The effects of real-time traffic information system(RTTIS)on traffic performance under parallel,grid and ring networks were investigated.The simulation results show that the effects of the proportion of RTTIS usage de...The effects of real-time traffic information system(RTTIS)on traffic performance under parallel,grid and ring networks were investigated.The simulation results show that the effects of the proportion of RTTIS usage depend on the road network structures.For traffic on a parallel network,the performance of groups with and without RTTIS level is improved when the proportion of vehicles using RTTIS is greater than 0 and less than 30%,and a proportion of RTTIS usage higher than 90%would actually deteriorate the performance.For both grid and ring networks,a higher proportion of RTTIS usage always improves the performance of groups with and without RTTIS.For all three network structures,vehicles without RTTIS benefit from some proportion of RTTIS usage in a system.展开更多
Image captioning has seen significant research efforts over the last decade.The goal is to generate meaningful semantic sentences that describe visual content depicted in photographs and are syntactically accurate.Man...Image captioning has seen significant research efforts over the last decade.The goal is to generate meaningful semantic sentences that describe visual content depicted in photographs and are syntactically accurate.Many real-world applications rely on image captioning,such as helping people with visual impairments to see their surroundings.To formulate a coherent and relevant textual description,computer vision techniques are utilized to comprehend the visual content within an image,followed by natural language processing methods.Numerous approaches and models have been developed to deal with this multifaceted problem.Several models prove to be stateof-the-art solutions in this field.This work offers an exclusive perspective emphasizing the most critical strategies and techniques for enhancing image caption generation.Rather than reviewing all previous image captioning work,we analyze various techniques that significantly improve image caption generation and achieve significant performance improvements,including encompassing image captioning with visual attention methods,exploring semantic information types in captions,and employing multi-caption generation techniques.Further,advancements such as neural architecture search,few-shot learning,multi-phase learning,and cross-modal embedding within image caption networks are examined for their transformative effects.The comprehensive quantitative analysis conducted in this study identifies cutting-edgemethodologies and sheds light on their profound impact,driving forward the forefront of image captioning technology.展开更多
Enhancing website security is crucial to combat malicious activities,and CAPTCHA(Completely Automated Public Turing tests to tell Computers and Humans Apart)has become a key method to distinguish humans from bots.Whil...Enhancing website security is crucial to combat malicious activities,and CAPTCHA(Completely Automated Public Turing tests to tell Computers and Humans Apart)has become a key method to distinguish humans from bots.While text-based CAPTCHAs are designed to challenge machines while remaining human-readable,recent advances in deep learning have enabled models to recognize them with remarkable efficiency.In this regard,we propose a novel two-layer visual attention framework for CAPTCHA recognition that builds on traditional attention mechanisms by incorporating Guided Visual Attention(GVA),which sharpens focus on relevant visual features.We have specifically adapted the well-established image captioning task to address this need.Our approach utilizes the first-level attention module as guidance to the second-level attention component,incorporating two LSTM(Long Short-Term Memory)layers to enhance CAPTCHA recognition.Our extensive evaluation across four diverse datasets—Weibo,BoC(Bank of China),Gregwar,and Captcha 0.3—shows the adaptability and efficacy of our method.Our approach demonstrated impressive performance,achieving an accuracy of 96.70%for BoC and 95.92%for Webo.These results underscore the effectiveness of our method in accurately recognizing and processing CAPTCHA datasets,showcasing its robustness,reliability,and ability to handle varied challenges in CAPTCHA recognition.展开更多
Improving website security to prevent malicious online activities is crucial,and CAPTCHA(Completely Automated Public Turing test to tell Computers and Humans Apart)has emerged as a key strategy for distinguishing huma...Improving website security to prevent malicious online activities is crucial,and CAPTCHA(Completely Automated Public Turing test to tell Computers and Humans Apart)has emerged as a key strategy for distinguishing human users from automated bots.Text-based CAPTCHAs,designed to be easily decipherable by humans yet challenging for machines,are a common form of this verification.However,advancements in deep learning have facilitated the creation of models adept at recognizing these text-based CAPTCHAs with surprising efficiency.In our comprehensive investigation into CAPTCHA recognition,we have tailored the renowned UpDown image captioning model specifically for this purpose.Our approach innovatively combines an encoder to extract both global and local features,significantly boosting the model’s capability to identify complex details within CAPTCHA images.For the decoding phase,we have adopted a refined attention mechanism,integrating enhanced visual attention with dual layers of Long Short-Term Memory(LSTM)networks to elevate CAPTCHA recognition accuracy.Our rigorous testing across four varied datasets,including those from Weibo,BoC,Gregwar,and Captcha 0.3,demonstrates the versatility and effectiveness of our method.The results not only highlight the efficiency of our approach but also offer profound insights into its applicability across different CAPTCHA types,contributing to a deeper understanding of CAPTCHA recognition technology.展开更多
Techniques in deep learning have significantly boosted the accuracy and productivity of computer vision segmentation tasks.This article offers an intriguing architecture for semantic,instance,and panoptic segmentation...Techniques in deep learning have significantly boosted the accuracy and productivity of computer vision segmentation tasks.This article offers an intriguing architecture for semantic,instance,and panoptic segmentation using EfficientNet-B7 and Bidirectional Feature Pyramid Networks(Bi-FPN).When implemented in place of the EfficientNet-B5 backbone,EfficientNet-B7 strengthens the model’s feature extraction capabilities and is far more appropriate for real-world applications.By ensuring superior multi-scale feature fusion,Bi-FPN integration enhances the segmentation of complex objects across various urban environments.The design suggested is examined on rigorous datasets,encompassing Cityscapes,Common Objects in Context,KITTI Karlsruhe Institute of Technology and Toyota Technological Institute,and Indian Driving Dataset,which replicate numerous real-world driving conditions.During extensive training,validation,and testing,the model showcases major gains in segmentation accuracy and surpasses state-of-the-art performance in semantic,instance,and panoptic segmentation tasks.Outperforming present methods,the recommended approach generates noteworthy gains in Panoptic Quality:+0.4%on Cityscapes,+0.2%on COCO,+1.7%on KITTI,and+0.4%on IDD.These changes show just how efficient it is in various driving circumstances and datasets.This study emphasizes the potential of EfficientNet-B7 and Bi-FPN to provide dependable,high-precision segmentation in computer vision applications,primarily autonomous driving.The research results suggest that this framework efficiently tackles the constraints of practical situations while delivering a robust solution for high-performance tasks involving segmentation.展开更多
从ISI Web of Knowledge和Science Direct数据库收集1987-2009年所报道的大气污染与新生儿低体重风险相关研究,按"母体大气污染暴露所涉及的污染物"、"暴露评估方法"和"暴露风险窗口识别"进行分类总结。...从ISI Web of Knowledge和Science Direct数据库收集1987-2009年所报道的大气污染与新生儿低体重风险相关研究,按"母体大气污染暴露所涉及的污染物"、"暴露评估方法"和"暴露风险窗口识别"进行分类总结。结果表明:(1)母体妊娠期大气颗粒物、CO和SO2暴露很可能会导致其新生儿低体重风险上升;但母体妊娠期O3和氮氧化物暴露造成其新生儿低体重风险上升的可能性较小;(2)当前国内外主流的评估母体妊娠期大气污染暴露的方法为大气质量监测法,暴露评估方法选择差异会对研究结果产生影响;(3)"整个妊娠期"是母体妊娠期间大气污染暴露的关键风险窗口,但对不同大气污染物的暴露风险窗口存在分歧。因此,在当前母体大气污染暴露评估方法存在缺陷和母体大气污染暴露风险窗口尚未明确的条件下,现有研究无法阐明母体妊娠期大气污染暴露对其新生儿低体重风险的影响机制。展开更多
Using degree distribution to assess network vulnerability represents a promising direction of network analysis.However,the traditional degree distribution model is inadequate for analyzing the vulnerability of spatial...Using degree distribution to assess network vulnerability represents a promising direction of network analysis.However,the traditional degree distribution model is inadequate for analyzing the vulnerability of spatial networks because it does not take into consideration the geographical aspects of spatial networks.This paper proposes a spatially weighted degree model in which both the functional class and the length of network links are considered to be important factors for determining the node degrees of spatial networks.A weight coefficient is used in this new model to account for the contribution of each factor to the node degree.The proposed model is compared with the traditional degree model and an accessibility-based vulnerability model in the vulnerabil-ity analysis of a highway network.Experiment results indicate that,although node degrees of spatial networks derived from the tra-ditional degree model follow a random distribution,node degrees determined by the spatially weighted model exhibit a scale-free distribution,which is a common characteristic of robust networks.Compared to the accessibility-based model,the proposed model has similar performance in identifying critical nodes but with higher computational efficiency and better ability to reveal the overall vulnerability of a spatial network.展开更多
The increase in southern China summer rainfall around 1993 was accompanied by an increase in tropical cyclones that formed in the South China Sea. This study documents the connection of these two features. Our analysi...The increase in southern China summer rainfall around 1993 was accompanied by an increase in tropical cyclones that formed in the South China Sea. This study documents the connection of these two features. Our analysis shows that the contribution of tropical cyclones that formed in the South China Sea to southern China summer rainfall experienced a significant increase around 1993, in particular, along the coast and in the heavy rain category. The number of tropical cyclones that formed in the western North Pacific and entered the South China Sea decreased, and their contribution to summer rainfall was reduced in eastern part of southern China （but statistically insignificant）. The increase in tropical cyclone-induced rainfall contributed up to -30＆ of the total rainfall increase along the coastal regions. The increase of tropical cyclones in the South China Sea appears to be related to an increase in local sea surface temperature.展开更多
This study explores the characteristics of high temperature anomalies over eastern China and associated influencing factors using observations and model outputs.Results show that more long-duration（over 8 days） high...This study explores the characteristics of high temperature anomalies over eastern China and associated influencing factors using observations and model outputs.Results show that more long-duration（over 8 days） high temperature events occur over the middle and lower reaches of the Yangtze River Valley（YRV） than over the surrounding regions,and control most of the interannual variation of summer mean temperature in situ.The synergistic effect of summer precipitation over the South China Sea（SCS） region（18°–27°N,115°–124°E） and the northwestern India and Arabian Sea（IAS） region（18°–27°N,60°–80°E） contributes more significantly to the variation of summer YRV temperature,relative to the respective SCS or IAS precipitation anomaly.More precipitation（enhanced condensational heating） over the SCS region strengthens the western Pacific subtropical high（WPSH） and simultaneously weakens the westerly trough over the east coast of Asia,and accordingly results in associated high temperature anomalies over the YRV region through stimulating an East Asia–Pacific（EAP） pattern.More precipitation over the IAS region further adjusts the variations of the WPSH and westerly trough,and eventually reinforces high temperature anomalies over the YRV region.Furthermore,the condensational heating related to more IAS precipitation can adjust upper-tropospheric easterly anomalies over the YRV region by exciting a circumglobal teleconnection,inducing cold horizontal temperature advection and related anomalous descent,which is also conducive to the YRV high temperature anomalies.The reproduction of the above association in the model results indicates that the above results can be explained both statistically and dynamically.展开更多
In machine learning,sentiment analysis is a technique to find and analyze the sentiments hidden in the text.For sentiment analysis,annotated data is a basic requirement.Generally,this data is manually annotated.Manual...In machine learning,sentiment analysis is a technique to find and analyze the sentiments hidden in the text.For sentiment analysis,annotated data is a basic requirement.Generally,this data is manually annotated.Manual annotation is time consuming,costly and laborious process.To overcome these resource constraints this research has proposed a fully automated annotation technique for aspect level sentiment analysis.Dataset is created from the reviews of ten most popular songs on YouTube.Reviews of five aspects—voice,video,music,lyrics and song,are extracted.An N-Gram based technique is proposed.Complete dataset consists of 369436 reviews that took 173.53 s to annotate using the proposed technique while this dataset might have taken approximately 2.07 million seconds(575 h)if it was annotated manually.For the validation of the proposed technique,a sub-dataset—Voice,is annotated manually as well as with the proposed technique.Cohen’s Kappa statistics is used to evaluate the degree of agreement between the two annotations.The high Kappa value(i.e.,0.9571%)shows the high level of agreement between the two.This validates that the quality of annotation of the proposed technique is as good as manual annotation even with far less computational cost.This research also contributes in consolidating the guidelines for the manual annotation process.展开更多
Machine learning(ML)practices such as classification have played a very important role in classifying diseases in medical science.Since medical science is a sensitive field,the pre-processing of medical data requires ...Machine learning(ML)practices such as classification have played a very important role in classifying diseases in medical science.Since medical science is a sensitive field,the pre-processing of medical data requires careful handling to make quality clinical decisions.Generally,medical data is considered high-dimensional and complex data that contains many irrelevant and redundant features.These factors indirectly upset the disease prediction and classification accuracy of any ML model.To address this issue,various data pre-processing methods called Feature Selection(FS)techniques have been presented in the literature.However,the majority of such techniques frequently suffer from local minima issues due to large solution space.Thus,this study has proposed a novel wrapper-based Sand Cat SwarmOptimization(SCSO)technique as an FS approach to find optimum features from ten benchmark medical datasets.The SCSO algorithm replicates the hunting and searching strategies of the sand cat while having the advantage of avoiding local optima and finding the ideal solution with minimal control variables.Moreover,K-Nearest Neighbor(KNN)classifier was used to evaluate the effectiveness of the features identified by the proposed SCSO algorithm.The performance of the proposed SCSO algorithm was compared with six state-of-the-art and recent wrapper-based optimization algorithms using the validation metrics of classification accuracy,optimum feature size,and computational cost in seconds.The simulation results on the benchmark medical datasets revealed that the proposed SCSO-KNN approach has outperformed comparative algorithms with an average classification accuracy of 93.96%by selecting 14.2 features within 1.91 s.Additionally,the Wilcoxon rank test was used to perform the significance analysis between the proposed SCSOKNN method and six other algorithms for a p-value less than 5.00E-02.The findings revealed that the proposed algorithm produces better outcomes with an average p-value of 1.82E-02.Moreover,potential future directions are also suggested as a result of the study’s promising findings.展开更多
A tri-port MIMO antenna designed for Micro/Pico-Cell application is proposed.It is based on printed elements with X-shaped arms,which are oriented to 0°,120° and240° in the azimuth plane.The arms of the...A tri-port MIMO antenna designed for Micro/Pico-Cell application is proposed.It is based on printed elements with X-shaped arms,which are oriented to 0°,120° and240° in the azimuth plane.The arms of these elements are connected,with which a selfdecoupled structure is formed.The mutual coupling between adjacent elements is below-15 dB.Meanwhile,it size is compact and bidirectional radiation patterns with around 4dBi Gain and 92° 3dB beam width is achieved,which can provide good pattern diversity and full azimuth coverage in real applications.展开更多
Trust is one of the core components of any ad hoc network security system.Trust management(TM)has always been a challenging issue in a vehicular network.One such developing network is the Internet of vehicles(IoV),whi...Trust is one of the core components of any ad hoc network security system.Trust management(TM)has always been a challenging issue in a vehicular network.One such developing network is the Internet of vehicles(IoV),which is expected to be an essential part of smart cities.IoV originated from the merger of Vehicular ad hoc networks(VANET)and the Internet of things(IoT).Security is one of the main barriers in the on-road IoV implementation.Existing security standards are insufficient to meet the extremely dynamic and rapidly changing IoV requirements.Trust plays a vital role in ensuring security,especially during vehicle to vehicle communication.Vehicular networks,having a unique nature among other wireless ad hoc networks,require dedicated efforts to develop trust protocols.Current TM schemes are inflexible and static.Predefined scenarios and limited parameters are the basis for existing TM models that are not suitable for vehicle networks.The vehicular network requires agile and adaptive solutions to ensure security,especially when it comes to critical messages.The vehicle network’s wireless nature increases its attack surface and exposes the network to numerous security threats.Moreover,internet involvement makes it more vulnerable to cyberattacks.The proposed TM framework is based on context-based cognition and machine learning to be best suited to IoV dynamics.Machine learning is the best solution to utilize the big data produced by vehicle sensors.To handle the uncertainty Bayesian machine learning statistical model is used.The proposed framework can adapt scenarios dynamically and infer using the maximum possible parameter available.The results indicated better performance than existing TM methods.Furthermore,for future work,a high-level machine learning model is proposed.展开更多
Because mining complete set of frequent patterns from dense database could be impractical, an interesting alternative has been proposed recently. Instead of mining the complete set of frequent patterns, the new model ...Because mining complete set of frequent patterns from dense database could be impractical, an interesting alternative has been proposed recently. Instead of mining the complete set of frequent patterns, the new model only finds out the maximal frequent patterns, which can generate all frequent patterns. FP-growth algorithm is one of the most efficient frequent-pattern mining methods published so far. However, because FP-tree and conditional FP-trees must be two-way traversable, a great deal memory is needed in process of mining. This paper proposes an efficient algorithm Unid_FP-Max for mining maximal frequent patterns based on unidirectional FP-tree. Because of generation method of unidirectional FP-tree and conditional unidirectional FP-trees, the algorithm reduces the space consumption to the fullest extent. With the development of two techniques: single path pruning and header table pruning which can cut down many conditional unidirectional FP-trees generated recursively in mining process, Unid_FP-Max further lowers the expense of time and space.展开更多
This paper has investigated quantum teleportation of even and odd coherent states in terms of the EPR entanglement states for continuous variables. It discusses the relationship between the fidelity and the entangleme...This paper has investigated quantum teleportation of even and odd coherent states in terms of the EPR entanglement states for continuous variables. It discusses the relationship between the fidelity and the entanglement of EPR states, which is characterized by the degree of squeezing and the gain of classical channels. It shows that the quality of teleporting quantum states also depends on the characteristics of the states themselves. The properties of teleporting even and odd coherent states at different intensities are investigated. The difference of teleporting two such kinds of quantum states are analysed based on the quantum distance function.展开更多
The process of selecting features or reducing dimensionality can be viewed as a multi-objective minimization problem in which both the number of features and error rate must be minimized.While it is a multi-objective ...The process of selecting features or reducing dimensionality can be viewed as a multi-objective minimization problem in which both the number of features and error rate must be minimized.While it is a multi-objective problem,current methods tend to treat feature selection as a single-objective optimization task.This paper presents enhanced multi-objective grey wolf optimizer with Lévy flight and mutation phase(LMuMOGWO)for tackling feature selection problems.The proposed approach integrates two effective operators into the existing Multi-objective Grey Wolf optimizer(MOGWO):a Lévy flight and a mutation operator.The Lévy flight,a type of random walk with jump size determined by the Lévy distribution,enhances the global search capability of MOGWO,with the objective of maximizing classification accuracy while minimizing the number of selected features.The mutation operator is integrated to add more informative features that can assist in enhancing classification accuracy.As feature selection is a binary problem,the continuous search space is converted into a binary space using the sigmoid function.To evaluate the classification performance of the selected feature subset,the proposed approach employs a wrapper-based Artificial Neural Network(ANN).The effectiveness of the LMuMOGWO is validated on 12 conventional UCI benchmark datasets and compared with two existing variants of MOGWO,BMOGWO-S(based sigmoid),BMOGWO-V(based tanh)as well as Non-dominated Sorting Genetic Algorithm II(NSGA-II)and Multi-objective Particle Swarm Optimization(BMOPSO).The results demonstrate that the proposed LMuMOGWO approach is capable of successfully evolving and improving a set of randomly generated solutions for a given optimization problem.Moreover,the proposed approach outperforms existing approaches in most cases in terms of classification error rate,feature reduction,and computational cost.展开更多
We investigate a system described by a conservative and a dissipative map concatenation. A fat fractal forbidden net, induced by interaction between discontinuous and noninvertible properties, introduces rippled-like ...We investigate a system described by a conservative and a dissipative map concatenation. A fat fractal forbidden net, induced by interaction between discontinuous and noninvertible properties, introduces rippled-like attraction basins of two periodic attractors. Small areas, which serve as escaping holes of a new type of crisis, are dominated by conventional strong dissipation and are bounded by the forbidden region, but only in the vicinity of each periodic point. Based on this understanding, the scaling behaviour of the averaged lifetime of the crisis is analytically and numerically determined to be （τ） ∝ （b-b0）^γ, where b denotes the control parameter, bo denotes its critical threshold, and γ≌-1.5.展开更多
文摘The effects of real-time traffic information system(RTTIS)on traffic performance under parallel,grid and ring networks were investigated.The simulation results show that the effects of the proportion of RTTIS usage depend on the road network structures.For traffic on a parallel network,the performance of groups with and without RTTIS level is improved when the proportion of vehicles using RTTIS is greater than 0 and less than 30%,and a proportion of RTTIS usage higher than 90%would actually deteriorate the performance.For both grid and ring networks,a higher proportion of RTTIS usage always improves the performance of groups with and without RTTIS.For all three network structures,vehicles without RTTIS benefit from some proportion of RTTIS usage in a system.
基金supported by the National Natural Science Foundation of China(Nos.U22A2034,62177047)High Caliber Foreign Experts Introduction Plan funded by MOST,and Central South University Research Programme of Advanced Interdisciplinary Studies(No.2023QYJC020).
文摘Image captioning has seen significant research efforts over the last decade.The goal is to generate meaningful semantic sentences that describe visual content depicted in photographs and are syntactically accurate.Many real-world applications rely on image captioning,such as helping people with visual impairments to see their surroundings.To formulate a coherent and relevant textual description,computer vision techniques are utilized to comprehend the visual content within an image,followed by natural language processing methods.Numerous approaches and models have been developed to deal with this multifaceted problem.Several models prove to be stateof-the-art solutions in this field.This work offers an exclusive perspective emphasizing the most critical strategies and techniques for enhancing image caption generation.Rather than reviewing all previous image captioning work,we analyze various techniques that significantly improve image caption generation and achieve significant performance improvements,including encompassing image captioning with visual attention methods,exploring semantic information types in captions,and employing multi-caption generation techniques.Further,advancements such as neural architecture search,few-shot learning,multi-phase learning,and cross-modal embedding within image caption networks are examined for their transformative effects.The comprehensive quantitative analysis conducted in this study identifies cutting-edgemethodologies and sheds light on their profound impact,driving forward the forefront of image captioning technology.
基金supported by the National Natural Science Foundation of China(Nos.U22A2034,62177047)High Caliber Foreign Experts Introduction Plan funded by MOST,and Central South University Research Programme of Advanced Interdisciplinary Studies(No.2023QYJC020).
文摘Enhancing website security is crucial to combat malicious activities,and CAPTCHA(Completely Automated Public Turing tests to tell Computers and Humans Apart)has become a key method to distinguish humans from bots.While text-based CAPTCHAs are designed to challenge machines while remaining human-readable,recent advances in deep learning have enabled models to recognize them with remarkable efficiency.In this regard,we propose a novel two-layer visual attention framework for CAPTCHA recognition that builds on traditional attention mechanisms by incorporating Guided Visual Attention(GVA),which sharpens focus on relevant visual features.We have specifically adapted the well-established image captioning task to address this need.Our approach utilizes the first-level attention module as guidance to the second-level attention component,incorporating two LSTM(Long Short-Term Memory)layers to enhance CAPTCHA recognition.Our extensive evaluation across four diverse datasets—Weibo,BoC(Bank of China),Gregwar,and Captcha 0.3—shows the adaptability and efficacy of our method.Our approach demonstrated impressive performance,achieving an accuracy of 96.70%for BoC and 95.92%for Webo.These results underscore the effectiveness of our method in accurately recognizing and processing CAPTCHA datasets,showcasing its robustness,reliability,and ability to handle varied challenges in CAPTCHA recognition.
基金supported by the National Natural Science Foundation of China(Nos.U22A2034,62177047)High Caliber Foreign Experts Introduction Plan funded by MOST,and Central South University Research Programme of Advanced Interdisciplinary Studies(No.2023QYJC020).
文摘Improving website security to prevent malicious online activities is crucial,and CAPTCHA(Completely Automated Public Turing test to tell Computers and Humans Apart)has emerged as a key strategy for distinguishing human users from automated bots.Text-based CAPTCHAs,designed to be easily decipherable by humans yet challenging for machines,are a common form of this verification.However,advancements in deep learning have facilitated the creation of models adept at recognizing these text-based CAPTCHAs with surprising efficiency.In our comprehensive investigation into CAPTCHA recognition,we have tailored the renowned UpDown image captioning model specifically for this purpose.Our approach innovatively combines an encoder to extract both global and local features,significantly boosting the model’s capability to identify complex details within CAPTCHA images.For the decoding phase,we have adopted a refined attention mechanism,integrating enhanced visual attention with dual layers of Long Short-Term Memory(LSTM)networks to elevate CAPTCHA recognition accuracy.Our rigorous testing across four varied datasets,including those from Weibo,BoC,Gregwar,and Captcha 0.3,demonstrates the versatility and effectiveness of our method.The results not only highlight the efficiency of our approach but also offer profound insights into its applicability across different CAPTCHA types,contributing to a deeper understanding of CAPTCHA recognition technology.
文摘Techniques in deep learning have significantly boosted the accuracy and productivity of computer vision segmentation tasks.This article offers an intriguing architecture for semantic,instance,and panoptic segmentation using EfficientNet-B7 and Bidirectional Feature Pyramid Networks(Bi-FPN).When implemented in place of the EfficientNet-B5 backbone,EfficientNet-B7 strengthens the model’s feature extraction capabilities and is far more appropriate for real-world applications.By ensuring superior multi-scale feature fusion,Bi-FPN integration enhances the segmentation of complex objects across various urban environments.The design suggested is examined on rigorous datasets,encompassing Cityscapes,Common Objects in Context,KITTI Karlsruhe Institute of Technology and Toyota Technological Institute,and Indian Driving Dataset,which replicate numerous real-world driving conditions.During extensive training,validation,and testing,the model showcases major gains in segmentation accuracy and surpasses state-of-the-art performance in semantic,instance,and panoptic segmentation tasks.Outperforming present methods,the recommended approach generates noteworthy gains in Panoptic Quality:+0.4%on Cityscapes,+0.2%on COCO,+1.7%on KITTI,and+0.4%on IDD.These changes show just how efficient it is in various driving circumstances and datasets.This study emphasizes the potential of EfficientNet-B7 and Bi-FPN to provide dependable,high-precision segmentation in computer vision applications,primarily autonomous driving.The research results suggest that this framework efficiently tackles the constraints of practical situations while delivering a robust solution for high-performance tasks involving segmentation.
文摘从ISI Web of Knowledge和Science Direct数据库收集1987-2009年所报道的大气污染与新生儿低体重风险相关研究,按"母体大气污染暴露所涉及的污染物"、"暴露评估方法"和"暴露风险窗口识别"进行分类总结。结果表明:(1)母体妊娠期大气颗粒物、CO和SO2暴露很可能会导致其新生儿低体重风险上升;但母体妊娠期O3和氮氧化物暴露造成其新生儿低体重风险上升的可能性较小;(2)当前国内外主流的评估母体妊娠期大气污染暴露的方法为大气质量监测法,暴露评估方法选择差异会对研究结果产生影响;(3)"整个妊娠期"是母体妊娠期间大气污染暴露的关键风险窗口,但对不同大气污染物的暴露风险窗口存在分歧。因此,在当前母体大气污染暴露评估方法存在缺陷和母体大气污染暴露风险窗口尚未明确的条件下,现有研究无法阐明母体妊娠期大气污染暴露对其新生儿低体重风险的影响机制。
基金Supported by the Institute of Crustal Dynamics Funds(No.ZDJ2009‐01,No.ZDJ2007‐13)
文摘Using degree distribution to assess network vulnerability represents a promising direction of network analysis.However,the traditional degree distribution model is inadequate for analyzing the vulnerability of spatial networks because it does not take into consideration the geographical aspects of spatial networks.This paper proposes a spatially weighted degree model in which both the functional class and the length of network links are considered to be important factors for determining the node degrees of spatial networks.A weight coefficient is used in this new model to account for the contribution of each factor to the node degree.The proposed model is compared with the traditional degree model and an accessibility-based vulnerability model in the vulnerabil-ity analysis of a highway network.Experiment results indicate that,although node degrees of spatial networks derived from the tra-ditional degree model follow a random distribution,node degrees determined by the spatially weighted model exhibit a scale-free distribution,which is a common characteristic of robust networks.Compared to the accessibility-based model,the proposed model has similar performance in identifying critical nodes but with higher computational efficiency and better ability to reveal the overall vulnerability of a spatial network.
基金supported by the National Key Basic Research Program of China (GrantNo. 2009CB421404)the National Natural Science Foundation of China (Grant No. 40730951)+2 种基金the Fundamental Research Funds for the Central Universities (Grant No.11lgjc10)the National Natural Science Foundation of major international collaborative research project (GrantNo. 40810059005)the support of a Direct Grant of the Chinese University of HongKong (Grant No. 2021090)
文摘The increase in southern China summer rainfall around 1993 was accompanied by an increase in tropical cyclones that formed in the South China Sea. This study documents the connection of these two features. Our analysis shows that the contribution of tropical cyclones that formed in the South China Sea to southern China summer rainfall experienced a significant increase around 1993, in particular, along the coast and in the heavy rain category. The number of tropical cyclones that formed in the western North Pacific and entered the South China Sea decreased, and their contribution to summer rainfall was reduced in eastern part of southern China （but statistically insignificant）. The increase in tropical cyclone-induced rainfall contributed up to -30＆ of the total rainfall increase along the coastal regions. The increase of tropical cyclones in the South China Sea appears to be related to an increase in local sea surface temperature.
基金the support of the National Natural Science Foundation of China(Grant Nos.41375090 and 41375091)the Basic Research Fund of the Chinese Academy of Meteorological Sciences(Grant Nos.2013Z002 and 2015Z001)the support of a Direct Grant of the Chinese University of Hong Kong(Grant No.4052057)
文摘This study explores the characteristics of high temperature anomalies over eastern China and associated influencing factors using observations and model outputs.Results show that more long-duration（over 8 days） high temperature events occur over the middle and lower reaches of the Yangtze River Valley（YRV） than over the surrounding regions,and control most of the interannual variation of summer mean temperature in situ.The synergistic effect of summer precipitation over the South China Sea（SCS） region（18°–27°N,115°–124°E） and the northwestern India and Arabian Sea（IAS） region（18°–27°N,60°–80°E） contributes more significantly to the variation of summer YRV temperature,relative to the respective SCS or IAS precipitation anomaly.More precipitation（enhanced condensational heating） over the SCS region strengthens the western Pacific subtropical high（WPSH） and simultaneously weakens the westerly trough over the east coast of Asia,and accordingly results in associated high temperature anomalies over the YRV region through stimulating an East Asia–Pacific（EAP） pattern.More precipitation over the IAS region further adjusts the variations of the WPSH and westerly trough,and eventually reinforces high temperature anomalies over the YRV region.Furthermore,the condensational heating related to more IAS precipitation can adjust upper-tropospheric easterly anomalies over the YRV region by exciting a circumglobal teleconnection,inducing cold horizontal temperature advection and related anomalous descent,which is also conducive to the YRV high temperature anomalies.The reproduction of the above association in the model results indicates that the above results can be explained both statistically and dynamically.
文摘In machine learning,sentiment analysis is a technique to find and analyze the sentiments hidden in the text.For sentiment analysis,annotated data is a basic requirement.Generally,this data is manually annotated.Manual annotation is time consuming,costly and laborious process.To overcome these resource constraints this research has proposed a fully automated annotation technique for aspect level sentiment analysis.Dataset is created from the reviews of ten most popular songs on YouTube.Reviews of five aspects—voice,video,music,lyrics and song,are extracted.An N-Gram based technique is proposed.Complete dataset consists of 369436 reviews that took 173.53 s to annotate using the proposed technique while this dataset might have taken approximately 2.07 million seconds(575 h)if it was annotated manually.For the validation of the proposed technique,a sub-dataset—Voice,is annotated manually as well as with the proposed technique.Cohen’s Kappa statistics is used to evaluate the degree of agreement between the two annotations.The high Kappa value(i.e.,0.9571%)shows the high level of agreement between the two.This validates that the quality of annotation of the proposed technique is as good as manual annotation even with far less computational cost.This research also contributes in consolidating the guidelines for the manual annotation process.
基金This research was supported by a Researchers Supporting Project Number(RSP2021/309)King Saud University,Riyadh,Saudi Arabia.The authors wish to acknowledge Yayasan Universiti Teknologi Petronas for supporting this work through the research grant(015LC0-308).
文摘Machine learning(ML)practices such as classification have played a very important role in classifying diseases in medical science.Since medical science is a sensitive field,the pre-processing of medical data requires careful handling to make quality clinical decisions.Generally,medical data is considered high-dimensional and complex data that contains many irrelevant and redundant features.These factors indirectly upset the disease prediction and classification accuracy of any ML model.To address this issue,various data pre-processing methods called Feature Selection(FS)techniques have been presented in the literature.However,the majority of such techniques frequently suffer from local minima issues due to large solution space.Thus,this study has proposed a novel wrapper-based Sand Cat SwarmOptimization(SCSO)technique as an FS approach to find optimum features from ten benchmark medical datasets.The SCSO algorithm replicates the hunting and searching strategies of the sand cat while having the advantage of avoiding local optima and finding the ideal solution with minimal control variables.Moreover,K-Nearest Neighbor(KNN)classifier was used to evaluate the effectiveness of the features identified by the proposed SCSO algorithm.The performance of the proposed SCSO algorithm was compared with six state-of-the-art and recent wrapper-based optimization algorithms using the validation metrics of classification accuracy,optimum feature size,and computational cost in seconds.The simulation results on the benchmark medical datasets revealed that the proposed SCSO-KNN approach has outperformed comparative algorithms with an average classification accuracy of 93.96%by selecting 14.2 features within 1.91 s.Additionally,the Wilcoxon rank test was used to perform the significance analysis between the proposed SCSOKNN method and six other algorithms for a p-value less than 5.00E-02.The findings revealed that the proposed algorithm produces better outcomes with an average p-value of 1.82E-02.Moreover,potential future directions are also suggested as a result of the study’s promising findings.
基金This work is supported by the National Basic Research Program of China under Contract 2013CB329002, in part by the National High Technology Research and Development Program of China （863 Program） under Contract 2011AA010202, the National Natural Science Foundation of China under Contract 61271135, the National Science and Technology Major Project of the Ministry of Science and Technology of China 2013ZX03003008- 002.
文摘A tri-port MIMO antenna designed for Micro/Pico-Cell application is proposed.It is based on printed elements with X-shaped arms,which are oriented to 0°,120° and240° in the azimuth plane.The arms of these elements are connected,with which a selfdecoupled structure is formed.The mutual coupling between adjacent elements is below-15 dB.Meanwhile,it size is compact and bidirectional radiation patterns with around 4dBi Gain and 92° 3dB beam width is achieved,which can provide good pattern diversity and full azimuth coverage in real applications.
基金The work is partially funded by CGS Universiti Teknologi PETRONAS,Malaysia.
文摘Trust is one of the core components of any ad hoc network security system.Trust management(TM)has always been a challenging issue in a vehicular network.One such developing network is the Internet of vehicles(IoV),which is expected to be an essential part of smart cities.IoV originated from the merger of Vehicular ad hoc networks(VANET)and the Internet of things(IoT).Security is one of the main barriers in the on-road IoV implementation.Existing security standards are insufficient to meet the extremely dynamic and rapidly changing IoV requirements.Trust plays a vital role in ensuring security,especially during vehicle to vehicle communication.Vehicular networks,having a unique nature among other wireless ad hoc networks,require dedicated efforts to develop trust protocols.Current TM schemes are inflexible and static.Predefined scenarios and limited parameters are the basis for existing TM models that are not suitable for vehicle networks.The vehicular network requires agile and adaptive solutions to ensure security,especially when it comes to critical messages.The vehicle network’s wireless nature increases its attack surface and exposes the network to numerous security threats.Moreover,internet involvement makes it more vulnerable to cyberattacks.The proposed TM framework is based on context-based cognition and machine learning to be best suited to IoV dynamics.Machine learning is the best solution to utilize the big data produced by vehicle sensors.To handle the uncertainty Bayesian machine learning statistical model is used.The proposed framework can adapt scenarios dynamically and infer using the maximum possible parameter available.The results indicated better performance than existing TM methods.Furthermore,for future work,a high-level machine learning model is proposed.
基金Supported by the National Natural Science Foundation of China ( No.60474022)Henan Innovation Project for University Prominent Research Talents (No.2007KYCX018)
文摘Because mining complete set of frequent patterns from dense database could be impractical, an interesting alternative has been proposed recently. Instead of mining the complete set of frequent patterns, the new model only finds out the maximal frequent patterns, which can generate all frequent patterns. FP-growth algorithm is one of the most efficient frequent-pattern mining methods published so far. However, because FP-tree and conditional FP-trees must be two-way traversable, a great deal memory is needed in process of mining. This paper proposes an efficient algorithm Unid_FP-Max for mining maximal frequent patterns based on unidirectional FP-tree. Because of generation method of unidirectional FP-tree and conditional unidirectional FP-trees, the algorithm reduces the space consumption to the fullest extent. With the development of two techniques: single path pruning and header table pruning which can cut down many conditional unidirectional FP-trees generated recursively in mining process, Unid_FP-Max further lowers the expense of time and space.
基金Project supported by the National Natural Science Foundation of China （Grant Nos 10434080, 10374062, 60578018）, NSFC-RFBR Joint Program, Research Funds for Returned Scholar Abroad from Shanxi Province and also supported by the CFKSTIP （Grant No 705010） and PCSIRT from Ministry of Education of China.
文摘This paper has investigated quantum teleportation of even and odd coherent states in terms of the EPR entanglement states for continuous variables. It discusses the relationship between the fidelity and the entanglement of EPR states, which is characterized by the degree of squeezing and the gain of classical channels. It shows that the quality of teleporting quantum states also depends on the characteristics of the states themselves. The properties of teleporting even and odd coherent states at different intensities are investigated. The difference of teleporting two such kinds of quantum states are analysed based on the quantum distance function.
基金supported by Universiti Teknologi PETRONAS,under the Yayasan Universiti Teknologi PETRONAS (YUTP)Fundamental Research Grant Scheme (YUTPFRG/015LC0-274)support by Researchers Supporting Project Number (RSP-2023/309),King Saud University,Riyadh,Saudi Arabia.
文摘The process of selecting features or reducing dimensionality can be viewed as a multi-objective minimization problem in which both the number of features and error rate must be minimized.While it is a multi-objective problem,current methods tend to treat feature selection as a single-objective optimization task.This paper presents enhanced multi-objective grey wolf optimizer with Lévy flight and mutation phase(LMuMOGWO)for tackling feature selection problems.The proposed approach integrates two effective operators into the existing Multi-objective Grey Wolf optimizer(MOGWO):a Lévy flight and a mutation operator.The Lévy flight,a type of random walk with jump size determined by the Lévy distribution,enhances the global search capability of MOGWO,with the objective of maximizing classification accuracy while minimizing the number of selected features.The mutation operator is integrated to add more informative features that can assist in enhancing classification accuracy.As feature selection is a binary problem,the continuous search space is converted into a binary space using the sigmoid function.To evaluate the classification performance of the selected feature subset,the proposed approach employs a wrapper-based Artificial Neural Network(ANN).The effectiveness of the LMuMOGWO is validated on 12 conventional UCI benchmark datasets and compared with two existing variants of MOGWO,BMOGWO-S(based sigmoid),BMOGWO-V(based tanh)as well as Non-dominated Sorting Genetic Algorithm II(NSGA-II)and Multi-objective Particle Swarm Optimization(BMOPSO).The results demonstrate that the proposed LMuMOGWO approach is capable of successfully evolving and improving a set of randomly generated solutions for a given optimization problem.Moreover,the proposed approach outperforms existing approaches in most cases in terms of classification error rate,feature reduction,and computational cost.
基金Supported by the National Natural Science Foundation of China under Grant No 10275053.
文摘We investigate a system described by a conservative and a dissipative map concatenation. A fat fractal forbidden net, induced by interaction between discontinuous and noninvertible properties, introduces rippled-like attraction basins of two periodic attractors. Small areas, which serve as escaping holes of a new type of crisis, are dominated by conventional strong dissipation and are bounded by the forbidden region, but only in the vicinity of each periodic point. Based on this understanding, the scaling behaviour of the averaged lifetime of the crisis is analytically and numerically determined to be （τ） ∝ （b-b0）^γ, where b denotes the control parameter, bo denotes its critical threshold, and γ≌-1.5.
