检索结果-内蒙古大学图书馆

Multi-View Graph Embedding Learning for Image Co-Segmentation and Co-Localization

IEEE Transactions on Circuits and Systems for Video Technology 2024年第6期34卷 4942-4956页

作者： Huang, Aiping Li, Lijian Zhang, Le Niu, Yuzhen Zhao, Tiesong Lin, Chia-Wen Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou350108 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering The Fujian Science and Technology Innovation Laboratory for Optoelectronic Information Fuzhou350108 China Institute of Communications Engineering National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan

Image co-segmentation and co-localization exploit inter-image information to identify and extract foreground objects with a batch mode. However, they remain challenging when confronted with large object variations or complex backgrounds. This paper proposes a multi-view graph embedding (MV-Gem) learning scheme which integrates diversity, robustness and discernibility of object features to alleviate this phenomenon. To encourage the diversity, the deep co-information containing both low-layer general representations and high-layer semantic information is generated to form a multi-view feature pool for comprehensive co-object description. To enhance the robustness, a multi-view adaptive weighted learning is formulated to fuse the deep co-information for feature complementation. To ensure the discernibility, the graph embedding and sparse constraint are embedded into the fusion formulation for feature selection. The former aims to inherit important structures from multiple views, and the latter further selects important features to restrain irrelevant backgrounds. With these techniques, MV-Gem gradually recovers all co-objects through optimization iterations. Extensive experimental results on real-world datasets demonstrate that MV-Gem is capable of locating and delineating co-objects in an image group. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Design of Evolutionary Algorithm Based Unequal Clustering for Energy Aware Wireless Sensor Networks

引用

computer Systems science & Engineering 2023年第10期47卷 1283-1297页

作者： Mohammed Altaf Ahmed T.Satyanarayana Murthy Fayadh Alenezi E.Laxmi Lydia Seifedine Kadry Yena Kim Yunyoung Nam Department of Computer Engineering College of Computer Engineering&SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Chaitanya Bharathi Institute of Technology HyderabadTelanganaIndia Department of Electrical Engineering College of EngineeringJouf UniversitySakaka 72388Saudi Arabia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeKristiansandNorway Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of ICT Convergence Soonchunhyang UniversityAsan 31538Korea

Wireless Sensor Networks(WSN)play a vital role in several real-time applications ranging from military to *** the benefits of WSN,energy efficiency becomes a major part of the challenging issue in WSN,which necessitate proper load balancing amongst the clusters and serves a wider monitoring *** clustering technique for WSN has several benefits:lower delay,higher energy efficiency,and collision *** clustering protocol has several *** a large-scale network,cluster-based protocols mainly adapt multi-hop routing to save energy,leading to hot spot problems.A hot spot problem becomes a problem where a cluster node nearer to the base station(BS)tends to drain the energy much quicker than other nodes because of the need to implement more *** article introduces a Jumping Spider Optimization Based Unequal Clustering Protocol for Mitigating Hotspot Problems(JSOUCP-MHP)in *** JSO algorithm is stimulated by the characteristics of spiders naturally and mathematically modelled the hunting mechanism such as search,persecution,and jumping skills to attack *** presented JSOUCPMHP technique mainly resolves the hot spot issue for maximizing the network *** JSOUCP-MHP technique elects a proper set of cluster heads(CHs)using average residual energy(RE)to attain *** addition,the JSOUCP-MHP technique determines the cluster sizes based on two measures,i.e.,RE and distance to BS(DBS),showing the novelty of the *** proposed JSOUCP-MHP technique is examined under several experiments to ensure its *** comparison study shows the significance of the JSOUCPMHP technique over other models.

关键词： Wireless sensor networks energy efficiency cluster heads unequal clustering hot spot issue lifetime enhancement

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic Computing Architectures for EnergyEfficient Edge Devices in Autonomous Vehicles

Neuromorphic Computing Architectures for EnergyEfficient Edg...

引用

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS)

作者： Rahul Pradhan Annapurna Gummadi P. Tanusha Gandla Sowmya S. Vaitheeshwari Ponni Valavan M Department of Computer Science and Engineering GLA University Mathura Uttar Pradesh India Department of CSE (Data Science) CVR College of Engineering Hyderabad India Department of Computer Science and Engineering KL University Vaddeswaram Andhra Pradesh India Department of Computer Science and Engineering NRI Institute of Technology Vijayawada Andhra Pradesh India Department of Computer Science Veltech Multitech Dr. Rangarajan Dr. Sakunthala Engineering College Avadi Chennai India Department of AI & DS K. Ramakrishnan College of Engineering Trichy Tamil Nadu India

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

Autonomous vehicles hold the promise of significantly reducing road accidents caused by human error, such as distracted driving or impaired judgment. However, the widespread adoption of autonomous vehicles faces challenges, including regulatory frameworks, liability concerns, ethical considerations, and the need for comprehensive infrastructure updates. This research focuses on the development of neuromorphic computing architectures tailored for energyefficient edge devices in autonomous vehicles. The significance of this study lies in addressing the escalating computational demands of real-time data processing in autonomous driving scenarios while mitigating the inherent power constraints of edge computing environments. The conventional approaches in autonomous vehicle computing, often centralized and powerintensive, pose challenges in terms of energy consumption and real-time responsiveness. The proposed neuromorphic computing architectures leverage spiking neural networks and event-driven processing to emulate the brain's efficiency, offering a novel solution to enhance both computational performance and energy efficiency. The research addresses prior issues related to the power-hungry nature of traditional computing paradigms in autonomous vehicles and emphasizes the need for more sustainable and responsive edge computing solutions. The novelty of this research lies in the integration of neuromorphic principles into edge devices, enabling onboard processing that is not only energy-efficient but also well-suited for the sporadic and dynamic nature of real-world driving environments. This study paves the way for advancements in autonomous vehicle technology, promising enhanced energy efficiency, reduced latency, and improved overall system performance.

关键词： Performance evaluation Neuromorphic engineering Signal processing algorithms computer architecture Energy efficiency Real-time systems Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Binary Code Similarity Detection

arXiv

引用

arXiv 2023年

作者： Liu, Zian Department of Computer Science and Software Engineering Swinburne University of Technology Data61 CSIRO Melbourne Australia

Binary code similarity detection is to detect the similarity of code at binary (assembly) level without source code. Existing works have their limitations when dealing with mutated binary code generated by different compiling options. In this paper, we propose a novel approach to addressing this problem. By inspecting the binary code, we found that generally, within a function, some instructions aim to calculate (prepare) values for other instructions. The latter instructions are defined by us as key instructions. Currently, we define four categories of key instructions: calling subfunctions, comparing instruction, returning instruction, and memory-store instruction. Thus if we symbolically execute similar binary codes, symbolic values at these key instructions are expected to be similar. As such, we implement a prototype tool, which has three steps. First, it symbolically executes binary code;Second, it extracts symbolic values at defined key instructions into a graph;Last, it compares the symbolic graph similarity. In our implementation, we also address some problems, including path explosion and loop handling. © 2023, CC BY.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

On the Robustness of Cross-Concentrated Sampling for Matrix Completion

arXiv

引用

arXiv 2024年

作者： Cai, HanQin Huang, Longxiu Kundu, Chandra Su, Bowen Department of Statistics and Data Science Department of Computer Science University of Central Florida OrlandoFL32816 United States Department of Computational Mathematics Science and Engineering Department of Mathematics Michigan State University East LansingMI48824 United States Department of Statistics and Data Science University of Central Florida OrlandoFL32816 United States Department of Mathematics Michigan State University East LansingMI48824 United States

Matrix completion is one of the crucial tools in modern data science research. Recently, a novel sampling model for matrix completion coined cross-concentrated sampling (CCS) has caught much attention. However, the robustness of the CCS model against sparse outliers remains unclear in the existing studies. In this paper, we aim to answer this question by exploring a novel Robust CCS Completion problem. A highly efficient non-convex iterative algorithm, dubbed Robust CUR Completion (RCURC), is proposed. The empirical performance of the proposed algorithm, in terms of both efficiency and robustness, is verified in synthetic and real datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

The Role of Machine Learning Algorithms in Developing Android App and to do Malware Detection 3

The Role of Machine Learning Algorithms in Developing Androi...

引用

3rd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2023

作者： Sudhamsu, Gadug Bhatt, Rahul Jakka, Geethamanikanta Jweeg, Muhsin J. Alfurhood, Badria Sulaiman Tripathi, Vikas Department of Computer Science and Engineering Bangalore India Dev Bhoomi Uttarakhand University Department of CSE Uttarakhand Dehradun India University of the Cumberlands Data Analytics Information Technology United States Al-Farahidi University College of Technical Engineering Baghdad Iraq Princess Νourah Hint Ahdulrahman University College of Computer and Information Sciences Department of Computer Sciences Saudi Arabia Graphic Era Deemed to Be University Department CSE India

ISBN: (纸本)9798350399264

Because there are so many issues that have had suitable solutions, cybersecurity is now the subject that worries computer scientists and system administrators the most. The rapid development of information technology and its inherent integration into every aspect of our lives have made it possible to analyze and identify a broad variety of harmful software packages and the targets of these programmes. Malware ***, Android malware has gotten some notice. It seems to attract a lot of attention on the internet. Android is one of the most well-liked operating systems that dominates the operating system market. In 2020, 85% of smartphones will run on the Android operating system, according to statistics from the system. Mobile virus attacks have increased in frequency over time. Known to infect a phone system with applications that seem harmless but really contain malware is one of the most popular approaches. Malware on cellphones has already been detected using machine learning. Deep learning and supervised learning techniques have been used to achieve this. Drawing on consumer rights, this study evaluates the effectiveness of multiple categorization approaches to find virus in Android apps. © 2023 IEEE.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

Genre Classification of Bangla Poem Using Machine Learning and Deep Learning Techniques

Genre Classification of Bangla Poem Using Machine Learning a...

引用

AI IoT Congress (AIIoT), World

作者： Syed Tangim Pasha Ashraful Islam Mohammed Masudur Rahman Eshtiak Ahmed Md. Ferdouse Ahmed Foysal Md Zahangir Alam Department of Computing and Information System Daffodil International University Bangladesh Center for Computational and Data Sciences Independent University Bangladesh Department of Computer Science and Engineering Independent University Bangladesh Department of Computer Science and Engineering International Standard University Bangladesh Department of Computer Science and Engineering Daffodil International University Bangladesh

The computational analysis of the Bangla poems is a challenging task due to the diverse linguistic, stylistic, and semantic features of the Bangla language. In this work, we prepared a dataset of 1311 Bangla poems of two separate categories: Love and Miscellaneous poem, which contain 500 and 811 poems respectively. We used word or semantic-based features to classify Bangla poems using the TF-IDF feature techniques. We used Logistic Regression, Naïve Bayes (NB), and Support Vector Machine (SVM) models for classification through machine learning, and we used Bayesian optimization techniques for hyperparameters tuning of these three models. We also used LSTM, CNN, and transformer models for this research. For the performance evaluation of the classification models, we used four evaluation metrics of precision, recall, F1-score, and accuracy. We also used the ROC-AUC curve to distinguish between all the machine learning and deep learning models. The experimental results expressed that, the transformer model achieved the highest accuracy compared to all the typical machine learning and deep learning models with an accuracy of 87%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values

arXiv

引用

arXiv 2024年

作者： Zheng, Yu Koh, Huan Yee Jin, Ming Chi, Lianhua Wang, Haishuai Phan, Khoa T. Chen, Yi-Ping Phoebe Pan, Shirui Xiang, Wei Department of Computer Science and Information Technology La Trobe University Australia Department of Data Science and AI Faculty of IT Monash University Australia School of Information and Communication Technology Griffith University Australia Zhejiang University China

The detection of anomalies in multivariate time series data is crucial for various practical applications, including smart power grids, traffic flow forecasting, and industrial process control. However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training;(2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values. In this work, we introduce a novel framework called GST-Pro, which utilizes a graph spatiotemporal process and anomaly scorer to tackle the aforementioned challenges in detecting anomalies on irregularly-sampled multivariate time series. Our approach comprises two main components. First, we propose a graph spatiotemporal process based on neural controlled differential equations. This process enables effective modeling of multivariate time series from both spatial and temporal perspectives, even when the data contains missing values. Second, we present a novel distribution-based anomaly scoring mechanism that alleviates the reliance on complete uniform observations. By analyzing the predictions of the graph spatiotemporal process, our approach allows anomalies to be easily detected. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods, regardless of whether there are missing values present in the data. Our code is available: https://***/huankoh/GST-Pro. © 2024, CC BY.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

HIERARCHICAL SLICED WASSERSTEIN DISTANCE 11

HIERARCHICAL SLICED WASSERSTEIN DISTANCE

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Nguyen, Khai Ren, Tongzheng Nguyen, Huy Rout, Litu Nguyen, Tan Ho, Nhat Department of Statistics and Data Sciences The University of Texas at Austin AustinTX78712 United States Department of Computer Science The University of Texas at Austin AustinTX78712 United States Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX78712 United States Department of Mathematics University of California Los Angeles Los AngelesCA90095 United States

Sliced Wasserstein (SW) distance has been widely used in different application scenarios since it can be scaled to a large number of supports without suffering from the curse of dimensionality. The value of sliced Wasserstein distance is the average of transportation cost between one-dimensional representations (projections) of original measures that are obtained by Radon Transform (RT). Despite its efficiency in the number of supports, estimating the sliced Wasserstein requires a relatively large number of projections in high-dimensional settings. Therefore, for applications where the number of supports is relatively small compared with the dimension, e.g., several deep learning applications where the mini-batch approaches are utilized, the complexities from matrix multiplication of Radon Transform become the main computational bottleneck. To address this issue, we propose to derive projections by linearly and randomly combining a smaller number of projections which are named bottleneck projections. We explain the usage of these projections by introducing Hierarchical Radon Transform (HRT) which is constructed by applying Radon Transform variants recursively. We then formulate the approach into a new metric between measures, named Hierarchical Sliced Wasserstein (HSW) distance. By proving the injectivity of HRT, we derive the metricity of HSW. Moreover, we investigate the theoretical properties of HSW including its connection to SW variants and its computational and sample complexities. Finally, we compare the computational cost and generative quality of HSW with the conventional SW on the task of deep generative modeling using various benchmark datasets including CIFAR10, CelebA, and Tiny ImageNet. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

ExpertDRL: Request Dispatching and Instance Configuration for Serverless Edge Inference with Foundation Models

引用

IEEE Transactions on Mobile Computing 2025年

作者： Zeng, Yue Zhou, Junlong Ye, Baoliu Qu, Zhihao Guo, Song Gong, Tianjian Li, Pan Nanjing University of Science and Technology Department of Computer Science and Engineering Jiangsu Nanjing210094 China Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing210023 China Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources Nanjing211100 China Hong Kong University of Science and Technology Hong Kong Southwest University College of Electronic and Information Engineering Chongqing400715 China

The prevalence of the pre-training & fine-tuning paradigm enables machine learning models to quickly adapt to various downstream tasks by fine-tuning pre-trained foundation models (FMs), greatly facilitating various IoT applications that rely on model inference in dynamic edge serverless environments. Efficiently dispatching inference requests and configuring instances to batch inference requests can significantly enhance resource efficiency. However, existing serverless inference solutions are tailored for traditional models, make coarse-grained request dispatching and instance configuration decisions, fail to exploit the shared model backbone characteristics of the FM and capture delayed rewards in dynamic environments, and ignore communication latency between edge sites, resulting in high costs and constraint violations. In this paper, we leverage our insight that fine-grained batch inference requests can effectively exploit the shared model backbone feature of FM to save monetary costs. We propose an algorithm that incorporates deep reinforcement learning (DRL) and expert intervention for fine-grained request dispatching and instance configuration, where the DRL component outputs fractional solutions as guidance, while the expert intervention module integrates our insights—batching reduces monetary costs at the expense of increased inference latency, whereas higher configurations shorten inference latency. This module rounds fractional solutions and adjusts instance configurations to search for optimal solutions while satisfying constraints, with theoretical guarantees rigorously proved. Finally, we conducted our experiments on an OpenFaas-based platform and simulator, and extensive trace-driven evaluation results show that ExpertDRL can save costs by up to 85.14% and improve request acceptance ratio by up to 26.93%, compared to the state-of-the-art solution. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

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：