检索结果-内蒙古大学图书馆

On Fixed-Order Book Thickness Parameterized by the Pathwidth of the Vertex Ordering 14th

学校读者我要写书评

暂无评论

On Fixed-Order Book Thickness Parameterized by the Pathwidth...

14th International Conference on Algorithmic Aspects in Information and Management, AAIM 2020

作者： Liu, Yunlong Chen, Jie Huang, Jingui Wang, Jianxin Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China School of Computer Science and Engineering Central South University Changsha410083 China

ISBN: (纸本)9783030576011

Given a graph (Formula Presented) and a fixed linear order (Formula Presented) of V, the problem fixed-order book thickness asks whether there is a page assignment (Formula Presented) such that (Formula Presented) is a k-page book embedding of G. Recently, Bhore et al.(GD2019) presented an algorithm parameterized by the pathwidth of the vertex ordering (denoted by (Formula Presented)). In this paper, we first re-analyze the running time for Bhore et al.’s algorithm, and prove a bound of (Formula Presented) improving on Bhore et al.’s bound of (Formula Presented). We further show that this parameterized problem does not admit a polynomial kernel unless NP (Formula Presented) coNP/poly. Finally, we show that the general fixed-order book thickness problem, in which a budget of at most c crossings over all pages was given, admits an algorithm running in time (Formula Presented). © 2020, Springer Nature Switzerland AG.

关键词： Budget control

Online multi-label streaming feature selection by affinity significance, affinity relevance and affinity redundancy

学校读者我要写书评

暂无评论

Pattern Recognition 2025年

作者： Jianhua Dai Duo Xu Chucai Zhang Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Normal University Changsha 410081 China Key Laboratory of Computing and Stochastic Mathematics (Ministry of Education) School of Mathematics and Statistics Hunan Normal University Changsha 410081 China

Multi-label streaming feature selection has applied to various fields to deal with the applications that features arrive dynamically. However, most exist multi-label streaming feature selection methods ignore that a feature tends to provide more classification information for part of labels, rather than equal information for all labels. This phenomenon results part of labels get more information from selected features, while other labels lack information. In order to address the issue, we propose a novel multi-label streaming feature selection method. Firstly, we come up with the concept of affinity between features and labels. Secondly, we propose the concepts of affinity significance, affinity relevance and affinity redundancy to evaluate streaming features in three dimensions. Thirdly, we propose a novel multi-label streaming feature selection method named OMFS-FA. OMFS-FA has three phases to retain affinity significant features, remove affinity irrelevant features and remove affinity redundant features respectively. Finally, experiments on performance analysis, statistic analysis, number of selected features and running time analysis are conducted, verifying that OMFS-FA significantly outperforms other eleven methods in terms of effectiveness and efficiency.

关键词：

Bert-pair-networks for sentiment classification 19

学校读者我要写书评

暂无评论

Bert-pair-networks for sentiment classification

19th International Conference on Machine Learning and Cybernetics, ICMLC 2020

作者： Wang, Ziwen Wu, Haiming Liu, H.A.N. Cai, Qian-Hua Guangdong University of Foreign Studies Laboratory of Language Engineering and Computing Guangzhou510006 China South China Normal University School of Physics and Telecommunication Engineering Guangzhou510006 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

ISBN: (纸本)9780738124261

BERT has demonstrated excellent performance in natural language processing due to the training on large amounts of text corpus in an unsupervised way. However, this model is trained to predict the next sentence, and thus it is good at dealing with sentence pair tasks but may not be sufficiently good for other tasks. In our paper, we introduce a novel representation framework BERT-pair-Networks (p-BERTs) for sentiment classification, where p-BERTs involve adopting BERT to encode sentences for sentiment classification as a classic task of single sentence classification, using the auxiliary sentence, and a feature extraction layer on the top. Results on three datasets show that our method achieves considerably improved performance. © 2020 IEEE.

关键词： Natural language processing systems

Large Generative Model Assisted 3D Semantic Communication

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Feibo Peng, Yubo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua You, Xiaohu Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China The Department of Computer Science Brunel University London United Kingdom The School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Changchun Institute of Technology China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Frontiers Science Center for Mobile Information Communication and Security National Mobile Communications Research Laboratory Southeast University Nanjing China The Purple Mountain Laboratories Nanjing China

Semantic Communication (SC) is a novel paradigm for data transmission in 6G. However, there are several challenges posed when performing SC in 3D scenarios: 1) 3D semantic extraction;2) Latent semantic redundancy;and 3) Uncertain channel estimation. To address these issues, we propose a Generative AI Model assisted 3D SC (GAM-3DSC) system. Firstly, we introduce a 3D Semantic Extractor (3DSE), which employs generative AI models, including Segment Anything Model (SAM) and Neural Radiance Field (NeRF), to extract key semantics from a 3D scenario based on user requirements. The extracted 3D semantics are represented as multi-perspective images of the goal-oriented 3D object. Then, we present an Adaptive Semantic Compression Model (ASCM) for encoding these multi-perspective images, in which we use a semantic encoder with two output heads to perform semantic encoding and mask redundant semantics in the latent semantic space, respectively. Next, we design a conditional Generative adversarial network and Diffusion model aided-Channel Estimation (GDCE) to estimate and refine the Channel State Information (CSI) of physical channels. Finally, simulation results demonstrate the advantages of the proposed GAM-3DSC system in effectively transmitting the goal-oriented 3D scenario. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Effect of representation format on conceptual question performance and eye-tracking measures

学校读者我要写书评

暂无评论

Physical Review Physics Education Research 2023年第2期19卷 020114-020114页

作者： Ana Susac Maja Planinic Andreja Bubic Katarina Jelicic Marijan Palmovic Department of Applied Physics Faculty of Electrical Engineering and Computing University of Zagreb Unska 3 10000 Zagreb Croatia Department of Physics Faculty of Science University of Zagreb Bijenicka 32 10000 Zagreb Croatia Department of Psychology Faculty of Humanities and Social Sciences University of Split Sinjska 2 21000 Split Croatia Laboratory for Psycholinguistic Research Department of Speech and Language Pathology University of Zagreb Borongajska cesta 83h 10000 Zagreb Croatia

Previous studies have shown the important role of different representations in the teaching and learning of physics. In this study, we used eye tracking to investigate the effect of different representations on the process of answering conceptual questions. We compared students’ scores and eye-tracking measures on isomorphic questions which contained graphical, pictorial, and verbal representations. On average, in two-thirds of cases, students were consistent in their answers (correct or incorrect) across all three representations. There was no statistically significant difference in students’ scores for different representations. However, eye-tracking measures suggest that it was easiest for students to extract information from verbal representations and most difficult from pictorial representations for the conceptual questions used in this study. These results could be useful to teachers and researchers when creating conceptual questions and, more generally, when teaching with multiple representations.

关键词： Instructional strategies Scientific reasoning & problem solving

Large AI Model-Based Semantic Communications

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang, Feibo Peng, Yubo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua You, Xiaohu Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China Department of Computer Science Brunel University London United Kingdom School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Changchun Institute of Technology China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

Semantic communication (SC) is an emerging intelligent paradigm, offering solutions for various future applications like metaverse, mixed reality, and the Internet of Everything. However, in current SC systems, the construction of the knowledge base (KB) faces several issues, including limited knowledge representation, frequent knowledge updates, and insecure knowledge sharing. Fortunately, the development of the large AI model (LAM) provides new solutions to overcome the above issues. Here, we propose a LAM-based SC framework (LAM-SC) specifically designed for image data, where we first apply the segment anything model (SAM)-based KB (SKB) that can split the original image into different semantic segments by universal semantic knowledge. Then, we present an attention-based semantic integration (ASI) to weigh the semantic segments generated by SKB without human participation and integrate them as the semanticaware image. Additionally, we propose an adaptive semantic compression (ASC) encoding to remove redundant information in semantic features, thereby reducing communication overhead. Finally, through simulations, we demonstrate the effectiveness of the LAM-SC framework and the possibility of applying the LAM-based KB in future SC paradigms. Copyright © 2023, The Authors. All rights reserved.

关键词： Latent semantic analysis

Using multiple reference audios and style embedding constraints for speech synthesis

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gong, Cheng Wang, Longbiao Ling, Zhenhua Zhang, Ju Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei China Co. Ltd Japan Advanced Institute of Science and Technology Ishikawa Japan

The end-to-end speech synthesis model can directly take an utterance as reference audio, and generate speech from the text with prosody and speaker characteristics similar to the reference audio. However, an appropriate acoustic embedding must be manually selected during inference. Due to the fact that only the matched text and speech are used in the training process, using unmatched text and speech for inference would cause the model to synthesize speech with low content quality. In this study, we propose to mitigate these two problems by using multiple reference audios and style embedding constraints rather than using only the target audio. Multiple reference audios are automatically selected using the sentence similarity determined by Bidirectional Encoder Representations from Transformers (BERT). In addition, we use "target" style embedding from a pre-trained encoder as a constraint by considering the mutual information between the predicted and "target" style embedding. The experimental results show that the proposed model can improve the speech naturalness and content quality with multiple reference audios and can also outperform the baseline model in ABX preference tests of style similarity. © 2021, CC BY.

关键词： Embeddings

Kidding bot: A chatbot against harassing phone calls 9

学校读者我要写书评

暂无评论

Kidding bot: A chatbot against harassing phone calls

2019 9th International Workshop on Computer Science and engineering, WCSE 2019

作者： Chen, Shihong Xu, Tianjiao Chen, Lu Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies Guangzhou China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China School of Business Guangdong University of Foreign Studies Guangzhou China

ISBN: (纸本)9789811416842

Nowadays, the majority of mobile phone users suffer from harassment calls. However, traditional way to intercept the harassment calls cannot reduce this annoying behavior. In this paper, we designed and developed Kidding bot: a chatbot to counterwork the harassment calls. When the user received the harassment calls, he could connect our Kidding bot server by call forwarding, then Kidding bot starts to talk with the harassers. Kidding bot is combined with Turing chatbot and a dual encoder specially added in sequence to sequence model. The anti-harassment telephone test result shows that Kidding bot based our model performed better than the two baselines: a single Turing chatbot and a chatbot based on Sequence-to-Sequence model. © WCSE 2019. All rights reserved.

关键词： Signal encoding

Reachable Distance Function for KNN Classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Shichao Li, Jiaye Li, Yangding School of Computer Science and Engineering Central South University Changsha410083 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China

Distance function is a main metrics of measuring the affinity between two data points in machine learning. Extant distance functions often provide unreachable distance values in real applications. This can lead to incorrect measure of the affinity between data points. This paper proposes a reachable distance function for KNN classification. The reachable distance function is not a geometric direct-line distance between two data points. It gives a consideration to the class attribute of a training dataset when measuring the affinity between data points. Concretely speaking, the reachable distance between data points includes their class center distance and real distance. Its shape looks like "Z," and we also call it a Z distance function. In this way, the affinity between data points in the same class is always stronger than that in different classes. Or, the intraclass data points are always closer than those interclass data points. We evaluated the reachable distance with experiments, and demonstrated that the proposed distance function achieved better performance in KNN classification. © 2021, CC BY-NC-ND.

关键词： Machine learning