Search

Your search keyword '"Lang, Bo"' showing total 144 results
Start Over Author "Lang, Bo" Search Limiters Full Text
144 results on '"Lang, Bo"'

1. APT-MMF: An advanced persistent threat actor attribution method based on multimodal and multilevel feature fusion

Author

Xiao, Nan, Lang, Bo, Wang, Ting, and Chen, Yikai

Subjects
Computer Science - Cryptography and Security, Computer Science - Machine Learning
Abstract

Threat actor attribution is a crucial defense strategy for combating advanced persistent threats (APTs). Cyber threat intelligence (CTI), which involves analyzing multisource heterogeneous data from APTs, plays an important role in APT actor attribution. The current attribution methods extract features from different CTI perspectives and employ machine learning models to classify CTI reports according to their threat actors. However, these methods usually extract only one kind of feature and ignore heterogeneous information, especially the attributes and relations of indicators of compromise (IOCs), which form the core of CTI. To address these problems, we propose an APT actor attribution method based on multimodal and multilevel feature fusion (APT-MMF). First, we leverage a heterogeneous attributed graph to characterize APT reports and their IOC information. Then, we extract and fuse multimodal features, including attribute type features, natural language text features and topological relationship features, to construct comprehensive node representations. Furthermore, we design multilevel heterogeneous graph attention networks to learn the deep hidden features of APT report nodes; these networks integrate IOC type-level, metapath-based neighbor node-level, and metapath semantic-level attention. Utilizing multisource threat intelligence, we construct a heterogeneous attributed graph dataset for verification purposes. The experimental results show that our method not only outperforms the existing methods but also demonstrates its good interpretability for attribution analysis tasks.

Published
2024

2. Whole genome resequencing reveals the evolutionary history and geographic isolation of the eastern Asian Hickory (Carya)

Author

Da Zhang, Rui‐Feng Yang, Jia‐Hui Chen, Lang‐Bo Pan, Wei Duan, Guo‐Hua Xia, Qi‐Xiang Zhang, and You‐Jun Huang

Subjects
Carya, disjunctive distribution, endangered, evolutionary history, hickory, resequencing, Environmental sciences, GE1-350, Botany, QK1-989
Abstract

Societal Impact Statement Unraveling the genetic intricacies and evolutionary history of Asian Hickories through advanced genome sequencing gives valuable insights into their ecological adaptations. Understanding the impact of historical dynamics, climate fluctuations, and geographical barriers on Asian hickories not only contributes to scientific knowledge but also empowers policymakers with evidence‐based decisions and guides conservationists in their efforts to protect vulnerable species. The identification of potential habitats, especially for the endangered Carya kweichowensis, offers a promising avenue for targeted conservation efforts, aligning with global initiatives to preserve Earth's precious biodiversity, but also ensures the conservation of a vital genetic reservoir for nut‐bearing economic tree species. Summary Biogeographic characteristics of disjunct distribution play a vital role in plant geography and the endangered mechanism. The whole genome resequencing provides an opportunity to study the genetic relationship, population diffusion, and floristic evolution of disjunctive‐distribution flora. Based on the SNPs (single nucleotide polymorphisms) data generated by the whole genome deep resequencing of five EA (Eastern Asian) Carya species, we constructed the phylogenetic tree, genetic structure, and species distribution modeling to clarify the phylogenetic relationships and to predict the potential distribution area of EA Carya. Phylogenetic analysis of Carya revealed two distinct clades, separating EA Carya from NA (North America) Carya. C. kweichowensis, an endangered species, showed the lowest nucleotide diversity and the earliest divergence among studied EA Carya species. Species distribution modeling predicted suitable habitats for five EA Carya species, revealing the potential distribution of endangered C. kweichowensis. Importantly, minimal spatial overlap was observed among distribution regions of EA Carya species during different time periods. The uneven regional distribution of EA Carya is believed to be a consequence of Quaternary climate fluctuations, mountain barriers hindering species dispersal, and the limited cold tolerance of these trees. EA Carya highlights the significant role of climate and geological changes in their regional distribution and migration routes in Asia. Furthermore, the discovery of potential habitats offers a promising avenue for the conservation of C. kweichowensis.

Published
2024
Full Text
View/download PDF

3. Student-friendly Knowledge Distillation

Author

Yuan, Mengyang, Lang, Bo, and Quan, Fengnan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

In knowledge distillation, the knowledge from the teacher model is often too complex for the student model to thoroughly process. However, good teachers in real life always simplify complex material before teaching it to students. Inspired by this fact, we propose student-friendly knowledge distillation (SKD) to simplify teacher output into new knowledge representations, which makes the learning of the student model easier and more effective. SKD contains a softening processing and a learning simplifier. First, the softening processing uses the temperature hyperparameter to soften the output logits of the teacher model, which simplifies the output to some extent and makes it easier for the learning simplifier to process. The learning simplifier utilizes the attention mechanism to further simplify the knowledge of the teacher model and is jointly trained with the student model using the distillation loss, which means that the process of simplification is correlated with the training objective of the student model and ensures that the simplified new teacher knowledge representation is more suitable for the specific student model. Furthermore, since SKD does not change the form of the distillation loss, it can be easily combined with other distillation methods that are based on the logits or features of intermediate layers to enhance its effectiveness. Therefore, SKD has wide applicability. The experimental results on the CIFAR-100 and ImageNet datasets show that our method achieves state-of-the-art performance while maintaining high training efficiency.

Published
2023

6. MG-SAGC: A multiscale graph and its self-adaptive graph convolution network for 3D point clouds

Author

Wu, Bo and Lang, Bo

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

To enhance the ability of neural networks to extract local point cloud features and improve their quality, in this paper, we propose a multiscale graph generation method and a self-adaptive graph convolution method. First, we propose a multiscale graph generation method for point clouds. This approach transforms point clouds into a structured multiscale graph form that supports multiscale analysis of point clouds in the scale space and can obtain the dimensional features of point cloud data at different scales, thus making it easier to obtain the best point cloud features. Because traditional convolutional neural networks are not applicable to graph data with irregular vertex neighborhoods, this paper presents an sef-adaptive graph convolution kernel that uses the Chebyshev polynomial to fit an irregular convolution filter based on the theory of optimal approximation. In this paper, we adopt max pooling to synthesize the features of different scale maps and generate the point cloud features. In experiments conducted on three widely used public datasets, the proposed method significantly outperforms other state-of-the-art models, demonstrating its effectiveness and generalizability.

Published
2020

9. Query-Adaptive Hash Code Ranking for Large-Scale Multi-View Visual Search

Author

Liu, Xianglong, Huang, Lei, Deng, Cheng, Lang, Bo, and Tao, Dacheng

Subjects
Computer Science - Information Retrieval, Computer Science - Machine Learning
Abstract

Hash based nearest neighbor search has become attractive in many applications. However, the quantization in hashing usually degenerates the discriminative power when using Hamming distance ranking. Besides, for large-scale visual search, existing hashing methods cannot directly support the efficient search over the data with multiple sources, and while the literature has shown that adaptively incorporating complementary information from diverse sources or views can significantly boost the search performance. To address the problems, this paper proposes a novel and generic approach to building multiple hash tables with multiple views and generating fine-grained ranking results at bitwise and tablewise levels. For each hash table, a query-adaptive bitwise weighting is introduced to alleviate the quantization loss by simultaneously exploiting the quality of hash functions and their complement for nearest neighbor search. From the tablewise aspect, multiple hash tables are built for different data views as a joint index, over which a query-specific rank fusion is proposed to rerank all results from the bitwise ranking by diffusing in a graph. Comprehensive experiments on image search over three well-known benchmarks show that the proposed method achieves up to 17.11% and 20.28% performance gains on single and multiple table search over state-of-the-art methods.

Published
2019

11. Decorrelated Batch Normalization

Author

Huang, Lei, Yang, Dawei, Lang, Bo, and Deng, Jia

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning, Statistics - Machine Learning
Abstract

Batch Normalization (BN) is capable of accelerating the training of deep models by centering and scaling activations within mini-batches. In this work, we propose Decorrelated Batch Normalization (DBN), which not just centers and scales activations but whitens them. We explore multiple whitening techniques, and find that PCA whitening causes a problem we call stochastic axis swapping, which is detrimental to learning. We show that ZCA whitening does not suffer from this problem, permitting successful learning. DBN retains the desirable qualities of BN and further improves BN's optimization efficiency and generalization ability. We design comprehensive experiments to show that DBN can improve the performance of BN on multilayer perceptrons and convolutional neural networks. Furthermore, we consistently improve the accuracy of residual networks on CIFAR-10, CIFAR-100, and ImageNet., Comment: Accepted to CVPR 2018. Code available at https://github.com/umich-vl/DecorrelatedBN

Published
2018

12. DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model

Author

Wu, Bo, Liu, Yang, Lang, Bo, and Huang, Lei

Subjects
Computer Science - Learning, Statistics - Machine Learning
Abstract

Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs. Graph CNNs are attracting increasing attention due to their effectiveness and efficiency. However, the existing convolution approaches focus only on regular data forms and require the transfer of the graph or key node neighborhoods of the graph into the same fixed form. During this transfer process, structural information of the graph can be lost, and some redundant information can be incorporated. To overcome this problem, we propose the disordered graph convolutional neural network (DGCNN) based on the mixed Gaussian model, which extends the CNN by adding a preprocessing layer called the disordered graph convolutional layer (DGCL). The DGCL uses a mixed Gaussian function to realize the mapping between the convolution kernel and the nodes in the neighborhood of the graph. The output of the DGCL is the input of the CNN. We further implement a backward-propagation optimization process of the convolutional layer by which we incorporate the feature-learning model of the irregular node neighborhood structure into the network. Thereafter, the optimization of the convolution kernel becomes part of the neural network learning process. The DGCNN can accept arbitrary scaled and disordered neighborhood graph structures as the receptive fields of CNNs, which reduces information loss during graph transformation. Finally, we perform experiments on multiple standard graph datasets. The results show that the proposed method outperforms the state-of-the-art methods in graph classification and retrieval., Comment: 16 pages,8 figures

Published
2017

13. Calculating Semantic Similarity between Academic Articles using Topic Event and Ontology

Author

Liu, Ming, Lang, Bo, and Gu, Zepeng

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Information Retrieval
Abstract

Determining semantic similarity between academic documents is crucial to many tasks such as plagiarism detection, automatic technical survey and semantic search. Current studies mostly focus on semantic similarity between concepts, sentences and short text fragments. However, document-level semantic matching is still based on statistical information in surface level, neglecting article structures and global semantic meanings, which may cause the deviation in document understanding. In this paper, we focus on the document-level semantic similarity issue for academic literatures with a novel method. We represent academic articles with topic events that utilize multiple information profiles, such as research purposes, methodologies and domains to integrally describe the research work, and calculate the similarity between topic events based on the domain ontology to acquire the semantic similarity between articles. Experiments show that our approach achieves significant performance compared to state-of-the-art methods., Comment: 21 pages, 10 Figures

Published
2017

14. Projection Based Weight Normalization for Deep Neural Networks

Author

Huang, Lei, Liu, Xianglong, Lang, Bo, and Li, Bo

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Abstract

Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear network will cause this negative effect. Therefore, we propose to constrain the incoming weights of each neuron to be unit-norm, which is formulated as an optimization problem over Oblique manifold. A simple yet efficient method referred to as projection based weight normalization (PBWN) is also developed to solve this problem. PBWN executes standard gradient updates, followed by projecting the updated weight back to Oblique manifold. This proposed method has the property of regularization and collaborates well with the commonly used batch normalization technique. We conduct comprehensive experiments on several widely-used image datasets including CIFAR-10, CIFAR-100, SVHN and ImageNet for supervised learning over the state-of-the-art convolutional neural networks, such as Inception, VGG and residual networks. The results show that our method is able to improve the performance of DNNs with different architectures consistently. We also apply our method to Ladder network for semi-supervised learning on permutation invariant MNIST dataset, and our method outperforms the state-of-the-art methods: we obtain test errors as 2.52%, 1.06%, and 0.91% with only 20, 50, and 100 labeled samples, respectively., Comment: 12 pages, 3 figures

Published
2017

15. Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks

Author

Huang, Lei, Liu, Xianglong, Lang, Bo, Yu, Adams Wei, Wang, Yongliang, and Li, Bo

Subjects
Computer Science - Learning
Abstract

Orthogonal matrix has shown advantages in training Recurrent Neural Networks (RNNs), but such matrix is limited to be square for the hidden-to-hidden transformation in RNNs. In this paper, we generalize such square orthogonal matrix to orthogonal rectangular matrix and formulating this problem in feed-forward Neural Networks (FNNs) as Optimization over Multiple Dependent Stiefel Manifolds (OMDSM). We show that the rectangular orthogonal matrix can stabilize the distribution of network activations and regularize FNNs. We also propose a novel orthogonal weight normalization method to solve OMDSM. Particularly, it constructs orthogonal transformation over proxy parameters to ensure the weight matrix is orthogonal and back-propagates gradient information through the transformation during training. To guarantee stability, we minimize the distortions between proxy parameters and canonical weights over all tractable orthogonal transformations. In addition, we design an orthogonal linear module (OLM) to learn orthogonal filter banks in practice, which can be used as an alternative to standard linear module. Extensive experiments demonstrate that by simply substituting OLM for standard linear module without revising any experimental protocols, our method largely improves the performance of the state-of-the-art networks, including Inception and residual networks on CIFAR and ImageNet datasets. In particular, we have reduced the test error of wide residual network on CIFAR-100 from 20.04% to 18.61% with such simple substitution. Our code is available online for result reproduction., Comment: 20 pages, Accepted by AAAI 2018

Published
2017

16. Whole genome resequencing reveals the evolutionary history and geographic isolation of the eastern Asian Hickory (Carya).

Author

Zhang, Da, Yang, Rui‐Feng, Chen, Jia‐Hui, Pan, Lang‐Bo, Duan, Wei, Xia, Guo‐Hua, Zhang, Qi‐Xiang, and Huang, You‐Jun

Subjects
SCIENTIFIC knowledge, SINGLE nucleotide polymorphisms, ENDANGERED plants, PHYTOGEOGRAPHY, HICKORIES, SPECIES distribution
Abstract

Societal Impact Statement: Unraveling the genetic intricacies and evolutionary history of Asian Hickories through advanced genome sequencing gives valuable insights into their ecological adaptations. Understanding the impact of historical dynamics, climate fluctuations, and geographical barriers on Asian hickories not only contributes to scientific knowledge but also empowers policymakers with evidence‐based decisions and guides conservationists in their efforts to protect vulnerable species. The identification of potential habitats, especially for the endangered Carya kweichowensis, offers a promising avenue for targeted conservation efforts, aligning with global initiatives to preserve Earth's precious biodiversity, but also ensures the conservation of a vital genetic reservoir for nut‐bearing economic tree species. Summary: Biogeographic characteristics of disjunct distribution play a vital role in plant geography and the endangered mechanism. The whole genome resequencing provides an opportunity to study the genetic relationship, population diffusion, and floristic evolution of disjunctive‐distribution flora. Based on the SNPs (single nucleotide polymorphisms) data generated by the whole genome deep resequencing of five EA (Eastern Asian) Carya species, we constructed the phylogenetic tree, genetic structure, and species distribution modeling to clarify the phylogenetic relationships and to predict the potential distribution area of EA Carya. Phylogenetic analysis of Carya revealed two distinct clades, separating EA Carya from NA (North America) Carya. C. kweichowensis, an endangered species, showed the lowest nucleotide diversity and the earliest divergence among studied EA Carya species. Species distribution modeling predicted suitable habitats for five EA Carya species, revealing the potential distribution of endangered C. kweichowensis. Importantly, minimal spatial overlap was observed among distribution regions of EA Carya species during different time periods. The uneven regional distribution of EA Carya is believed to be a consequence of Quaternary climate fluctuations, mountain barriers hindering species dispersal, and the limited cold tolerance of these trees. EA Carya highlights the significant role of climate and geological changes in their regional distribution and migration routes in Asia. Furthermore, the discovery of potential habitats offers a promising avenue for the conservation of C. kweichowensis. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

19. Elucidating the Fundamental Process of Methyl-(5hydroxymethyl) Furan-2-Carboxylate Toxin Biosynthesis in Curvularia lunata Causing Maize Leaf Spot.

Author

Lu, Zhixiang, Lang, Bo, Wang, Shaoqing, Liu, Hongyi, Wang, Xinhua, and Chen, Jie

Subjects
*ALCOHOL dehydrogenase, *AGRICULTURE, *CULTIVARS, *BIOSYNTHESIS, *CLIMATE change
Abstract

Maize leaf spot, which is caused by Curvularia lunata (Wakkre) Boedijn, was epidemic in the maize-growing regions of northeastern and northern China in the mid-1990s, where it led to large yield losses. Since then, the epidemic has evolved into a kind of common disease. In recent years, however, a tendency of becoming an epidemic disease again has been observed in some areas in China due to significant changes in climate, farming, systems and crop varieties. The significance of methyl-(5hydroxymethyl) furan-2-carboxylate (M5HF2C) as a nonspecific host toxin in causing maize leaf spot disease has been demonstrated in previous research. However, the key enzymes involved in M5HF2C toxin synthesis remain unclear. In our study, we demonstrate that the synthesis of M5HF2C toxin starts from a precursor substrate in the pathogen, furfural, which is then catalytically dehydrogenated into furoic acid via an alcohol dehydrogenase (CLADH6). The furoic acid was further confirmed as one of the raw materials for the biosynthesis of M5HF2C toxin based on deletion mutants of the alcohol dehydrogenase gene (Cladh6) in C. lunata, which had reduced M5HF2C toxin-producing ability; however, this ability could be restored in all deletion mutants through complementation with furoic acid, thereby confirming that furoic acid is an intermediate in the biosynthesis of M5HF2C toxin. In summary, the biosynthesis process of M5HF2C toxin in C. lunata involves three transformation steps: (1) from xylose to furfural; (2) then from furfural to furoic acid; and (3) eventually from furoic acid to M5HF2C toxin. Our research findings provide new clues in elucidating the major steps in the process of M5HF2C toxin biosynthesis in C. lunata. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

22. Change of insulin resistance in impaired fasting glucose patients with hypertension: a follow-up study of 5 years

Author

LANG Bo, DUAN Shanshan, LENG Weiling, GUO Li, LIU Ling, and WEI Ping

Subjects
impaired fasting glucose, hypertension, insulin resistance, diabetes, Medicine (General), R5-920
Abstract

Objective To observe the change of insulin resistance in the impaired fasting glucose patients with hypertension along with time elapse, and to investigate the relationship between hypertension and insulin resistance. Methods A total of 180 patients with impaired fasting glucose admitted in our outpatient department of endocrinology and physical examination center of our hospital during October 2012 and August 2013 were recruited in this study. All of them were given long-term lifestyle intervention, and were followed up for 5 years. Till the end of the follow-up, there were 114 patients included, and they were divided into the hypertension group (n=56) and the normal blood pressure group (n=58). Routine antihypertensive drugs were given to the hypertension group. Clinical data, such as fasting blood glucose, 2 h postprandial blood glucose, fasting insulin, 2 h postprandial insulin, and insulin resistance index (HOMA-IR) and insulin sensitivity index (ISI) from the third to the fifth year of follow-up were collected and analyzed. Results In the 5 years' follow-up, the prevalence of diabetes in the hypertension group was 22.83%, significantly higher than that of the normal blood pressure group (11.36%, P=0.042). The hypertension group had obviously higher HOMA-IR but statistically lower ISI when compared with the normal blood pressure group (both P < 0.001). Conclusion In the patients with impaired fasting glucose, elevated blood pressure is closely associated with insulin resistance. As time goes by, those impaired fasting glucose accompanied with hypertension are more prone to severe insulin resistance, and are more likely to progress to diabetes.

Published
2020
Full Text
View/download PDF

25. Cyber Security

Author

Lu, Wei, Wen, Qiaoyan, Zhang, Yuqing, Lang, Bo, Wen, Weiping, Yan, Hanbing, Li, Chao, Ding, Li, Li, Ruiguang, and Zhou, Yu

Subjects
Systems and Data Security, Computer Communication Networks, Information Systems Applications (incl. Internet), Computer System Implementation, Cryptology, Mobile and Network Security, Data and Information Security, Computer and Information Systems Applications, communication channels (information theory), communication systems, computer crime, computer hardware, computer networks, computer security, computer systems, cryptography, data communication systems, data security, databases, network protocols, network security, sensors, signal processing, telecommunication networks, telecommunication systems, telecommunication traffic, wireless telecommunication systems, Network hardware, Information retrieval, Internet searching, Systems analysis & design, Coding theory & cryptology, Data encryption, bic Book Industry Communication::U Computing & information technology::UR Computer security, bic Book Industry Communication::U Computing & information technology::UK Computer hardware::UKN Network hardware, bic Book Industry Communication::U Computing & information technology::UN Databases::UNH Information retrieval, bic Book Industry Communication::U Computing & information technology::UY Computer science::UYD Systems analysis & design, bic Book Industry Communication::G Reference, information & interdisciplinary subjects::GP Research & information: general::GPJ Coding theory & cryptology, bic Book Industry Communication::U Computing & information technology::UT Computer networking & communications::UTN Network security
Abstract

This open access book constitutes the refereed proceedings of the 16th International Annual Conference on Cyber Security, CNCERT 2020, held in Beijing, China, in August 2020. The 17 papers presented were carefully reviewed and selected from 58 submissions. The papers are organized according to the following topical sections: access control; cryptography; denial-of-service attacks; hardware security implementation; intrusion/anomaly detection and malware mitigation; social network security and privacy; systems security.

Published
2020
Full Text
View/download PDF

29. Cyber Security

Author

Yun, Xiaochun, Wen, Weiping, Lang, Bo, Yan, Hanbing, Ding, Li, Li, Jia, and Zhou, Yu

Subjects
Computer science, Computer security, thema EDItEUR::U Computing and Information Technology::UR Computer security
Abstract

This open access book constitutes the refereed proceedings of the 15th International Annual Conference on Cyber Security, CNCERT 2018, held in Beijing, China, in August 2018. The 14 full papers presented were carefully reviewed and selected from 53 submissions. The papers cover the following topics: emergency response, mobile internet security, IoT security, cloud security, threat intelligence analysis, vulnerability, artificial intelligence security, IPv6 risk research, cybersecurity policy and regulation research, big data analysis and industrial security.

Published
2019
Full Text
View/download PDF

30. Exploring the tidal effect of urban business district with large-scale human mobility data

Author

Niu, Hongting, Sun, Ying, Zhu, Hengshu, Geng, Cong, Yang, Jiuchun, Xiong, Hui, Lang, Bo, Niu, Hongting, Sun, Ying, Zhu, Hengshu, Geng, Cong, Yang, Jiuchun, Xiong, Hui, and Lang, Bo

Abstract

Business districts are urban areas that have various functions for gathering people, such as work, consumption, leisure and entertainment. Due to the dynamic nature of business activities, there exists significant tidal effect on the boundary and functionality of business districts. Indeed, effectively analyzing the tidal patterns of business districts can benefit the economic and social development of a city. However, with the implicit and complex nature of business district evolution, it is non-trivial for existing works to support the fine-grained and timely analysis on the tidal effect of business districts. To this end, we propose a data-driven and multi-dimensional framework for dynamic business district analysis. Specifically, we use the large-scale human trajectory data in urban areas to dynamically detect and forecast the boundary changes of business districts in different time periods. Then, we detect and forecast the functional changes in business districts. Experimental results on real-world trajectory data clearly demonstrate the effectiveness of our framework on detecting and predicting the boundary and functionality change of business districts. Moreover, the analysis on practical business districts shows that our method can discover meaningful patterns and provide interesting insights into the dynamics of business districts. For example, the major functions of business districts will significantly change in different time periods in a day and the rate and magnitude of boundaries varies with the functional distribution of business districts.

Published
2023

32. DAG: Dual Attention Graph Representation Learning for Node Classification.

Author

Lin, Siyi, Hong, Jie, Lang, Bo, and Huang, Lin

Subjects
REPRESENTATIONS of graphs, MESSAGE passing (Computer science), CLASSIFICATION, MACHINE learning, INFORMATION sharing
Abstract

Transformer-based graph neural networks have accomplished notable achievements by utilizing the self-attention mechanism for message passing in various domains. However, traditional methods overlook the diverse significance of intra-node representations, focusing solely on internode interactions. To overcome this limitation, we propose a DAG (Dual Attention Graph), a novel approach that integrates both intra-node and internode dynamics for node classification tasks. By considering the information exchange process between nodes from dual branches, DAG provides a holistic understanding of information propagation within graphs, enhancing the interpretability of graph-based machine learning applications. The experimental evaluations demonstrate that DAG excels in node classification tasks, outperforming current benchmark models across ten datasets. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

36. miR-503/Apelin-12 mediates high glucose-induced microvascular endothelial cells injury via JNK and p38MAPK signaling pathway

Author

Zhuo Tang, Juan Luo, Xin-Lan Zhao, Fang Hu, Ai-Ping Qin, Ling-Yun Huang, Lang-Bo Li, Li Yang, and Kai Chen

Subjects
0301 basic medicine, mutant, Mut, Diabetic angiopathy, DA, Biomedical Engineering, Inflammation, Diabetic angiopathy, Pharmacology, medicine.disease_cause, MicroRNAs, miRNAs, Biomaterials, 03 medical and health sciences, Quantitative Real-time-PCR, qPCR, 0302 clinical medicine, reactive oxygen species, ROS, Downregulation and upregulation, medicine, Apelin-12, Enzyme linked immunosorbent assay, ELISA, High glucose, HG, lcsh:QH573-671, wild type, WT, lcsh:R5-920, malondialdehyde, MDA, Chemistry, lcsh:Cytology, miR-503, medicine.disease, Apelin, Blot, 030104 developmental biology, Apoptosis, superoxide dismutase, SOD, p38MAPK, Original Article, JNK, medicine.symptom, Signal transduction, lcsh:Medicine (General), 030217 neurology & neurosurgery, Oxidative stress, Developmental Biology
Abstract

Introduction Diabetic patients are often accompanied by complications of diabetic vascular disease, which could lead to heart failure or stroke. In this work, we explored the role of miR-503/Apelin-12 in diabetic angiopathy (DA) in vitro. Methods ELISA and qPCR were applied to assess the expression of miR-503 and Apelin-12 in high glucose (HG)-treated microvascular endothelial cells (HMEC-1). The effects of miR-503 on apoptosis, inflammation and oxidative stress were assessed by flow cytometry, western blotting, qPCR, and ELISA. The interaction between miR-503 and Apelin-12 was evaluated by dual-luciferase reporter assay, qPCR and ELISA, respectively. Western blotting was performed to examine the function of miR-503/Apelin-12 on JNK and p38MAPK activation. Results MiR-503 was markedly increased and Apelin-12 was decreased in HG-treated HMEC-1 cells. MiR-503 inhibitor significantly assuaged apoptosis, inflammation and oxidative stress in HMEC-1 cells. MiR-503 could specifically bind to the 3′UTR of Apelin and inversely downregulate Apelin-12 expression. Furthermore, Apelin-12 suppressed apoptosis, inflammation and oxidative stress. Inhibition of Apelin-12 could partially reverse the decrease of p-JNK and p-p38 expression levels induced by miR-503 suppression. Conclusion In HG-induced microvascular cells injury, miR-503/Apelin-12 enhances inflammation and oxidative stress by regulating JNK and p38MAPK pathway, suggesting a potential therapeutic target for DA.

Published
2020

37. Exploring the Risky Travel Area and Behavior of Car-hailing Service

Author

Niu, Hongting, Zhu, Hengshu, Sun, Ying, Lu, Xinjiang, Sun, Jing, Zhao, Zhiyuan, Xiong, Hui, Lang, Bo, Niu, Hongting, Zhu, Hengshu, Sun, Ying, Lu, Xinjiang, Sun, Jing, Zhao, Zhiyuan, Xiong, Hui, and Lang, Bo

Abstract

Recent years have witnessed the rapid development of car-hailing services, which provide a convenient approach for connecting passengers and local drivers using their personal vehicles. At the same time, the concern on passenger safety has gradually emerged and attracted more and more attention. While car-hailing service providers have made considerable efforts on developing real-time trajectory tracking systems and alarm mechanisms, most of them only focus on providing rescue-supporting information rather than preventing potential crimes. Recently, the newly available large-scale car-hailing order data have provided an unparalleled chance for researchers to explore the risky travel area and behavior of car-hailing services, which can be used for building an intelligent crime early warning system. To this end, in this article, we propose a Risky Area and Risky Behavior Evaluation System (RARBEs) based on the real-world car-hailing order data. In RARBEs, we first mine massive multi-source urban data and train an effective area risk prediction model, which estimates area risk at the urban block level. Then, we propose a transverse and longitudinal double detection method, which estimates behavior risk based on two aspects, including fraud trajectory recognition and fraud patterns mining. In particular, we creatively propose a bipartite graph-based algorithm to model the implicit relationship between areas and behaviors, which collaboratively adjusts area risk and behavior risk estimation based on random walk regularization. Finally, extensive experiments on multi-source real-world urban data clearly validate the effectiveness and efficiency of our system. © 2021 Association for Computing Machinery.

Published
2022

38. Access control oriented quantified trust degree representation model for distributed systems

Author

LANG Bo

Subjects
access control, trust quantificational expression, trust calculating, distributed system, Telecommunication, TK5101-6720
Abstract

Based on the research fruit of social trust in sociology,the semantics,properties and elements of trust in the context of access control of distributed systems were defined.By combining fuzzy set theory with probability theory,a mathematical definition of trust was given,a quantified trust degree representation model including an integrated trust evaluation model and a trust calculating algorithm was established.The model integrates multiple elements of trust,and is in accordance with the decreasing and enhancing rules of the recommended trust.

Published
2010

41. Detection of Algorithmically Generated Malicious Domain Names with Feature Fusion of Meaningful Word Segmentation and N-Gram Sequences.

Author

Chen, Shaojie, Lang, Bo, Chen, Yikai, and Xie, Chong

Subjects
STANDARD deviations, VOCABULARY
Abstract

Domain generation algorithms (DGAs) play an important role in network attacks and can be mainly divided into two types: dictionary-based and character-based. Dictionary-based algorithmically generated domains (AGDs) are similar in composition to normal domains and are harder to detect. Although methods based on meaningful word segmentation and n-gram sequence features exhibit good detection performance for AGDs, they are inadequate for mining meaningful word features of domain names, and the performance of hybrid detection of character-based and dictionary-based AGDs needs to be further improved. Therefore, in this paper, we first describe the composition of dictionary-based AGDs using meaningful word segmentation, introduce the standard deviation to better measure the word distribution features, and construct additional 11-dimensional statistical features for word segmentation results as a supplement. Then, by combining 3-gram and 1-gram sequence features, we improve the detection performance for both character-based and dictionary-based AGDs. Finally, we perform feature fusion of the above four kinds of features to achieve an end-to-end detection method for both kinds of AGDs. Experimental results showed that our method achieved an accuracy of 97.24% on the full dataset and better accuracy and F1 values than existing methods on both dictionary-based and character-based AGD datasets. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

42. Adsorption of methane onto mudstones under supercritical conditions: Mechanisms, physical properties and thermodynamic parameters.

Author

Yang Wang, Hong-Fei Cheng, Qin-Hong Hu, Lang-Bo Jia, Xi-Meng Wang, Sha-Sha Gao, and Luo-Fu Liu

Subjects
THERMODYNAMICS, MUDSTONE, ADSORPTION (Chemistry), METHANE, NATURAL gas reserves, GEOLOGICAL carbon sequestration, SORPTION, SUPERCRITICAL carbon dioxide, SHALE gas
Abstract

Since the mechanisms of methane-mudstone interactions are important for estimating shale gas reserves, methane adsorption under supercritical conditions of 30 MPa pressure and 303.15, 333.15, 363.15 K temperatures was studied to measure the excess methane adsorption in two mudstone samples from Yanchang Formation, Ordos Basin. Excess adsorption features inflection points where the amount of adsorbed gas changes from increasing to decreasing concentrations. Three methods (fixed, slope, and freely fitted density) were applied to calculate the adsorbed-phase density (rad), which was then used to fit the measured excess adsorption. Two criteria, the goodness-of-fit and whether the fitting can obtain reasonable absolute adsorption, were applied to determine the most accurate model. Results indicated that the supercritical Dubinin-Radushkevich (SDR) model with freely fitted rad was the most reasonable model. The volume of adsorbed methane at 363.15 K is close to the micropore (d < 2 nm) volume of the corresponding mudstone. Considering the actual geological conditions, the adsorbed gas should be predominantly stored in micropores. Thermodynamic parameters reveal that the methane adsorption on mudstone is a physisorption process that is jointly controlled by the heterogeneity of, and interaction forces between the methane molecule and, the rock surface. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

45. Establishment of an animal model of chronic osteomyelitis with Staphylococcus aureus by ligating the femoral artery of rats

Author

Feng Jian-bo, Yang Li-dan, Wang Yu-qi, Li Chen-cheng, Yu Lang-bo, Zhao Chun-tao, Liu Jin-yue, He Wen-bin, Xiang Hao, Hong Jie-fan, Wang Xiao-min, and Peng -jiachen

Abstract

Background Osteomyelitis caused by Staphylococcus aureus (S. aureus) is an important post-operation complication, especially after fracture internal fixation and artificial joint replacement. Animal models play an indispensable role in exploring the pathogenesis of osteomyelitis. Most models use internal fixation, bacterial suspension and vascular sclerosing agent to destroy blood vessels. Vascular sclerosing agents not only damage blood vessels but also lead to local inflammatory immune disorders, which is different from simple vascular disease and osteomyelitis caused by ischemia in clinical practice. Methods The experimental animals were randomly divided into three groups: femoral artery ligation group, vascular sclerosing agent group and non-infection aseptic operation group. In the femoral artery ligation group, the femoral artery was ligated to reduce the blood flow of the affected limb to simulate the clinical ischemic state and increase the susceptibility, then the Kirschner needle with S. aureus biofilm was implanted into the tibia of rats, and the bone defect was sealed with aseptic paraffin. The non-infection aseptic operation group and the infection model group caused by vascular sclerosing agent have been used as the blank and positive control group. After operation, survival rate, body temperature and incision healing were monitored. Four weeks later, radiological and pathological changes of all animals were evaluated, and the secretions from osteomyelitis experienced etiological separation and cultivation. Results The chronic osteomyelitis model was established successfully by ligating femoral artery and implanting Kirschner needle covered with S. aureus biofilm. Signs of chronic osteomyelitis were observed in all rats of femoral artery ligation infection group and positive control group. No signs of infection and chronic osteomyelitis were found in the non-infection aseptic operation control group. Conclusion The method of ligating the femoral artery and implanting Kirschner needle with S. aureus biofilm into the tibia of rats can effectively establish a stable and reproducible chronic osteomyelitis model which is closer to the clinical pathogenesis and natural route of infection. This model could be useful for the study of pathogenesis and therapeutics of chronic osteomyelitis with S. aureus.

Published
2020
Full Text
View/download PDF

47. A ciphertext-policy hidden vector encryption scheme supporting multiuser keyword search

Author

Wang Jinmiao, Lang Bo, and Liao Zhenhua

Subjects
Theoretical computer science, Computer Networks and Communications, Computer science, business.industry, Client-side encryption, Computer security, computer.software_genre, Encryption, Multiple encryption, Filesystem-level encryption, Probabilistic encryption, Link encryption, Attribute-based encryption, On-the-fly encryption, business, computer, Information Systems
Abstract

In cloud computing, large amount of data can be effectively stored and managed. People could outsource the encrypted data using searchable encryption SE for data security and efficient retrieval. However, most existing SE schemes only support the single-user access, and multiuser searchable encryption is required in many enterprise applications. From the attribute-based encryption ABE, we found that the flexibility and usability of encryption schemes can be greatly improved by embedding attribute-based access policy in the ciphertext. In this paper, by using the idea of ABE, we propose a ciphertext-policy hidden vector encryption CPHVE scheme to support both encryption and search operations for multiple users. In the scheme, a keyword is encrypted with an attribute-based access policy, which can be searched when the users' attributes satisfy the policy. The security of CPHVE is also defined and proved in this paper. Moreover, the CPHVE scheme is based on standard complexity assumptions on bilinear groups of prime order, thus it is more efficient than the existing schemes. Copyright © 2014 John Wiley & Sons, Ltd.

Published
2014
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results