检索结果-内蒙古大学图书馆

Rational 3D object placement based on deep learning based plane detection

Multimedia Tools and Applications 2023年第28期82卷 44555-44576页

作者： Yang, Wei-Jong Lu, Li-Yu Chan, Din-Yuen Department of Artificial Intelligence and Computer Engineering National Chin-Yi University of Technology Taichung Taiwan Telecommunication Laboratories Chunghwa Telecom Co. Ltd. Internet of Things Laboratory Taoyuan Taiwan Department of Computer Science and Information Engineering National Chiayi University Chiayi Taiwan

Effective acquisition of 3D planar features from a 2D image for immersive AR applications is challenging without any 3D depth information. In this paper, we present a novel planar object placement (POP) system for rational insertion of 3D objects on plane surfaces and fitting their plane orientations in a given 2D image. The POP system is composed of an adaptive edge extractor (AEE), a vanishing point detector (VPD), a rational fitting transformer (RFT) and a plane normal detection network (PNDnet), which performs the estimation of planar features. With the inputs of the color image and the guided edge map retrieved by the AEE, the PNDnet based on a gating weighted U-Net, whose gating weights are controlled by global cross-level connection (GCC) blocks, can properly extract 3D information including planar pixel-wise normal map, semantic plane-segmented map and plane-wise normal vectors. Simultaneously, with plane-wise normal vectors and the VPD-estimated vanishing points, the RFT can easily induce the best placement position for projecting the AR object on a destination plane with better coherent 3D perspectives. Besides, the POP system allows the users to make the subtle tunes of 3D orientation to the inserted object for personal preferences. Experimental results show that the proposed POP system, which successfully guides the 3D-inserted objects to match up the surfaces and orientations of the planes in the target image, will become an effective AR tool for the insertion of 3D objects in target images and videos in the future. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

LDE-UNet: A Novel Model for Rapid COVID-19 Diagnosis via CT Image Segmentation

LDE-UNet: A Novel Model for Rapid COVID-19 Diagnosis via CT ...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, QiSong Wu, JiaRou Wang, YingZhuo Qu, HuiLi Nie, Shanling Yang, Hai East China University of Science and Technology Department of Computer Science and Engineering Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China The University of Sydney Faculty of Engineering Australia

ISBN: (纸本)9798350337488

The COVID-19 pandemic has had a profound impact on human society. It has highlighted the need for faster diagnostic methods. Research has shown that combining semantic segmentation with traditional medical approaches can significantly accelerate the process. To address this, leveraging COVID-19 CT images, our team designs a revolutionary semantic segmentation model called Level of Detail Enhancement U-Net (LDE-UNet), which shows the lesion area on CT images. By introducing the LDE block, the model has the unique advantage of overcoming the loss of data details during the downsampling process by emphasizing and transmitting details at the same level. Our SOTA model outperforms the second-best model by at least 0.7% in the most critical indicator precision. Compared with other models, LDE-UNet's strong reliability determines its ability to be used in the medical field to accelerate the localization and division of lesion areas on CT images by professional doctors, thus completing patient diagnosis faster. In addition, we also propose a standardized method for processing medical images. © 2023 IEEE.

关键词： COVID-19 Downsample LDE-UNet Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Endogenous Security of FQn Networks: Adaptive System-Level Fault Self-Diagnosis

引用

IEEE Transactions on Reliability 2024年第3期73卷 1659-1668页

作者： Lin, Yuhang Lin, Limei Huang, Yanze Xu, Li Hsieh, Sun-Yuan Fujian Normal University College of Computer and Cyber Security Fujian Provincial Key Laboratory of Network Security and Cryptology Fuzhou350117 China Fujian University of Technology School of Computer Science and Mathematics Fuzhou350118 China National Cheng Kung University Department of Computer Science and Information Engineering Tainan701 Taiwan

Endogenous security has the ability to discover, eliminate, and solve internal security problems and hidden dangers within the network, and is a superior technology to ensure future network security. The t/k-diagnosis strategy, as a strong and adaptive self-diagnosis strategy, is an important part for ensuring endogenous security. Moreover, the folded hypercube (FQn) as a data transmission network (e.g., optical network) topology offers new potential for the construction of large-scale, high data throughput, and low-latency systems, such as computing network, human-cyber-physical systems, and smart grid. However, there are few studies on endogenous security based on FQn networks. Therefore, this article designs an adaptive system-level fault self-diagnosis strategy, namely Fast t/k-Diagnosis Under Maeng-Malek Model (Ftk-DIAG-MM*) to diagnosis the faulty vertices in FQn network under the Maeng-Malek model (MM∗ mod). Then, we provide a proof of the algorithm correctness theoretically by the fault tolerance of FQn network. It is derived by theoretical derivation that the t/k-diagnosability inherent to the FQn network is (n+1)(k+1)-k(k+3)/2. The simulation experiments demonstrate that the designed Ftk-DIAG-MM∗ strategy can correctly diagnose all vertices within the range allowed by the diagnosability, and still has a great performance when it exceeds the range allowed by the diagnosability. It greatly enhances the fault diagnosis capability of FQn network in the circumstance of misdiagnosing a few vertices, which provides an important theoretical basis for the reliability and endogenous security of FQn networks. © 1963-2012 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Position Measurement Based Slave Torque Feedback Control for Teleoperation Systems With Time-Varying Communication Delays

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 388-402页

作者： Xian Yang Jing Yan Changchun Hua Xinping Guan the Institute of Information Science and Engineering Yanshan University the Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004China IEEE the Institute of Electrical Engineering Yanshan UniversityQinhuangdao 066004China the Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China

Bilateral teleoperation system is referred to as a promising technology to extend human actions and intelligence to manipulating objects *** the tracking control of teleoperation systems,velocity measurements are necessary to provide feedback ***,due to hardware technology and cost constraints,the velocity measurements are not always *** addition,the time-varying communication delay makes it challenging to achieve tracking *** paper provides a solution to the issue of real-time tracking for teleoperation systems,subjected to unavailable velocity signals and time-varying communication *** order to estimate the velocity information,immersion and invariance(I&I)technique is employed to develop an exponential stability velocity *** the proposed velocity observer,a linear relationship between position and observation state is constructed,through which the need of solving partial differential and certain integral equations can be ***,the mean value theorem is exploited to separate the observation error terms,and hence,all functions in our observer can be analytically *** the estimated velocity information,a slave-torque feedback control law is presented.A novel Lyapunov-Krasovskii functional is constructed to establish asymptotic tracking *** particular,the relationship between the controller design parameters and the allowable maximum delay values is ***,simulation and experimental results reveal that the proposed velocity observer and controller can guarantee that the observation errors and tracking error converge to zero.

关键词： Asymptotic stability bilateral teleoperation time-varying delay velocity observer

来源：评论

学校读者我要写书评

暂无评论

Task Consistent Prototype Learning for Incremental Few-Shot Semantic Segmentation 27th

Task Consistent Prototype Learning for Incremental Few-Shot...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Xu, Wenbo Wu, Yanan Jiang, Haoran Wang, Yang Wu, Qiang Zhang, Jian Faculty of Engineering and Information Technology University of Technology Sydney Sydney2007 Australia School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

ISBN: (纸本)9783031783463

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a challenge that the objective of the base training phase (fitting base classes with sufficient instances) does not align with the incremental learning phase (rapidly adapting to new classes with less forgetting). This disconnect can result in suboptimal performance in the incremental setting. This study introduces a meta-learning-based prototype approach that encourages the model to learn how to adapt quickly while preserving previous knowledge. Concretely, we mimic the incremental evaluation protocol during the base training session by sampling a sequence of pseudo-incremental tasks. Each task in the simulated sequence is trained using a meta-objective to enable rapid adaptation without forgetting. To enhance discrimination among class prototypes, we introduce prototype space redistribution learning, which dynamically updates class prototypes to establish optimal inter-prototype boundaries within the prototype space. Extensive experiments on iFSS datasets built upon PASCAL and COCO benchmarks show the advanced performance of the proposed approach, offering valuable insights for addressing iFSS challenges. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Virtual Mock Interview Development 13

AI-Driven Virtual Mock Interview Development

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Mishra, Prabhat Kumar Arulappan, Arun Kumar Ra, In-Ho Thanga Mariappan, L. Gina Rose, G. Lee, Young-Seok School of Computer Science Engineering and Information Systems Vit University Vellore India School of Computer and Software Kunsan National University Gunsan Korea Republic of Anna University Department of Computer Technology Chennai India

ISBN: (纸本)9798350373332

The integration of Artificial Intelligence (AI) into educational technologies marks a significant shift in learning methodologies and operational dynamics within educational institutions. At the forefront is an AI-driven virtual mock interview platform designed to address the high Customer Acquisition Costs (CAC) in the edtech sector, especially for interview preparation services. This initiative harnesses a blend of AI technologies, including ADA 2 for creating context-aware embeddings and Machine Learning (ML), to transform the traditional mock interview process into a dynamic, cost-effective system. Central to the platform is its use of advanced Natural Language Processing (NLP) techniques and GPT-4 Large Language Model (LLM), automating the process of mock interviews and providing personalized feedback, ensuring a preparation journey that meets specific candidate needs and mirrors real interview scenarios. A key evaluation among 100 students from a cohort of 1800 demonstrated a 90% cost reduction for three mock interviews, reducing expenses from 3000 to just 300 per candidate. This cost efficiency significantly enhances access to quality interview preparation, improving student satisfaction and accessibility. Moreover, the platform provides valuable insights into student performance, setting a new standard in educational technology by offering an effective, personalized interview preparation experience. This project reflects a holistic approach to student development and the critical role of technology in addressing the evolving needs of learners. © 2024 IEEE.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Novel Approach for Enhancing Mental Well-Being Through Machine Learning Techniques 5

Novel Approach for Enhancing Mental Well-Being Through Machi...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Roshani, O.V.D.E. Ayuwardhana, H.M.K.J.J. Rodrigo, P.H.M.S. Hewageegana, R.U. Fernando, Harinda De Silva, Dilshan I. Sri Lanka Institute of Information Technology Faculty of Computing Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Computing Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

Frequently, individuals undergo specific episodes of mental health challenges throughout their lifetime. But the COVID pandemic has triggered a surge in mental health disorders arising from isolation, monotonous routines, demanding workloads, financial disparities, and disruptions to daily schedules. Furthermore, the global pandemic has induced constant anxiety and stress. Beyond the pandemic, the competition and intense pressure of the modern world impact mental health. Access to advanced mental health solutions and the necessary familiarity remain limited for most of the population. Given the integration of technology into daily life, diverse remedies, including mobile and web applications, have emerged to tackle the escalating challenge of mental health disorders. This study proposes an accessible and cost-effective approach that employs machine learning to detect stress levels and discern user emotions from journal entries and facial expressions while integrating self-journaling, video recommendations, and visual content generation to stimulate positive emotions and relieve stress. © 2023 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Weighted Poisson-disk Resampling on Large-Scale Point Clouds 39

Weighted Poisson-disk Resampling on Large-Scale Point Clouds

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Jiao, Xianhe Lv, Chenlei Zhao, Junli Yi, Ran Wen, Yu-Hui Pan, Zhenkuan Wu, Zhongke Liu, Yong-Jin College of Computer Science and Technology Qingdao University China College of Computer Science and Software Engineering Shenzhen University China Department of Computer Science and Engineering Shanghai Jiao Tong University China School of Computer Science & Technology Beijing Jiaotong University China School of Artificial Intelligence Beijing Normal University China Department of Computer Science and Technology MOE-Key Laboratory of Pervasive Computing Tsinghua University China

ISBN: (纸本)157735897X

For large-scale point cloud processing, resampling takes the important role of controlling the point number and density while keeping the geometric consistency. However, current methods cannot balance such different requirements. Particularly with large-scale point clouds, classical methods often struggle with decreased efficiency and accuracy. To address such issues, we propose a weighted Poisson-disk (WPD) resampling method to improve the usability and efficiency for the processing. We first design an initial Poisson resampling with a voxel-based estimation strategy. It is able to estimate a more accurate radius of the Poisson-disk while maintaining high efficiency. Then, we design a weighted tangent smoothing step to further optimize the Voronoi diagram for each point. At the same time, sharp features are detected and kept in the optimized results with isotropic property. Finally, we achieve a resampling copy from the original point cloud with the specified point number, uniform density, and high-quality geometric consistency. Experiments show that our method significantly improves the performance of large-scale point cloud resampling for different applications, and provides a highly practical solution. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Lifelong Scalable Generative System via Online Maximum Mean Discrepancy 39

Lifelong Scalable Generative System via Online Maximum Mean ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ye, Fei Bors, Adrian G. School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science University of York YorkYO10 5GH United Kingdom

ISBN: (纸本)157735897X

Diffusion-based models have been recently shown to be high-quality data generators. However, their performance severely degrades when training on non-stationary changing data distributions in an online manner, due to the catastrophic forgetting. In this paper, we propose enabling the diffusion model with a novel Dynamic Expansion Memory Unit (DEMU) methodology that adaptively creates new memory buffers, to be added to a memory system, in order to preserve information deemed critical for training the model. Having a selective memory unit is essential for training diffusion networks, which are expensive to train, especially when deployed in resource-constrained environments. A Maximum Mean Discrepancy (MMD) based expansion mechanism, that evaluates probabilistic distances between each of the previously defined memory buffers and the newly given data, and uses them as expansion signals, is employed for ensuring the diversity of information learning. We propose a new model expansion mechanism to automatically add new diffusion models as experts in a mixture system, which enhances the multi-domain image generation performance. Also a novel memory compaction approach is proposed to automatically remove statistically overlapping memory units, through a graph relationship evaluation, preventing the limitless expansion of DEMU. Comprehensive results show that the proposed approach performs better than the state-of-the-art. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Buffer storage

来源：评论

学校读者我要写书评

暂无评论

Exact Algorithm for Batch Scheduling with Many-to-Many Job-Tool Matching and Job Release Time Constraints

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 16499-16511页

作者： Li, Shengchao Liu, Shixin Zhao, Ziyan Zhou, Mengchu Northeastern University State Key Laboratory of Synthetical Automation for Process Industries College of Information Science and Engineering Shenyang 110819 China Northeastern University at Qinhuangdao Hebei Key Laboratory of Industrial Software for Advanced Planning and Scheduling of Complex Industrial Processes School of Control Engineering Qinhuangdao 066004 China New Jersey Institute of Technology Department of Electrical and Computer Engineering Newark 07102 NJ United States

Job-dependent tool switching is necessary in many batch processing systems (BPSs). Heterogeneous tool demand and extra time consumption for tool switch bring great challenge for high-performance production scheduling in BPSs. In this study, we present a novel batch scheduling problem derived from a satellite vibration test system. Different from basic scheduling problems in BPSs with tool switching, it has complications caused by many-to-many task-tool matching and job release time constraints. Specifically, each job has predetermined candidate tools. One of them should be selected and equipped to process a given job. Unlike sequence-dependent setup time that is only related to two adjacent jobs, tool switching time is additionally dependent on the tools selected by both jobs from their respective candidate tools. Both job sequence and tool selections need to be determined to minimize makespan. Mixed-integer linear programming (MILP) and constraint programming (CP) models are developed for formulating the problem. We prove that the problem is NP hard. To obtain exact solutions, we propose a novel branch-and-bound algorithm (B&B) based on the analysis and extraction of problem properties. It integrates a domain reduction mechanism, branching strategies, and dominance rules. Among them, the domain reduction mechanism reduces the number of jobs to be scheduled;the branching strategies accelerate solving speed;and the dominance rules save the memory consumption. Ablation studies and key influencing factor experiments are performed. The results show that the proposed B&B can optimally solve much larger instances than state-of-the-art methods (including some heuristics). It can optimally solve industrial-size problems in a short time, implying that it can well satisfy the performance demand of a satellite vibration test system and thus advancing the filed of optimal scheduling for BPSs. © 2004-2012 IEEE.

关键词： Batch scheduling branch-and-bound algorithm heterogenerous tool demand mixed-integer linear programming satellite vibration test system

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：