检索结果-内蒙古大学图书馆

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Komal Pokale Shiv Nath Chaudhri Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology DMIHER (DU) Maharashtra India Department of Computer Science and Design Faculty of Engineering and Technology DMIHER (DU) Maharashtra India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Fine-tuning a pre-trained model is a type of transfer learning: a pre-trained model that works on a large dataset is transferred onto a particular task or a smaller dataset, such as a hyperspectral image. The efficacy of such a technique is most visible in hyperspectral imaging since the data is usually too high-dimensional with a very scarce number of available annotated datasets. By using the pre-trained model, fine-tuning enables spatial and spectral features to be captured with lower computational overheads than fully training models. Domain adaptation approaches, including feature alignment and adversarial training, are also adapted to overcome limitations caused by the domain shift phenomenon due to the variability of the sensor, environmental changes, and temporal changes. Hyperspectral imaging is applied in diverse fields, including agriculture, environmental monitoring, mineral exploration, defense, medical diagnostics, and food quality assessment. Such applications are unique in the sense that HSI can integrate spatial and spectral information to achieve detailed material analysis. Advanced learning techniques will enhance the effectiveness of HSI models in real-world scenarios.

关键词： Training Deep learning Adaptation models Computational modeling Transfer learning data models Agriculture Medical diagnosis Environmental monitoring Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Categorization of data Analytics Projects in Smart Manufacturing

Categorization of Data Analytics Projects in Smart Manufactu...

引用

IEEE International Conference on Big data

作者： Matthias Pohl Christian Haertel Daniel Staegemann Klaus Turowski Institute of Data Science German Aerospace Center (DLR) Jena Germany Faculty of Computer Science Otto-von-Guericke-University Magdeburg Germany

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

The emergence of the Internet of Things and Industry 4.0 has transformed production processes, with data analytics and AI playing key roles. Smart Manufacturing projects often appear ambiguous due to interconnected terms. data analytics is foundational, involving specific goals, evaluation of current infrastructure, and small-scale pilot projects. Having a structured map tailored to Smart Manufacturing is invaluable for identifying an optimal starting point for data analytics projects. The primary objective is to provide a comprehensive overview of data analytics in the context of Smart Manufacturing and to answer the research question regarding identified categories and data analytics projects.

关键词： data analysis Production Big data Fourth Industrial Revolution Object recognition Internet of Things Artificial intelligence Smart manufacturing Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

QiMINT: Quantum-Inspired Mobile Intelligence - Advancing Complex Signal Processing with Machine Learning

QiMINT: Quantum-Inspired Mobile Intelligence - Advancing Com...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Vinothkumar Kolluru E. Helen Parimala Kokilavani T Sunil Raj Y Bastin Jesuraj Afrig Aminuddin Department of Data Science Stevens Institute of Technology NJ USA Department of Computer Science Gitam Deemed to be University Bangalore India Department of Computer Science School of Sciences Christ (Deemed) University Bangalore India Department of Data Science St. Xavier's College (Autonomous) Palayamkottai India Department of Computer Science Mother Theresa Arts and Science College Theni Tamilnadu India Department of Information System Faculty of Computer Science Universitas Amikom Yogyakarta Sleman Indonesia

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Integrating mobile intelligence with quantum-inspired machine learning (QiML) opens space for challenging mobile signal processing tasks. By utilizing superposition and entanglement, quantum computing principles, QiML boosts the agility of mobile devices by allowing real-time data processing, pattern recognition, and decision making. This work introduces Quantum-Inspired Mobile Intelligence (QiMINT) a new mobile computing framework that integrates quantum-inspired designs with classical machine learning, which increases mobile devices' accuracy, latency, and energy efficiency. Results show that medical QiML based models exceeded traditional machine learning methods in most key performance indicators. The quantum convolutional neural network (QCNN) achieved an accuracy of 92.3% in contrast with the CNNs' 87.5%, but with a processing time of 80 ms as to 120 ms, energy consumption of 10 mJ in comparison to the CNNs' 15mJ. Also, quantum-inspired random forests lowered processing delay by 40%, sustaining superior accuracy than the classical-base system. These results demonstrate that QiML can effectively balance computation complexity while making it suitable for edge computing, IoT, and mobile intelligence systems.

关键词： Quantum computing Accuracy Decision making Machine learning Signal processing Real-time systems Mobile handsets Pattern recognition Optimization Edge computing

来源：评论

学校读者我要写书评

暂无评论

MTC-Net: Multi-granular Temporal Cascade Learning for Weakly Supervised Video Anomaly Detection

MTC-Net: Multi-granular Temporal Cascade Learning for Weakly...

引用

Image Processing, computer Vision and Machine Learning (ICICML), International Conference on

作者： Minghe Xu Dalin Li Rouying Wu Hui Ding Kexiang Huang Chiawei Chu Faculty of Data Science City University of Macau Macau SAR China School of Big Data Zhuhai College of Science and Technology Zhuhai China School of Computer Science Zhuhai College of Science and Technology Zhuhai China Faculty of Innovation Engineering FIE Macau University of Science and Technology Macau SAR China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

In this paper, we propose a novel Multi-granular Temporal Cascade Learning framework (MTC-Net), which effectively combines coarse-grained and fine-grained detection capabilities. By leveraging visual features extracted from CLIP and integrating visual-language associations, MTC-Net addresses the limitations of existing methods and achieves outstanding performance across multiple benchmark datasets. Furthermore, we incorporate multiscale temporal feature fusion and an improved attention mechanism into the framework, and introduce a feature consistency-based auxiliary loss to enhance the model's focus on anomalous patterns and generalization ability. Extensive experiments on the XD-Violence and UCF-Crime datasets demonstrate that MTC-Net outperforms both semi-supervised and classification-based weakly supervised methods across all evaluation metrics. For the coarse-grained Weakly Supervised Video Anomaly Detection (WSVAD) task, MTC-Net achieves an AP of 84.83% on XD-Violence and an AUC of 75.23% on UCF-Crime, significantly surpassing current state-of-the-art methods. In the more challenging fine-grained WSVAD task, MTC-Net achieves a 13.1% improvement in average precision over previous methods. These results validate the effectiveness of our approach, highlighting MTC-Net's potential to advance the field of video anomaly detection through the efficient use of weak supervision, multiscale temporal feature fusion, and multimodal feature integration.

关键词： Location awareness computer vision Visualization Weak supervision Attention mechanisms Accuracy Feature extraction Robustness Anomaly detection Optimization

来源：评论

学校读者我要写书评

暂无评论

Graph Compression for Adjacency-Matrix Multiplication

引用

SN computer science 2022年第3期3卷 193页

作者： Francisco, Alexandre P. Gagie, Travis Köppl, Dominik Ladra, Susana Navarro, Gonzalo INESC-ID / IST Universidade de Lisboa Lisbon Portugal Faculty of Computer Science Dalhousie University Halifax NS Canada M & D Data Science Center Tokyo Medical and Dental University Tokyo Japan CITIC Universidade da Coruña Coruña Spain Millennium Institute for Foundational Research on Data Santiago Chile Department of Computer Science University of Chile Santiago Chile

Computing the product of the (binary) adjacency matrix of a large graph with a real-valued vector is an important operation that lies at the heart of various graph analysis tasks, such as computing PageRank. In this paper, we show that some well-known webgraph and social graph compression formats are computation-friendly, in the sense that they allow boosting the computation. We focus on the compressed representations of (a) Boldi and Vigna and (b) Hernández and Navarro, and show that the product computation can be conducted in time proportional to the compressed graph size. Our experimental results show speedups of at least 2 on graphs that were compressed at least 5 times with respect to the original. © 2022, The Author(s).

关键词： Bicliques data compression Matrix multiplication Webgraph

来源：评论

学校读者我要写书评

暂无评论

Formation of Research Area for Malaysian Urban data Centre and Waste Heat Recovery

Formation of Research Area for Malaysian Urban Data Centre a...

引用

2022 International Conference on Digital Transformation and Intelligence, ICDI 2022

作者： Othman, Marini Maidin, Siti Sarah Suliman, Azizah Zakaria, Nur Zakri Nassar, Dua' Al-Ghaili, Abbas M. Inti International University Faculty of Data Science and Information Technology Nilai Malaysia Independent Researcher Sepang Malaysia Princess Nourah Bint Abdulrahman University Faculty of Computer & Information Science Riyadh Saudi Arabia Malaysia

ISBN: (纸本)9798350397000

The realization that the energy consumption due to digital application will continue to rise significantly while climate change has persistently demand efficiency in the energy use, has triggered data centers to become more accountable in shouldering the task to operate sustainably. Green strategy for data centers, among others, should look at improving treatment of waste heat generated by their operation and cooling process. While intensive efforts are taking place in Scandinavian countries, many countries are yet to follow in their steps. A case study involving three urban data centres in Malaysia is conducted to gain insight on their potential in implementing waste heat recovery for utilization by relevant systems within their vicinity. It is found that the data centers have attained favourable in term of safety, security and reliability. However, there are a lot to be desired from the aspect of energy efficiency. A way forward suggests for further study to explore adoption and innovation of waste heat recycling models to improve the performance of Malaysian urban data centers in alignment to improve use and reuse of energy whilst making them more climate-neutral. © 2022 IEEE.

关键词： Waste heat

来源：评论

学校读者我要写书评

暂无评论

MI-MCF: A Mutual Information-Based Multilabel Causal Feature Selection

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年第6期36卷 9864-9878页

作者： Lin Ma Liang Hu Yonghao Li Weiping Ding Wanfu Gao Department of Computer Science and Technology Jilin University Changchun Jilin China School of Computing and Artificial Intelligence Southwestern University of Finance and Economics Chengdu Sichuan China School of Artificial Intelligence and Computer Science Nantong University Nantong China Faculty of Data Science City University of Macau Macau China

Multilabel causal feature selection has attracted extensive attention in recent years. Current multilabel causal feature selection algorithms typically employ existing Markov Blanket (MB) search methods for the initial construction of the MB, followed by further optimization. These methods generally treat labels and features as equally weighted nodes during the MB construction process. However, the search for spouse sets often involves extensive conditional independence (CI) tests, which are time-consuming. Furthermore, they fail to consider the distinct contributions of labels and features to the target nodes. Information theory is often used to evaluate the contributions of nodes. Inspired by this, we carry out a theoretical investigation into the causal relationships within multilabel datasets and propose the mutual information-based multilabel causal feature selection (MI-MCF) method. First, MI-MCF employs MI and conditional MI (CMI) instead of CI test when constructing the MB of labels without incurring significant time overhead. Then, MI-MCF uses MI to compare the contributions of features and labels to the target nodes. This helps identify which nodes should be retained when recovering features hindered by strong label correlation. Finally, MI-MCF eliminates spurious nodes through a symmetry check. Experiments on real-world datasets demonstrate that MI-MCF can autonomously determine the optimal number of selected features and consistently outperform compared methods. The code is available at https://***/malinjlu/MI-MCF .

关键词： Feature extraction Correlation Learning systems Redundancy Optimization Mutual information Manifolds Electronic mail Computational complexity Accuracy

来源：评论

学校读者我要写书评

暂无评论

Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs

arXiv

引用

arXiv 2024年

作者： Filmus, Yuval Hanneke, Steve Mehalel, Idan Moran, Shay The Henry and Marilyn Taub Faculty of Computer Science Technion Israel Faculty of Mathematics Technion Israel Department of Computer Science Purdue University United States Faculty of Data and Decision Sciences Technion Israel Google Research Israel

Consider the domain of multiclass classification within the adversarial online setting. What is the price of relying on bandit feedback as opposed to full information? To what extent can an adaptive adversary amplify the loss compared to an oblivious one? To what extent can a randomized learner reduce the loss compared to a deterministic one? We study these questions in the mistake bound model and provide nearly tight answers. We demonstrate that the optimal mistake bound under bandit feedback is at most O(k) times higher than the optimal mistake bound in the full information case, where k represents the number of labels. This bound is tight and provides an answer to an open question previously posed and studied by Daniely and Helbertal [’13] and by Long [’17,’20], who focused on deterministic learners. Moreover, we present nearly optimal bounds of Θ˜(k) on the gap between randomized and deterministic learners, as well as between adaptive and oblivious adversaries in the bandit feedback setting. This stands in contrast to the full information scenario, where adaptive and oblivious adversaries are equivalent, and the gap in mistake bounds between randomized and deterministic learners is a constant multiplicative factor of 2. In addition, our results imply that in some cases the optimal randomized mistake bound is approximately the square-root of its deterministic parallel. Previous results show that this is essentially the smallest it can get. Copyright © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Plastic Waste Hotspot Detection System and Its Application to Measuring Environmental Improvement

A Plastic Waste Hotspot Detection System and Its Application...

引用

IEEE International Symposium on Consumer Electronics (ISCE)

作者： Shiori Sasaki Ryota Nakamura Prasetyo Wibowo Department of Data Science Musashino University Tokyo Japan Faculty of Data Science Musashino University Tokyo Japan Department of Informatics and Computer Engineering Politeknik Elektronika Negeri Surabaya Indonesia

ISBN: (数字)9798350365191

ISBN: (纸本)9798350365207

This paper describes a Plastic Waste Hotspot Detection System which has been developed in an international collaborative research project to realize an “Environmental AI-Human Actions integration” with marine plastic waste reduction actions. In this project, various local conditions are obtained to the system to realize an environmentally resilient society. The nature conservation activities such as marine plastic waste collection and reduction actions are implemented based on these conditions. In the process of integration of Environmental AI and Human Actions, the effects of these activities and activists' contribution to environmental improvement and global-scale knowledge are accumulated, shared, analyzed, and visualized through global-scale analysis. This paper describes the Plastic Waste Hotspot Detection system as one of the systems that integrate AI systems and human actions. This paper examines the feasibility and effectiveness of the system through the fieldwork tests in Phuket, Thailand and Surabaya, Indonesia.

关键词： Visualization Collaboration Artificial intelligence Environmental management Plastic waste

来源：评论

学校读者我要写书评

暂无评论

SP-DSTS-MIMO Scheme-Aided H.266 for Reliable High data Rate Mobile Video Communication

引用

computers, Materials & Continua 2023年第1期74卷 995-1010页

作者： Khadem Ullah Nasru Minallah Durre Nayab Ishtiaque Ahmed Jaroslav Frnda Jan Nedoma Department of Computer Systems Engineering University of Engineering and Technology PeshawarPeshawar25000Pakistan National Centre in Big Data and Cloud Computing University of Engineering and Technology Peshawar(NCBC-UETP)Peshawar25000Pakistan Department of Quantitative Methods and Economic Informatics Faculty of Operation and Economics of Transport and CommunicationsUniversity of Zilina01026ZilinaSlovakia Department of Telecommunications Faculty of Electrical Engineering and Computer ScienceVSB-Technical University of OstravaOstrava-PorubaCzech Republic

With the ever growth of Internet users,video applications,and massive data traffic across the network,there is a higher need for reliable bandwidth-efficient multimedia *** Video Coding(VVC/H.266)is finalized in September 2020 providing significantly greater compression efficiency compared to Highest Efficient Video Coding(HEVC)while providing versatile effective use for Ultra-High Definition(HD)*** article analyzes the quality performance of convolutional codes,turbo codes and self-concatenated convolutional(SCC)codes based on performance metrics for reliable future video *** advent of turbo codes was a significant achievement ever in the era of wireless communication approaching nearly the Shannon *** codes are operated by the deployment of an interleaver between two Recursive Systematic Convolutional(RSC)encoders in a parallel *** RSC encoders may be operating on the same or different architectures and code *** proposed work utilizes the latest source compression standards H.266 and H.265 encoded standards and Sphere Packing modulation aided differential Space Time Spreading(SP-DSTS)for video transmission in order to provide bandwidth-efficient wireless video ***,simulation results show that turbo codes defeat convolutional codes with an averaged E_(b)/N_(0) gain of 1.5 dB while convolutional codes outperformcompared to SCC codes with an E_(b)/N_(0) gain of 3.5 dBatBit ErrorRate(BER)of 10−*** Peak Signal to Noise Ratio(PSNR)results of convolutional codes with the latest source coding standard of H.266 is plotted against convolutional codes with H.265 and it was concluded H.266 outperform with about 6 dB PSNR gain at E_(b)/N_(0) value of 4.5 dB.

关键词： H.265 RSC turbo codes SCC SP-DSTS BP-CNN BER PSNR

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：