Broadcasting is an important operation and been widely used in wireless sensor networks （WSNs）. These networks are power constrained as nodes operate with limited battery power. Wireless sensor networks are spatial ...Broadcasting is an important operation and been widely used in wireless sensor networks （WSNs）. These networks are power constrained as nodes operate with limited battery power. Wireless sensor networks are spatial graphs that have much more clustered and much high path-length characteristics. After considering energy- efficient broadcasting in such networks, by combining the small-world characteristic of WSNs and the properties of ant algorithm to quickly identify an optimal path, small-world power-aware broadcast algorithm is introduced and evaluated. Given different densities of network, simulation results show that our algorithm significantly improves life of networks and also reduces communication distances and power consumption.展开更多
In order to solve the ambiguity problems in the semantic context(structure,granularity or scale)emerging in the process of ontology integration application,this paper analyzes the essential characters of context struc...In order to solve the ambiguity problems in the semantic context(structure,granularity or scale)emerging in the process of ontology integration application,this paper analyzes the essential characters of context structure,proposes a novel semantic context generating algorithm,which is implemented over VO-Editor(visual ontology editor),from the satisfiability-based point of view,and proves that the context entity generated by this algorithm is smallest in scale and unique.It offers a feasible means for developers to handle context problems for ontology integration application.展开更多
How to organize crossing social network resources on a higher level of integration and address them to users＇ desktops is an important difficult problem. Especially, there is a lack of efficient approaches to softwar...How to organize crossing social network resources on a higher level of integration and address them to users＇ desktops is an important difficult problem. Especially, there is a lack of efficient approaches to software architecture to build reusable system over the crossing social network, From the viewpoint of temporal logic XYZ/E, this paper proposes a kind of Architecture Descrip- tion Language about the Crossing Social Network system （CSN_ADL）, which can be used to depict the main key processes over the cross-social network system, and formally defines some key concepts, such as relation component, corelation component, override corelation connector, interaction connector, corelation network-oriented architecture, as well as system correctness, system activity, and system safety. Furthermore, some properties of correctness, activity, and safety under the flame CSN_ADL is discussed and depicted formally, which provides a formally theo- retical instruction for architecture reuses.展开更多
In order to improve the performance of classifiers in subjective domains, this paper defines a metric to measure the quality of the subjectively labelled training data (QoSTD) by means of K-means clustering. Then, the...In order to improve the performance of classifiers in subjective domains, this paper defines a metric to measure the quality of the subjectively labelled training data (QoSTD) by means of K-means clustering. Then, the QoSTD is used as a weight of the predicted class scores to adjust the likelihoods of instances. Moreover, two measurements are defined to assess the performance of the classifiers trained by the subjective labelled data. The binary classifiers of Traditional Chinese Medicine (TCM) Zhengs are trained and retrained by the real-world data set, utilizing the support vector machine (SVM) and the discrimination analysis (DA) models, so as to verify the effectiveness of the proposed method. The experimental results show that the consistency of likelihoods of instances with the corresponding observations is increased notable for the classes, especially in the cases with the relatively low QoSTD training data set. The experimental results also indicate the solution how to eliminate the miss-labelled instances from the training data set to re-train the classifiers in the subjective domains.展开更多
Background Lip reading uses lip images for visual speech recognition.Deep-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of shor...Background Lip reading uses lip images for visual speech recognition.Deep-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of short-term temporal dependencies of lip-shape variations between adjacent frames,which leaves space for further improvement in feature extraction.Methods This article presents a spatiotemporal feature fusion network(STDNet)that compensates for the deficiencies of current lip-reading approaches in short-term temporal dependency modeling.Specifically,to distinguish more similar and intricate content,STDNet adds a temporal feature extraction branch based on a 3D-CNN,which enhances the learning of dynamic lip movements in adjacent frames while not affecting spatial feature extraction.In particular,we designed a local–temporal block,which aggregates interframe differences,strengthening the relationship between various local lip regions through multiscale convolution.We incorporated the squeeze-and-excitation mechanism into the Global-Temporal Block,which processes a single frame as an independent unitto learn temporal variations across the entire lip region more effectively.Furthermore,attention pooling was introduced to highlight meaningful frames containing key semantic information for the target word.Results Experimental results demonstrated STDNet's superior performance on the LRW and LRW-1000,achieving word-level recognition accuracies of 90.2% and 53.56%,respectively.Extensive ablation experiments verified the rationality and effectiveness of its modules.Conclusions The proposed model effectively addresses short-term temporal dependency limitations in lip reading,and improves the temporal robustness of the model against variable-length sequences.These advancements validate the importance of explicit short-term dynamics modeling for practical lip-reading systems.展开更多
Ciphertext-Policy Attribute-Based Encryption(CP-ABE)enables fine-grained access control on ciphertexts,making it a promising approach for managing data stored in the cloud-enabled Internet of Things.But existing schem...Ciphertext-Policy Attribute-Based Encryption(CP-ABE)enables fine-grained access control on ciphertexts,making it a promising approach for managing data stored in the cloud-enabled Internet of Things.But existing schemes often suffer from privacy breaches due to explicit attachment of access policies or partial hiding of critical attribute content.Additionally,resource-constrained IoT devices,especially those adopting wireless communication,frequently encounter affordability issues regarding decryption costs.In this paper,we propose an efficient and fine-grained access control scheme with fully hidden policies(named FHAC).FHAC conceals all attributes in the policy and utilizes bloom filters to efficiently locate them.A test phase before decryption is applied to assist authorized users in finding matches between their attributes and the access policy.Dictionary attacks are thwarted by providing unauthorized users with invalid values.The heavy computational overhead of both the test phase and most of the decryption phase is outsourced to two cloud servers.Additionally,users can verify the correctness of multiple outsourced decryption results simultaneously.Security analysis and performance comparisons demonstrate FHAC's effectiveness in protecting policy privacy and achieving efficient decryption.展开更多
This paper dealt with composite scheduling problems which combine manufacturing scheduling problems and/or transportation routing problems.Two scheduling models were formulated as the elements of the composite schedul...This paper dealt with composite scheduling problems which combine manufacturing scheduling problems and/or transportation routing problems.Two scheduling models were formulated as the elements of the composite scheduling model,and the composite model was formulated composing these models with indispensable additional constraints.A hybrid genetic algorithm was developed to solve the composite scheduling problems.An improved representation based on random keys was developed to search permutation space.A genetic algorithm based dynamic programming approach was applied to select resource.The proposed technique and a previous technique are compared by three types of problems.All results indicate that the proposed technique is superior to the previous one.展开更多
In order to evaluate the structural complexity of class diagrams systematically and deeply, a new guiding framework of structural complexity is presented. An index system of structural complexity for class diagrams is...In order to evaluate the structural complexity of class diagrams systematically and deeply, a new guiding framework of structural complexity is presented. An index system of structural complexity for class diagrams is given. This article discusses the formal description of class diagrams, and presents the method of formally structural complexity metrics for class diagrams from associations, dependencies, aggregations, generalizations and so on. An applicable example proves the feasibility of the presented method.展开更多
By considering energy-efficient anycast routing in wireless sensor network （WSN）, and combining small world characteristics of WSN with the properties of the ant algorithm, a power-aware anycast routing algorithm （...By considering energy-efficient anycast routing in wireless sensor network （WSN）, and combining small world characteristics of WSN with the properties of the ant algorithm, a power-aware anycast routing algorithm （SWPAR） with multi-sink nodes is pro- posed and evaluated. By SWPAR, the optimal sink node is found and the problem of routing path is effectively solved. Simulation results show that compared with the sink-based anycast routing protocol （SARP） and the hierarchy-based anyeast routing protocol （HARP）, the proposed algorithm improves network lifetime and reduces power consumption.展开更多
Diet plays an important role in people’s daily life with its strong correlation to health and chronic diseases. Meanwhile, deep based food computing emerges to provide lots of works which including food recognition, ...Diet plays an important role in people’s daily life with its strong correlation to health and chronic diseases. Meanwhile, deep based food computing emerges to provide lots of works which including food recognition, food retrieval, and food recommendation, and so on. This work focuses on the food recognition, specially, the ingredients identification from food images. The paper proposes two types of ways for ingredient identification. Type1 method involves the combination of salient ingredients classifier with salient ingredient identifiers. Type 2 method introduces the segment-based classifier. Furthermore, this work chooses 35 kinds of ingredients in the daily life as identification categories, and constructs three kinds of novel datasets for establishing the ingredient identification models. All of the classifiers and identifiers are trained on Resnet50 by transfer learning. Many experiments are conducted to analyze the effectiveness of proposed methods. As the results, Salient ingredients classifier predict one ingredient and achieves 91.97% on test set of salient ingredients dataset and 82.48% on test dish image dataset. Salient ingredients identifiers predict remained ingredients and achieve mean accuracy of 85.96% on test dish image dataset. Furthermore, Segment-based classifier achieves 94.81% on test set of segment-based ingredients dataset.展开更多
1 Introduction With the rapid development of mobile networks,locationbased services has become popular in the daily lives of people.The service providers can recommend the profitable services to persons through mining...1 Introduction With the rapid development of mobile networks,locationbased services has become popular in the daily lives of people.The service providers can recommend the profitable services to persons through mining the frequent interests or places of persons.However,one aspect is that the historical data on Internet can easily cause the leakage of user-relationship privacy,another aspect is that the historical interests of person are always bound to time.Therefore,this paper devotes to study a privacy protection method on time-constrained point of interests(PoIs)based on the group relationships of users.展开更多
Unmanned Aerial Vehicles(UAVs)have become integral components in smart city infrastructures,supporting applications such as emergency response,surveillance,and data collection.However,the high mobility and dynamic top...Unmanned Aerial Vehicles(UAVs)have become integral components in smart city infrastructures,supporting applications such as emergency response,surveillance,and data collection.However,the high mobility and dynamic topology of Flying Ad Hoc Networks(FANETs)present significant challenges for maintaining reliable,low-latency communication.Conventional geographic routing protocols often struggle in situations where link quality varies and mobility patterns are unpredictable.To overcome these limitations,this paper proposes an improved routing protocol based on reinforcement learning.This new approach integrates Q-learning with mechanisms that are both link-aware and mobility-aware.The proposed method optimizes the selection of relay nodes by using an adaptive reward function that takes into account energy consumption,delay,and link quality.Additionally,a Kalman filter is integrated to predict UAV mobility,improving the stability of communication links under dynamic network conditions.Simulation experiments were conducted using realistic scenarios,varying the number of UAVs to assess scalability.An analysis was conducted on key performance metrics,including the packet delivery ratio,end-to-end delay,and total energy consumption.The results demonstrate that the proposed approach significantly improves the packet delivery ratio by 12%–15%and reduces delay by up to 25.5%when compared to conventional GEO and QGEO protocols.However,this improvement comes at the cost of higher energy consumption due to additional computations and control overhead.Despite this trade-off,the proposed solution ensures reliable and efficient communication,making it well-suited for large-scale UAV networks operating in complex urban environments.展开更多
The problem of subgraph matching is one fundamental issue in graph search,which is NP-Complete problem.Recently,subgraph matching has become a popular research topic in the field of knowledge graph analysis,which has ...The problem of subgraph matching is one fundamental issue in graph search,which is NP-Complete problem.Recently,subgraph matching has become a popular research topic in the field of knowledge graph analysis,which has a wide range of applications including question answering and semantic search.In this paper,we study the problem of subgraph matching on knowledge graph.Specifically,given a query graph q and a data graph G,the problem of subgraph matching is to conduct all possible subgraph isomorphic mappings of q on G.Knowledge graph is formed as a directed labeled multi-graph having multiple edges between a pair of vertices and it has more dense semantic and structural features than general graph.To accelerate subgraph matching on knowledge graph,we propose a novel subgraph matching algorithm based on subgraph index for knowledge graph,called as FGqT-Match.The subgraph matching algorithm consists of two key designs.One design is a subgraph index of matching-driven flow graph(FGqT),which reduces redundant calculations in advance.Another design is a multi-label weight matrix,which evaluates a near-optimal matching tree for minimizing the intermediate candidates.With the aid of these two key designs,all subgraph isomorphic mappings are quickly conducted only by traversing FGqj.Extensive empirical studies on real and synthetic graphs demonstrate that our techniques outperform the state-of-the-art algorithms.展开更多
文摘Broadcasting is an important operation and been widely used in wireless sensor networks （WSNs）. These networks are power constrained as nodes operate with limited battery power. Wireless sensor networks are spatial graphs that have much more clustered and much high path-length characteristics. After considering energy- efficient broadcasting in such networks, by combining the small-world characteristic of WSNs and the properties of ant algorithm to quickly identify an optimal path, small-world power-aware broadcast algorithm is introduced and evaluated. Given different densities of network, simulation results show that our algorithm significantly improves life of networks and also reduces communication distances and power consumption.
基金the National Natural Science Foundation of China(90604005)
文摘In order to solve the ambiguity problems in the semantic context(structure,granularity or scale)emerging in the process of ontology integration application,this paper analyzes the essential characters of context structure,proposes a novel semantic context generating algorithm,which is implemented over VO-Editor(visual ontology editor),from the satisfiability-based point of view,and proves that the context entity generated by this algorithm is smallest in scale and unique.It offers a feasible means for developers to handle context problems for ontology integration application.
基金Supported by the Fujian Province Science Research Foundation Grant (2009J01272)the Research Fund (type A) (JA09038) from the Education Department of Fujian Provincethe Humanities and Social Science Research Projects of the Ministry of Education (11YJA860028)
文摘How to organize crossing social network resources on a higher level of integration and address them to users＇ desktops is an important difficult problem. Especially, there is a lack of efficient approaches to software architecture to build reusable system over the crossing social network, From the viewpoint of temporal logic XYZ/E, this paper proposes a kind of Architecture Descrip- tion Language about the Crossing Social Network system （CSN_ADL）, which can be used to depict the main key processes over the cross-social network system, and formally defines some key concepts, such as relation component, corelation component, override corelation connector, interaction connector, corelation network-oriented architecture, as well as system correctness, system activity, and system safety. Furthermore, some properties of correctness, activity, and safety under the flame CSN_ADL is discussed and depicted formally, which provides a formally theo- retical instruction for architecture reuses.
文摘In order to improve the performance of classifiers in subjective domains, this paper defines a metric to measure the quality of the subjectively labelled training data (QoSTD) by means of K-means clustering. Then, the QoSTD is used as a weight of the predicted class scores to adjust the likelihoods of instances. Moreover, two measurements are defined to assess the performance of the classifiers trained by the subjective labelled data. The binary classifiers of Traditional Chinese Medicine (TCM) Zhengs are trained and retrained by the real-world data set, utilizing the support vector machine (SVM) and the discrimination analysis (DA) models, so as to verify the effectiveness of the proposed method. The experimental results show that the consistency of likelihoods of instances with the corresponding observations is increased notable for the classes, especially in the cases with the relatively low QoSTD training data set. The experimental results also indicate the solution how to eliminate the miss-labelled instances from the training data set to re-train the classifiers in the subjective domains.
基金Supported by the National Key Research and Development Program of China(2023YFC3306201)the National Natural Science Foundation of China(61772125)the Fundamental Research Funds for the Central Universities(N2317004).
文摘Background Lip reading uses lip images for visual speech recognition.Deep-learning-based lip reading has greatly improved performance in current datasets;however,most existing research ignores the significance of short-term temporal dependencies of lip-shape variations between adjacent frames,which leaves space for further improvement in feature extraction.Methods This article presents a spatiotemporal feature fusion network(STDNet)that compensates for the deficiencies of current lip-reading approaches in short-term temporal dependency modeling.Specifically,to distinguish more similar and intricate content,STDNet adds a temporal feature extraction branch based on a 3D-CNN,which enhances the learning of dynamic lip movements in adjacent frames while not affecting spatial feature extraction.In particular,we designed a local–temporal block,which aggregates interframe differences,strengthening the relationship between various local lip regions through multiscale convolution.We incorporated the squeeze-and-excitation mechanism into the Global-Temporal Block,which processes a single frame as an independent unitto learn temporal variations across the entire lip region more effectively.Furthermore,attention pooling was introduced to highlight meaningful frames containing key semantic information for the target word.Results Experimental results demonstrated STDNet's superior performance on the LRW and LRW-1000,achieving word-level recognition accuracies of 90.2% and 53.56%,respectively.Extensive ablation experiments verified the rationality and effectiveness of its modules.Conclusions The proposed model effectively addresses short-term temporal dependency limitations in lip reading,and improves the temporal robustness of the model against variable-length sequences.These advancements validate the importance of explicit short-term dynamics modeling for practical lip-reading systems.
基金supported in part by the National Key R&D Program of China(Grant No.2019YFB2101700)the National Natural Science Foundation of China(Grant No.62272102,No.62172320,No.U21A20466)+4 种基金the Open Research Fund of Key Laboratory of Cryptography of Zhejiang Province(Grant No.ZCL21015)the Qinghai Key R&D and Transformation Projects(Grant No.2021-GX-112)the Natural Science Foundation of Nanjing University of Posts and Telecommunications(Grant No.NY222141)the Natural Science Foundation of Jiangsu Higher Education Institutions of China under Grant(No.22KJB520029)Henan Key Laboratory of Network Cryptography Technology(No.LNCT2022-A10)。
文摘Ciphertext-Policy Attribute-Based Encryption(CP-ABE)enables fine-grained access control on ciphertexts,making it a promising approach for managing data stored in the cloud-enabled Internet of Things.But existing schemes often suffer from privacy breaches due to explicit attachment of access policies or partial hiding of critical attribute content.Additionally,resource-constrained IoT devices,especially those adopting wireless communication,frequently encounter affordability issues regarding decryption costs.In this paper,we propose an efficient and fine-grained access control scheme with fully hidden policies(named FHAC).FHAC conceals all attributes in the policy and utilizes bloom filters to efficiently locate them.A test phase before decryption is applied to assist authorized users in finding matches between their attributes and the access policy.Dictionary attacks are thwarted by providing unauthorized users with invalid values.The heavy computational overhead of both the test phase and most of the decryption phase is outsourced to two cloud servers.Additionally,users can verify the correctness of multiple outsourced decryption results simultaneously.Security analysis and performance comparisons demonstrate FHAC's effectiveness in protecting policy privacy and achieving efficient decryption.
基金Project supported by the Grant-in-Aid for Young Scientists (B) from the Ministry of Education,Culture,Sports,Science and Technology,Japan
文摘This paper dealt with composite scheduling problems which combine manufacturing scheduling problems and/or transportation routing problems.Two scheduling models were formulated as the elements of the composite scheduling model,and the composite model was formulated composing these models with indispensable additional constraints.A hybrid genetic algorithm was developed to solve the composite scheduling problems.An improved representation based on random keys was developed to search permutation space.A genetic algorithm based dynamic programming approach was applied to select resource.The proposed technique and a previous technique are compared by three types of problems.All results indicate that the proposed technique is superior to the previous one.
基金Science and Technology Department Term of Education of Heilongjiang Province(Grant No.11511127)
文摘In order to evaluate the structural complexity of class diagrams systematically and deeply, a new guiding framework of structural complexity is presented. An index system of structural complexity for class diagrams is given. This article discusses the formal description of class diagrams, and presents the method of formally structural complexity metrics for class diagrams from associations, dependencies, aggregations, generalizations and so on. An applicable example proves the feasibility of the presented method.
基金The Grand Fundamental Advanced Research of Chinese National Defense (No.S0500A001)
文摘By considering energy-efficient anycast routing in wireless sensor network （WSN）, and combining small world characteristics of WSN with the properties of the ant algorithm, a power-aware anycast routing algorithm （SWPAR） with multi-sink nodes is pro- posed and evaluated. By SWPAR, the optimal sink node is found and the problem of routing path is effectively solved. Simulation results show that compared with the sink-based anycast routing protocol （SARP） and the hierarchy-based anyeast routing protocol （HARP）, the proposed algorithm improves network lifetime and reduces power consumption.
文摘Diet plays an important role in people’s daily life with its strong correlation to health and chronic diseases. Meanwhile, deep based food computing emerges to provide lots of works which including food recognition, food retrieval, and food recommendation, and so on. This work focuses on the food recognition, specially, the ingredients identification from food images. The paper proposes two types of ways for ingredient identification. Type1 method involves the combination of salient ingredients classifier with salient ingredient identifiers. Type 2 method introduces the segment-based classifier. Furthermore, this work chooses 35 kinds of ingredients in the daily life as identification categories, and constructs three kinds of novel datasets for establishing the ingredient identification models. All of the classifiers and identifiers are trained on Resnet50 by transfer learning. Many experiments are conducted to analyze the effectiveness of proposed methods. As the results, Salient ingredients classifier predict one ingredient and achieves 91.97% on test set of salient ingredients dataset and 82.48% on test dish image dataset. Salient ingredients identifiers predict remained ingredients and achieve mean accuracy of 85.96% on test dish image dataset. Furthermore, Segment-based classifier achieves 94.81% on test set of segment-based ingredients dataset.
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.61976032 and 62002039)the General Scientific Research Project of Liaoning(No.LJKZ0063).
文摘1 Introduction With the rapid development of mobile networks,locationbased services has become popular in the daily lives of people.The service providers can recommend the profitable services to persons through mining the frequent interests or places of persons.However,one aspect is that the historical data on Internet can easily cause the leakage of user-relationship privacy,another aspect is that the historical interests of person are always bound to time.Therefore,this paper devotes to study a privacy protection method on time-constrained point of interests(PoIs)based on the group relationships of users.
基金funded by Hung Yen University of Technology and Education under grand number UTEHY.L.2025.62.
文摘Unmanned Aerial Vehicles(UAVs)have become integral components in smart city infrastructures,supporting applications such as emergency response,surveillance,and data collection.However,the high mobility and dynamic topology of Flying Ad Hoc Networks(FANETs)present significant challenges for maintaining reliable,low-latency communication.Conventional geographic routing protocols often struggle in situations where link quality varies and mobility patterns are unpredictable.To overcome these limitations,this paper proposes an improved routing protocol based on reinforcement learning.This new approach integrates Q-learning with mechanisms that are both link-aware and mobility-aware.The proposed method optimizes the selection of relay nodes by using an adaptive reward function that takes into account energy consumption,delay,and link quality.Additionally,a Kalman filter is integrated to predict UAV mobility,improving the stability of communication links under dynamic network conditions.Simulation experiments were conducted using realistic scenarios,varying the number of UAVs to assess scalability.An analysis was conducted on key performance metrics,including the packet delivery ratio,end-to-end delay,and total energy consumption.The results demonstrate that the proposed approach significantly improves the packet delivery ratio by 12%–15%and reduces delay by up to 25.5%when compared to conventional GEO and QGEO protocols.However,this improvement comes at the cost of higher energy consumption due to additional computations and control overhead.Despite this trade-off,the proposed solution ensures reliable and efficient communication,making it well-suited for large-scale UAV networks operating in complex urban environments.
基金the National Natural Science Foundation of China(Grant Nos.61976032,62002039).
文摘The problem of subgraph matching is one fundamental issue in graph search,which is NP-Complete problem.Recently,subgraph matching has become a popular research topic in the field of knowledge graph analysis,which has a wide range of applications including question answering and semantic search.In this paper,we study the problem of subgraph matching on knowledge graph.Specifically,given a query graph q and a data graph G,the problem of subgraph matching is to conduct all possible subgraph isomorphic mappings of q on G.Knowledge graph is formed as a directed labeled multi-graph having multiple edges between a pair of vertices and it has more dense semantic and structural features than general graph.To accelerate subgraph matching on knowledge graph,we propose a novel subgraph matching algorithm based on subgraph index for knowledge graph,called as FGqT-Match.The subgraph matching algorithm consists of two key designs.One design is a subgraph index of matching-driven flow graph(FGqT),which reduces redundant calculations in advance.Another design is a multi-label weight matrix,which evaluates a near-optimal matching tree for minimizing the intermediate candidates.With the aid of these two key designs,all subgraph isomorphic mappings are quickly conducted only by traversing FGqj.Extensive empirical studies on real and synthetic graphs demonstrate that our techniques outperform the state-of-the-art algorithms.
