检索结果-内蒙古大学图书馆

Development of a Low-Power Microcontroller-Based Wrist-Worn Device With Resource-Constrained Activity detection Algorithm

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2020年第10期69卷 7522-7529页

作者： Chowdhury, Debjyoti Chattopadhyay, Madhurima Heritage Inst Technol Dept Appl Elect & Instrumentat Engn Kolkata 700107 India

This article deals with the development of a resource-constrained activity detection algorithm for microcontroller-based wrist-worn devices. The various market available activity detection devices lack adequate agility and ease of use in certain applications, as they heavily rely upon computationally intensive algorithms to detect physical activity and step count. Therefore, by extension, they always need to stay connected with a smartphone that can perform these computations. To address this problem, this article introduces a standalone wearable device with the simplified algorithm for activity detection in a human being. The developed system consists of microelectromechanical systems (MEMS) triaxial accelerometer connected to a low-power microcontroller with a wrist anchor-able form factor. The step detection algorithm uses a moving average threshold filter to detect the change in acceleration data to identify specific events. A detailed comparative study considering power consumption and the step detection made between the developed device (with the resource-constrained algorithm) against market available devices shows that the average detection error of the developed algorithm is approximately 2% under various test conditions (i.e., walking, fast walking, and running) and has an accuracy of 94.96% for activity detection. This study reveals that the use of the proposed algorithm for activity detection not only brings down the cost of the overall device but also reduces the power consumption (< 45.7 mW) with a minimal covering size (12.56 cm(2)) for the wearable part that can extend the application area of such devices.

关键词： Accelerometers Micromechanical devices Acceleration detection algorithms Matlab Calibration Mathematical model Activity detection microelectromechanical systems (MEMS) accelerometer resource-constrained algorithm wearable device wrist-worn

来源：评论

学校读者我要写书评

暂无评论

Optimal Placement and Intelligent Smoke detection Algorithm for Wildfire-Monitoring Cameras

引用

IEEE ACCESS 2020年 8卷 72326-72339页

作者： Shi, Jie Wang, Wei Gao, Yuanqi Yu, Nanpeng Univ Calif Riverside Dept Elect & Comp Engn Riverside CA 92501 USA

Smoke produced by wildfires is usually visible much earlier than flames. Hence, early detection of wildfire smoke is essential to prevent severe property losses and heavy casualties from catastrophic wildfires. Camera networks are being built and expanded to achieve timely wildfire smoke detection. To achieve the best camera coverage and detection accuracy with limited budget, an intelligent video smoke detection algorithm and an optimal wildfire camera placement strategy are in a critical need. In this paper, we propose an efficient video smoke detection framework designed for embedded applications on local cameras. It consists of two modules. In the first module, the original video frames are processed by local binary patterns and a dense optical flow estimator. In the second module, the produced features are then fed into a lightweight deep convolutional neural network, which serves as a binary classifier to detect the presence of smoke. We also formulate the wildfire camera placement problem as a binary integer programming problem to minimize the overall fire risk of a given area. Case studies on real-world videos are carried out to validate the accuracy as well as the computational and memory efficiency of the proposed smoke detection framework. We also validate our proposed camera placement strategy by simulating the deployment of wildfire cameras across a test region in Southern California.

关键词： Cameras Feature extraction Image color analysis detection algorithms Computer vision Neural networks Machine learning Smoke detection camera placement deep neural network local binary patterns optical flow

来源：评论

学校读者我要写书评

暂无评论

Near-Optimal Performance With Low-Complexity ML-Based Detector for MIMO Spatial Multiplexing

引用

IEEE COMMUNICATIONS LETTERS 2021年第1期25卷 122-126页

作者： Hijazi, Hussein Haroun, Ali Saad, Majed Al Ghouwayel, Ali Chamas Dhayni, Achraf Lebanese Int Univ CCE Dept Beirut Lebanon IETR Cent Supelec SCEE Signal Commun & Embedded Elect Res Grp Campus Rennes F-35510 Cesson Sevigne France EFREI Sch Engn F-94800 Villejuif France STMicroelectronics F-06560 Valbonne France

In Spatial Multiplexing MIMO systems, many powerful non-linear detection techniques as sphere decoding have emerged to overcome the performance limitations of linear detection techniques. However, these non-linear techniques suffer from high complexity that increases dramatically with the number of antennas and the modulation order. Hence, they cannot be implemented on highly parallel hardware architecture and are thus not suitable for real-time high data rate transmission. In this letter, a new detection technique is proposed to approach the optimal performance obtained by Maximum Likelihood (ML) detector without increasing the complexity significantly. This detector is denoted by OSIC-ML since it combines two techniques: the Ordered Successive Interference Cancellation (OSIC) and the ML. The proposed OSIC-ML detector shows a near-optimal performance at very low complexity even with large scale MIMO and imperfect channel estimation, where this complexity can be efficiently controlled to achieve the desired complexity-performance tradeoff.

关键词： Multiple-input multiple-output (MIMO) detection algorithms equalizers maximum likelihood (ML) detection sphere decoding (SD) ordered successive interference cancellation (OSIC)

来源：评论

学校读者我要写书评

暂无评论

Safeness-Based Community Penetration

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2021年第7期68卷 2690-2694页

作者： Yu, Zisheng Jiang, Zhongyuan Ma, Jianfeng Zheng, Yu Xidian Univ Sch Cyber Engn Xian 710071 Peoples R China JD Com JD Intelligent Cities Res Beijing 100176 Peoples R China JD Digits JD Intelligent Cities Business Unit Beijing 100176 Peoples R China

Automatic community divisions often facilitate the convenience of rich community applications such as interest group recommendations. However, it faces a serious community security issue referred to as community penetration (CommPen) such that the colluding attackers might very smartly deceive the community detection mechanism and infiltrate into one or more social communities to disclose the community privacy by perturbating a budget limited social links. From the attacker perspective, the CommPen aims to maximally disperse a group of colluding users into other communities escaping the detections with low cost, which is very challenging in problem formulation, attack model building, and optimal solution. In this brief, we first introduce the CommPen problem against community detection, which has not been extensively focused on so far. Secondly, we formalize the CommPen as an optimization problem, which is a combination explosion problem. Thirdly, an efficient algorithm based on multi simulated annealing (MSA) is proposed to solve this problem by rewiring a small number of connections, leading to privacy protection. Finally, community penetration on real-world networks is conducted in experiments, which shows that our proposed method outperforms baselines, including Random Selection, Greedy Search, and Genetic Algorithm.

关键词： Image edge detection detection algorithms Circuits and systems Privacy Simulated annealing Optimization Topology Community detection community penetration multi simulated annealing privacy protection

来源：评论

学校读者我要写书评

暂无评论

A Novel Low Complexity Faster-Than-Nyquist Signaling Detector Based on the Primal-Dual Predictor-Corrector Interior Point Method

引用

IEEE COMMUNICATIONS LETTERS 2021年第7期25卷 2370-2374页

作者： Ibrahim, Ahmed Bedeer, Ebrahim Yanikomeroglu, Halim Carleton Univ Dept Syst & Comp Engn Ottawa ON K1S 5B6 Canada Univ Saskatchewan Dept Elect & Comp Engn Saskatoon SK S7N 5A9 Canada

Faster-than-Nyquist signaling (FTNS) is a promising non-orthogonal physical layer transmission technique to improve the spectral efficiency of next-generation communication systems but at the expense of increased transciever complexity to remove the artificially introduced intersymbol-interference (ISI). In this paper, we investigate the detection problem of FTNS and propose a low-complexity sub-optimal detection algorithm, stemming in operations research, that is based on convex relaxation, primal-dual predictor-corrector interior point method, and quantization. The proposed convex quadratic relax-and-quantize sequence estimation (CQRAQSE) algorithm is suitable for low rates FTNS and demonstrates an excellent trade-off between the detection performance and computational effort.

关键词： Complexity theory Estimation Optimization Detectors detection algorithms Receivers Communication systems Convex optimization faster-than-Nyquist signaling inter-symbolic-interference (ISI) Mazo limit sequence estimation

来源：评论

学校读者我要写书评

暂无评论

Land Cover Change detection With VHR Satellite Imagery Based on Multi-Scale SLIC-CNN and SCAE Features

引用

IEEE ACCESS 2020年 8卷 228070-228087页

作者： Jing, Ran Gong, Zhaoning Guan, Hongliang Yangtze Univ Sch Geosci Wuhan 430100 Peoples R China Capital Normal Univ Coll Resource Environm & Tourism Beijing 100048 Peoples R China Capital Normal Univ Coll Geospatial Informat Sci & Technol Beijing 100048 Peoples R China

Change detection with very high resolution (VHR) satellite images is of great application values when evaluating and monitoring land use changes. However, intrinsic complexity of satellite images will introduce more difficulties to change detection tasks. In this study, a new change detection method is proposed by combining multi-scale simple linear iterative clustering-convolutional neural network (SLIC-CNN) with stacked convolutional auto-encoder (SCAE) features to improve change detection capabilities with VHR satellite images. First, the multi-scale SLIC-based image segmentation is performed on multi-temporal images to generate segment objects while keeping their edge information as much as possible. Second, the convolutional layers in a CNN architecture are used to generate change map, then, an SCAE feature-based classification procedure is performed to generate "from-to" change information. Finally, a Bayesian information criterion is used to optimize the results of change detection. In this study, the experiments carried out reveal that the multi-scale SLIC image segmentation algorithm affects the integrity of change regions;CNN features have an effect on the consistency of change regions;and SCAE features influence the performance of support vector machine (SVM) classifiers. And, features extracted from the architectures enhance the ability of information extraction from ground objects. Comparison results also show the superiority to other change detection methods.

关键词： Image segmentation Feature extraction Satellites Change detection algorithms Spatial resolution Computer architecture detection algorithms Change detection image segmentation multi-scale simple linear iterative clustering-convolutional neural network (SLIC-CNN) stacked convolutional auto-encoder (SCAE) VHR satellite imagery

来源：评论

学校读者我要写书评

暂无评论

On detection of Faint Edges in Noisy Images

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2020年第4期42卷 894-908页

作者： Ofir, Nati Galun, Meirav Alpert, Sharon Brandt, Achi Nadler, Boaz Basri, Ronen Weizman Inst Sci Dept Comp Sci & Appl Math IL-7610001 Rehovot Israel

A fundamental question for edge detection in noisy images is how faint can an edge be and still be detected. In this paper we offer a formalism to study this question and subsequently introduce computationally efficient multiscale edge detection algorithms designed to detect faint edges in noisy images. In our formalism we view edge detection as a search in a discrete, though potentially large, set of feasible curves. First, we derive approximate expressions for the detection threshold as a function of curve length and the complexity of the search space. We then present two edge detection algorithms, one for straight edges, and the second for curved ones. Both algorithms efficiently search for edges in a large set of candidates by hierarchically constructing difference filters that match the curves traced by the sought edges. We demonstrate the utility of our algorithms in both simulations and applications involving challenging real images. Finally, based on these principles, we develop an algorithm for fiber detection and enhancement. We exemplify its utility to reveal and enhance nerve axons in light microscopy images.

关键词： Image edge detection Noise measurement Matched filters Smoothing methods detection algorithms Microscopy Signal to noise ratio Edge detection fiber enhancement multiscale methods low signal-to-noise ratio multiple hypothesis tests microscopy images

来源：评论

学校读者我要写书评

暂无评论

Scalable Spectral Clustering for Overlapping Community detection in Large-Scale Networks

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2020年第4期32卷 754-767页

作者： Van Lierde, Hadrien Chow, Tommy W. S. Chen, Guanrong City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

While the majority of methods for community detection produce disjoint communities of nodes, most real-world networks naturally involve overlapping communities. In this paper, a scalable method for the detection of overlapping communities in large networks is proposed. The method is based on an extension of the notion of normalized cut to cope with overlapping communities. A spectral clustering algorithm is formulated to solve the related cut minimization problem. When available, the algorithm may take into account prior information about the likelihood for each node to belong to several communities. This information can either be extracted from the available metadata or from node centrality measures. We also introduce a hierarchical version of the algorithm to automatically detect the number of communities. In addition, a new benchmark model extending the stochastic blockmodel for graphs with overlapping communities is formulated. Our experiments show that the proposed spectral method outperforms the state-of-the-art algorithms in terms of computational complexity and accuracy on our benchmark graph model and on five real-world networks, including a lexical network and large-scale social networks. The scalability of the proposed algorithm is also demonstrated on large synthetic graphs with millions of nodes and edges.

关键词： Clustering algorithms Image edge detection Benchmark testing Partitioning algorithms Social network services detection algorithms Optimization Community detection algorithm overlapping communities real-world network spectral clustering normalized cut

来源：评论

学校读者我要写书评

暂无评论

Segment-Based Methods for Facial Attribute detection from Partial Faces

引用

IEEE TRANSACTIONS ON AFFECTIVE COMPUTING 2020年第4期11卷 601-613页

作者： Mahbub, Upal Sarkar, Sayantan Chellappa, Rama Univ Maryland Ctr Automat Res Dept Elect & Comp Engn UMIACS College Pk MD 20742 USA

State-of-the-art methods of attribute detection from faces almost always assume the presence of a full, unoccluded face. Hence, their performance degrades for partially visible and occluded faces. In this paper, we introduce SPLITFACE, a deep convolutional neural network-based method that is explicitly designed to perform attribute detection in partially occluded faces. Taking several facial segments and the full face as input, the proposed method takes a data driven approach to determine which attributes are localized in which facial segments. The unique architecture of the network allows each attribute to be predicted by multiple segments, which permits the implementation of committee machine techniques for combining local and global decisions to boost performance. With access to segment-based predictions, SPLITFACE can predict well those attributes which are localized in the visible parts of the face, without having to rely on the presence of the whole face. We use the CelebA and LFWA facial attribute datasets for standard evaluations. We also modify both datasets, to occlude the faces, so that we can evaluate the performance of attribute detection algorithms on partial faces. Our evaluation shows that SPLITFACE significantly outperforms other recent methods especially for partial faces.

关键词： Training Task analysis Image segmentation Feature extraction Hair Computer architecture detection algorithms Attribute detection facial segment committee machines score fusion local to global decision propagation

来源：评论

学校读者我要写书评

暂无评论

A Novel Trust Model Based Overlapping Community detection Algorithm for Social Networks

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2020年第11期32卷 2101-2114页

作者： Ding, Shuai Yue, Zijie Yang, Shanlin Niu, Feng Zhang, Youtao Hefei Univ Technol Minist Educ Sch Management Hefei 23009 Anhui Peoples R China Hefei Univ Technol Minist Educ Key Lab Proc Optimizat & Intelligent Decis Making Hefei 23009 Anhui Peoples R China Univ Pittsburgh Comp Sci Dept Pittsburgh PA 15260 USA

With the fast advances in Internet technologies, social networks have become a major platform for social interaction, lifestyle demonstration, and message dissemination. Effective community detection in social networks helps to assess public sentiment, identify community leaders, and produce personalized recommendation. While different community detection approaches have been proposed in the literature, the trust model based detection schemes model user interactions as trust transfer, which helps to capture the implicit relation in the network. Unfortunately, trust model based detection schemes face a cold start problem, i.e., they cannot accurately model newly joined users as these users have few interactions for a duration after joining the network. In this paper, we propose TLCDA, a novel trust model based community detection algorithm. By enhancing the traditional trust computation with inter-node relation strength and similarity in social networks, TLCDA detects communities through coarse-grained K-Mediods clustering. Our evaluation on real social networks shows that the communities detected by TLCDA exhibit superior preference cohesion while satisfying the topology cohesion.

关键词： Social networking (online) detection algorithms Computational modeling Network topology Peer-to-peer computing Topology Clustering algorithms Community detection social network trust coarse cluster

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：