As urban landscapes evolve and vehicular volumes soar,traditional traffic monitoring systems struggle to scale,often failing under the complexities of dense,dynamic,and occluded environments.This paper introduces a no...As urban landscapes evolve and vehicular volumes soar,traditional traffic monitoring systems struggle to scale,often failing under the complexities of dense,dynamic,and occluded environments.This paper introduces a novel,unified deep learning framework for vehicle detection,tracking,counting,and classification in aerial imagery designed explicitly for modern smart city infrastructure demands.Our approach begins with adaptive histogram equalization to optimize aerial image clarity,followed by a cutting-edge scene parsing technique using Mask2Former,enabling robust segmentation even in visually congested settings.Vehicle detection leverages the latest YOLOv11 architecture,delivering superior accuracy in aerial contexts by addressing occlusion,scale variance,and fine-grained object differentiation.We incorporate the highly efficient ByteTrack algorithm for tracking,enabling seamless identity preservation across frames.Vehicle counting is achieved through an unsupervised DBSCAN-based method,ensuring adaptability to varying traffic densities.We further introduce a hybrid feature extraction module combining Convolutional Neural Networks(CNNs)with Zernike Moments,capturing both deep semantic and geometric signatures of vehicles.The final classification is powered by NASNet,a neural architecture search-optimized model,ensuring high accuracy across diverse vehicle types and orientations.Extensive evaluations of the VAID benchmark dataset demonstrate the system’s outstanding performance,achieving 96%detection,94%tracking,and 96.4%classification accuracy.On the UAVDT dataset,the system attains 95%detection,93%tracking,and 95%classification accuracy,confirming its robustness across diverse aerial traffic scenarios.These results establish new benchmarks in aerial traffic analysis and validate the framework’s scalability,making it a powerful and adaptable solution for next-generation intelligent transportation systems and urban surveillance.展开更多
This paper presents a unified Unmanned Aerial Vehicle-based(UAV-based)traffic monitoring framework that integrates vehicle detection,tracking,counting,motion prediction,and classification in a modular and co-optimized...This paper presents a unified Unmanned Aerial Vehicle-based(UAV-based)traffic monitoring framework that integrates vehicle detection,tracking,counting,motion prediction,and classification in a modular and co-optimized pipeline.Unlike prior works that address these tasks in isolation,our approach combines You Only Look Once(YOLO)v10 detection,ByteTrack tracking,optical-flow density estimation,Long Short-Term Memory-based(LSTM-based)trajectory forecasting,and hybrid Speeded-Up Robust Feature(SURF)+Gray-Level Co-occurrence Matrix(GLCM)feature engineering with VGG16 classification.Upon the validation across datasets(UAVDT and UAVID)our framework achieved a detection accuracy of 94.2%,and 92.3%detection accuracy when conducting a real-time UAV field validation.Our comprehensive evaluations,including multi-metric analyses,ablation studies,and cross-dataset validations,confirm the framework’s accuracy,efficiency,and generalizability.These results highlight the novelty of integrating complementary methods into a single framework,offering a practical solution for accurate and efficient UAV-based traffic monitoring.展开更多
This study investigates the weak-form efficiency and asymmetric multifractal scaling behavior of rare earth stock indices in the global,U.S.and Chinese markets during the trade war and the COVID-19 period.We examine t...This study investigates the weak-form efficiency and asymmetric multifractal scaling behavior of rare earth stock indices in the global,U.S.and Chinese markets during the trade war and the COVID-19 period.We examine the scaling behavior across overall,upward(bullish),and downward(bearish)market states from 2013 to 2021,employing an asymmetric multifractal detrended fluctuation analysis approach.Our findings indicate asymmetric multifractality in U.S.rare earth stock prices,caused by fat tails and long-range correlations.Weak-form price inefficiency and asymmetry in U.S.rare earth stock prices are prominent during market downturns,such as the trade war and COVID-19 periods.Chinese rare earth stocks demonstrate greater efficiency than U.S.and global stocks;thus,the latter markets provide arbitrage opportunities during upward and downward trends.展开更多
Objective: To evaluate NS1 antigen detection ELISA for the early laboratory diagnosis of dengue virus infection. Methods: The present study was conducted to evaluate the overall positivity of NS1 antigen detection ELI...Objective: To evaluate NS1 antigen detection ELISA for the early laboratory diagnosis of dengue virus infection. Methods: The present study was conducted to evaluate the overall positivity of NS1 antigen detection ELISA and its comparison with viral RNA detection via real time PCR and Ig M antibodies detection by ELISA. Results: A total of 1 270 serum samples were tested 86%(1 097/1 270) were detected positive by one or more than one diagnostic test. Out of 1 270, 64%(807/1 270) were positive by NS1 ELISA and 52%(662/1 270), 51%(646/1 270) were positive by real-time RT-PCR and Ig M ELISA respectively.Conclusions: NS1 antigen detection ELISA is highly suitable diagnostic tools and it also has great value for use in outbreak and epidemic situation.展开更多
Objective:To High light some epidemiological,clinical and diagnostic features of dengue fever during an outbreak and the role of different diagnostic techniques to achieve the highest level of accuracy in results.Meth...Objective:To High light some epidemiological,clinical and diagnostic features of dengue fever during an outbreak and the role of different diagnostic techniques to achieve the highest level of accuracy in results.Methods:Blood samples(n=323) were collected along with epidemiological and clinical data from suspected dengue patients who visited different hospitals in Swat and Mansehra district of Pakistan between May-November 2013 during a dengue outbreak.Samples were tested for the detection of viral nucleic acid by real-lime PCR.non structural protein-1(NS1antigen and IgM antibodies by ELISA.Results:Out of 323 cases with clinical dengue infection,304 were positive by one or more diagnostic parameter:201 samples were positive by real-time PCR,209 were positive by NS1 ELISA and 190 were positive by IgM antibodies.Sensitivities of real-time PCR and NS1 F.LISA were comparable for early diagnosis of dengue virus infection.IgM antibody detection assay was found useful for the diagnosis in the samples collected later than day 5 of onset.Conclusions:The use of real-lime PCR or detection of non stnictural protein NS 1 by ELISA followed by IgM antibodies detection can be recommended for early diagnosis of dengue virus infection with a high level of accuracy.展开更多
The Coronavirus Disease 2019(COVID-19)pandemic poses the worldwide challenges surpassing the boundaries of country,religion,race,and economy.The current benchmark method for the detection of COVID-19 is the reverse tr...The Coronavirus Disease 2019(COVID-19)pandemic poses the worldwide challenges surpassing the boundaries of country,religion,race,and economy.The current benchmark method for the detection of COVID-19 is the reverse transcription polymerase chain reaction(RT-PCR)testing.Nevertheless,this testing method is accurate enough for the diagnosis of COVID-19.However,it is time-consuming,expensive,expert-dependent,and violates social distancing.In this paper,this research proposed an effective multimodality-based and feature fusion-based(MMFF)COVID-19 detection technique through deep neural networks.In multi-modality,we have utilized the cough samples,breathe samples and sound samples of healthy as well as COVID-19 patients from publicly available COSWARA dataset.Extensive set of experimental analyses were performed to evaluate the performance of our proposed approach.Several useful features were extracted from the aforementioned modalities that were then fed as an input to long short-term memory recurrent neural network algorithms for the classification purpose.Extensive set of experimental analyses were performed to evaluate the performance of our proposed approach.The experimental results showed that our proposed approach outperformed compared to four baseline approaches published recently.We believe that our proposed technique will assists potential users to diagnose the COVID-19 without the intervention of any expert in minimum amount of time.展开更多
Background:Dengue virus is the causative agent of dengue fever,a vector borne infection which causes selflimiting to life threatening disease in humans.A sero-epidemiological study was conducted to understand the curr...Background:Dengue virus is the causative agent of dengue fever,a vector borne infection which causes selflimiting to life threatening disease in humans.A sero-epidemiological study was conducted to understand the current epidemiology of dengue virus in Pakistan which is now known as a dengue endemic country after its first reported outbreak in 1994.Methods:To investigate the prevalence of dengue virus in Pakistan during 2009-2014,a total of 9,493 blood samples were screened for the detection of anti-dengue IgM antibodies using ELISA.Clinical and demographic features available with hospital records were reviewed to ascertain mortalities related to dengue hemorrhagic shock syndrome.Results:Out of 9,493 samples tested,37%(3,504)were found positive for anti-dengue IgM antibodies.Of the seropositive cases,73.6%(2,578/3,504)were male and 26.4%(926/3,504)were female.The highest number(382/929;41.1%)of sero-positive cases was observed among the individuals of age group 31-40 years.The highest number of symptomatic cases was reported in October(46%;4,400/9,493),and the highest number of sero-positive cases among symptomatic cases was observed in November(45.7%;806/1,764).Mean annual patient incidence(MAPI)during 2009-2014 in Pakistan remained 0.30 with the highest annual patient incidence(11.03)found in Islamabad.According to the available medical case record,472 dengue related deaths were reported during 2009-2014.Conclusion:The data from earlier reports in Pakistan described the dengue virus incidence from limited areas of the country.Our findings are important considering the testing of clinical samples at a larger scale covering patients of vast geographical regions and warrants timely implementation of dengue vector surveillance and control programs.Trial registration number:It is an epidemiological research study,so trial registration is not required.展开更多
基金funded by the Open Access Initiative of the University of Bremen and the DFG via SuUB BremenThe authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through Large Group Project under grant number(RGP2/367/46)+1 种基金This research is supported and funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R410)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘As urban landscapes evolve and vehicular volumes soar,traditional traffic monitoring systems struggle to scale,often failing under the complexities of dense,dynamic,and occluded environments.This paper introduces a novel,unified deep learning framework for vehicle detection,tracking,counting,and classification in aerial imagery designed explicitly for modern smart city infrastructure demands.Our approach begins with adaptive histogram equalization to optimize aerial image clarity,followed by a cutting-edge scene parsing technique using Mask2Former,enabling robust segmentation even in visually congested settings.Vehicle detection leverages the latest YOLOv11 architecture,delivering superior accuracy in aerial contexts by addressing occlusion,scale variance,and fine-grained object differentiation.We incorporate the highly efficient ByteTrack algorithm for tracking,enabling seamless identity preservation across frames.Vehicle counting is achieved through an unsupervised DBSCAN-based method,ensuring adaptability to varying traffic densities.We further introduce a hybrid feature extraction module combining Convolutional Neural Networks(CNNs)with Zernike Moments,capturing both deep semantic and geometric signatures of vehicles.The final classification is powered by NASNet,a neural architecture search-optimized model,ensuring high accuracy across diverse vehicle types and orientations.Extensive evaluations of the VAID benchmark dataset demonstrate the system’s outstanding performance,achieving 96%detection,94%tracking,and 96.4%classification accuracy.On the UAVDT dataset,the system attains 95%detection,93%tracking,and 95%classification accuracy,confirming its robustness across diverse aerial traffic scenarios.These results establish new benchmarks in aerial traffic analysis and validate the framework’s scalability,making it a powerful and adaptable solution for next-generation intelligent transportation systems and urban surveillance.
基金supported by the IITP(Institute of Information&Communications Technology Planning&Evaluation)-ICAN(ICT Challenge and Advanced Network of HRD)(IITP-2025-RS-2022-00156326,50)grant funded by theKorea government(Ministry of Science and ICT)supported and funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R410)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia。
文摘This paper presents a unified Unmanned Aerial Vehicle-based(UAV-based)traffic monitoring framework that integrates vehicle detection,tracking,counting,motion prediction,and classification in a modular and co-optimized pipeline.Unlike prior works that address these tasks in isolation,our approach combines You Only Look Once(YOLO)v10 detection,ByteTrack tracking,optical-flow density estimation,Long Short-Term Memory-based(LSTM-based)trajectory forecasting,and hybrid Speeded-Up Robust Feature(SURF)+Gray-Level Co-occurrence Matrix(GLCM)feature engineering with VGG16 classification.Upon the validation across datasets(UAVDT and UAVID)our framework achieved a detection accuracy of 94.2%,and 92.3%detection accuracy when conducting a real-time UAV field validation.Our comprehensive evaluations,including multi-metric analyses,ablation studies,and cross-dataset validations,confirm the framework’s accuracy,efficiency,and generalizability.These results highlight the novelty of integrating complementary methods into a single framework,offering a practical solution for accurate and efficient UAV-based traffic monitoring.
文摘This study investigates the weak-form efficiency and asymmetric multifractal scaling behavior of rare earth stock indices in the global,U.S.and Chinese markets during the trade war and the COVID-19 period.We examine the scaling behavior across overall,upward(bullish),and downward(bearish)market states from 2013 to 2021,employing an asymmetric multifractal detrended fluctuation analysis approach.Our findings indicate asymmetric multifractality in U.S.rare earth stock prices,caused by fat tails and long-range correlations.Weak-form price inefficiency and asymmetry in U.S.rare earth stock prices are prominent during market downturns,such as the trade war and COVID-19 periods.Chinese rare earth stocks demonstrate greater efficiency than U.S.and global stocks;thus,the latter markets provide arbitrage opportunities during upward and downward trends.
文摘Objective: To evaluate NS1 antigen detection ELISA for the early laboratory diagnosis of dengue virus infection. Methods: The present study was conducted to evaluate the overall positivity of NS1 antigen detection ELISA and its comparison with viral RNA detection via real time PCR and Ig M antibodies detection by ELISA. Results: A total of 1 270 serum samples were tested 86%(1 097/1 270) were detected positive by one or more than one diagnostic test. Out of 1 270, 64%(807/1 270) were positive by NS1 ELISA and 52%(662/1 270), 51%(646/1 270) were positive by real-time RT-PCR and Ig M ELISA respectively.Conclusions: NS1 antigen detection ELISA is highly suitable diagnostic tools and it also has great value for use in outbreak and epidemic situation.
文摘Objective:To High light some epidemiological,clinical and diagnostic features of dengue fever during an outbreak and the role of different diagnostic techniques to achieve the highest level of accuracy in results.Methods:Blood samples(n=323) were collected along with epidemiological and clinical data from suspected dengue patients who visited different hospitals in Swat and Mansehra district of Pakistan between May-November 2013 during a dengue outbreak.Samples were tested for the detection of viral nucleic acid by real-lime PCR.non structural protein-1(NS1antigen and IgM antibodies by ELISA.Results:Out of 323 cases with clinical dengue infection,304 were positive by one or more diagnostic parameter:201 samples were positive by real-time PCR,209 were positive by NS1 ELISA and 190 were positive by IgM antibodies.Sensitivities of real-time PCR and NS1 F.LISA were comparable for early diagnosis of dengue virus infection.IgM antibody detection assay was found useful for the diagnosis in the samples collected later than day 5 of onset.Conclusions:The use of real-lime PCR or detection of non stnictural protein NS 1 by ELISA followed by IgM antibodies detection can be recommended for early diagnosis of dengue virus infection with a high level of accuracy.
文摘The Coronavirus Disease 2019(COVID-19)pandemic poses the worldwide challenges surpassing the boundaries of country,religion,race,and economy.The current benchmark method for the detection of COVID-19 is the reverse transcription polymerase chain reaction(RT-PCR)testing.Nevertheless,this testing method is accurate enough for the diagnosis of COVID-19.However,it is time-consuming,expensive,expert-dependent,and violates social distancing.In this paper,this research proposed an effective multimodality-based and feature fusion-based(MMFF)COVID-19 detection technique through deep neural networks.In multi-modality,we have utilized the cough samples,breathe samples and sound samples of healthy as well as COVID-19 patients from publicly available COSWARA dataset.Extensive set of experimental analyses were performed to evaluate the performance of our proposed approach.Several useful features were extracted from the aforementioned modalities that were then fed as an input to long short-term memory recurrent neural network algorithms for the classification purpose.Extensive set of experimental analyses were performed to evaluate the performance of our proposed approach.The experimental results showed that our proposed approach outperformed compared to four baseline approaches published recently.We believe that our proposed technique will assists potential users to diagnose the COVID-19 without the intervention of any expert in minimum amount of time.
文摘Background:Dengue virus is the causative agent of dengue fever,a vector borne infection which causes selflimiting to life threatening disease in humans.A sero-epidemiological study was conducted to understand the current epidemiology of dengue virus in Pakistan which is now known as a dengue endemic country after its first reported outbreak in 1994.Methods:To investigate the prevalence of dengue virus in Pakistan during 2009-2014,a total of 9,493 blood samples were screened for the detection of anti-dengue IgM antibodies using ELISA.Clinical and demographic features available with hospital records were reviewed to ascertain mortalities related to dengue hemorrhagic shock syndrome.Results:Out of 9,493 samples tested,37%(3,504)were found positive for anti-dengue IgM antibodies.Of the seropositive cases,73.6%(2,578/3,504)were male and 26.4%(926/3,504)were female.The highest number(382/929;41.1%)of sero-positive cases was observed among the individuals of age group 31-40 years.The highest number of symptomatic cases was reported in October(46%;4,400/9,493),and the highest number of sero-positive cases among symptomatic cases was observed in November(45.7%;806/1,764).Mean annual patient incidence(MAPI)during 2009-2014 in Pakistan remained 0.30 with the highest annual patient incidence(11.03)found in Islamabad.According to the available medical case record,472 dengue related deaths were reported during 2009-2014.Conclusion:The data from earlier reports in Pakistan described the dengue virus incidence from limited areas of the country.Our findings are important considering the testing of clinical samples at a larger scale covering patients of vast geographical regions and warrants timely implementation of dengue vector surveillance and control programs.Trial registration number:It is an epidemiological research study,so trial registration is not required.
