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-articleAugust 2024
Defending against similarity shift attack for EaaS via adaptive multi-target watermarking
Information Sciences: an International Journal (ISCI), Volume 678, Issue CSep 2024https://doi.org/10.1016/j.ins.2024.120893AbstractLarge language models have revolutionized natural language processing, leading to the emergence of Embedding as a Service (EaaS). While EaaS facilitates access to advanced embedding models, it also presents challenges in copyright protection. ...
- short-paperAugust 2024
Xraytest: An X-ray Test system for finding faults of RDMA-NIC Design and Implementation
NAIC '24: Proceedings of the 2024 SIGCOMM Workshop on Networks for AI ComputingAugust 2024, Pages 7–8https://doi.org/10.1145/3672198.3673802This paper presents a test system, which can find faults of RDMA-NIC design and implementation as well as X-ray in medical examination, which can supply a gap between self-developed RDMA NIC and business RDMA NIC such as Mellanox. Our work, Xraytest, ...
- research-articleJuly 2024
Joint Variational Inference Network for domain generalization
AbstractDomain generalization is a machine learning task that involves training a model on a set of domains with the goal of achieving high performance on unseen domains. While most domain generalization methods focus on extracting domain-invariant ...
Highlights- Propose an end-to-end variational-based discriminative framework for domain generalization.
- Construct a latent mapping structure to describe the relationship between domain-specific and class-relevant information in an explicit manner.
- research-articleJuly 2024
A two-stage clonal selection algorithm for local feature selection on high-dimensional data
Information Sciences: an International Journal (ISCI), Volume 677, Issue CAug 2024https://doi.org/10.1016/j.ins.2024.120867AbstractVarious evolutionary computation algorithms have shown their excellent performance for high-dimensional feature selection (FS). However, most of current FS methods choose a global feature subset and ignore the correlations between feature subsets ...
Highlights- A two-stage clonal selection algorithm for filter-based local feature selection is proposed.
- A feature subset for each sample region is selected based on a local clustering idea.
- A discrete clonal selection algorithm is developed ...
- research-articleJuly 2024
Failure risk assessment by multi-state dynamic Bayesian network based on interval type-2 fuzzy sets and leaky-weighted sum algorithm: A case study of crude oil pipelines
Expert Systems with Applications: An International Journal (EXWA), Volume 250, Issue CSep 2024https://doi.org/10.1016/j.eswa.2024.123942AbstractFailures of the pipelines can not only result in economic losses, but also potentially lead to serious safety accidents. Therefore, it is important to assess the failure risk of pipelines in order to prevent and mitigate pipeline failure ...
-
- research-articleJuly 2024
Towards constructing a DOE-based practical optical neural system for ship recognition in remote sensing images
AbstractThe optical neural network system based on the 4f system (4f-ONN) is a feasible solution for on-orbit real-time target detection and recognition on remote sensing images, as it can directly modulate and encode the two-dimensional image ...
Highlights- A structurally more compact and stable DOE-based 4f system is proposed.
- The effects of quantization and manufacturing errors on the performance of the DOE-based 4f system are analyzed.
- Extensive experiments demonstrate the ...
- posterAugust 2024
Adaptive Immune Optimization Algorithm: Combining Mutual Information and Differential Evolution-based Mutation for Local Feature Selection on Microarray Data
GECCO '24 Companion: Proceedings of the Genetic and Evolutionary Computation Conference CompanionJuly 2024, Pages 483–486https://doi.org/10.1145/3638530.3654412Microarray data, characterized by high dimensionality and small sample sizes, poses significant challenges in identifying genes relevant for disease classification and prognosis. Our study proposes a one-stage filter local feature selection based on an ...
- research-articleJuly 2024
Big data-driven TBM tunnel intelligent construction system with automated-compliance-checking (ACC) optimization
Expert Systems with Applications: An International Journal (EXWA), Volume 244, Issue CJun 2024https://doi.org/10.1016/j.eswa.2023.122972AbstractTBM tunneling in subsea areas with adverse geological conditions presents potential risks due to non-compliant tunneling strategies resulting from manual adjustments and untimely communications. This study proposes an innovative subsea TBM tunnel ...
- research-articleJuly 2024
AKA-SafeMed: A safe medication recommendation based on attention mechanism and knowledge augmentation
Information Sciences: an International Journal (ISCI), Volume 670, Issue CJun 2024https://doi.org/10.1016/j.ins.2024.120577AbstractMedication recommendation (MR) focuses on generating a medication combination without adverse drug-drug interactions (DDIs) based on electronic health records (EHRs) in making prescriptions. However, how to capture the temporality in historical ...
Highlights- We model EHR sequential data for patient and medication representations.
- Both BiLSTM and self-attention mechanism are beneficial to patient representations.
- We deploy knowledge augmentation strategy for safe medication ...
- research-articleJuly 2024
Distributed virtual simulation experimental software for high-power electric traction system of 600 km/h high-speed maglev train
Advances in Engineering Software (ADES), Volume 192, Issue CJun 2024https://doi.org/10.1016/j.advengsoft.2024.103627AbstractThe operational speed of high-speed maglev trains has reached a groundbreaking 600 km/h, facilitating faster intercity transportation. However, the design and verification of corresponding high-power electric traction systems face significant ...
Highlights- Innovated virtual simulation experimental software for high-speed maglev train.
- Designed the simulation client and server architecture for electric traction system.
- Constructed virtual digital models to simulate 600km/h operational ...
- research-articleJuly 2024
A transformer-CNN parallel network for image guided depth completion
AbstractImage guided depth completion aims to predict a dense depth map from sparse depth measurements and the corresponding single color image. However, most state-of-the-art methods only rely on convolutional neural network (CNN) or transformer. In ...
Highlights- We propose a transformer-CNN parallel network by exploiting local details and global contexts.
- We design a correlation-based transformer branch to compute attention only with the top-k relevant tokens.
- We propose a multi-scale ...
- research-articleMay 2024
Securing Contrastive mmWave-based Human Activity Recognition against Adversarial Label Flipping
WiSec '24: Proceedings of the 17th ACM Conference on Security and Privacy in Wireless and Mobile NetworksMay 2024, Pages 31–41https://doi.org/10.1145/3643833.3656123Wireless Human Activity Recognition (HAR), leveraging their non-intrusive nature, has the potential to revolutionize various sectors, including healthcare, virtual reality, and surveillance. The advent of millimeter wave (mmWave) technology has ...
- research-articleMay 2024
PASS: Predictive Auto-Scaling System for Large-scale Enterprise Web Applications
WWW '24: Proceedings of the ACM on Web Conference 2024May 2024, Pages 2747–2758https://doi.org/10.1145/3589334.3645330We confront two challenges in the management of a vast and diverse array of online web applications deployed on enterprise-grade auto-scaling infrastructure, primarily focused on ensuring Quality of Service (QoS) for large-scale applications and ...
- research-articleMay 2024
Automatic Macro Mining from Interaction Traces at Scale
CHI '24: Proceedings of the CHI Conference on Human Factors in Computing SystemsMay 2024, Article No.: 1038, Pages 1–16https://doi.org/10.1145/3613904.3642074Macros are building block tasks of our everyday smartphone activity (e.g., "login", or "booking a flight"). Effectively extracting macros is important for understanding mobile interaction and enabling task automation. These macros are however difficult ...
- research-articleJuly 2024
Dynamic temperature distribution characteristics of a large glasshouse with cooling system during the start-stop stage
Computers and Electronics in Agriculture (COEA), Volume 220, Issue CMay 2024https://doi.org/10.1016/j.compag.2024.108913Highlights- The internal environment of a large glasshouse with a cooling system was tested.
- Temperature dynamics during the start-stop stage was investigated.
- Uniform and stable temperature distribution after system operation stabilization.
Excessive heat accumulation leads to high temperature in the glasshouse, the high temperature directly affects the normal growth of crops. This research based on the cooling system as the cooling method of glasshouse, experimental and ...
- research-articleJuly 2024
Context CVGN: A conditional multimodal trajectory prediction network based on scene semantic modeling
Information Sciences: an International Journal (ISCI), Volume 666, Issue CMay 2024https://doi.org/10.1016/j.ins.2024.120433AbstractPedestrian behavior and trajectory prediction in highly dynamic and interactive scenes have emerged as among the most daunting challenges in the realm of autonomous driving. In addressing the modeling of pedestrian interaction and the generation ...
- research-articleJune 2024
Towards robust neural networks via orthogonal diversity
AbstractDeep Neural Networks (DNNs) are vulnerable to invisible perturbations on the images generated by adversarial attacks, which raises researches on the adversarial robustness of DNNs. A series of methods represented by the adversarial training and ...
Highlights- A novel adversarial defense exploring model properties to improve DNNs’ robustness
- Multiple paths augment DNNs for diverse features adaptive to adversarial inputs
- An orthogonality loss and a margin-maximization loss contribute to ...
- research-articleApril 2024
Multi-scale deep echo state network for time series prediction
Neural Computing and Applications (NCAA), Volume 36, Issue 21Jul 2024, Pages 13305–13325https://doi.org/10.1007/s00521-024-09761-4AbstractEcho state network (ESN) has widely attracted many researchers due to its training process without backpropagation. However, it is hard for single ESN to fit those complex and polytrophic situations. Under this case, a novel multiscale deep ESN (...
- research-articleApril 2024
CSGAT-Net: a conditional pedestrian trajectory prediction network based on scene semantic maps and spatiotemporal graph attention
Neural Computing and Applications (NCAA), Volume 36, Issue 19Jul 2024, Pages 11409–11423https://doi.org/10.1007/s00521-024-09784-xAbstractPedestrian behavior exhibits high levels of dynamism, and pedestrian trajectories are influenced not only by the pedestrians themselves, but also by interactions with surrounding objects. Efficiently understanding pedestrian motion behavior and ...
- research-articleJune 2024
JPMDP: Joint base placement and multi-configuration path planning for 3D surface disinfection with a UV-C robotic system
Robotics and Autonomous Systems (ROAS), Volume 174, Issue CApr 2024https://doi.org/10.1016/j.robot.2024.104644AbstractTo effectively mitigate the spread of epidemics, disinfection robots are increasingly utilized for automatic disinfection. However, tradition robots and disinfection methods cannot ensure controllable disinfection coverage, potentially causing ...
Highlights- Proposing a novel UV-C disinfection robot for epidemic control.
- Introducing a multi-side disinfection end-effector for complex surface adaptability.
- Presenting a JPMDP method for optimal coordination of base and manipulator ...