This article analyzed the importance of information monitoring and quick response on agricultural focuses and significant events, proposed the workflow and technical framework for information monitoring and quick resp...This article analyzed the importance of information monitoring and quick response on agricultural focuses and significant events, proposed the workflow and technical framework for information monitoring and quick response based on modern information technologies, and explained key technologies during implementation and the functional structure for prototype system of the technical support platform.展开更多
Owing to the fast growth of global market,textile and apparel industries which are a typical seasonal business are facing crucial challenges from both competitors and consumers.In order to get survived,forming supply ...Owing to the fast growth of global market,textile and apparel industries which are a typical seasonal business are facing crucial challenges from both competitors and consumers.In order to get survived,forming supply chain and utilizing the emerged technology to establish a quick response system become an important common practice for enterprises in terms of cost reduction and efficiency improvement.This paper presents a multi-agent-based integrated framework for quick response in textile and apparel supply chain.By sharing information and collaborating among chain partner,the multi-agent system provides a promising computing paradigm for quick response business processes.A prototype based on the proposed framework is implemented using ZEUS toolkit.It presents how the proposed architecture is being designed to establish collaborative business environment by providing dynamic quick response processes.展开更多
In order to increase the watermarking capacity and improve the anti-counterfeiting performance of quick response （QR） two-dimensional （2D） barcode based on digital watermarking technique, this paper proposes a kin...In order to increase the watermarking capacity and improve the anti-counterfeiting performance of quick response （QR） two-dimensional （2D） barcode based on digital watermarking technique, this paper proposes a kind of graying algorithm for binary image to make transform domain watermarking methods possible. Based on the graying Mgorithm, the quantizatiombased watermarking scheme in discrete wavelet transform （DWT） domain is then designed. The experiments show that the proposed watermarking scheme for QR 2D barcode greatly improves anti-counterfeiting performance without loss of any barcode information.展开更多
The filter proposed in this paper is expected to reduce noise whose frequency is lower than higher order harmonics of real signals.It is based on the distributive characteristics of noise,and uses analog circuits to s...The filter proposed in this paper is expected to reduce noise whose frequency is lower than higher order harmonics of real signals.It is based on the distributive characteristics of noise,and uses analog circuits to select the high peak and low peak of the input signal and applies their average in order to reduce random noise.So it has no cutoff frequency and higher order harmonics of real signals are remained.As a result,it gives an instant response to changes in input signals and retains the integrity of real signals.Furthermore,it has only a small phase delay.The simulation results of slew rate,phase delay and spectral analysis under MULTISIM indicate that the quick response noise filter achieves a high slew rate of 472 V/ms and the phase shift is nearly zero.By having it used in a color tester design,it is also demonstrated that the proposed filter effectively reduces noise and remains signal integrity.With the filter 's help,the relative standard deviation of the spectrograph decreases from 1% to 0.22%,indicating better stability.展开更多
The scheme of robot positioning based on multiple quick response(QR)code landmarks is proposed.Firstly,the pose of the robot relative to the QR code landmarks is obtained by extracting the feature points of the QR cod...The scheme of robot positioning based on multiple quick response(QR)code landmarks is proposed.Firstly,the pose of the robot relative to the QR code landmarks is obtained by extracting the feature points of the QR code,combined with the visual computing technology.Then,the conversion of the absolute pose of the robot is completed based on the absolute position of the QR code landmark,and thus the real-time position of the robot is obtained.The proposed scheme makes full use of the QR code fault tolerance and multiple QR code landmarks to improve the calculation accuracy.It has good robustness and versatility,and it is easy to implement.It can help the robot to complete the positioning in the actual work,making robot navigation more accurate.展开更多
Quick response research conducted by social scientists in the aftermath of a disaster can reveal important findings about hazards and their impacts on communities.Research to collect perishable data,or data that will ...Quick response research conducted by social scientists in the aftermath of a disaster can reveal important findings about hazards and their impacts on communities.Research to collect perishable data,or data that will change or be lost over time,immediately following disaster has been supported for decades by two programs in the United States,amassing a collection of quick response studies and an associated research culture.That culture is currently being challenged to better address power imbalances between researchers and disaster-affected participants.Until recently,Canada has not had a quick response grant program.In order to survey the state of knowledge and draw from it in helping to shape the new program in Canada,this article systematically analyzes the body of research created by the two US programs.The results reveal a wide-ranging literature:the studies are theoretically,conceptually,topically,and methodologically quite unique to one another.This diversity might appropriately reflect the nature of disasters,but the finding that many studies are not building on previous quick response research and other in sights indicate opportunities for how a new grant program in Canada can contribute to growing a robust subdiscipline of disaster research.展开更多
COVID-19 prompted an abundance of independent and collaborative quick response disaster research(QRDR)initiatives globally.The 2020 federal COVID-19-driven granting opportunities initiated the first official QRDR effo...COVID-19 prompted an abundance of independent and collaborative quick response disaster research(QRDR)initiatives globally.The 2020 federal COVID-19-driven granting opportunities initiated the first official QRDR effort in Canadian history,engaging social scientists to rapidly address the pandemic-related societal influences.This study aims to portray the landscape of this nascent social science QRDR workforce through the first round of federal COVID-19-specific grant recipients.A case study approach was employed to analyze 337 social science projects with 1119 associated researchers,examining the demographic structure of these COVID-19-driven social science researchers and their research projects'characteristics.Accordingly,the findings are presented through the following two streams:(1)From a researcher perspective,this case study describes researcher typology,geographic location,primary discipline,and educational background,highlighting the diverse characteristics of social sciences researchers,and uneven research development across Canada.(2)From a research project perspective,this case study identifies and synthesizes research project subjects,themes,collaborations,and Canadian distinctions,emphasizing the need for galvanizing cooperation and focusing on uniquely Canadian contexts.The case study illustrates challenges associated with data curation that pose barriers to developing a nuanced understanding of the Canadian social science community COVID-19 research landscape.Consequently,the case study develops three recommendations to improve QRDR development in Canada:promoting information transparency,dissemination,and updates;improving hazards and disaster research workforce evaluation;and enhancing multi-stakeholder cooperation.展开更多
This study introduces a lightweight deep learning model and a novel synthetic dataset designed to restore damaged one-dimensional(1D)barcodes and Quick Response(QR)codes,addressing critical challenges in logistics ope...This study introduces a lightweight deep learning model and a novel synthetic dataset designed to restore damaged one-dimensional(1D)barcodes and Quick Response(QR)codes,addressing critical challenges in logistics operations.The proposed solution leverages an efficient Pix2Pix-based framework,a type of conditional Generative Adversarial Network(GAN)optimized for image-to-image translation tasks,enabling the recovery of degraded barcodes and QR codes with minimal computational overhead.A core contribution of this work is the development of a synthetic dataset that simulates realistic damage scenarios frequently encountered in logistics environments,such as low contrast,misalignment,physical wear,and environmental interference.By training on this diverse and realistic dataset,the model demonstrates exceptional performance in restoring readability and decoding accuracy.The lightweight architecture,featuring a U-Net-based encoder-decoder with separable convolutions,ensures computational efficiency,making the approach suitable for real-time deployment on embedded and resource-constrained devices commonly used in logistics systems.Experimental results reveal significant improvements:QR code decoding ratios increased from 14%to 99%on training data and from 15%to 68%on validation data,while 1D barcode decoding ratios improved from 7%to 73%on training data and from 9%to 44%on validation data.By providing a robust,resource-efficient solution for restoring damaged barcodes and QR codes,this study offers practical advancements for enhancing the reliability of automated scanning systems in logistics operations,particularly under challenging conditions.展开更多
A novel strategy was developed to fabricate FeNx-doped carbon quantum dots(Fe-N-CQDs)to detect Cu^(2+) ions selectively as a fluorescence probe.The Fe-N-CQDs were synthesized by an efficient electrolysis of a carbon c...A novel strategy was developed to fabricate FeNx-doped carbon quantum dots(Fe-N-CQDs)to detect Cu^(2+) ions selectively as a fluorescence probe.The Fe-N-CQDs were synthesized by an efficient electrolysis of a carbon cloth electrode,which was coated with monoatomic ironanchored nitrogen-doped carbon(Fe-N-C).The obtained Fe-N-CQDs emitted blue fluorescence and possessed a quantum yield(QY)of 7.5%.An extremely wide linear relationship between the Cu^(2+) concentration and the fluorescence intensity was obtained in the range from 100 nmol L^(-1) to 1000 nmol L^(-1)(R^(2)=0.997),and the detection limit was calculated as 59 nmol L^(-1).Moreover,the Fe-N-CQDs demonstrated wide range pH compatibility between 2 and 13 due to the coordination between pyridine nitrogen and Fe^(3+),which dramatically reduced the affection of the protonation and deprotonation process between H^(+) and Fe-N-CQDs.It is notable that the Fe-N-CQDs exhibited a rapid response in Cu^(2+) detection,where stable quenching can be completed in 7 s.The mechanism of excellent selective detection of Cu^(2+) was revealed by energy level simulation that the LUMO level of Fe-N-CQDs(-4.37 eV)was close to the redox potential of Cu^(2+),thus facilitating the electron transport from Fe-N-CQDs to Cu^(2+).展开更多
In this paper a label-based simultaneous localization and mapping（ SLAM） system is proposed to provide localization to indoor autonomous robots. In the system quick response（ QR） codes encoded with serial numbers ...In this paper a label-based simultaneous localization and mapping（ SLAM） system is proposed to provide localization to indoor autonomous robots. In the system quick response（ QR） codes encoded with serial numbers are utilized as labels. These labels are captured by two webcams,then the distances and angles between the labels and webcams are computed. Motion estimated from the two rear wheel encoders is adjusted by observing QR codes. Our system uses the extended Kalman filter（ EKF） for the back-end state estimation. The number of deployed labels controls the state estimation dimension. The label-based EKF-SLAM system eliminates complicated processes,such as data association and loop closure detection in traditional feature-based visual SLAM systems. Our experiments include software-simulation and robot-platform test in a real environment. Results demonstrate that the system has the capability of correcting accumulated errors of dead reckoning and therefore has the advantage of superior precision.展开更多
Recently,both the importance and awareness relating to food safety relating to agrochemicals,chemical fertilizers,the pollution of ecosystem and unwholesome foods are growing rapidly.For the same reason,the purchaser&...Recently,both the importance and awareness relating to food safety relating to agrochemicals,chemical fertilizers,the pollution of ecosystem and unwholesome foods are growing rapidly.For the same reason,the purchaser's curiosity increases to know about the production process which can be accomplished by production traceability system.The traceability system can store and superintend the specific attribute information about products regarding the productive centre,producer and production finish data.The products undergo various circulation processes and they are being managed by individually constructed traceability system.Thus,it is difficult for the producer and the consumer to guarantee the safety from transpirable issues about the falsification of production traceability because the traceability information can be re-produced by forging through various ways.So in this paper,we proposed a system for integrated management of agro-fishery products based on quick response code(QR-code)for forgery prevention which may help to solve these issues.The proposed system makes QR-code using production information provided by producer.And then it is provided to the distributor and the consumer through integrated service model using the QR-code.Therefore,this system make sure to provide the same production traceability about the products to the distributor and the consumer and always keeps both updated with the same information.展开更多
This paper briefly introduces the characteristics and structure of symbol QR two-dimensional code, a detailed analysis of the image processing method to identify QR code of the whole process, and the bilinear mapping ...This paper briefly introduces the characteristics and structure of symbol QR two-dimensional code, a detailed analysis of the image processing method to identify QR code of the whole process, and the bilinear mapping method is applied to image correction, the final steps of decoding are given. The actual test results show that, the design algorithm has theoretical and practical, this recognition system can correctly read QR code, and has high recognition rate and recognition speed, has practical value and application prospect.展开更多
QR codes are widely used in applications such as information sharing,advertising,and digital payments.However,their growing adoption has made them attractive targets for malicious activities,including malware distribu...QR codes are widely used in applications such as information sharing,advertising,and digital payments.However,their growing adoption has made them attractive targets for malicious activities,including malware distribution and phishing attacks.Traditional detection approaches rely on URL analysis or image-based feature extraction,whichmay introduce significant computational overhead and limit real-time applicability,and their performance often depends on the quality of extracted features.Previous studies in malicious detection do not fully focus on QR code securitywhen combining convolutional neural networks(CNNs)with recurrent neural networks(RNNs).This research proposes a deep learning model that integrates AlexNet for feature extraction,principal component analysis(PCA)for dimensionality reduction,and RNNs to detect malicious activity in QR code images.The proposed model achieves both efficiency and accuracy by transforming image data into a compact one-dimensional sequence.Experimental results,including five-fold cross-validation,demonstrate that the model using gated recurrent units(GRU)achieved an accuracy of 99.81%on the first dataset and 99.59%in the second dataset with a computation time of only 7.433 ms per sample.A real-time prototype was also developed to demonstrate deployment feasibility.These results highlight the potential of the proposed approach for practical,real-time QR code threat detection.展开更多
文摘This article analyzed the importance of information monitoring and quick response on agricultural focuses and significant events, proposed the workflow and technical framework for information monitoring and quick response based on modern information technologies, and explained key technologies during implementation and the functional structure for prototype system of the technical support platform.
基金Supported by National Natural Science Foundation of China(No.70772073)Shanghai Social Science Foundation(No.2007BZH001)Shanghai Natural Science Foundation(No.07ZR14003)
文摘Owing to the fast growth of global market,textile and apparel industries which are a typical seasonal business are facing crucial challenges from both competitors and consumers.In order to get survived,forming supply chain and utilizing the emerged technology to establish a quick response system become an important common practice for enterprises in terms of cost reduction and efficiency improvement.This paper presents a multi-agent-based integrated framework for quick response in textile and apparel supply chain.By sharing information and collaborating among chain partner,the multi-agent system provides a promising computing paradigm for quick response business processes.A prototype based on the proposed framework is implemented using ZEUS toolkit.It presents how the proposed architecture is being designed to establish collaborative business environment by providing dynamic quick response processes.
基金the National Natural Science Foundation of China(No.60903203)the Fujian Educational Bureau JK Projects(No.JK2012044)the Xiamen Municipal Science and Technology Plan Projects(No.3502Z20103036)
文摘In order to increase the watermarking capacity and improve the anti-counterfeiting performance of quick response （QR） two-dimensional （2D） barcode based on digital watermarking technique, this paper proposes a kind of graying algorithm for binary image to make transform domain watermarking methods possible. Based on the graying Mgorithm, the quantizatiombased watermarking scheme in discrete wavelet transform （DWT） domain is then designed. The experiments show that the proposed watermarking scheme for QR 2D barcode greatly improves anti-counterfeiting performance without loss of any barcode information.
基金Sponsored by the National High Technology Research and Development Program(Grant No.863-2-5-1-13B)
文摘The filter proposed in this paper is expected to reduce noise whose frequency is lower than higher order harmonics of real signals.It is based on the distributive characteristics of noise,and uses analog circuits to select the high peak and low peak of the input signal and applies their average in order to reduce random noise.So it has no cutoff frequency and higher order harmonics of real signals are remained.As a result,it gives an instant response to changes in input signals and retains the integrity of real signals.Furthermore,it has only a small phase delay.The simulation results of slew rate,phase delay and spectral analysis under MULTISIM indicate that the quick response noise filter achieves a high slew rate of 472 V/ms and the phase shift is nearly zero.By having it used in a color tester design,it is also demonstrated that the proposed filter effectively reduces noise and remains signal integrity.With the filter 's help,the relative standard deviation of the spectrograph decreases from 1% to 0.22%,indicating better stability.
基金Project of Introducing Urgently Needed Talents in Key Support Areas of Shandong Province,China。
文摘The scheme of robot positioning based on multiple quick response(QR)code landmarks is proposed.Firstly,the pose of the robot relative to the QR code landmarks is obtained by extracting the feature points of the QR code,combined with the visual computing technology.Then,the conversion of the absolute pose of the robot is completed based on the absolute position of the QR code landmark,and thus the real-time position of the robot is obtained.The proposed scheme makes full use of the QR code fault tolerance and multiple QR code landmarks to improve the calculation accuracy.It has good robustness and versatility,and it is easy to implement.It can help the robot to complete the positioning in the actual work,making robot navigation more accurate.
基金Funding in support of this study was provided by the Marine Environmental Observation,Prediction and Response(MEOPAR)Network of Centres of Excellence of Canada。
文摘Quick response research conducted by social scientists in the aftermath of a disaster can reveal important findings about hazards and their impacts on communities.Research to collect perishable data,or data that will change or be lost over time,immediately following disaster has been supported for decades by two programs in the United States,amassing a collection of quick response studies and an associated research culture.That culture is currently being challenged to better address power imbalances between researchers and disaster-affected participants.Until recently,Canada has not had a quick response grant program.In order to survey the state of knowledge and draw from it in helping to shape the new program in Canada,this article systematically analyzes the body of research created by the two US programs.The results reveal a wide-ranging literature:the studies are theoretically,conceptually,topically,and methodologically quite unique to one another.This diversity might appropriately reflect the nature of disasters,but the finding that many studies are not building on previous quick response research and other in sights indicate opportunities for how a new grant program in Canada can contribute to growing a robust subdiscipline of disaster research.
基金supported by the Research Development Grants from the Faculty of Health at Dalhousie Universityfunding from the Canada Research Chairs Program (Award # CRC-2020-00128)
文摘COVID-19 prompted an abundance of independent and collaborative quick response disaster research(QRDR)initiatives globally.The 2020 federal COVID-19-driven granting opportunities initiated the first official QRDR effort in Canadian history,engaging social scientists to rapidly address the pandemic-related societal influences.This study aims to portray the landscape of this nascent social science QRDR workforce through the first round of federal COVID-19-specific grant recipients.A case study approach was employed to analyze 337 social science projects with 1119 associated researchers,examining the demographic structure of these COVID-19-driven social science researchers and their research projects'characteristics.Accordingly,the findings are presented through the following two streams:(1)From a researcher perspective,this case study describes researcher typology,geographic location,primary discipline,and educational background,highlighting the diverse characteristics of social sciences researchers,and uneven research development across Canada.(2)From a research project perspective,this case study identifies and synthesizes research project subjects,themes,collaborations,and Canadian distinctions,emphasizing the need for galvanizing cooperation and focusing on uniquely Canadian contexts.The case study illustrates challenges associated with data curation that pose barriers to developing a nuanced understanding of the Canadian social science community COVID-19 research landscape.Consequently,the case study develops three recommendations to improve QRDR development in Canada:promoting information transparency,dissemination,and updates;improving hazards and disaster research workforce evaluation;and enhancing multi-stakeholder cooperation.
基金supported by the Scientific and Technological Research Council of Turkey(TÜB˙ITAK)through the Industrial R&D Projects Grant Program(TEYDEB)under Project No.3211077(grant recipient:Metin Kahraman)。
文摘This study introduces a lightweight deep learning model and a novel synthetic dataset designed to restore damaged one-dimensional(1D)barcodes and Quick Response(QR)codes,addressing critical challenges in logistics operations.The proposed solution leverages an efficient Pix2Pix-based framework,a type of conditional Generative Adversarial Network(GAN)optimized for image-to-image translation tasks,enabling the recovery of degraded barcodes and QR codes with minimal computational overhead.A core contribution of this work is the development of a synthetic dataset that simulates realistic damage scenarios frequently encountered in logistics environments,such as low contrast,misalignment,physical wear,and environmental interference.By training on this diverse and realistic dataset,the model demonstrates exceptional performance in restoring readability and decoding accuracy.The lightweight architecture,featuring a U-Net-based encoder-decoder with separable convolutions,ensures computational efficiency,making the approach suitable for real-time deployment on embedded and resource-constrained devices commonly used in logistics systems.Experimental results reveal significant improvements:QR code decoding ratios increased from 14%to 99%on training data and from 15%to 68%on validation data,while 1D barcode decoding ratios improved from 7%to 73%on training data and from 9%to 44%on validation data.By providing a robust,resource-efficient solution for restoring damaged barcodes and QR codes,this study offers practical advancements for enhancing the reliability of automated scanning systems in logistics operations,particularly under challenging conditions.
基金the National Natural Science Foundation of China(Nos.21776302 and 21776308)the Science Foundation of China University of Petroleum,Beijing(No.2462020YXZZ033).
文摘A novel strategy was developed to fabricate FeNx-doped carbon quantum dots(Fe-N-CQDs)to detect Cu^(2+) ions selectively as a fluorescence probe.The Fe-N-CQDs were synthesized by an efficient electrolysis of a carbon cloth electrode,which was coated with monoatomic ironanchored nitrogen-doped carbon(Fe-N-C).The obtained Fe-N-CQDs emitted blue fluorescence and possessed a quantum yield(QY)of 7.5%.An extremely wide linear relationship between the Cu^(2+) concentration and the fluorescence intensity was obtained in the range from 100 nmol L^(-1) to 1000 nmol L^(-1)(R^(2)=0.997),and the detection limit was calculated as 59 nmol L^(-1).Moreover,the Fe-N-CQDs demonstrated wide range pH compatibility between 2 and 13 due to the coordination between pyridine nitrogen and Fe^(3+),which dramatically reduced the affection of the protonation and deprotonation process between H^(+) and Fe-N-CQDs.It is notable that the Fe-N-CQDs exhibited a rapid response in Cu^(2+) detection,where stable quenching can be completed in 7 s.The mechanism of excellent selective detection of Cu^(2+) was revealed by energy level simulation that the LUMO level of Fe-N-CQDs(-4.37 eV)was close to the redox potential of Cu^(2+),thus facilitating the electron transport from Fe-N-CQDs to Cu^(2+).
基金Supported by Program for Changjiang Scholars and Innovative Research Team in University,National Science Foundation of China(61105092)the National Natural Science Foundation of China(61473042)
文摘In this paper a label-based simultaneous localization and mapping（ SLAM） system is proposed to provide localization to indoor autonomous robots. In the system quick response（ QR） codes encoded with serial numbers are utilized as labels. These labels are captured by two webcams,then the distances and angles between the labels and webcams are computed. Motion estimated from the two rear wheel encoders is adjusted by observing QR codes. Our system uses the extended Kalman filter（ EKF） for the back-end state estimation. The number of deployed labels controls the state estimation dimension. The label-based EKF-SLAM system eliminates complicated processes,such as data association and loop closure detection in traditional feature-based visual SLAM systems. Our experiments include software-simulation and robot-platform test in a real environment. Results demonstrate that the system has the capability of correcting accumulated errors of dead reckoning and therefore has the advantage of superior precision.
基金The MSIP(Ministry of Science,ICT&Future Planning),Korea,under the ITRC(Information Technology Research Center)support program(NIPA-2013-H0301-13-2006)supervised by the NIPA(National IT Industry Promotion Agency)
文摘Recently,both the importance and awareness relating to food safety relating to agrochemicals,chemical fertilizers,the pollution of ecosystem and unwholesome foods are growing rapidly.For the same reason,the purchaser's curiosity increases to know about the production process which can be accomplished by production traceability system.The traceability system can store and superintend the specific attribute information about products regarding the productive centre,producer and production finish data.The products undergo various circulation processes and they are being managed by individually constructed traceability system.Thus,it is difficult for the producer and the consumer to guarantee the safety from transpirable issues about the falsification of production traceability because the traceability information can be re-produced by forging through various ways.So in this paper,we proposed a system for integrated management of agro-fishery products based on quick response code(QR-code)for forgery prevention which may help to solve these issues.The proposed system makes QR-code using production information provided by producer.And then it is provided to the distributor and the consumer through integrated service model using the QR-code.Therefore,this system make sure to provide the same production traceability about the products to the distributor and the consumer and always keeps both updated with the same information.
文摘This paper briefly introduces the characteristics and structure of symbol QR two-dimensional code, a detailed analysis of the image processing method to identify QR code of the whole process, and the bilinear mapping method is applied to image correction, the final steps of decoding are given. The actual test results show that, the design algorithm has theoretical and practical, this recognition system can correctly read QR code, and has high recognition rate and recognition speed, has practical value and application prospect.
基金funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University Jeddah,under grant no.(GPIP:1168-611-2024)The authors acknowledge the DSR for financial and technical support.
文摘QR codes are widely used in applications such as information sharing,advertising,and digital payments.However,their growing adoption has made them attractive targets for malicious activities,including malware distribution and phishing attacks.Traditional detection approaches rely on URL analysis or image-based feature extraction,whichmay introduce significant computational overhead and limit real-time applicability,and their performance often depends on the quality of extracted features.Previous studies in malicious detection do not fully focus on QR code securitywhen combining convolutional neural networks(CNNs)with recurrent neural networks(RNNs).This research proposes a deep learning model that integrates AlexNet for feature extraction,principal component analysis(PCA)for dimensionality reduction,and RNNs to detect malicious activity in QR code images.The proposed model achieves both efficiency and accuracy by transforming image data into a compact one-dimensional sequence.Experimental results,including five-fold cross-validation,demonstrate that the model using gated recurrent units(GRU)achieved an accuracy of 99.81%on the first dataset and 99.59%in the second dataset with a computation time of only 7.433 ms per sample.A real-time prototype was also developed to demonstrate deployment feasibility.These results highlight the potential of the proposed approach for practical,real-time QR code threat detection.
基金supported by the National Natural Science Foundation of China (21971185 and 52173177)the Natural Science Foundation of Jiangsu Province (BK20230010 and BK20221362)+4 种基金the Science and Technology Support Program of Jiangsu Province (TJ-2022-002)funded by the Collaborative Innovation Center of Suzhou Nano Science&Technologythe 111 Projectthe Joint International Research Laboratory of Carbon-Based Functional Materials and DevicesSoochow University Tang Scholar。
