Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
The competitive diffusion of knowledge and rumor in a multiplex network: A mathematical model
Applied Mathematics and Computation (APMC), Volume 475, Issue CAug 2024https://doi.org/10.1016/j.amc.2024.128719AbstractThe competition between rumor and knowledge has received significant attention from the global world. How to spread knowledge to better contain rumor has also become an important practical issue. In this study, we build a multi-compartment model ...
Highlights- An extended UAU model is proposed to study the competitive diffusion of rumor and knowledge in a multiplex network.
- The mechanism of knowledge penetrating rumor is introduced into the rumor-knowledge competitive diffusion model.
- ...
- ArticleJuly 2024
Temporal Difference Enhancement Network for Driving Behavior Recognition
Advances in Neural Networks – ISNN 2024Jul 2024, Pages 211–221https://doi.org/10.1007/978-981-97-4399-5_20AbstractAccurately recognizing bad driving behaviors, such as fatigue, using mobile phone, eye deviation and smoking, can greatly avoid the occurrence of traffic accidents. Existing techniques would be heavily affected by some uncertainties including ...
- research-articleJune 2024
Two-stage greedy algorithm based on crowd sensing for tour route recommendation
Applied Soft Computing (APSC), Volume 153, Issue CMar 2024https://doi.org/10.1016/j.asoc.2024.111260AbstractCurrently, the demand for tourism is increasing, but traditional tour group routes have been unable to meet individual needs. This paper proposes a novel personalized recommendation method for tour routes based on crowd sensing. First, we utilize ...
Highlights- We propose two recommendation algorithms to address the weaknesses of existing methods in terms of multiple POI route recommendation and the difficulty of quantifying user preference constraints.
- We utilize a crowd sensing score ...
- research-articleFebruary 2024
Adaptive stepsize estimation based accelerated gradient descent algorithm for fully complex-valued neural networks
Expert Systems with Applications: An International Journal (EXWA), Volume 236, Issue CFeb 2024https://doi.org/10.1016/j.eswa.2023.121166AbstractNesterov accelerated gradient (NAG) method is an efficient first-order algorithm for optimization problems. To ensure the convergence, it usually takes a relatively conservative constant as the stepsize. However, the choice of stepsize has a ...
Highlights- Adaptive stepsize design methods without manual tuning are proposed for CNAG.
- Stepsize is obtained by estimating the norm of approximate Hessian matrix.
- Theoretical analysis is presented to support the validity of the design ...
- research-articleMay 2024
Triple eagle: simple, fast and practical budget-feasible mechanisms
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 1470, Pages 33894–33911We revisit the classical problem of designing Budget-Feasible Mechanisms (BFMs) for submodular valuation functions, which has been extensively studied since the seminal paper of Singer [FOCS'10] due to its wide applications in crowdsourcing and social ...
-
- research-articleMay 2024
MM-Fi: multi-modal non-intrusive 4D human dataset for versatile wireless sensing
- Jianfei Yang,
- He Huang,
- Yunjiao Zhou,
- Xinyan Chen,
- Yuecong Xu,
- Shenghai Yuan,
- Han Zou,
- Chris Xiaoxuan Lu,
- Lihua Xie
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 822, Pages 18756–187684D human perception plays an essential role in a myriad of applications, such as home automation and metaverse avatar simulation. However, existing solutions which mainly rely on cameras and wearable devices are either privacy intrusive or inconvenient ...
- research-articleMay 2024
DSR: dynamical surface representation as implicit neural networks for protein
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsDecember 2023, Article No.: 611, Pages 13873–13886We propose a novel neural network-based approach to modeling protein dynamics using an implicit representation of a protein's surface in 3D and time. Our method utilizes the zero-level set of signed distance functions (SDFs) to represent protein surfaces,...
- research-articleNovember 2023
Memory-Efficient and Flexible Detection of Heavy Hitters in High-Speed Networks
Proceedings of the ACM on Management of Data (PACMMOD), Volume 1, Issue 3Article No.: 214, Pages 1–24https://doi.org/10.1145/3617334Heavy-hitter detection is a fundamental task in network traffic measurement and security. Existing work faces the dilemma of suffering dynamic and imbalanced traffic characteristics or lowering the detection efficiency and flexibility. In this paper, we ...
- research-articleOctober 2023
Weak Regression Enhanced Lifelong Learning for Improved Performance and Reduced Training Data
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementOctober 2023, Pages 1587–1596https://doi.org/10.1145/3583780.3615108As an emerging learning paradigm, lifelong learning intends to solve multiple consecutive tasks over long-time scales upon previously accumulated knowledge. When facing with a new task, existing lifelong learning approaches need first gather sufficient ...
- ArticleFebruary 2024
- ArticleFebruary 2024
Persistent Sketch: A Memory-Efficient and Robust Algorithm for Finding Top-k Persistent Flows
Algorithms and Architectures for Parallel ProcessingOct 2023, Pages 19–38https://doi.org/10.1007/978-981-97-0811-6_2AbstractFinding top-k persistent flows in high-speed network traffic is crucial for applications like click-fraud detection and covert attacker detection. The prior studies either do not separate persistent and non-persistent flows during online traffic ...
- research-articleOctober 2023
Stochastic adaptive CL-BFGS algorithms for fully complex-valued dendritic neuron model
Knowledge-Based Systems (KNBS), Volume 277, Issue COct 2023https://doi.org/10.1016/j.knosys.2023.110788AbstractThis paper proposes two stochastic variance reduced gradient algorithms based on adaptive complex-valued limited-memory BFGS (ACL-BFGS) algorithm, which are established on the calculation of Wirtinger gradient for fully complex-valued ...
Revisiting Cardinality Estimation in COTS RFID Systems
ACM MobiCom '23: Proceedings of the 29th Annual International Conference on Mobile Computing and NetworkingOctober 2023, Article No.: 80, Pages 1–14https://doi.org/10.1145/3570361.3613295With 30 billion RFID tags sold worldwide in 2021, a common basic functionality needed by RFID-enabled applications is cardinality estimation --- to quickly estimate the number of distinct tags in an RFID system. Although many advanced solutions have ...
- articleSeptember 2023
A comprehensive survey on DDoS defense systems: New trends and challenges
Computer Networks: The International Journal of Computer and Telecommunications Networking (CNTW), Volume 233, Issue CSep 2023https://doi.org/10.1016/j.comnet.2023.109895AbstractIn the past ten years, the source of DDoS has migrated to botnets composed of IoT devices. The scale of DDoS attacks increases dramatically with the number of IoT devices.New variants of DDoS attacks using different system vulnerabilities emerge ...
- ArticleDecember 2023
LS-Net: COVID-19 Lesion Segmentation from CT Image via Diffusion Probabilistic Model
AbstractCoronavirus Disease 2019 (COVID-19) ravaged the world in early 2020, causing great harm to human health. However, there are several challenges to segment the infected areas from computed tomography (CT) image, including blurry boundaries between ...
- research-articleAugust 2023
Adaptive Block-Wise Regularization and Knowledge Distillation for Enhancing Federated Learning
IEEE/ACM Transactions on Networking (TON), Volume 32, Issue 1Pages 791–805https://doi.org/10.1109/TNET.2023.3301972Federated Learning (FL) is a distributed model training framework that allows multiple clients to collaborate on training a global model without disclosing their local data in edge computing (EC) environments. However, FL usually faces statistical ...
- research-articleAugust 2023
Adaptive orthogonal gradient descent algorithm for fully complex-valued neural networks
AbstractFor optimization algorithms of fully complex-valued neural networks, complex-valued stepsize is helpful to make the training escape from saddle points. In this paper, an adaptive orthogonal gradient descent algorithm with complex-...
- research-articleAugust 2023
Strengthening transferability of adversarial examples by adaptive inertia and amplitude spectrum dropout
Neural Networks (NENE), Volume 165, Issue CAug 2023, Pages 925–937https://doi.org/10.1016/j.neunet.2023.06.031AbstractDeep neural networks are sensitive to adversarial examples and would produce wrong results with high confidence. However, most existing attack methods exhibit weak transferability, especially for adversarially trained models and defense models. ...
- research-articleAugust 2023
Impacts of distributional fairness concerns on quality disclosure in a dyadic supply chain
Computers and Industrial Engineering (CINE), Volume 182, Issue CAug 2023https://doi.org/10.1016/j.cie.2023.109416Highlights- The manufacturer’s fairness concerns incentivize both the manufacturer and the retailer to disclose more quality information.
- The retailer’s fairness concerns do not affect its own quality disclosure but induce the manufacturer to ...
In a dyadic channel, firms are concerned with both monetary payouts and distributional fairness, in which they exhibit fairness concerns when another member receives a larger share of total profit. Previous studies have neglected the impact of ...
- research-articleJuly 2023
Efficient sequence transduction by jointly predicting tokens and durations
ICML'23: Proceedings of the 40th International Conference on Machine LearningJuly 2023, Article No.: 1602, Pages 38462–38484This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly predicting both a token and its duration, i.e. the number of input frames ...