Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- ArticleSeptember 2024
Layer-Wised Sparsification Based on Hypernetwork for Distributed NN Training
Artificial Neural Networks and Machine Learning – ICANN 2024Pages 186–201https://doi.org/10.1007/978-3-031-72347-6_13AbstractAs Deep Neural Networks (DNNs) evolve in complexity, so does their parameter size, resulting in prolonged training time. While various distributed training strategies have been proposed to speed up training, the efficiency of these strategies is ...
- research-articleSeptember 2024
A multiscale neural architecture search framework for multimodal fusion
Information Sciences: an International Journal (ISCI), Volume 679, Issue Chttps://doi.org/10.1016/j.ins.2024.121005AbstractMultimodal fusion, a machine learning technique, significantly enhances decision-making by leveraging complementary information extracted from different data modalities. The success of multimodal fusion relies heavily on the design of the fusion ...
Highlights- This paper presents the first theoretical and empirical evidence demonstrating that DARTS suffers from catastrophic search bias in multimodal fusion, rendering the entire search ineffective. We term this phenomenon as the “Matthew Effect” ...
- articleSeptember 2024
Global Structure Preservation and Self-Representation-Based Supervised Feature Selection
International Journal of Cognitive Informatics and Natural Intelligence (IJCINI-IGI), Volume 18, Issue 1Pages 1–19https://doi.org/10.4018/IJCINI.346987Feature selection aims to select a subset of features from high-dimensional data, which can overcome the curse of dimensionality for the next dealing steps. However, the feature selection itself could face the curse of dimensionality. To overcome the ...
- research-articleOctober 2024
Empirical analysis of evaluation indicators for blended teaching mode in vocational colleges based on SPSS
EKI '24: Proceedings of the 2nd International Conference on Educational Knowledge and InformatizationPages 51–58https://doi.org/10.1145/3691720.3691730To enhance the teaching effectiveness of the blended teaching model in higher vocational colleges, this article studies the impact of factors such as teachers' information technology proficiency, innovative teaching strategies, and students' autonomous ...
- research-articleOctober 2024
Research on the Construction of Evaluation Index System for Hybrid Teaching in Vocational Colleges Based on Analytic Hierarchy Process
IECT '24: Proceedings of the 2024 International Conference on Intelligent Education and Computer TechnologyPages 71–76https://doi.org/10.1145/3687311.3687325In order to improve the mixed teaching quality of computer technology teaching in vocational colleges, the Analytic Hierarchy Process (AHP) is used to construct and optimize the evaluation index system of teaching quality, covering key dimensions such as ...
-
- research-articleJuly 2024
DeFTA: A plug-and-play peer-to-peer decentralized federated learning framework
Information Sciences: an International Journal (ISCI), Volume 670, Issue Chttps://doi.org/10.1016/j.ins.2024.120582AbstractFederated learning (FL) is a pivotal catalyst for enabling large-scale privacy-preserving distributed machine learning (ML). By eliminating the need for local raw dataset sharing, FL substantially reduces privacy concerns and alleviates the ...
Highlights- A novel model aggregating formula is proposed that eliminates the aggregating bias in decentralized FL.
- Selfish workers are introduced to the decentralized FL setting, which is simple and robust against backdoor attacks.
- A general ...
- research-articleMay 2024
AAPF*: a safer autonomous vehicle path planning algorithm based on the improved A* algorithm and APF algorithm
Cluster Computing (KLU-CLUS), Volume 27, Issue 8Pages 11393–11406https://doi.org/10.1007/s10586-024-04287-9AbstractIn this paper, we introduce the AAPF* algorithm, an innovative approach that synergistically integrates the A-star search algorithm (A*) with the artificial potential field (APF) method. This algorithm is designed to enhance safety and ensure ...
- research-articleMay 2024
CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
- Peng Di,
- Jianguo Li,
- Hang Yu,
- Wei Jiang,
- Wenting Cai,
- Yang Cao,
- Chaoyu Chen,
- Dajun Chen,
- Hongwei Chen,
- Liang Chen,
- Gang Fan,
- Jie Gong,
- Zi Gong,
- Wen Hu,
- Tingting Guo,
- Zhichao Lei,
- Ting Li,
- Zheng Li,
- Ming Liang,
- Cong Liao,
- Bingchang Liu,
- Jiachen Liu,
- Zhiwei Liu,
- Shaojun Lu,
- Min Shen,
- Guangpei Wang,
- Huan Wang,
- Zhi Wang,
- Zhaogui Xu,
- Jiawei Yang,
- Qing Ye,
- Gehao Zhang,
- Yu Zhang,
- Zelin Zhao,
- Xunjin Zheng,
- Hailian Zhou,
- Lifu Zhu,
- Xianying Zhu
ICSE-SEIP '24: Proceedings of the 46th International Conference on Software Engineering: Software Engineering in PracticePages 418–429https://doi.org/10.1145/3639477.3639719Code Large Language Models (Code LLMs) have gained significant attention in the industry due to their wide applications in the full lifecycle of software engineering. However, the effectiveness of existing models in understanding non-English inputs for ...
- research-articleMarch 2024
Edge intelligence empowered delivery route planning for handling changes in uncertain supply chain environment
Journal of Cloud Computing: Advances, Systems and Applications (JOCCASA), Volume 13, Issue 1https://doi.org/10.1186/s13677-024-00613-zAbstractTraditional delivery route planning faces challenges in reducing logistics costs and improving customer satisfaction with growing customer demand and complex road traffic, especially in uncertain supply chain environment. To address these ...
- research-articleJune 2024
Design and control of a new omnidirectional levelling system for hilly crawler work machines
Computers and Electronics in Agriculture (COEA), Volume 218, Issue Chttps://doi.org/10.1016/j.compag.2024.108661Highlights- A new structure of omnidirectional levelling system is proposed.
- The sensitivity analysis of the structural parameters for levelling system is carried out.
- The structural parameter optimization based on NSGA-Ⅱ algorithm is ...
To address the challenges posed by significant body inclination, suboptimal work quality, and safety concerns during agricultural machinery operations in hilly terrains, this study presents the design of an omnidirectional levelling system ...
- research-articleMarch 2024
Event-Oriented Linkable Group Signature From Lattice
IEEE Transactions on Consumer Electronics (ITOCE), Volume 70, Issue 1Pages 2224–2234https://doi.org/10.1109/TCE.2024.3364188With the ever-increasing volume of transactions on e-commerce platforms, the protection of consumer privacy becomes a paramount concern. In this context, group signatures have proven to be an effective tool for the privacy-preserving of consumers. However,...
- research-articleMay 2024
PRIOR: personalized prior for reactivating the information overlooked in federated learning
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsArticle No.: 1234, Pages 28378–28392Classical federated learning (FL) enables training machine learning models without sharing data for privacy preservation, but heterogeneous data characteristic degrades the performance of the localized model. Personalized FL (PFL) addresses this by ...
- research-articleMarch 2024
Amplitude prediction from uplink to downlink CSI against receiver distortion in FDD systems
AbstractIn frequency division duplex (FDD) massive multiple-input multiple-output (mMIMO) systems, the reciprocity mismatch caused by receiver distortion seriously degrades the amplitude prediction performance of channel state information (CSI). To ...
- research-articleMay 2024
Human Behavior Analysis Methods Based on Temporal Information Enhancement
ICAICE '23: Proceedings of the 4th International Conference on Artificial Intelligence and Computer EngineeringPages 703–707https://doi.org/10.1145/3652628.3652745Aiming at the difficulty in extracting temporal information from human behavior in videos, we propose a temporal information enhancement algorithm based on frame differencing. This algorithm computes the frame difference intensity through frame ...
- research-articleMay 2024
Video Anomaly Detection based on Foreground Objects
ICAICE '23: Proceedings of the 4th International Conference on Artificial Intelligence and Computer EngineeringPages 471–475https://doi.org/10.1145/3652628.3652706In the context of complex scenes in surveillance environments, the detection of video anomalies is often hindered. To address this issue, this paper proposes a video anomaly detection algorithm based on foreground objects. Firstly, by combining frame ...
- research-articleMay 2024
Pedestrian ranging algorithm based on improved YOLOv7 and DeepSORT
ICAICE '23: Proceedings of the 4th International Conference on Artificial Intelligence and Computer EngineeringPages 102–107https://doi.org/10.1145/3652628.3652645The pedestrian ranging algorithm in public places can be used for epidemic prevention and control, which has high research value. Aiming at the shortcomings of the existing pedestrian ranging algorithms in precision and running speed, an improved ...
- research-articleNovember 2023
Efficient lattice-based traceable ring signature scheme with its application in blockchain
Information Sciences: an International Journal (ISCI), Volume 648, Issue Chttps://doi.org/10.1016/j.ins.2023.119536Highlights- A novel lattice-based traceable ring signature scheme is proposed.
- The proposed scheme is constructed based on a novel TripleRing structure.
- A quantum resistant blockchain model based on the proposed scheme is developed.
- The ...
Traceable ring signatures (TRSs) were proposed by Fujisaki and Suzuki (PKC 2007), which is a variant of ring signatures that aims to restrict excessive anonymity of them. If the signer signs two identical messages about the same group of ring ...
- research-articleApril 2024
A graph comparison learning recommendation algorithm based on knowledge graph enhancement
EITCE '23: Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer EngineeringPages 1020–1024https://doi.org/10.1145/3650400.3650572The recommender system's overall suggestion results may be erroneous and weakly robust due to the sparse interaction behavior between users and items in the system and the noise inherent in interaction samples. This research suggests a graph comparison ...
- research-articleApril 2024
Gradually Stabilized Random Walk Algorithm for Tongue Image Extraction Based on Meta-Heuristic Parameter Optimization
EITCE '23: Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer EngineeringPages 277–281https://doi.org/10.1145/3650400.3650445Aiming at the problems that there are several parameters to be set manually, and traditional random walk algorithm may be unstable under some circumstances. In this paper, 2 meta-heuristic methods are introduced to make adaptive parameter optimizations. ...
- research-articleMay 2023
Human object interaction detection based on feature optimization and key human-object enhancement
Journal of Visual Communication and Image Representation (JVCIR), Volume 93, Issue Chttps://doi.org/10.1016/j.jvcir.2023.103824AbstractAiming at the problem of unclear or missing human object interaction behavior objects in complex background, we propose a human object interaction detection algorithm based on feature optimization and key human-object enhancement. In ...