Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods...Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods,based on reliable existing data stored in project management tools’datasets,automating this evaluation process becomes a natural step forward.In this context,our approach focuses on quantifying software developer expertise by using metadata from the task-tracking systems.For this,we mathematically formalize two categories of expertise:technology-specific expertise,which denotes the skills required for a particular technology,and general expertise,which encapsulates overall knowledge in the software industry.Afterward,we automatically classify the zones of expertise associated with each task a developer has worked on using Bidirectional Encoder Representations from Transformers(BERT)-like transformers to handle the unique characteristics of project tool datasets effectively.Finally,our method evaluates the proficiency of each software specialist across already completed projects from both technology-specific and general perspectives.The method was experimentally validated,yielding promising results.展开更多
A facile one-step hydrothermal method has been reported to synthesize theα-Fe_(2)O_(3)nanosheet arrays with the preferred orientation along the[104]direction on the ITO substrate.Theα-Fe_(2)O_(3)nanosheet arrays-bas...A facile one-step hydrothermal method has been reported to synthesize theα-Fe_(2)O_(3)nanosheet arrays with the preferred orientation along the[104]direction on the ITO substrate.Theα-Fe_(2)O_(3)nanosheet arrays-based W/α-Fe_(2)O_(3)/ITO memristor has been achieved by depositing the circular W top electrodes on theα-Fe_(2)O_(3)nanosheet arrays.The as-prepared W/α-Fe_(2)O_(3)/ITO memristor shows a reliable nonvolatile bipolar resistive switching behavior with the high resistance ratio of about 103at the reading voltage of 0.1 V,good resistance retention over 10~3s,ultralow set voltage of-0.6 V and reset voltage of 0.7 V,and good durability.In addition,the tunneling conduction mechanism modified by the oxygen vacancies has been proposed and suggested to be responsible for the nonvolatile resistive switching behavior of the as-prepared W/α-Fe_(2)O_(3)/ITO memristor.This work demonstrates that the as-preparedα-Fe_(2)O_(3)nanosheet arrays-based W/α-Fe_(2)O_(3)/ITO memristor would be a promising candidate for further ultralow power nonvolatile memory applications.展开更多
The role that visual discriminative ability plays among giant pandas in social communication and individual discrimination has received less attention than olfactory and auditory modalities.Here,we used an eye-tracker...The role that visual discriminative ability plays among giant pandas in social communication and individual discrimination has received less attention than olfactory and auditory modalities.Here,we used an eye-tracker technology to investigate pupil fixation patterns for 8 captive male giant pandas Ailuropoda melanoleuca.We paired images(N=26)of conspecifics against:1)sympatric predators(gray wolves and tigers),and non-threatening sympatric species(golden pheasant,golden snub-nosed monkey,takin,and red panda),2)conspecifics with atypical fur colora-tion(albino and brown),and 3)zookeepers/non-zookeepers wearing either work uniform or plain clothing.For each session,we tracked the pan-da's pupil movements and measured pupil first fixation point(FFP),fixation latency,total fixation count(TFC),and duration(TFD)of attention to each image.Overall,pandas exhibited similar attention(FFPs and TFCs)to images of predators and non-threatening sympatric species.Images of golden pheasant,snub-nosed monkey,and tiger received less attention(TFD)than images of conspecifics,whereas images of takin and red panda received more attention,suggesting a greater alertness to habitat or food competitors than to potential predators.Pandas'TFCs were greater for images of black-white conspecifics than for albino or brown phenotypes,implying that familiar color elicited more interest.Pandas reacted differently to images of men versus women.For images of women only,pandas gave more attention(TFC)to familiar combinations(uniformed zookeepers and plain-clothed non-zookeepers),consistent with the familiarity hypothesis.That pandas can use visual perception to discriminate intra-specifically and inter-specifically,including details of human appearance,has applications for panda conservation and captive husbandry.展开更多
This paper investigates the age of information(AoI)-based multi-user mobile edge computing(MEC)network with partial offloading mode.The weighted sum AoI(WSA)is first analyzed and derived,and then a WSA minimization pr...This paper investigates the age of information(AoI)-based multi-user mobile edge computing(MEC)network with partial offloading mode.The weighted sum AoI(WSA)is first analyzed and derived,and then a WSA minimization problem is formulated by jointly optimizing the user scheduling and data assignment.Due to the non-analytic expression of the WSA w.r.t.the optimization variables and the unknowability of future network information,the problem cannot be solved with known solution methods.Therefore,an online Joint Partial Offloading and User Scheduling Optimization(JPOUSO)algorithm is proposed by transforming the original problem into a single-slot data assignment subproblem and a single-slot user scheduling sub-problem and solving the two sub-problems separately.We analyze the computational complexity of the presented JPO-USO algorithm,which is of O(N),with N being the number of users.Simulation results show that the proposed JPO-USO algorithm is able to achieve better AoI performance compared with various baseline methods.It is shown that both the user’s data assignment and the user’s AoI should be jointly taken into account to decrease the system WSA when scheduling users.展开更多
Information security and quality management are often considered two different fields. However, organizations must be mindful of how software security may affect quality control. This paper examines and promotes metho...Information security and quality management are often considered two different fields. However, organizations must be mindful of how software security may affect quality control. This paper examines and promotes methods through which secure software development processes can be integrated into the Systems Software Development Life-cycle (SDLC) to improve system quality. Cyber-security and quality assurance are both involved in reducing risk. Software security teams work to reduce security risks, whereas quality assurance teams work to decrease risks to quality. There is a need for clear standards, frameworks, processes, and procedures to be followed by organizations to ensure high-level quality while reducing security risks. This research uses a survey of industry professionals to help identify best practices for developing software with fewer defects from the early stages of the SDLC to improve both the quality and security of software. Results show that there is a need for better security awareness among all members of software development teams.展开更多
Brain tumors,one of the most lethal diseases with low survival rates,require early detection and accurate diagnosis to enable effective treatment planning.While deep learning architectures,particularly Convolutional N...Brain tumors,one of the most lethal diseases with low survival rates,require early detection and accurate diagnosis to enable effective treatment planning.While deep learning architectures,particularly Convolutional Neural Networks(CNNs),have shown significant performance improvements over traditional methods,they struggle to capture the subtle pathological variations between different brain tumor types.Recent attention-based models have attempted to address this by focusing on global features,but they come with high computational costs.To address these challenges,this paper introduces a novel parallel architecture,ParMamba,which uniquely integrates Convolutional Attention Patch Embedding(CAPE)and the Conv Mamba block including CNN,Mamba and the channel enhancement module,marking a significant advancement in the field.The unique design of ConvMamba block enhances the ability of model to capture both local features and long-range dependencies,improving the detection of subtle differences between tumor types.The channel enhancement module refines feature interactions across channels.Additionally,CAPE is employed as a downsampling layer that extracts both local and global features,further improving classification accuracy.Experimental results on two publicly available brain tumor datasets demonstrate that ParMamba achieves classification accuracies of 99.62%and 99.35%,outperforming existing methods.Notably,ParMamba surpasses vision transformers(ViT)by 1.37%in accuracy,with a throughput improvement of over 30%.These results demonstrate that ParMamba delivers superior performance while operating faster than traditional attention-based methods.展开更多
Automatic segmentation and recognition of content and element information in color geological map are of great significance for researchers to analyze the distribution of mineral resources and predict disaster informa...Automatic segmentation and recognition of content and element information in color geological map are of great significance for researchers to analyze the distribution of mineral resources and predict disaster information.This article focuses on color planar raster geological map(geological maps include planar geological maps,columnar maps,and profiles).While existing deep learning approaches are often used to segment general images,their performance is limited due to complex elements,diverse regional features,and complicated backgrounds for color geological map in the domain of geoscience.To address the issue,a color geological map segmentation model is proposed that combines the Felz clustering algorithm and an improved SE-UNet deep learning network(named GeoMSeg).Firstly,a symmetrical encoder-decoder structure backbone network based on UNet is constructed,and the channel attention mechanism SENet has been incorporated to augment the network’s capacity for feature representation,enabling the model to purposefully extract map information.The SE-UNet network is employed for feature extraction from the geological map and obtain coarse segmentation results.Secondly,the Felz clustering algorithm is used for super pixel pre-segmentation of geological maps.The coarse segmentation results are refined and modified based on the super pixel pre-segmentation results to obtain the final segmentation results.This study applies GeoMSeg to the constructed dataset,and the experimental results show that the algorithm proposed in this paper has superior performance compared to other mainstream map segmentation models,with an accuracy of 91.89%and a MIoU of 71.91%.展开更多
Breast cancer diagnosis relies heavily on many kinds of information from diverse sources—like mammogram images,ultrasound scans,patient records,and genetic tests—but most AI tools look at only one of these at a time...Breast cancer diagnosis relies heavily on many kinds of information from diverse sources—like mammogram images,ultrasound scans,patient records,and genetic tests—but most AI tools look at only one of these at a time,which limits their ability to produce accurate and comprehensive decisions.In recent years,multimodal learning has emerged,enabling the integration of heterogeneous data to improve performance and diagnostic accuracy.However,doctors cannot always see how or why these AI tools make their choices,which is a significant bottleneck in their reliability,along with adoption in clinical settings.Hence,people are adding explainable AI techniques that show the steps the model takes.This review investigates previous work that has employed multimodal learning and XAI for the diagnosis of breast cancer.It discusses the types of data,fusion techniques,and XAI models employed.It was done following the PRISMA guidelines and included studies from 2021 to April 2025.The literature search was performed systematically and resulted in 61 studies.The review highlights a gradual increase in current studies focusing on multimodal fusion and XAI,particularly in the years 2023–2024.It found that studies using multi-modal data fusion achieved the highest accuracy by 5%–10%on average compared to other studies that used single-modality data,an intermediate fusion strategy,and modern fusion techniques,such as cross attention,achieved the highest accuracy and best performance.The review also showed that SHAP,Grad-CAM,and LIME techniques are the most used in explaining breast cancer diagnostic models.There is a clear research shift toward integrating multimodal learning and XAI techniques into the breast cancer diagnostics field.However,several gaps were identified,including the scarcity of public multimodal datasets.Lack of a unified explainable framework in multimodal fusion systems,and lack of standardization in evaluating explanations.These limitations call for future research focused on building more shared datasets and integrating multimodal data and explainable AI techniques to improve decision-making and enhance transparency.展开更多
Images and videos play an increasingly vital role in daily life and are widely utilized as key evidentiary sources in judicial investigations and forensic analysis.Simultaneously,advancements in image and video proces...Images and videos play an increasingly vital role in daily life and are widely utilized as key evidentiary sources in judicial investigations and forensic analysis.Simultaneously,advancements in image and video processing technologies have facilitated the widespread availability of powerful editing tools,such as Deepfakes,enabling anyone to easily create manipulated or fake visual content,which poses an enormous threat to social security and public trust.To verify the authenticity and integrity of images and videos,numerous approaches have been proposed,which are primarily based on content analysis and their effectiveness is susceptible to interference from various image or video post-processing operations.Recent research has highlighted the potential of file containers analysis as a promising forensic approach that offers efficient and interpretable results.However,there is still a lack of review articles on this kind of approach.In order to fill this gap,we present a comprehensive review of file containers-based image and video forensics in this paper.Specifically,we categorize the existing methods into two distinct stages,qualitative analysis and quantitative analysis.In addition,an overall framework is proposed to organize the exiting approaches.Then,the advantages and disadvantages of the schemes used across different forensic tasks are provided.Finally,we outline the trends in this research area,aiming to provide valuable insights and technical guidance for future research.展开更多
A facile sol–gel method and heating treatment process have been reported to synthesize the wurtzite phase ZnO nanofilms with the preferential growth orientation along the[001]direction on the FTO substrates.The as-pr...A facile sol–gel method and heating treatment process have been reported to synthesize the wurtzite phase ZnO nanofilms with the preferential growth orientation along the[001]direction on the FTO substrates.The as-prepared wurtzite phase ZnO nanofilms-based memristor with the W/ZnO/FTO sandwich has demonstrated a reliable nonvolatile bipolar resistive switching behaviors with an ultralow set voltage of about +3 V and reset voltage of approximately-3.6 V,high resistive switching ratio of more than two orders of magnitude,good resistance retention ability(up to 10^(4)s),and excellent durability.Furthermore,the resistive switching behavior in the low-resistance state is attributed to the Ohmic conduction mechanism,while the resistive switching behavior in the high-resistance state is controlled by the trap-modulated space charge limited current(SCLC)mechanism.In addition,the conductive filament model regulated by the oxygen vacancies has been proposed,where the nonvolatile bipolar resistive switching behaviors could be attributed to the formation and rupture of conductive filaments in the W/ZnO/FTO memristor.This work demonstrates that the as-prepared wurtzite phase ZnO nanofilms-based W/ZnO/FTO memristor has promising prospects in future nonvolatile memory applications.展开更多
Polygonati Rhizoma,a functional food and a traditional Chinese medicine broadly used in China and several Southeast Asia countries,possesses effective health-promoting activities.Prepared from 3 plants in Polygonatum ...Polygonati Rhizoma,a functional food and a traditional Chinese medicine broadly used in China and several Southeast Asia countries,possesses effective health-promoting activities.Prepared from 3 plants in Polygonatum genus(Polygonatum kingianum,Polygonatum sibiricum,and Polygonatum cyrtonema),Polygonati Rhizoma has drawn increasing attention due to its remarkable immune-enhancing and metabolic regulatory activities in recent years.In this review,we summarized the updated research of chemical constituents and biological activities of Polygonati Rhizoma,especially the metabolic regulation,immunomodulatory effects,and anti-fatigue activities,aiming to provide a comprehensive understanding,broaden the usage and promote more in-depth exploration of Polygonati Rhizoma as a functional food.展开更多
This study aimed to explore the relationship between Soil-Plant Analysis Development(SPAD)values and key environmental factors in cucumber(Cucumis sativus L.)cultivation in a greenhouse.SPAD values,indicative of chlor...This study aimed to explore the relationship between Soil-Plant Analysis Development(SPAD)values and key environmental factors in cucumber(Cucumis sativus L.)cultivation in a greenhouse.SPAD values,indicative of chlorophyll content,reflect plant health and productivity.The analysis revealed strong positive correlations between SPADvalues and both indoor light intensity(ILI,r=0.59,p<0.001)and outdoor light intensity(OLI,r=0.62,p<0.001),suggesting that higher light intensities were associated with enhanced SPAD values.In contrast,significant negative correlations were found between SPAD values and soil temperature at 15-30 cm depth(ST1530,r=−0.47,p<0.001)and volumetric soil moisture content at the same depth(SM1530,r=−0.52,p<0.001),with higher soil temperatures(e.g.,28℃)and excessive moisture(e.g.,25%)leading to reduced SPAD values.Multiple regression analysis identified ST1530 and SM1530 as significant negative predictors of SPAD,with coefficients of−0.97(p=0.05)and−0.34(p=0.05),respectively,suggesting that increases in soil temperature and moisture result in lower SPAD values.Indoor light intensity(e.g.,600-800μmol/m^(2)/s)emerged as a significant positive contributor,with a coefficient of 0.01(p<0.001),highlighting its role in promoting chlorophyll synthesis.Additionally,relative humidity(r=0.27,p<0.01)showed a positive,although less pronounced,association with SPAD.These results underscore the importance of both direct and indirect environmental factors in influencing SPAD variability and,by extension,plant health and productivity in cucumber cultivation.展开更多
Earlier notification and fire detection methods provide safety information and fire prevention to blind and visually impaired(BVI)individuals in a limited timeframe in the event of emergencies,particularly in enclosed...Earlier notification and fire detection methods provide safety information and fire prevention to blind and visually impaired(BVI)individuals in a limited timeframe in the event of emergencies,particularly in enclosed areas.Fire detection becomes crucial as it directly impacts human safety and the environment.While modern technology requires precise techniques for early detection to prevent damage and loss,few research has focused on artificial intelligence(AI)-based early fire alert systems for BVI individuals in indoor settings.To prevent such fire incidents,it is crucial to identify fires accurately and promptly,and alert BVI personnel using a combination of smart glasses,deep learning(DL),and computer vision(CV).The most recent technologies require effective methods to identify fires quickly,preventing damage and physical loss.In this manuscript,an Enhanced Fire Detection System for Blind and Visually Challenged People using Artificial Intelligence with Deep Convolutional Neural Networks(EFDBVC-AIDCNN)model is presented.The EFDBVC-AIDCNN model presents an advanced fire detection system that utilizes AI to detect and classify fire hazards for BVI people effectively.Initially,image pre-processing is performed using the Gabor filter(GF)model to improve texture details and patterns specific to flames and smoke.For the feature extractor,the Swin transformer(ST)model captures fine details across multiple scales to represent fire patterns accurately.Furthermore,the Elman neural network(ENN)technique is implemented to detect fire.The improved whale optimization algorithm(IWOA)is used to efficiently tune ENN parameters,improving accuracy and robustness across varying lighting and environmental conditions to optimize performance.An extensive experimental study of the EFDBVC-AIDCNN technique is accomplished under the fire detection dataset.A short comparative analysis of the EFDBVC-AIDCNN approach portrayed a superior accuracy value of 96.60%over existing models.展开更多
Finding suitable initial noise that retains the original image’s information is crucial for image-to-image(I2I)translation using text-to-image(T2I)diffusion models.A common approach is to add random noise directly to...Finding suitable initial noise that retains the original image’s information is crucial for image-to-image(I2I)translation using text-to-image(T2I)diffusion models.A common approach is to add random noise directly to the original image,as in SDEdit.However,we have observed that this can result in“semantic discrepancy”issues,wherein T2I diffusion models misinterpret the semantic relationships and generate content not present in the original image.We identify that the noise introduced by SDEdit disrupts the semantic integrity of the image,leading to unintended associations between unrelated regions after U-Net upsampling.Building on the widely-used latent diffusion model,Stable Diffusion,we propose a training-free,plugand-play method to alleviate semantic discrepancy and enhance the fidelity of the translated image.By leveraging the deterministic nature of denoising diffusion implicit models(DDIMs)inversion,we correct the erroneous features and correlations from the original generative process with accurate ones from DDIM inversion.This approach alleviates semantic discrepancy and surpasses recent DDIM-inversion-based methods such as PnP with fewer priors,achieving a speedup of 11.2 times in experiments conducted on COCO,ImageNet,and ImageNet-R datasets across multiple I2I translation tasks.展开更多
Fuzzy c-means （FCM） algorithm is one of the most popular methods for image segmentation. However, the standard FCM algorithm is sensitive to noise because of not taking into account the spatial information in the im...Fuzzy c-means （FCM） algorithm is one of the most popular methods for image segmentation. However, the standard FCM algorithm is sensitive to noise because of not taking into account the spatial information in the image. An improved FCM algorithm is proposed to improve the antinoise performance of FCM algorithm. The new algorithm is formulated by incorporating the spatial neighborhood information into the membership function for clustering. The distribution statistics of the neighborhood pixels and the prior probability are used to form a new membership func- tion. It is not only effective to remove the noise spots but also can reduce the misclassified pixels. Experimental results indicate that the proposed algorithm is more accurate and robust to noise than the standard FCM algorithm.展开更多
Indian agriculture is striving to achieve sustainable intensification,the system aiming to increase agricultural yield per unit area without harming natural resources and the ecosystem.Modern farming employs technolog...Indian agriculture is striving to achieve sustainable intensification,the system aiming to increase agricultural yield per unit area without harming natural resources and the ecosystem.Modern farming employs technology to improve productivity.Early and accurate analysis and diagnosis of plant disease is very helpful in reducing plant diseases and improving plant health and food crop productivity.Plant disease experts are not available in remote areas thus there is a requirement of automatic low-cost,approachable and reliable solutions to identify the plant diseases without the laboratory inspection and expert’s opinion.Deep learning-based computer vision techniques like Convolutional Neural Network(CNN)and traditional machine learning-based image classification approaches are being applied to identify plant diseases.In this paper,the CNN model is proposed for the classification of rice and potato plant leaf diseases.Rice leaves are diagnosed with bacterial blight,blast,brown spot and tungro diseases.Potato leaf images are classified into three classes:healthy leaves,early blight and late blight diseases.Rice leaf dataset with 5932 images and 1500 potato leaf images are used in the study.The proposed CNN model was able to learn hidden patterns from the raw images and classify rice images with 99.58%accuracy and potato leaves with 97.66%accuracy.The results demonstrate that the proposed CNN model performed better when compared with other machine learning image classifiers such as Support Vector Machine(SVM),K-Nearest Neighbors(KNN),Decision Tree and Random Forest.展开更多
Abstract： The mathematical model of a high-speed underwater vehicle getting catastrophe in the out-of-water course and a nonlinear sliding mode control with the adaptive backstepping approach for the catastrophic cou...Abstract： The mathematical model of a high-speed underwater vehicle getting catastrophe in the out-of-water course and a nonlinear sliding mode control with the adaptive backstepping approach for the catastrophic course are proposed. The speed change is large at the moment that the high-speed underwater vehicle launches out of the water to attack an air target. It causes motion parameter uncertainties and affects the precision attack ability. The trajectory angle dynamic characteristic is based on the description of the transformed state-coordinates, the nonlinear sliding mode control is designed to track a linear reference model. Furthermore, the adaptive backstepping control approach is utilized to improve the robustness against the unknown parameter uncertainties. With the proposed control of attitude tracking, the controlled navigational control system possesses the advantages of good transient performance and robustness to parametric uncertainties. These can be predicted and regulated through the design of a linear reference model that has the desired dynamic behavior for the trajectory of the high-speed underwater vehicle to attack its target. Finally, some digital simulation results show that the control system can be applied to a catastrophic course, and that it illustrates great robustness against system parameter uncertainties and external disturbances.展开更多
The fifth generation （5G） wireless communication is currently a hot research topic and wireless communication systems on high speed railways （HSR） are important applications of 5G technologies. Existing stud- ies ...The fifth generation （5G） wireless communication is currently a hot research topic and wireless communication systems on high speed railways （HSR） are important applications of 5G technologies. Existing stud- ies about 5G wireless systems on high speed railways （HSR） often utilize ideal channel parameters and are usually based on simple scenarios. In this paper, we evaluate the down- link throughput of 5G HSR communication systems on three typical scenarios including urban, cutting and viaduct with three different channel estimators. The channel parameters of each scenario are generated with tapped delay line （TDL） models through ray-tracing sim- ulations, which can be considered as a good match to practical situations. The channel estimators including least square （LS）, linear minimum mean square error （LMMSE）, and our proposed historical information based ba- sis expansion model （HiBEM）. We analyze the performance of the HiBEM estimator in terms of mean square error （MSE） and evaluate the system throughputs with different channel estimates over each scenario. Simulation results are then provided to corroborate our proposed studies. It is shown that our HiBEM estimator outperforms other estimators and that the sys-tem throughput can reach the highest point in the viaduct scenario.展开更多
The 5th generation mobile communications aims at connecting everything and future Internet of Things(IoT)will get everything smartly connected.To realize it,there exist many challenges.One key challenge is the battery...The 5th generation mobile communications aims at connecting everything and future Internet of Things(IoT)will get everything smartly connected.To realize it,there exist many challenges.One key challenge is the battery problem for small devices,such as sensors or tags.Batteryless backscatter,also referred to as or battery-free backscatter,is a new potential technology to address this problem.One early and typical type of batteryless backscatter is ambient backscatter.Generally,batteryless backscatter utilizes environmental wireless signals to enable battery-free devices to communicate with each other.These devices first harvest energy from ambient wireless signals and then backscatter these signals so as to transmit their own information.This paper reviews the current studies about batteryless backscatter,including various backscatter schemes and theoretical works,and then introduces open problems for future research.展开更多
The occurrence of geological disasters can have a large impact on urban safety. Protecting people’s safety is the most important concern when disasters occur. Safety improvement requires a large amount of comprehensi...The occurrence of geological disasters can have a large impact on urban safety. Protecting people’s safety is the most important concern when disasters occur. Safety improvement requires a large amount of comprehensive and representative risk analysis and a large collection of information related to geological hazards, including unstructured knowledge and experience. To address the relevant information and support safety risk analysis, a geological hazard knowledge graph is developed automatically based on computer vision and domain-geoscience ontology to identify geological hazards from input images while obeying safety rules and regulations, even when affected by changes. In the implementation of the knowledge graph, we design an ontology schema of geological disasters based on a top-down approach, and by organizing knowledge as a logical semantic expression, it can be shared using ontology technologies and therefore enable semantic interoperability. Computer vision approaches are then used to automatically detect a set of entities and attributes, using the data from input images, and object types and their attributes are identified so that they can be stored in Neo4j for reasoning and searching. Finally, a reasoning model for geological hazard identification was developed using the Neo4j database to create nodes, relationships, and their properties for modeling, and geological hazards in the images can be automatically identified by searching the Neo4j database. An application on geological hazard is presented. The results show the effectiveness of the proposed approach in terms of identifying possible potential hazards in geological hazards and assisting in formulating targeted preventive measures.展开更多
基金supported by the project“Romanian Hub for Artificial Intelligence-HRIA”,Smart Growth,Digitization and Financial Instruments Program,2021–2027,MySMIS No.334906.
文摘Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods,based on reliable existing data stored in project management tools’datasets,automating this evaluation process becomes a natural step forward.In this context,our approach focuses on quantifying software developer expertise by using metadata from the task-tracking systems.For this,we mathematically formalize two categories of expertise:technology-specific expertise,which denotes the skills required for a particular technology,and general expertise,which encapsulates overall knowledge in the software industry.Afterward,we automatically classify the zones of expertise associated with each task a developer has worked on using Bidirectional Encoder Representations from Transformers(BERT)-like transformers to handle the unique characteristics of project tool datasets effectively.Finally,our method evaluates the proficiency of each software specialist across already completed projects from both technology-specific and general perspectives.The method was experimentally validated,yielding promising results.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.62341305 and 22269002)the Natural Science Foundation of Guangxi Zhuang Autonomous Region,China(Grant No.2024GXNSFFA010007)+2 种基金the Science and Technology Project of Guangxi Zhuang Autonomous Region,China(Grant No.AD19110038)the Key Laboratory of AI and Information Processing,Education Department of Guangxi Zhuang Autonomous Region(Grant No.2024GXZDSY015)the Innovation Project of Guangxi University of Science and Technology Graduate Education(Grant No.GKYC202408)。
文摘A facile one-step hydrothermal method has been reported to synthesize theα-Fe_(2)O_(3)nanosheet arrays with the preferred orientation along the[104]direction on the ITO substrate.Theα-Fe_(2)O_(3)nanosheet arrays-based W/α-Fe_(2)O_(3)/ITO memristor has been achieved by depositing the circular W top electrodes on theα-Fe_(2)O_(3)nanosheet arrays.The as-prepared W/α-Fe_(2)O_(3)/ITO memristor shows a reliable nonvolatile bipolar resistive switching behavior with the high resistance ratio of about 103at the reading voltage of 0.1 V,good resistance retention over 10~3s,ultralow set voltage of-0.6 V and reset voltage of 0.7 V,and good durability.In addition,the tunneling conduction mechanism modified by the oxygen vacancies has been proposed and suggested to be responsible for the nonvolatile resistive switching behavior of the as-prepared W/α-Fe_(2)O_(3)/ITO memristor.This work demonstrates that the as-preparedα-Fe_(2)O_(3)nanosheet arrays-based W/α-Fe_(2)O_(3)/ITO memristor would be a promising candidate for further ultralow power nonvolatile memory applications.
基金supported by grants from International Collaborative Project on The Conservation for the Giant Panda(Grant#2017-127 G.Zhang and 2017-115 to D.Liu)National Natural Science Foundation of China(Grant#31772466).
文摘The role that visual discriminative ability plays among giant pandas in social communication and individual discrimination has received less attention than olfactory and auditory modalities.Here,we used an eye-tracker technology to investigate pupil fixation patterns for 8 captive male giant pandas Ailuropoda melanoleuca.We paired images(N=26)of conspecifics against:1)sympatric predators(gray wolves and tigers),and non-threatening sympatric species(golden pheasant,golden snub-nosed monkey,takin,and red panda),2)conspecifics with atypical fur colora-tion(albino and brown),and 3)zookeepers/non-zookeepers wearing either work uniform or plain clothing.For each session,we tracked the pan-da's pupil movements and measured pupil first fixation point(FFP),fixation latency,total fixation count(TFC),and duration(TFD)of attention to each image.Overall,pandas exhibited similar attention(FFPs and TFCs)to images of predators and non-threatening sympatric species.Images of golden pheasant,snub-nosed monkey,and tiger received less attention(TFD)than images of conspecifics,whereas images of takin and red panda received more attention,suggesting a greater alertness to habitat or food competitors than to potential predators.Pandas'TFCs were greater for images of black-white conspecifics than for albino or brown phenotypes,implying that familiar color elicited more interest.Pandas reacted differently to images of men versus women.For images of women only,pandas gave more attention(TFC)to familiar combinations(uniformed zookeepers and plain-clothed non-zookeepers),consistent with the familiarity hypothesis.That pandas can use visual perception to discriminate intra-specifically and inter-specifically,including details of human appearance,has applications for panda conservation and captive husbandry.
基金supported in part by the Fundamental Research Funds for the Central Universities under Grant 2022JBGP003in part by the National Natural Science Foundation of China(NSFC)under Grant 62071033in part by ZTE IndustryUniversity-Institute Cooperation Funds under Grant No.IA20230217003。
文摘This paper investigates the age of information(AoI)-based multi-user mobile edge computing(MEC)network with partial offloading mode.The weighted sum AoI(WSA)is first analyzed and derived,and then a WSA minimization problem is formulated by jointly optimizing the user scheduling and data assignment.Due to the non-analytic expression of the WSA w.r.t.the optimization variables and the unknowability of future network information,the problem cannot be solved with known solution methods.Therefore,an online Joint Partial Offloading and User Scheduling Optimization(JPOUSO)algorithm is proposed by transforming the original problem into a single-slot data assignment subproblem and a single-slot user scheduling sub-problem and solving the two sub-problems separately.We analyze the computational complexity of the presented JPO-USO algorithm,which is of O(N),with N being the number of users.Simulation results show that the proposed JPO-USO algorithm is able to achieve better AoI performance compared with various baseline methods.It is shown that both the user’s data assignment and the user’s AoI should be jointly taken into account to decrease the system WSA when scheduling users.
文摘Information security and quality management are often considered two different fields. However, organizations must be mindful of how software security may affect quality control. This paper examines and promotes methods through which secure software development processes can be integrated into the Systems Software Development Life-cycle (SDLC) to improve system quality. Cyber-security and quality assurance are both involved in reducing risk. Software security teams work to reduce security risks, whereas quality assurance teams work to decrease risks to quality. There is a need for clear standards, frameworks, processes, and procedures to be followed by organizations to ensure high-level quality while reducing security risks. This research uses a survey of industry professionals to help identify best practices for developing software with fewer defects from the early stages of the SDLC to improve both the quality and security of software. Results show that there is a need for better security awareness among all members of software development teams.
基金supported by the Outstanding Youth Science and Technology Innovation Team Project of Colleges and Universities in Hubei Province(Grant no.T201923)Key Science and Technology Project of Jingmen(Grant nos.2021ZDYF024,2022ZDYF019)Cultivation Project of Jingchu University of Technology(Grant no.PY201904).
文摘Brain tumors,one of the most lethal diseases with low survival rates,require early detection and accurate diagnosis to enable effective treatment planning.While deep learning architectures,particularly Convolutional Neural Networks(CNNs),have shown significant performance improvements over traditional methods,they struggle to capture the subtle pathological variations between different brain tumor types.Recent attention-based models have attempted to address this by focusing on global features,but they come with high computational costs.To address these challenges,this paper introduces a novel parallel architecture,ParMamba,which uniquely integrates Convolutional Attention Patch Embedding(CAPE)and the Conv Mamba block including CNN,Mamba and the channel enhancement module,marking a significant advancement in the field.The unique design of ConvMamba block enhances the ability of model to capture both local features and long-range dependencies,improving the detection of subtle differences between tumor types.The channel enhancement module refines feature interactions across channels.Additionally,CAPE is employed as a downsampling layer that extracts both local and global features,further improving classification accuracy.Experimental results on two publicly available brain tumor datasets demonstrate that ParMamba achieves classification accuracies of 99.62%and 99.35%,outperforming existing methods.Notably,ParMamba surpasses vision transformers(ViT)by 1.37%in accuracy,with a throughput improvement of over 30%.These results demonstrate that ParMamba delivers superior performance while operating faster than traditional attention-based methods.
基金financially supported by the Natural Science Foundation of China(42301492)the Open Fund of Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering(2022SDSJ04,2024SDSJ03)+1 种基金the Opening Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education(GLAB 2023ZR01,GLAB2024ZR08)the Fundamental Research Funds for the Central Universities.
文摘Automatic segmentation and recognition of content and element information in color geological map are of great significance for researchers to analyze the distribution of mineral resources and predict disaster information.This article focuses on color planar raster geological map(geological maps include planar geological maps,columnar maps,and profiles).While existing deep learning approaches are often used to segment general images,their performance is limited due to complex elements,diverse regional features,and complicated backgrounds for color geological map in the domain of geoscience.To address the issue,a color geological map segmentation model is proposed that combines the Felz clustering algorithm and an improved SE-UNet deep learning network(named GeoMSeg).Firstly,a symmetrical encoder-decoder structure backbone network based on UNet is constructed,and the channel attention mechanism SENet has been incorporated to augment the network’s capacity for feature representation,enabling the model to purposefully extract map information.The SE-UNet network is employed for feature extraction from the geological map and obtain coarse segmentation results.Secondly,the Felz clustering algorithm is used for super pixel pre-segmentation of geological maps.The coarse segmentation results are refined and modified based on the super pixel pre-segmentation results to obtain the final segmentation results.This study applies GeoMSeg to the constructed dataset,and the experimental results show that the algorithm proposed in this paper has superior performance compared to other mainstream map segmentation models,with an accuracy of 91.89%and a MIoU of 71.91%.
基金supported by the Deanship of Scientific Research,King Saud University through the Vice Deanship of Scientific Research Chairs,Chair of Pervasive and Mobile Computing.
文摘Breast cancer diagnosis relies heavily on many kinds of information from diverse sources—like mammogram images,ultrasound scans,patient records,and genetic tests—but most AI tools look at only one of these at a time,which limits their ability to produce accurate and comprehensive decisions.In recent years,multimodal learning has emerged,enabling the integration of heterogeneous data to improve performance and diagnostic accuracy.However,doctors cannot always see how or why these AI tools make their choices,which is a significant bottleneck in their reliability,along with adoption in clinical settings.Hence,people are adding explainable AI techniques that show the steps the model takes.This review investigates previous work that has employed multimodal learning and XAI for the diagnosis of breast cancer.It discusses the types of data,fusion techniques,and XAI models employed.It was done following the PRISMA guidelines and included studies from 2021 to April 2025.The literature search was performed systematically and resulted in 61 studies.The review highlights a gradual increase in current studies focusing on multimodal fusion and XAI,particularly in the years 2023–2024.It found that studies using multi-modal data fusion achieved the highest accuracy by 5%–10%on average compared to other studies that used single-modality data,an intermediate fusion strategy,and modern fusion techniques,such as cross attention,achieved the highest accuracy and best performance.The review also showed that SHAP,Grad-CAM,and LIME techniques are the most used in explaining breast cancer diagnostic models.There is a clear research shift toward integrating multimodal learning and XAI techniques into the breast cancer diagnostics field.However,several gaps were identified,including the scarcity of public multimodal datasets.Lack of a unified explainable framework in multimodal fusion systems,and lack of standardization in evaluating explanations.These limitations call for future research focused on building more shared datasets and integrating multimodal data and explainable AI techniques to improve decision-making and enhance transparency.
基金supported in part by Natural Science Foundation of Hubei Province of China under Grant 2023AFB016the 2022 Opening Fund for Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering under Grant 2022SDSJ02the Construction Fund for Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering under Grant 2019ZYYD007.
文摘Images and videos play an increasingly vital role in daily life and are widely utilized as key evidentiary sources in judicial investigations and forensic analysis.Simultaneously,advancements in image and video processing technologies have facilitated the widespread availability of powerful editing tools,such as Deepfakes,enabling anyone to easily create manipulated or fake visual content,which poses an enormous threat to social security and public trust.To verify the authenticity and integrity of images and videos,numerous approaches have been proposed,which are primarily based on content analysis and their effectiveness is susceptible to interference from various image or video post-processing operations.Recent research has highlighted the potential of file containers analysis as a promising forensic approach that offers efficient and interpretable results.However,there is still a lack of review articles on this kind of approach.In order to fill this gap,we present a comprehensive review of file containers-based image and video forensics in this paper.Specifically,we categorize the existing methods into two distinct stages,qualitative analysis and quantitative analysis.In addition,an overall framework is proposed to organize the exiting approaches.Then,the advantages and disadvantages of the schemes used across different forensic tasks are provided.Finally,we outline the trends in this research area,aiming to provide valuable insights and technical guidance for future research.
基金supported by the National Natural Science Foundation of China(Grant Nos.62341305,61805053,and 22269002)the Science and Technology Project of Guangxi Zhuang Autonomous Region,China(Grant Nos.AD19110038 and AD21238033)。
文摘A facile sol–gel method and heating treatment process have been reported to synthesize the wurtzite phase ZnO nanofilms with the preferential growth orientation along the[001]direction on the FTO substrates.The as-prepared wurtzite phase ZnO nanofilms-based memristor with the W/ZnO/FTO sandwich has demonstrated a reliable nonvolatile bipolar resistive switching behaviors with an ultralow set voltage of about +3 V and reset voltage of approximately-3.6 V,high resistive switching ratio of more than two orders of magnitude,good resistance retention ability(up to 10^(4)s),and excellent durability.Furthermore,the resistive switching behavior in the low-resistance state is attributed to the Ohmic conduction mechanism,while the resistive switching behavior in the high-resistance state is controlled by the trap-modulated space charge limited current(SCLC)mechanism.In addition,the conductive filament model regulated by the oxygen vacancies has been proposed,where the nonvolatile bipolar resistive switching behaviors could be attributed to the formation and rupture of conductive filaments in the W/ZnO/FTO memristor.This work demonstrates that the as-prepared wurtzite phase ZnO nanofilms-based W/ZnO/FTO memristor has promising prospects in future nonvolatile memory applications.
基金funded by Scientific and Technological Research Project and Technology Innovation Platform Project of Huibei Provincial Department of Science and Technology(2025AFD345 and 2024CSA071)grant from Huanggang Science and Technology Bureau(ZDZX20240008)。
文摘Polygonati Rhizoma,a functional food and a traditional Chinese medicine broadly used in China and several Southeast Asia countries,possesses effective health-promoting activities.Prepared from 3 plants in Polygonatum genus(Polygonatum kingianum,Polygonatum sibiricum,and Polygonatum cyrtonema),Polygonati Rhizoma has drawn increasing attention due to its remarkable immune-enhancing and metabolic regulatory activities in recent years.In this review,we summarized the updated research of chemical constituents and biological activities of Polygonati Rhizoma,especially the metabolic regulation,immunomodulatory effects,and anti-fatigue activities,aiming to provide a comprehensive understanding,broaden the usage and promote more in-depth exploration of Polygonati Rhizoma as a functional food.
文摘This study aimed to explore the relationship between Soil-Plant Analysis Development(SPAD)values and key environmental factors in cucumber(Cucumis sativus L.)cultivation in a greenhouse.SPAD values,indicative of chlorophyll content,reflect plant health and productivity.The analysis revealed strong positive correlations between SPADvalues and both indoor light intensity(ILI,r=0.59,p<0.001)and outdoor light intensity(OLI,r=0.62,p<0.001),suggesting that higher light intensities were associated with enhanced SPAD values.In contrast,significant negative correlations were found between SPAD values and soil temperature at 15-30 cm depth(ST1530,r=−0.47,p<0.001)and volumetric soil moisture content at the same depth(SM1530,r=−0.52,p<0.001),with higher soil temperatures(e.g.,28℃)and excessive moisture(e.g.,25%)leading to reduced SPAD values.Multiple regression analysis identified ST1530 and SM1530 as significant negative predictors of SPAD,with coefficients of−0.97(p=0.05)and−0.34(p=0.05),respectively,suggesting that increases in soil temperature and moisture result in lower SPAD values.Indoor light intensity(e.g.,600-800μmol/m^(2)/s)emerged as a significant positive contributor,with a coefficient of 0.01(p<0.001),highlighting its role in promoting chlorophyll synthesis.Additionally,relative humidity(r=0.27,p<0.01)showed a positive,although less pronounced,association with SPAD.These results underscore the importance of both direct and indirect environmental factors in influencing SPAD variability and,by extension,plant health and productivity in cucumber cultivation.
基金the King Salman Centre for Disability Research for funding this work through Research Group No.KSRG-2024-068。
文摘Earlier notification and fire detection methods provide safety information and fire prevention to blind and visually impaired(BVI)individuals in a limited timeframe in the event of emergencies,particularly in enclosed areas.Fire detection becomes crucial as it directly impacts human safety and the environment.While modern technology requires precise techniques for early detection to prevent damage and loss,few research has focused on artificial intelligence(AI)-based early fire alert systems for BVI individuals in indoor settings.To prevent such fire incidents,it is crucial to identify fires accurately and promptly,and alert BVI personnel using a combination of smart glasses,deep learning(DL),and computer vision(CV).The most recent technologies require effective methods to identify fires quickly,preventing damage and physical loss.In this manuscript,an Enhanced Fire Detection System for Blind and Visually Challenged People using Artificial Intelligence with Deep Convolutional Neural Networks(EFDBVC-AIDCNN)model is presented.The EFDBVC-AIDCNN model presents an advanced fire detection system that utilizes AI to detect and classify fire hazards for BVI people effectively.Initially,image pre-processing is performed using the Gabor filter(GF)model to improve texture details and patterns specific to flames and smoke.For the feature extractor,the Swin transformer(ST)model captures fine details across multiple scales to represent fire patterns accurately.Furthermore,the Elman neural network(ENN)technique is implemented to detect fire.The improved whale optimization algorithm(IWOA)is used to efficiently tune ENN parameters,improving accuracy and robustness across varying lighting and environmental conditions to optimize performance.An extensive experimental study of the EFDBVC-AIDCNN technique is accomplished under the fire detection dataset.A short comparative analysis of the EFDBVC-AIDCNN approach portrayed a superior accuracy value of 96.60%over existing models.
基金supported in part by the National Natural Science Foundation of China(62176059)supported by The Pennsylvania State University.
文摘Finding suitable initial noise that retains the original image’s information is crucial for image-to-image(I2I)translation using text-to-image(T2I)diffusion models.A common approach is to add random noise directly to the original image,as in SDEdit.However,we have observed that this can result in“semantic discrepancy”issues,wherein T2I diffusion models misinterpret the semantic relationships and generate content not present in the original image.We identify that the noise introduced by SDEdit disrupts the semantic integrity of the image,leading to unintended associations between unrelated regions after U-Net upsampling.Building on the widely-used latent diffusion model,Stable Diffusion,we propose a training-free,plugand-play method to alleviate semantic discrepancy and enhance the fidelity of the translated image.By leveraging the deterministic nature of denoising diffusion implicit models(DDIMs)inversion,we correct the erroneous features and correlations from the original generative process with accurate ones from DDIM inversion.This approach alleviates semantic discrepancy and surpasses recent DDIM-inversion-based methods such as PnP with fewer priors,achieving a speedup of 11.2 times in experiments conducted on COCO,ImageNet,and ImageNet-R datasets across multiple I2I translation tasks.
基金supported by the National Natural Science Foundation of China(6087403160740430664)
文摘Fuzzy c-means （FCM） algorithm is one of the most popular methods for image segmentation. However, the standard FCM algorithm is sensitive to noise because of not taking into account the spatial information in the image. An improved FCM algorithm is proposed to improve the antinoise performance of FCM algorithm. The new algorithm is formulated by incorporating the spatial neighborhood information into the membership function for clustering. The distribution statistics of the neighborhood pixels and the prior probability are used to form a new membership func- tion. It is not only effective to remove the noise spots but also can reduce the misclassified pixels. Experimental results indicate that the proposed algorithm is more accurate and robust to noise than the standard FCM algorithm.
基金This research supported by KAU Scientific Endowment,King Abdulaziz University,Jeddah,Saudi Arabia under Grant Number KAU 2020/251.
文摘Indian agriculture is striving to achieve sustainable intensification,the system aiming to increase agricultural yield per unit area without harming natural resources and the ecosystem.Modern farming employs technology to improve productivity.Early and accurate analysis and diagnosis of plant disease is very helpful in reducing plant diseases and improving plant health and food crop productivity.Plant disease experts are not available in remote areas thus there is a requirement of automatic low-cost,approachable and reliable solutions to identify the plant diseases without the laboratory inspection and expert’s opinion.Deep learning-based computer vision techniques like Convolutional Neural Network(CNN)and traditional machine learning-based image classification approaches are being applied to identify plant diseases.In this paper,the CNN model is proposed for the classification of rice and potato plant leaf diseases.Rice leaves are diagnosed with bacterial blight,blast,brown spot and tungro diseases.Potato leaf images are classified into three classes:healthy leaves,early blight and late blight diseases.Rice leaf dataset with 5932 images and 1500 potato leaf images are used in the study.The proposed CNN model was able to learn hidden patterns from the raw images and classify rice images with 99.58%accuracy and potato leaves with 97.66%accuracy.The results demonstrate that the proposed CNN model performed better when compared with other machine learning image classifiers such as Support Vector Machine(SVM),K-Nearest Neighbors(KNN),Decision Tree and Random Forest.
基金supported by Hubei Provincial Natural Science Foundation of China(No.2012FFC09401)
文摘Abstract： The mathematical model of a high-speed underwater vehicle getting catastrophe in the out-of-water course and a nonlinear sliding mode control with the adaptive backstepping approach for the catastrophic course are proposed. The speed change is large at the moment that the high-speed underwater vehicle launches out of the water to attack an air target. It causes motion parameter uncertainties and affects the precision attack ability. The trajectory angle dynamic characteristic is based on the description of the transformed state-coordinates, the nonlinear sliding mode control is designed to track a linear reference model. Furthermore, the adaptive backstepping control approach is utilized to improve the robustness against the unknown parameter uncertainties. With the proposed control of attitude tracking, the controlled navigational control system possesses the advantages of good transient performance and robustness to parametric uncertainties. These can be predicted and regulated through the design of a linear reference model that has the desired dynamic behavior for the trajectory of the high-speed underwater vehicle to attack its target. Finally, some digital simulation results show that the control system can be applied to a catastrophic course, and that it illustrates great robustness against system parameter uncertainties and external disturbances.
基金supported by the National Natural Science Foundation of China(Grant Nos.61522109,61671253,61571037and 91738201)the Fundamental Research Funds for the Central Universities(No.2016JBZ006)+1 种基金the Natural Science Foundation of Jiangsu Province(Grant Nos.BK20150040and BK20171446)the Key Project of Natural Science Research of Higher Education Institutions of Jiangsu Province(No.15KJA510003)
文摘The fifth generation （5G） wireless communication is currently a hot research topic and wireless communication systems on high speed railways （HSR） are important applications of 5G technologies. Existing stud- ies about 5G wireless systems on high speed railways （HSR） often utilize ideal channel parameters and are usually based on simple scenarios. In this paper, we evaluate the down- link throughput of 5G HSR communication systems on three typical scenarios including urban, cutting and viaduct with three different channel estimators. The channel parameters of each scenario are generated with tapped delay line （TDL） models through ray-tracing sim- ulations, which can be considered as a good match to practical situations. The channel estimators including least square （LS）, linear minimum mean square error （LMMSE）, and our proposed historical information based ba- sis expansion model （HiBEM）. We analyze the performance of the HiBEM estimator in terms of mean square error （MSE） and evaluate the system throughputs with different channel estimates over each scenario. Simulation results are then provided to corroborate our proposed studies. It is shown that our HiBEM estimator outperforms other estimators and that the sys-tem throughput can reach the highest point in the viaduct scenario.
基金This paper is funded by Scientific Research Program of Beijing Municipal Commission of Education No.KM201910853003.
文摘The 5th generation mobile communications aims at connecting everything and future Internet of Things(IoT)will get everything smartly connected.To realize it,there exist many challenges.One key challenge is the battery problem for small devices,such as sensors or tags.Batteryless backscatter,also referred to as or battery-free backscatter,is a new potential technology to address this problem.One early and typical type of batteryless backscatter is ambient backscatter.Generally,batteryless backscatter utilizes environmental wireless signals to enable battery-free devices to communicate with each other.These devices first harvest energy from ambient wireless signals and then backscatter these signals so as to transmit their own information.This paper reviews the current studies about batteryless backscatter,including various backscatter schemes and theoretical works,and then introduces open problems for future research.
基金the IUGS Deep-time Digital Earth (DDE) Big Science Programfinancially supported by the National Key R & D Program of China (No.2022YFF0711601)+3 种基金the Natural Science Foundation of Hubei Province of China (No.2022CFB640)the Opening Fund of Hubei Key Laboratory of Intelligent Vision-Based Monitoring for Hydroelectric Engineering (No.2022SDSJ04)the Opening Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education (No.GLAB 2023ZR01)the Fundamental Research Funds for the Central Universities。
文摘The occurrence of geological disasters can have a large impact on urban safety. Protecting people’s safety is the most important concern when disasters occur. Safety improvement requires a large amount of comprehensive and representative risk analysis and a large collection of information related to geological hazards, including unstructured knowledge and experience. To address the relevant information and support safety risk analysis, a geological hazard knowledge graph is developed automatically based on computer vision and domain-geoscience ontology to identify geological hazards from input images while obeying safety rules and regulations, even when affected by changes. In the implementation of the knowledge graph, we design an ontology schema of geological disasters based on a top-down approach, and by organizing knowledge as a logical semantic expression, it can be shared using ontology technologies and therefore enable semantic interoperability. Computer vision approaches are then used to automatically detect a set of entities and attributes, using the data from input images, and object types and their attributes are identified so that they can be stored in Neo4j for reasoning and searching. Finally, a reasoning model for geological hazard identification was developed using the Neo4j database to create nodes, relationships, and their properties for modeling, and geological hazards in the images can be automatically identified by searching the Neo4j database. An application on geological hazard is presented. The results show the effectiveness of the proposed approach in terms of identifying possible potential hazards in geological hazards and assisting in formulating targeted preventive measures.
