检索结果-内蒙古大学图书馆

23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024

作者： Wu, Xiaoliang Feng, Qilong Huang, Ziyun Xu, Jinhui Wang, Jianxin School of Computer Science and Engineering Central South University Xiangjiang Laboratory Changsha China Department of Computer Science and Software Engineering Penn State Erie The Behrend College Erie United States Department of Computer Science and Engineering State University of New York at Buffalo Buffalo United States Hunan Provincial Key Lab on Bioinformatics Central South University Xiangjiang Laboratory Changsha China

Fair clustering problems have been paid lots of attention recently. In this paper, we study the k-Center problem under the group fairness and data summarization fairness constraints, denoted as Group Fair k-Center (GFkC) and Data Summarization Fair k-Center (DSFkC), respectively, in the massively parallel computational (MPC) distributed model. The previous best results for the above two problems in the MPC model are a 9-approximation with violation 7 (WWW 2022) and a (17 + ∊)-approximation without fairness violation (ICML 2020), respectively. In this paper, we obtain a (3 + ∊)- approximation with violation 1 for the GFkC problem in the MPC model, which is almost as accurate as the best known approximation ratio 3 with violation 1 for the sequential algorithm of the GFkC problem. Moreover, for the DSFkC problem in the MPC model, we obtain a (4 + ∊)-approximation without fairness violation, which is very close to the best known approximation ratio 3 for the sequential algorithm of the DSFkC problem. Empirical experiments show that our distributed algorithms perform better than existing state-of-the-art distributed methods for the above two problems. © 2024 International Foundation for Autonomous Agents and Multiagent Systems.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Autoencoder-Based Deep Neural Architecture for Epileptic Seizures Classification 1

引用

11th International Conference on Soft Computing for Problem Solving, SocProS 2022

作者： Mahapatra, Monalisha Barbhuiya, Tariq Arshad Nandy, Anup Machine Intelligence and Bio-motion Lab Department of Computer Science and Engineering National Institute of Technology Rourkela India

ISBN: (数字)9789811965258

ISBN: (纸本)9789811965241

This paper discusses a deep neural network architecture of Long Short-Term Memory (LSTM) with an autoencoder-based encoder-decoder scheme. Primarily, the proposed structure determines the time-domain features of electroencephalography (EEG) signals, which is subsequently trained to acquire reduced dimensions of EEG features. Later, these features are provided to a one-dimensional (1D) Convolutional Neural Network (CNN) for classification. The effectiveness of the proposed model is corroborated on the public benchmark Kaggle Epileptic Seizure Recognition dataset. The dataset consists of five classes corresponding to five different health states;comprising a seizure state (subjects with epileptic seizure) and four normal states (subjects without seizure). In this work, the binary classification task of epileptic seizure is performed. The outcomes exhibit that the proposed architecture attains a recognition accuracy of 92.47% on this task. Additionally, a relative study has been carried out with other standard neural models, specifically, deep neural networks (DNN), and CNN. Few machine learning models, namely, logistic regression (LR),random forest (RF), and K-Nearest Neighbors (KNN) are also studied for comparison. It further substantiates the dominance of the proposed model. The outcomes have proven the purpose of this study to demonstrate the efficacy of the proposed model in EEG epileptic seizure classification. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

computer-Aided Leaf Disease Classification Based on Logistic Regression and Transfer Learning Approach

Computer-Aided Leaf Disease Classification Based on Logistic...

引用

International Conference on Machine Vision and Augmented Intelligence, MAI 2022

作者： Saikia, Trishna Hansdah, Malho Singh, Koushlendra Kumar Machine Vision and Intelligence Lab Department of Computer Science and Engineering National Institute of Technology Jamshedpur Jamshedpur India

ISBN: (纸本)9789819901883

Over 60% of the total Indian population depends on agriculture. It is one of the key fields of Indian Economy which comes up with 17%–18% of total GDP. Therefore, it is very important to detect and classify plant leaf diseases properly in agricultural field. Sometimes, it is difficult to detect and identify the disease correctly by naked eye. So, a computer-aided system is very much necessary to identify the disease accurately. Moreover, it is also helpful in large farms of crops as it reduces great work of monitoring each plant individually. In this research study, we have implemented three different techniques, among those one is Logistic Regression (LR) and another two techniques are the combination of transfer learning method with Support Vector Machine (SVM). For all the techniques, we have used Adam optimizer. For our experiment, we have utilized a subset of PlantVillage datasets. We have compared all the methods and listed in a table. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Harnessing Large Language Models for Text-Rich Sequential Recommendation 24

Harnessing Large Language Models for Text-Rich Sequential Re...

引用

33rd ACM Web Conference, WWW 2024

作者： Zheng, Zhi Chao, WenShuo Qiu, Zhaopeng Zhu, Hengshu Xiong, Hui School of Data Science University of Science and Technology of China China Career Science Lab BOSS Zhipin China China China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9798400701719

Recent advances in Large Language Models (LLMs) have been changing the paradigm of Recommender Systems (RS). However, when items in the recommendation scenarios contain rich textual information, such as product descriptions in online shopping or news headlines on social media, LLMs require longer texts to comprehensively depict the historical user behavior sequence. This poses significant challenges to LLM-based recommenders, such as over-length limitations, extensive time and space overheads, and suboptimal model performance. To this end, in this paper, we design a novel framework for harnessing Large Language Models for Text-Rich Sequential Recommendation (LLM-TRSR). Specifically, we first propose to segment the user historical behaviors and subsequently employ an LLM-based summarizer for summarizing these user behavior blocks. Particularly, drawing inspiration from the successful application of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) models in user modeling, we introduce two unique summarization techniques in this paper, respectively hierarchical summarization and recurrent summarization. Then, we construct a prompt text encompassing the user preference summary, recent user interactions, and candidate item information into an LLM-based recommender, which is subsequently fine-tuned using Supervised Fine-Tuning (SFT) techniques to yield our final recommendation model. We also use Low-Rank Adaptation (LoRA) for Parameter-Efficient Fine-Tuning (PEFT). We conduct experiments on two public datasets, and the results clearly demonstrate the effectiveness of our approach. © 2024 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

ZPP: A Dynamic Technique to Eliminate Cache Pollution in NoC based MPSoCs

ZPP: A Dynamic Technique to Eliminate Cache Pollution in NoC...

引用

作者： Deb, Dipika Jose, John Indian Institute of Technology Guwahati Mars Lab Department of Computer Science and Engineering Assam Guwahati781039 India

Data prefetching efficiently reduces the memory access latency in NUCA architectures as the Last Level Cache (LLC) is shared and distributed across multiple cores. But cache pollution generated by prefetcher reduces its efficiency by causing contention for shared resources such as LLC and the underlying network. The paper proposes Zero Pollution Prefetcher (ZPP) that eliminates cache pollution for NUCA architecture. For this purpose, ZPP uses L1 prefetcher and places the prefetched blocks in the data locations of LLC where modified blocks are stored. Since modified blocks in LLC are stale and request for such blocks are served from the exclusively owned private cache, their space unnecessary consumes power to maintain such stale data in the cache. The benefits of ZPP are (a) Eliminates cache pollution in L1 and LLC by storing prefetched blocks in LLC locations where stale blocks are stored. (b) Insufficient cache space is solved by placing prefetched blocks in LLC as LLCs are larger in size than L1 cache. This helps in prefetching more cache blocks, thereby increasing prefetch aggressiveness. (c) Increasing prefetch aggressiveness increases its coverage. (d) It also maintains an equivalent lookup latency to L1 cache for prefetched blocks. Experimentally it has been found that ZPP increases weighted speedup by 2.19x as compared to a system with no prefetching while prefetch coverage and prefetch accuracy increases by 50%, and 12%, respectively compared to the baseline.1 © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Pseudo-labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5475-5488页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing101408 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science 314100 China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic-like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. First, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic-like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. © 1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

TASK-CUSTOMIZED MASKED AUTOENCODER VIA MIXTURE OF CLUSTER-CONDITIONAL EXPERTS 11

TASK-CUSTOMIZED MASKED AUTOENCODER VIA MIXTURE OF CLUSTER-CO...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Liu, Zhili Chen, Kai Han, Jianhua Hong, Lanqing Xu, Hang Li, Zhenguo Kwok, James T. Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Huawei Noah's Ark Lab Canada

Masked Autoencoder (MAE) is a prevailing self-supervised learning method that achieves promising results in model pre-training. However, when the various downstream tasks have data distributions different from the pre-training data, the semantically irrelevant pre-training information might result in negative transfer, impeding MAE's scalability. To address this issue, we propose a novel MAE-based pre-training paradigm, Mixture of Cluster-conditional Experts (MoCE), which can be trained once but provides customized pre-training models for diverse downstream tasks. Different from the mixture of experts (MoE), our MoCE trains each expert only with semantically relevant images by using cluster-conditional gates. Thus, each downstream task can be allocated to its customized model pre-trained with data most similar to the downstream data. Experiments on a collection of 11 downstream tasks show that MoCE outperforms the vanilla MAE by 2.45% on average. It also obtains new state-of-the-art self-supervised learning results on detection and segmentation. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Facial Image Manipulation Detection Using Cellular Automata and Transfer Learning 1

引用

The 9th International Conference on Mathematics and Computing (ICMC 2023)

作者： Chakraborty, Shramona Chowdhury, Dipanwita Roy Crypto Research Lab Department of Computer Science and Engineering Indian Institute of Technology Kharagpur721 302 India

ISBN: (数字)9789819930807

ISBN: (纸本)9789819930791

In digital media forensics, detecting manipulated facial images is a crucial topic. With the advancement of synthetic face generation technologies, different types of face morphing have raised serious concerns in social media implications. Hence, we have worked on detecting the manipulated face image thoroughly. Despite just using a multi-task learning approach, we propose a facial image manipulation detection scheme using cellular automata (CA) and transfer learning (TL) as feature extractors to enhance the classifier model’s feature maps. The extracted features point out the informative regions to refine the binary classification power. We have collected datasets that contain diverse facial forgeries. We have also built our dataset, keeping every possible morphing way in mind. We have analyzed the datasets thoroughly and demonstrated that using a combination of CA and TL improves manipulated fake detection on different morphing techniques. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Marine Stability: A Review of Cutting-Edge Gyro Stabilizer Designs and Techniques for Vessels

引用

IEEE Access 2025年 13卷 89542-89555页

作者： Rahiman, Wan Ghazali, Mohamad Hazwan Mohd Mahmood, Iskandar Al-Thani Universiti Sains Malaysia Engineering Campus School of Electrical and Electronic Engineering Penang Nibong Tebal14300 Malaysia Daffodil International University Daffodil Robotics Lab Department of Computer Science and Engineering Dhaka1216 Bangladesh Universiti Kebangsaan Malaysia Faculty of Engineering and Built Environment Department of Mechanical and Manufacturing Engineering Selangor Bangi43600 Malaysia PETRONAS Research Sdn Bhd Selangor Kajang43000 Malaysia

Advancement in marine vessel stabilization technologies has greatly improved the safety and comfort for crews, cargo, and passengers, while also lowering the risk of capsizing. Marine vessels operating in open waters experience disturbances from unpredictable waves and strong winds, leading to instability and potential accidents. To mitigate these risks, stabilizers are integrated into ships to maintain stability, safety, and seaworthiness. As modern vessels evolve, stabilizers play an increasingly vital role, with gyro stabilizers emerging as a highly effective solution for mitigating roll motion without external appendages. This paper provides a comprehensive review of gyro stabilizer designs and techniques, covering their historical development, mathematical modeling, advantages, limitations, and case studies. A review of current research highlights a strong emphasis on simulating gyro stabilizer control systems, demonstrating their potential in enhancing vessel stability. However, key challenges persist, including accurate wave moment prediction during the design phase and gyroscopic drift, which can impact long-term performance and efficiency. Despite these challenges, recent advancements in control algorithms and optimization techniques have improved gyro stabilizer adaptability under varying sea conditions. By exploring the latest developments, this review serves as a valuable reference for researchers, engineers, and maritime professionals seeking to advance marine stabilization technologies. The findings underscore the potential of next-generation gyro stabilizers, including fiber optic gyros, in achieving higher precision, stability, and operational efficiency. © 2013 IEEE.

关键词： Warships

来源：评论

学校读者我要写书评

暂无评论

End-to-End Multi-View Structure-from-Motion with Hypercorrelation Volume 3

End-to-End Multi-View Structure-from-Motion with Hypercorrel...

引用

3rd IEEE International Conference on Power, Electronics and computer Applications, ICPECA 2023

作者： Chen, Qiao Poullis, Charalambos Concordia University Immersive and Creative Technologies Lab Department of Computer Science and Software Engineering MontrealQC Canada

ISBN: (纸本)9781665472784

Image-based 3D reconstruction is one of the most important tasks in computer Vision with many solutions proposed over the last few decades. The objective is to extract metric information i.e. the geometry of scene objects directly from images. These can then be used in a wide range of applications such as film, games, virtual reality, etc. Recently, deep learning techniques have been proposed to tackle this problem. They rely on training on vast amounts of data to learn to associate features between images through deep convolutional neural networks and have been shown to outperform traditional procedural techniques. In this paper, we improve on the state-of-the-art two-view structure-from-motion(SfM) approach of [11] by incorporating 4D correlation volume for more accurate feature matching and reconstruction. Furthermore, we extend it to the general multi- view case and evaluate it on the complex benchmark dataset DTU [5]. Quantitative evaluations and comparisons with state-of-the-art multi-view 3D reconstruction methods demonstrate its superiority in terms of the accuracy of reconstructions. © 2023 IEEE.

关键词： computer vision

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：