In fire rescue scenarios,traditional manual operations are highly dangerous,as dense smoke,low visibility,extreme heat,and toxic gases not only hinder rescue efficiency but also endanger firefighters’safety.Although ...In fire rescue scenarios,traditional manual operations are highly dangerous,as dense smoke,low visibility,extreme heat,and toxic gases not only hinder rescue efficiency but also endanger firefighters’safety.Although intelligent rescue robots can enter hazardous environments in place of humans,smoke poses major challenges for human detection algorithms.These challenges include the attenuation of visible and infrared signals,complex thermal fields,and interference frombackground objects,all ofwhichmake it difficult to accurately identify trapped individuals.To address this problem,we propose VIF-YOLO,a visible–infrared fusion model for real-time human detection in dense smoke environments.The framework introduces a lightweight multimodal fusion(LMF)module based on learnable low-rank representation blocks to end-to-end integrate visible and infrared images,preserving fine details while enhancing salient features.In addition,an efficient multiscale attention(EMA)mechanism is incorporated into the YOLOv10n backbone to improve feature representation under low-light conditions.Extensive experiments on our newly constructedmultimodal smoke human detection(MSHD)dataset demonstrate thatVIF-YOLOachievesmAP50 of 99.5%,precision of 99.2%,and recall of 99.3%,outperforming YOLOv10n by a clear margin.Furthermore,when deployed on the NVIDIA Jetson Xavier NX,VIF-YOLO attains 40.6 FPS with an average inference latency of 24.6 ms,validating its real-time capability on edge-computing platforms.These results confirm that VIF-YOLO provides accurate,robust,and fast detection across complex backgrounds and diverse smoke conditions,ensuring reliable and rapid localization of individuals in need of rescue.展开更多
In modern industrial production,foreign object detection in complex environments is crucial to ensure product quality and production safety.Detection systems based on deep-learning image processing algorithms often fa...In modern industrial production,foreign object detection in complex environments is crucial to ensure product quality and production safety.Detection systems based on deep-learning image processing algorithms often face challenges with handling high-resolution images and achieving accurate detection against complex backgrounds.To address these issues,this study employs the PatchCore unsupervised anomaly detection algorithm combined with data augmentation techniques to enhance the system’s generalization capability across varying lighting conditions,viewing angles,and object scales.The proposed method is evaluated in a complex industrial detection scenario involving the bogie of an electric multiple unit(EMU).A dataset consisting of complex backgrounds,diverse lighting conditions,and multiple viewing angles is constructed to validate the performance of the detection system in real industrial environments.Experimental results show that the proposed model achieves an average area under the receiver operating characteristic curve(AUROC)of 0.92 and an average F1 score of 0.85.Combined with data augmentation,the proposed model exhibits improvements in AUROC by 0.06 and F1 score by 0.03,demonstrating enhanced accuracy and robustness for foreign object detection in complex industrial settings.In addition,the effects of key factors on detection performance are systematically analyzed,providing practical guidance for parameter selection in real industrial applications.展开更多
With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comp...With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.展开更多
Antibiotic resistance genes(ARGs) are recognized as a primary threat to the sustainability of environment and human health in the 21^(st) century.Nanomaterials(NMs) have attracted substantial attention due to their un...Antibiotic resistance genes(ARGs) are recognized as a primary threat to the sustainability of environment and human health in the 21^(st) century.Nanomaterials(NMs) have attracted substantial attention due to their unique dimensions and structures.Unfortunately,emerging evidence suggests that NMs may facilitate the transmission of ARGs.It is crucial to elucidate how NMs affect the evolution and dissemination of ARGs.The current review comprehensively examines the role of NMs in the widespread transmission of ARGs in aquatic environments and the underlying mechanisms involved in the process.It aims to clarify the effects and mechanisms of NMs on the horizontal gene transfer processes that are associated with ARGs,including the enhancement of cell membrane permeability,the formation of nanopores on membranes,promotion of mutagenesis,and the generation of reactive oxygen species(ROSs).Furthermore,the trade-off between the removal of ARGs and horizontal transfer has been elucidated.The review aspires to guide future research directions,advance knowledge on the implications of NMs in the field of ARGs' transmission,and provide a theoretical foundation for the development of safer and more effective applications of NMs.展开更多
The atmospheric corrosion behavior of 510L low alloy steel subjected to acid-cleaned surface(ACS)and eco-pickled surface(EPS)treatments is systematically examined.After 1 year of atmospheric exposure,both ACS-and EPS-...The atmospheric corrosion behavior of 510L low alloy steel subjected to acid-cleaned surface(ACS)and eco-pickled surface(EPS)treatments is systematically examined.After 1 year of atmospheric exposure,both ACS-and EPS-treated samples demonstrate protective ability index values exceeding 2,indicating robust protective properties of the developed rust layers.The corrosion rates of ACS-and EPS-treated samples are similar.During the initial corrosion stage,γ-FeOOH emerges as the dominant corrosion product.With the prolonged atmospheric exposure,γ-FeOOH content progressively decreases through phase transformation into thermodynamically stableα-FeOOH and densely structured Fe_(3)O_(4),which markedly suppresses the corrosion of the steel.Notably,the corrosion rate of the coated EPS sample is obviously lower than that of the coated ACS counterpart,which is ascribed to the distinctive micro-roughness of EPS-treated surfaces that promote mechanical interlocking with protective coatings.展开更多
As large,room-scale environments become increasingly common,their spatial complexity increases due to variable,unstructured elements.Consequently,demand for room-scale service robots is surging,yet most technologies r...As large,room-scale environments become increasingly common,their spatial complexity increases due to variable,unstructured elements.Consequently,demand for room-scale service robots is surging,yet most technologies remain corridor-centric,and autonomous navigation in expansive rooms becomes unstable even around static obstacles.Existing approaches face several structural limitations.These include the labor-intensive requirement for large-scale object annotation and continual retraining,as well as the vulnerability of vanishing point or linebased methods when geometric cues are insufficient.In addition,the high cost of LiDAR and 3D perception errors caused by limited wall cues and dense interior clutter further limit their effectiveness.To address these challenges,we propose a zero-shot vision-based algorithm for robust 3D map reconstruction in geometry-deficient room-scale environments.The algorithm operates in three layers:Layer 1 performs dimension-wise boundary detection;Layer 2 estimates vanishing points,refines the precise perspective space,and extracts a floor mask;and Layer 3 conducts 3D spatial mapping and obstacle recognition.The proposed method was experimentally validated across various geometric-deficient room-scale environments,including lobbies,seminar rooms,conference rooms,cafeterias,and museums—demonstrating its ability to reliably reconstruct 3D maps and accurately recognize obstacles.Experimental results show that the proposed algorithm achieved an F1 score of 0.959 in precision perspective space detection and 0.965 in floor mask extraction.For obstacle recognition and classification,it obtained F1 scores of 0.980 in obstacle absent areas,0.913 in solid obstacle environments,and 0.939 in skeleton-type sparse obstacle environments,confirming its high precision and reliability in geometric-deficient room-scale environments.展开更多
Federated Learning(FL)provides an effective framework for efficient processing in vehicular edge computing.However,the dynamic and uncertain communication environment,along with the performance variations of vehicular...Federated Learning(FL)provides an effective framework for efficient processing in vehicular edge computing.However,the dynamic and uncertain communication environment,along with the performance variations of vehicular devices,affect the distribution and uploading processes of model parameters.In FL-assisted Internet of Vehicles(IoV)scenarios,challenges such as data heterogeneity,limited device resources,and unstable communication environments become increasingly prominent.These issues necessitate intelligent vehicle selection schemes to enhance training efficiency.Given this context,we propose a new scenario involving FL-assisted IoV systems under dynamic and uncertain communication conditions,and develop a dynamic interval multi-objective optimization algorithm to jointly optimize various factors including training experiments,system energy consumption,and bandwidth utilization to meet multi-criteria resource optimization requirements.For the problem at hand,we design a dynamic interval multi-objective optimization algorithm based on interval overlap detection.Simulation results demonstrate that our method outperforms other solutions in terms of accuracy,training cost,and server utilization.It effectively enhances training efficiency under wireless channel environments while rationally utilizing bandwidth resources,thus possessing significant scientific value and application potential in the field of IoV.展开更多
To assess the effectiveness of vaccination in contaminated environments,this study introduces a modeling framework that encompasses two transmission routes,namely direct human-to-human contact and indirect human-to-en...To assess the effectiveness of vaccination in contaminated environments,this study introduces a modeling framework that encompasses two transmission routes,namely direct human-to-human contact and indirect human-to-environment contact,as well as the implementation of new M72/AS01_(E)vaccine.Motivated by this,a coupled age-structured tuberculosis(TB)model is proposed.Its well-posedness requirement is verified using the integrated semigroup theory.Furthermore,this study presents a comprehensive analysis of threshold dynamics associated with the proposed model.Specifically,the global stability of the disease-free and positive steady states is demonstrated by employing Lyapunov functionals.Lastly,the effects of the vaccination with M72/AS01_(E)and contaminated environments on TB control are numerically simulated.Experimental results indicate that high concentrations of Mycobacterium tuberculosis in contaminated environments may somewhat impede TB control efforts,but that large-scale deployment of new vaccine could significantly reduce the prevalence of TB.展开更多
To meet the requirements of electromagnetic(EM)theory and applied physics,this study presents an overview of the state-of-the-art research on obtaining the EM properties of media and points out potential solutions tha...To meet the requirements of electromagnetic(EM)theory and applied physics,this study presents an overview of the state-of-the-art research on obtaining the EM properties of media and points out potential solutions that can break through the bottlenecks of current methods.Firstly,based on the survey of three mainstream approaches for acquiring EM properties of media,we identify the difficulties when implementing them in realistic environments.With a focus on addressing these problems and challenges,we propose a novel paradigm for obtaining the EM properties of multi-type media in realistic environments.Particularly,within this paradigm,we describe the implementation approach of the key technology,namely“multipath extraction using heterogeneous wave propagation data in multi-spectrum cases”.Finally,the latest measurement and simulation results show that the EM properties of multi-type media in realistic environments can be precisely and efficiently acquired by the methodology proposed in this study.展开更多
Aiming to address the Unmanned Aerial Vehicle(UAV) formation collision avoidance problem in Three-Dimensional(3-D) low-altitude environments where dense various obstacles exist, a fluid-based path planning framework n...Aiming to address the Unmanned Aerial Vehicle(UAV) formation collision avoidance problem in Three-Dimensional(3-D) low-altitude environments where dense various obstacles exist, a fluid-based path planning framework named the Formation Interfered Fluid Dynamical System(FIFDS) with Moderate Evasive Maneuver Strategy(MEMS) is proposed in this study.First, the UAV formation collision avoidance problem including quantifiable performance indexes is formulated. Second, inspired by the phenomenon of fluids continuously flowing while bypassing objects, the FIFDS for multiple UAVs is presented, which contains a Parallel Streamline Tracking(PST) method for formation keeping and the traditional IFDS for collision avoidance. Third, to rationally balance flight safety and collision avoidance cost, MEMS is proposed to generate moderate evasive maneuvers that match up with collision risks. Comprehensively containing the time and distance safety information, the 3-D dynamic collision regions are modeled for collision prediction. Then, the moderate evasive maneuver principle is refined, which provides criterions of the maneuver amplitude and direction. On this basis, an analytical parameter mapping mechanism is designed to online optimize IFDS parameters. Finally, the performance of the proposed method is validated by comparative simulation results and real flight experiments using fixed-wing UAVs.展开更多
Human interaction with natural environments is gaining increasing attention in environmental sciences as research consistently shows that access to green spaces,clean air,and biodiversity plays a crucial role in enhan...Human interaction with natural environments is gaining increasing attention in environmental sciences as research consistently shows that access to green spaces,clean air,and biodiversity plays a crucial role in enhancing physical health,reducing stress,and improving overall well-being.This study conducts a bibliometric and visualization-based analysis of forest therapy research,emphasizing its physiological and psychological benefits.Using the Web of Science database,we identified and analyzed 414 studies from 1998 to 2023.Through CiteSpace and VOSviewer,we mapped these documents to examine research trends,publication networks,leading scholars and institutions,key journals,and thematic evolution.Findings indicate that forest therapy research is predominantly concentrated in East Asia,North America,Australia,and Europe,with strong collaborative networks among authors and institutions.The concentration of publications,research evolution,and keyword trends reflect the development of forest therapy research.The analysis further identifies sixteen research clusters and discusses two research themes:physiological and psychological effects.By analyzing how the natural environment contributes to human well-being,we provide a comprehensive and visually structured understanding of forest therapy as an intersection of environmental science,public health and well-being,and ecosystem conservation.Our findings offer a new perspective for future interdisciplinary research,emphasizing the need for well-designed clinical trials to substantiate forest therapy’s diverse health effects and its role in promoting sustainable interactions between human societies and natural environments.展开更多
With the rapid development of drone technology,drones are increasingly used in urban environments,but they also bring many security risks,such as illegal reconnaissance,smuggling,and terrorist attacks.Therefore,it is ...With the rapid development of drone technology,drones are increasingly used in urban environments,but they also bring many security risks,such as illegal reconnaissance,smuggling,and terrorist attacks.Therefore,it is of great significance to study the anti-UAV technology in the urban environment.This paper analyzes the advantages and disadvantages of existing technologies and their applicability in the urban environment from the aspects of UAV detection,identification,and countermeasures,and discusses the future development trend of anti-UAV technology,aiming to provide a reference for urban safety protection.展开更多
When a fire breaks out in a high-rise building,the occlusion of smoke and obstacles results in dearth of crucial information concerning people in distress,thereby creating a challenge in their detection.Given the rest...When a fire breaks out in a high-rise building,the occlusion of smoke and obstacles results in dearth of crucial information concerning people in distress,thereby creating a challenge in their detection.Given the restricted sensing range of a single unmanned aerial vehicle(UAV)cam-era,enhancing the target recognition rate becomes challenging without target information.To tackle this issue,this paper proposes a multi-agent autonomous collaborative detection method for multi-targets in complex fire environments.The objective is to achieve the fusion of multi-angle visual information,effectively increasing the target’s information dimension,and ultimately address-ing the problem of low target recognition rate caused by the lack of target information.The method steps are as follows:first,the you only look once version5(YOLOv5)is used to detect the target in the image;second,the detected targets are tracked to monitor their movements and trajectories;third,the person re-identification(ReID)model is employed to extract the appearance features of targets;finally,by fusing the visual information from multi-angle cameras,the method achieves multi-agent autonomous collaborative detection.The experimental results show that the method effectively combines the visual information from multi-angle cameras,resulting in improved detec-tion efficiency for people in distress.展开更多
Background:Cold temperatures cause blood vessels to constrict,shallow breathing,and slight thickening of the blood.Working in extremely cold environments can have negative effects on health,yet there are currently no ...Background:Cold temperatures cause blood vessels to constrict,shallow breathing,and slight thickening of the blood.Working in extremely cold environments can have negative effects on health,yet there are currently no effective biomarkers to monitor these health conditions.Proteins are important intermediate phenotypes that can provide a theoretical basis for understanding disease pathophysiology.Proteins in the circulatory system reflect the physiological status of individuals,and plasma proteins have significant potential as biomarkers for various health conditions.Methods:In this study,we employed the Mendelian randomization(MR)method to analyze the effects of freezing temperatures on over 2900 plasma proteins.Subsequently,the selected plasma proteins were subjected to causal analysis in relation to 55 diseases,including respiratory disorders,cardiovascular diseases,various cancers,and oral diseases.The aim was to identify proteins that could serve as biomarkers for health status.Results:Our results indicate that cold environments may affect the concentrations of 78 plasma proteins.Further MR analysis revealed that nine of these plasma proteins are associated with the risk of respiratory disorders,cardiovascular diseases,various cancers,and oral diseases.Conclusion:These proteins show promise as biomarkers for monitoring the hazards and risks faced by individuals working in cold environments.These findings provide valuable insights into the biological mechanisms underlying occupational hazards.展开更多
To the editor:Adverse home environments(AHE),characterised by family conflict,parental separation or dysfunctional parenting,are linked to negative mental health outcomes in children and adults.12 AHE disproportionate...To the editor:Adverse home environments(AHE),characterised by family conflict,parental separation or dysfunctional parenting,are linked to negative mental health outcomes in children and adults.12 AHE disproportionately affect children with neurodevelopmental disorders such as attention-deficit/hyperactivity disorder(ADHD),which is characterised by inattention,hyperactivity/impulsivity and functional impairments.3 Apart from core symptoms,including inattention and hyperactivity,disruptive behaviour disorders(DBD),such as oppositional defiant disorder(ODD)and conduct disorder(CD),may be associated with AHE.Conduct problems are risk factors for ODD.And CD has become a main concern for childhood mental health.展开更多
This research investigates the application of digital images in military contexts by utilizing analytical equations to augment human visual capabilities.A comparable filter is used to improve the visual quality of the...This research investigates the application of digital images in military contexts by utilizing analytical equations to augment human visual capabilities.A comparable filter is used to improve the visual quality of the photographs by reducing truncations in the existing images.Furthermore,the collected images undergo processing using histogram gradients and a flexible threshold value that may be adjusted in specific situations.Thus,it is possible to reduce the occurrence of overlapping circumstances in collective picture characteristics by substituting grey-scale photos with colorized factors.The proposed method offers additional robust feature representations by imposing a limiting factor to reduce overall scattering values.This is achieved by visualizing a graphical function.Moreover,to derive valuable insights from a series of photos,both the separation and in-version processes are conducted.This involves analyzing comparison results across four different scenarios.The results of the comparative analysis show that the proposed method effectively reduces the difficulties associated with time and space to 1 s and 3%,respectively.In contrast,the existing strategy exhibits higher complexities of 3 s and 9.1%,respectively.展开更多
Meteorological detection environments hold a fundamental and pioneering position in the development of meteorological undertakings,serving as the scientific support for accurately conducting weather forecast,professio...Meteorological detection environments hold a fundamental and pioneering position in the development of meteorological undertakings,serving as the scientific support for accurately conducting weather forecast,professional meteorological services,and disaster prevention and mitigation decision.The safety and stability of meteorological detection environments are of vital importance,and any behavior that damages or affects the detection environments is not allowed.In this paper,the factors influencing meteorological detection environments in the new era were explored,and measures to protect meteorological detection environments were proposed,such as strictly implementing the protection system of meteorological detection environments,lawfully investigating and punishing destructive behaviors,intensifying the publicity of the protection law,and enhancing public awareness.展开更多
Tensegrity structures,embodying the principles of continuous tensioning and discrete compression,have emerged as fundamental frameworks in locomotive soft robotics for navigating uneven and unpredictable environments,...Tensegrity structures,embodying the principles of continuous tensioning and discrete compression,have emerged as fundamental frameworks in locomotive soft robotics for navigating uneven and unpredictable environments,owing to their flexible and resilient traits.By means of a straightforward and cost-effective method to achieve structure-driven,vibration-driven tensegrity shows great potential,particularly in tasks demanding random exploration.However,the design guidance for vibration-driven tensegrity and their performance evaluation in unstructured terrain remain unrevealed due to the complex dynamics of the structure.This paper presents a small six-bar tensegrity robot,driven by wireless vibration motors,designed for deployment in disaster rescue and search scenarios.Finite element simulation is used to investigate how structural characteristics,excitation parameters,and the arrangement of motors affect the kinematic performance of this tensegrity system.A prototype of the six-bar tensegrity robot with three motors located on the lower ends of the three lower struts is designed and manufactured after the numerical simulations.A simple control policy which adjusts the motion of the tensegrity robot by turning on or off the motors on different locations is proposed.The prototype with and without the control policy is tested in man-made environments of various complexity.It shows that the ability and efficiency of the tensegrity robot in exploring unstructured environments is significantly enhanced by the proposed control policy.It is believed that the potential of the vibration-driven tensegrity robot could be further exploited by integrating multi-source sensors and more intelligent control policies.展开更多
Essentially clearing the structure-activity relationship between iron carbide catalysts involving multiple active centers to understand the reaction mechanism of CO hydrogenation conversion process is still a great ch...Essentially clearing the structure-activity relationship between iron carbide catalysts involving multiple active centers to understand the reaction mechanism of CO hydrogenation conversion process is still a great challenge.Here,two main micro-environment factors,namely electronic properties and geometrical effects were found to have an integrated effect on the mechanism of CO hydrogenation conversion,involving active sites on multiple crystal phases.The Bader charge of the surface Fe atoms on the active sites had a guiding effect on the CO activation pathway,while the spatial configuration of the active sites greatly affected the energy barriers of CO activation.Although the defective surfaces were more conducive to CO activation,the defective sites were not the only sites to dissociate CO,as CO always tended to dissociate in a wider area.This synergistic effect of the micro-environment also occurred during the CO conversion process.Surface C atoms on relatively flat configurations were more likely to form methane,while the electronic properties of the active sites could effectively describe the C-C coupling process,as well as distinguish the coupling mechanisms.展开更多
Urban combat environments pose complex and variable challenges for UAV path planning due to multidimensional factors,such as static and dynamic obstructions as well as risks of exposure to enemy detection,which threat...Urban combat environments pose complex and variable challenges for UAV path planning due to multidimensional factors,such as static and dynamic obstructions as well as risks of exposure to enemy detection,which threaten flight safety and mission success.Traditional path planning methods typically depend solely on the distribution of static obstacles to generate collision-free paths,without accounting for constraints imposed by enemy detection and strike capabilities.Such a simplified approach can yield safety-compromising routes in highly complex urban airspace.To address these limitations,this study proposes a multi-parameter path planning method based on reachable airspace visibility graphs,which integrates UAV performance constraints,environmental limitations,and exposure risks.An innovative heuristic algorithm is developed to balance operational safety and efficiency by both exposure risks and path length.In the case study set in a typical mixed-use urban area,analysis of airspace visibility graphs reveals significant variations in exposure risk at different regions and altitudes due to building encroachments.Path optimization results indicate that the method can effectively generate covert and efficient flight paths by dynamically adjusting the exposure index,which represents the likelihood of enemy detection,and the path length,which corresponds to mission execution time.展开更多
基金funded by the National Natural Science Foundation of China under Grant 62306128the Leading Innovation Project of Changzhou Science and Technology Bureau underGrant CQ20230072+2 种基金the Basic Science Research Project of Jiangsu Provincial Department of Education under Grant 23KJD520003the Science and Technology Development Plan Project of Jilin Provinceunder Grant 20240101382JCthe National KeyR esearch and Development Program of China under Grant 2023YFF1105102.
文摘In fire rescue scenarios,traditional manual operations are highly dangerous,as dense smoke,low visibility,extreme heat,and toxic gases not only hinder rescue efficiency but also endanger firefighters’safety.Although intelligent rescue robots can enter hazardous environments in place of humans,smoke poses major challenges for human detection algorithms.These challenges include the attenuation of visible and infrared signals,complex thermal fields,and interference frombackground objects,all ofwhichmake it difficult to accurately identify trapped individuals.To address this problem,we propose VIF-YOLO,a visible–infrared fusion model for real-time human detection in dense smoke environments.The framework introduces a lightweight multimodal fusion(LMF)module based on learnable low-rank representation blocks to end-to-end integrate visible and infrared images,preserving fine details while enhancing salient features.In addition,an efficient multiscale attention(EMA)mechanism is incorporated into the YOLOv10n backbone to improve feature representation under low-light conditions.Extensive experiments on our newly constructedmultimodal smoke human detection(MSHD)dataset demonstrate thatVIF-YOLOachievesmAP50 of 99.5%,precision of 99.2%,and recall of 99.3%,outperforming YOLOv10n by a clear margin.Furthermore,when deployed on the NVIDIA Jetson Xavier NX,VIF-YOLO attains 40.6 FPS with an average inference latency of 24.6 ms,validating its real-time capability on edge-computing platforms.These results confirm that VIF-YOLO provides accurate,robust,and fast detection across complex backgrounds and diverse smoke conditions,ensuring reliable and rapid localization of individuals in need of rescue.
文摘In modern industrial production,foreign object detection in complex environments is crucial to ensure product quality and production safety.Detection systems based on deep-learning image processing algorithms often face challenges with handling high-resolution images and achieving accurate detection against complex backgrounds.To address these issues,this study employs the PatchCore unsupervised anomaly detection algorithm combined with data augmentation techniques to enhance the system’s generalization capability across varying lighting conditions,viewing angles,and object scales.The proposed method is evaluated in a complex industrial detection scenario involving the bogie of an electric multiple unit(EMU).A dataset consisting of complex backgrounds,diverse lighting conditions,and multiple viewing angles is constructed to validate the performance of the detection system in real industrial environments.Experimental results show that the proposed model achieves an average area under the receiver operating characteristic curve(AUROC)of 0.92 and an average F1 score of 0.85.Combined with data augmentation,the proposed model exhibits improvements in AUROC by 0.06 and F1 score by 0.03,demonstrating enhanced accuracy and robustness for foreign object detection in complex industrial settings.In addition,the effects of key factors on detection performance are systematically analyzed,providing practical guidance for parameter selection in real industrial applications.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2023-00235509Development of security monitoring technology based network behavior against encrypted cyber threats in ICT convergence environment).
文摘With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.
基金supported by the State Key Laboratory of Urban Water Resource and Environment (Harbin Institute of Technology) (No.2022TS13)the key projects of National Natural Science Foundation of China (No.2019YFC0408503)the Key Research Program of Wuhan (No.2022022202015015)。
文摘Antibiotic resistance genes(ARGs) are recognized as a primary threat to the sustainability of environment and human health in the 21^(st) century.Nanomaterials(NMs) have attracted substantial attention due to their unique dimensions and structures.Unfortunately,emerging evidence suggests that NMs may facilitate the transmission of ARGs.It is crucial to elucidate how NMs affect the evolution and dissemination of ARGs.The current review comprehensively examines the role of NMs in the widespread transmission of ARGs in aquatic environments and the underlying mechanisms involved in the process.It aims to clarify the effects and mechanisms of NMs on the horizontal gene transfer processes that are associated with ARGs,including the enhancement of cell membrane permeability,the formation of nanopores on membranes,promotion of mutagenesis,and the generation of reactive oxygen species(ROSs).Furthermore,the trade-off between the removal of ARGs and horizontal transfer has been elucidated.The review aspires to guide future research directions,advance knowledge on the implications of NMs in the field of ARGs' transmission,and provide a theoretical foundation for the development of safer and more effective applications of NMs.
基金support by National Natural Science Foundation of China(Grant No.52401103)Key Scientific Research Project in Shanxi Province(Grant No.202302050201015)+3 种基金Central Guiding Science and Technology Development of Local Fund(Grant No.YDZJSK20231A046)the Special Fund for Science and Technology Innovation Teams of Shanxi Province(202204051001004)Science and Technology Cooperation and Exchange Special Project of Shanxi Province(202404041101038)Postgraduate Education Innovation Project of Shanxi Province(Grant No.2024SJ304).
文摘The atmospheric corrosion behavior of 510L low alloy steel subjected to acid-cleaned surface(ACS)and eco-pickled surface(EPS)treatments is systematically examined.After 1 year of atmospheric exposure,both ACS-and EPS-treated samples demonstrate protective ability index values exceeding 2,indicating robust protective properties of the developed rust layers.The corrosion rates of ACS-and EPS-treated samples are similar.During the initial corrosion stage,γ-FeOOH emerges as the dominant corrosion product.With the prolonged atmospheric exposure,γ-FeOOH content progressively decreases through phase transformation into thermodynamically stableα-FeOOH and densely structured Fe_(3)O_(4),which markedly suppresses the corrosion of the steel.Notably,the corrosion rate of the coated EPS sample is obviously lower than that of the coated ACS counterpart,which is ascribed to the distinctive micro-roughness of EPS-treated surfaces that promote mechanical interlocking with protective coatings.
基金supported by Kyonggi University Research Grant 2025.
文摘As large,room-scale environments become increasingly common,their spatial complexity increases due to variable,unstructured elements.Consequently,demand for room-scale service robots is surging,yet most technologies remain corridor-centric,and autonomous navigation in expansive rooms becomes unstable even around static obstacles.Existing approaches face several structural limitations.These include the labor-intensive requirement for large-scale object annotation and continual retraining,as well as the vulnerability of vanishing point or linebased methods when geometric cues are insufficient.In addition,the high cost of LiDAR and 3D perception errors caused by limited wall cues and dense interior clutter further limit their effectiveness.To address these challenges,we propose a zero-shot vision-based algorithm for robust 3D map reconstruction in geometry-deficient room-scale environments.The algorithm operates in three layers:Layer 1 performs dimension-wise boundary detection;Layer 2 estimates vanishing points,refines the precise perspective space,and extracts a floor mask;and Layer 3 conducts 3D spatial mapping and obstacle recognition.The proposed method was experimentally validated across various geometric-deficient room-scale environments,including lobbies,seminar rooms,conference rooms,cafeterias,and museums—demonstrating its ability to reliably reconstruct 3D maps and accurately recognize obstacles.Experimental results show that the proposed algorithm achieved an F1 score of 0.959 in precision perspective space detection and 0.965 in floor mask extraction.For obstacle recognition and classification,it obtained F1 scores of 0.980 in obstacle absent areas,0.913 in solid obstacle environments,and 0.939 in skeleton-type sparse obstacle environments,confirming its high precision and reliability in geometric-deficient room-scale environments.
基金supported in part by the Central Guidance for Local Science and Technology Development Funds under Grant No.YDZJSX2025D049Shanxi Provincial Graduate Innovation Research Program under Grant No.2024KY652.
文摘Federated Learning(FL)provides an effective framework for efficient processing in vehicular edge computing.However,the dynamic and uncertain communication environment,along with the performance variations of vehicular devices,affect the distribution and uploading processes of model parameters.In FL-assisted Internet of Vehicles(IoV)scenarios,challenges such as data heterogeneity,limited device resources,and unstable communication environments become increasingly prominent.These issues necessitate intelligent vehicle selection schemes to enhance training efficiency.Given this context,we propose a new scenario involving FL-assisted IoV systems under dynamic and uncertain communication conditions,and develop a dynamic interval multi-objective optimization algorithm to jointly optimize various factors including training experiments,system energy consumption,and bandwidth utilization to meet multi-criteria resource optimization requirements.For the problem at hand,we design a dynamic interval multi-objective optimization algorithm based on interval overlap detection.Simulation results demonstrate that our method outperforms other solutions in terms of accuracy,training cost,and server utilization.It effectively enhances training efficiency under wireless channel environments while rationally utilizing bandwidth resources,thus possessing significant scientific value and application potential in the field of IoV.
文摘To assess the effectiveness of vaccination in contaminated environments,this study introduces a modeling framework that encompasses two transmission routes,namely direct human-to-human contact and indirect human-to-environment contact,as well as the implementation of new M72/AS01_(E)vaccine.Motivated by this,a coupled age-structured tuberculosis(TB)model is proposed.Its well-posedness requirement is verified using the integrated semigroup theory.Furthermore,this study presents a comprehensive analysis of threshold dynamics associated with the proposed model.Specifically,the global stability of the disease-free and positive steady states is demonstrated by employing Lyapunov functionals.Lastly,the effects of the vaccination with M72/AS01_(E)and contaminated environments on TB control are numerically simulated.Experimental results indicate that high concentrations of Mycobacterium tuberculosis in contaminated environments may somewhat impede TB control efforts,but that large-scale deployment of new vaccine could significantly reduce the prevalence of TB.
基金supported by the Beijing Natural Science Foundation(No.L212029)the National Natural Science Foundation of China(No.62271043).
文摘To meet the requirements of electromagnetic(EM)theory and applied physics,this study presents an overview of the state-of-the-art research on obtaining the EM properties of media and points out potential solutions that can break through the bottlenecks of current methods.Firstly,based on the survey of three mainstream approaches for acquiring EM properties of media,we identify the difficulties when implementing them in realistic environments.With a focus on addressing these problems and challenges,we propose a novel paradigm for obtaining the EM properties of multi-type media in realistic environments.Particularly,within this paradigm,we describe the implementation approach of the key technology,namely“multipath extraction using heterogeneous wave propagation data in multi-spectrum cases”.Finally,the latest measurement and simulation results show that the EM properties of multi-type media in realistic environments can be precisely and efficiently acquired by the methodology proposed in this study.
基金supported in part by the National Natural Science Foundations of China(Nos.61175084,61673042 and 62203046)the China Postdoctoral Science Foundation(No.2022M713006).
文摘Aiming to address the Unmanned Aerial Vehicle(UAV) formation collision avoidance problem in Three-Dimensional(3-D) low-altitude environments where dense various obstacles exist, a fluid-based path planning framework named the Formation Interfered Fluid Dynamical System(FIFDS) with Moderate Evasive Maneuver Strategy(MEMS) is proposed in this study.First, the UAV formation collision avoidance problem including quantifiable performance indexes is formulated. Second, inspired by the phenomenon of fluids continuously flowing while bypassing objects, the FIFDS for multiple UAVs is presented, which contains a Parallel Streamline Tracking(PST) method for formation keeping and the traditional IFDS for collision avoidance. Third, to rationally balance flight safety and collision avoidance cost, MEMS is proposed to generate moderate evasive maneuvers that match up with collision risks. Comprehensively containing the time and distance safety information, the 3-D dynamic collision regions are modeled for collision prediction. Then, the moderate evasive maneuver principle is refined, which provides criterions of the maneuver amplitude and direction. On this basis, an analytical parameter mapping mechanism is designed to online optimize IFDS parameters. Finally, the performance of the proposed method is validated by comparative simulation results and real flight experiments using fixed-wing UAVs.
文摘Human interaction with natural environments is gaining increasing attention in environmental sciences as research consistently shows that access to green spaces,clean air,and biodiversity plays a crucial role in enhancing physical health,reducing stress,and improving overall well-being.This study conducts a bibliometric and visualization-based analysis of forest therapy research,emphasizing its physiological and psychological benefits.Using the Web of Science database,we identified and analyzed 414 studies from 1998 to 2023.Through CiteSpace and VOSviewer,we mapped these documents to examine research trends,publication networks,leading scholars and institutions,key journals,and thematic evolution.Findings indicate that forest therapy research is predominantly concentrated in East Asia,North America,Australia,and Europe,with strong collaborative networks among authors and institutions.The concentration of publications,research evolution,and keyword trends reflect the development of forest therapy research.The analysis further identifies sixteen research clusters and discusses two research themes:physiological and psychological effects.By analyzing how the natural environment contributes to human well-being,we provide a comprehensive and visually structured understanding of forest therapy as an intersection of environmental science,public health and well-being,and ecosystem conservation.Our findings offer a new perspective for future interdisciplinary research,emphasizing the need for well-designed clinical trials to substantiate forest therapy’s diverse health effects and its role in promoting sustainable interactions between human societies and natural environments.
文摘With the rapid development of drone technology,drones are increasingly used in urban environments,but they also bring many security risks,such as illegal reconnaissance,smuggling,and terrorist attacks.Therefore,it is of great significance to study the anti-UAV technology in the urban environment.This paper analyzes the advantages and disadvantages of existing technologies and their applicability in the urban environment from the aspects of UAV detection,identification,and countermeasures,and discusses the future development trend of anti-UAV technology,aiming to provide a reference for urban safety protection.
文摘When a fire breaks out in a high-rise building,the occlusion of smoke and obstacles results in dearth of crucial information concerning people in distress,thereby creating a challenge in their detection.Given the restricted sensing range of a single unmanned aerial vehicle(UAV)cam-era,enhancing the target recognition rate becomes challenging without target information.To tackle this issue,this paper proposes a multi-agent autonomous collaborative detection method for multi-targets in complex fire environments.The objective is to achieve the fusion of multi-angle visual information,effectively increasing the target’s information dimension,and ultimately address-ing the problem of low target recognition rate caused by the lack of target information.The method steps are as follows:first,the you only look once version5(YOLOv5)is used to detect the target in the image;second,the detected targets are tracked to monitor their movements and trajectories;third,the person re-identification(ReID)model is employed to extract the appearance features of targets;finally,by fusing the visual information from multi-angle cameras,the method achieves multi-agent autonomous collaborative detection.The experimental results show that the method effectively combines the visual information from multi-angle cameras,resulting in improved detec-tion efficiency for people in distress.
基金funded by the Health Commission of Heilongjiang Province(Project Number:20230808010517).
文摘Background:Cold temperatures cause blood vessels to constrict,shallow breathing,and slight thickening of the blood.Working in extremely cold environments can have negative effects on health,yet there are currently no effective biomarkers to monitor these health conditions.Proteins are important intermediate phenotypes that can provide a theoretical basis for understanding disease pathophysiology.Proteins in the circulatory system reflect the physiological status of individuals,and plasma proteins have significant potential as biomarkers for various health conditions.Methods:In this study,we employed the Mendelian randomization(MR)method to analyze the effects of freezing temperatures on over 2900 plasma proteins.Subsequently,the selected plasma proteins were subjected to causal analysis in relation to 55 diseases,including respiratory disorders,cardiovascular diseases,various cancers,and oral diseases.The aim was to identify proteins that could serve as biomarkers for health status.Results:Our results indicate that cold environments may affect the concentrations of 78 plasma proteins.Further MR analysis revealed that nine of these plasma proteins are associated with the risk of respiratory disorders,cardiovascular diseases,various cancers,and oral diseases.Conclusion:These proteins show promise as biomarkers for monitoring the hazards and risks faced by individuals working in cold environments.These findings provide valuable insights into the biological mechanisms underlying occupational hazards.
基金supported by National Natural Science Foundation Youth Project (81901386)the Fundamental Research Funds for the Central Universities (YG2025ZD07)+5 种基金the National Science and Technology Innovation 2030 Major Project of China (2021ZD0203900)National Natural Science Foundation of China (NSFC) grant (82422029)the Science and Technology Commission of Shanghai Municipality (24Y22800200, 22QA1407900)NSFC grant (82271530)Innovation teams of high-level universities in Shanghaithe Scientific Research and Innovation Team of Liaoning Normal University (24TD004).
文摘To the editor:Adverse home environments(AHE),characterised by family conflict,parental separation or dysfunctional parenting,are linked to negative mental health outcomes in children and adults.12 AHE disproportionately affect children with neurodevelopmental disorders such as attention-deficit/hyperactivity disorder(ADHD),which is characterised by inattention,hyperactivity/impulsivity and functional impairments.3 Apart from core symptoms,including inattention and hyperactivity,disruptive behaviour disorders(DBD),such as oppositional defiant disorder(ODD)and conduct disorder(CD),may be associated with AHE.Conduct problems are risk factors for ODD.And CD has become a main concern for childhood mental health.
基金financially supported by Ongoing Research Funding Program(ORF-2025-846),King Saud University,Riyadh,Saudi Arabia.
文摘This research investigates the application of digital images in military contexts by utilizing analytical equations to augment human visual capabilities.A comparable filter is used to improve the visual quality of the photographs by reducing truncations in the existing images.Furthermore,the collected images undergo processing using histogram gradients and a flexible threshold value that may be adjusted in specific situations.Thus,it is possible to reduce the occurrence of overlapping circumstances in collective picture characteristics by substituting grey-scale photos with colorized factors.The proposed method offers additional robust feature representations by imposing a limiting factor to reduce overall scattering values.This is achieved by visualizing a graphical function.Moreover,to derive valuable insights from a series of photos,both the separation and in-version processes are conducted.This involves analyzing comparison results across four different scenarios.The results of the comparative analysis show that the proposed method effectively reduces the difficulties associated with time and space to 1 s and 3%,respectively.In contrast,the existing strategy exhibits higher complexities of 3 s and 9.1%,respectively.
文摘Meteorological detection environments hold a fundamental and pioneering position in the development of meteorological undertakings,serving as the scientific support for accurately conducting weather forecast,professional meteorological services,and disaster prevention and mitigation decision.The safety and stability of meteorological detection environments are of vital importance,and any behavior that damages or affects the detection environments is not allowed.In this paper,the factors influencing meteorological detection environments in the new era were explored,and measures to protect meteorological detection environments were proposed,such as strictly implementing the protection system of meteorological detection environments,lawfully investigating and punishing destructive behaviors,intensifying the publicity of the protection law,and enhancing public awareness.
基金supported by the National Natural Science Foundation of China(Grant Nos.52178175 and 52108182)the National Natural Science Foundation of Zhejiang Province(Grant No.LZ23E080003).
文摘Tensegrity structures,embodying the principles of continuous tensioning and discrete compression,have emerged as fundamental frameworks in locomotive soft robotics for navigating uneven and unpredictable environments,owing to their flexible and resilient traits.By means of a straightforward and cost-effective method to achieve structure-driven,vibration-driven tensegrity shows great potential,particularly in tasks demanding random exploration.However,the design guidance for vibration-driven tensegrity and their performance evaluation in unstructured terrain remain unrevealed due to the complex dynamics of the structure.This paper presents a small six-bar tensegrity robot,driven by wireless vibration motors,designed for deployment in disaster rescue and search scenarios.Finite element simulation is used to investigate how structural characteristics,excitation parameters,and the arrangement of motors affect the kinematic performance of this tensegrity system.A prototype of the six-bar tensegrity robot with three motors located on the lower ends of the three lower struts is designed and manufactured after the numerical simulations.A simple control policy which adjusts the motion of the tensegrity robot by turning on or off the motors on different locations is proposed.The prototype with and without the control policy is tested in man-made environments of various complexity.It shows that the ability and efficiency of the tensegrity robot in exploring unstructured environments is significantly enhanced by the proposed control policy.It is believed that the potential of the vibration-driven tensegrity robot could be further exploited by integrating multi-source sensors and more intelligent control policies.
基金supported by the Research Fund for National Key Research and Development Program of China(2022YFA1503804,2021YFA1501403)the Natural Science Foundation of China(22208094,21922803,92034301,22008066 and 21776077)+2 种基金the China Postdoctoral Science Foundation(BX20190116)the Innovation Program of Shanghai Municipal Education Commission(17ZR1407300)the Program of Shanghai Academic/Technology Research Leader(21XD1421000).
文摘Essentially clearing the structure-activity relationship between iron carbide catalysts involving multiple active centers to understand the reaction mechanism of CO hydrogenation conversion process is still a great challenge.Here,two main micro-environment factors,namely electronic properties and geometrical effects were found to have an integrated effect on the mechanism of CO hydrogenation conversion,involving active sites on multiple crystal phases.The Bader charge of the surface Fe atoms on the active sites had a guiding effect on the CO activation pathway,while the spatial configuration of the active sites greatly affected the energy barriers of CO activation.Although the defective surfaces were more conducive to CO activation,the defective sites were not the only sites to dissociate CO,as CO always tended to dissociate in a wider area.This synergistic effect of the micro-environment also occurred during the CO conversion process.Surface C atoms on relatively flat configurations were more likely to form methane,while the electronic properties of the active sites could effectively describe the C-C coupling process,as well as distinguish the coupling mechanisms.
基金supported by the Ministry of Industry and Information Technology(No.23100002022102001)。
文摘Urban combat environments pose complex and variable challenges for UAV path planning due to multidimensional factors,such as static and dynamic obstructions as well as risks of exposure to enemy detection,which threaten flight safety and mission success.Traditional path planning methods typically depend solely on the distribution of static obstacles to generate collision-free paths,without accounting for constraints imposed by enemy detection and strike capabilities.Such a simplified approach can yield safety-compromising routes in highly complex urban airspace.To address these limitations,this study proposes a multi-parameter path planning method based on reachable airspace visibility graphs,which integrates UAV performance constraints,environmental limitations,and exposure risks.An innovative heuristic algorithm is developed to balance operational safety and efficiency by both exposure risks and path length.In the case study set in a typical mixed-use urban area,analysis of airspace visibility graphs reveals significant variations in exposure risk at different regions and altitudes due to building encroachments.Path optimization results indicate that the method can effectively generate covert and efficient flight paths by dynamically adjusting the exposure index,which represents the likelihood of enemy detection,and the path length,which corresponds to mission execution time.
