检索结果-内蒙古大学图书馆

Cross-Dimension Attentive Feature Fusion Network for Unsupervised Time-Series Anomaly Detection

computer Modeling in Engineering & Sciences 2024年第6期139卷 3011-3027页

作者： Rui Wang Yao Zhou Guangchun Luo Peng Chen Dezhong Peng School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China School of Computer and Software Engineering Xihua UniversityChengdu610039China School of Computer Science Sichuan UniversityChengdu610065China National Innovation Center for UHD Video Technology Chengdu610095China

Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series *** to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly ***,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time *** this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as ***,a series and feature mixing block is introduced to learn representations in 1D ***,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature ***,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly *** results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.

关键词： Time series anomaly detection unsupervised feature learning feature fusion

来源：评论

学校读者我要写书评

暂无评论

Design and Implement for Intelligent Water Quality Detecting and Alarm System 5

Design and Implement for Intelligent Water Quality Detecting...

引用

5th International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2024

作者： Kang, Xiaona Tang, Fu Chengdu Neusoft University Dept. School of Computer and Software Chengdu China Chengdu Neusoft University Dept. Chengdu School of Computer and Software Chengdu China

ISBN: (纸本)9798350366174

nowadays, people begin to pay more and more attention to the environmental protection of the ocean and lake water. We can find there are many products on the market that are about testing the quality of drinking water, but there are no products about testing the water quality of lakes, reservoirs and so on. So we want to design and develop a system that can detect water quality in real time and make alarms. In 2022, we officially approved the project to start research and develop intelligent water quality detecting system. The system mainly includes the following functions: First, it can detect water quality data in real time, such as temperature, pH, TDS and other parameters by using various sensors;second, it can send the data to the PC or mobile phone in real time and show it in the screen;third, it supports scenario customization. The system can judge whether the water quality data is normal according to the scenario set, and decide whether to issue an alarm;Fourth, In order to ensure normal data transmission outdoors, the system supports WIFI, Lora and 4G communication;Fifth, it supports two power supply modes: solar energy and lithium battery;sixth, it supports remote control mode, which means when it works in the large body of water, we can use the remote control to direct the device to the area where we want to detect;Last, it supports check the historical data through a discountable graph or a graph. Sony SPRESENSE development board is used for the main board;Using Turbidity sensor, temperature sensor, TDS sensor and PH sensor for detecting water quality data. After one and a half years' development, we finished all the development and release it. © 2024 IEEE.

关键词： Lithium batteries

来源：评论

学校读者我要写书评

暂无评论

APT Attack Organization Identification Profiling Based on Big Language Models 7

APT Attack Organization Identification Profiling Based on Bi...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Tang, Binhui Lu, Yishan Peng, Haokang Chen, Zhiran Ming, Yang Chengdu Jincheng College School of Computer and Software Chengdu China

ISBN: (纸本)9798350350890

In this paper, we introduce a novel method for detecting APT (Advanced Persistent Threat) malware and generating organizational profiles by integrating deep learning with a large-scale language model. We address the challenges of gradient explosion and vanishing in traditional grayscale image feature extraction by employing an RGB image-based feature representation, which captures richer texture information and enables deeper mining of APT malware characteristics. Our enhanced convolutional neural network model incorporates the Self-Attention mechanism and Spatial Pyramid Pooling (SPP-net) to effectively handle varying image input sizes, significantly improving model adaptability and accuracy. Experimental results demonstrate that our method not only enhances the detection accuracy of APT malware and its variants but also enables precise tracing of the organization behind the APT attack and identification of specific attack methodologies. The outputs from the deep learning model are further processed by a large-scale language model, which provides detailed analysis and generates comprehensive organizational profiles. Visual analysis of APT threat features underscores the effectiveness of our approach in both malware variant detection and traceability. This method empowers security experts with enhanced detection capabilities and detailed organizational insights, facilitating a more informed and timely response to APT attacks. The findings highlight the importance of integrating deep learning and large-scale language models in advancing cybersecurity, particularly in the context of timely APT detection and defense. © 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

A Novel Graph Structure Learning Based Semi-Supervised Framework for Anomaly Identification in Fluctuating IoT Environment

引用

computer Modeling in Engineering & Sciences 2024年第9期140卷 3001-3016页

作者： Weijian Song Xi Li Peng Chen Juan Chen Jianhua Ren Yunni Xia School of Computer and Software Engineering Xihua UniversityChengdu610039China West China Second University Hospital Sichuan UniversityChengdu610065China School of Computer Science Chongqing UniversityChongqing400044China

With the rapid development of Internet of Things(IoT)technology,IoT systems have been widely applied in health-care,transportation,home,and other ***,with the continuous expansion of the scale and increasing complexity of IoT systems,the stability and security issues of IoT systems have become increasingly ***,it is crucial to detect anomalies in the collected IoT time series from various ***,deep learning models have been leveraged for IoT anomaly ***,owing to the challenges associated with data labeling,most IoT anomaly detection methods resort to unsupervised learning ***,the absence of accurate abnormal information in unsupervised learning methods limits their *** address these problems,we propose AS-GCN-MTM,an adaptive structural Graph Convolutional Networks(GCN)-based framework using a mean-teacher mechanism(AS-GCN-MTM)for anomaly *** performs better than unsupervised methods using only a small amount of labeled *** Teachers is an effective semi-supervised learning method that utilizes unlabeled data for training to improve the generalization ability and performance of the ***,the dependencies between data are often unknown in time series *** solve this problem,we designed a graph structure adaptive learning layer based on neural networks,which can automatically learn the graph structure from time series *** not only better captures the relationships between nodes but also enhances the model’s performance by augmenting key *** have demonstrated that our method improves the baseline model with the highest F1 value by 10.4%,36.1%,and 5.6%,respectively,on three real datasets with a 10%data labeling rate.

关键词： IoT multivariate time series anomaly detection graph learning semi-supervised mean teachers

来源：评论

学校读者我要写书评

暂无评论

Multi-scale persistent spatiotemporal transformer for long-term urban traffic flow prediction

引用

Journal of Electronic Science and Technology 2024年第1期22卷 53-69页

作者： Jia-Jun Zhong Yong Ma Xin-Zheng Niu Philippe Fournier-Viger Bing Wang Zu-kuan Wei School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China College of Computer Science&Software Engineering Shenzhen UniversityShenzhen518060China School of Computer Science Southwest Petroleum UniversityChengdu610500China

Long-term urban traffic flow prediction is an important task in the field of intelligent transportation,as it can help optimize traffic management and improve travel *** improve prediction accuracy,a crucial issue is how to model spatiotemporal dependency in urban traffic *** recent years,many studies have adopted spatiotemporal neural networks to extract key information from traffic ***,most models ignore the semantic spatial similarity between long-distance areas when mining spatial *** also ignore the impact of predicted time steps on the next unpredicted time step for making long-term ***,these models lack a comprehensive data embedding process to represent complex spatiotemporal *** paper proposes a multi-scale persistent spatiotemporal transformer(MSPSTT)model to perform accurate long-term traffic flow prediction in *** adopts an encoder-decoder structure and incorporates temporal,periodic,and spatial features to fully embed urban traffic data to address these *** model consists of a spatiotemporal encoder and a spatiotemporal decoder,which rely on temporal,geospatial,and semantic space multi-head attention modules to dynamically extract temporal,geospatial,and semantic *** spatiotemporal decoder combines the context information provided by the encoder,integrates the predicted time step information,and is iteratively updated to learn the correlation between different time steps in the broader time range to improve the model’s accuracy for long-term *** on four public transportation datasets demonstrate that MSPSTT outperforms the existing models by up to 9.5%on three common metrics.

关键词： Graph neural network Multi-head attention mechanism Spatio-temporal dependency Traffic flow prediction

来源：评论

学校读者我要写书评

暂无评论

Robust copy-move detection and localization of digital audio based CFCC feature

引用

Multimedia Tools and Applications 2025年第11期84卷 9573-9589页

作者： Wang, Dongyu Li, Xiaojie Shi, Canghong Niu, Xianhua Xiong, Ling Wu, Hanzhou Qian, Qing Qi, Chao School of Computer and Software Engineering Xihua University Chengdu610039 China The College of Computer Science Chengdu University of Information Technology Chengdu610225 China School of Information Shanghai University Shanghai200444 China School of Information Guizhou University of Finance and Economics Guiyang550000 China

Copy-move forgery is a common audio tampering technique in which users copy the contents of one speech and paste them into another region of the same speech signal, thus achieving the effect of tampering with the semantics. To verify the authenticity of the audio, this paper proposes a method to detect and localize audio copy-move forgery based on the cochlear filter of cochlear filter cepstral coefficients (CFCC) feature. The pitch tracking algorithm is used to distinguish the voiced and unvoiced segments in the audio, and then the CFCC coefficients are extracted for each voiced segment. The CFCC feature simulates the entire transmission process of signals in the cochlear basilar membrane using wavelet transformation. Finally, we use Pearson correlation coefficients (PCCs) and dynamic time warping (DTW) in combination to compare the similarity of voiced segments, accurately determining the tampered locations in the audio through threshold judgment. Through extensive experiments on relevant datasets, this algorithm achieves a precision rate of 98.39% and a recall rate of 98.00% in detecting audio without post-processing. Even when detecting audio that has undergone different post-processing, the precision and recall rates remain above 90%. Compared to existing methods, this approach not only achieves precise localization of replicated segments but also demonstrates superior experimental results. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Dependent Task Offloading for QoS Optimization in Satellite Edge Computing 25th

Deep Reinforcement Learning-Based Dependent Task Offloading ...

引用

25th International Conference on Web Information Systems Engineering, WISE 2024

作者： Tian, Di Chen, Juan Chen, Peng Zhong, Jie Li, Xi Xiong, Ling School of Computer and Software Engineering Xihua University Chengdu610039 China

ISBN: (纸本)9789819605699

Satellite edge computing (SatEC) is an emerging computing paradigm for remote and disaster-affected areas with scarce computing resources. It is crucial to make the appropriate offloading strategy to maximize quality of service (QoS) due to the scarcity of satellite computing resources. However, existing researches mostly focus on the offloading of independent tasks without considering tasks with dependencies. To address this problem, we first design a satellite-aerial task offloading (SATO) framework. In the SATO, unmanned aerial vehicles (UAVs) collect ground tasks and upload them to high-altitude platform (HAP), while HAP provides local computing, and low earth orbit (LEO) satellites provide edge computing. Furthermore, we propose SatEC directed acyclic graph (DAG) task offloading (SECDTO) algorithm to investigate the task offloading problem. Specifically, we model tasks with dependencies as a DAG, then we propose an encoder-decoder model with attention based on deep reinforcement learning (DRL) to translate graph vector information into offloading strategies. In order to maximize QoS, we use proximal policy optimization (PPO) to train the model. Simulation results show that our method converges quickly and stably during the training process and outperforms several baseline algorithms in terms of QoS@. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Negative Sample Enhancement Strategy to Improve Contrastive Learning for Unsupervised Sentence Representation

A Negative Sample Enhancement Strategy to Improve Contrastiv...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Li, Hao Xie, Chunzhi Cao, Zhoulin Lee, Yan-Li Liu, Jia Gao, Zhisheng Xihua University School of Computer and Software Engineering Chengdu China

ISBN: (纸本)9798350362480

Contrastive learning has achieved remarkable success in sentence representation research within the field of natural language processing. Nevertheless, most existing studies focus primarily on the construction of negative samples while paying insufficient attention to the mechanisms for handling these samples. Such methods tend to treat all negative samples within a batch as equally important, neglecting the crucial role that negative samples play in semantic learning. This oversight can result in suboptimal model performance in semantic understanding. To address these issues, this study proposes a negative sample enhancement strategy that applies fine-grained processing to different types of constructed negative samples based on their importance. In the high-dimensional semantic space, hard negative samples and false negative samples are treated respectively - by increasing the distance between hard negative samples and positive samples, while treating false negative samples as pseudo-positive samples to enhance the attraction between them and the anchor sample. This strategy enables the model to perform more effective semantic differentiation and representation. Experimental results on the Semantic Textual Similarity (STS) task demonstrate that the proposed method outperforms existing baseline methods in unsupervised sentence representation learning. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Survey Of Automatic Fact Verification Research 7

A Survey Of Automatic Fact Verification Research

引用

7th World Conference on Computing and Communication Technologies, WCCCT 2024

作者： Yang, Song Yuan, Xue Gan, Tong Wu, Yue Xihua University School of Computer and Software Engineering Chengdu China

ISBN: (纸本)9798350372328

With the evolution of social media technology, the mode of information exchange has transitioned from a singular text format to a multifaceted blend of text, images, audio, and video. This transformation has given rise to the proliferation of multimodal false information, sparking widespread concern across diverse sectors of society. This paper takes a fact-checking perspective, offering a comprehensive review of pertinent research in the field. It commences by introducing prevalent datasets used in contemporary fact-checking. Subsequently, a detailed analysis of fact-checking methods and multimodal detection techniques, centered around the FEVER dataset, is presented, accompanied by comparative insights into various approaches. Finally, the paper delves into the anticipated challenges faced by fact-checking methods in the future. © 2024 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

A Sentiment Classification Method Focused on Emotional Regions and Image-text Interaction Fusion 4

A Sentiment Classification Method Focused on Emotional Regio...

引用

4th International Conference on Electronic Information Engineering and computer Technology, EIECT 2024

作者： Yuan, Xianzhi Liu, Kejian School of Computer and Software Engineering Xihua University Chengdu China

ISBN: (纸本)9798331528850

Image-text information has become mainstream on current social platforms, with image-text sentiment analysis leveraging the complementarity between different modalities to improve sentiment classification performance. In current tasks for image-text sentiment analysis, images often contain significant emotion-irrelevant noise, so focusing on emotional regions within images can greatly impact sentiment classification. Facial expressions, in particular, play a critical role in determining sentiment polarity. This paper proposes an image-text sentiment analysis model that emphasizes facial regions and image-text interactive fusion. In this model, BERT and ResNet are used to extract text and image features, while a convolutional model fine-tuned for facial emotion recognition captures facial expression features. By incorporating a global attention mechanism and a multi-modal fusion module, the model selectively filters and integrates emotional signals from cross-modal information, enabling effective classification of image-text sentiment tendencies. Experimental results on the MVSA datasets show an average improvement in accuracy and F1-score by 1.18% and 1.59%, respectively, compared to the best-performing baseline model. © 2024 IEEE.

关键词： Image classification

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：