The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among users.However,it has also heightened concerns about digital safety,particularly for children a...The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among users.However,it has also heightened concerns about digital safety,particularly for children and adolescents who are increasingly exposed to online grooming crimes.Early and accurate identification of grooming conversations is crucial in preventing long-term harm to victims.However,research on grooming detection in South Korea remains limited,as existing models trained primarily on English text and fail to reflect the unique linguistic features of SNS conversations,leading to inaccurate classifications.To address these issues,this study proposes a novel framework that integrates optical character recognition(OCR)technology with KcELECTRA,a deep learning-based natural language processing(NLP)model that shows excellent performance in processing the colloquial Korean language.In the proposed framework,the KcELECTRA model is fine-tuned by an extensive dataset,including Korean social media conversations,Korean ethical verification data from AI-Hub,and Korean hate speech data from Hug-gingFace,to enable more accurate classification of text extracted from social media conversation images.Experimental results show that the proposed framework achieves an accuracy of 0.953,outperforming existing transformer-based models.Furthermore,OCR technology shows high accuracy in extracting text from images,demonstrating that the proposed framework is effective for online grooming detection.The proposed framework is expected to contribute to the more accurate detection of grooming text and the prevention of grooming-related crimes.展开更多
Atomic surfaces are strictly required by high-performance devices of diamond.Nevertheless,diamond is the hardest material in nature,leading to the low material removal rate(MRR)and high surface roughness during machin...Atomic surfaces are strictly required by high-performance devices of diamond.Nevertheless,diamond is the hardest material in nature,leading to the low material removal rate(MRR)and high surface roughness during machining.Noxious slurries are widely used in conventional chemical mechanical polishing(CMP),resulting in the possible pollution to the environment.Moreover,the traditional slurries normally contain more than four ingredients,causing difficulties to control the process and quality of CMP.To solve these challenges,a novel green CMP for single crystal diamond was developed,consisting of only hydrogen peroxide,diamond abrasive and Prussian blue(PB)/titania catalyst.After CMP,atomic surface is achieved with surface roughness Sa of 0.079 nm,and the MRR is 1168 nm·h^(-1).Thickness of damaged layer is merely 0.66 nm confirmed by transmission electron microscopy(TEM).X-ray photoelectron spectroscopy,electron paramagnetic resonance and TEM reveal that·OH radicals form under ultraviolet irradiation on PB/titania catalyst.The·OH radicals oxidize diamond,transforming it from monocrystalline to amorphous atomic structure,generating a soft amorphous layer.This contributes the high MRR and formation of atomic surface on diamond.The developed novel green CMP offers new insights to achieve atomic surface of diamond for potential use in their high-performance devices.展开更多
The medical convergence industry has gradually adopted ICT devices,which has led to legacy security problems related to ICT devices.However,it has been difficult to solve these problems due to data resource issues.Suc...The medical convergence industry has gradually adopted ICT devices,which has led to legacy security problems related to ICT devices.However,it has been difficult to solve these problems due to data resource issues.Such problems can cause a lack of reliability in medical artificial intelligence services that utilize medical information.Therefore,to provide reliable services focused on security internalization,it is necessary to establish a medical convergence environment-oriented security management system.This study proposes the use of system identification and countermeasures to secure systemreliabilitywhen using medical convergence environment information in medical artificial intelligence.We checked the life cycle of medical information and the flow and location of information,analyzed the security threats that may arise during the life cycle,and proposed technical countermeasures to overcome such threats.We verified the proposed countermeasures through a survey of experts.Security requirements were defined based on the information life cycle in the medical convergence environment.We also designed technical countermeasures for use in the security management systems of hospitals of diverse sizes.展开更多
The penetration and use of social media services differs from city to city.This paper is aimed to provide a comparison of the use of Twitter between different cities of the world.We present a temporal analysis of acti...The penetration and use of social media services differs from city to city.This paper is aimed to provide a comparison of the use of Twitter between different cities of the world.We present a temporal analysis of activity on Twitter in 15 cities.Our study consists of two parts:First,we created temporal graphs of the activity in the 15 cities,through which hours of high and low activity could be identified.Second,we created heat map visualizations of the Twitter activities during the period of 19 September 2012–25 September 2013.The heat map visualizations make the periods of intense and sparse activity apparent and provide a snapshot of the activity during the whole year.展开更多
The spontaneous combustion is a smoldering process and characterized by a slow burning speed and a long duration. Therefore, it is a hazard to coal mines. Early detection of coal mine spontaneous combustion is quite d...The spontaneous combustion is a smoldering process and characterized by a slow burning speed and a long duration. Therefore, it is a hazard to coal mines. Early detection of coal mine spontaneous combustion is quite difficult because of the complexity of different coal mines. And the traditional threshold discriminance is not suitable for spontaneous combustion detection due to the uncertainty of coalmine combustion. Restrictions of the single detection method will also affect the detection precision in the early time of spontaneous combustion. Although multiple detection methods can be adopted as a complementarity to improve the accuracy of detection, the synthesized method will in- crease the complicacy of criterion, making it difficult to estimate the combustion. To solve this problem, a fuzzy inference system based on CRI （Compositional Rule of Inference） and fuzzy reasoning method FITA （First Infer Then Aggregate） are presented. And the neural network is also developed to realize the fuzzy inference system. Finally, the effectiveness of the inference system is demonstrated bv means of an experiment.展开更多
Cobalt(Co)is a silver-gray,high-intensity,widely distributed metal element that exists in cobalt compounds,and its common valences are bivalence(Co2+)and trivalence(Co3+)[1].The main routes of Co-exposure are occupati...Cobalt(Co)is a silver-gray,high-intensity,widely distributed metal element that exists in cobalt compounds,and its common valences are bivalence(Co2+)and trivalence(Co3+)[1].The main routes of Co-exposure are occupational and environmental exposures.The human body can be exposed to high concentrations of Co2+through inhalation of contaminated air,consumption of contaminated food and water,or ingestion of Co-containing supplements[2].展开更多
In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)da...In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)datasets?This study is crucial because it addresses the challenge of identifying rare and complex anomalous patterns in the vast amounts of time series data generated by Internet of Things(IoT)devices,which can significantly improve the reliability and safety of these systems.In this paper,we propose a hybrid autoencoder model,called ConvBiLSTMAE,which combines convolutional neural network(CNN)and bidirectional long short-term memory(BiLSTM)to more effectively train complex temporal data patterns in anomaly detection.On the hardware-in-the-loopbased extended industrial control system dataset,the ConvBiLSTM-AE model demonstrated remarkable anomaly detection performance,achieving F1 scores of 0.78 and 0.41 for the first and second datasets,respectively.The results suggest that hybrid autoencoder models are not only viable,but potentially superior alternatives for unsupervised anomaly detection in complex industrial systems,offering a promising approach to improving their reliability and safety.展开更多
Decentralized Finance(DeFi)is a system of financial products and services built and delivered through smart contracts on various blockchains.In recent years,DeFi has gained popularity and market capitalization.However...Decentralized Finance(DeFi)is a system of financial products and services built and delivered through smart contracts on various blockchains.In recent years,DeFi has gained popularity and market capitalization.However,it has also been connected to crime,particularly various types of securities violations.The lack of Know Your Customer requirements in DeFi poses challenges for governments trying to mitigate potential offenses.This study aims to determine whether this problem is suited to a machine learning approach,namely,whether we can identify DeFi projects potentially engaging in securities violations based on their tokens’smart contract code.We adapted prior works on detecting specific types of securities violations across Ethereum by building classifiers based on features extracted from DeFi projects’tokens’smart contract code(specifically,opcode-based features).Our final model was a random forest model that achieved an 80%F-1 score against a baseline of 50%.Notably,we further explored the code-based features that are the most important to our model’s performance in more detail by analyzing tokens’Solidity code and conducting cosine similarity analyses.We found that one element of the code that our opcode-based features can capture is the implementation of the SafeMath library,although this does not account for the entirety of our features.Another contribution of our study is a new dataset,comprising(a)a verified ground truth dataset for tokens involved in securities violations and(b)a set of legitimate tokens from a reputable DeFi aggregator.This paper further discusses the potential use of a model like ours by prosecutors in enforcement efforts and connects it to a wider legal context.展开更多
Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission.Recent research has focused on using semi-supervised learning mechani...Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission.Recent research has focused on using semi-supervised learning mechanisms to identify abnormal network traffic to deal with labeled and unlabeled data in the industry.However,real-time training and classifying network traffic pose challenges,as they can lead to the degradation of the overall dataset and difficulties preventing attacks.Additionally,existing semi-supervised learning research might need to analyze the experimental results comprehensively.This paper proposes XA-GANomaly,a novel technique for explainable adaptive semi-supervised learning using GANomaly,an image anomalous detection model that dynamically trains small subsets to these issues.First,this research introduces a deep neural network(DNN)-based GANomaly for semi-supervised learning.Second,this paper presents the proposed adaptive algorithm for the DNN-based GANomaly,which is validated with four subsets of the adaptive dataset.Finally,this study demonstrates a monitoring system that incorporates three explainable techniques—Shapley additive explanations,reconstruction error visualization,and t-distributed stochastic neighbor embedding—to respond effectively to attacks on traffic data at each feature engineering stage,semi-supervised learning,and adaptive learning.Compared to other single-class classification techniques,the proposed DNN-based GANomaly achieves higher scores for Network Security Laboratory-Knowledge Discovery in Databases and UNSW-NB15 datasets at 13%and 8%of F1 scores and 4.17%and 11.51%for accuracy,respectively.Furthermore,experiments of the proposed adaptive learning reveal mostly improved results over the initial values.An analysis and monitoring system based on the combination of the three explainable methodologies is also described.Thus,the proposed method has the potential advantages to be applied in practical industry,and future research will explore handling unbalanced real-time datasets in various scenarios.展开更多
A method for precise conversion between virtual world and real world is put forward in this paper. The method aims to precisely establish the connection between the virtual coordinates and the real coordinates with Op...A method for precise conversion between virtual world and real world is put forward in this paper. The method aims to precisely establish the connection between the virtual coordinates and the real coordinates with OpenGL. In the virtual world, two virtual cameras are set to capture the left and right perspective planar images, and coordinates of the planar images can be calculated by the perspective projection model. With coordinates of planar images, coordinates of the stereo- scopic image synthesized in the real world can be calculated by the binocular observation model. Therefore, the corresponding connection between the two systems is established. Experimental re- suits match data from this method well. Therefore, this method can precisely realize the conversion and the interactivity, laying a solid foundation for further study.展开更多
Hyper-connectivity in Industry 4.0 has resulted in not only a rapid increase in the amount of information,but also the expansion of areas and assets to be protected.In terms of information security,it has led to an en...Hyper-connectivity in Industry 4.0 has resulted in not only a rapid increase in the amount of information,but also the expansion of areas and assets to be protected.In terms of information security,it has led to an enormous economic cost due to the various and numerous security solutions used in protecting the increased assets.Also,it has caused difficulties in managing those issues due to reasons such as mutual interference,countless security events and logs’data,etc.Within this security environment,an organization should identify and classify assets based on the value of data and their security perspective,and then apply appropriate protection measures according to the assets’security classification for effective security management.But there are still difficulties stemming from the need to manage numerous security solutions in order to protect the classified assets.In this paper,we propose an information classification management service based on blockchain,which presents and uses a model of the value of data and the security perspective.It records transactions of classifying assets and managing assets by each class in a distributed ledger of blockchain.The proposed service reduces assets to be protected and security solutions to be applied,and provides security measures at the platform level rather than individual security solutions,by using blockchain.In the rapidly changing security environment of Industry 4.0,this proposed service enables economic security,provides a new integrated security platform,and demonstrates service value.展开更多
This research discusses how to use a real-time Artificial Intelligence(AI)object detection model to improve on-site incident command and personal accountability in fire response.We utilized images of firegrounds obtai...This research discusses how to use a real-time Artificial Intelligence(AI)object detection model to improve on-site incident command and personal accountability in fire response.We utilized images of firegrounds obtained from an online resource and a local fire department to train the AI object detector,YOLOv4.Consequently,the real-time AI object detector can reach more than ninety percent accuracy when counting the number of fire trucks and firefighters on the ground utilizing images from local fire departments.Our initial results indicate AI provides an innovative method to maintain fireground personnel accountability at the scenes of fires.By connecting cameras to additional emergency management equipment(e.g.,cameras in fire trucks and ambulances or drones),this research highlights how this technology can be broadly applied to various scenarios of disaster response,thus improving on-site incident fire command and enhancing personnel accountability on the fireground.展开更多
Over the past decade,robot systems have become more commonplace and increasingly autonomous.In recent years,first responders have started to use novel technologies at the scene of disasters in order to save more lives...Over the past decade,robot systems have become more commonplace and increasingly autonomous.In recent years,first responders have started to use novel technologies at the scene of disasters in order to save more lives.Technologies are also used for early warning,surveillance and to enhance disaster response capabilities.Increasingly,technologies like robots are used for warning people,monitoring compliance,SAR(Search and Rescue),damage assessment,to search disaster sites.In the case of emergency situations,emergency guidance robots are sent inside of buildings or deployed to search for victims,guide evacuees to safety and other unsafe response tasks.This paper explores the application of robotics for disaster warning and response,benefits and factors influencing deployment of robots,in order to justify the effective usage of robotics for disaster management in the UAE(United Arab Emirates).A pilot study is conducted to achieve this aim,with 24 participants selected through random sampling from three emergency organizations in the country.To increase knowledge and usage of robotics for future disaster warning and response in UAE,it is needful to continue to highlight the role of robotics deployment in helping to minimize risks and disaster impacts on first responders and the public.展开更多
Helicobacter pylori(H.pylori)infection is one of the most common chronic bacterial infections all over the world.University students are a group with strong comprehensive ability.Their cognition and behavior can exert...Helicobacter pylori(H.pylori)infection is one of the most common chronic bacterial infections all over the world.University students are a group with strong comprehensive ability.Their cognition and behavior can exert great impact on society.However,up to now,reports on the awareness and attitudes regarding H.pylori infection among university students are scarce.This study aimed to survey dietary,habits,knowledge,and attitudes towards H.pylori infection.A total of 5794 participants,including undergraduates,postgraduates,and doctoral students,were recruited from the top 100 universities in China.A selfconstructed questionnaire was used to assess the knowledge and attitudes of students toward H.pylori infection and its impact.In our study,most of the population preferred dining in the canteen(69.6%),whereas 20.6% chose restaurants or takeaway.Up to 24.1% of the respondents had at least one lifestyle habit associated with H.pylori colonization.Almost half had at least one digestive symptom related to H.pylori infection.Most students were aware of its association with gastritis(84.4%)and peptic ulcer(86.6%).However,only half of them were aware of its association with gastric cancer(57.9%).Furthermore,only 14.1% of the respondents had been tested for H.pylori,and 25.1% of them tested positive.The H.pylori-detection rate was higher in Hunan province compared with Guangdong and Jilin provinces.Regarding knowledge of H.pylori,65.4% of the respondents had known about it,and 24.3% correctly answered all questions.When comparing the acquisition of H.pylori knowledge between tested and untested students,32.5% of the tested participants answered all questions correctly,which was significantly higher than the untested group(13.1%).There was no significant difference between genders in H.pylori knowledge and detection.University students are highly educated population.If they were fully aware of the harm of H.pylori infection,their parents,friends,and even future families would benefit,thus reducing the incidence of H.pylori infection,as well as gastric cancer and healthcare finances.This survey not only investigated but also spread the awareness of H.pylori among university students,which is of great medical,economic and sociological importance.展开更多
The 21st-century global health landscape presents unprecedented challenges,such as antimicrobial resistance,mental health issues,and the rapid spread of infectious diseases due to urbanization and mobility.The Sendai ...The 21st-century global health landscape presents unprecedented challenges,such as antimicrobial resistance,mental health issues,and the rapid spread of infectious diseases due to urbanization and mobility.The Sendai Framework and initiatives such as Singapore’s analytics in combating dengue exemplify the push for disaster risk reduction and advanced preparedness.The recent pandemic has underscored the vulnerabilities of health systems,highlighting the need for telehealth and improved emergency response capacities.Military-civilian partner-ships and psychological support for healthcare workers have emerged as some critical components.Embracing an all-hazard approach and prioritizing environmental and psychological resilience are key to a robust,culturally sensitive global health strategy,emphasizing the im-portance of open-access research for comprehensive global preparedness.展开更多
In this rapid review,we critically scrutinize the disaster management infrastructure in Saudi Arabia,illuminating pivotal issues of interoperability,global cooperation,established procedures,community readiness,and th...In this rapid review,we critically scrutinize the disaster management infrastructure in Saudi Arabia,illuminating pivotal issues of interoperability,global cooperation,established procedures,community readiness,and the integration of cuttingedge technologies.Our exploration uncovers a significant convergence with international benchmarks,while pinpointing areas primed for enhancement.We recognize that continual commitments to infrastructural progression and technology adoption are indispensable.Moreover,we underscore the value of robust community involvement and cross-border collaborations as key factors in bolstering disaster response capabilities.Importantly,we spotlight the transformative influence of emerging technologies,such as artificial intelligence and the Internet of Things,in elevating the effectiveness of disaster management strategies.Our review champions in all-encompassing approach to disaster management,which entails harnessing innovative technologies,nurturing resilient communities,and promoting comprehensive disaster management strategies,encapsulating planning,preparedness,response,and recovery.As a result of our analysis,we provide actionable recommendations to advance Saudi Arabia's disaster management framework.Our insights are timely and crucial,considering the escalating global focus on disaster response in the face of increasing disaster and humanitarian events.展开更多
As the world transitions into a postpandemic era,hospitals and healthcare systems must adapt their emergency management plans to address the unique challenges that remain.Building upon the previous Hospital Emergency ...As the world transitions into a postpandemic era,hospitals and healthcare systems must adapt their emergency management plans to address the unique challenges that remain.Building upon the previous Hospital Emergency Management Plan^([1])during the coronavirus disease 2019 pandemic,this commentary offers updated and novel suggestions for emergency preparedness,emphasizing the need for international coordination and the implementation of innovative strategies.展开更多
基金supported by the IITP(Institute of Information&Communications Technology Planning&Evaluation)-ITRC(Information Technology Research Center)grant funded by the Korean government(Ministry of Science and ICT)(IITP-2025-RS-2024-00438056).
文摘The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among users.However,it has also heightened concerns about digital safety,particularly for children and adolescents who are increasingly exposed to online grooming crimes.Early and accurate identification of grooming conversations is crucial in preventing long-term harm to victims.However,research on grooming detection in South Korea remains limited,as existing models trained primarily on English text and fail to reflect the unique linguistic features of SNS conversations,leading to inaccurate classifications.To address these issues,this study proposes a novel framework that integrates optical character recognition(OCR)technology with KcELECTRA,a deep learning-based natural language processing(NLP)model that shows excellent performance in processing the colloquial Korean language.In the proposed framework,the KcELECTRA model is fine-tuned by an extensive dataset,including Korean social media conversations,Korean ethical verification data from AI-Hub,and Korean hate speech data from Hug-gingFace,to enable more accurate classification of text extracted from social media conversation images.Experimental results show that the proposed framework achieves an accuracy of 0.953,outperforming existing transformer-based models.Furthermore,OCR technology shows high accuracy in extracting text from images,demonstrating that the proposed framework is effective for online grooming detection.The proposed framework is expected to contribute to the more accurate detection of grooming text and the prevention of grooming-related crimes.
基金financial support from the National Key Research and Development Program of China(2018YFA0703400)the Fundamental Research Funds for the Provincial Universities of Zhejiang(GK239909299001021)+1 种基金the Ninth China Association for Science and Technology Youth Talent Lift Project Support Plan(KYZ015324002)the Changjiang Scholars Program of Chinese Ministry of Education。
文摘Atomic surfaces are strictly required by high-performance devices of diamond.Nevertheless,diamond is the hardest material in nature,leading to the low material removal rate(MRR)and high surface roughness during machining.Noxious slurries are widely used in conventional chemical mechanical polishing(CMP),resulting in the possible pollution to the environment.Moreover,the traditional slurries normally contain more than four ingredients,causing difficulties to control the process and quality of CMP.To solve these challenges,a novel green CMP for single crystal diamond was developed,consisting of only hydrogen peroxide,diamond abrasive and Prussian blue(PB)/titania catalyst.After CMP,atomic surface is achieved with surface roughness Sa of 0.079 nm,and the MRR is 1168 nm·h^(-1).Thickness of damaged layer is merely 0.66 nm confirmed by transmission electron microscopy(TEM).X-ray photoelectron spectroscopy,electron paramagnetic resonance and TEM reveal that·OH radicals form under ultraviolet irradiation on PB/titania catalyst.The·OH radicals oxidize diamond,transforming it from monocrystalline to amorphous atomic structure,generating a soft amorphous layer.This contributes the high MRR and formation of atomic surface on diamond.The developed novel green CMP offers new insights to achieve atomic surface of diamond for potential use in their high-performance devices.
基金This paper was supported by a Korea Institute for the Advancement of Technology(KIAT)grant funded by the Korean government(MOTIE,No.P0008703)by a National Research Foundation of Korea(NRF)grant funded by the Korean government(MSIT,No.2018R1C1B5046760).
文摘The medical convergence industry has gradually adopted ICT devices,which has led to legacy security problems related to ICT devices.However,it has been difficult to solve these problems due to data resource issues.Such problems can cause a lack of reliability in medical artificial intelligence services that utilize medical information.Therefore,to provide reliable services focused on security internalization,it is necessary to establish a medical convergence environment-oriented security management system.This study proposes the use of system identification and countermeasures to secure systemreliabilitywhen using medical convergence environment information in medical artificial intelligence.We checked the life cycle of medical information and the flow and location of information,analyzed the security threats that may arise during the life cycle,and proposed technical countermeasures to overcome such threats.We verified the proposed countermeasures through a survey of experts.Security requirements were defined based on the information life cycle in the medical convergence environment.We also designed technical countermeasures for use in the security management systems of hospitals of diverse sizes.
基金This work was completed as part of the EPSRC research Grant“The Uncertainty of Identity:Linking Spatiotemporal Information in the Real and Virtual Worlds”(EP/J005266/1).
文摘The penetration and use of social media services differs from city to city.This paper is aimed to provide a comparison of the use of Twitter between different cities of the world.We present a temporal analysis of activity on Twitter in 15 cities.Our study consists of two parts:First,we created temporal graphs of the activity in the 15 cities,through which hours of high and low activity could be identified.Second,we created heat map visualizations of the Twitter activities during the period of 19 September 2012–25 September 2013.The heat map visualizations make the periods of intense and sparse activity apparent and provide a snapshot of the activity during the whole year.
基金Project 20050290010 supported by the Doctoral Foundation of Chinese Education Ministry and 2005AA133070 by National 863 Program for High Technique Research Development
文摘The spontaneous combustion is a smoldering process and characterized by a slow burning speed and a long duration. Therefore, it is a hazard to coal mines. Early detection of coal mine spontaneous combustion is quite difficult because of the complexity of different coal mines. And the traditional threshold discriminance is not suitable for spontaneous combustion detection due to the uncertainty of coalmine combustion. Restrictions of the single detection method will also affect the detection precision in the early time of spontaneous combustion. Although multiple detection methods can be adopted as a complementarity to improve the accuracy of detection, the synthesized method will in- crease the complicacy of criterion, making it difficult to estimate the combustion. To solve this problem, a fuzzy inference system based on CRI （Compositional Rule of Inference） and fuzzy reasoning method FITA （First Infer Then Aggregate） are presented. And the neural network is also developed to realize the fuzzy inference system. Finally, the effectiveness of the inference system is demonstrated bv means of an experiment.
基金funded by the Grant of the Department of Science and Technology of Jilin Province,grant number[20200201156JC]Jilin Province Health Science and Technology ability advancement project,grant number[2022Jc081].
文摘Cobalt(Co)is a silver-gray,high-intensity,widely distributed metal element that exists in cobalt compounds,and its common valences are bivalence(Co2+)and trivalence(Co3+)[1].The main routes of Co-exposure are occupational and environmental exposures.The human body can be exposed to high concentrations of Co2+through inhalation of contaminated air,consumption of contaminated food and water,or ingestion of Co-containing supplements[2].
基金supported by the Culture,Sports,and Tourism R&D Program through the Korea Creative Content Agency grant funded by the Ministry of Culture,Sports,and Tourism in 2024(Project Name:Development of Distribution and Management Platform Technology and Human Resource Development for Blockchain-Based SW Copyright Protection,Project Number:RS-2023-00228867,Contribution Rate:100%)and also supported by the Soonchunhyang University Research Fund.
文摘In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)datasets?This study is crucial because it addresses the challenge of identifying rare and complex anomalous patterns in the vast amounts of time series data generated by Internet of Things(IoT)devices,which can significantly improve the reliability and safety of these systems.In this paper,we propose a hybrid autoencoder model,called ConvBiLSTMAE,which combines convolutional neural network(CNN)and bidirectional long short-term memory(BiLSTM)to more effectively train complex temporal data patterns in anomaly detection.On the hardware-in-the-loopbased extended industrial control system dataset,the ConvBiLSTM-AE model demonstrated remarkable anomaly detection performance,achieving F1 scores of 0.78 and 0.41 for the first and second datasets,respectively.The results suggest that hybrid autoencoder models are not only viable,but potentially superior alternatives for unsupervised anomaly detection in complex industrial systems,offering a promising approach to improving their reliability and safety.
基金funded by the UK EPSRC grant EP/S022503/1 that supports the Centre for Doctoral Training in Cybersecurity at UCL.
文摘Decentralized Finance(DeFi)is a system of financial products and services built and delivered through smart contracts on various blockchains.In recent years,DeFi has gained popularity and market capitalization.However,it has also been connected to crime,particularly various types of securities violations.The lack of Know Your Customer requirements in DeFi poses challenges for governments trying to mitigate potential offenses.This study aims to determine whether this problem is suited to a machine learning approach,namely,whether we can identify DeFi projects potentially engaging in securities violations based on their tokens’smart contract code.We adapted prior works on detecting specific types of securities violations across Ethereum by building classifiers based on features extracted from DeFi projects’tokens’smart contract code(specifically,opcode-based features).Our final model was a random forest model that achieved an 80%F-1 score against a baseline of 50%.Notably,we further explored the code-based features that are the most important to our model’s performance in more detail by analyzing tokens’Solidity code and conducting cosine similarity analyses.We found that one element of the code that our opcode-based features can capture is the implementation of the SafeMath library,although this does not account for the entirety of our features.Another contribution of our study is a new dataset,comprising(a)a verified ground truth dataset for tokens involved in securities violations and(b)a set of legitimate tokens from a reputable DeFi aggregator.This paper further discusses the potential use of a model like ours by prosecutors in enforcement efforts and connects it to a wider legal context.
基金supported by Korea Institute for Advancement of Technology(KIAT)grant funded by theKoreaGovernment(MOTIE)(P0008703,The CompetencyDevelopment Program for Industry Specialist).
文摘Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission.Recent research has focused on using semi-supervised learning mechanisms to identify abnormal network traffic to deal with labeled and unlabeled data in the industry.However,real-time training and classifying network traffic pose challenges,as they can lead to the degradation of the overall dataset and difficulties preventing attacks.Additionally,existing semi-supervised learning research might need to analyze the experimental results comprehensively.This paper proposes XA-GANomaly,a novel technique for explainable adaptive semi-supervised learning using GANomaly,an image anomalous detection model that dynamically trains small subsets to these issues.First,this research introduces a deep neural network(DNN)-based GANomaly for semi-supervised learning.Second,this paper presents the proposed adaptive algorithm for the DNN-based GANomaly,which is validated with four subsets of the adaptive dataset.Finally,this study demonstrates a monitoring system that incorporates three explainable techniques—Shapley additive explanations,reconstruction error visualization,and t-distributed stochastic neighbor embedding—to respond effectively to attacks on traffic data at each feature engineering stage,semi-supervised learning,and adaptive learning.Compared to other single-class classification techniques,the proposed DNN-based GANomaly achieves higher scores for Network Security Laboratory-Knowledge Discovery in Databases and UNSW-NB15 datasets at 13%and 8%of F1 scores and 4.17%and 11.51%for accuracy,respectively.Furthermore,experiments of the proposed adaptive learning reveal mostly improved results over the initial values.An analysis and monitoring system based on the combination of the three explainable methodologies is also described.Thus,the proposed method has the potential advantages to be applied in practical industry,and future research will explore handling unbalanced real-time datasets in various scenarios.
基金Supported by the National Natural Science Foundation of China ( 60674052)
文摘A method for precise conversion between virtual world and real world is put forward in this paper. The method aims to precisely establish the connection between the virtual coordinates and the real coordinates with OpenGL. In the virtual world, two virtual cameras are set to capture the left and right perspective planar images, and coordinates of the planar images can be calculated by the perspective projection model. With coordinates of planar images, coordinates of the stereo- scopic image synthesized in the real world can be calculated by the binocular observation model. Therefore, the corresponding connection between the two systems is established. Experimental re- suits match data from this method well. Therefore, this method can precisely realize the conversion and the interactivity, laying a solid foundation for further study.
基金supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2020-2018-0-01799)supervised by the IITP(Institute for Information&communications Technology Planning&Evaluation).
文摘Hyper-connectivity in Industry 4.0 has resulted in not only a rapid increase in the amount of information,but also the expansion of areas and assets to be protected.In terms of information security,it has led to an enormous economic cost due to the various and numerous security solutions used in protecting the increased assets.Also,it has caused difficulties in managing those issues due to reasons such as mutual interference,countless security events and logs’data,etc.Within this security environment,an organization should identify and classify assets based on the value of data and their security perspective,and then apply appropriate protection measures according to the assets’security classification for effective security management.But there are still difficulties stemming from the need to manage numerous security solutions in order to protect the classified assets.In this paper,we propose an information classification management service based on blockchain,which presents and uses a model of the value of data and the security perspective.It records transactions of classifying assets and managing assets by each class in a distributed ledger of blockchain.The proposed service reduces assets to be protected and security solutions to be applied,and provides security measures at the platform level rather than individual security solutions,by using blockchain.In the rapidly changing security environment of Industry 4.0,this proposed service enables economic security,provides a new integrated security platform,and demonstrates service value.
基金the financial support provided by the Hudson College of Public Health at The University of Oklahoma Health Sciences Center,and the Presbyterian Health Foundation(PHF,grant number 20000243)for exploring the AI applications.
文摘This research discusses how to use a real-time Artificial Intelligence(AI)object detection model to improve on-site incident command and personal accountability in fire response.We utilized images of firegrounds obtained from an online resource and a local fire department to train the AI object detector,YOLOv4.Consequently,the real-time AI object detector can reach more than ninety percent accuracy when counting the number of fire trucks and firefighters on the ground utilizing images from local fire departments.Our initial results indicate AI provides an innovative method to maintain fireground personnel accountability at the scenes of fires.By connecting cameras to additional emergency management equipment(e.g.,cameras in fire trucks and ambulances or drones),this research highlights how this technology can be broadly applied to various scenarios of disaster response,thus improving on-site incident fire command and enhancing personnel accountability on the fireground.
文摘Over the past decade,robot systems have become more commonplace and increasingly autonomous.In recent years,first responders have started to use novel technologies at the scene of disasters in order to save more lives.Technologies are also used for early warning,surveillance and to enhance disaster response capabilities.Increasingly,technologies like robots are used for warning people,monitoring compliance,SAR(Search and Rescue),damage assessment,to search disaster sites.In the case of emergency situations,emergency guidance robots are sent inside of buildings or deployed to search for victims,guide evacuees to safety and other unsafe response tasks.This paper explores the application of robotics for disaster warning and response,benefits and factors influencing deployment of robots,in order to justify the effective usage of robotics for disaster management in the UAE(United Arab Emirates).A pilot study is conducted to achieve this aim,with 24 participants selected through random sampling from three emergency organizations in the country.To increase knowledge and usage of robotics for future disaster warning and response in UAE,it is needful to continue to highlight the role of robotics deployment in helping to minimize risks and disaster impacts on first responders and the public.
基金funded by the Development and Reform Commission of Hunan Province to Yuqian Zhou(Grant No.2021-212-17).
文摘Helicobacter pylori(H.pylori)infection is one of the most common chronic bacterial infections all over the world.University students are a group with strong comprehensive ability.Their cognition and behavior can exert great impact on society.However,up to now,reports on the awareness and attitudes regarding H.pylori infection among university students are scarce.This study aimed to survey dietary,habits,knowledge,and attitudes towards H.pylori infection.A total of 5794 participants,including undergraduates,postgraduates,and doctoral students,were recruited from the top 100 universities in China.A selfconstructed questionnaire was used to assess the knowledge and attitudes of students toward H.pylori infection and its impact.In our study,most of the population preferred dining in the canteen(69.6%),whereas 20.6% chose restaurants or takeaway.Up to 24.1% of the respondents had at least one lifestyle habit associated with H.pylori colonization.Almost half had at least one digestive symptom related to H.pylori infection.Most students were aware of its association with gastritis(84.4%)and peptic ulcer(86.6%).However,only half of them were aware of its association with gastric cancer(57.9%).Furthermore,only 14.1% of the respondents had been tested for H.pylori,and 25.1% of them tested positive.The H.pylori-detection rate was higher in Hunan province compared with Guangdong and Jilin provinces.Regarding knowledge of H.pylori,65.4% of the respondents had known about it,and 24.3% correctly answered all questions.When comparing the acquisition of H.pylori knowledge between tested and untested students,32.5% of the tested participants answered all questions correctly,which was significantly higher than the untested group(13.1%).There was no significant difference between genders in H.pylori knowledge and detection.University students are highly educated population.If they were fully aware of the harm of H.pylori infection,their parents,friends,and even future families would benefit,thus reducing the incidence of H.pylori infection,as well as gastric cancer and healthcare finances.This survey not only investigated but also spread the awareness of H.pylori among university students,which is of great medical,economic and sociological importance.
文摘The 21st-century global health landscape presents unprecedented challenges,such as antimicrobial resistance,mental health issues,and the rapid spread of infectious diseases due to urbanization and mobility.The Sendai Framework and initiatives such as Singapore’s analytics in combating dengue exemplify the push for disaster risk reduction and advanced preparedness.The recent pandemic has underscored the vulnerabilities of health systems,highlighting the need for telehealth and improved emergency response capacities.Military-civilian partner-ships and psychological support for healthcare workers have emerged as some critical components.Embracing an all-hazard approach and prioritizing environmental and psychological resilience are key to a robust,culturally sensitive global health strategy,emphasizing the im-portance of open-access research for comprehensive global preparedness.
基金the Deputyship for Research&Innovation,Ministry of Education in Saudi Arabia for funding this research work through the project number(ISP2398)。
文摘In this rapid review,we critically scrutinize the disaster management infrastructure in Saudi Arabia,illuminating pivotal issues of interoperability,global cooperation,established procedures,community readiness,and the integration of cuttingedge technologies.Our exploration uncovers a significant convergence with international benchmarks,while pinpointing areas primed for enhancement.We recognize that continual commitments to infrastructural progression and technology adoption are indispensable.Moreover,we underscore the value of robust community involvement and cross-border collaborations as key factors in bolstering disaster response capabilities.Importantly,we spotlight the transformative influence of emerging technologies,such as artificial intelligence and the Internet of Things,in elevating the effectiveness of disaster management strategies.Our review champions in all-encompassing approach to disaster management,which entails harnessing innovative technologies,nurturing resilient communities,and promoting comprehensive disaster management strategies,encapsulating planning,preparedness,response,and recovery.As a result of our analysis,we provide actionable recommendations to advance Saudi Arabia's disaster management framework.Our insights are timely and crucial,considering the escalating global focus on disaster response in the face of increasing disaster and humanitarian events.
文摘As the world transitions into a postpandemic era,hospitals and healthcare systems must adapt their emergency management plans to address the unique challenges that remain.Building upon the previous Hospital Emergency Management Plan^([1])during the coronavirus disease 2019 pandemic,this commentary offers updated and novel suggestions for emergency preparedness,emphasizing the need for international coordination and the implementation of innovative strategies.
