检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Chen, Yaqi Zhang, Hao Yang, Xukui Zhang, Wenlin Qu, Dan School of Information Systems Engineering Information Engineering University China Laboratory for Advanced Computing and Intelligence Engineering China

ISBN: (纸本)9782493814104

Self-supervised models have demonstrated remarkable performance in speech processing by learning latent representations from large amounts of unlabeled data. Although these models yield promising results on low-resource languages, the computational expense of fine-tuning all model parameters is prohibitively high. Adapters offer a solution by incorporating lightweight bottleneck structures into pre-trained models, enabling efficient parameter adaptation for downstream tasks. However, randomly initialized adapters often underperform in low-resource scenarios, limiting their applicability in low-resource languages. To address this issue, we develop the Meta-Adapter for self-supervised models to obtain meta-initialized parameters that facilitate quick adaptation to low-resource languages. Extensive experiments on the Common Voice and FLEURS datasets demonstrate the superior performance of Meta-Adapters on 12 low-resource languages spanning four different language families. Moreover, Meta-adapters show better generalization and extensibility than traditional pretraining methods. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

Mining and Validating Belief-Based Agent Explanations 5th

Mining and Validating Belief-Based Agent Explanations

引用

Proceedings of the 5th International Workshop on EXTRAAMAS 2023

作者： Alelaimat, Ahmad Ghose, Aditya Dam, Hoa Khanh Decision Systems Lab School of Computing and Information Technology University of Wollongong Wollongong2522 Australia

ISBN: (纸本)9783031408779

Agent explanation generation is the task of justifying the decisions of an agent after observing its behaviour. Much of the previous explanation generation approaches can theoretically do so, but assuming the availability of explanation generation modules, reliable observations, and deterministic execution of plans. However, in real-life settings, explanation generation modules are not readily available, unreliable observations are frequently encountered, and plans are non-deterministic. We seek in this work to address these challenges. This work presents a data-driven approach to mining and validating explanations (and specifically belief-based explanations) of agent actions. Our approach leverages the historical data associated with agent system execution, which describes action execution events and external events (represented as beliefs). We present an empirical evaluation, which suggests that our approach to mining and validating belief-based explanations can be practical. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Inverse kinematics solution for a six-degree-of-freedom upper limb rehabilitation robot using deep learning models

引用

Neural computing and Applications 2025年第18期37卷 12991-13009页

作者： Shah, Muhammad Faizan Khan, Naveed Ahmad Jamwal, Prashant K. Chetty, Girija Goecke, Roland Hussain, Shahid School of Information Technology & Systems University of Canberra Canberra Australia Department of Electrical and Computer Engineering Nazarbayev University Astana Kazakhstan School of Systems and Computing University of New South Wales Canberra Australia

The inverse kinematics problem in serially manipulated upper limb rehabilitation robots implies the usage of the end-effector position to obtain the joint rotation angles. In contrast to the forward kinematics, there are no systematic approaches for solving the inverse kinematics problem. Furthermore, for some morphology of the upper limb rehabilitation robots, the inverse kinematics problem is particularly challenging to solve. Conventional methods to solve the inverse kinematics problem reported in the literature are computationally expensive. In the present work, we propose a deep learning-based model to acquire the joint angles for a given end-effector position. The proposed approach exhibits high efficacy in determining the joint angles for various target positions and can accurately predict the end-effector positions once trained, improving the ability of the upper limb rehabilitation robot to adapt to varying patient needs. Due to its improved capability and effectiveness to track positions, the proposed algorithm lays the foundation for the development of efficient controllers in future. © The Author(s) 2025.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

Parameter-efficient fine-tuning of Whisper for low-resource speech recognition 5

Parameter-efficient fine-tuning of Whisper for low-resource ...

引用

5th International Seminar on Artificial Intelligence, Networking and information Technology, AINIT 2024

作者： Liu, Yunpeng Qu, Dan School of Information Systems Engineering University of Information Engineering Laboratory For Advanced Computing and Intelligence Engineering Department of Artificial Intelligence Henan China Systems Engineering University of Information Engineering Laboratory For Advanced Computing and Intelligence Engineering Henan China

ISBN: (纸本)9798350385557

Limited data availability remains a significant challenge for Whisper's low-resource speech recognition performance, falling short of practical application requirements. While previous studies have successfully reduced the recognition error rates of target language speech through fine-tuning, a comprehensive exploration and analysis of Whisper's parameter-efficient fine-tuning capabilities, the advantages and disadvantages are still lacking. This paper aims to fill this gap by conducting comprehensive experimental exploration for Whisper's low-resource speech recognition performance using two parameter-efficient fine-tuning strategies with limited supervised data from multiple low-resource languages. The results and analysis demonstrate that all fine-tuning strategies explored in this paper significantly enhance Whisper's performance. However, different strategies vary in their suitability and practical effectiveness, highlighting the need for careful selection based on specific use cases and resources available. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Leveraging Imperfect Explanations for Plan Recognition Problems 5th

Leveraging Imperfect Explanations for Plan Recognition Prob...

引用

Proceedings of the 5th International Workshop on EXTRAAMAS 2023

作者： Alelaimat, Ahmad Ghose, Aditya Dam, Hoa Khanh Decision Systems Lab School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia

ISBN: (纸本)9783031408779

Open environments require dynamic execution of plans where agents must engage in settings that include, for example, re-planning, plan reusing, plan repair, etc. Hence, real-life Plan Recognition (PR) approaches are required to deal with different classes of observations (e.g., exogenous actions, switching between activities, and missing observations). Many approaches to PR consider these classes of observations, but none have dealt with them as deliberated events. Actually, using existing PR methods to explain such classes of observations may generate only so-called imperfect explanations (plans that partially explain a sequence of observations). Our overall approach is to leverage (in the sense of plan editing) imperfect explanations by exploiting new classes of observations. We use the notation of capabilities in the well-known Belief-Desire-Intention (BDI) agents programming as an ideal platform to discuss our work. To validate our approach, we show the implementation of our approach using practical examples from the Monroe Plan Corpus. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

LPL-VIO: monocular visual-inertial odometry with deep learning-based point and line features

引用

Neural computing and Applications 2024年第36期36卷 23061-23075页

作者： Liu, Changxiang Yang, Qinhan Yu, Hongshan Fu, Qiang Akhtar, Naveed College of Electrical and Information Engineering School of Robotics Quanzhou Institute of Industrial Design and Machine Intelligence Innovation Hunan University Changsha China School of Computing and Information Systems The University of Melbourne VIC Australia

Visual-inertial SLAM (VINS) has garnered substantial interest in the field of mobile robotics due to its robustness and cost-effectiveness. The incorporation of both point and line features in visual SLAM has shown significant performance improvements compared to relying solely on point features. Furthermore, learning-based features consistently outperform traditional hand-crafted features across a diverse range of tasks. Leveraging all these observations, we propose a novel deep learning technique, termed learning-based point and line visual-inertial odometry (LPL-VIO), which is aimed to enhance robustness and performance of traditional systems. LPL-VIO takes a 2-stage approach, including a deep learning front-end and a traditional nonlinear optimization back-end. In the first stage (front-end), we employ proposed networks for points and lines to extract and track deep learning-based point and line features in visual images, while implementing IMU preintegration. In the second stage (back-end), we adopt a sliding window strategy to tightly couple point and line re-projection errors with IMU preintegration residuals. These residuals are optimized using bundle adjustment for precise global pose estimation. Extensive experiments are conducted on both public EuRoC datasets and our own real-world dataset collected in challenging outdoor environments. Qualitative and quantitative results show that our method exhibits strong competitiveness compared with the existing point–line techniques, and outperforms the popular VINS-Mono. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Deep learning on medical image analysis

引用

CAAI Transactions on Intelligence Technology 2025年第1期10卷 1-35页

作者： Jiaji Wang Shuihua Wang Yudong Zhang School of Computing and Mathematical Sciences University of LeicesterLeicesterUK Department of Biological Sciences Xi'an Jiaotong-Liverpool UniversitySuzhouJiangsuChina Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia School of Computer Science and Engineering Southeast UniversityNanjingJiangsuChina

Medical image analysis plays an irreplaceable role in diagnosing,treating,and monitoring various *** neural networks(CNNs)have become popular as they can extract intricate features and patterns from extensive *** paper covers the structure of CNN and its advances and explores the different types of transfer learning strategies as well as classic pre-trained *** paper also discusses how transfer learning has been applied to different areas within medical image *** comprehensive overview aims to assist researchers,clinicians,and policymakers by providing detailed insights,helping them make informed decisions about future research and policy initiatives to improve medical image analysis and patient outcomes.

关键词： CNN deep learning medical image transfer learning

来源：评论

学校读者我要写书评

暂无评论

Efficient 3D Hilbert Curve Encoding and Decoding Algorithms

引用

Chinese Journal of Electronics 2022年第2期31卷 277-284页

作者： JIA Lianyin LIANG Binbin LI Mengjuan LIU Yong CHEN Yinong DING Jiaman Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Library Yunnan Normal University School of Information Science and Engineering Guangxi University for Nationalities School of Computing Informatics and Decision Systems Arizona State University

Hilbert curve describes a one-to-one mapping between multidimensional space and 1 D *** traditional 3D Hilbert encoding and decoding algorithms work on order-wise manner and are not aware of the difference between different input data and spend equivalent computing costs on them, thus resulting in a low efficiency. To solve this problem, in this paper we design efficient 3D state views for fast encoding and decoding. Based on the state views designed, a new encoding algorithm(JFK-3HE) and a new decoding algorithm(JFK-3HD) are proposed. JFK-3HE and JFK-3HD can avoid executing iteratively encoding or decoding each order by skipping the first 0 s in input data, thus decreasing the complexity and improving the efficiency. Experimental results show that JFK-3HE and JFK-3HD outperform the state-of-the-arts algorithms for both uniform and skew-distributed data.

关键词： order-wise manner multidimensional space encoding state-of-the-arts algorithms encoding algorithm parallel algorithms JFK-3HE statistical distributions decoding solid modelling design efficient 3D JFK-3HD traditional 3D Hilbert encoding equivalent computing costs different input data decoding algorithm Hilbert curve state views iterative methods

来源：评论

学校读者我要写书评

暂无评论

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

引用

Neural computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Models in Power Generation for Energy Consumption Prediction 4

Artificial Intelligence Models in Power Generation for Energ...

引用

4th International Conference on Emerging Trends in Networks and Computer Communications, ETNCC 2024

作者： Tan, Lit Yang Chen Kwan, Charis Shwu Ajibade, Samuel-Soma M. Ramly, Athirah Mohd School of Engineering and Technology Sunway University Department of Computing and Information Systems Selangor Malaysia School of Architecture Computing and Engineering University of East London Department of Computing London United Kingdom

ISBN: (纸本)9798350353266

The incorporation of artificial intelligence (AI) into power-related applications signifies a new and unexplored domain in machine learning for predicting power generation. This novel method utilizes prediction models, often used in different fields, to predict energy-related patterns, providing a unique and specialized viewpoint. The synergy of academicians, AI experts, and industry professionals in the energy sector has resulted in the creation of customized AI models to optimize operational efficiency. By customizing various AI models to suit the distinct attributes of energy scenarios and datasets, these models are positioned to transform energy management methods. This study examines the utilization of AI models to enhance energy efficiency in power generation in Malaysia. The project seeks to predict future power consumption in various sectors, analyze growth rates, and identify sectors with investment potential by developing a Linear Regression model. In addition, a thorough power plan is developed using the estimated energy usage. A comparative analysis is performed to determine the most appropriate model for this particular scenario, which will improve decision-making in the energy sector. The results of this study present promising opportunities for further investigation. By broadening the study's focus to encompass a broader array of AI models and their assessment of performance, it is possible to gain useful insights for predicting power generation. Furthermore, the integration of real-time data streams and the inclusion of feedback loops in the AI models could improve their ability to adapt and increase their accuracy as time progresses. © 2024 IEEE.

关键词： Prediction models

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：