Climate change is a global phenomenon that has profound impacts on ecological dynamics and biodiversity,shaping the interactions between species and their environment.To gain a deeper understanding of the mechanisms d...Climate change is a global phenomenon that has profound impacts on ecological dynamics and biodiversity,shaping the interactions between species and their environment.To gain a deeper understanding of the mechanisms driving climate change,phenological monitoring is essential.Traditional methods of defining phenological phases often rely on fixed thresholds.However,with the development of technology,deep learning-based classification models are now able to more accurately delineate phenological phases from images,enabling phenological monitoring.Despite the significant advancements these models have made in phenological monitoring,they still face challenges in fully capturing the complexity of biotic-environmental interactions,which can limit the fine-grained accuracy of phenological phase identification.To address this,we propose a novel deep learning model,RESformer,designed to monitor tree phenology at a fine-grained level using PhenoCam images.RESformer features a lightweight structure,making it suitable for deployment in resource-constrained environments.It incorporates a dual-branch routing mechanism that considers both global and local information,thereby improving the accuracy of phenological monitoring.To validate the effectiveness of RESformer,we conducted a case study involving 82,118 images taken over two years from four different locations in Wisconsin,focusing on the phenology of Acer.The images were classified into seven distinct phenological stages,with RESformer achieving an overall monitoring accuracy of 96.02%.Furthermore,we compared RESformer with a phenological monitoring approach based on the Green Chromatic Coordinate(GCC)index and ten popular classification models.The results showed that RESformer excelled in fine-grained monitoring,effectively capturing and identifying changes in phenological stages.This finding not only provides strong support for monitoring the phenology of Acer species but also offers valuable insights for understanding ecological trends and developing more effective ecosystem conservation and management strategies.展开更多
The number of mobile application services is showing an explosive growth trend,which makes it difficult for users to determine which ones are of interest.Especially,the new mobile application services are emerge conti...The number of mobile application services is showing an explosive growth trend,which makes it difficult for users to determine which ones are of interest.Especially,the new mobile application services are emerge continuously,most of them have not be rated when they need to be recommended to users.This is the typical problem of cold start in the field of collaborative filtering recommendation.This problem may makes it difficult for users to locate and acquire the services that they actually want,and the accuracy and novelty of service recommendations are also difficult to satisfy users.To solve this problem,a hybrid recommendation method for mobile application services based on content feature extraction is proposed in this paper.First,the proposed method in this paper extracts service content features through Natural Language Processing technologies such as word segmentation,part-of-speech tagging,and dependency parsing.It improves the accuracy of describing service attributes and the rationality of the method of calculating service similarity.Then,a language representation model called Bidirectional Encoder Representation from Transformers(BERT)is used to vectorize the content feature text,and an improved weighted word mover’s distance algorithm based on Term Frequency-Inverse Document Frequency(TFIDF-WMD)is used to calculate the similarity of mobile application services.Finally,the recommendation process is completed by combining the item-based collaborative filtering recommendation algorithm.The experimental results show that by using the proposed hybrid recommendation method presented in this paper,the cold start problem is alleviated to a certain extent,and the accuracy of the recommendation result has been significantly improved.展开更多
In order to optimize resource integration and optimal scheduling problems in the cloud manufacturing environment,this paper proposes to use load balancing,service cost and service quality as optimization goals for res...In order to optimize resource integration and optimal scheduling problems in the cloud manufacturing environment,this paper proposes to use load balancing,service cost and service quality as optimization goals for resource scheduling,however,resource providers have resource utilization requirements for cloud manufacturing platforms.In the process of resource optimization scheduling,the interests of all parties have conflicts of interest,which makes it impossible to obtain better optimization results for resource scheduling.Therefore,amultithreaded auto-negotiation method based on the Stackelberg game is proposed to resolve conflicts of interest in the process of resource scheduling.The cloud manufacturing platform first calculates the expected value reduction plan for each round of global optimization,using the negotiation algorithm based on the Stackelberg game,the cloud manufacturing platformnegotiates andmediateswith the participants’agents,to maximize self-interest by constantly changing one’s own plan,iteratively find multiple sets of locally optimized negotiation plans and return to the cloud manufacturing platform.Through multiple rounds of negotiation and calculation,we finally get a target expected value reduction plan that takes into account the benefits of the resource provider and the overall benefits of the completion of the manufacturing task.Finally,through experimental simulation and comparative analysis,the validity and rationality of the model are verified.展开更多
Pine wood nematode infection is a devastating disease.Unmanned aerial vehicle(UAV)remote sensing enables timely and precise monitoring.However,UAV aerial images are challenged by small target size and complex sur-face...Pine wood nematode infection is a devastating disease.Unmanned aerial vehicle(UAV)remote sensing enables timely and precise monitoring.However,UAV aerial images are challenged by small target size and complex sur-face backgrounds which hinder their effectiveness in moni-toring.To address these challenges,based on the analysis and optimization of UAV remote sensing images,this study developed a spatio-temporal multi-scale fusion algorithm for disease detection.The multi-head,self-attention mechanism is incorporated to address the issue of excessive features generated by complex surface backgrounds in UAV images.This enables adaptive feature control to suppress redundant information and boost the model’s feature extraction capa-bilities.The SPD-Conv module was introduced to address the problem of loss of small target feature information dur-ing feature extraction,enhancing the preservation of key features.Additionally,the gather-and-distribute mechanism was implemented to augment the model’s multi-scale feature fusion capacity,preventing the loss of local details during fusion and enriching small target feature information.This study established a dataset of pine wood nematode disease in the Huangshan area using DJI(DJ-Innovations)UAVs.The results show that the accuracy of the proposed model with spatio-temporal multi-scale fusion reached 78.5%,6.6%higher than that of the benchmark model.Building upon the timeliness and flexibility of UAV remote sensing,the pro-posed model effectively addressed the challenges of detect-ing small and medium-size targets in complex backgrounds,thereby enhancing the detection efficiency for pine wood nematode disease.This facilitates early preemptive preser-vation of diseased trees,augments the overall monitoring proficiency of pine wood nematode diseases,and supplies technical aid for proficient monitoring.展开更多
Diagnosing multi-stage diseases typically requires doctors to consider multiple data sources,including clinical symptoms,physical signs,biochemical test results,imaging findings,pathological examination data,and even ...Diagnosing multi-stage diseases typically requires doctors to consider multiple data sources,including clinical symptoms,physical signs,biochemical test results,imaging findings,pathological examination data,and even genetic data.When applying machine learning modeling to predict and diagnose multi-stage diseases,several challenges need to be addressed.Firstly,the model needs to handle multimodal data,as the data used by doctors for diagnosis includes image data,natural language data,and structured data.Secondly,privacy of patients’data needs to be protected,as these data contain the most sensitive and private information.Lastly,considering the practicality of the model,the computational requirements should not be too high.To address these challenges,this paper proposes a privacy-preserving federated deep learning diagnostic method for multi-stage diseases.This method improves the forward and backward propagation processes of deep neural network modeling algorithms and introduces a homomorphic encryption step to design a federated modeling algorithm without the need for an arbiter.It also utilizes dedicated integrated circuits to implement the hardware Paillier algorithm,providing accelerated support for homomorphic encryption in modeling.Finally,this paper designs and conducts experiments to evaluate the proposed solution.The experimental results show that in privacy-preserving federated deep learning diagnostic modeling,the method in this paper achieves the same modeling performance as ordinary modeling without privacy protection,and has higher modeling speed compared to similar algorithms.展开更多
The problem of data island hinders the application of big data in artificial intelligence model training,so researchers propose a federated learning framework.It enables model training without having to centralize all...The problem of data island hinders the application of big data in artificial intelligence model training,so researchers propose a federated learning framework.It enables model training without having to centralize all data in a central storage point.In the current horizontal federated learning scheme,each participant gets the final jointly trained model.No solution is proposed for scenarios where participants only provide training data in exchange for benefits,but do not care about the final jointly trained model.Therefore,this paper proposes a newboosted tree algorithm,calledRPBT(the originator Rights Protected federated Boosted Tree algorithm).Compared with the current horizontal federal learning algorithm,each participant will obtain the final jointly trained model.RPBT can guarantee that the local data of the participants will not be leaked,while the final jointly trained model cannot be obtained.It is worth mentioning that,from the perspective of the participants,the scheme uses the batch idea to make the participants participate in the training in random batches.Therefore,this scheme is more suitable for scenarios where a large number of participants are jointly modeling.Furthermore,a small number of participants will not actually participate in the joint training process.Therefore,the proposed scheme is more secure.Theoretical analysis and experimental evaluations show that RPBT is secure,accurate and efficient.展开更多
Road networks have been used in a wide range of applications to reduces the cost of transportation and improve the quality of related services.The shortest road distance computation has been considered as one of the m...Road networks have been used in a wide range of applications to reduces the cost of transportation and improve the quality of related services.The shortest road distance computation has been considered as one of the most fundamental operations of road networks computation.To alleviate privacy concerns about location privacy leaks during road distance computation,it is desirable to have a secure and efficient road distance computation approach.In this paper,we propose two secure road distance computation approaches,which can compute road distance over encrypted data efficiently.An approximate road distance computation approach is designed by using Partially Homomorphic Encryption and road network set embedding.An exact road distance computation is built by using Somewhat Homomorphic Encryption and road network hypercube embedding.We implement our two road distance computation approaches,and evaluate them on the real cityscale road network.Evaluation results show that our approaches are accurate and efficient.展开更多
In the medical field,the classification and analysis of blood samples has always been arduous work.In the previous work of this task,manual classification maneuvers have been used,which are time consuming and laboriou...In the medical field,the classification and analysis of blood samples has always been arduous work.In the previous work of this task,manual classification maneuvers have been used,which are time consuming and laborious.The conventional blood image classification research is mainly focused on the microscopic cell image classification,while the macroscopic reagent processing blood coagulation image classification research is still blank.These blood samples processed with reagents often show some inherent shape characteristics,such as coagulation,attachment,discretization and so on.The shape characteristics of these blood samples also make it possible for us to recognize their classification through computer vision algorithms.Blood sample classification focuses on the texture and shape of the picture.HOG feature is a kind of feature descriptor used for object detection in computer vision and image processing.It can better extract the outline and texture features of the image by calculating and counting the histogram of oriented gradient of the local region of the image.Because the medical machines that need to identify and classify blood samples often lack strong calculation power,the current popular machine-learning classification algorithms cannot play a good role in these machines.In addition,the characteristics of blood samples produced by different types of reagents and processing methods are different,and it is difficult to obtain real samples,so the amount of data that can be used for training is small.Combining the above conditions and the experimental comparison of a variety of classification algorithms,we find that the lightweight SVMmodel has a better performance on this problem,and the combination of HOG and SVM has also been widely used in other research.The experiment demonstrated that the classification algorithm based on SVM and HOG can give a good result of both performance and accuracy in the classification of blood samples problem.展开更多
基金supported by the National Natural Science Foundation of China(32171777)the Natural Science Foundation of Heilongjiang for Distinguished Young Scientists(JQ2023F002)the Fundamental Research Funds for Central Universities(2572023CT16).
文摘Climate change is a global phenomenon that has profound impacts on ecological dynamics and biodiversity,shaping the interactions between species and their environment.To gain a deeper understanding of the mechanisms driving climate change,phenological monitoring is essential.Traditional methods of defining phenological phases often rely on fixed thresholds.However,with the development of technology,deep learning-based classification models are now able to more accurately delineate phenological phases from images,enabling phenological monitoring.Despite the significant advancements these models have made in phenological monitoring,they still face challenges in fully capturing the complexity of biotic-environmental interactions,which can limit the fine-grained accuracy of phenological phase identification.To address this,we propose a novel deep learning model,RESformer,designed to monitor tree phenology at a fine-grained level using PhenoCam images.RESformer features a lightweight structure,making it suitable for deployment in resource-constrained environments.It incorporates a dual-branch routing mechanism that considers both global and local information,thereby improving the accuracy of phenological monitoring.To validate the effectiveness of RESformer,we conducted a case study involving 82,118 images taken over two years from four different locations in Wisconsin,focusing on the phenology of Acer.The images were classified into seven distinct phenological stages,with RESformer achieving an overall monitoring accuracy of 96.02%.Furthermore,we compared RESformer with a phenological monitoring approach based on the Green Chromatic Coordinate(GCC)index and ten popular classification models.The results showed that RESformer excelled in fine-grained monitoring,effectively capturing and identifying changes in phenological stages.This finding not only provides strong support for monitoring the phenology of Acer species but also offers valuable insights for understanding ecological trends and developing more effective ecosystem conservation and management strategies.
基金Project supported by the National Natural Science Foundation,China(No.62172123)the Postdoctoral Science Foundation of Heilongjiang Province,China(No.LBH-Z19067)+1 种基金the special projects for the central government to guide the development of local science and technology,China(No.ZY20B11)the Natural Science Foundation of Heilongjiang Province,China(No.QC2018081).
文摘The number of mobile application services is showing an explosive growth trend,which makes it difficult for users to determine which ones are of interest.Especially,the new mobile application services are emerge continuously,most of them have not be rated when they need to be recommended to users.This is the typical problem of cold start in the field of collaborative filtering recommendation.This problem may makes it difficult for users to locate and acquire the services that they actually want,and the accuracy and novelty of service recommendations are also difficult to satisfy users.To solve this problem,a hybrid recommendation method for mobile application services based on content feature extraction is proposed in this paper.First,the proposed method in this paper extracts service content features through Natural Language Processing technologies such as word segmentation,part-of-speech tagging,and dependency parsing.It improves the accuracy of describing service attributes and the rationality of the method of calculating service similarity.Then,a language representation model called Bidirectional Encoder Representation from Transformers(BERT)is used to vectorize the content feature text,and an improved weighted word mover’s distance algorithm based on Term Frequency-Inverse Document Frequency(TFIDF-WMD)is used to calculate the similarity of mobile application services.Finally,the recommendation process is completed by combining the item-based collaborative filtering recommendation algorithm.The experimental results show that by using the proposed hybrid recommendation method presented in this paper,the cold start problem is alleviated to a certain extent,and the accuracy of the recommendation result has been significantly improved.
基金Project was supported by the special projects for the central government to guide the development of local science and technology(ZY20B11).
文摘In order to optimize resource integration and optimal scheduling problems in the cloud manufacturing environment,this paper proposes to use load balancing,service cost and service quality as optimization goals for resource scheduling,however,resource providers have resource utilization requirements for cloud manufacturing platforms.In the process of resource optimization scheduling,the interests of all parties have conflicts of interest,which makes it impossible to obtain better optimization results for resource scheduling.Therefore,amultithreaded auto-negotiation method based on the Stackelberg game is proposed to resolve conflicts of interest in the process of resource scheduling.The cloud manufacturing platform first calculates the expected value reduction plan for each round of global optimization,using the negotiation algorithm based on the Stackelberg game,the cloud manufacturing platformnegotiates andmediateswith the participants’agents,to maximize self-interest by constantly changing one’s own plan,iteratively find multiple sets of locally optimized negotiation plans and return to the cloud manufacturing platform.Through multiple rounds of negotiation and calculation,we finally get a target expected value reduction plan that takes into account the benefits of the resource provider and the overall benefits of the completion of the manufacturing task.Finally,through experimental simulation and comparative analysis,the validity and rationality of the model are verified.
基金funded by The National Natural Science Foundation of China(32271865)The Fundamental Research Funds for Central Universities(2572023CT16)the Fundamental Research Funds for Natural Science Foundation of Heilongjiang for Distinguished Young Scientists(JQ2023F002).
文摘Pine wood nematode infection is a devastating disease.Unmanned aerial vehicle(UAV)remote sensing enables timely and precise monitoring.However,UAV aerial images are challenged by small target size and complex sur-face backgrounds which hinder their effectiveness in moni-toring.To address these challenges,based on the analysis and optimization of UAV remote sensing images,this study developed a spatio-temporal multi-scale fusion algorithm for disease detection.The multi-head,self-attention mechanism is incorporated to address the issue of excessive features generated by complex surface backgrounds in UAV images.This enables adaptive feature control to suppress redundant information and boost the model’s feature extraction capa-bilities.The SPD-Conv module was introduced to address the problem of loss of small target feature information dur-ing feature extraction,enhancing the preservation of key features.Additionally,the gather-and-distribute mechanism was implemented to augment the model’s multi-scale feature fusion capacity,preventing the loss of local details during fusion and enriching small target feature information.This study established a dataset of pine wood nematode disease in the Huangshan area using DJI(DJ-Innovations)UAVs.The results show that the accuracy of the proposed model with spatio-temporal multi-scale fusion reached 78.5%,6.6%higher than that of the benchmark model.Building upon the timeliness and flexibility of UAV remote sensing,the pro-posed model effectively addressed the challenges of detect-ing small and medium-size targets in complex backgrounds,thereby enhancing the detection efficiency for pine wood nematode disease.This facilitates early preemptive preser-vation of diseased trees,augments the overall monitoring proficiency of pine wood nematode diseases,and supplies technical aid for proficient monitoring.
基金funded by the National Natural Science Foundation,China(No.62172123)the Key Research and Development Program of Heilongjiang(Grant No.2022ZX01A36)+1 种基金the Special Projects for the Central Government to Guide the Development of Local Science and Technology,China(No.ZY20B11)the Harbin Manufacturing Technology Innovation Talent Project(No.CXRC20221104236).
文摘Diagnosing multi-stage diseases typically requires doctors to consider multiple data sources,including clinical symptoms,physical signs,biochemical test results,imaging findings,pathological examination data,and even genetic data.When applying machine learning modeling to predict and diagnose multi-stage diseases,several challenges need to be addressed.Firstly,the model needs to handle multimodal data,as the data used by doctors for diagnosis includes image data,natural language data,and structured data.Secondly,privacy of patients’data needs to be protected,as these data contain the most sensitive and private information.Lastly,considering the practicality of the model,the computational requirements should not be too high.To address these challenges,this paper proposes a privacy-preserving federated deep learning diagnostic method for multi-stage diseases.This method improves the forward and backward propagation processes of deep neural network modeling algorithms and introduces a homomorphic encryption step to design a federated modeling algorithm without the need for an arbiter.It also utilizes dedicated integrated circuits to implement the hardware Paillier algorithm,providing accelerated support for homomorphic encryption in modeling.Finally,this paper designs and conducts experiments to evaluate the proposed solution.The experimental results show that in privacy-preserving federated deep learning diagnostic modeling,the method in this paper achieves the same modeling performance as ordinary modeling without privacy protection,and has higher modeling speed compared to similar algorithms.
基金National Natural Science Foundation of China(Grant No.61976064)the National Natural Science Foundation of China(Grant No.62172123).
文摘The problem of data island hinders the application of big data in artificial intelligence model training,so researchers propose a federated learning framework.It enables model training without having to centralize all data in a central storage point.In the current horizontal federated learning scheme,each participant gets the final jointly trained model.No solution is proposed for scenarios where participants only provide training data in exchange for benefits,but do not care about the final jointly trained model.Therefore,this paper proposes a newboosted tree algorithm,calledRPBT(the originator Rights Protected federated Boosted Tree algorithm).Compared with the current horizontal federal learning algorithm,each participant will obtain the final jointly trained model.RPBT can guarantee that the local data of the participants will not be leaked,while the final jointly trained model cannot be obtained.It is worth mentioning that,from the perspective of the participants,the scheme uses the batch idea to make the participants participate in the training in random batches.Therefore,this scheme is more suitable for scenarios where a large number of participants are jointly modeling.Furthermore,a small number of participants will not actually participate in the joint training process.Therefore,the proposed scheme is more secure.Theoretical analysis and experimental evaluations show that RPBT is secure,accurate and efficient.
基金This work was partially supported by National Natural Science Foundation of China(Grant Nos.61601146,61732022)National Key R&D Program of China(Grant No.2016QY05X1000).
文摘Road networks have been used in a wide range of applications to reduces the cost of transportation and improve the quality of related services.The shortest road distance computation has been considered as one of the most fundamental operations of road networks computation.To alleviate privacy concerns about location privacy leaks during road distance computation,it is desirable to have a secure and efficient road distance computation approach.In this paper,we propose two secure road distance computation approaches,which can compute road distance over encrypted data efficiently.An approximate road distance computation approach is designed by using Partially Homomorphic Encryption and road network set embedding.An exact road distance computation is built by using Somewhat Homomorphic Encryption and road network hypercube embedding.We implement our two road distance computation approaches,and evaluate them on the real cityscale road network.Evaluation results show that our approaches are accurate and efficient.
基金supported by the National Natural Science Foundation,China(No.62172123)the Fundamental Research Foundation for of Heilongjiang Province,China(No.2019KYYWF0214),the Postdoctoral Science Foundation of Heilongjiang Province,China(No.LBHZ19067)+1 种基金the special projects for the central government to guide the development of local science and technology,China(No.ZY20B11)the Heilongjiang ProvincialNatural Science Foundation of China,China(No.YQ2019F010).
文摘In the medical field,the classification and analysis of blood samples has always been arduous work.In the previous work of this task,manual classification maneuvers have been used,which are time consuming and laborious.The conventional blood image classification research is mainly focused on the microscopic cell image classification,while the macroscopic reagent processing blood coagulation image classification research is still blank.These blood samples processed with reagents often show some inherent shape characteristics,such as coagulation,attachment,discretization and so on.The shape characteristics of these blood samples also make it possible for us to recognize their classification through computer vision algorithms.Blood sample classification focuses on the texture and shape of the picture.HOG feature is a kind of feature descriptor used for object detection in computer vision and image processing.It can better extract the outline and texture features of the image by calculating and counting the histogram of oriented gradient of the local region of the image.Because the medical machines that need to identify and classify blood samples often lack strong calculation power,the current popular machine-learning classification algorithms cannot play a good role in these machines.In addition,the characteristics of blood samples produced by different types of reagents and processing methods are different,and it is difficult to obtain real samples,so the amount of data that can be used for training is small.Combining the above conditions and the experimental comparison of a variety of classification algorithms,we find that the lightweight SVMmodel has a better performance on this problem,and the combination of HOG and SVM has also been widely used in other research.The experiment demonstrated that the classification algorithm based on SVM and HOG can give a good result of both performance and accuracy in the classification of blood samples problem.
