检索结果-内蒙古大学图书馆

Proceedings of the 38th IEEE/ACM International Conference on Automated software engineering

作者： Cheryl Lee Tianyi Yang Zhuangbin Chen Yuxin Su Michael R. Lyu Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China School of Software Engineering Sun Yat-sen University Zhuhai China. School of Software Engineering Sun Yat-sen University Zhuhai China

ISBN: (纸本)9798350329964

Ensuring the reliability and user satisfaction of cloud services necessitates prompt anomaly detection followed by diagnosis. Existing techniques for anomaly detection focus solely on real-time detection, meaning that anomaly alerts are issued as soon as anomalies occur. However, anomalies can propagate and escalate into failures, making faster-than-real-time anomaly detection highly desirable for expediting downstream analysis and intervention. This paper proposes Maat, the first work to address anomaly anticipation of performance metrics in cloud services. Maat adopts a novel two-stage paradigm for anomaly anticipation, consisting of metric forecasting and anomaly detection on forecasts. The metric forecasting stage employs a conditional denoising diffusion model to enable multi-step forecasting in an auto-regressive manner. The detection stage extracts anomaly-indicating features based on domain knowledge and applies isolation forest with incremental learning to detect upcoming anomalies. Thus, our method can uncover anomalies that better conform to human expertise. Evaluation on three publicly available datasets demonstrates that Maat can anticipate anomalies faster than real-time comparatively or more effectively compared with state-of-the-art real-time anomaly detectors. We also present cases highlighting Maat's success in forecasting abnormal metrics and discovering anomalies.

关键词： could computing

来源：评论

学校读者我要写书评

暂无评论

Accuracy and Interpretability: Developing a computer-Aided Diagnosis System for Pneumonia Detection in Chest X-Ray Images

Accuracy and Interpretability: Developing a Computer-Aided D...

引用

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Krishna Mridha Apu Chandra Barman Shekhar Biswas Shakil Sarkar Sunanda Biswas Masrur Ahsan Priyok Computer Engineering Marwadi University Rajkot India Department of Pharmacy Marwadi University Rajkot India Computer Science and Engineering BRAC University Software Engineering Tianjin University China

People of all ages can contract pneumonia, a deadly respiratory illness that is more common in underdeveloped countries. For successful treatment and higher survival rates, pneumonia must be accurately and quickly diagnosed. While chest X-ray imaging is a frequently used diagnostic technique for detecting pneumonia, its interpretation can be arbitrary and error-prone. In this study, we used a convolutional neural network (CNN) architecture to construct a computer-aided diagnostic system for pneumonia identification in chest X-ray images. Our dataset comprises 5,863 anterior-posterior view X-ray pictures that have been divided into two categories: normal and pneumonia. The photos were chosen from the Guangzhou Women and Children's Medical Center's pediatric patients between the ages of one and five, and they were first checked for quality control before being judged by two highly qualified doctors. A third expert also reviewed the assessment set to verify correctness. For the test set, our CNN model performed well, with 99% accuracy, 99% precision, 99.25% f1-score, and 98% specificity. To improve the interpretability of our model, we also included explainable AI techniques like Grad-CAM and Grad-CAM++. These approaches offer insights into CNN's decision-making process. Our computer-aided diagnosis system offers a trustworthy and unbiased method for detecting pneumonia in chest X-ray pictures, which can help with the quick identification and treatment of this potentially fatal condition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A generative deep learning framework for airfoil flow field prediction with sparse data

引用

Chinese Journal of Aeronautics 2022年第1期35卷 470-484页

作者： Haizhou WU Xuejun LIU Wei AN Hongqiang LYU MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjing 211106China Key Laboratory of Aerodynamic Noise Control Mianyang 621000China State Key Laboratory of Aerodynamics Mianyang 621000China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 210023China College of Aerospace Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China

Deep learning has been probed for the airfoil performance prediction in recent *** with the expensive CFD simulations and wind tunnel experiments,deep learning models can be leveraged to somewhat mitigate such expenses with proper ***,effective training of the data-driven models in deep learning severely hinges on the data in diversity and *** this paper,we present a novel data augmented Generative Adversarial Network(GAN),daGAN,for rapid and accurate flow filed prediction,allowing the adaption to the task with sparse *** presented approach consists of two modules,pre-training module and fine-tuning *** pre-training module utilizes a conditional GAN(cGAN)to preliminarily estimate the distribution of the training *** the fine-tuning module,we propose a novel adversarial architecture with two generators one of which fulfils a promising data augmentation operation,so that the complement data is adequately incorporated to boost the generalization of the *** use numerical simulation data to verify the generalization of daGAN on airfoils and flow conditions with sparse training *** results show that daGAN is a promising tool for rapid and accurate evaluation of detailed flow field without the requirement for big training data.

关键词： CFD Flow field Generative adversarial networks(GANs) Sparse data Supercritical airfoil

来源：评论

学校读者我要写书评

暂无评论

Time-Aware Missing Traffic Flow Prediction for Sensors with Privacy-Preservation 11th

Time-Aware Missing Traffic Flow Prediction for Sensors with ...

引用

11th International Conference on computer engineering and Networks, CENet2021

作者： Qi, Lianyong Wang, Fan Xu, Xiaolong Dou, Wanchun Zhang, Xuyun Khosravi, Mohammad R. Zhou, Xiaokang School of Computer Science Qufu Normal University Qufu China School of Computer and Software Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and Technology Nanjing China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China Department of Computing Macquarie University SydneyNSW2109 Australia Department of Computer Engineering Persian Gulf University Bushehr Iran Department of Electrical and Electronic Engineering Shiraz University of Technology Shiraz Iran Faculty of Data Science Shiga University Hikone Japan

ISBN: (纸本)9789811665530

With the continuous development of IoT, a number of sensors establish on the roadside to monitor traffic conditions in real time. The continuously traffic data generated by these sensors makes traffic management feasible. However, loss of data may occur due to inevitable sensor failure, impeding traffic managers to understand traffic dynamics clearly. In this situation, it is becoming a necessity to predict missing traffic flow accurately for effective traffic management. Furthermore, the traffic sensor data are often distributed and stored by different agencies, which inhibits the multi-party sensor data sharing significantly due to privacy concerns. Therefore, it has become a major obstacle to balance the tradeoff between data sharing and vehicle privacy. In light of these challenges, we propose a privacy-aware and accurate missing traffic flow prediction approach based on time-aware Locality-Sensitive Hashing technique. At last, we deploy a set of experiments based on a real traffic dataset. Experimental reports demonstrate the feasibility of our proposal in terms of traffic flow prediction accuracy and efficiency while guaranteeing sensor data privacy. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Ensemble method based architecture using random forest importance to predict employee's turn over 5

Ensemble method based architecture using random forest impor...

引用

5th International Conference on Electronic Design, ICED 2020

作者： Hossen, Md. Anwar Hossain, Emran Ishwar, Abdul Khalib Zahereel Siddika, Fatema Department Software Engineering Daffodil International University Bangladesh School of Computer and Communication Engineering Universiti Malaysia Perlis Malaysia Department of Computer Science and Engineering Jagannath University Bangladesh

The departure of a skilled employee can create a problem for a company and this incident is increasing globally. Employee turnover has become an important issue these days due to the heavy workload, low pay, low job satisfaction, poor working environment. Companies face problems as their budget will increase, losing skilled manpower and employees' trust. It's taking time to adjust for a new employee and bring risk and increase the cost for the company. It is necessary to bring appropriate solutions to the problem. The main purpose of this paper is to predict the turnover of employees with the help of state of the art machine learning classifier. We have determined employee turnover selection factors using some prediction models. We first pre-processed the dataset by removing correlative attributes. Then, we have scaled the attributes. Secondly, a Sequential selection algorithm (SBS) has been using to reduce features from a high number to a relatively small signal-canton. Then use Chi-square and Random Forest important algorithms to determine the most significant shared key features. Then we get average-montly-hours, satisfaction-level, time-spend-company are responsible for the employee's departure. Then, we have applied different state of the art machine learning algorithm to measure the accuracy. We have achieved the highest accuracy of 99.4% using the reduced feature with 10-Fold Cross-validation by applied the Random Forest classifier and which is higher than the mentioned reference work. © 2021 Published under licence by IOP Publishing Ltd.

关键词： Job satisfaction

来源：评论

学校读者我要写书评

暂无评论

Image-Based Criticality-Aware Fire Detection

Image-Based Criticality-Aware Fire Detection

引用

Frontiers of Information Technology (FIT)

作者： Alina Arshad Jawwad Ahmed Shamsi Muhammad Burhan Khan Narmeen Zakaria Bawany Department of Software Engineering National University of Computer and Emerging Sciences Karachi Pakistan Department of Computer Science National University of Computer and Emerging Sciences Karachi Pakistan Department of Electrical Engineering National University of Computer and Emerging Sciences Karachi Pakistan Faculty of Science Jinnah University for Women Karachi Pakistan

ISBN: (数字)9798331510503

ISBN: (纸本)9798331510510

Context-aware fire detection is a significant task in the era of new urban monitoring. Severe damage might result from fire events. To minimize the occurrence of these events, timely detection of fire accidents is necessary. Various machinelearning and deep learning methods are used for fire detection. Most of them do not focus on the extent of the fire or the damage it causes. All these methods need the detection of the criticality of the fire event. This work proposes an identification system based on Large Vision Models (LVMs) for fire detection. We proposed an intelligent criticality-aware fire detection system that can detect fire and its varying scales from small to large and generate alarming alerts accordingly. The model integrates advanced computer vision techniques with LVMs to explain the hidden context in a textual format. The system is tested on realtime data collected from surveillance cameras and achieves an accuracy of 86.67 % in correctly identifying the context-based criticality of the fire events depicted in the input data. This proposed framework can revolutionize surveillance applications by enhancing security and responding to crucial fire incidents in real-time. The system provides an efficient method for allocating resources and facilitates rapid response to incidents to prioritize activities intelligently. Using this approach, we identified and prioritized fire incidents in the urban environment.

关键词： Deep learning computer vision Surveillance Computational modeling Urban areas Cameras Real-time systems Security Information technology Context modeling

来源：评论

学校读者我要写书评

暂无评论

FAS-reid: Fair Architecture Search for Person Re-IDentification

FAS-reid: Fair Architecture Search for Person Re-IDentificat...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Shengbo Chen Shijie Chen Zhou Lei School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai China

The development of deep learning has driven the development of ReID, and more and more excellent methods have been proposed, but most of these are artificially designed network backbones. Automation is a trend in the development of deep learning. This paper propose FAS-ReID(Fair Architecture Search for Person Re-IDentification), which can automatically design and generate a neural network backbone for ReID. This paper compare operation selection to competition, and inject noise to make the competition fairer, while making the architecture of automated search More adaptable to ReID We use TriHard loss to improve the feature extraction ability. Our experiments show that the backbone searched by FAS-ReID is better and reduces the search time. Meanwhile, as for the problem of performance collapse caused by skip-connection enrichment in the search process, FAS-Reid does not use the early stop strategy to avoid performance loss like other solutions, which is also the reason why our method is more reliable and robust.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-Cope: Category-Level Object Pose Estimation with Dual Sim2real Unsupervised Domain Adaptation Module

SSRN

引用

SSRN 2024年

作者： Ren, Xi Guo, Nan Zhu, Zichen Jiang, Xinbei Department of Computer Science and Engineering Northeastern University Shenyang110004 China Software College Northeastern University Shenyang110004 China

Category-level pose estimation offers the generalization ability to novel objects unseen during training, which has attracted increasing attention in recent years. Despite the advantage, annotating real-world data with pose label is intricate and laborious. Although using synthetic data with free annotations can greatly reduce training costs, the Synthetic-to-Real (Sim2Real) domain gap could result in a sharp performance decline on real-world test. In this paper, we propose Dual-COPE, a novel category-level object pose estimation method with dual Sim2Real domain adaptation to avoid expensive real pose annotations. First, we propose an estimation network featured with dual prior deformation and transformer-based matching to realize high-precision pose prediction. Upon that, an efficient dual Sim2Real domain adaptation module is further designed to reduce the feature distribution discrepancy between synthetic and real-world data both semantically and geometrically, thus maintaining superior performance on real-world test. Moreover, the adaptation module is loosely coupled with estimation network, allowing for easy integration with other methods without any additional inference overhead. Comprehensive experiments show that Dual-COPE achieves state-of-the-art performance on REAL275 dataset under both unsupervised and supervised settings. © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transitive Transfer Learning for Lungs CT Segmentation 3

Transitive Transfer Learning for Lungs CT Segmentation

引用

3rd IEEE International Conference on System Analysis and Intelligent Computing, SAIC 2022

作者： Sineglazov, Victor Klanovets, Olexander Riazanovskiy, Kirill Aviation University Department of Aviation Computer-Integrated Complexes National Kiev Ukraine National Technical University of Ukraine 'Igor Sikorsky Kyiv Polytechnic Institute' Department of Computer Science and Software Engineering Kiev Ukraine

ISBN: (数字)9798350396744

ISBN: (纸本)9798350396744

This paper studies the effect of transitive transfer learning (TTL) in the medical image processing field on the practical task of tuberculosis (TB) diagnosis. A series of experiments on semantic segmentation of nodules on lung CT images based on ImageNet, LIDC-IDRI and a private dataset with pulmonary tuberculosis of tuberculoma type were performed. The LIDC-IDRI dataset was selected as a transitive one among other datasets based on the Optimal Transport Dataset Distance (OTDD) metric. The TTL with LIDC-IDRI dataset in this case is designed to reduce the distribution gap between the ImageNet dataset and the private TB dataset. DeepLabV3+ was used for the experiments. The following approaches based on this network were compared: training the network on a private dataset from scratch, training the network on a private dataset using ImageNet dataset weights, pre-training the network on a LIDC-IDRI dataset using ImageNet weights, with post-training on a private tuberculosis dataset. In this way, the effectiveness of conventional deep learning, transfer learning, and transitive transfer learning approaches in the popular lung CT image domain is compared. Experiments have shown that using transitive transfer learning with the LIDC-IDRI dataset effectively bridges the distributional gap between the ImageNet source domain and the target domain of the private tuberculosis dataset. The accuracy increments for mIoU, F1 and F2 score were 0.1622, 0.1577 and 0.1645, respectively. The obtained results proved the efficiency of TTL with dataset selection based on OTDD in the task of segmentation of CT lung images on private practical datasets. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Temporal Up-Sampling for Asynchronous Events

Temporal Up-Sampling for Asynchronous Events

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Xiang, Xijie Zhu, Lin Li, Jianing Tian, Yonghong Huang, Tiejun Shanghai Jiao Tong University Department of Electrical and Computer Engineering China School of Computer Science Peking University China Peng Cheng National Laboratory China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

The event camera is a novel bio-inspired vision sensor. When the brightness change exceeds the preset threshold, the sensor generates events asynchronously. The number of valid events directly affects the performance of event-based tasks, such as reconstruction, detection, and recognition. However, when in low-brightness or slow-moving scenes, events are often sparse and accompanied by noise, which poses challenges for event-based tasks. To solve these challenges, we propose an event temporal up-sampling algorithm 11Code: https://***/XIJIE-XIANG/Event-Temporal-Up-sampling to generate more effective and reliable events. The main idea of our algorithm is to generate up-sampling events on the event motion trajectory. First, we estimate the event motion trajectory by contrast maximization algorithm and then up-sampling the events by temporal point processes. Experimental results show that up-sampling events can provide more effective information and improve the performance of downstream tasks, such as improving the quality of reconstructed images and increasing the accuracy of object detection. © 2022 IEEE.

关键词： Cameras

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：