检索结果-内蒙古大学图书馆

IEEE Workshop on Applications of computer Vision (WACV)

作者： Qianyi Liu Siqi Zhang Yanyuan Qiao Junyou Zhu Xiang Li Longteng Guo Qunbo Wang Xingjian He Qi Wu Jing Liu Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Department of Computer Science and Technology Tongji University Australian Institute for Machine Learning The University of Adelaide

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Goal-Oriented Vision-and-Language Navigation (VLN) aims to enable agents to navigate to specified locations and identify designated target objects following natural language instruction. This approach has gained popularity due to its close alignment with real-world scenarios. However, existing studies have predominantly focused on enhancing navigation performance, neglecting the ability to locate objects at the navigation endpoint. This oversight has resulted in a significant discrepancy between the success rates of navigation and object grounding. The challenge is compounded by the complex reasoning required by the instructions and the necessity to synthesize multiperspective images of objects, which overwhelms traditional object grounding methods. We leverage the Multi-Modal Large Language Model (MLLM) to bridge this gap, allowing agents to seek assistance from these models when struggling to locate the target object. The agent conducts a multi-stage evaluation to discern the cause of its confusion and promptly extracts and updates the most relevant information for MLLM to assess. Our method is plug-and-play and model-agnostic, facilitating integration with numerous existing VLN strategies without the need for retraining. Implementing our approach across four distinct methods has improved performance on the REVERIE and SOON datasets, demonstrating the effectiveness and generalizability of our technique.

关键词： Bridges computer vision Navigation Grounding Large language models Computational modeling Natural languages Cognition Data mining Object recognition

来源：评论

学校读者我要写书评

暂无评论

DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement learning from Human Feedback 39

DUO: Diverse, Uncertain, On-Policy Query Generation and Sele...

引用

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Feng, Xuening Jiang, Zhaohui Kaufmann, Timo Xu, Puchen Hüllermeier, Eyke Weng, Paul Zhu, Yifei UM-SJTU Joint Institute Shanghai Jiao Tong University Shanghai China Institute for Informatics LMU Munich Munich Germany Munich Center of Machine Learning Munich Germany German Research Center for Artificial Intelligence Germany Data Science Research Center Duke Kunshan University Kunshan China

ISBN: (纸本)157735897X

Defining a reward function is usually a challenging but critical task for the system designer in reinforcement learning, especially when specifying complex behaviors. Reinforcement learning from human feedback (RLHF) emerges as a promising approach to circumvent this. In RLHF, the agent typically learns a reward function by querying a human teacher using pairwise comparisons of trajectory segments. A key question in this domain is how to reduce the number of queries necessary to learn an informative reward function, since asking a human teacher too many queries is impractical and costly. To tackle this question, most existing methods mainly focus on improving exploration, introducing data augmentation or designing sophisticated training objectives for RLHF, while the potential of query generation and selection schemes have not been fully exploited. In this paper, we propose DUO, a novel method for diverse, uncertain, on-policy query generation and selection in RLHF. Our method produces queries that are (1) more relevant for policy training (via an on-policy criterion), (2) more informative (via a principled measure of epistemic uncertainty), and (3) diverse (via a clustering-based filter). Experimental results on a variety of locomotion and robotic manipulation tasks demonstrate that our method can outperform state-of-the-art RLHF methods given the same total budget of queries while being robust to possibly irrational teachers. Copyright © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

UAV-Assisted Real-Time Disaster Detection Using Optimized Transformer Model

arXiv

引用

arXiv 2025年

作者： Jankovic, Branislava Jangirova, Sabina Ullah, Waseem Khan, Latif U. Guizani, Mohsen Computer Vision Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

Dangerous surroundings and difficult-to-reach landscapes introduce significant complications for adequate disaster management and recuperation. These problems can be solved by engaging unmanned aerial vehicles (UAVs) provided with embedded platforms and optical sensors. In this work, we focus on enabling onboard aerial image processing to ensure proper and real-time disaster detection. Such a setting usually causes challenges due to the limited hardware resources of UAVs. However, privacy, connectivity, and latency issues can be avoided. We suggest a UAV-assisted edge framework for disaster detection, leveraging our proposed model optimized for onboard real-time aerial image classification. The optimization of the model is achieved using post-training quantization techniques. To address the limited number of disaster cases in existing benchmark datasets and therefore ensure real-world adoption of our model, we construct a novel dataset, DisasterEye, featuring disaster scenes captured by UAVs and individuals on-site. Experimental results reveal the efficacy of our model, reaching high accuracy with lowered inference latency and memory use on both traditional machines and resource-limited devices. This shows that the scalability and adaptability of our method make it a powerful solution for real-time disaster management on resource-constrained UAV platforms. Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Financial Cloud Services: AI and Blockchain-driven Resource Allocation for Maximized Transaction Speed and Security 3

Revolutionizing Financial Cloud Services: AI and Blockchain-...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Kumar, M. Lenin Amanullah, M. Krishnamurthy, Revatthy Suganthi, N. Mohana Kalaiselvan, S.A. Vignan Institute of Technology and Sciences Department of Electronics Communication and Engineering Telangana India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning Tamil Nadu Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Chennai Tamil Nadu Avadi India

ISBN: (纸本)9798350369083

In response to the evolving challenges of real-time monitoring in financial cloud environments, we propose a comprehensive solution integrating cutting-edge technologies. Our system employs AI-driven decision-making (ADDM) with a Dynamic Nested Neural Network (DNN) for adaptive resource allocation. This is coupled with a Markov Decision Process (MDP) for probabilistic decision-making, optimizing computational power, storage, and network resources dynamically. Blockchain technology fortifies transaction verification through a decentralized consensus mechanism and cryptographic techniques like RSA. The collaborative synergy of optimized resource allocation and Blockchain security ensures near-instantaneous processing, meeting the demands of a dynamic financial landscape. Our proposed system transforms the financial cloud environment into an adaptive and intelligent system, enhancing efficiency, security, and responsiveness for seamless and reliable real-time transaction processing. The results demonstrate accelerated transaction speeds, resource efficiency, and a robust security framework, addressing critical concerns in the realm of financial transactions. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Big Data Solutions for Predictive Healthcare Analytics: Enhancing Patient Outcomes and Operational Efficiency 3

Big Data Solutions for Predictive Healthcare Analytics: Enha...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Kumar, Nishi Kant Nandhini, J. Vinitha, S. Madhubala, P. Trimukhe, Dipmala Bhagwat Salunkhe, Kalpana Birla Institute of Technology Department of Computer Science and Engineering Mesra Off Campus Jharkhand Deoghar India Jai Shriram Engineering College Department of Ece Tirupur India Jerusalem College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India Bharathiyar Institute of Engineering for Women Department of Computer Science and Engineering Salem India Government College of Engineering & Research Department of Instrumentation Avasari Khurd India School of Computational Sciences Jspm University Wagholi Pune India

ISBN: (纸本)9798331542375

The embracing of Big Data solutions in healthcare comes with widely prospect to enhance patient satisfaction and increase organizational effectiveness. The research aims to use Predictive techniques and models coupled with modern data integration systems to improve the health care services. The components of the suggested methodology are deep neural networks for patient monitoring and prognosis, wearable devices, and operational prognosis models for resources use. From the practice of this approach, we have noticed marked increase in the patient monitoring frequency, efficiency of timely intervention, and generalization of health care organization productivity factors such as wait time and other resource utilization. In addition, the Onshape plan carried measurable benefits for the patient results such as satisfaction, reduced mortality, improved chronic disease, and the lesser hospital readmission. The results emphasize that the opportunities that Big Data and predictive analytics offer for healthcare can be indeed immense - offering improved care and more effective outcomes at a lower total cost. This research focuses on how Big Data solutions can help create a better future of healthcare improving the clinical and operational activities in this sphere and, thus, the population's health. © 2025 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Computational Modelling of Plurality and Definiteness in Chinese Noun Phrases 30

Computational Modelling of Plurality and Definiteness in Chi...

引用

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

作者： Liu, Yuqi Chen, Guanyi van Deemter, Kees Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning National Language Resources Monitoring and Research Center for Network Media School of Computer Science Central China Normal University China Department of Information and Computing Sciences Utrecht University Netherlands

ISBN: (纸本)9782493814104

Theoretical linguists have suggested that some languages (e.g., Chinese and Japanese) are "cooler" than other languages based on the observation that the intended meaning of phrases in these languages depends more on their contexts. As a result, many expressions in these languages are shortened, and their meaning is inferred from the context. In this paper, we focus on the omission of the plurality and definiteness markers in Chinese noun phrases (NPs) to investigate the predictability of their intended meaning given the contexts. To this end, we built a corpus of Chinese NPs, each of which is accompanied by its corresponding context, and by labels indicating its singularity/plurality and definiteness/indefiniteness. We carried out corpus assessments and analyses. The results suggest that Chinese speakers indeed drop plurality and definiteness markers very frequently. Building on the corpus, we train a bank of computational models using both classic machine learning models and state-of-the-art pre-trained language models to predict the plurality and definiteness of each NP. We report on the performance of these models and analyse their behaviours. The code and data used in this paper are available at: https://***/andyzxq/chinese_np_def. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Dissipativity Analysis: Application of the Matrix S-Lemma

引用

IEEE Control Systems 2022年第3期42卷 140-149页

作者： Van Waarde, Henk J. Camlibel, M. Kanat Rapisarda, Paolo Trentelman, Harry L. Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Groningen9747 AG Netherlands Vision Learning and Control Group of the University of Southampton SouthamptonSO17 1BJ United Kingdom

The concept of dissipativity, as introduced by Jan Willems, is one of the cornerstones of systems and control theory. Typically, dissipativity properties are verified by resorting to a mathematical model of the system under consideration. This article aims to assess dissipativity using computing storage functions for linear systems directly from measured data. As our main contributions, we provide conditions under which dissipativity can be ascertained from a finite collection of noisy data samples. Three different noise models are considered that can capture a variety of situations, including the cases where the data samples are noise-free, the energy of the noise is bounded, or the individual noise samples are bounded. All conditions are phrased in terms of data-based linear matrix inequalities, which can be readily solved using existing software packages. © 1991-2012 IEEE.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Smart Emergency Management System Using Raspberry Pi Pico, GPS and GSM Modules 4

Smart Emergency Management System Using Raspberry Pi Pico, G...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Govinda Rajulu, G. Sharmila, L. Venkatesan, D. Soumya, E. Prakash, Sargu Chandra Priyanka, Ms. P. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Avadi Department of Computer Science and Engineering Tamil Nadu Chennai India St. Martin's Engineeringollege Dept. of Artificial Intelligence and Machine Learning Telangana Dhulapally Secunderabad India St. Martin's Engineeringollege Deptarment of Cse Telangana Dhulapally Secunderabad India Telangana Dhulapally Secunderabad India

ISBN: (纸本)9798331523923

This paper proposes a GSM-based children's rescue system designed for earthquake emergencies, emphasizing cost-effectiveness and simplicity while ensuring rapid child rescue. The system operates in three key stages: data acquisition, classification, and alert notification. Sensors collect temperature, pH, and heart rate data, which are then digitized and classified to assess the child's condition. If abnormal values are detected, an alert notification is sent via GSM to parents and rescue teams, providing real-time location data through GPS. The hardware implementation, based on Raspberry Pi, converts analog sensor signals into digital data for processing. The system's efficacy is validated through various scenarios, demonstrating its ability to detect critical conditions and promptly trigger alerts, enhancing child safety during disasters. © 2025 IEEE.

关键词： Earthquakes

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving computer-Aided Diagnosis Framework for Medical Applications Using Federated learning and Homomorphic Encryption 7th

A Privacy-Preserving Computer-Aided Diagnosis Framework for...

引用

7th International Conference on Attacks and Defenses for Internet-of-Things, ADIoT 2024

作者： Xiong, Jichao Chen, Jiageng Liu, Hui Zhou, Guangyou Cui, Jianqun Lin, Junyu Jiao, Dian School of Computer Science and Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal University Wuhan430079 China School of Central China Normal University Wollongong Joint Institute Central China Normal University Wuhan430079 China

ISBN: (纸本)9783031855924

Skin cancer is one of the most common cancers worldwide, where early detection significantly reduces mortality rates. Integrating Internet of Things (IoT) technologies into healthcare enables continuous monitoring and early diagnosis through connected devices, offering new prospects for real-time medical assessment. Advanced machine learning classifiers have shown superior performance over human experts in diagnosing pigmented skin lesions, underscoring their potential for IoT-based applications. However, training high-precision computer-aided diagnosis (CAD) systems requires extensive data, and secure data sharing poses significant challenges due to privacy concerns in IoT healthcare networks. This paper introduces an IoT-oriented skin cancer CAD system combining federated learning and homomorphic encryption to address these issues. Federated learning supports collaborative model training across distributed IoT devices, mitigating data scarcity without compromising data privacy. Homomorphic encryption ensures that patient data remains encrypted during diagnosis, enhancing security within IoT frameworks. To achieve an efficient and high-accuracy model suited for IoT, we implemented Self-Learnable Activation Functions (SLAF), optimized for homomorphic encryption and resource constraints of IoT devices. Our system, validated using the HAM10000 dataset, achieved 94.39% accuracy with dual privacy protection, enhancing both diagnostic precision and data security. Comprehensive evaluations and comparisons with state-of-the-art frameworks confirmed the effectiveness of our approach. Results demonstrate the strong potential and practicality of our IoT-based solution for real-world healthcare, providing a secure, efficient, and accurate diagnostic tool that supports the wider adoption of IoT in medical applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

CCTV Surveillance-Based Vehicle Identification: Query-Driven Search Using Colour, Manufacturer & License Plate

CCTV Surveillance-Based Vehicle Identification: Query-Driven...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Ramakanth Kumar P Pranav V Jambur Diptanshu Kumar Computer Science & Engineering R. V. College of Engineering Bengaluru India Artificial Intelligence & Machine Learning Engineering R. V. College of Engineering Bengaluru India

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

The paper addresses the challenges of vehicle detection and identification in road safety and surveillance, especially in hit-and-run incidents and vehicle theft cases. The solution combines computer vision with YOLO models for real-time vehicle detection, colour classification, and a custom CNN for accurate vehicle type classification. YOLO is also used for license plate recognition, paired with Tesseract OCR to extract alphanumeric details for precise identification. The colour identification process is two-fold: YOLO detects vehicles in video frames and isolates their bounding boxes, which are then processed through a YOLO-based classifier trained on the VCoR dataset with 15 vehicle colour labels. Trained over 25 epochs, the model achieved 85.6% top-1 accuracy and 99.5%top-5 accuracy, proving reliable across diverse lighting, weather, and traffic conditions. This system automates vehicle detection and identification, reducing the time and manual effort needed to review large video datasets. Integrating vehicle type classification, colour recognition, and license plate identification, it provides a scalable and efficient tool for law enforcement and surveil- lance, enabling rapid suspect vehicle identification in complex traffic environments. The solution enhances traffic monitoring and security, delivering high accuracy in real-world scenarios. Scalable across urban areas, highways, toll booths, and smart city infrastructure, it offers a versatile approach to modern traffic surveillance.

关键词： YOLO Accuracy Smart cities Law enforcement Surveillance Computational modeling Color Traffic control Real-time systems License plate recognition

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：