检索结果-内蒙古大学图书馆

Business Analytics for Technology and Security (ICBATS), International Conference on

作者： Muhammad Waseem Iqbal Khowla Khaliq Nidal A. Al-Dmour Muhammad Aqeel Nasir Ali K. Hamid Department of Software Engineering Superior University Lahore Pakistan Department of Computer Sciecnce Superior University Lahore Pakistan Department of Computer Engineering College of Engineering Mutah University Jordan School of Computer Science NCBA&E Lahore Pakistan Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Science Superior University Lahore Pakistan

Internet of things is progressing very rapidly and involving multiple domains of everyday life including environment, governance, healthcare system, transportation system, energy management system, etc. smart city is a platform for collecting and storing the information that is accessed through various sensor-based IoT devices and make their information available in required and authorized domains. This interoperability can be achieved by semantic web technology. In this paper, I have reviewed multiple papers related to IoT in Smart Cities and presented a comparison among the semantic parameters. Moreover, I’ve presented my future domain of research which is about delivering the COVID-19 patients report to the concerned domains by the healthcare system domain.

关键词： Semantic Web COVID-19 Smart cities Scalability Semantics Transportation Medical services

来源：评论

学校读者我要写书评

暂无评论

iCTS: Iterative and Hierarchical Clock Tree Synthesis With Skew-Latency-Load Tree

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Li, Weiguo Huang, Zhipeng Yu, Bei Zhu, Wenxing Chen, Jian He, Zhixue Li, Xingquan South China University of Technology School of Software Engineering Guangzhou China Pengcheng Laboratory Shenzhen China Beijing Institute of Open Source Chip Beijing China Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong Hong Kong Fuzhou University Center for Discrete Mathematics and Theoretical Computer Science Fuzhou China

The advancement of modern clock tree synthesis (CTS) encounters a bottleneck, primarily due to the difficulty in achieving multi-objective co-optimization among complex design processes. To concurrently optimize skew, latency, and load capacitance, we propose an iterative and hierarchical CTS framework, which is composed of clustering, topology generation and routing, buffering, and optimization. First, we introduce a capacitance-based metric to achieve adaptive balanced clustering and optimize the cluster results through simulated annealing. Second, to construct a clock tree with lower latency, load capacitance, and skew, we introduce the skew-latency-load tree (SLLT), which combines the advantages of bound skew tree and Steiner shallow-light tree, and we propose an effective SLLT construction algorithm. Third, to further optimize CTS result by buffering, we introduce the critical wirelength evaluation (CWE) to evaluate the capability of each buffer, and propose the insertion delay estimation (IDE) to reduce the evaluation bias during buffering, then design the iterative skew convergence algorithm (ISCA) to achieve complete convergence of skew. We validate our solution using 28nm process technology. Compared to our method, the commercial tool increases skew, latency, and clock capacitance by 39.5%, 13.0%, and 18.5%, respectively, while the OpenROAD by 101.6%, 50.7%, and 25.5%, respectively. © 1982-2012 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Snapshot boosting: a fast ensemble framework for deep neural networks

引用

science China(Information sciences) 2020年第1期63卷 77-88页

作者： Wentao ZHANG Jiawei JIANG Yingxia SHAO Bin CUI Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications Department of Computer Science Beijing Key Lab of Intelligent Telecommunications Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications Key Lab of High Confidence Software Technologies Department of Computer SciencePeking University

Boosting has been proven to be effective in improving the generalization of machine learning models in many fields. It is capable of getting high-diversity base learners and getting an accurate ensemble model by combining a sufficient number of weak learners. However, it is rarely used in deep learning due to the high training budget of the neural network. Another method named snapshot ensemble can significantly reduce the training budget, but it is hard to balance the tradeoff between training costs and diversity. Inspired by the ideas of snapshot ensemble and boosting, we propose a method named snapshot boosting. A series of operations are performed to get many base models with high diversity and accuracy, such as the use of the validation set, the boosting-based training framework, and the effective ensemble strategy. Last, we evaluate our method on the computer vision(CV) and the natural language processing(NLP) tasks, and the results show that snapshot boosting can get a more balanced trade-off between training expenses and ensemble accuracy than other well-known ensemble methods.

关键词： ensemble learning deep learning boosting neural network snapshot ensemble

来源：评论

学校读者我要写书评

暂无评论

Mu-Net:Multi-Path Upsampling Convolution Network for Medical Image Segmentation

引用

computer Modeling in engineering & sciences 2022年第4期131卷 73-95页

作者： Jia Chen Zhiqiang He Dayong Zhu Bei Hui Rita Yi Man Li Xiao-Guang Yue School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China Department of Economics and Finance/Sustainable Real Estate Research Center Hong Kong Shue Yan UniversityHongkongChina Rattanakosin International College of Creative Entrepreneurship Rajamangala University of Technology RattanakosinNakhon Pathom73170Thailand Department of Computer Science and Engineering School of SciencesEuropean University CyprusNicosia1516Cyprus CIICESI ESTGPolit′ecnico do Porto4610-156FelgueirasPortugal

Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment *** 2015,U-Net-based approaches have been widely used formedical image *** purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature ***,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level *** high-level information can make the segmentationmore *** this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level *** MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive *** proposed MU-Net architecture is evaluated based on three different medical imaging *** experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different *** the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.

关键词： Medical image segmentation MU-Net(multi-path upsampling convolution network) U-Net clinical diagnosis encoder-decoder networks

来源：评论

学校读者我要写书评

暂无评论

An optimized deep learning based technique for grading and extraction of diabetic retinopathy severities

引用

Informatica (Slovenia) 2021年第5期45卷 659-665页

作者： Zhang, Qiu-Ming Luo, Jing Cengiz, Korhan School of Computer science China University of Geosciences Wuhan430074 China Practice training center Wuhan Vocational College of Software and Engineering Wuhan430205 China Department of Electrical - Electronics Engineering Trakya University Edirne22030 Turkey

The prognosis of Diabetic Retinopathy (DR) requires regular eye examinations, as ophthalmologists depends on fundus segmentation to treat DR pathologies. Automated approaches for detection, segmentation and classification have developed as an imperative area of research for the effective diagnosis of DR for the treatment of serious eye conditions that prevent visual impairment. Diagnosis of various DR lesions, as well as different severities, helping the ophthalmologists to analyze variations in fundus images and take the necessary measures before the disease progresses. Deep learning techniques have evolved as a recent advent to combat the issues of conventional machine leaning based methods. An optimized deep learning framework is proposed in this article for grading and extraction of diabetic retinopathy severities. This involves various steps like background segmentation, feature set extraction, feature optimization using Cuckoo search and Convolutional Neural Network (CNN) severity grade classification. The method was validated on two standard datasets MESSIDOR and IDRiD. The proposed method yields an accuracy value of 97.55%, cross entropy loss of 0.367 and time intricacy of 20 mins and 15 secs for MESSIDOR and 98.02% cross entropy loss of 0.345 and time intricacy of 22 mins and 21 secs for IDRiD dataset;respectively. The state-of-the-art comparison depicts that the proposed CNN based method provides a maximum accuracy improvement of 10.46% comparative to the existing methodology. The proposed framework yields better accuracy by procurement of the investigative outcomes acquired exhibits proficient DR determination. © 2021 Slovene Society Informatika. All rights reserved.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement Units 39

HiPoser: 3D Human Pose Estimation with Hierarchical Shared L...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liao, Guorui Zheng, Chunyuan Cheng, Li Xie, Haoyu Huang, Shanshan Liao, Jun Li, Haoxuan Liu, Li School of Big Data & Software Engineering Chongqing University China School of Mathematical Sciences Peking University China Department of Electrical and Computer Engineering University of Alberta Canada Center for Data Science Peking University China

ISBN: (纸本)157735897X

This paper considers the challenging problem of 3D Human Pose Estimation (HPE) from a sparse set of Inertial Measurement Units (IMUs). Existing efforts typically reconstruct a pose sequence by either directly tackling whole-body motions or focusing on distinctive spatio-temporal features of local body parts. Unfortunately, these methods ignore existing interdependent motor synergies amongst body parts, which may lead to pose estimation with ambiguous local parts. This observation motivates us to propose a hierarchical learning-based approach, HiPoser, which utilizes a hierarchical shared structure using Mamba blocks as the backbone to focus on the following estimation tasks, involving: 1) torso pose, 2) lower limbs pose, 3) upper limbs pose, and finally 4) global translation. These tasks selectively incorporate body motion states and are to be carried out sequentially in reconstructing part-based poses, which are amalgamated to estimate the final full-body pose with the global translation that satisfies inter-part consistencies. Our hierarchical structure allows HiPoser the flexibility in prioritizing different aspects of pose estimation, to emphasize more on detail or stability. Empirical evaluations over three benchmark datasets demonstrate the superiority of HiPoser over existing state-of-the-art models, suggesting that analyzing the synergistic movement of body parts is indeed important for advancing IMU-based 3D HPE. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Metric system

来源：评论

学校读者我要写书评

暂无评论

A Secure Authentication Framework for Consumer Mobile Crowdsourcing Networks

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Aldosary, Abdallah Tanveer, Muhammad Ahmad, Musheer Maghrabi, Louai A. Ahmed, Emad A. Hussain, Amir El-Latif, Ahmed A. Abd Department of Computer Engineering Prince Sattam bin Abdulaziz University Riyadh Wadi Addwasir11991 Saudi Arabia University of Management and Technology Department of Computer Science Lahore54770 Pakistan Jamia Millia Islamia Department of Computer Engineering New Delhi110025 India University of Business and Technology College of Engineering Department of Software Engineering Jeddah Saudi Arabia South Valley University Faculty of Computers and Information Department of Computer Science Qena Egypt Edinburgh Napier University United Kingdom Prince Sultan University EIAS Data Science Lab College of Computer and Information Sciences Center of Excellence in Quantum and Intelligent Computing Riyadh11586 Saudi Arabia Menoufia University Faculty of Science Department of Mathematics and Computer Science Shebin El-Koom32511 Egypt

The Mobile crowdsourcing network (MCN) leverages collaborative intelligence to solve complex tasks through group cooperation. It comprises three main components: the end-user, the service provider, and the mobile user. The end-user requests crowd-sensing and computing services from the service provider, who handles task decomposition, distribution, re-composition, and recommendation. Mobile users perform the crowd sensing and computing tasks. Despite its benefits, MCN faces significant security and privacy challenges. Communications between the service provider and the end-user involve sensitive data, and mobile users and service providers communicate over open channels, making them vulnerable to security threats. To address these concerns, we propose a secure authentication framework for MCN, called SAF-MCN. This framework combines the lightweight cryptographic primitive ' ASCON' with elliptic curve cryptography. SAF-MCN allows the service provider to authenticate mobile users before they join the MCN. Once authenticated, a secure channel is established for encrypted communication over the public Internet. The security of SAFMCN is validated using both formal and informal methods, demonstrating its resilience against potential attacks. The use of Scyther further ensures the security of SAF-MCN. Comparative analysis shows that SAF-MCN is superior in terms of security features, computational efficiency, and communication cost. © 1975-2011 IEEE.

关键词： ASCON Authenticated Encryption Authentication Mobile Crowdsourcing Network Scyther Security

来源：评论

学校读者我要写书评

暂无评论

FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection

FishEye8K: A Benchmark and Dataset for Fisheye Camera Object...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Gochoo, Munkhjargal Otgonbold, Munkh-Erdene Ganbold, Erkhembayar Hsieh, Jun-Wei Chang, Ming-Ching Chen, Ping-Yang Dorj, Byambaa Al Jassmi, Hamad Batnasan, Ganzorig Alnajjar, Fady Abduljabbar, Mohammed Lin, Fang-Pang United Arab Emirates University Department of Computer Science and Software Engineering United Arab Emirates United Arab Emirates University Emirates Center for Mobility Research United Arab Emirates National Yang Ming Chiao Tung University College of AI and Green Energy Taiwan University at Albany - State University of New York NY United States National Yang Ming Chiao Tung University Department of Computer Science Taiwan Mongolian University of Science and Technology Mongolia National Center for High-Performance Computing Taiwan

ISBN: (纸本)9798350302493

With the advance of AI, road object detection has been a prominent topic in computer vision, mostly using perspective cameras. Fisheye lens provides omnidirectional wide coverage for using fewer cameras to monitor road intersections, however with view distortions. To our knowledge, there is no existing open dataset prepared for traffic surveillance on fisheye cameras. This paper introduces an open FishEye8K benchmark dataset for road object detection tasks, which comprises 157K bounding boxes across five classes (Pedestrian, Bike, Car, Bus, and Truck). In addition, we present benchmark results of State-of-The-Art (SoTA) models, including variations of YOLOv5, YOLOR, YOLO7, and YOLOv8. The dataset comprises 8,000 images recorded in 22 videos using 18 fisheye cameras for traffic monitoring in Hsinchu, Taiwan, at resolutions of 1080×1080 and 1280×1280. The data annotation and validation process were arduous and time-consuming, due to the ultra-wide panoramic and hemispherical fisheye camera images with large distortion and numerous road participants, particularly people riding scooters. To avoid bias, frames from a particular camera were assigned to either the training or test sets, maintaining a ratio of about 70:30 for both the number of images and bounding boxes in each class. Experimental results show that YOLOv8 and YOLOR outperform on input sizes 640×640 and 1280×1280, respectively. The dataset will be available on the GitHub link with PASCAL VOC, MS COCO, and YOLO annotation formats. The FishEye8K benchmark will provide significant contributions to the fisheye video analytics and smart city applications. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Positive Sample Augmentation with Graph Mixup for DDI Prediction

Positive Sample Augmentation with Graph Mixup for DDI Predic...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Hailong Yu Xinyu Ma Xu Chu Yasha Wang Rengyu Wu Qiang Zhou School of Computer Science Peking University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Shenzhen Center for Prehospital Care Shenzhen China

Unexpected drug-drug interactions (DDIs) may occur when drugs are taken at the same time. Harmful DDIs can reduce drug efficacy and even increase unintended toxicity, putting patients treated with different drugs at risk. Previous works on DDI prediction mainly rely on hand-engineered domain knowledge, which is laborious to obtain and cannot handle the problem of sparse positive samples in DDI prediction. Even though some works attempt to handle data sparsity from the perspective of data distribution to improve the generalization ability of the model, they are limited to negative samples distribution. To address these limitations, we propose a novel method, Graph Mixup for Positive Sample Augmentation (GMPSA), to effectively combine positive drug molecule graphs and extend the training distribution to alleviate the problem of sparse positive samples. To model the graph signals and graph structures jointly, we map source graphs to the fused gromov-wasserstein metric space, then minimizes the weighted sum of transportation distances between the distributions of the source graphs and the objective graph in this metric space. By doing so, interpolated positive samples improve the the generalization error of the model. Experiments results on a real-word dataset show that our method effectively improve the perfomermance in DDI prediction on a state-of-the-art architecture. Further studies also verify the robustness and generalizability of GMPSA under different GNN backbones and parameter settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attention weights accurately predict language representations in the brain

Attention weights accurately predict language representation...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Lamarre, Mathis Chen, Catherine Deniz, Fatma Institute of Software Engineering and Theoretical Computer Science Technische Universität Berlin Germany Bernstein Center for Computational Neuroscience Berlin Germany Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Helen Wills Neuroscience Institute University of California Berkeley United States

In Transformer-based language models (LMs) the attention mechanism converts token embeddings into contextual embeddings that incorporate information from neighboring words. The resulting contextual hidden state embeddings have enabled highly accurate models of brain responses, suggesting that the attention mechanism constructs contextual embeddings that carry information reflected in language-related brain representations. However, it is unclear whether the attention weights that are used to integrate information across words are themselves related to language representations in the brain. To address this question we analyzed functional magnetic resonance imaging (fMRI) recordings of participants reading English language narratives. We provided the narrative text as input to two LMs (BERT and GPT-2) and extracted their corresponding attention weights. We then used encoding models to determine how well attention weights can predict recorded brain responses. We find that attention weights accurately predict brain responses in much of the frontal and temporal cortices. Our results suggest that the attention mechanism itself carries information that is reflected in brain representations. Moreover, these results indicate cortical areas in which context integration may occur. © 2022 Association for Computational Linguistics.

关键词： Brain

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：