摘要：
The development of decision-making systems based on artificial intelligence can lead to achieving optimal solutions water-land-food nexus. In this paper, an extreme learning machine model was developed with the objective function of wheat production maximization. The constraints defined for this problem are divided into three categories: technical parameters of production in agriculture, climatic stress on water resources and land limits. The water, land and food nexus was simulated using 23 experimental farms in Henan province during the 2021–2022 cultivation year. Root-mean-square error was used as an error criterion, and Pearson's coefficient was incorporated into the decision-making system as a correlation index of variables. Harvest index, length of the growth period, cultivation costs and irrigation water were the criteria to evaluate the impact of the sustainable model. The harvest index and the length of the growth period showed the highest and lowest correlation with the production rate, respectively. Furthermore, the optimal management of irrigation water and cost had the most significant impact on increasing crop production. The method proposed in this paper can be a virtual cropping model by changing the area under cultivation of a crop in the different farms of a study area, which increases yield production.
期刊：
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,2023年27(6):3061-3071 ISSN：2168-2194
通讯作者：
Zhao, Weizhong;Shen, XJ
作者机构：
[Shen, Xianjun; Wang, Haodong; Wang, Yue; Zhao, Weizhong; Zhao, WZ; Shen, XJ; Jiang, Xingpeng; Li, Dandan] Cent China Normal Univ, Sch Comp, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Peoples R China.;[Sun, Han] Cent China Normal Univ, Sch Math & Stat, Wuhan 430079, Peoples R China.;[Shen, Xianjun; Wang, Haodong; Wang, Yue; Zhao, Weizhong; Zhao, WZ; Shen, XJ; Jiang, Xingpeng; Li, Dandan] Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netwo, Wuhan 430079, Peoples R China.
通讯机构：
[Zhao, WZ; Shen, XJ ] C;Cent China Normal Univ, Sch Comp, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netwo, Wuhan 430079, Peoples R China.
关键词：
graph representation learning;heterogeneous information network;multi-head attention mechanism;Phage-host interactions prediction
摘要：
In the treatment of bacterial infectious diseases, overuse of antibiotics may lead to not only bacterial resistance to antibiotics but also dysbiosis of beneficial bacteria which are essential for maintaining normal human life activities. Instead, phage therapy, which invades and lyses specific pathogenic bacteria without affecting beneficial bacteria, becomes more and more popular to treat bacterial infectious diseases. For the effective phage therapy, it requires to accurately predict potential phage-host interactions from heterogeneous information network consisting of bacteria and phages. Although many models have been proposed for predicting phage-host interactions, most methods fail to consider fully the sparsity and unconnectedness of phage-host heterogeneous information network, deriving the undesirable performance on phage-host interactions prediction. To address the challenge, we propose an effective model called GERMAN-PHI for predicting Phage-Host Interactions via Graph Embedding Representation learning with Multi-head Attention mechaNism. In GERMAN-PHI, the multi-head attention mechanism is utilized to learn representations of phages and hosts from multiple perspectives of phage-host associations, addressing the sparsity and unconnectedness in phage-host heterogeneous information network. More specifically, a module of GAT with talking-heads is employed to learn representations of phages and bacteria, on which neural induction matrix completion is conducted to reconstruct the phage-host association matrix. Results of comprehensive experiments demonstrate that GERMAN-PHI performs better than the state-of-the-art methods on phage-host interactions prediction. In addition, results of case study for two high-risk human pathogens show that GERMAN-PHI can predict validated phages with high accuracy, and some potential or new associated phages are provided as well.
期刊：
Pervasive and Mobile Computing,2023年95:101843 ISSN：1574-1192
通讯作者：
Guo, YJ
作者机构：
[Guo, Yajun; Yang, Huan] Cent China Normal Univ, Sch Comp, Luoyu Rd 152, Wuhan 430079, Peoples R China.;[Guo, Yimin] Zhongnan Univ Econ & Law, Sch Informat & Safety Engn, South Lake Ave 182, Wuhan 430073, Peoples R China.
通讯机构：
[Guo, YJ ] C;Cent China Normal Univ, Sch Comp, Luoyu Rd 152, Wuhan 430079, Peoples R China.
关键词：
Authentication;Security;Fog computing;Physical unclonable functions;Smart home
摘要：
With the rise of Internet of Things (IoT), the smart home is another emerging concept and application of IoT, where security and private data of devices are important. In this paper, fog computing is applied to the smart home environment, where fog can provide many smart features and services to the smart home. Fog computing has many advantages, such as low latency and real-time interaction. However, when fog computing is combined with smart home, it also faces some security threats: first, some fog nodes and smart home devices are deployed in public places, vulnerable to damage or theft by attackers, not considered fully trusted, and vulnerable to device loss/theft attacks, impersonation attacks, and message tampering attacks, etc. These threats can lead to adversaries controlling devices in the smart home or modifying messages to make smart home devices execute wrong commands, causing irreparable damage; Second, the smart home system should have good real-time interaction, and the authentication process using the low latency feature of fog computing should not be involved by the cloud. Considering these, it is necessary to design a secure and effective fog-enabled smart home authentication system that is secure against various known attacks, especially when the fog node is not fully trusted or the smart home device is captured as well. Finally, the authentication scheme should also be lightweight due to the limited resources of many smart home devices. To address these issues, this paper proposes a lightweight authentication scheme for the fog-enabled smart home system. It also employs a physical unclonable function to achieve mutual authentication among three parties: smart home devices, fog nodes and users. Formal security analysis under the Real-Or-Random model shows that this scheme is provably secure. And informal security analysis shows that our scheme is robust against various known attacks. At the same time, the proposed scheme requires less computation cost (8.239 ms) and is approximately 40% to 390% faster than existing related schemes. Although the communication cost is slightly higher (4512 bits), it is reasonable because the proposed scheme implements fog/gateway node compromised attack that has not been achieved by any other existing related schemes.
期刊：
BRIEFINGS IN BIOINFORMATICS,2023年24(2) ISSN：1467-5463
通讯作者：
Weizhong Zhao
作者机构：
[Shen, Xianjun; Zhao, Weizhong; Yuan, Xueling; He, Tingting; Jiang, Xingpeng] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Shi, Chuan] Beijing Univ Posts & Telecommun, Sch Comp Sci, Beijing, Peoples R China.;[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
通讯机构：
[Weizhong Zhao] H;Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University , Wuhan, Hubei 430079, P R China<&wdkj&>School of Computer Science, Beijing University of Posts and Telecommunications , Beijing, 100876, P R China<&wdkj&>National Language Resources Monitoring & Research Center for Network Media, Central China Normal University , Wuhan, Hubei 430079, P R China
关键词：
drug–drug interaction;heterogeneous information network;meta-path-based information fusion
摘要：
Drug-drug interactions (DDIs) are compound effects when patients take two or more drugs at the same time, which may weaken the efficacy of drugs or cause unexpected side effects. Thus, accurately predicting DDIs is of great significance for the drug development and the drug safety surveillance. Although many methods have been proposed for the task, the biological knowledge related to DDIs is not fully utilized and the complex semantics among drug-related biological entities are not effectively captured in existing methods, leading to suboptimal performance. Moreover, the lack of interpretability for the predicted results also limits the wide application of existing methods for DDIs prediction. In this study, we propose a novel framework for predicting DDIs with interpretability. Specifically, we construct a heterogeneous information network (HIN) by explicitly utilizing the biological knowledge related to the procedure of inducing DDIs. To capture the complex semantics in HIN, a meta-path-based information fusion mechanism is proposed to learn high-quality representations of drugs. In addition, an attention mechanism is designed to combine semantic information obtained from meta-paths with different lengths to obtain final representations of drugs for DDIs prediction. Comprehensive experiments are conducted on 2410 approved drugs, and the results of predictive performance comparison show that our proposed framework outperforms selected representative baselines on the task of DDIs prediction. The results of ablation study and cold-start scenario indicate that the meta-path-based information fusion mechanism red is beneficial for capturing the complex semantics among drug-related biological entities. Moreover, the results of case study demonstrate that the designed attention mechanism is able to provide partial interpretability for the predicted DDIs. Therefore, the proposed method will be a feasible solution to the task of predicting DDIs.
作者机构：
[Hu, Zhanxuan; Ning, Hailong] Xian Univ Posts & Telecommun, Sch Comp Sci & Technol, Shaanxi Key Lab Network Data Anal & Intelligent Pr, Xian, Peoples R China.;[Hu, Zhanxuan; Ning, Hailong; An, Mengyuan] Xian Key Lab Big Data & Intelligent Comp, Xian, Peoples R China.;[Lei, Tao] Shaanxi Univ Sci & Technol, Sch Elect Informat & Artificial Intelligence, Xian, Peoples R China.;[Sun, Hao] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Nandi, Asoke K.] Brunel Univ London, Dept Elect & Elect Engn, London, England.
通讯机构：
[Tao Lei; Tao Lei Tao Lei Tao Lei] S;School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi'an, China
关键词：
deep learning;image analysis;image classification;information fusion
摘要：
Aerial scene recognition (ASR) has attracted great attention due to its increasingly essential applications. Most of the ASR methods adopt the multi-scale architecture because both global and local features play great roles in ASR. However, the existing multi-scale methods neglect the effective interactions among different scales and various spatial locations when fusing global and local features, leading to a limited ability to deal with challenges of large-scale variation and complex background in aerial scene images. In addition, existing methods may suffer from poor generalisations due to millions of to-be-learnt parameters and inconsistent predictions between global and local features. To tackle these problems, this study proposes a scale-wise interaction fusion and knowledge distillation (SIF-KD) network for learning robust and discriminative features with scale-invariance and background-independent information. The main highlights of this study include two aspects. On the one hand, a global-local features collaborative learning scheme is devised for extracting scale-invariance features so as to tackle the large-scale variation problem in aerial scene images. Specifically, a plug-and-play multi-scale context attention fusion module is proposed for collaboratively fusing the context information between global and local features. On the other hand, a scale-wise knowledge distillation scheme is proposed to produce more consistent predictions by distilling the predictive distribution between different scales during training. Comprehensive experimental results show the proposed SIF-KD network achieves the best overall accuracy with 99.68%, 98.74% and 95.47% on the UCM, AID and NWPU-RESISC45 datasets, respectively, compared with state of the arts.
作者机构：
[Peng, Pai; Li, Le; Chen, Qiyuan] Cent China Normal Univ, Sch Math & Stat, Wuhan 430079, Peoples R China.;[Yang, Haitong] Cent China Normal Univ, Sch Comp Sci, Wuhan 430079, Peoples R China.;[Li, Le] Hubei Key Lab Math Sci, Wuhan 430072, Peoples R China.
通讯机构：
[Li, L.] C;Central China Normal University, China
摘要：
Temporal knowledge graph embedding (TKGE) aims to learn the embedding of entities and relations in a temporal knowledge graph (TKG). Although the previous graph neural networks (GNN) based models have achieved promising results, they cannot directly capture the interactions of multi-facts at different timestamps. To address the above limitation, we propose a time-aware relational graph attention model (TARGAT), which takes the multi-facts at different timestamps as a unified graph. First, we develop a relational generator to dynamically generate a series of time-aware relational message transformation matrices, which jointly models the relations and the timestamp information into a unified way. Then, we apply the generated message transformation matrices to project the neighborhood features into different time-aware spaces and aggregate these neighborhood features to explicitly capture the interactions of multi-facts. Finally, a temporal transformer classifier is applied to learn the representation of the query quadruples and predict the missing entities. The experimental results show that our TARGAT model beats the GNN-based models by a large margin and achieves new state-of-the-art results on four popular benchmark datasets.
期刊：
IEEE TRANSACTIONS ON SERVICES COMPUTING,2023年16(6):4102-4114 ISSN：1939-1374
通讯作者：
Guo, YM
作者机构：
[Guo, Yimin; Guo, YM] Zhongnan Univ Econ & Law, Sch Informat & Safety Engn, Wuhan 430073, Hubei, Peoples R China.;[Guo, Yajun] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.
通讯机构：
[Guo, YM ] Z;Zhongnan Univ Econ & Law, Sch Informat & Safety Engn, Wuhan 430073, Hubei, Peoples R China.
关键词：
Internet of Things (IoT);authentication;robust synchronization;anonymity;perfect forward secrecy
摘要：
Anonymity, robust synchronization, and perfect forward secrecy are the most important security properties of authenticated key agreement (AKA) protocols. Designing AKA protocols that simultaneously achieve these security properties and availability in the IoT environment is a challenging task. AKA protocols built using public key cryptographic primitives have advantages in achieving these critical security properties, but performing expensive public-key cryptographic operations is inefficient for resource-constrained IoT devices. The authentication protocols based on symmetric cryptographic primitives are often subject to various attacks. This paper proposes a secure lightweight AKA protocol with critical security properties (called CS-LAKA) for IoT environments without using public-key cryptographic primitives. LAKA cleverly achieves the security goals of anonymity, robust synchronization, and perfect forward secrecy by embedding dynamic identities in authenticators, and a few additional exchange messages are added. This enables LAKA to have both robust security and high efficiency. Subsequently, we perform a formal security analysis to prove that LAKA is secure, and compared with existing related schemes, LAKA has obvious advantages in terms of security, functionality and running performance.
摘要：
A direction-aware augmented spatial keyword top- $k$ query (DAT $k\text{Q}$ ) returns the top- $k$ objects based on a ranking function that considers spatial distance, textual similarity, query numeric attributes, and query direction. When a user initiates a DAT $k\text{Q}$ , some user-desired objects (missing objects) may not appear in the query result set, and then the user wonders why they do not appear, which is called the why-not question. This paper focuses on answering why-not questions on DAT $k$ Qs. We first discuss how to obtain the refined query direction by analyzing the position relationship between missing objects and original query direction in Polar coordinates. Then a DAPC index structure is designed, which can cut down irrelevant search space based on not only conventional distance pruning, keyword pruning, and attribute pruning but also query direction pruning. Particularly, by comparing the position relationship between the query direction and the sector (sector ring) region segmented by the DAPC-based method, the search space that does not meet the query direction is pruned. In addition, we discuss the applicability of our scheme for handling why-not questions on regional spatial keyword queries (SKQ), ordinary direction-aware top- $k$ SKQ queries and complex scoring SKQ queries. Finally, a series of experiments are conducted on two real datasets to show the efficiency of our DAPC-based method.
摘要：
Cervical cancer seriously endangers the health of the female reproductive system and even risks women's life in severe cases. Optical coherence tomography (OCT) is a non-invasive, real-time, high-resolution imaging technology for cervical tissues. However, since the interpretation of cervical OCT images is a knowledge-intensive, time-consuming task, it is tough to acquire a large number of high-quality labeled images quickly, which is a big challenge for supervised learning. In this study, we introduce the vision Transformer (ViT) architecture, which has recently achieved impressive results in natural image analysis, into the classification task of cervical OCT images. Our work aims to develop a computer-aided diagnosis (CADx) approach based on a self-supervised ViT-based model to classify cervical OCT images effectively. We leverage masked autoencoders (MAE) to perform self-supervised pre-training on cervical OCT images, so the proposed classification model has a better transfer learning ability. In the fine-tuning process, the ViT-based classification model extracts multi-scale features from OCT images of different resolutions and fuses them with the cross-attention module. The ten-fold cross-validation results on an OCT image dataset from a multi-center clinical study of 733 patients in China indicate that our model achieved an AUC value of 0.9963 ± 0.0069 with a 95.89 ± 3.30% sensitivity and 98.23 ± 1.36 % specificity, outperforming some state-of-the-art classification models based on Transformers and convolutional neural networks (CNNs) in the binary classification task of detecting high-risk cervical diseases, including high-grade squamous intraepithelial lesion (HSIL) and cervical cancer. Furthermore, our model with the cross-shaped voting strategy achieved a sensitivity of 92.06% and specificity of 95.56% on an external validation dataset containing 288 three-dimensional (3D) OCT volumes from 118 Chinese patients in a different new hospital. This result met or exceeded the average of four medical experts who have used OCT for over one year. In addition to promising classification performance, our model has a remarkable ability to detect and visualize local lesions using the attention map of the standard ViT model, providing good interpretability for gynecologists to locate and diagnose possible cervical diseases. Cervical cancer seriously endangers the health of the female reproductive system and even risks women's life in severe cases. Optical coherence tomography (OCT) is a non-invasive, real-time, high-resolution imaging technology for cervical tissues. However, since the interpretation of cervical OCT images is a knowledge-intensive, time-consuming task, it is tough to acquire a large number of high-quality labeled images quickly, which is a big challenge for supervised learning. In this study, we introduce the vision Transformer (ViT) architecture, which has recently achieved impressive results in natural image analysis, into the classification task of cervical OCT images. Our work aims to develop a computer-aided diagnosis (CADx) approach based on a self-supervised ViT-based model to classify cervical OCT images effectively. We leverage masked autoencoders (MAE) to perform self-supervised pre-training on cervical OCT images, so the proposed classification model has a better transfer learning ability. In the fine-tuning process, the ViT-based classification model extracts multi-scale features from OCT images of different resolutions and fuses them with the cross-attention module. The ten-fold cross-validation results on an OCT image dataset from a multi-center clinical study of 733 patients in China indicate that our model achieved an AUC value of 0.9963 ± 0.0069 with a 95.89 ± 3.30% sensitivity and 98.23 ± 1.36 % specificity, outperforming some state-of-the-art classification models based on Transformers and convolutional neural networks (CNNs) in the binary classification task of detecting high-risk cervical diseases, including high-grade squamous intraepithelial lesion (HSIL) and cervical cancer. Furthermore, our model with the cross-shaped voting strategy achieved a sensitivity of 92.06% and specificity of 95.56% on an external validation dataset containing 288 three-dimensional (3D) OCT volumes from 118 Chinese patients in a different new hospital. This result met or exceeded the average of four medical experts who have used OCT for over one year. In addition to promising classification performance, our model has a remarkable ability to detect and visualize local lesions using the attention map of the standard ViT model, providing good interpretability for gynecologists to locate and diagnose possible cervical diseases.
作者机构：
[Wang, Chao; Zhang, Jiaxu; Tu, Zhigang] Wuhan Univ, State Key Lab Informat Engn Surveying, Wuhan 430072, Hubei, Peoples R China.;[Xie, Wei] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Tu, Ruide] Cent China Normal Univ, Sch Informat Management, Wuhan 430079, Hubei, Peoples R China.
通讯机构：
[Chao Wang; Ruide Tu] S;State Key Laboratory of Information Engineering in Surveying, Wuhan University, Wuhan, China<&wdkj&>School Of Information Management, Central China Normal University, Wuhan, China
关键词：
Skeleton action recognition;Visual transformer;Graph-aware transformer;Velocity information of human body joints;Graph neural network
摘要：
Recently, graph convolutional networks (GCNs) play a critical role in skeleton-based human action recognition. However, most GCN-based methods still have two main limitations: (1) The semantic-level adjacency matrix of the skeleton graph is difficult to be manually defined, which restricts the perception field of GCN and limits its ability to extract the spatial–temporal features. (2) The velocity information of human body joints cannot be efficiently used and fully exploited by GCN, because GCN does not represent the correlation between the velocity vectors explicitly. To address these issues, we propose a graph-aware transformer (GAT), which can make full use of the velocity information and learn discriminative spatial–temporal motion features from the sequence of the skeleton graphs in a data-driven way. Besides, similar to the GCN-based model, our GAT also considers the prior structures of the human body including the link-aware structure and the part-aware structure. Extensive experiments on three large-scale datasets, i.e., NTU-RGB+D 60, NTU-RGB+D 120, and Kinetics-Skeleton, demonstrated that the proposed GAT obtains significant improvement compared to the GCN-based baseline for skeleton action recognition.
摘要：
Identifying temporal and subevent relationships between different events (i.e., event relation extraction) is an important step towards event-centric natural language processing, which can help understand how events evolve and potentially facilitate many downstream tasks, such as timeline generation and event knowledge graph construction. Existing work has extensively leveraged external knowledge to improve the performance of relation extraction. Despite the progress made, the current knowledge-enhanced approach still has some shortcomings, e.g., knowledge missing, knowledge noise, and suboptimal knowledge injection. In this paper, we propose OntoEnhance, a novel event relation extraction framework that fuses semantic information from event ontologies to enhance event representation. Specifically, we first inject the latent knowledge in the event ontology into the prompt text to address the issue of knowledge missing. Then a dual-stack attention fusion mechanism is further introduced to enhance the injection of key knowledge to alleviate knowledge noise. In order to prevent the knowledge in the event ontology from being wrongly dominated, we use the event direction induction mechanism to obtain the event context-based relational sequence representation. Finally, a gate mechanism is used to fuse ontology-based knowledge and context-based event features dynamically. Extensive experiments demonstrate that OntoEnhance outperforms all comparison baselines by a large margin on all four datasets under both standard and few-shot settings.
期刊：
Journal of Information Security and Applications,2023年77:103576 ISSN：2214-2126
通讯作者：
Hsu, CF
作者机构：
[Harn, Lein] Univ Missouri Kansas City, Dept Comp Sci Elect Engn, Kansas City, MO 64110 USA.;[Hsu, Chingfang] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Hubei, Peoples R China.;[Zeng, Shuchang; Xu, Hang; Pang, Fengling; Hsu, Chingfang] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Xia, Zhe] Wuhan Univ Technol, Dept Comp Sci, Wuhan 430071, Peoples R China.
通讯机构：
[Hsu, CF ] C;Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Hubei, Peoples R China.
关键词：
General construction;Anonymously releasing data;Secure multiparty computation;Dealer-free;Non-interaction;TCSS
摘要：
Shamir's (t, n) threshold secret sharing (SS) is one of the most important cryptographic primitives in various security applications designed to protect highly sensitive information, such as intellectual property and network security. A dealer in a (t, n) threshold SS divides the secret into n shares such that with t or more than t of these shares, the secret can be retrieved; but with less than t of these shares, no information of the secret can be revealed. In order to adapt the dynamic environment in various applications, the threshold changeable SS (TCSS) allows the threshold of the original secret to be dynamically adjusted. Note that Shamir's original SS is unable to achieve this property. In the literature, most existing TCSS schemes are suffering from limitations that either it requires a trusted dealer to generate and distribute new shares, or requires interactions among shareholders to generate new shares. In this paper, we propose a novel idea to construct a dealer-free and non-interactive TCSS based on pairwise keys between users. Research papers related to pairwise key distribution schemes have been published over last 40 years and it has become one of fundamental tools used in design of cryptographic solutions. First, we show that our idea can be used to construct a scheme for anonymously releasing data and a secure multiparty computation scheme. Both schemes are very simple and security analysis can be understood easily. Second, we demonstrate that a TCSS can also be designed based on same approach. Our design of TCSS is novel and it can be applied to convert any existing SS into a TCSS.
期刊：
Artificial Intelligence in Medicine,2023年145:102677 ISSN：0933-3657
通讯作者：
Jiang, XP
作者机构：
[Fu, Chengcheng] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Jiang, Xingpeng; Fu, Chengcheng; He, Tingting] Cent China Normal Univ, Sch Comp Sci, Wuhan, Peoples R China.;[Fu, Chengcheng; van Harmelen, Frank; Huang, Zhisheng] Vrije Univ Amsterdam, Dept Comp Sci, Amsterdam, Netherlands.;[Fu, Chengcheng; He, Tingting; Jiang, Xingpeng] Cent China Normal Univ, Natl Language Resources Monitor Res Ctr Network Me, Wuhan, Peoples R China.;[Huang, Zhisheng] Tongji Univ, Sch Med, Clin Res Ctr Mental Disorders, Shanghai Pudong New Area Mental Hlth Ctr, Shanghai, Peoples R China.
通讯机构：
[Jiang, XP ] C;Cent China Normal Univ, Sch Comp Sci, Wuhan, Peoples R China.
关键词：
Food;Gut microbiota;Knowledge graph;Mental health
期刊：
INTERNATIONAL JOURNAL OF SATELLITE COMMUNICATIONS AND NETWORKING,2023年41(1):42-58 ISSN：1542-0973
通讯作者：
Jianqun Cui
作者机构：
[Wu, Jike; Cui, Jianqun; Zhang, Ruijie; Chang, Yanan; Wan, Qiyun] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.;[Zhou, Hao] Wuhan Polytech Univ, Network & Informatizat Ctr, Wuhan, Hubei, Peoples R China.
通讯机构：
[Jianqun Cui] S;School of Computing, Central China Normal University, Wuhan, Hubei, China
关键词：
communication capability;delay-tolerant network;message priority;message strength;relay node selection strategy
摘要：
In delay-tolerant networks (DTN), node connection time and message transmission time are two important influencing factors that can improve the delivery rate. In this paper, we first define a new concept called communication capability (CC) and then apply this concept to the delivery predictability formulation in Prophet and improve it. Then, in Prophet, the selection of relay nodes relies only on the delivery predictability and ignores the caching and forwarding capability of the node. Therefore, we combine delivery predictability, buffering, and forwarding capability to develop a new adaptive relay node selection strategy. Subsequently, we define two metrics called message priority (MP) and message strength (MS). The node forwards messages sequentially based on message priority and discards messages based on message strength. Finally, we present a probabilistic routing algorithm based on node communication capability and message strength (CAMS). The simulation results show that compared with traditional routing algorithms, the CAMS can effectively improve the message delivery rate, reduce the overhead ratio, and keep average hop counts low.
摘要：
Metaverse is the fusion of cyber–physical–social intelligence, and the fusion becomes the core and fundamental property of the metaverse. As an important part of social operationalization, the education domain leads to the birth of the education metaverse. This article answers three basic questions about smart services in the education metaverse: 1) learning scene; 2) technical framework; and 3) initial expansion. Specifically, four key elements constitute the learning scene in the education metaverse: 1) the learner; 2) its time; 3) space; and 4) learning event. In this learning scene, we propose a novel data-knowledge-driven group intelligence framework, aiming to transform data in the education metaverse into knowledge, and intersect and integrate intelligence with knowledge; based on this framework, we apply it to specific services, i.e., transaction and management services. We hope that our work opens the door to research on smart services in the education metaverse and more scholars will work for these challenges.
期刊：
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2023年20:1-5 ISSN：1545-598X
通讯作者：
Zhang, M.
作者机构：
[Tang, Ping; Zhang, Meng] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;[Liu, Zhihui] China Univ Geosci, Sch Math & Phys, Wuhan 430074, Peoples R China.;[Song, Rong] Cent China Normal Univ, Sch Marxism, Wuhan 430079, Peoples R China.
通讯机构：
[Zhang, M.] C;Central China Normal University, China
摘要：
Convolutional neural networks (CNNs) have become one of the most popular tools to tackle hyperspectral image (HSI) classification tasks. However, CNN suffers from the long-range dependencies problem, which may degrade the classification performance. To address this issue, this letter proposes a transformer-based backbone network for HSI classification. The core component is a newly designed double-attention transformer encoder (DATE), which contains two self-attention modules, termed spectral attention module (SPE) and spatial attention module (SPA). SPE extracts the global dependency among spectral bands, and SPA mines the local features of spatial correlation information among pixels. The local spatial tokens and the global spectral token are fused together and updated by SPA. In this way, DATE can not only capture the global dependence among spectral bands but also extract the local spatial information, which greatly improves the classification performance. To reduce the possible information loss as the network depth increases, a new skip connection mechanism is devised for cross-layer feature fusion. Experimental results in several datasets indicate that the new algorithm holds very competitive classification performance compared to the state-of-the-art methods.
期刊：
Multimedia Tools and Applications,2023年82(1):1105-1129 ISSN：1380-7501
通讯作者：
Cong Jin
作者机构：
[Jin, Cong] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
通讯机构：
[Cong Jin] S;School of Computer, Central China Normal University, Wuhan, People’s Republic of China
关键词：
Cross-database;Facial expression recognition;Database adaptation;Learning feature;Images in the wild
摘要：
Since the labeled wild facial expression database is relatively rare, the existing Facial Expression Recognition (FER) models based on machine learning can only be trained with a relatively limited number of samples and whether the trained FER model can have satisfactory recognition performance is a challenge. In this paper, the facial expression database from the Laboratory Environment (LE) is used as the source domain, and the facial expression database from the wild is used as the target domain. Based on these two different databases, a hybrid improved unsupervised Cross-Domain Adaptation (CDA) approach is proposed, which can not only match the data distribution between different databases, but also maximize the correlation of data between different databases, and also maximize data separability on the source database. In the proposed CDA approach, the objective functions of the two improved techniques and those of traditional CDA are to achieve the simultaneous optimization of the three objective functions. After that, the proposed CDA approach was used for Cross-domain FER (CFER) task. To confirm the effectiveness of the proposed CFER model, some experiments are implemented on four cross-database pairs. The comparison and analysis of experimental results show that, compared with other existing CFER models, the proposed CFER model can realize the reuse of LE facial expression data and achieve better recognition performance for wild facial expression data.
