检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Perera, Judith Tempero, Ewan Tu, Yu-Cheng Blincoe, Kelly Galster, Matthias School of Computer Science The University of Auckland Auckland1010 New Zealand Department of Electrical Computer and Software Engineering The University of Auckland Auckland1010 New Zealand Department of Computer Science and Software Engineering College of Engineering University of Canterbury Christchurch1010 New Zealand

software practitioners can make sub-optimal decisions concerning requirements during gathering, documenting, prioritizing, and implementing requirements as software features or architectural design decisions - this is captured by the metaphor 'Requirements Technical Debt (RTD).' In our prior work, we developed a conceptual model to understand the quantification of RTD and support its management. In this paper, we present our perspective and the vision to apply the lens of RTD to software requirements concerning veracity, i.e., requirements related to truth, trust, authenticity, and demonstrability in software-intensive systems. Our goal is to cultivate awareness of veracity as an important concern and eventually support the management of RTD for software requirements concerning veracity, what we term as 'Veracity Debt,' through its quantification. Copyright © 2024, The Authors. All rights reserved.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Unikdd: A Unified Generative Model for Knowledge-Driven Dialogue

SSRN

引用

SSRN 2024年

作者： Wang, Qian Chen, Yan Wang, Yang Wang, Xu School of Computer Science and Software Engineering Southwest Petroleum University Chengdu610500 China College of Computer Science Sichuan University Chengdu610065 China

knowledge-driven dialogue (KDD) is to introduce an external knowledge base,generating an informative and fluent response. However, previous works employ different models to conduct the sub-tasks of KDD, ignoring the connection between sub-tasks and resulting in a difficulty of training and inference. Tosolve those issues above, we propose the UniKDD, a unified generative model for KDD, which models all sub-tasks into a generation task, enhancing the connection between tasks and facilitating the training and inference. Specifically, UniKDD simplifies the complex KDD tasks into three main sub-tasks, i.e., entity prediction, attribute prediction, and dialogue generation. These tasks are transformed into a text generation task and trained by an end-to-end way. In the inference phase, UniKDD first predicts a set of entities used for current turn dialog according to the dialogue history. Then, for each predicted entity, UniKDD predicts the corresponding attributes by the dialogue history. Finally, UniKDD generates a high-quality and informative response using the dialogue history and predicted knowledge triplets. The experimental results show that our proposed UniKDD can perform KDD task well and outperform the baseline on the evaluation of knowledge selection and response generation. The code is available athttps://***/qianandfei/***. © 2024, The Authors. All rights reserved.

关键词： Petroleum reservoir evaluation

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Cardiac MRI Segmentation Based on Generative Adversarial Network and Variational Auto-Encoder

Semi-supervised Cardiac MRI Segmentation Based on Generative...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Li, Shaojie Zhang, Yifan Yang, Xuan Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9781665401265

Segmentation of the heart structure plays an essential role in cardiac diseases diagnosis and treatment planning. This paper proposes a semi-supervised learning network for multi-objective segmentation of cardiac MRI data, which comprises a U-Net as encoder and a conditional generative adversarial network (GAN) as the decoder. The process of segmentation takes the predictive result as latent variables and aims to estimate the distribution of the latent. We pre-align cardiac images to each other in an affine way and pre-train the GAN using a small amount of annotated data. A loss function focusing on the region of interest (ROI) is proposed. Experimental results on MICCAI 2020 Multi-Centre, Multi-Vendor MultiDisease Cardiac Image Segmentation Challenge (M Ms) dataset show that the performance of our semi-supervised learning network not only reaches or exceeds the supervised methods in multi-object segmentation but also has the generalization ability of supervised learning-based networks. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Periodically Updating Rough Approximations Upon Multi-Dimension Variation 2

A Novel Approach for Periodically Updating Rough Approximati...

引用

2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022

作者： Nosheen, Faryal Qamar, Usman Raza, Summair National University of Sciences and Technology Department of Computer and Software Engineering College of Electrical and Mechanical Engineering Islamabad Pakistan Virtual University of Pakistan Department of Computer Science and Information Technology Lahore Pakistan

ISBN: (纸本)9781665498197

In present era, transformation of almost all fields of life toward digitalization, poses various challenges. One of them is effective data analysis of large datasets and its complexity multiplies when dataset evolves with time. Dominance based rough set theory is a mathematical based tool, which efficiently probes hidden patterns from preference ordered based datasets. But in case of large datasets, computation of DRSA approximations becomes crucial step. In conventional DRSA algorithm, approximation sets have to be re-calculated when some change occurs in data over time. Therefore, repetitive calculations further increase the computational cost of approximations in real-time domain. In this paper, we researched the execution cost of approximations and designed a periodic approach to efficiently update DRSA approximations when variations occur in an object set and value set of decision attribute. We tested and compared the proposed dynamic approach with conventional approach and another dynamic approach, using UCI datasets. The results have shown that the proposed approach marked 98% reduction in computational time in comparison with conventional approach and 25% reduction in comparison with dynamic approach while updating DRSA approximations upon multi-dimensional variations. © 2022 IEEE.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Reparameterizable Dual-Resolution Network for Real-Time Semantic Segmentation

SSRN

引用

SSRN 2025年

作者： Yang, Guoyu Shi, Daming Wang, Yuan College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Zhejiang University of Technology China

Semantic segmentation plays a key role in applications such as autonomous driving and medical image. Although existing real-time semantic segmentation models achieve a commendable balance between accuracy and speed, their multi-path blocks still affect overall speed. To address this issue, this study proposes a Reparameterizable Dual-Resolution Network (RDRNet) dedicated to real-time semantic segmentation. Specifically, RDRNet employs a two-branch architecture, utilizing multi-path blocks during training and reparameterizing them into single-path blocks during inference, thereby enhancing both accuracy and inference speed simultaneously. Furthermore, we propose the Reparameterizable Pyramid Pooling Module (RPPM) to enhance the feature representation of the pyramid pooling module without increasing its inference time. Experimental results on the Cityscapes, CamVid, and Pascal VOC 2012 datasets demonstrate that RDRNet outperforms existing state-of-the-art models in terms of both performance and speed. Specifically, without using ImageNet pre-trained weight, RDRNet achieves 76.8\% mIoU and 134.6 FPS on the Cityscapes validation set with an RTX 3090. The code is available at \url{https://***/gyyang23/RDRNet}. © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploring Natural Language Processing Model Acceleration in Molecular Dynamics Simulation Using High-Performance Computing and Machine Learning

Exploring Natural Language Processing Model Acceleration in ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Du, Qi Wang, Feng Huang, Hui Wan, Heng Wu, Xiaoyu Wu, Chengkun Hunan University College of Computer Science and Electronic Engineering Hunan Changsha China Hunan Institute of Scientific and Technical Information Hunan Changsha China National University of Defense Technology Laboratory of Digitizing Software for Frontier Equipment Hunan Changsha China

ISBN: (纸本)9798350386226

In molecular dynamics simulations, the integral methods used to calculate molecular trajectories, such as the Verlet integral method, involve significant computational costs. On the premise of ensuring the accuracy of simulation, how to effectively reduce the amount of computation is always a challenging problem. This paper applies Natural Language Processing models to simulate molecular motion trajectories in molecular dynamics, integrating the MPI programming model and machine learning on a high-performance computing platform to achieve MPI parallelization during model training and inference. The results indicate that different types of neural network architectures have a significant impact on inference performance and accuracy. When using the deep spatio-temporal networks model, the mean absolute error is 0.0032. At an atomic scale of 3M, the parallel efficiency with 1024 computational nodes exceeds 90%, demonstrating excellent parallel performance. © 2024 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

Hybrid Power Generation Forecasting Using an Intellectual Evolutionary Energy-Preserve Rate Clustering Technique 1

引用

10th International Conference on Innovations in computer science and engineering, ICICSE 2022

作者： Webber, Julian L. Jayagopal, Vellingiri Mehbodniya, Abolfazl Sengan, Sudhakar Velayutham, Priya Rangasamy, Rajasekar Stalin David, D. Doha Kuwait Department of Software & System Engineering School of Information Technology & Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627152 India Department of Computer Science and Engineering Paavai Engineering College Tamil Nadu Namakkal637018 India Department of Computer Science and Engineering GITAM School of Technology GITAM University Karnataka Bengaluru561203 India Department of Information Technology Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Tamil Nadu Chennai600072 India

ISBN: (数字)9789811974557

ISBN: (纸本)9789811974540

The significant growth of Wind Power (WP) has significant challenges due to the inconsistency and uncertainty of Wind Power Generation (WPG) to ensure the power system. Solar energy and WP calculation are great ways to overcome the problem. Mainly voltage and frequency fluctuations and harmonics have a high impact on the power generation and distribution system;in any high case, the power quality of grid systems is reduced. This can be primarily solved with proper design, advanced rapid response control facilities and optimization of power systems. A new type of Multi-term Wind Energy (WE) with an IEEE 30 bus forecasting system based on digital weather forecasting and error modification methods is presented. From the Evolutionary Energy- Preserve Rate Clustering (EEPRC) Technique-based technique for the evaluates the probability ratio in Solar and wind error energy prediction, the error assessment model is proposed, which has the advantage of estimating from real wind farms and statistical Weather Forecast (WF) data and has proven to be a nominal method for improving the predictive accuracy of Multi-term WPG. The primary step of the Energy-Preserve Rate Clustering (EPRC) method is to calculate the uncertainty of real-time data with the predicted value. The computed values are helpful for the increases in Solar WPG production. The proposed wind forecasting system is utilized in the Coastal area-based energy generation. Also, it has been demonstrated that wind speed and WPG with its probability ratio have been evaluated with the EEPRC-based forecasting method, especially for its powerful predictive capability for the complex properties of the controller function. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Detection of Cardiovascular Diseases Using ECG Images

Deep Learning Based Detection of Cardiovascular Diseases Usi...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： P Ananthi K Nirmala Devi Pradisa. T Department of Computer Technology Kongu Engineering College Perundurai TamilNadu Department of Computer Science(PG) Kristu Jayanti College Bangaluru MSc Software Systems Kongu Engineering College Perundurai TamilNadu

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

In today's world, cardiovascular disease is still a major concern. The electrocardiogram (ECG) is one of the most trustworthy non-invasive tools for identifying heart problems. ECG interpretation, however, takes a lot of effort and specialized knowledge. The quality and effectiveness of medical care are enhanced by the development of a revolutionary technique for early disease detection. Using a public dataset of ECG scans from cardiac patients, this study leveraged deep learning algorithms to predict two primary cardiac abnormalities: abnormal heartbeat and normal person classes. The low-scale pre-trained deep neural Alex Net was used to study the transfer learning process. To forecast cardiac issues, a novel Convolutional Neural Network (CNN) architecture was put out. We used the conventional deep learning methods, VGG-16, Resnet50, RNN, and LSTM, to feature-extracted data utilizing the previously mentioned pre-trained models and our suggested LSTM model. The experimental results show that the LSTM model outperforms the previous attempts in terms of performance measures.

关键词： Deep learning Transfer learning Medical services Electrocardiography Prediction algorithms Data models Convolutional neural networks Cardiovascular diseases Long short term memory Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Communication-Efficient Federated Learning in Mobile Edge Environments

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Jia, Ninghui Qu, Zhihao Ye, Baoliu Wang, Yanyan Hu, Shihong Guo, Song Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Nanjing211100 China Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing210023 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Kowloon Hong Kong

In traditional centralized machine learning, transmitting raw data to a cloud center incurs high communication costs and raises privacy concerns. This is particularly challenging in mobile edge environments, where devices are dynamic and resource-constrained. Federated Learning (FL) addresses these issues by allowing devices to train models locally and upload parameters to a central server without sharing local data. However, limited wireless channel resources and dynamic transmission performance make communication overhead a major bottleneck of FL in mobile edge environments. Concerning this challenge, this survey provides a comprehensive summary of methods to improve communication efficiency in FL, focusing on: 1) minimizing communication complexity to reduce total transmission volume, 2) scheduling resources appropriately to improve training efficiency, 3) utilizing over-the-air computation (OTA) to integrate computation into communication for accommodating the computation/communication characteristics of FL in mobile edge environments. Thus, this work analyzes research from the perspective of convergence and data heterogeneity to reduce communication rounds by optimizing algorithm performance. We hope that this survey could offer insights into communication-efficient FL for future research. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Online experiments based on the CTF model for information security MOOC courses 16

Online experiments based on the CTF model for information se...

引用

16th IEEE International Conference on computer science and Education, ICCSE 2021

作者： Yan, Qiao Lai, Weimin Wang, Zhiqiang Shenzhen University College of Computer Science Software Engineering Shenzhen China

ISBN: (纸本)9781665414685

With the development of the Internet, more and more courses are being launched online. However, for information security courses involving a large number of experiments, the time and space constraints and the varying levels of online learners make it difficult to conduct experiments. In this paper, we propose a method that combines online experiments with the Capture The Flag (CTF) model. Compared with traditional information security experiments, the introduction of CTF solution mode will be able to stimulate student's interest in information security. Based on dynamic scoring rules, the system can automatically grade individual tests, which can give more objective evaluation and reduce the pressure of teachers to correct assignments. In addition, the experiment questions can be automatically customized according to the overall level of the class. © 2021 IEEE.

关键词： Security of data

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：