检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Hou, Haowen Zeng, Peigen Ma, Fei Yu, Fei Richard Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shool of Information Technology Carleton University Canada

ISBN: (纸本)9798891761964

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: https://***/howard-hou/VisualRWKV. © 2025 Association for Computational Linguistics.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Image Hiding with High Robustness Based on Dynamic Region Attention in the Wavelet Domain

引用

computer Modeling in engineering & Sciences 2024年第10期141卷 847-869页

作者： Zengxiang Li Yongchong Wu Alanoud Al Mazroa Donghua Jiang Jianhua Wu Xishun Zhu Department of Information Engineering Gongqing CollegeNanchang UniversityJiujiang332020China School of Information Engineering Gongqing Institute of Science and TechnologyJiujiang332020China Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou511400China School of Information Engineering Nanchang UniversityNanchang330031China School of Mathematics and Statistics Hainan Normal UniversityHaikou571158China

Hidden capacity,concealment,security,and robustness are essential indicators of hiding ***,hiding algorithms tend to focus on algorithmic capacity,concealment,and security but often overlook the robustness of the *** practical applications,the container can suffer from damage caused by noise,cropping,and other attacks during transmission,resulting in challenging or even impossible complete recovery of the secret *** image hiding algorithm based on dynamic region attention in the multi-scale wavelet domain is proposed to address this issue and enhance the robustness of hiding *** this proposed algorithm,a secret image of size 256×256 is first decomposed using an eight-level Haar wavelet *** wavelet transform generates one coefficient in the approximation component and twenty-four detail bands,which are then embedded into the carrier image via a hiding *** the recovery process,the container image is divided into four non-overlapping parts,each employed to reconstruct a low-resolution secret *** lowresolution secret images are combined using densemodules to obtain a high-quality secret *** experimental results showed that even under destructive attacks on the container image,the proposed algorithm is successful in recovering a high-quality secret image,indicating that the algorithm exhibits a high degree of robustness against various *** proposed algorithm effectively addresses the robustness issue by incorporating both spatial and channel attention mechanisms in the multi-scale wavelet domain,making it suitable for practical *** conclusion,the image hiding algorithm introduced in this study offers significant improvements in robustness compared to existing *** ability to recover high-quality secret images even in the presence of destructive attacksmakes it an attractive option for various *** research and experimentation can explore the algorith

关键词： Image hiding robustness wavelet transform dynamic region attention

来源：评论

学校读者我要写书评

暂无评论

Stationary wavelet transform and SpinalNet trained light spectrum Tasmanian devil optimization enabled DR detection using fundus images

引用

Multimedia Tools and Applications 2025年第4期84卷 1597-1626页

作者： Tamboli, Mubin Shoukat Dhumane, Amol Prasad, Rajesh Prasad, Jayashree Rajesh Ranjan, Nihar M. Computer Engineering Pimpri Chinchwad College of Engineering Pradhikaran Maharashtra Pune411044 India Computer Science and Engineering Symbiosis Institute of Technology Maharashtra Pune India Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Maharashtra Pune412201 India Information Technology JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India

Diabetes is a common disease that causes complications in the eyes known as Diabetic Retinopathy (DR). It aids in discovering the DR and tends to be the main cause behind people’s blindness amidst the previous decades. For prevent the complications of DR and to control the level of blood Glucose, the timely and crucial diagnosis is essential. A model is provided for detecting the DR. Here, Light Spectrum Tasmanian Devil Optimization (LSTDO) is utilized with SpinalNet for DR detection. The method undergoes an adaptive median filter and Region of interest mining process to generate a pre-processed image. The Sparse Fuzzy C-Means (FCM) is adapted for segmenting the optic disks followed by feature extraction. Then, the Hough line transformation with Tyler Coye algorithm (HLTCA) is used for blood vessel segmentation. Concurrently, the Stationary Wavelet Transform (SWT) is adapted to input image to overwhelm the deficiency of translation-invariance issue and then the feature mining is done. The feature vector is generated by unifying the outputs of the three-feature extraction phases and is employed to detect DR. The accuracy, sensitivity, and specificity obtained by the LSTDO-based SpinalNet are 91.6%, 89.9% and 92.1%, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Detecting Evolving Fake News in Social Media by Leveraging Heterogeneous Deep Learning Model 2

Detecting Evolving Fake News in Social Media by Leveraging H...

引用

2nd IEEE International Conference on Advances in information Technology, ICAIT 2024

作者： Brinda, B.M. Rajan, C. Geetha, K. Computer Science and Engineering Paavai College of Engineering Namakkal India Information Technology KSR College of Technology Thiruchengode India Computer Science and Engineering Excel Engineering College Komarapalayam India

ISBN: (纸本)9798350383867

A recent study revealed that fake articles spread considerably faster than factual content on Twitter, specifically at a 70% higher rate of retweets and reaching the first 1,500 users six times faster. This highlights the urgent need for scalable automated detection solutions to combat the pervasive threat of fake news online. While machine learning methods often rely solely on semantic text analysis, evolving fake news campaigns mimic genuine news, employing tactics like bot networks and sophisticated language imitation. This renders text-based meth- ods increasingly vulnerable. To address this challenge,we propose a heterogeneous deep learning model that incorporates richer information beyond text, specifically dissemination structure features from social networks. These features capture aspects like user interactions, sharing patterns, and network topology, providing valuable insights into the spread of information. Our model leverages the sentiment and affects the enriched Alt dataset for text analysis. Instead of using a popular language model called BERT, we explore alternative pre-trained language models like the Sentence Transformer, which focuses on capturing con- textual sentence embeddings, or the Universal Language Model (ULMFiT), which excels at understanding semantic relationships within text. Additionally, we consider spaCy, a versatile NLP library offering similar functionalities for text processing and feature extraction. While The Quint Dataset Challenge Dataset lacks sentiment annotations, it could be a potential alternative to Alt depending on research goals. This network-aware approach achieves an impressive 95.27% accuracy on The Boom Live dataset and demonstrates generalizability to The Quint dataset with 92.1% accuracy, highlighting its effectiveness in combatting evolving fake news tactics. © 2024 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Unequal Fault Tolerance Clustering Approach

引用

computer Systems Science & engineering 2023年第5期45卷 1971-1983页

作者： Sowjanya Ramisetty Divya Anand Kavita Sahil Verma NZ Jhanjhi Mehedi Masud Mohammed Baz Department of Computer Science and Engineering KG Reddy College of Engineering and TechnologyHyderabadIndia School of Computer Science and Engineering Lovely Professional UniversityPhagwaraIndia Department of Computer Science and Engineering Chandigarh UniversityMohaliIndia Department of Computer Science and Engineering Tailor’s UniversityMalaysia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Engineering College of Computer and Information TechnologyTaif UniversityTaif21994Saudi Arabia

For achieving Energy-Efficiency in wireless sensor networks(WSNs),different schemes have been proposed which focuses only on reducing the energy consumption.A shortest path determines for the Base Station(BS),but fault tolerance and energy balancing gives equal importance for improving the network *** saving energy in WSNs,clustering is considered as one of the effective methods for Wireless Sensor *** of the excessive overload,more energy consumed by cluster heads(CHs)in a cluster based WSN to receive and aggregate the information from member sensor nodes and it leads to *** increasing the WSNs’lifetime,the CHs selection has played a key role in energy consumption for sensor *** Energy Efficient Unequal Fault Tolerant Clustering Approach(EEUFTC)is proposed for reducing the energy utilization through the intelligent methods like Particle Swarm Optimization(PSO).In this approach,an optimal Master Cluster Head(MCH)-Master data Aggregator(MDA),selection method is proposed which uses the fitness values and they evaluate based on the PSO for two optimal nodes in each cluster to act as Master Data Aggregator(MDA),and Master Cluster *** data from the cluster members collected by the chosen MCH exclusively and the MDA is used for collected data reception from MCH transmits to the ***,the MCH overhead *** the heavy communication of data,overhead controls using the scheduling of Energy-Efficient Time Division Multiple Access(EE-TDMA).To describe the proposed method superiority based on various performance metrics,simulation and results are compared to the existing methods.

关键词： Energy-efficiency unequal fault tolerant clustering approach particle swarm optimization master data aggregator energy efficient time division multiple access optimal nodes

来源：评论

学校读者我要写书评

暂无评论

Fitness Sharing Chaotic Particle Swarm Optimization (FSCPSO): A Metaheuristic Approach for Allocating Dynamic Virtual Machine (VM) in Fog Computing Architecture

引用

computers, Materials & Continua 2024年第8期80卷 2557-2578页

作者： Prasanna Kumar Kannughatta Ranganna Siddesh Gaddadevara Matt Chin-Ling Chen Ananda Babu Jayachandra Yong-Yuan Deng Department of Computer Science&Engineering Ramaiah Institute of TechnologyBangalore560054India Department of Artificial Intelligence&Data Science Ramaiah Institute of TechnologyBangalore560054India School of Information Engineering Changchun Sci-Tech UniversityChangchun130600China Department of Computer Science and Information Engineering Chaoyang University of TechnologyTaichung41349Taiwan Department of Information Science and Engineering Malnad College of EngineeringHassan573202India

In recent decades,fog computing has played a vital role in executing parallel computational tasks,specifically,scientific workflow *** cloud data centers,fog computing takes more time to run workflow ***,it is essential to develop effective models for Virtual Machine(VM)allocation and task scheduling in fog computing *** task scheduling,VM migration,and allocation,altogether optimize the use of computational resources across different fog *** process ensures that the tasks are executed with minimal energy consumption,which reduces the chances of resource *** this manuscript,the proposed framework comprises two phases:(i)effective task scheduling using a fractional selectivity approach and(ii)VM allocation by proposing an algorithm by the name of Fitness Sharing Chaotic Particle Swarm Optimization(FSCPSO).The proposed FSCPSO algorithm integrates the concepts of chaos theory and fitness sharing that effectively balance both global exploration and local *** balance enables the use of a wide range of solutions that leads to minimal total cost and makespan,in comparison to other traditional optimization *** FSCPSO algorithm’s performance is analyzed using six evaluation measures namely,Load Balancing Level(LBL),Average Resource Utilization(ARU),total cost,makespan,energy consumption,and response *** relation to the conventional optimization algorithms,the FSCPSO algorithm achieves a higher LBL of 39.12%,ARU of 58.15%,a minimal total cost of 1175,and a makespan of 85.87 ms,particularly when evaluated for 50 tasks.

关键词： Fog computing fractional selectivity approach particle swarm optimization algorithm task scheduling virtual machine allocation

来源：评论

学校读者我要写书评

暂无评论

Abnormal Crowd Behavior Detection Using Optimized Pyramidal Lucas-Kanade Technique

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 2399-2412页

作者： G.Rajasekaran J.Raja Sekar Department of information technology mepco schlenk engineering collegesivakasi626005india Department of computer science and engineering mepco schlenk engineering collegesivakasi626005india

Abnormal behavior detection is challenging and one of the growing research areas in computer *** main aim of this research work is to focus on panic and escape behavior detections that occur during unexpected/uncertain *** this work,Pyramidal Lucas Kanade algorithm is optimized using EME-HOs to achieve the *** stage,OPLKT-EMEHOs algorithm is used to generate the opticalﬂow from *** stage,the MIIs opticalﬂow is applied as input to 3 layer CNN for detect the abnormal crowd *** of Minnesota(UMN)dataset is used to evaluate the proposed *** experi-mental result shows that the proposed method provides better classiﬁcation accu-racy by comparing with the existing *** method provides 95.78%of precision,90.67%of recall,93.09%of f-measure and accuracy with 91.67%.

关键词： Crowd behavior analysis anomaly detection Motion information

来源：评论

学校读者我要写书评

暂无评论

OTFS on Overspread Doubly Selective Channel

引用

China Communications 2024年第11期21卷 205-215页

作者： Qing Hua Liu Yun Shi Xiayang Yu Hua Ji Fei Cui Yinming College of Software Engineering Zhengzhou University of Light IndustryZhengzhou 450002China School of Internet Finance and Information Engineering Guangdong University of FinanceGuangzhou 510520China School of Electronic and Information Engineering South China University of TechnologyGuangzhou 510641China

The orthogonal time frequency space(OTFS)modulation proposed in recent years is considered to have superior performance than orthogonal frequency division multiplexing(OFDM)for the doubly selective(DS)*** works in the existing literature on OTFS mainly focus on the cases where the channels are underspread(i.e.,the product of the delay spread and the Doppler spread is less than 1).In the scenario of overspread DS channel,which has large delay spread and severe Doppler spread,such as underwater acoustic(UWA)channel,the channel model in delay-Doppler(DD)Domain derived by existing work is no longer *** this paper,we derive a more generalized expression of the channel model in delay-Doppler domain,which allows the product of the delay spread and Doppler spread to be larger *** result shows that the existing channel model is just a special case of the one we *** the proposed channel matrix in DD domain,we build the OTFS detectors with the minimum mean square error(MMSE)and message passing(MP)algorithms on overspread doubly selective ***,simulation results are presented to verify the theoretical derivation and the effectiveness of the detectors.

关键词： delay-Doppler domain doubly selective channel OTFS overspread underwater acoustic communications

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Corn Leaf Blights in Natural Light Images Captured by Drones Using Deep Learning Frameworks 9

Automated Detection of Corn Leaf Blights in Natural Light Im...

引用

9th International Conference on Image, Vision and Computing, ICIVC 2024

作者： Wang, YaLi Liu, Lei Yang, MengLing Ji, HaiYan College of Computer and Information Engineering Henan Normal University Xinxiang453007 China College of Information Engineering Wuhan Engineering Institute Wuhan430415 China

ISBN: (纸本)9798350385991

Drones have significantly reduced the reliance on agricultural experts for disease diagnosis, thereby enhancing the efficiency of disease detection and diagnosis. However, the detection accuracy still needs improvement due to various factors such as lighting conditions, wind speed, temperature, humidity, or leaf occlusion in natural environments. To address this challenge, this paper proposes a multi-scale feature extraction model called R50F-NLB, designed explicitly for detecting corn leaf blight in natural settings by improving the Faster R-CNN target detection model. Our R50F-NLB model, with the deep residual network ResNet-50 as its backbone, addresses gradient disappearance and explosion issues. By leveraging the Feature Pyramid Network (FPN) for multi-scale feature fusion, our model enhances the detection of small targets, such as corn leaf blight. This practical application of our model can significantly improve disease detection in agriculture. Furthermore, we adjust the anchor size and aspect ratio based on the shape characteristics of corn leaves, employing sizes more suitable for the contours of corn leaves. This modification further improves the adaptability of the algorithm to target detection, reducing false positives and missed detections. Our experimental results speak for themselves. The R50F-NLB model, compared to the baseline model, demonstrates superior detection performance. It achieves an impressive improvement of 25.3%, a clear testament to the effectiveness of our proposed model in detecting corn leaf blight in natural settings. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Enhancing aquaculture water quality forecasting using novel adaptive multi-channel spatial-temporal graph convolutional network

引用

International Journal of Agricultural and Biological engineering 2025年第1期18卷 279-291页

作者： Tianqi Xiang Xiangyun Guo Junjie Chi Juan Gao Luwei Zhang College of Computer Science Beijing Information Science&Technology UniversityBeijing 102206China College of Management Science and Engineering Beijing Information Science&Technology UniversityBeijing 102206China College of Engineering China Agricultural UniversityBeijing 100083China

In recent years,aquaculture has developed rapidly,especially in coastal and open ocean *** practice,water quality prediction is of critical ***,traditional water quality prediction models face limitations in handling complex spatiotemporal *** address this challenge,a prediction model was proposed for water quality,namely an adaptive multi-channel temporal graph convolutional network(AMTGCN).The AMTGCN integrates adaptive graph construction,multi-channel spatiotemporal graph convolutional network,and fusion layers,and can comprehensively capture the spatial relationships and spatiotemporal patterns in aquaculture water quality *** aquaculture water quality data and the metrics MAE,RMSE,MAPE,and R^(2) were collected to validate the *** results show that the AMTGCN presents an average improvement of 34.01%,34.59%,36.05%,and 17.71%compared to LSTM,respectively;an average improvement of 64.84%,56.78%,64.82%,and 153.16%compared to the STGCN,respectively;an average improvement of 55.25%,48.67%,57.01%,and 209.00%compared to GCN-LSTM,respectively;and an average improvement of 7.05%,5.66%,7.42%,and 2.47%compared to TCN,*** indicates that the AMTGCN,integrating the innovative structure of adaptive graph construction and multi-channel spatiotemporal graph convolutional network,could provide an efficient solution for water quality prediction in aquaculture.

关键词： water quality prediction aquaculture spatial-temporal graph convolutional network multi-channel adaptive graph construction

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：