily and quickly separated. Experimental results show that the proposed system is efficient and practical.
文摘This paper examines automatic recognition and extraction of tables from a large collection of het-erogeneous documents. The heterogeneous documents are initially pre-processed and converted to HTML codes, after which an algorithm recognises the table portion of the documents. Hidden Markov Model (HMM) is then applied to the HTML code in order to extract the tables. The model was trained and tested with five hundred and twenty six self-generated tables (three hundred and twenty-one (321) tables for training and two hundred and five (205) tables for testing). Viterbi algorithm was implemented for the testing part. The system was evaluated in terms of accuracy, precision, recall and f-measure. The overall evaluation results show 88.8% accuracy, 96.8% precision, 91.7% recall and 88.8% F-measure revealing that the method is good at solving the problem of table extraction.
基金This work was supported by Science and Technology Plan Special Project of Guangzhou,China(No.GZDD201808)National Key Research Program for International Cooperation-MOST/STDF(2021YFE0104500).
文摘Deacidification and self-cleaning are important for the preservation of paper documents.In this study,nano-CaCO_(3) was used as a deacidification agent and stabilized by nanocellulose(CNC)and hydroxypropyl methylcellulose(HPMC)to form a uniform dispersion.Followed by polydimethylsiloxane(PDMS)treatment and chemical vapor deposition(CVD)of methyltrimethoxysilane(MTMS),a hydrophobic coating was constructed for self-cleaning purposes.The pH value of the treated paper was approximately 8.20,and the static contact angle was as high as 152.29°.Compared to the untreated paper,the tensile strength of the treated paper increased by 12.6%.This treatment method endows the paper with a good deacidification effect and self-cleaning property,which are beneficial for its long-term preservation.
文摘The issue of document management has been raised for a long time, especially with the appearance of office automation in the 1980s, which led to dematerialization and Electronic Document Management (EDM). In the same period, workflow management has experienced significant development, but has become more focused on the industry. However, it seems to us that document workflows have not had the same interest for the scientific community. But nowadays, the emergence and supremacy of the Internet in electronic exchanges are leading to a massive dematerialization of documents;which requires a conceptual reconsideration of the organizational framework for the processing of said documents in both public and private administrations. This problem seems open to us and deserves the interest of the scientific community. Indeed, EDM has mainly focused on the storage (referencing) and circulation of documents (traceability). It paid little attention to the overall behavior of the system in processing documents. The purpose of our researches is to model document processing systems. In the previous works, we proposed a general model and its specialization in the case of small documents (any document processed by a single person at a time during its processing life cycle), which represent 70% of documents processed by administrations, according to our study. In this contribution, we extend the model for processing small documents to the case where they are managed in a system comprising document classes organized in subclasses;which is the case for most administrations. We have thus observed that this model is a Markovian <i>M<sup>L×K</sup>/M<sup>L×K</sup>/</i>1 queues network. We have analyzed the constraints of this model and deduced certain characteristics and metrics. <span style="white-space:normal;"><i></i></span><i>In fine<span style="white-space:normal;"></span></i>, the ultimate objective of our work is to design a document workflow management system, integrating a component of global behavior prediction.
文摘While XML web services become recognized as a solution to business-to-business transactions, there are many problems that should be solved. For example, it is not easy to manipulate business documents of existing standards such as RosettaNet and UN/EDIFACT EDI, traditionally regarded as an important resource for managing B2B relationships. As a starting point for the complete implementation of B2B web services, this paper deals with how to support B2B business documents in XML web services. In the first phase, basic requirements for driving XML web services by business documents are introduced. As a solution, this paper presents how to express B2B business documents in WSDL, a core standard for XML web services. This kind of approach facilitates the reuse of existing business documents and enhances interoperability between implemented web services. Furthermore, it suggests how to link with other conceptual modeling frameworks such as ebXML/UMM, built on a rich heritage of electronic business experience.
基金supported by the National Key R&D Program of China(2018YFC0830200,Zhang,B,www.most.gov.cn)the Fundamental Research Funds for the Central Universities(2242018S30021 and 2242017S30023,Zhou S,www.seu.edu.cn)the Open Research Fund from Key Laboratory of Computer Network and Information Integration In Southeast University,Ministry of Education,China(3209012001C3,Zhang B,www.seu.edu.cn).
文摘The Internet of Medical Things(IoMT)will come to be of great importance in the mediation of medical disputes,as it is emerging as the core of intelligent medical treatment.First,IoMT can track the entire medical treatment process in order to provide detailed trace data in medical dispute resolution.Second,IoMT can infiltrate the ongoing treatment and provide timely intelligent decision support to medical staff.This information includes recommendation of similar historical cases,guidance for medical treatment,alerting of hired dispute profiteers etc.The multi-label classification of medical dispute documents(MDDs)plays an important role as a front-end process for intelligent decision support,especially in the recommendation of similar historical cases.However,MDDs usually appear as long texts containing a large amount of redundant information,and there is a serious distribution imbalance in the dataset,which directly leads to weaker classification performance.Accordingly,in this paper,a multi-label classification method based on key sentence extraction is proposed for MDDs.The method is divided into two parts.First,the attention-based hierarchical bi-directional long short-term memory(BiLSTM)model is used to extract key sentences from documents;second,random comprehensive sampling Bagging(RCS-Bagging),which is an ensemble multi-label classification model,is employed to classify MDDs based on key sentence sets.The use of this approach greatly improves the classification performance.Experiments show that the performance of the two models proposed in this paper is remarkably better than that of the baseline methods.
基金This work was supported by the UK Engineering and Physical Sciences Research Council(EPSRC)(No.GR/R67507/01).
文摘Engineers often need to look for the right pieces of information by sifting through long engineering documents, It is a very tiring and time-consuming job. To address this issue, researchers are increasingly devoting their attention to new ways to help information users, including engineers, to access and retrieve document content. The research reported in this paper explores how to use the key technologies of document decomposition （study of document structure）, document mark-up （with EXtensible Mark- up Language （XML）, HyperText Mark-up Language （HTML）, and Scalable Vector Graphics （SVG））, and a facetted classification mechanism. Document content extraction is implemented via computer programming （with Java）. An Engineering Document Content Management System （EDCMS） developed in this research demonstrates that as information providers we can make document content in a more accessible manner for information users including engineers.The main features of the EDCMS system are： 1） EDCMS is a system that enables users, especially engineers, to access and retrieve information at content rather than document level. In other words, it provides the right pieces of information that answer specific questions so that engineers don＇t need to waste time sifting through the whole document to obtain the required piece of information. 2） Users can use the EDCMS via both the data and metadata of a document to access engineering document content. 3） Users can use the EDCMS to access and retrieve content objects, i.e. text, images and graphics （including engineering drawings） via multiple views and at different granularities based on decomposition schemes. Experiments with the EDCMS have been conducted on semi-structured documents, a textbook of CADCAM, and a set of project posters in the Engineering Design domain. Experimental results show that the system provides information users with a powerful solution to access document content.
