检索结果-内蒙古大学图书馆

Computational Visual Media 2023年第3期9卷 495-512页

作者： Kaiyi Zhang Liang Zhou Lu Chen Shitong He Daniel Weiskopf Yunhai Wang School of Computer Science and Technology Shandong UniversityQingdao 266237China National Institute of Health Data Science Peking UniversityBeijing 100191China Visualization Research Center(VISUS) University of Stuttgart70569 StuttgartGermany

We present angle-uniform parallel coordinates,a data-independent technique that deforms the image plane of parallel coordinates so that the angles of linear relationships between two variables are linearly mapped along the horizontal axis of the parallel coordinates *** being a common method for visualizing multidimensional data,parallel coordinates are ineffective for revealing positive correlations since the associated parallel coordinates points of such structures may be located at infinity in the image plane and the asymmetric encoding of negative and positive correlations may lead to unreliable *** address this issue,we introduce a transformation that bounds all points horizontally using an angleuniform mapping and shrinks them vertically in a structure-preserving fashion;polygonal lines become smooth curves and a symmetric representation of data correlations is *** further propose a combined subsampling and density visualization approach to reduce visual clutter caused by *** method enables accurate visual pattern interpretation of data correlations,and its data-independent nature makes it applicable to all multidimensional *** usefulness of our method is demonstrated using examples of synthetic and real-world datasets.

关键词： parallel coordinates multidimensional data deformation correlations

来源：评论

学校读者我要写书评

暂无评论

MPNAS: Multimodal Sentiment Analysis Pruning via Neural Architecture Search

MPNAS: Multimodal Sentiment Analysis Pruning via Neural Arch...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Binyan Ren, Ao Zhang, Zihao Duan, Moming Liu, Duo Tan, Yujuan Zhong, Kan College of Computer Science Chongqing University Chongqing China School of Big Data Software & Engineering Chongqing University Chongqing China Institute of Data Science National University of Singapore Singapore

ISBN: (纸本)9798350368741

With the rapid development of social media, sentiment analysis from multimodal posts has garnered significant attention in recent years. However, the substantial size of these models impedes their deployment on resource-constrained embedded devices. Although pruning has been extensively studied to reduce the size of unimodal models, specific challenges remain for Multimodal Sentiment Analysis (MSA) models. First, existing techniques prune fixed original models into sparse models, while our findings indicate that different model architectures of identical size yield varying performance outcomes. Second, prior studies fail to explore the unique characteristics of MSA models, resulting in suboptimal pruning performance. To address these challenges, we propose MPNAS, a unified pruning framework via Neural Architecture Search (NAS) for MSA models. Specifically, we formulate pruning as a NAS problem and analyze MSA model characteristics to guide the subnet search. We conduct an initial coarse-grained NAS on the original model, expanding the search space slightly to identify suitable subnets that enhance pruning rates and accuracy. Subsequently, we refine coarse-grained subnets in a fine-grained NAS stage, where MSA model characteristics guide the search process. Extensive experiments on three representative datasets demonstrate the superiority of our approach over existing methods. © 2025 IEEE.

关键词： Multimodal Compression NAS

来源：评论

学校读者我要写书评

暂无评论

On the Design of Cancer Tumor Type Prediction using Machine Learning Techniques for Efficient Diagnosis 2

On the Design of Cancer Tumor Type Prediction using Machine ...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Thakkar, Hiren Kumar Kumar, Yogesh Kathirisetty, Nikhila School of Technology Pandit Deendayal Energy University Department of Computer Science and Engineering Gujarat 382007 India Vardhaman College of Engineering Department of Computer Science and Data Science Hyderabad Shamshabad India

ISBN: (纸本)9798350370188

In the recent past, cancer is designated as the life threatening disease causing significant deaths across the globe. Countries are putting efforts for early stage cancer detection, and mortality prediction. Machine Learning (ML) models are proven to efficiently find the correlation among the features for robust predictions over statistical approaches. In this paper, we used kaggle dataset that includes 569 cancer cells and around 30 features cancer cells' classification. The proposed study employs ML models (e.g., binary classifiers) for effective predictive analytics. The evaluation results indicate that Random Forest achieves better results with Area Under Curve (AUC) of 0.99 followed by Decision tree with AUC be 0.92. However, the Logistic Regression (LR) and Support Vector Machine (SVM) fails to capture the generalized behavior of the cancer data for predictive analysis. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Latency- and Privacy-Aware Convolutional Neural Network Distributed Inference for Reliable Artificial Intelligence Systems

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 365-377页

作者： Hu, Yuhao Xu, Xiaolong Qi, Lianyong Zhou, Xiaokang Xia, Xiaoyu Nanjing University of Information Science and Technology School of Software Nanjing210044 China College of computer science and technology Qingdao266850 China Shiga University Faculty of Data Science Hikone522-8522 Japan RMIT University School of Computing Technologies MelbourneVIC3000 Australia

Reliable artificial intelligence (AI) systems not only propose a challenge on providing intelligent services with high quality for customers but also require customers' privacy to be protected as much as possible during process of the services. Given the ultrahigh computing load brought by deep-learning-based intelligent services to edge devices and the ultralong distance between edge and cloud, low-latency requirement of intelligent services is hard to meet in single edge computing or cloud computing. Edge-cloud collaborative inference of deep neural networks (DNNs) is considered a feasible solution to the problem. However, former work has not reduced the inference latency to the greatest extent and has not considered privacy protection in distributed systems. To solve the problem, we first establish a novel queue mechanism. Then, the convolution layer split decisions are made based on deep reinforcement learning (DRL) to realize the parallel inference of convolutional neural networks (CNNs) for inference latency reduction. Next, for each CNN, the partition decision is made based on brute force algorithm to further reduce inference latency and protect customers' privacy. Finally, simulation results show that our method performs better than the existing other methods. © 2020 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

An Improved Honey Badger Algorithm through Fusing Multi-Strategies

引用

computers, Materials & Continua 2023年第8期76卷 1479-1495页

作者： Zhiwei Ye Tao Zhao Chun Liu Daode Zhang Wanfang Bai School of Computer Science Hubei University of TechnologyWuhan430068China Xining Big Data Service Administration Xining810000China

TheHoney Badger Algorithm(HBA)is a novelmeta-heuristic algorithm proposed recently inspired by the foraging behavior of honey *** dynamic search behavior of honey badgers with sniffing and wandering is divided into exploration and exploitation in HBA,which has been applied in photovoltaic systems and optimization problems ***,HBA tends to suffer from the local optimum and low *** alleviate these challenges,an improved HBA(IHBA)through fusing multi-strategies is presented in the *** introduces Tent chaotic mapping and composite mutation factors to HBA,meanwhile,the random control parameter is improved,moreover,a diversified updating strategy of position is put forward to enhance the advantage between exploration and *** is compared with 7 meta-heuristic algorithms in 10 benchmark functions and 5 engineering *** Wilcoxon Rank-sum Test,Friedman Test and Mann-WhitneyU Test are conducted after *** results indicate the competitiveness and merits of the IHBA,which has better solution quality and convergence *** source code is currently available from:https://***/zhaotao789/IHBA.

关键词： Honey Badger Algorithm multi-strategies fusion tent chaotic mapping compound random factors

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Based Student Computational Thinking Analysis Model (AI-SCTAM) for Curriculum Development 2

Artificial Intelligence-Based Student Computational Thinking...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Sowmiya, S. Umar Farook, R. Giridharan, B. Shalini, A. Airtifical Intellegence and Data Science Karpagam Academy Higher Education Coimbatore India Airtifical Intellegence and Data Science Karpagam Academy Higher Education India Computer Science and Engineering Karpagam Academy Higher Education Coimbatore India

ISBN: (纸本)9798331505745

Computational thinking (CT) has been widely used to improve students' comprehension of mathematical and scientific subjects. However, there is a scarcity of information available regarding the challenges faced by students and the development of their conceptual knowledge in these learning environments, particularly in relation to the integrated curriculum. There is a need to help with course-level curriculum development to improve teaching and learning. Hence, this paper proposes an artificial intelligence-based student computational thinking analysis model (AI-SCTAM) to predict student engagement in learning and improve curriculum development. This research attempted to determine the association between student engagement measures using the machine learning (ML) method to determine the degrees of student involvement. The ML divides students into two groups: highly engaged and poorly engaged, according to the criteria used to measure their degree of involvement. The findings of the correlation study showed a positive association between engagement measures and performance. Analyzing the relationship between student engagement and performance will guide the development of course materials and activities. STEM education metrics based on engagement levels will be proposed to personalize students' learning experiences. © 2025 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Vision: Supporting Citizens in Adopting Privacy Enhancing Technologies 23

Vision: Supporting Citizens in Adopting Privacy Enhancing Te...

引用

2023 European Symposium on Usable Security, EuroUSEC 2023

作者： Shams, Shirin Reinhardt, Delphine University of Göttingen Institute of Computer Science Germany University of Göttingen Institute of Computer Science Campus Institute Data Science Germany

ISBN: (纸本)9798400708145

We have witnessed an alarming growth in collecting citizens' information by businesses and organizations. The more citizens' information they collect, the greater their ability to utilize this knowledge for their own interests, often at the expense of society members. Despite the efforts made by privacy ecosystem members (such as researchers and regulatory entities) to protect citizens' privacy against data collectors, the low adoption of Privacy Enhancing Technologies (PETs) by citizens remains concerning. To address these concerns, this vision paper proposes a user-centred approach to develop a tool that assists citizens in adopting PETs effectively. To this end, we plan to (1) understand the factors contributing to low PETs adoption via methods such as focus groups and in-depth interviews, (2) design an interactive tool to support citizens in adopting PETs in a user-friendly manner, and (3) evaluate the tool's effectiveness through usability testing. The outcome will serve as an interactive tool which first receives the privacy concerns and needs of each user and then provides personalised PET recommendations accordingly. © 2023 ACM.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Domain Reductions After Preprocessing: Effects on Dynamic Variable Ordering Heuristics in Constraint Satisfaction Search 23rd

Domain Reductions After Preprocessing: Effects on Dynamic V...

引用

23rd EPIA Conference on Artificial Intelligence, EPIA 2024

作者： Wallace, Richard J. Insight Centre for Data Analytics and Department of Computer Science University College Cork Cork Ireland

ISBN: (纸本)9783031734991

We still do not have an adequate understanding of heuristic methods used for solving constraint satisfaction problems (CSPs). An example involves the effects of preprocessing, an essential means of improving CSP search. The traditional explanation for its beneficial effect is that the resulting "problem reduction" leaves fewer possibilities to explore. Recently, however, it was shown that when dynamic variable ordering heuristics are used, other factors related to domain size reduction are much more important. This paper extends this analysis and explores some implications of this new perspective. The key idea is that pattern of domain reductions produced by preprocessing transmits information that guides heuristic decisions. Treating domain reduction as a code and the set of reductions as a message of length n transmitted to the search algorithm, we distinguish two factors, message discriminability and code quality, and show that greater problem reduction enhances both. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Holistic Speaker Independent Visual Speech Recognition

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第6期4卷 1705-1713页

作者： Nemani, Praneeth Krishna, Ghanta Sai Ramisetty, Nikhil Sai, B Digvijay Sri Kumar, Santosh IIIT Naya Raipur Department of Computer Science and Engineering Raipur493661 India IIIT Naya Raipur Department of Data Science and Artificial Intelligence Raipur493661 India

From a broader perspective, the objective of visual speech recognition (VSR) is to comprehend the speech spoken by an individual using visual deformations. However, some of the significant limitations of existing solutions include the dearth of training data, improper end-to-end deployed solutions, lack of holistic feature representation, and less accuracy. To resolve these limitations, this study proposes a novel, scalable, and robust VSR system that uses the videotape of the user to determine the word which is being spoken. In this regard, a customized 3-D convolutional neural network (3-D CNN) architecture is proposed by extracting the spatio-temporal features and eventually mapping the prediction probabilities of the elements in the corpus. We have created a customized dataset resembling the metadata contained in the MIRACL-VC1 dataset to validate the concept of person-independence. While being robust to a broad spectrum of lighting conditions across multiple devices, our model achieves a training accuracy of 80.2% and a testing accuracy of 77.9% in predicting the word spoken by the user. © 2020 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-task Genetic Programming with Semantic based Crossover for Multi-output Regression

Multi-task Genetic Programming with Semantic based Crossover...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Wang, Chunyu Chen, Qi Xue, Bing Zhang, Mengjie Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand

ISBN: (纸本)9798400704956

Multi-output regression involves predicting two or more target variables simultaneously. In contrast to its single-output counterpart, multi-output regression poses additional challenges primarily because the target variables are frequently interdependent. Achieving accurate predictions for one variable may necessitate a thorough consideration of its relationships with other variables. In this paper, multi-output regression problems are regarded as multi-task optimization problems where predicting one output variable is considered as one task. A new multi-task multi-population genetic programming method is proposed to solve the problem. The method utilizes the semantic based crossover operator to transfer positive knowledge and accelerate convergence. Additionally, it adopts an offspring reservation strategy to keep the quality of the individuals for the corresponding tasks. The empirical results demonstrate that our proposed method significantly enhances the training and the test performances of multi-task multi-population GP and also outperforms standard GP on five real-world multi-output regression datasets. © 2024 Copyright held by the owner/author(s).

关键词： Genetic programming

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：