检索结果-内蒙古大学图书馆

5th ECCOMAS Thematic Conference on Uncertainty Quantification in Computational sciences and engineering, UNCECOMP 2023

作者： Liu, Chao Zhou, Xinlei Wang, Xizhao College of Computer Science and Software Engineering Shenzhen University 3688 Nanhai Avenue Nanshan District Guangdong Province Shenzhen China

The representation, measure, and handling of uncertainty in an application of deep learning have a significant impact on the performance of learning systems. Uncertainty is embedded in the entire process of learning from data, which can roughly be categorized as three types, i.e., data uncertainty, model uncertainty, and prediction uncertainty. Appropriately modeling and processing uncertainties in different phases of learning can significantly improve accuracy and robustness. Focusing on the 3rd type of uncertainty, i.e., the prediction uncertainty which lies on the phase from the model output (i.e., a probability distribution on label space) to the final class(s) determination, we present in this paper a new viewpoint regarding uncertainty processing. Theoretically and experimentally, it establishes a statistical relationship between the prediction uncertainty and the learning performance, which implicitly points out that some results about uncertainty processing in traditional textbooks may be incorrect. Based on this viewpoint, we propose an approach to optimize the output layer of neural network models. The method improves the prediction accuracy by replacing the last layer of softmax with a random weight model which is a simple and fast non-iterative training algorithm. Extensive experiments and simulations on the synthetic and real datasets demonstrate the effectiveness and good generalization of the proposed scheme. © 2023 UNCECOMP Proceedings. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dynamic Multimodal Optimzation 13

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dy...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Wu, Xunfeng Liu, Songbai Ji, Junkai Ma, Lijia Leung, Victor C. M. Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China The University of British Columbia Department of Electrical and Computer Engineering Vancouver Canada

ISBN: (纸本)9798350308365

Surrogate-assisted evolutionary algorithms (SAEAs) have demonstrated promising optimization performance in addressing expensive dynamic optimization problems or expensive multimodal optimization problems. However, none of existing SAEAs are designed specifically for tackling expensive dynamic multimodal optimization problems (EDMMOPs). Therefore, in this paper, a first SAEA for tackling EDMMOPs is proposed. First, a nearest density clustering is designed to divide the population into a number of subpopulations, enhancing the diversity of the population. Then, a surrogate-assisted evolutionary optimizer is developed to construct surrogate models for each subpopulation and evolve all solutions in subpopulations by means of the built surrogate models, accelerating the population's converge towards several optimal solutions rapidly. Finally, a transfer learning-based prediction is devised to generate initial samples for next environment by leveraging the stored training samples in the previous environments. To assess the performance of our proposed algorithm, a set of complex benchmark problems is adopted, and the experimental results confirm its superior performance over several competitive algorithms on most test cases. © 2024 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

mRS-DBFT: An improved consensus mechanism suitable for end-edge-cloud hybrid trust models 5

mRS-DBFT: An improved consensus mechanism suitable for end-e...

引用

5th International Conference on Frontiers Technology of Information and computer, ICFTIC 2023

作者： Zhai, Xue Pang, Shanchen Qiao, Sibo Yu, Shihang Qingdao Institute of Software College Computer Science and Technology Qingdao China Tiangong University School of Mechanical Engineering Tianjin China

ISBN: (纸本)9798350309034

As a three-terminal collaborative architecture of terminal, edge and cloud, end-edge-cloud is jointly participated by multiple institutions or organizations, and has the characteristics of a hybrid trust architecture of 'partially trustworthy, globally untrustworthy'. Traditional consensus algorithm designs are mostly used in relatively unified trust model environments and do not provide a mechanism for cross-organizational cooperation. Therefore, they cannot effectively solve the trust and consensus issues between organizations. We propose an improved DPoS-PBFT consensus mechanism based on reputation scoring (mRS-DBFT). The core idea of the mRS-DBFT is to add a reputation scoring mechanism based on the DPOS-PBFT consensus algorithm. The reputation score is calculated based on factors such as the node's historical behavior, contribution, and credibility. Nodes with higher reputation score have greater influence and decision-making power in the consensus process. This mechanism can solve the problem of mutual distrust among nodes of different organizations in the end-edge-cloud architecture, and each node participates in the consensus process based on its reputation score, thus forming a credible and consistent system, achieving cross-organizational consensus, and ensuring node trust and data consistency in an open end-edge-cloud environment. The experimental results demonstrate that the mRS-DBFT consensus algorithm helps select nodes with higher stability to participate in the consensus by evaluating the reputation of computing devices, it can reduce fluctuations in delay and improve the stability of the consensus process. © 2023 IEEE.

关键词： consensus mechanism delegated proof of stake end-edge-cloud computing practical byzantine fault tolerance reputation scoring

来源：评论

学校读者我要写书评

暂无评论

BGHR: Bridging the Gap Between HBox-Supervised and RBox-Supervised Oriented Object Detection via Adaptive Fine-Grained Sample Mining 39

BGHR: Bridging the Gap Between HBox-Supervised and RBox-Supe...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Fu, Chenlin Zhu, Yingying College of Computer Science and Software Engineering Shenzhen University China

ISBN: (纸本)157735897X

Oriented object detection is crucial for complex scenes such as aerial images and industrial inspection, providing precise delineation by minimizing background interference. Recently, the weakly-supervised detector paradigm H2RBox has demonstrated promise in learning rotated bounding box (RBox) from the more readily available horizontal bounding box (HBox), alleviating the scarcity and high cost of RBox annotations. However, these H2RBox-based methods have primarily focused on the gap in orientation information between HBox- and RBox-supervised approaches, overlooking the gap in training sample selection. In response, we propose the Adaptive Fine-grained Sample Mining (AFSM) strategy, which improves the selection of fine-grained training samples in HBox-supervised methods. AFSM assigns the best-matching prediction RBox to each ground truth (GT) HBox and selects positive samples based on these paired boxes. Furthermore, to effectively filter the best-matching prediction RBox for AFSM, we introduce the Prediction Rbox Assignment (PRA) scheme, employing Kullback-Leibler Divergence (KLD) as a localization quality metric. Additionally, we introduce an improved self-supervised branch loss (Lss*) to address the symmetry of weakly-supervised branch prediction boxes. Incorporating these core components (AFSM, PRA, and Lss*), we develop an end-to-end network architecture (BGHR) to further bridge the gap between HBox- and RBox-supervised oriented object detection. Extensive experiments on DOTA-v1.0 and DIOR-R demonstrate that BGHR achieves state-of-the-art performance compared to HBox-supervised methods without additional overhead. Even when benchmarked against fully supervised FCOS, our method still exhibits a slight performance advantage. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Trust-aware Cloudlet Federation Model for Secure Service Selection

Trust-aware Cloudlet Federation Model for Secure Service Sel...

引用

2023 International Conference on Energy, Power, Environment, Control, and Computing, ICEPECC 2023

作者： Shahid, Vaneeza Nayyer, Muhammad Ziad Ahmed, Usama GIFT University Department of Computer Science Gujranwala Pakistan Government College University Faisalabad Department of Software Engineering Faisalabad Pakistan

ISBN: (纸本)9781665476010

The introduction of Edge computing has pushed the horizon to the edge of the network and the user's proximity. The openness of data on the edge raised many issues about the security of data. Although edge computing is an extension of the cloud, besides this, its solutions to handle security threats are different from cloud computing because of its architectural dissimilarities. There is a need for a comprehensive mechanism to ensure the choice of secure service. For this purpose, the combination of trust would be a better approach to deal with the service selection tasks in edge computing. In this paper, a trust-aware cloudlet federation model has been proposed which ultimately helps in the safe service selection of an edge node. Before using a service 'A' of any edge node, the trust value of the edge node for service 'A' should be calculated, called Service Trust Value (STV). Then the edge nodes with a higher STV for service 'A' are filtered. Lastly, the model will select the edge node with a satisfactory value of trust for service 'A'. This proposed model will be beneficial in secure service selection. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Gliding over the Pareto Front with Uniform Designs 38

Gliding over the Pareto Front with Uniform Designs

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Xiaoyuan Li, Genghui Lin, Xi Zhang, Yichi Chen, Yifan Zhang, Qingfu Department of Computer Science City University of Hong Kong Hong Kong College of Computer Science and Software Engineering Shenzhen University China Department of Statistics Indiana University Bloomingtom United States Department of Mathematics and Computer Science Hong Kong Baptist University Hong Kong

Multiobjective optimization (MOO) plays a critical role in various real-world domains. A major challenge therein is generating K uniform Pareto-optimal solutions to approximate the entire Pareto front. To address this issue, this paper firstly introduces fill distance to evaluate the K design points, which provides a quantitative metric for the representativeness of the design. However, directly specifying the optimal design that minimizes the fill distance is nearly intractable due to the involved nested min − max − min problem structure. To address this, we propose a surrogate "max-packing" design for the fill distance design, which is easier to optimize and leads to a rate-optimal design with a fill distance at most 4× the minimum value. Extensive experiments on synthetic and real-world benchmarks demonstrate that our proposed paradigm efficiently produces high-quality, representative solutions and outperforms baseline MOO methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multitask Graph Neural Network for Knowledge Graph Link Prediction 9th

Multitask Graph Neural Network for Knowledge Graph Link Pred...

引用

9th International Conference of Pioneering computer Scientists, Engineers and Educators, ICPCSEE 2023

作者： Wang, Ye Yang, Jianhua Li, Lijie Yao, Jian College of Computer Science and Technology Harbin Engineering University Harbin China TaoBao Software Co. Ltd Hangzhou China

ISBN: (纸本)9789819959709

Predicting entities in knowledge graphs is a crucial research area, and convolutional neural networks (CNNs) have exhibited significant performance due to their ability to generate expressive feature embeddings. However, several existing methods in this field tend to disrupt entities and relational embeddings, disregarding the original translation characteristics in triples, leading to incomplete feature *** address this issue and preserve the translation characteristics of triples, the present study introduces a novel representation technique, termed MultiGNN. The suggested approach uses a graph convolutional neural network for encoding and implements a parameter sharing technique. It employs a convolutional neural network and a translation model as decoders. The model’s parameter space is expanded to effectively integrate translation characteristics into the convolutional neural network, which allows it to capture these characteristics and enhance the model’s performance. The proposed method in this paper has demonstrated significant enhancements in several metrics on the public benchmark dataset when compared to the baseline method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Staging of Different Tumor by Utilizing Laser Guidance (@405 nm) in CT Scan Images Along with Statistical Analysis

引用

Lasers in engineering 2025年第4-6期59卷 309-325页

作者： Amjad, M. Ullah, H. Siddique, M.A. Majid, M.A. Aleem, A. Akhtar, M. Gilanie, G. Abdullah-Al-Wadud, M. Farhan, M. Akram, A. Batool, Z. Nazir, A. Biophotonics Imaging Techniques Laboratory Institute of Physics The Islamia University of Bahawalpur 63100 Pakistan Department of Computer Science Faculty of Computing The Islamia University of Bahawalpur Bahawalpur Pakistan Dept. of Software Engineering College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia School of Earth Sciences and Engineering Hohai University Nanjing China

Early detection of lung cancer, liver cancer (HCC), and pancreatitis is crucial for effective treatment. This study assessed the use of laser guidance CT scans for diagnosis and staging. 26 patients of CT scan which were collected from BVH and civil hospital Bahawalpur, Pakistan. Visible light with a 405 nm wavelength is used. Results showed staging of lung cancer (2 at stage 1, 2 at stage 2, 3 at stage 4) and HCC (stages 1 to 4a). Pancreatic diseases detected included acute pancreatitis (44%), chronic pancreatitis (22%), gallstones (22%), and pancreatic tumors (11%). Alkaline phosphatase, SGOT, and blood urea levels were notably elevated in all three cancers compared to controls. CT scans show promise in identifying cancer stages and diagnosing pancreatitis, aiding in tailored treatment. Statistical analysis shows that alkaline phosphatase emerges as a potential biomarker for these conditions. ©2025 Old City Publishing, Inc.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Few-shot Semantic Segmentation via Perceptual Attention and Spatial Control 24

Few-shot Semantic Segmentation via Perceptual Attention and ...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Shi, Guangchen Zhu, Wei Wu, Yirui Zhao, Danhuai Zheng, Kang Lu, Tong National Key Lab for Novel Software Technology Nanjing University Nanjing China China Mobile Zijin Innovation Insititute Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9798400706868

Few-shot semantic segmentation (FSS) aims to locate pixels of unseen classes with clues from a few labeled samples. Recently, thanks to profound prior knowledge, diffusion models have been expanded to achieve FSS tasks. However, due to probabilistic noising and denoising processes, it is difficult for them to maintain spatial relationships between inputs and outputs, leading to inaccurate segmentation masks. To address this issue, we propose a Diffusion-based Segmentation network (DiffSeg), which decouples probabilistic denoising and segmentation processes. Specifically, DiffSeg leverages attention maps extracted from a pretrained diffusion model as support-query interaction information to guide segmentation, which mitigates the impact of probabilistic processes while benefiting from rich prior knowledge of diffusion models. In the segmentation stage, we present a Perceptual Attention Module (PAM), where two cross-attention mechanisms capture semantic information of support-query interaction and spatial information produced by the pretrained diffusion model. Furthermore, a self-attention mechanism within PAM ensures a balanced dependence for segmentation, thus preventing inconsistencies between the aforementioned semantic and spatial information. Additionally, considering the uncertainty inherent in the generation process of diffusion models, we equip DiffSeg with a Spatial Control Module (SCM), which models spatial structural information of query images to control boundaries of attention maps, thus aligning the spatial location between knowledge representation and query images. Experiments on PASCAL-5i and COCO datasets show that DiffSeg achieves new state-of-the-art performance with remarkable advantages. © 2024 ACM.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Empirical Study on Mispronunciation Detection for Tajweed Rules during Quran Recitation 6

Empirical Study on Mispronunciation Detection for Tajweed Ru...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Alsahafí, Yousef S. Asad, Muhammad Department of Information technology Computing and Information technology Khulis College University of Jeddah Jeddah Saudi Arabia Department of Computer and Software Engineering College of Electrical and Mechanical Engineering National University of Science and Technology Islamabad Pakistan

ISBN: (纸本)9798350373875

This paper presents an extensive empirical study aiming to identify the optimal combination of feature extraction techniques and machine learning algorithms, including deep learning, for automated mispronunciation detection during Quran recitation. Three feature extraction methods-Mel-Frequency Cepstral Coefficients (MFCC), Spectrogram, and Kaldi pitch - are systematically evaluated in conjunction with a diverse set of classifiers, including Gradient Boosting (GB), Support Vector Machines (SVM), Logistic Regression (LR), Random Forest (RF), Artificial Neural Network (ANN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks. The study leverages the QDAT dataset, comprising 1500 audio samples from 150 readers, with metadata specifying age, gender, and three distinct rules for mispronunciation detection. Experimental results demonstrate that the integration of MFCC with deep learning classifiers consistently achieves the highest performance across multiple evaluation metrics. Model robustness is validated using receiver operator characteristic curves (ROC) and accuracy metrics. © 2024 IEEE.

关键词： Speech 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：