检索结果-内蒙古大学图书馆

2024 International Conference on Innovation and intelligence for Informatics, Computing, and Technologies, 3ICT 2024

作者： Karakaş, Çağrı Aydin, İlhan Akin, Erhan Dept. of Computer Engineering Firat University Elazığ Turkey

ISBN: (纸本)9798331533137

This study examines the use of artificial intelligence-based image segmentation and image processing techniques in disaster management. The aim of the study is to integrate artificial intelligence and image processing techniques for fast and effective response in disaster areas to facilitate disaster management. Our hypothesis is that fast and accurate analysis can be performed with high-performance and fast AI-based segmentation models and image processing techniques on images taken from UAVs and satellites in disaster areas. In this process, important regions in the images are identified by applying segmentation processes and masks are created. Then, using these masks, numerical results can be obtained with image processing techniques with low computational cost. Thus, it is aimed to make fast and accurate decisions in disaster management. In this study, popular segmentation models were compared and analyzed using 2343 images obtained from Floodnet dataset. The results show that the SegFormer model provides detailed damage analysis and contour area or connected component analysis, which can provide both detailed and numerically accurate results for disaster management. This study reveals that the use of image processing and artificial intelligence in disaster management can improve response processes by increasing operational efficiency. ©2024 ieee.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

SEMI-SUPERVISED MEDICAL image SEGMENTATION VIA MULTI-GROUP NETWORK WITH CONSISTENCY AMONG HETEROGENEOUS LOSS SUPERVISION 21

SEMI-SUPERVISED MEDICAL IMAGE SEGMENTATION VIA MULTI-GROUP N...

引用

21st ieee International symposium on Biomedical Imaging (ISBI)

作者： Ye, Ping Li, He Zhang, Shaoting Wang, Guotai Univ Elect Sci & Technol China Sch Mech & Elect Engn Chengdu Peoples R China Shanghai Artificial Intelligence Lab Shanghai Peoples R China SenseTime Res Shanghai Peoples R China

ISBN: (纸本)9798350313345;9798350313338

Semi-Supervised Learning (SSL) is appealing for reducing the annotation cost for training medical image segmentation models. State-of-the-art SSL methods typically generate multiple predictions via multiple networks/branches or perturbed inputs, then employ cross-supervision or consistency regularization to leverage unannotated images. Nevertheless, these approaches are often encumbered by either high computational costs or excessive time consumption due to their complexity. To solve these problems, we introduce an efficient framework Multi-Group network with Consistency among Heterogeneous Loss (MGCHL) for SSL. First, a Multi-Group Convolutional Network (MGCNet) is proposed to efficiently produce multiple predictions, each from an independent group of features. Furthermore, to encourage inter-group interaction for robust learning, we propose heterogeneous supervision where each group is supervised by a distinct loss on labeled images, and then inter-group consistency is imposed on unlabeled images for regularization. Experimental results demonstrated that our method outperforms four state-of-the-art methods on both skin lesion segmentation in the ISIC 2018 dataset and heart structure segmentation in the ACDC dataset.

关键词： Semi-supervised learning Group convolution Consistency regularization

来源：评论

学校读者我要写书评

暂无评论

Objectives, Methods, and Challenges of Applying Intelligent Assessment in Education: A systematic review 10

Objectives, Methods, and Challenges of Applying Intelligent ...

引用

10th International symposium on Educational Technology (ISET)

作者： Kuang, Yuanyuan Tang, Ying Xie, Tao Southwest Univ Dept Educ Chongqing Peoples R China

ISBN: (纸本)9798350361414

With the development of artificial intelligence technology, traditional assessment has been gradually replaced by intelligent assessment. This study systematically reviews research on the use of intelligent assessment in education between 2015 and 2024. 51 papers were finally included and analyzed for the objectives, methods, and challenges of adopting intelligent assessment in educational activities. The results show that the goals of intelligent assessment in education can be grouped into three categories: 1) assessment of students' competence and knowledge levels;2) assessment of students' personality and mental health;and 3) assessment of teaching and learning processes. The studies reviewed used a range of assessment methods to achieve their objectives. These encompassed process-based, student competency-based, and dynamism-based approaches, as well as social media text-based, audio, and video-based assessment methods. Additionally, they employed student assessment-based and teacher performance assessment-based methods. These methods involved designing algorithms, application systems, or scale assessment tools to effectively measure and evaluate various aspects of learning and teaching. The challenges were present in three areas: data collection and processing, adaptation of assessment models, and accuracy and interpretability of assessment results.

关键词： Intelligent Assessment Artificial intelligence Educational Evaluation Synthesis

来源：评论

学校读者我要写书评

暂无评论

AdaBM: On-the-Fly Adaptive Bit Mapping for image Super-Resolution

AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resol...

引用

ieee/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hong, Cheeun Lee, Kyoung Mu Seoul Natl Univ Dept ECE Seoul South Korea Seoul Natl Univ ASRI Seoul South Korea Seoul Natl Univ IPAI Seoul South Korea

ISBN: (纸本)9798350353013;9798350353006

Although image super-resolution (SR) problem has experienced unprecedented restoration accuracy with deep neural networks, it has yet limited versatile applications due to the substantial computational costs. Since different input images for SR face different restoration difficulties, adapting computational costs based on the input image, referred to as adaptive inference, has emerged as a promising solution to compress SR networks. Specifically, adapting the quantization bit-widths has successfully reduced the inference and memory cost without sacrificing the accuracy. However, despite the benefits of the resultant adaptive network, existing works rely on time-intensive quantization-aware training with full access to the original training pairs to learn the appropriate bit allocation policies, which limits its ubiquitous usage. To this end, we introduce the first on-the-fly adaptive quantization framework that accelerates the processing time from hours to seconds. We formulate the bit allocation problem with only two bit mapping modules: one to map the input image to the image-wise bit adaptation factor and one to obtain the layer-wise adaptation factors. These bit mappings are calibrated and fine-tuned using only a small number of calibration images. We achieve competitive performance with the previous adaptive quantization methods, while the processing time is accelerated by x2000. Codes are available at https://***/Cheeun/AdaBM.

关键词： Adaptive quantization image super resolution Network quantization

来源：评论

学校读者我要写书评

暂无评论

Advancing Natural Language to SQL: A Comparative Study of Open Source LLMs on Benchmark Datasets

Advancing Natural Language to SQL: A Comparative Study of Op...

引用

2025 ieee symposium on computational intelligence in Natural Language processing and Social Media, CI-NLPSoMe Companion 2025

作者： Sharma, Ashwin K Kanumuri, Sri Charan Pranav, A.R. Sharath, Shylaja S Pes University Department of Cse Bengaluru India

ISBN: (纸本)9798331519742

Translating Natural Language to SQL (NL-to-SQL) allows users to communicate with databases using a common language instead of complicated query syntax. This is important as it frees the non-technical user from querying the database, making interactions more easier. This work primarily evaluates open-source language models on three key NL-to-SQL bench-mark datasets: SPIDER, a cross-domain dataset;WikiSQL, a simpler single-domain dataset;and BIRD, a dataset comprising of real-world data. These datasets were selected because of the variety of problems they present: WikiSQL concentrates on effective querying using straightforward single-tables, while BIRD simulates noisy, real-world data scenarios where precise and effective SQL creation is essential. SPIDER analyzes how well models generalize over complex schemas and multi-table queries. We fine-tuned eight models from the LLM families of LLama, Gemma, and Mistral across these datasets with consistent hyper-parameters to tackle these challenges. We used an SQL evaluation framework that examines model generalization, considering both linguistic variety and complex query patterns against a baseline of accuracy and correctness of existing NL-to-SQL models available. This study demonstrates how different models perform across datasets, with some performing better in simpler queries and others being suited for managing inconsistent, real-world data or difficult cross-domain tasks. © 2025 ieee.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Exploring Vulnerabilities of No-Reference image Quality Assessment Models: A Query-Based Black-Box Method

引用

ieee TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第12期34卷 12715-12729页

作者： Yang, Chenxi Liu, Yujia Li, Dingquan Jiang, Tingting Peking Univ Natl Engn Res Ctr Visual Technol Sch Math Sci Sch Comp SciState Key Lab Multimedia Informat Pro Beijing Peoples R China Peking Univ Natl Engn Res Ctr Visual Technol Sch Comp Sci State Key Lab Multimedia Informat Proc Beijing Peoples R China Pengcheng Lab Dept Networked Intelligence Shenzhen Peoples R China

No-Reference image Quality Assessment (NR-IQA) aims to predict image quality scores consistent with human perception without relying on pristine reference images, serving as a crucial component in various visual tasks. Ensuring the robustness of NR-IQA methods is vital for reliable comparisons of different image processing techniques and consistent user experiences in recommendations. The attack methods for NR-IQA provide a powerful instrument to test the robustness of NR-IQA. However, current attack methods of NR-IQA heavily rely on the gradient of the NR-IQA model, leading to limitations when the gradient information is unavailable. In this paper, we present a pioneering query-based black box attack against NR-IQA methods. We propose the concept of score boundary and leverage an adaptive iterative approach with multiple score boundaries. Meanwhile, the initial attack directions are also designed to leverage the characteristics of the Human Visual System (HVS). Experiments show our method outperforms all compared state-of-the-art attack methods and is far ahead of previous black-box methods. The effective NR-IQA model DBCNN suffers a Spearman's rank-order correlation coefficient (SROCC) decline of 0.6381 attacked by our method, revealing the vulnerability of NR-IQA models to black-box attacks. The proposed attack method also provides a potent tool for further exploration into NR-IQA robustness.

关键词： Closed box Perturbation methods Task analysis image quality Robustness computational modeling Glass box No-reference image quality assessment black-box attack query-based attack robustness

来源：评论

学校读者我要写书评

暂无评论

Federated Clouds for Efficient Multitasking in Distributed Artificial intelligence Applications

引用

ieee TRANSACTIONS ON CLOUD COMPUTING 2023年第2期11卷 2084-2095页

作者： Li, Yuejin Hwang, Kai Shuai, Kefan Li, Zhengdao Zomaya, Albert Chinese Univ Hong Kong Shenzhen 518172 Guangdong Peoples R China Univ Sydney Sydney NSW 2006 Australia

Distributed cloud/edge resources are needed to execute pervasive artificial intelligence tasks, collectively. The AI workload and data sets have variable multitasking granularity, privacy constraints, and communication latency concerns. This article presents a novel federated cloud/edge (FCE) framework, illustrated by distributed medical image processing across multiple hospital sites. This federated cloud system appeals to train many machine learning models efficiently with workload balancing and reduced communication overheads. We tested the FCE model on a multi-cloud platform recently built at the Chinese University of Hong Kong in Shenzhen. We claim three distinct advantages in using the FCE system. First, our federated cloud system results in 41.3% reduction in total AI processing time in large-scale ML/DL experiments. Second, high machine model accuracy was achieved at 87% level in telemedicine experiments. The virtual graph helps reduce internode traffic latencies to avoid ML inference slowdowns. Third, the system can tolerate multiple cloud failures to enter a graceful degradation mode in case of node failures. The scalable performance gains in AI processing speed, model accuracy, and fault tolerance make our federated clouds a truly viable approach to solving massive AI multitasking problems in pervasive AI applications.

关键词： Cloud computing Hospitals computational modeling Servers Atmospheric modeling Training Software defined networking Cloud computing federated machine learning graphs and networks latency reduction and fault tolerance

来源：评论

学校读者我要写书评

暂无评论

SIGNAL processing METHODS FOR LONG-RANGE UAV-SAR FOCUSING WITH PARTIALLY UNKNOWN TRAJECTORY

SIGNAL PROCESSING METHODS FOR LONG-RANGE UAV-SAR FOCUSING WI...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Polisano, Mattia G. Grassi, Pietro Manzoni, Marco Tebaldini, Stefano Politecn Milan Ride Lab DEIB Milan Italy

ISBN: (纸本)9798350360332;9798350360325

This work provides the signal processing workflow to focus Unmanned Aerial Vehicles (UAV) Synthetic Aperture Radar (SAR) images with partially unknown or corrupted trajectories. The processing chain is divided into two modular blocks. The former involves a novel and low-complexity autofocusing technique. This method applies geometric corrections directly to the nominal trajectory, getting rid of the assumption of a constant phase correction, that does not hold with highly variable squint and off-nadir angles, as for the case of UAV-borne SAR. The latter modular block concerns a Fast Factorised Back Projection (FFBP) based focusing scheme. In particular, for a given scenario the processor computes a priori the computational burden in order to define the most appropriate reference system and the degree of hierarchical merging to focus the scene at the minimum computational cost. In light of this, the proposed focusing algorithm is able to deal with a complex trajectory typical of UAVs and to focus a large image at high resolution. Two scenarios are considered. The former is a UAV-borne SAR experiment with a small aperture, a long range, and a wide area covered by a large antenna aperture. The latter is a proper UAV-borne SAR stripmap scenario. Here, the proposed focusing scheme performs better than the traditional FFBP. Finally, the results are supported by a numerical simulation to prove the effectiveness of the whole processing scheme.

关键词： UAV-borne SAR SAR Autofocusing FastFactorized Backprojection

来源：评论

学校读者我要写书评

暂无评论

Deep Efficient Continuous Manifold Learning for Time Series Modeling

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE intelligence 2024年第1期46卷 171-184页

作者： Jeong, Seungwoo Ko, Wonjun Mulyadi, Ahmad Wisnu Suk, Heung-Il Korea Univ Dept Artificial Intelligence Seoul 02841 South Korea Korea Univ Dept Brain & Cognit Engn Seoul 02841 South Korea

Modeling non-euclidean data is drawing extensive attention along with the unprecedented successes of deep neural networks in diverse fields. Particularly, a symmetric positive definite matrix is being actively studied in computer vision, signal processing, and medical image analysis, due to its ability to learn beneficial statistical representations. However, owing to its rigid constraints, it remains challenging to optimization problems and inefficient computational costs, especially, when incorporating it with a deep learning framework. In this paper, we propose a framework to exploit a diffeomorphism mapping between Riemannian manifolds and a Cholesky space, by which it becomes feasible not only to efficiently solve optimization problems but also to greatly reduce computation costs. Further, for dynamic modeling of time-series data, we devise a continuous manifold learning method by systematically integrating a manifold ordinary differential equation and a gated recurrent neural network. It is worth noting that due to the nice parameterization of matrices in a Cholesky space, training our proposed network equipped with Riemannian geometric metrics is straightforward. We demonstrate through experiments over regular and irregular time-series datasets that our proposed model can be efficiently and reliably trained and outperforms existing manifold methods and state-of-the-art methods in various time-series tasks.

关键词： Cholesky space deep learning manifold learning manifold ordinary differential equation multivariate time series modeling symmetric positive definite matrix

来源：评论

学校读者我要写书评

暂无评论

computational Imaging and Artificial intelligence: The Next Revolution of Mobile Vision

引用

PROCEEDINGS OF THE ieee 2023年第12期111卷 1607-1639页

作者： Suo, Jinli Zhang, Weihang Gong, Jin Yuan, Xin Brady, David J. Dai, Qionghai Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Tsinghua Univ Inst Brain & Cognit Sci Beijing 100084 Peoples R China Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China Westlake Univ Res Ctr Ind Future Hangzhou 310030 Zhejiang Peoples R China Westlake Univ Sch Engn Hangzhou 310030 Zhejiang Peoples R China Univ Arizona Wyant Coll Opt Sci Tucson AZ 85721 USA

Signal capture is at the forefront of perceiving and understanding the environment;thus, imaging plays a pivotal role in mobile vision. Recent unprecedented progress in artificial intelligence (AI) has shown great potential in the development of advanced mobile platforms with new imaging devices. Traditional imaging systems based on the "capturing images first and processing afterward" mechanism cannot meet this explosive demand. On the other hand, computational imaging (CI) systems are designed to capture high-dimensional data in an encoded manner to provide more information for mobile vision systems. Thanks to AI, CI can now be used in real-life systems by integrating deep learning algorithms into the mobile vision platform to achieve a closed loop of intelligent acquisition, processing, and decision-making, thus leading to the next revolution of mobile vision. Starting from the history of mobile vision using digital cameras, this work first introduces the advancement of CI in diverse applications and then conducts a comprehensive review of current research topics combining CI and AI. Although new-generation mobile platforms, represented by smart mobile phones, have deeply integrated CI and AI for better image acquisition and processing, most mobile vision platforms, such as self-driving cars and drones only loosely connect CI and AI, and are calling for a closer integration. Motivated by this fact, at the end of this work, we propose some potential technologies and disciplines that aid the deep integration of CI and AI and shed light on new directions in the future generation of mobile vision platforms.

关键词： Artificial intelligence (AI) autonomous driving brain science cameras cloud computing computational imag-ing (CI) deep learning edge cloud edge computing machine learning machine vision mobile vision neural networks optics self-driving

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：