检索结果-内蒙古大学图书馆

Context-aware Telco outdoor localization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Yige Rao, Weixiong Yuan, Mingxuan Zeng, Jia Hui, Pan School of Software Engineering Tongji University Shanghai China Huawei Noahs Ark Lab Hong Kong Department of Computer Science and Engineering Hong Kong University of Science and Technology Department of Computer Science University of Helsinki

Recent years have witnessed the fast growth in telecommunication (Telco) techniques from 2G to upcoming 5G. Precise outdoor localization is important for Telco operators to manage, operate and optimize Telco networks. Differing from GPS, Telco localization is a technique employed by Telco operators to localize outdoor mobile devices by using measurement report (MR) data. When given MR samples containing noisy signals (e.g., caused by Telco signal interference and attenuation), Telco localization often suffers from high errors. To this end, the main focus of this paper is how to improve Telco localization accuracy via the algorithms to detect and repair outlier positions with high errors. Specifically, we propose a context-aware Telco localization technique, namely RLoc, which consists of three main components: a machine-learning-based localization algorithm, a detection algorithm to find flawed samples, and a repair algorithm to replace outlier localization results by better ones (ideally ground truth positions). Unlike most existing works to detect and repair every flawed MR sample independently, we instead take into account spatio-temporal locality of MR locations and exploit trajectory context to detect and repair flawed positions. Our experiments on the real MR data sets from 2G GSM and 4G LTE Telco networks verify that our work RLoc can greatly improve Telco location accuracy. For example, RLoc on a large 4G MR data set can achieve 32.2 meters of median errors, around 17.4% better than state-of-the-art. © 2021, CC BY.

关键词： Statistics

Agricultural Production Evaluation and Spatial Correlation Analysis of Townships in Hainan Island

学校读者我要写书评

暂无评论

Agricultural Production Evaluation and Spatial Correlation A...

2018 International Conference on Mathematics, Modeling, Simulation and Statistics application（MMSSA2018）

作者： Lu Ye Maofen Li Xiaoli Qin Yuping Li Weihong Liang Institute of Scientific and Technical Information Chinese Academy of Tropical Agricultural Sciences Key Lab of Tropical Crops Information Technology Application Research of Hainan Province School of Software Engineering Beijing University of Posts and Telecommunications

ISBN: (纸本)9781510880504

Using principal component analysis, natural breaks, spatial correlation analysis methods, based on the status evaluation, spatial differentiation and correlation of agricultural production of 195 townships in Hainan Island were analyzed, so as to provide a reference for formulating scientific township agricultural plans and policies. The results show that:(1) Townships with better agricultural production are located in cities and counties with better agricultural development. The major factors that affect agricultural production are area of cultivated land, area of facility agriculture, and the proportion of employees in primary industry.(2) Above 45% of townships in the first three levels of agricultural production are distributed in eastern and western cities and counties, and 50% in the fourth level are distributed in central cities and counties.(3) There are spatial agglomerations in areas with similar agricultural production. Meanwhile, some suggestions were put forward to promote the development of agricultural production in Hainan Island.

关键词： agriclutural production evaluation of townships principal component analysis natural breaks spatial correlation analysis suggestions

QCluster: Clustering Packets for Flow Scheduling

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yang, Tong Wang, Hao Li, Jizhou Jiang, Jie Zhao, Yikai Zhang, Yinda Yang, Kaicheng Zhang, Nicholas School of Computer Science National Engineering Laboratory for Big Data Analysis Technology and Application Peking University China Peng Cheng Laboratory Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Huawei Theory Lab China

Flow scheduling is crucial in data centers, as it directly influences user experience of applications. According to different assumptions and design goals, there are four typical flow scheduling problems/solutions: SRPT, LAS, Fair Queueing, and Deadline-Aware scheduling. When implementing these solutions in commodity switches with limited number of queues, they need to set static parameters by measuring traffic in advance, while optimal parameters vary across time and space. This paper proposes a generic framework, namely QCluster, to adapt all scheduling problems for limited number of queues. The key idea of QCluster is to cluster packets with similar weights/properties into the same queue. QCluster is implemented in Tofino switches, and can cluster packets at a speed of 3.2 Tbps. To the best of our knowledge, QCluster is the fastest clustering algorithm. Experimental results in testbed with programmable switches and ns-2 show that QCluster reduces the average flow completion time (FCT) for short flows up to 56.6%, and reduces the overall average FCT up to 21.7% over state-of-the-art. All the source code in ns-2 is available in Github [45]. Copyright © 2020, The Authors. All rights reserved.

关键词： Queueing theory

Intelligent Monitoring of IoT Devices using Neural Networks

学校读者我要写书评

暂无评论

Intelligent Monitoring of IoT Devices using Neural Networks

International Conference on Intelligence in Next Generation Networks (ICIN)

作者： Ashima Chawla Pradeep Babu Trushnesh Gawande Erik Aumayr Paul Jacob Sheila Fallon Software Research Institute Athlone Institute of Technology Athlone Ireland Cloud Pipeline Engineering Workday Dublin Ireland Application Development Platform Ericsson Athlone Ireland Network Management Lab Ericsson Athlone Ireland

ISBN: (数字)9781728177052

ISBN: (纸本)9781728177069

The Internet of Things (IoT) has seen expeditious growth in recent times with 7 billion connected devices in 2020, thus leading to the vital importance of real-time monitoring of IoT devices. Through this paper, we demonstrate the idea of building a cloud-native application to monitor smart home devices. The application intends to provide valuable performance metrics from the perspective of end-users and react to anomalies in real-time. In this demo paper, we conduct the demonstration using Autoencoder (an unsupervised technique) based Deep Neural Networks (DNNs) to learn the normal operating conditions of power consumption of smart devices. When an anomaly is detected, the DNNs take proactive action and send appropriate commands back to the device. In addition, the users are provided with a real-time graphical representation of power consumption. This will help to save electricity on a domestic as well as industrial level. Finally, we discuss the future prospects of monitoring IoT devices.

关键词： Cloud computing Technological innovation Power demand Neural networks Real-time systems Internet of Things Monitoring

Design of Fine Management System for Civil Aviation Airspace Resources Based on Spatiotemporal Grid Model

学校读者我要写书评

暂无评论

Design of Fine Management System for Civil Aviation Airspace...

IEEE International Conference on Civil Aviation Safety and Information technology (ICCASIT)

作者： Yinger Zheng Juqing Liu Jun Li Yubin Xu Qian Huang Yan Zhu Yanqiu Pei Big Data Application Center China Academy of Civil Aviation Science and Technology Beijing China College of Geoscience and Surveying Engineering China University of Mining and Technology Beijing China Research and Development Center China Academy of Civil Aviation Science and Technology Beijing China Service Lab Huawei Research Institute Huawei Technology Co. Ltd Beijing China

ISBN: (纸本)9781728125992

Along with the rapid development of aviation industry, airspace demand is increasing. However, the current airspace resources are tight and the utilization efficiency is low. Aiming at addressing this problem, this paper proposes a fine management system for civil aviation airspace resources based on spatiotemporal grid model. Relying on massive, multisource, multi-scale and multi-dimensional aviation big data, this study expands the time dimension of global discrete grid technology and establishes a global unified spatiotemporal grid model. On this basis, the calculation and analysis method of the spatiotemporal grid model is designed to carry out route management, conduct flight collision detection, allocate airspace resources, and then realize efficient and intelligent management, allocation and intelligent application of airspace resources. Finally, the scientificity and feasibility of the management system is verified through the practical application of civil aviation ADS-B data, meteorological data and route data.

关键词： Spatiotemporal grid Airspace resources Fine management En-route capacity civil aviation utilization efficiency grids Grid MANAGEMENT SYSTEMS time dimension

Log-based Anomaly Detection based on EVT Theory with feedback

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Jinyang Huang, Junjie Huo, Yintong Jiang, Zhihan Gu, Jiazhen Chen, Zhuangbin Feng, Cong Yan, Minzhi Lyu, Michael R. The Chinese University of Hong Kong Hong Kong School of Software Engineering Sun Yat-sen University China Computing and Networking Innovation Lab Huawei Cloud Computing Technology Co. Ltd China HCC Lab Huawei Cloud Computing Technology Co. Ltd China The Chinese University of Hong Kong China

System logs play a critical role in maintaining the reliability of software systems. Fruitful studies have explored automatic log-based anomaly detection and achieved notable accuracy on benchmark datasets. However, when applied to large-scale cloud systems, these solutions face limitations due to high resource consumption and lack of adaptability to evolving logs. In this paper, we present an accurate, lightweight, and adaptive log-based anomaly detection framework, referred to as ScaleAD. Our method introduces a Trie-based Detection Agent (TDA) that employs a lightweight, dynamically-growing trie structure for real-time anomaly detection. To enhance TDA’s accuracy in response to evolving log data, we enable it to receive feedback from experts. Interestingly, our findings suggest that contemporary large language models, such as ChatGPT, can provide feedback with a level of consistency comparable to human experts, which can potentially reduce manual verification efforts. We extensively evaluate ScaleAD on two public datasets and an industrial dataset. The results show that ScaleAD outperforms all baseline methods in terms of effectiveness, runs 2× to 10× faster and only consumes 5% to 41% of the memory resource. © 2023, CC BY-NC-ND.

关键词： Anomaly detection

Practical Anomaly Detection over Multivariate Monitoring Metrics for Online Services

学校读者我要写书评

暂无评论

Practical Anomaly Detection over Multivariate Monitoring Met...

International Symposium on software Reliability engineering (ISSRE)

作者： Jinyang Liu Tianyi Yang Zhuangbin Chen Yuxin Su Cong Feng Zengyin Yang Michael R. Lyu The Chinese University of Hong China School of Software Engineering Sun Yat-sen University Zhuhai China Computing and Networking Innovation Lab Huawei Cloud Computing Technology Co. Ltd China

As modern software systems continue to grow in terms of complexity and volume, anomaly detection on multivariate monitoring metrics, which profile systems’ health status, becomes more and more critical and challenging. In particular, the dependency between different metrics and their historical patterns plays a critical role in pursuing prompt and accurate anomaly detection. Existing approaches fall short of industrial needs for being unable to capture such information efficiently. To fill this significant gap, in this paper, we propose CMAnomaly, an anomaly detection framework on multivariate monitoring metrics based on collaborative machine. The proposed collaborative machine is a mechanism to capture the pairwise interactions along with feature and temporal dimensions with linear time complexity. Cost-effective models can then be employed to leverage both the dependency between monitoring metrics and their historical patterns for anomaly detection. The proposed framework is extensively evaluated with both public data and industrial data collected from a large-scale online service system of huawei Cloud. The experimental results demonstrate that compared with state-of-the-art baseline models, CMAnomaly achieves an average F1 score of 0.9494, outperforming baselines by 6.77% ~ 10.68%, and runs 10× ~ 20× faster. Furthermore, we also share our experience of deploying CMAnomaly in huawei Cloud.

关键词：

Bayesian Optimized 1-Bit CNNs

学校读者我要写书评

暂无评论

Bayesian Optimized 1-Bit CNNs

International Conference on Computer Vision (ICCV)

作者： Jiaxin Gu Junhe Zhao Xiaolong Jiang Baochang Zhang Jianzhuang Liu Guodong Guo Rongrong Ji Beihang University Beijing China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Huawei Noah’s Ark Lab China School of Information Science and Engineering Xiamen University Fujian China Peng Cheng Lab Shenzhen China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Deep convolutional neural networks (DCNNs) have dominated the recent developments in computer vision through making various record-breaking models. However, it is still a great challenge to achieve powerful DCNNs in resource-limited environments, such as on embedded devices and smart phones. Researchers have realized that 1-bit CNNs can be one feasible solution to resolve the issue; however, they are baffled by the inferior performance compared to the full-precision DCNNs. In this paper, we propose a novel approach, called Bayesian optimized 1-bit CNNs (denoted as BONNs), taking the advantage of Bayesian learning, a well-established strategy for hard problems, to significantly improve the performance of extreme 1-bit CNNs. We incorporate the prior distributions of full-precision kernels and features into the Bayesian framework to construct 1-bit CNNs in an end-to-end manner, which have not been considered in any previous related methods. The Bayesian losses are achieved with a theoretical support to optimize the network simultaneously in both continuous and discrete spaces, aggregating different losses jointly to improve the model capacity. Extensive experiments on the ImageNet and CIFAR datasets show that BONNs achieve the best classification performance compared to state-of-the-art 1-bit CNNs.

关键词： Bayes methods Kernel Quantization (signal) Convolution Training Frequency modulation Indexes

Globally optimal consensus maximization for robust visual inertial localization in point and line map

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jiao, Yanmei Wang, Yue Fu, Bo Tan, Qimeng Chen, Lei Wang, Minhang Huang, Shoudong Xiong, Rong State Key Laboratory of Industrial Control and Technology Zhejiang University Hangzhou China Beijing Key Laboratory of Intelligent Space Robotic System Technology and Applications Beijing Institute of Spacecraft System Engineering Beijing China Application Lab Huawei Incorporated Company China University of Technology Sydney Australia

Map based visual inertial localization is a crucial step to reduce the drift in state estimation of mobile robots. The underlying problem for localization is to estimate the pose from a set of 3D-2D feature correspondences, of which the main challenge is the presence of outliers, especially in changing environment. In this paper, we propose a robust solution based on efficient global optimization of the consensus maximization problem, which is insensitive to high percentage of outliers. We first introduce translation invariant measurements (TIMs) for both points and lines to decouple the consensus maximization problem into rotation and translation subproblems, allowing for a two-stage solver with reduced search space. Then we show that (i) the rotation can be estimated by minimizing TIMs using only 1-dimensional branch-and-bound (BnB), (ii) the translation can be estimated by running 1-dimensional search for each of the three axes with prioritized progressive voting. Compared with the popular randomized solver, our solver achieves deterministic global convergence without requiring an initial value. Furthermore, ours is exponentially faster compared with existing BnB based methods. Finally, our experiments on both simulation and real-world datasets demonstrate that the proposed method gives accurate pose estimation even in the presence of 90% outliers (only 2 inliers). Copyright © 2020, The Authors. All rights reserved.

关键词： Statistics