Analyzed the main problems which were found in current conditions and prob- lems of informationization in coal enterprises.It clarified how to achieve informationization in coal mine and put forward a general configur...Analyzed the main problems which were found in current conditions and prob- lems of informationization in coal enterprises.It clarified how to achieve informationization in coal mine and put forward a general configuration of informationization construction in which informationization in coal enterprises was divided into two parts: informationization of safety production and informationization of management.Planned a platform of inte- grated management of informationization in coal enterprises.Ultimately,it has brought forward that an overall integrated digital mine is the way to achieve the goal of informa- tionization in coal enterprises,which can promote the application of automation,digitaliza- tion,networking,informaitionization to intellectualization.At the same time,the competi- tiveness of enterprises can be improved entirely,and new type of coal industry can be supported by information technology.展开更多
This paper explains the basic concepts of " Internet + " and big data,analyzes the main problems in the application of big data technology in agricultural informationization of Shandong Province,summarizes c...This paper explains the basic concepts of " Internet + " and big data,analyzes the main problems in the application of big data technology in agricultural informationization of Shandong Province,summarizes corresponding solutions from the aspects of government guidance,financial input,open sharing of agricultural big data,big data storage and processing,data mining,etc.,and prospects the application trend of big data technology in agricultural informationization to achieve the connotative development of agriculture in Shandong Province.展开更多
The informationization of accounting information systems has brought many improvements to those systems. This paper highlights some of those significant advances in the informationization of accounting information sys...The informationization of accounting information systems has brought many improvements to those systems. This paper highlights some of those significant advances in the informationization of accounting information systems in China. As China has become a major industrial power in the international economy, further improvements for these information systems are critical to the continued successes of China. To additionally improve these systems, China can draw upon the systems from other world economic leaders. With its fully developed capital markets, the United States offers development experience for the external reporting components of a fully integrated information system. This paper discusses a typical integrated information system in the United States and addresses the regulatory milestones that were instrumental in the development of those external components of accounting information systems. Recommendations are presented for improving informationization of systems in China based on U.S. systems＇ responses to those milestones.展开更多
In China, household registration system has the problems of unreasonable standard setting and relevant supporting measures failure to keep pace with the development trend. From analysis of current problems and situati...In China, household registration system has the problems of unreasonable standard setting and relevant supporting measures failure to keep pace with the development trend. From analysis of current problems and situations, it is believed that household registration system should undertake reform and take a new road by means of informationization. Strengthening informationization management in land, population, education and labor market can better perform urban and rural integration.展开更多
The purpose of rural informationization is to provide effective information for farmers,increase production efficiency and income level of farmers in agricultural production.In recent years,under the guidance of No.1 ...The purpose of rural informationization is to provide effective information for farmers,increase production efficiency and income level of farmers in agricultural production.In recent years,under the guidance of No.1 document of central government,China's rural informationization has obtained considerable development.However,due to influence of terrain,mountain areas are still backward in informationization development.Combining actual conditions of Pingshan County of Hebei Province,the authors visited local farmers and made detailed survey on basic conditions of farmers,and analyzed factors obstructing agricultural informationization development in mountain areas,to provide theoretical reference for promoting informationization development in mountain areas and increasing income of local farmers.展开更多
Agricultural informationization is the objective demand for transforming the traditional agriculture and promoting the development of agricultural modernization. Using the statistical data of the gross agricultural ou...Agricultural informationization is the objective demand for transforming the traditional agriculture and promoting the development of agricultural modernization. Using the statistical data of the gross agricultural output value of Hubei Province in 2005-2014,based on the C-D production function,it calculated the average contribution rate(2. 48%) of agricultural informationization to the growth of agricultural economy in Hubei Province,indicating that agricultural informationization can promote growth of agricultural economy. This is basically consistent with previous findings. In addition,investment in agricultural informationization and broadband access rate also influenced the growth of agricultural economy in Hubei Province. Therefore,government should further improve the infrastructure of agricultural informationization,strengthen training of farmers’ information skills,establish auxiliary mechanism for achievement feedback of information-based agricultural production,increase the contribution rate of informationization to agricultural operation and management,promote the contribution of informationization to the growth of agricultural economy,so as to increase agricultural income of farmers.展开更多
Based on the current situation of rural educational informationization, my study found that the boost of rural elementary and secondary school’s educational informationization needed the cooperation of higher normal ...Based on the current situation of rural educational informationization, my study found that the boost of rural elementary and secondary school’s educational informationization needed the cooperation of higher normal universities and local education administrative department. The construction of “IT education community” is the key to step off the predicament. The practice application and effect in Gaoping City further proved that the cooperation project broke the bottleneck of rural elementary and secondary school’s educational informationization.展开更多
With the constant development of China's economy,rural financial management information gradually plays a major role in China's economic development. This paper mainly studied related management information of...With the constant development of China's economy,rural financial management information gradually plays a major role in China's economic development. This paper mainly studied related management information of accounting information system and main characteristics of rural management. On the basis of analysis,it came up with pertinent recommendations,including improving software for financial informationization,improving the quality of rural financial personnel,strengthening government support for rural financial management informationization,and enhancing popularization of accounting computerized software.展开更多
The enterprise informationization （El） project has already become modernization level and synthesis power of the enterprise. However, information project risk. In order to reduce the El project risk, it is necessary...The enterprise informationization （El） project has already become modernization level and synthesis power of the enterprise. However, information project risk. In order to reduce the El project risk, it is necessary to adopt reasonable incentive and constraint effectively and to structure perfect market environment. an urgent work to raise the asymmetry increases the EI investment mode, to carry on incentive and constraint effectively and to structure perfect market environment.展开更多
Enterprise Informationization （El） is encountering a large variety of non-systematic risks in demanding and planning, designing and selecting, implementing and controlling, managerial and cultural aspects,due to whi...Enterprise Informationization （El） is encountering a large variety of non-systematic risks in demanding and planning, designing and selecting, implementing and controlling, managerial and cultural aspects,due to which the investment in IT normally cannot simultaneously create the expected commercial values. Through analyzing the factors influencing non-systematic risks of EI, the paper established a risk evaluating index system and accordingly proposed a set of appropriate risk evaluating methodology, with which enterprise can well control informationization risks.展开更多
With the advent of 5G era,it has become an inevitable trend to drive educational modernization with educational informationization.The modern-day education uses science and technology as well as culture in cultivating...With the advent of 5G era,it has become an inevitable trend to drive educational modernization with educational informationization.The modern-day education uses science and technology as well as culture in cultivating independent learning as the ultimate goal.However,there are many drawbacks in the system and practical aspects of higher vocational education in which one of it is that the independent learning has been neglected in the learning process.This article analyzed the issues in the autonomous learning of the English language among higher vocational college students and discussed strategies to improve their autonomous learning ability based on informationization to promote bidirectional interaction between teachers and students,cultivate students'consciousness of lifelong learning,improve teachers5 technical skills,and perfect the development of a connotative system in higher vocational colleges.展开更多
2025年12月22日,上海交通大学医学院医学技术学院李文杰在人工智能与信息融合领域国际顶级期刊Information Fusion发表了一项研究成果“CX-Mind:a pioneering multimodal large language model for interleaved reasoning in chest X-ra...2025年12月22日,上海交通大学医学院医学技术学院李文杰在人工智能与信息融合领域国际顶级期刊Information Fusion发表了一项研究成果“CX-Mind:a pioneering multimodal large language model for interleaved reasoning in chest X-ray via curriculum-guided reinforcement learning”。展开更多
The Chinese Journal of Chemical Engineering is the official journal of The Chemical Industry and Engineering Society of China and published by the Chemical Industry Press Co.,Ltd.The aim of the journal is to develop t...The Chinese Journal of Chemical Engineering is the official journal of The Chemical Industry and Engineering Society of China and published by the Chemical Industry Press Co.,Ltd.The aim of the journal is to develop the international exchange of scientific and technical information in the field of chemical engineering.Submission of Papers All papers will be submitted on line.展开更多
Journal Customer services For ordering information,claims and any enquiry concerning your journal subscription please go to contact your nearest office.America:Tel:(401)515-4764 Europe,Middle East,Africa and Asia Paci...Journal Customer services For ordering information,claims and any enquiry concerning your journal subscription please go to contact your nearest office.America:Tel:(401)515-4764 Europe,Middle East,Africa and Asia Pacific:Email:asiaar@163.com;523404392@qq.com;434421224@qq.com Tel:+86-551-65148112 Annual subscription rate(12 issues):US$300.展开更多
Aims ENGINEERING Information Technology&Electronic Engineering(EITEE),formerly known as Frontiers of Information Technology&Electronic Engineering(2015-2025)and Journal of Zhejiang University SCIENCE C(Compute...Aims ENGINEERING Information Technology&Electronic Engineering(EITEE),formerly known as Frontiers of Information Technology&Electronic Engineering(2015-2025)and Journal of Zhejiang University SCIENCE C(Computers&Electronics)(2010-2014),is a peer-reviewed scientific journal launched by the Chinese Academy of Engineering and Zhejiang University that aims to present the latest developments and achievements in information technology and electronic engineering to stimulate and promote academic exchanges between Chinese and foreign scientists.展开更多
Generative steganography uses generative stego images to transmit secret message.It also effectively defends against statistical steganalysis.However,most existing methods focus primarily on matching the feature distr...Generative steganography uses generative stego images to transmit secret message.It also effectively defends against statistical steganalysis.However,most existing methods focus primarily on matching the feature distribution of training data,often neglecting the sequential continuity between moves in the game.This oversight can result in unnatural patterns that deviate from real user behavior,thereby reducing the security of the hidden communication.To address this issue,we design a Gomoku agent based on the AlphaZero algorithm.The model engages in self-play to generate a sequence of plausible moves.These moves formthe basis of the stego images.We then apply an attractionmatrix at each step.It guides themove selection so that themoves appearmore natural.Thismethod helps maintain logical flow between moves.It also extends the game length,which increases the embedding capacity.Next,we filter and prioritize the generated moves.The selected moves are embedded into a move pool.Secret message is mapped to thesemoves.It is then embedded step by step as the game progresses.The finalmove sequence constitutes a complete steganographic game record.The receiver can extract the secret message using this record and a predefined mapping rule.Experiments show that our method reaches a maximum embedding capacity of 223 bits per carrier.Detection accuracy is 0.500 under XuNet and 0.498 under YeNet.These results are equal to random guessing,showing strong imperceptibility.The proposed method demonstrates superior concealment,higher embedding capacity,and greater robustness against common image distortions and steganalysis attacks.展开更多
Traffic sign detection is a critical component of driving systems.Single-stage network-based traffic sign detection algorithms,renowned for their fast detection speeds and high accuracy,have become the dominant approa...Traffic sign detection is a critical component of driving systems.Single-stage network-based traffic sign detection algorithms,renowned for their fast detection speeds and high accuracy,have become the dominant approach in current practices.However,in complex and dynamic traffic scenes,particularly with smaller traffic sign objects,challenges such as missed and false detections can lead to reduced overall detection accuracy.To address this issue,this paper proposes a detection algorithm that integrates edge and shape information.Recognizing that traffic signs have specific shapes and distinct edge contours,this paper introduces an edge feature extraction branch within the backbone network,enabling adaptive fusion with features of the same hierarchical level.Additionally,a shape prior convolution module is designed to replaces the first two convolutional modules of the backbone network,aimed at enhancing the model's perception ability for specific shape objects and reducing its sensitivity to background noise.The algorithm was evaluated on the CCTSDB and TT100k datasets,and compared to YOLOv8s,the mAP50 values increased by 3.0%and 10.4%,respectively,demonstrating the effectiveness of the proposed method in improving the accuracy of traffic sign detection.展开更多
Quantitative analysis of aluminum-silicon(Al-Si)alloy microstructure is crucial for evaluating and controlling alloy performance.Conventional analysis methods rely on manual segmentation,which is inefficient and subje...Quantitative analysis of aluminum-silicon(Al-Si)alloy microstructure is crucial for evaluating and controlling alloy performance.Conventional analysis methods rely on manual segmentation,which is inefficient and subjective,while fully supervised deep learning approaches require extensive and expensive pixel-level annotated data.Furthermore,existing semi-supervised methods still face challenges in handling the adhesion of adjacent primary silicon particles and effectively utilizing consistency in unlabeled data.To address these issues,this paper proposes a novel semi-supervised framework for Al-Si alloy microstructure image segmentation.First,we introduce a Rotational Uncertainty Correction Strategy(RUCS).This strategy employs multi-angle rotational perturbations andMonte Carlo sampling to assess prediction consistency,generating a pixel-wise confidence weight map.By integrating this map into the loss function,the model dynamically focuses on high-confidence regions,thereby improving generalization ability while reducing manual annotation pressure.Second,we design a Boundary EnhancementModule(BEM)to strengthen boundary feature extraction through erosion difference and multi-scale dilated convolutions.This module guides the model to focus on the boundary regions of adjacent particles,effectively resolving particle adhesion and improving segmentation accuracy.Systematic experiments were conducted on the Aluminum-Silicon Alloy Microstructure Dataset(ASAD).Results indicate that the proposed method performs exceptionally well with scarce labeled data.Specifically,using only 5%labeled data,our method improves the Jaccard index and Adjusted Rand Index(ARI)by 2.84 and 1.57 percentage points,respectively,and reduces the Variation of Information(VI)by 8.65 compared to stateof-the-art semi-supervised models,approaching the performance levels of 10%labeled data.These results demonstrate that the proposed method significantly enhances the accuracy and robustness of quantitative microstructure analysis while reducing annotation costs.展开更多
Although Named Entity Recognition(NER)in cybersecurity has historically concentrated on threat intelligence,vital security data can be found in a variety of sources,such as open-source intelligence and unprocessed too...Although Named Entity Recognition(NER)in cybersecurity has historically concentrated on threat intelligence,vital security data can be found in a variety of sources,such as open-source intelligence and unprocessed tool outputs.When dealing with technical language,the coexistence of structured and unstructured data poses serious issues for traditional BERT-based techniques.We introduce a three-phase approach for improved NER inmulti-source cybersecurity data that makes use of large language models(LLMs).To ensure thorough entity coverage,our method starts with an identification module that uses dynamic prompting techniques.To lessen hallucinations,the extraction module uses confidence-based self-assessment and cross-checking using regex validation.The tagging module links to knowledge bases for contextual validation and uses SecureBERT in conjunction with conditional random fields to detect entity boundaries precisely.Our framework creates efficient natural language segments by utilizing decoderbased LLMs with 10B parameters.When compared to baseline SecureBERT implementations,evaluation across four cybersecurity data sources shows notable gains,with a 9.4%–25.21%greater recall and a 6.38%–17.3%better F1-score.Our refined model matches larger models and achieves 2.6%–4.9%better F1-score for technical phrase recognition than the state-of-the-art alternatives Claude 3.5 Sonnet,Llama3-8B,and Mixtral-7B.The three-stage architecture identification-extraction-tagging pipeline tackles important cybersecurity NER issues.Through effective architectures,these developments preserve deployability while setting a new standard for entity extraction in challenging security scenarios.The findings show how specific enhancements in hybrid recognition,validation procedures,and prompt engineering raise NER performance above monolithic LLM approaches in cybersecurity applications,especially for technical entity extraction fromheterogeneous sourceswhere conventional techniques fall short.Because of itsmodular nature,the framework can be upgraded at the component level as new methods are developed.展开更多
基金the Hi-Tech and Research Development Program of China(2005AA133070)the Electronics Information Industry Development Fund Tender Project(XDJ2-0514-27)
文摘Analyzed the main problems which were found in current conditions and prob- lems of informationization in coal enterprises.It clarified how to achieve informationization in coal mine and put forward a general configuration of informationization construction in which informationization in coal enterprises was divided into two parts: informationization of safety production and informationization of management.Planned a platform of inte- grated management of informationization in coal enterprises.Ultimately,it has brought forward that an overall integrated digital mine is the way to achieve the goal of informa- tionization in coal enterprises,which can promote the application of automation,digitaliza- tion,networking,informaitionization to intellectualization.At the same time,the competi- tiveness of enterprises can be improved entirely,and new type of coal industry can be supported by information technology.
基金Supported by Science Research Foundation of Binzhou University(BZXYG1712,BZXYG1714)Teaching and Research Project(BZXYSYXM201606,BZXYWTXM201621)Soft Science Research Project of Shandong Province(2018RKB01136)
文摘This paper explains the basic concepts of " Internet + " and big data,analyzes the main problems in the application of big data technology in agricultural informationization of Shandong Province,summarizes corresponding solutions from the aspects of government guidance,financial input,open sharing of agricultural big data,big data storage and processing,data mining,etc.,and prospects the application trend of big data technology in agricultural informationization to achieve the connotative development of agriculture in Shandong Province.
文摘The informationization of accounting information systems has brought many improvements to those systems. This paper highlights some of those significant advances in the informationization of accounting information systems in China. As China has become a major industrial power in the international economy, further improvements for these information systems are critical to the continued successes of China. To additionally improve these systems, China can draw upon the systems from other world economic leaders. With its fully developed capital markets, the United States offers development experience for the external reporting components of a fully integrated information system. This paper discusses a typical integrated information system in the United States and addresses the regulatory milestones that were instrumental in the development of those external components of accounting information systems. Recommendations are presented for improving informationization of systems in China based on U.S. systems＇ responses to those milestones.
基金Supported by Key Project of National Soft Science Research Plan (Grant No.:2011GXS1D003 )Key Project of Soft Science Research Plan of Chongqing Municipality (Grant No.:cstc2011cx-rkxB00008)
文摘In China, household registration system has the problems of unreasonable standard setting and relevant supporting measures failure to keep pace with the development trend. From analysis of current problems and situations, it is believed that household registration system should undertake reform and take a new road by means of informationization. Strengthening informationization management in land, population, education and labor market can better perform urban and rural integration.
文摘The purpose of rural informationization is to provide effective information for farmers,increase production efficiency and income level of farmers in agricultural production.In recent years,under the guidance of No.1 document of central government,China's rural informationization has obtained considerable development.However,due to influence of terrain,mountain areas are still backward in informationization development.Combining actual conditions of Pingshan County of Hebei Province,the authors visited local farmers and made detailed survey on basic conditions of farmers,and analyzed factors obstructing agricultural informationization development in mountain areas,to provide theoretical reference for promoting informationization development in mountain areas and increasing income of local farmers.
基金Supported by Soft Science Project of Wuhan City in Hubei Province(201604-0306010178)
文摘Agricultural informationization is the objective demand for transforming the traditional agriculture and promoting the development of agricultural modernization. Using the statistical data of the gross agricultural output value of Hubei Province in 2005-2014,based on the C-D production function,it calculated the average contribution rate(2. 48%) of agricultural informationization to the growth of agricultural economy in Hubei Province,indicating that agricultural informationization can promote growth of agricultural economy. This is basically consistent with previous findings. In addition,investment in agricultural informationization and broadband access rate also influenced the growth of agricultural economy in Hubei Province. Therefore,government should further improve the infrastructure of agricultural informationization,strengthen training of farmers’ information skills,establish auxiliary mechanism for achievement feedback of information-based agricultural production,increase the contribution rate of informationization to agricultural operation and management,promote the contribution of informationization to the growth of agricultural economy,so as to increase agricultural income of farmers.
文摘Based on the current situation of rural educational informationization, my study found that the boost of rural elementary and secondary school’s educational informationization needed the cooperation of higher normal universities and local education administrative department. The construction of “IT education community” is the key to step off the predicament. The practice application and effect in Gaoping City further proved that the cooperation project broke the bottleneck of rural elementary and secondary school’s educational informationization.
基金Supported by Student Innovation Project of University of Science and Technology Liaoning in 2016
文摘With the constant development of China's economy,rural financial management information gradually plays a major role in China's economic development. This paper mainly studied related management information of accounting information system and main characteristics of rural management. On the basis of analysis,it came up with pertinent recommendations,including improving software for financial informationization,improving the quality of rural financial personnel,strengthening government support for rural financial management informationization,and enhancing popularization of accounting computerized software.
文摘The enterprise informationization （El） project has already become modernization level and synthesis power of the enterprise. However, information project risk. In order to reduce the El project risk, it is necessary to adopt reasonable incentive and constraint effectively and to structure perfect market environment. an urgent work to raise the asymmetry increases the EI investment mode, to carry on incentive and constraint effectively and to structure perfect market environment.
基金Supported by National Natural Science Foundation of China （NSFC） （70302006）
文摘Enterprise Informationization （El） is encountering a large variety of non-systematic risks in demanding and planning, designing and selecting, implementing and controlling, managerial and cultural aspects,due to which the investment in IT normally cannot simultaneously create the expected commercial values. Through analyzing the factors influencing non-systematic risks of EI, the paper established a risk evaluating index system and accordingly proposed a set of appropriate risk evaluating methodology, with which enterprise can well control informationization risks.
基金Supported by Guangdong University Innovation Young Talents Project,''Research on the Cultivation of English Autonomous Learning Ability in Higher Vocational Colleges Based on SPOC55(Project number:2020WQNCX240)Achievements of the visiting period of Guangdong University of Foreign Studies.
文摘With the advent of 5G era,it has become an inevitable trend to drive educational modernization with educational informationization.The modern-day education uses science and technology as well as culture in cultivating independent learning as the ultimate goal.However,there are many drawbacks in the system and practical aspects of higher vocational education in which one of it is that the independent learning has been neglected in the learning process.This article analyzed the issues in the autonomous learning of the English language among higher vocational college students and discussed strategies to improve their autonomous learning ability based on informationization to promote bidirectional interaction between teachers and students,cultivate students'consciousness of lifelong learning,improve teachers5 technical skills,and perfect the development of a connotative system in higher vocational colleges.
文摘2025年12月22日,上海交通大学医学院医学技术学院李文杰在人工智能与信息融合领域国际顶级期刊Information Fusion发表了一项研究成果“CX-Mind:a pioneering multimodal large language model for interleaved reasoning in chest X-ray via curriculum-guided reinforcement learning”。
文摘The Chinese Journal of Chemical Engineering is the official journal of The Chemical Industry and Engineering Society of China and published by the Chemical Industry Press Co.,Ltd.The aim of the journal is to develop the international exchange of scientific and technical information in the field of chemical engineering.Submission of Papers All papers will be submitted on line.
文摘Journal Customer services For ordering information,claims and any enquiry concerning your journal subscription please go to contact your nearest office.America:Tel:(401)515-4764 Europe,Middle East,Africa and Asia Pacific:Email:asiaar@163.com;523404392@qq.com;434421224@qq.com Tel:+86-551-65148112 Annual subscription rate(12 issues):US$300.
文摘Aims ENGINEERING Information Technology&Electronic Engineering(EITEE),formerly known as Frontiers of Information Technology&Electronic Engineering(2015-2025)and Journal of Zhejiang University SCIENCE C(Computers&Electronics)(2010-2014),is a peer-reviewed scientific journal launched by the Chinese Academy of Engineering and Zhejiang University that aims to present the latest developments and achievements in information technology and electronic engineering to stimulate and promote academic exchanges between Chinese and foreign scientists.
基金funded by theWuxi“Taihu Light”Science and Technology Key Project(Basic Research)(K20241046)the National Natural Science Foundation of China(Grant Nos.62102189,62122032,42305158)+1 种基金the Open Project of the National Engineering Research Center for Sensor Networks(2024YJZXKFKT02)Wuxi University Research Start-up Fund for High-Level Talents(No.2022r043).
文摘Generative steganography uses generative stego images to transmit secret message.It also effectively defends against statistical steganalysis.However,most existing methods focus primarily on matching the feature distribution of training data,often neglecting the sequential continuity between moves in the game.This oversight can result in unnatural patterns that deviate from real user behavior,thereby reducing the security of the hidden communication.To address this issue,we design a Gomoku agent based on the AlphaZero algorithm.The model engages in self-play to generate a sequence of plausible moves.These moves formthe basis of the stego images.We then apply an attractionmatrix at each step.It guides themove selection so that themoves appearmore natural.Thismethod helps maintain logical flow between moves.It also extends the game length,which increases the embedding capacity.Next,we filter and prioritize the generated moves.The selected moves are embedded into a move pool.Secret message is mapped to thesemoves.It is then embedded step by step as the game progresses.The finalmove sequence constitutes a complete steganographic game record.The receiver can extract the secret message using this record and a predefined mapping rule.Experiments show that our method reaches a maximum embedding capacity of 223 bits per carrier.Detection accuracy is 0.500 under XuNet and 0.498 under YeNet.These results are equal to random guessing,showing strong imperceptibility.The proposed method demonstrates superior concealment,higher embedding capacity,and greater robustness against common image distortions and steganalysis attacks.
基金supported by the National Natural Science Foundation of China(Grant Nos.62572057,62272049,U24A20331)Beijing Natural Science Foundation(Grant Nos.4232026,4242020)Academic Research Projects of Beijing Union University(Grant No.ZK10202404).
文摘Traffic sign detection is a critical component of driving systems.Single-stage network-based traffic sign detection algorithms,renowned for their fast detection speeds and high accuracy,have become the dominant approach in current practices.However,in complex and dynamic traffic scenes,particularly with smaller traffic sign objects,challenges such as missed and false detections can lead to reduced overall detection accuracy.To address this issue,this paper proposes a detection algorithm that integrates edge and shape information.Recognizing that traffic signs have specific shapes and distinct edge contours,this paper introduces an edge feature extraction branch within the backbone network,enabling adaptive fusion with features of the same hierarchical level.Additionally,a shape prior convolution module is designed to replaces the first two convolutional modules of the backbone network,aimed at enhancing the model's perception ability for specific shape objects and reducing its sensitivity to background noise.The algorithm was evaluated on the CCTSDB and TT100k datasets,and compared to YOLOv8s,the mAP50 values increased by 3.0%and 10.4%,respectively,demonstrating the effectiveness of the proposed method in improving the accuracy of traffic sign detection.
基金funded by the National Natural Science Foundation of China (52061020).
文摘Quantitative analysis of aluminum-silicon(Al-Si)alloy microstructure is crucial for evaluating and controlling alloy performance.Conventional analysis methods rely on manual segmentation,which is inefficient and subjective,while fully supervised deep learning approaches require extensive and expensive pixel-level annotated data.Furthermore,existing semi-supervised methods still face challenges in handling the adhesion of adjacent primary silicon particles and effectively utilizing consistency in unlabeled data.To address these issues,this paper proposes a novel semi-supervised framework for Al-Si alloy microstructure image segmentation.First,we introduce a Rotational Uncertainty Correction Strategy(RUCS).This strategy employs multi-angle rotational perturbations andMonte Carlo sampling to assess prediction consistency,generating a pixel-wise confidence weight map.By integrating this map into the loss function,the model dynamically focuses on high-confidence regions,thereby improving generalization ability while reducing manual annotation pressure.Second,we design a Boundary EnhancementModule(BEM)to strengthen boundary feature extraction through erosion difference and multi-scale dilated convolutions.This module guides the model to focus on the boundary regions of adjacent particles,effectively resolving particle adhesion and improving segmentation accuracy.Systematic experiments were conducted on the Aluminum-Silicon Alloy Microstructure Dataset(ASAD).Results indicate that the proposed method performs exceptionally well with scarce labeled data.Specifically,using only 5%labeled data,our method improves the Jaccard index and Adjusted Rand Index(ARI)by 2.84 and 1.57 percentage points,respectively,and reduces the Variation of Information(VI)by 8.65 compared to stateof-the-art semi-supervised models,approaching the performance levels of 10%labeled data.These results demonstrate that the proposed method significantly enhances the accuracy and robustness of quantitative microstructure analysis while reducing annotation costs.
文摘Although Named Entity Recognition(NER)in cybersecurity has historically concentrated on threat intelligence,vital security data can be found in a variety of sources,such as open-source intelligence and unprocessed tool outputs.When dealing with technical language,the coexistence of structured and unstructured data poses serious issues for traditional BERT-based techniques.We introduce a three-phase approach for improved NER inmulti-source cybersecurity data that makes use of large language models(LLMs).To ensure thorough entity coverage,our method starts with an identification module that uses dynamic prompting techniques.To lessen hallucinations,the extraction module uses confidence-based self-assessment and cross-checking using regex validation.The tagging module links to knowledge bases for contextual validation and uses SecureBERT in conjunction with conditional random fields to detect entity boundaries precisely.Our framework creates efficient natural language segments by utilizing decoderbased LLMs with 10B parameters.When compared to baseline SecureBERT implementations,evaluation across four cybersecurity data sources shows notable gains,with a 9.4%–25.21%greater recall and a 6.38%–17.3%better F1-score.Our refined model matches larger models and achieves 2.6%–4.9%better F1-score for technical phrase recognition than the state-of-the-art alternatives Claude 3.5 Sonnet,Llama3-8B,and Mixtral-7B.The three-stage architecture identification-extraction-tagging pipeline tackles important cybersecurity NER issues.Through effective architectures,these developments preserve deployability while setting a new standard for entity extraction in challenging security scenarios.The findings show how specific enhancements in hybrid recognition,validation procedures,and prompt engineering raise NER performance above monolithic LLM approaches in cybersecurity applications,especially for technical entity extraction fromheterogeneous sourceswhere conventional techniques fall short.Because of itsmodular nature,the framework can be upgraded at the component level as new methods are developed.
