检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6121-6133页

作者： Cheng, Jiang-Xing Lin, Huibin Zhang, Chun-Yang Chen, C. L. Philip Fuzhou University College of Computer and Data Science Fuzhou350108 China South China University of Technology School of Computer Science and Engineering Guangdong Guangzhou510006 China

Point clouds can capture the precise geometric information of objects and scenes, which are an important source of 3-D data and one of the most popular 3-D geometric data structures for cognitions in many real-world applications like automatic driving and remote sensing. However, due to the influence of sensors and varieties of objects, the point clouds obtained by different devices may suffer obvious geometric changes, resulting in domain gaps that are prone to the neural networks trained in one domain failing to preserve the performance in other domains. To alleviate the above problem, this article proposes an unsupervised domain adaptation framework, named HO-GSM, as the first attempt to model high-order geometric structures of point clouds. First, we construct multiple self-supervised tasks to learn the invariant semantic and geometric features of the source and target domains, especially to capture the feature invariance of high-order geometric structures of point clouds. Second, the discriminative feature space of target domain is acquired by using contrastive learning to refine domain alignment to specific class level. Experiments on the PointDA-10 and GraspNetPC-10 collection of datasets show that the proposed HO-GSM can significantly outperform the state-of-the-art counterparts. © 2020 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Semantic and Robust Authentication Scheme for User-Based Access Control on Cloud Storage 6th

A Semantic and Robust Authentication Scheme for User-Based A...

引用

6th International Conference on Information Systems and Management Science, ISMS 2023

作者： Agarwal, Saumye Vardhan, Harsha Kothapalle Prasanth, Narayanan Joshva Devadas, T. Naveenkumar, J. Sureshkumar, Williams School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India

ISBN: (纸本)9783031707889

Cloud computing and cloud related services are gaining ground in today’s technology driven world. It allows an individual to delegate their work and store it in the cloud. The cloud provides pay per usage kind of services to the users. However, this model of services needs to ensure privacy and authentication so that only authorized users can access resources in the cloud. In this paper, we proposed a user authentication architecture that aims to improve user authentication for different cloud services and simultaneously incorporating a fine-grained access. A blockchain based approach is used to provide the security. We tested the architecture with two different scenarios and the result proves that the approach is effective and secure. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Cloud computing architecture

来源：评论

学校读者我要写书评

暂无评论

Scaling Up the Transformers: A Survey of Training and Inference Optimization Techniques

Scaling Up the Transformers: A Survey of Training and Infere...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Jahangir, Hadya Goel, Shobhit Kumar Khurana, Shiraz Sharda School of Engineering and Technology Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350378092

Transformer models have shown great success in Natural Language Processing (NLP) tasks, but they come with unique challenges such as the vanishing gradient, unbalanced gradient, and computational costs. To overcome these challenges, various optimization techniques have been developed including regularization, parallelism, and hybrid architectures. In this survey paper, we review the recent advances in optimizing transformers for NLP tasks and highlight their applications on weakly labelled data and low-resource settings. We discuss how to improve the performance of Transformers on Convolutional Neural Network (CNN)-Transformer models, which leverage both CNN and Transformer architectures. Furthermore, we explore techniques specifically designed for weak supervision and low-resource scenarios such as Segment-wise training, Cluster-based attention mechanism, and Transfer learning from a teacher model to a student model. We also highlight some recent works on Sound Event Detection using CNN-Transformer, which leverages the strength of CNNs for feature extraction and Transformers for long range dependencies. Overall, this paper provides an overview of the challenges faced during optimization of transformers in NLP tasks and offers insights into the state-of-the-art techniques to overcome these challenges. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Traffic sign recognition model based on scale sequence features and high-order spatial interactions

引用

Neural Computing and Applications 2025年第5期37卷 3605-3620页

作者： Zhang, Gan Wang, Yafei Li, Wenju Fu, Xianping School of Information Science and Technology Dalian Maritime University Dalian116026 China School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai201418 China Pengcheng Laboratory Shenzhen518055 China

Traffic sign recognition is an integral part of driver assistance systems play a crucial role in enhancing road safety. Due to a large number of challenging targets, such as occlusion, distortion, and small targets in actual scenes, existing methods still have bottlenecks in the accuracy of detection and recognition. Therefore, this paper proposes a real-time traffic sign recognition model based on scale sequence features (SSFs) and high-order spatial interactions (HOSIs) on the basis of YOLOv5. This model extracted scale-invariant SSF using a high-dimensional convolution on the underlying feature map to improve the detection effect of multi-scale targets. At the same time, recursive gated convolution modules are integrated into the feature pyramid network, expanding the interactions to arbitrary order and providing richer feature information for high-order convolutions. In addition, a cross-stage partial (CSP) structure is incorporated into the spatial pooling pyramid, which improves the structure’s performance without introducing excessive computational complexity. The experimental results show that the proposed model achieves 95.5% and 99.92% of mAP on Tsinghua–Tencent 100K (TT100K) and German Traffic Sign Recognition Benchmark (GTSRB), respectively, which surpass the performance of the most advanced model and meets the requirements of real-time detection. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5475-5488页

作者： Wang, Youze Hu, Wenbo Dong, Yinpeng Liu, Jing Zhang, Hanwang Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230009 China Tsinghua University Beijing100084 China Chinese academy of science Institute of automation Beijing100190 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human intelligence, which processes a variety of data forms beyond just text. Despite advancements, the undesirable generation of these models remains a critical concern, particularly due to vulnerabilities exposed by text-based jailbreak attacks, which have represented a significant threat by challenging existing safety protocols. Motivated by the unique security risks posed by the integration of new and old modalities for MLLMs, we propose a unified multimodal universal jailbreak attack framework that leverages iterative image-text interactions and transfer-based strategy to generate a universal adversarial suffix and image. Our work not only highlights the interaction of image-text modalities can be used as a critical vulnerability but also validates that multimodal universal jailbreak attacks can bring higher-quality undesirable generations across different MLLMs. We evaluate the undesirable context generation of MLLMs like LLaVA, Yi-VL, MiniGPT4, MiniGPT-v2, and InstructBLIP, and reveal significant multimodal safety alignment issues, highlighting the inadequacy of current safety mechanisms against sophisticated multimodal attacks. This study underscores the urgent need for robust safety measures in MLLMs, advocating for a comprehensive review and enhancement of security protocols to mitigate potential risks associated with multimodal capabilities. © 1991-2012 IEEE.

关键词： Human form models

来源：评论

学校读者我要写书评

暂无评论

AI-driven Solutions for Autonomous Maintenance and Fault Detection in Electrical Power Grids 4

AI-driven Solutions for Autonomous Maintenance and Fault Det...

引用

4th IEEE Asian Conference on Innovation in technology, ASIANCON 2024

作者： Kanimozhi, S. Enakshi Chhabra, Rohan Rai, Shashank Shekhar School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus School of Electronics Engineering Vellore Institute of Technology Chennai Campus

ISBN: (纸本)9798350354218

Efficient and reliable power grids are crucial for the functioning of modern society. However, increasing energy demand and renewable sources can lead to power failures. Traditional methods struggle. AI, particularly Random Forest Classifiers, offers a promising approach. These classifiers analyse vast amounts of grid data to identify patterns indicative of faults. This allows for real-time anomaly detection. This research investigates the efficacy of Random Forest models for fault classification, focusing on optimising data preprocessing and collection. Transparency in data collection and model development is crucial for data privacy. While simulated environments pose challenges for early fault detection, real-world data presents even greater complexities. The effectiveness of Random Forest Classifiers in early fault detection is critical for grid reliability, reducing power outages, and enhancing long-term operational efficiency. © 2024 IEEE.

关键词： Artificial Intelligence (AI) Autonomous Maintenance Data Security Fault Detection Power Grid Predictive Maintenance Random Forest

来源：评论

学校读者我要写书评

暂无评论

A Novel and Optimized Collaborative Diversity-Driven Routing Mechanism in MANETs

引用

SN computer Science 2024年第1期5卷 22页

作者： Malyadri, Neelam Ramakrishna, M. Department of Computer Science and Engineering Vemana Institute of Technology VTU Belagavi India School of Computer Science and Engineering REVA University Karnataka Bengaluru India Department of Computer Science and Engineering Vemana Institute of Technology Karnataka Bengaluru India

Wireless networks such as MANETs present unique challenges due to their dynamic and decentralized nature. Efficient routing protocols are essential for achieving reliable and robust communication in such networks. In this research, we propose a novel routing mechanism called collaborative diversity-driven routing (CollabNet) that integrates collaborative diversity to enhance the routing process in ad hoc networks. CollabNet utilizes a collaborative approach to address the challenges posed by dynamic network environments. CollabNet incorporates collaborative power control, adaptive power allocation, and energy-efficient routing to automatically adjust the dynamic power of nodes. By promoting collaborative behavior and optimizing power levels. It fosters collaborative behavior among nodes by establishing cooperation groups and leveraging multiple relay nodes. Through collaborative multipath diversity CollabNet facilitates the transmission of packets toward the destination via multiple paths within the transmission range. This approach increases the probability of successful packet delivery by establishing redundant connections. By promoting collaboration among nodes, CollabNet improves the reliability and connectivity of wireless ad hoc networks. The mechanism leverages the strength of collaborative diversity to enhance the overall performance of routing protocols. Extensive simulations demonstrate that CollabNet outperforms traditional routing protocols in terms of network connectivity, reliability, and efficiency. The proposed mechanism offers a promising solution for efficient routing in MANETs contributing to the advancement of wireless communication in dynamic ad hoc network environments. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Collaborative diversity Collaborative diversity-driven routing MANETs Routing protocols Wireless ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

A CNN Approach for Brain Tumor Detection Using Diverse Optimizers 3

A CNN Approach for Brain Tumor Detection Using Diverse Optim...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Revathi, Ar Venkataraman, Rishab Naveen Moola, Maitreya School of Computer Science and Engineering Vellore Institute of Technology Chennai India School of Electronics Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350375190

The ability to recognize brain tumors via medical imaging is crucial for brain tumor treatment. This proposed work focused on a technique for detecting brain tumors by employing Convolutional Neural Networks (CNNs) to achieve precise and prompt diagnosis of brain tumors. This frame utilizes a variety of optimizers such as Stochastic Gradient Descent, RMSprop, Adam (Adaptive Moment Estimation), Adadelta, Adagrad, Adamax, and Nadam. The model's performance is evaluated using accuracy, sensitivity, specificity, precision, and recall as the primary metrics. Leveraging a dataset of 6951 MRI images, results reveal varying performance across optimizers, with a peak accuracy of 98.8% emphasizing the need for careful selection based on specific requirements and dataset characteristics. Advancing brain tumor identification, aiming to enhance early intervention and patient outcomes through the integration of cutting-edge technology, particularly Convolutional Neural Networks (CNNs), which offer high precision in analyzing intricate patterns within medical imaging data. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A Self-Adapting and Efficient Dandelion Algorithm and Its Application to Feature Selection for Credit Card Fraud Detection

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 377-390页

作者： Honghao Zhu MengChu Zhou Yu Xie Aiiad Albeshri IEEE School of Computer and Information Engineering Bengbu UniversityBengbu 233030China School of Information and Electronic Engineering Zhejiang Gongshang UniversityHangzhou 310018China Helen and John C.Hartmann the Department of Electrical and Computer EngineeringNew Jersey Institute of TechnologyNewark NJ 07102 USA College of Information Engineering Shanghai Maritime UniversityShanghai 201306China Department of Computer Science King Abdulaziz UniversityJeddah 21481Saudi Arabia

A dandelion algorithm(DA) is a recently developed intelligent optimization algorithm for function optimization problems. Many of its parameters need to be set by experience in DA,which might not be appropriate for all optimization problems. A self-adapting and efficient dandelion algorithm is proposed in this work to lower the number of DA's parameters and simplify DA's structure. Only the normal sowing operator is retained;while the other operators are discarded. An adaptive seeding radius strategy is designed for the core dandelion. The results show that the proposed algorithm achieves better performance on the standard test functions with less time consumption than its competitive peers. In addition, the proposed algorithm is applied to feature selection for credit card fraud detection(CCFD), and the results indicate that it can obtain higher classification and detection performance than the-state-of-the-art methods.

关键词： Credit card fraud detection(CCFD) dandelion algorithm(DA) feature selection normal sowing operator

来源：评论

学校读者我要写书评

暂无评论

Changes in physiology, antioxidant system, and gene expression in Microcystis aeruginosa under fenoxaprop-p-ethyl stress

引用

Environmental Science and Pollution Research 2024年第19期31卷 28754-28763页

作者： Liu, Sijia Ni, Jiawei Guan, Ying Tao, Jianwei Wu, Liang Hou, Meifang Wu, Shichao Xu, Wenwu Zhang, Chu Ye, Jing School of Chemical and Environmental Engineering Shanghai Institute of Technology Shanghai201418 China Los Angeles Regional Water Quality Control Board Los AngelesCA90013 United States School of Ecological Technology and Engineering Shanghai Institute of Technology Shanghai201418 China School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai201418 China

Fenoxaprop-p-ethyl (FE) is one of the typical aryloxyphenoxypropionate herbicides. FE has been widely applied in agriculture in recent years. Human health and aquatic ecosystems are threatened by the cyanobacteria blooms caused by Microcystis aeruginosa, which is one of the most common cyanobacteria responsible for freshwater blooming. Few studies have been reported on the physiological effects of FE on M. aeruginosa. This study analyzed the growth curves, the contents of chlorophyll a and protein, the oxidative stress, and the microcystin-LR (MC-LR) levels of M. aeruginosa exposed to various FE concentrations (i.e., 0, 0.5, 1, 2, and 5 mg/L). FE was observed to stimulate the cell density, chlorophyll a content, and protein content of M. aeruginosa at 0.5- and 1-mg/L FE concentrations but inhibit them at 2 and 5 mg/L FE concentrations. The superoxide dismutase and catalase activities were enhanced and the malondialdehyde concentration was increased by FE. The intracellular (intra-) and extracellular (extra-) MC-LR contents were also affected by FE. The expression levels of photosynthesis-related genes psbD1, psaB, and rbcL varied in response to FE exposure. Moreover, the expressions of microcystin synthase-related genes mcyA and mcyD and microcystin transportation-related gene mcyH were significantly inhibited by the treatment with 2 and 5 mg/L FE concentrations. These results might be helpful in evaluating the ecotoxicity of FE and guiding the rational application of herbicides in modern agriculture. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：