检索结果-内蒙古大学图书馆

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Dharshiniya, S. Daniel Madan Raja, S. School of Computer Science and Technology Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore641114 India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518097

The growing complexity and scale of Internet of Things (IoT) networks have made them a prime target for cyber-attacks, necessitating the creation of Intrusion Detection Systems (IDS) to secure confidential data. A key challenge in existing IDS models is that a high loss value can indicate inadequate detection capabilities, potentially leading to missed attacks especially in time-sensitive environments. This study proposes a robust IDS framework by integrating an Autoencoder for feature extraction with Temporal Fusion Transformer (TFT) for attack detection of network intrusion in IoT environments. UNSW-NB15 dataset, was used to assess the model's efficiency. Data preprocessing techniques, including data cleaning and the applying the SMOTE, were employed to ensure balanced dataset representation. The Autoencoder's encoding layer reduces dimensionality to capture essential features and extracted that feature and that as an input to models like the TFT. The Temporal Fusion Transformer (TFT) leverages LSTM encoding, temporal attention, and Gated Residual Networks to capture complex time-series dependencies with the extracted features which help to detect attacks like Fuzzers, Dos, Backdoor, Exploits, Generic, Reconnaissance, Shellcode, Worms. After detecting the attacks, the voice alert is automatically sent to the admin which helps to maintain the robustness. The accuracy achieved by the proposed IDS is 99.06%, with a recall of 98.66%, precision of 91.59%, F1-score of 94.27% and a loss of 0.030 when compared to other traditional algorithms. These results demonstrate the model's effectiveness in identifying various types of cyber-attacks while maintaining a low loss when compared to others. The integration of the voice alert system further enhances the security of the IDS by providing immediate notifications of detected intrusion, thereby facilitating timely responses. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Progressive Growth for Point Cloud Completion by Surface-Projection Optimization

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第5期9卷 1-15页

作者： Fei, Ben Zhang, Rui Yang, Weidong Li, Zhijun Chen, Wen-Ming School of Computer Science Fudan University Shanghai China School of Mechanical Engineering Tongji University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China

Point cloud completion concentrates on completing geometric and topological shapes from incomplete 3D shapes. Nevertheless, the unordered nature of point clouds will hamper the generation of high-quality point clouds without predicting structured and topological information of the complete shapes and introducing noisy points. To effectively address the challenges posed by missing topology and noisy points, we introduce SPOFormer, a novel topology-aware model that utilizes surface-projection optimization in a progressive growth manner. SPOFormer consists of three distinct steps for completing the missing topology: (1) Missing Keypoints Prediction. A topology-aware transformer auto-encoder is integrated for missing keypoint prediction. (2) Skeleton Generation. The skeleton generation module produces a new type of representation named skeletons with the aid of keypoints predicted by topology-aware transformer auto-encoder and the partial input. (3) Progressively Growth. We design a progressive growth module to predict final output under Multi-scale Supervision and Surface-projection Optimization. Surface-projection Optimization is firstly devised for point cloud completion, aiming to enforce the generated points to align with the underlying object surface. Experimentally, SPOFormer model achieves an impressive Chamfer Distance-$\ell _{1}$ (CD) score of 8.11 on PCN dataset. Furthermore, it attains average CD-$\ell _{2}$ scores of 1.13, 1.14, and 1.70 on ShapeNet-55, ShapeNet-34, and ShapeNet-Unseen21 datasets, respectively. Additionally, the model achieves a Maximum Mean Discrepancy (MMD) of 0.523 on the real-world KITTI dataset. These outstanding qualitative and quantitative performances surpass previous approaches by a significant margin, firmly establishing new state-of-the-art performance across various benchmark datasets. Our code is available at https://***/kiddoray/SPOFormer IEEE

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A High-Performance 220-290 GHz Micromachined Waveguide Switch Based on Interference Between MEMS Reconfigurable Surfaces

引用

IEEE Transactions on Terahertz science and technology 2024年第2期14卷 188-198页

作者： Karimi, Armin Shah, Umer Yu, Suxian Oberhammer, Joachim Kth Royal Institute of Technology Micro and Nanosystems Technology Division School of Electrical Engineering and Computer Science StockholmSE-100 44 Sweden

This article presents a highly integrated novel silicon micromachined single-pole-single-throw waveguide switch based on two microelectromechanically reconfigurable switching surfaces (MEMS-RSs), which allows optimizing the switching performance by tuning the interference between the two such MEMS-RSs utilizing integrated electrostatic comb-drive actuators. The switch prototype is implemented with axially aligned standard WR-3.4 waveguide ports with a total footprint of 3 mm×3.5 mm×1.2 mm. The measured blocking (off) state insertion loss (isolation) and return loss, measured between two standard WR-3.4 waveguide flanges, are 28.5-32.5 dB and better than 0.7 dB, and the propagating (on) state insertion and return losses are 0.7-1.2 dB and better than 17 dB in the 220-290 GHz frequency band, respectively. The measured results were in excellent agreement with the simulation data, implying 27.5% fractional bandwidth, which is very close to a full waveguide band performance. For further investigations, two variants of the switching circuit with only a single MEMS-RS and without any MEMS-RSs have also been fabricated. The single MEMS-RS switch achieved the off-state isolation, on-state insertion loss, and return loss of only 11.5-12.5 dB, 0.8-1.3 dB, and better than 12 dB from 220 to 274 GHz, respectively, which clearly indicates the drastic performance improvement of the interference-based double MEMS-RS switch design. Moreover, measurement of the waveguide-only reference structure showed that the waveguide section alone attributed to 0.2-0.5 dB of the measured on-state insertion loss of the double MEMS-RS switch, and the rest is due to the introduction of the MEMS-RSs inside the waveguides. © 2011-2012 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Forecasting Cloud Workload through Reinforcement Learning-Based Ensemble Model 4

Forecasting Cloud Workload through Reinforcement Learning-Ba...

引用

4th International Conference on Electronic Information engineering and computer Communication, EIECC 2024

作者： Kang, Yuliang Li, Yongke Zhang, Gongxuan Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798331534622

The escalating demand for cloud computing has intensified the need for accurate workload forecasting to optimize resource allocation and maintain service quality. This paper presents a novel approach employing a reinforcement learning-based ensemble model to enhance the accuracy of workload predictions in cloud environments. The study addresses the challenges posed by complex and dynamic workload patterns, leveraging deep learning techniques to improve prediction outcomes. The proposed model dynamically selects the optimal subset of predictors, demonstrating superior performance on the Google Cluster dataset. The research aims to contribute to more efficient and intelligent resource management in cloud computing. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

MTPNet: Learning Multiple Twin-support Prototypes for Few-shot Medical Image Segmentation

MTPNet: Learning Multiple Twin-support Prototypes for Few-sh...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Song, Feifan Cheng, Ziming Li, Lunbo Zhang, Haofeng Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350386226

Given the high annotation costs and ethical considerations associated with medical images, leveraging a limited number of annotated samples for Few-Shot Medical Image Segmentation (FSMIS) has become increasingly prevalent. However, existing models tend to focus on visible foreground support information, often overlooking extreme foreground-background imbalances. In addition, query images sometimes have slight different appearance compared to support images of the same category due to the differences in size as well as slicing angle, thus employing only support images to generate prototypes inevitably leads to matching bias. To address these challenges, we present an innovative approach through learning a Multiple Twin-support Prototypes Network (MTPNet). Our approach includes the design of the Scale Consistent Sampling (SCS) module, which adaptively adjusts the foreground and background points within the support set, thereby balancing the influence of various structural elements in the image. Additionally, the Twin-support Prototypes Extraction (TPE) module facilitates the critical interaction between query and support features to extract twin-support prototypes. This module incorporates a Backtrace Interaction Filter (BIF) to eliminate erroneous interaction prototypes. Extensive experimental validation on three widely used medical image datasets demonstrates that our method surpasses current State-of-the-arts, showcasing its potential to address key limitations in FSMIS. The code is available at https://***/FeifanSong/MTPNet. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Embedded System I/O Isolation technology for Raspberry Pi 4

An Embedded System I/O Isolation Technology for Raspberry Pi

引用

4th International Conference on Intelligent technology and Embedded Systems, ICITES 2024

作者： Yaoyong, Wang Gongxuan, Zhang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798331506292

Nowadays user's data in devices is at high risk. To ensure security of program's runtime environment, Trusted Computing and Trusted Execution Environment(TEE) are proposed, which construct trusted base at the hardware level. Hardware vendors implement hardware trusted base for their new products, Intel's Software Guard eXtension(SGX) as an example. SGX lacks isolation for device I/O so there are many SGX-based mechanisms proposed that add protection for device I/O. However, all the above trusted mechanisms must be based on that the CPU has extensions for trusted computing, which means that lots of devices equipped with old chips and those embedded devices on other ISA like Arm and RISC-V have no possibility to support this trusted computing mechanism. Therefore, we proposes an I/O isolation technology for embedded devices and implements a trusted computing mechanism named XiRang(eXtended I/O Reliable Authentication Guard) for Raspberry Pi. Specifically, we do the following work. (1) Use an external trusted device as the physical trusted root for embedded devices, which made up for the lack of trusted computing extension of their chips. (2) On the premise of trusted hardware, XiRang realizes the trusted isolation of USB disk, uses trusted Linux container as the application runtime environment, and completes the trusted chain transfer from the external trusted device to the application. (3) Finally, we evaluate performance of XiRang. © 2024 IEEE.

关键词： Embedded System I/O Isolation Raspberry Pi Trusted Computing Trusted Execution Environment

来源：评论

学校读者我要写书评

暂无评论

Observe before Generate: Emotion-Cause aware Video Caption for Multimodal Emotion Cause Generation in Conversations 24

Observe before Generate: Emotion-Cause aware Video Caption f...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Fanfan Ma, Heqing Shen, Xiangqing Yu, Jianfei Xia, Rui School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798400706868

Emotion cause analysis has attracted increasing attention in recent years. However, the integration of multimodal information with emotion causes remains underexplored. Existing studies merely extract utterances from conversations as cause evidence, which is too coarse-grained to locate the exact causes from other modalities, especially those that may be reflected only in a specific video frame of an utterance. To address these limitations, we introduce a new task named Multimodal Emotion Cause Generation in Conversations (MECGC), which aims to generate an abstractive summary clearly and intuitively describing the causes that trigger the given emotion based on the multimodal context of conversations. We accordingly construct a dataset named ECGF that contains 1,374 conversations and 7,690 emotion instances from TV series. We further develop a generative framework that first generates emotion-cause aware video captions (Observe) and then facilitates the generation of emotion causes (Generate). The captioning model is trained with examples synthesized by a Multimodal Large Language Model (MLLM). Experimental results demonstrate the effectiveness of our framework and the significance of multimodal information for emotion cause analysis. Our dataset and source codes are available at https://***/NUSTM/MECGC. © 2024 ACM.

关键词： emotion cause analysis in conversations

来源：评论

学校读者我要写书评

暂无评论

HACS: An Enhancement Framework for Deep Code Search Benefiting from Hard Negative Samples 36

HACS: An Enhancement Framework for Deep Code Search Benefiti...

引用

36th International Conference on Software engineering and Knowledge engineering, SEKE 2024

作者： Song, Qihong Liu, Jianxun Hu, Haize School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)1891706594

Code search aims to retrieve relevant code snippets from large code repositories based on query, promoting code reuse and enhancing software development efficiency. Deep Learning is a powerful approach for code search, in which the hard negative samples within training batches critically impact model performance. However, most existing deep code search models only randomly sample negative samples, resulting in a paucity or complete lack of hard negative samples. To address this limitation, we introduce a novel enhancement framework named HACS to optimize the composition of negative samples within batches, thus enhancing the training effectiveness of deep code search models. The core idea is to increase the count of hard negative samples within the negative samples corresponding to each query in the training batch. Specifically, HACS utilizes deep reinforcement learning techniques for sampling hard negative samples and implements vector-level mixed data augmentation strategy to generate hard negative samples. We evaluated our framework on a public dataset covering six programming languages. Experimental results reveal that HACS significantly improves the code search performance of existing models. © 2024 Knowledge Systems Institute Graduate school. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in IoV Can Bus Traffic Using Variational Autoencoder-LSTM with Attention Mechanism 5

Anomaly Detection in IoV Can Bus Traffic Using Variational A...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Pradeep, C. Malar Dhas, Julia Punitha Isravel, Deva Priya School of Computer Science and Technology Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore641114 India

ISBN: (纸本)9798331518097

The rapid growth of the Internet of Vehicles (IoV) greatly enhances the communication and data exchange capability between vehicles, which allows the real-time transmission of critical information. The CAN bus is the backbone developed to transmit data between Electronic Control Units in the in-vehicle networks and it is prone to various cyberattacks that can breach its security and integrity. To identify cyberattacks on a CAN bus this paper proposes a deep learning model employing a Variational Autoencoder in conjunction with Long Short-Term Memory (LSTM) that features an integrated attention mechanism. The proposed model leverages the temporal characteristics of CAN bus traffic to detect anomalies by identifying the differences in the reconstruction loss. The CICIoV2024 dataset, containing benign and malicious messages for the CAN bus, was used for the proposed model, which achieved high effectiveness with the accuracy of 99.78%, precision of 99.81%, a recall of 99.32%, and F1 score of 99.56%. The results show that the model is strong in accurately detecting unusual behaviour and offers a flexible solution for improving cybersecurity in IoV systems. © 2024 IEEE.

关键词： Buses

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection Based on the Transformer and High-Resolution Network

引用

computers, Materials & Continua 2023年第2期74卷 3439-3454页

作者： Dengyong Zhang Huaijian Pu Feng Li Xiangling Ding Victor S.Sheng Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411004China Department of Computer Science Texas Tech UniversityLubbock79409TXUSA

Now object detection based on deep learning tries different *** uses fewer data training networks to achieve the effect of large dataset ***,the existing methods usually do not achieve the balance between network parameters and training *** makes the information provided by a small amount of picture data insufficient to optimize model parameters,resulting in unsatisfactory detection *** improve the accuracy of few shot object detection,this paper proposes a network based on the transformer and high-resolution feature extraction(THR).High-resolution feature extractionmaintains the resolution representation of the *** and spatial attention are used to make the network focus on features that are more useful to the *** addition,the recently popular transformer is used to fuse the features of the existing *** compensates for the previous network failure by making full use of existing object *** on the Pascal VOC and MS-COCO datasets prove that the THR network has achieved better results than previous mainstream few shot object detection.

关键词： Object detection few shot object detection transformer high-resolution

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：