检索结果-内蒙古大学图书馆

6th International conference on Intelligent Computing and signal processing (ICSP)

作者： Yafei Liu Liehui Jiang Tieming Liu Youwei Zhang Zhongyuan Network Security Research institute Zhengzhou University Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China Zhengzhou Xinda Institute of Advanced Technology Zhengzhou China

ISBN: (纸本)9781665447300

With the development of information technology, electronic evidence plays an increasingly important role in the judicial trial. In Judicial Forensics, it is difficult to extract effective electronic evidence accurately and quickly from a large number of electronic data. Traditional means generally take artificial identification to collect, which takes a long time and is not efficient. Using SSD target detection and recognition algorithm instead of traditional means can effectively reduce the time of screening evidence, but the basic SSD neural network is prone to miss detection for small targets. To solve the above problems, an improved SSD-based image electronic evidence screening method is proposed. this method optimizes the SSD neural network adaptively, introduces the attention mechanism module in the shallow convolution layer of the network to improve the representation ability of the feature map, and fuses the image features obtained from different convolution layers with multi-scale features to increase the shallow feature information. the experimental data are used to test the improved algorithm and analyze the experimental results. It is found that compared with the original SSD neural network algorithm, the detection mean average precision of the improved algorithm is increased by 4.7%, reaching 84.3%, which shows the feasibility and effectiveness of the improved algorithm.

关键词： Image recognition Convolution Target recognition Fuses Neural networks Stacking signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

AI-Aided Downlink Interference Control in Dense Interference-Aware Drone small Cells Networks

引用

IEEE ACCESS 2020年 8卷 15110-15122页

作者： Li, Lixin Zhang, Zihe Xue, Kaiyuan Wang, Meng Pan, Miao Han, Zhu Northwestern Polytech Univ Sch Elect & Informat Xian 710129 Shaanxi Peoples R China 54th Res Inst China Elect Sci & Technol Grp Corp Shijiazhuang 050081 Hebei Peoples R China Univ Houston Dept Elect & Comp Engn Houston TX 77004 USA Kyung Hee Univ Dept Comp Sci & Engn Seoul 446701 South Korea

Recently, drone small cells (DSCs) has been brought into significant focus, which is the one key enabler for potentially facilitating terrestrial wireless communication systems. Meanwhile, in ultra-dense unmanned networks, artificial intelligence (AI) has been a useful and efficient tool for control and management of the multi-agents. this paper investigates a downlink interference control problem in ultra-dense unmanned networks with AI-aided approach, that each DSC can adjust its altitude to increase the data-rate. this problem is formulated as a mean field game (MFG) framework, an AI-aided method to make decisions. In this framework, each DSC controls its velocity to minimize the cost over a period, where the cost function is composed by the data-rate and height adjusting consumption. Meanwhile, in this model, we adopt the mean-field approximation (MFA) approach to derive the interference introduced from a large number of DSCs. Besides, the control strategy is described and explained by using the related Hamilton-Jacobi-Bellman (HJB) and Fokker-Planck-Kolmogorov (FPK) equations, respectively. thus, a finite difference algorithm is proposed to solve the coupled partial differential equations, which can obtain the optimal altitude control strategy. the algorithm outputs show the optimal behaviors of DSCs in different environment scenarios. In additon, the simulation results verify that the proposed control strategy has better average signal to interference plus noise ratio (SINR) compared with the baseline method.

关键词： Artificial intelligence drone small cell downlink interference control mean field game ultra-dense unmanned networks

来源：评论

学校读者我要写书评

暂无评论

Recognition of Pest Based on Faster RCNN 6th

Recognition of Pest Based on Faster RCNN

引用

6th conference on signal and Information processing, Networking and Computers, ICSINC 2019

作者： Zhang, Miaohui Chen, Yunzhong Zhang, Bo Pang, Kangning Lv, Bingxue Key Laboratory of Data Analysis and Processing of Henan Province Henan University Kaifeng China Postdoctoral Research Station of Geography Henan University Kaifeng China College of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou China

ISBN: (纸本)9789811541629

Effective prediction of crop pest species and quantities can provide a priori knowledge for pest control. However, there are many kinds of pests and the color and texture of different pests are similar, traditional image processing and recognition methods based on time or frequency domain features and classifiers are hard to meet the needs of high-precision recognition. In order to improve the recognition result of agricultural pests, based on the target detection algorithm Faster RCNN, we put forward a method for the classification and identification of pests on the basis of online hard sample mining and residual network. the main work is as follows: (1) According to the different size of pests, the detection ability of the network for small targets is enhanced by changing the size and number of anchors;(2) In the feature extraction stage, we use ResNet-50 with stronger feature extraction ability rather than the original VGG16 network;(3) In order to solve the imbalance of samples, online hard Sample Mining Strategy is introduced in the training stage. the experimental outcome demonstrate that our method is effective, the improved algorithm achieves about 5% improvement in accuracy, and the network has a stronger ability to detect small targets. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A double-threshold target detection method in detecting low slow small target 8

A double-threshold target detection method in detecting low ...

引用

8th International conference on Identification, Information and Knowledge in the Internet of things, IIKI 2019

作者： Yu, Jie Liu, Yulan Bai, Yang Liu, Feiliang Science and Technology on Electromagnetic Scattering Laboratory Beijing1100854 China Chaohu University Hefei230000 China

With the rapid development of Unmanned Aerial Vehicle (UAV), stealth warship and stealth tank, the mission of radar has become more difficult. the modern radar system must detect and track target through strong clutter from many aspect, such as ground and sea. Radar detection for low slow small （LSS）targets has gradually become a new focus. LSS target has a small Radar Cross Section (RCS) because of its small size, making the SNR of the echo signal very low. At the same time, the Doppler frequency of slow target is very low, making it difficult for conventional signal processing methods to separate the Doppler information from the clutter spectrum. thus, it does make sense to study how to detect the LSS target in strong clutter efficiently. In this paper, the distribution characteristics of radar clutter and coherent accumulation algorithm for LSS target detection in complex electromagnetic environment are studied. On the base of that, a double-threshold target detection method based on coherent accumulation is proposed. To check out the efficiency of the detection method, an experiment has been conducted, and the data collected was used to test the detection algorithm, and the result has been shown in this paper. © 2020 the Authors. Published by Elsevier B.V.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Positioning Algorithm for Arterial Blood Pressure Pneumatic Sensor 8th

Positioning Algorithm for Arterial Blood Pressure Pneumatic ...

引用

8th International Work-conference on Bioinformatics and Biomedical Engineering (IWBBIO)

作者： Antsiperov, Viacheslav Mansurov, Gennady RAS Kotelnikov Inst Radioengn & Elect IRE Mokhovaya St 11-7 Moscow 125009 Russia

ISBN: (纸本)9783030453848;9783030453855

the paper is devoted to the algorithmic solution of quality control over the pneumatic blood pressure sensor positioning. Previously, this problem was solved by the operator based on his subjective assessment of the presence/absence of a pulse wave in the observed signal and its quality estimation. Recent studies have led us to a simple algorithm for automatically evaluating the accuracy of positioning. the algorithm is based on the value of the variability of the intervals of side peaks that the multiscale autocorrelation function can manifest as part of its structure. Since this value is closely related to such a characteristic of the signal as its quasi-periodicity, the algorithm essentially estimates the degree of periodicity of the signal, which is high in the presence of a pulse wave and small in its absence. In addition to the general principle of quasi-periodicity estimation much empirical information has been accumulated on the necessary preliminary normalization of the signal, the censorship of the side peaks to be considered, on the numerical values of the comparison thresholds, etc. the main ideas of the algorithm are illustrated by examples of processing real data obtained by positioning the developed pneumatic sensor.

关键词： Pneumatic blood pressure sensor Positioning problem Arterial blood pressure signal analysis Quasi-periodicity detection Degree of quasi-periodicity

来源：评论

学校读者我要写书评

暂无评论

Quantization and Knowledge Distillation for Efficient Federated Learning on Edge Devices

Quantization and Knowledge Distillation for Efficient Federa...

引用

IEEE International conference on High Performance Computing and Communications (HPCC)

作者： Xiaoyang Qu Jianzong Wang Jing Xiao Ping An Technology (Shenzhen) Co. Ltd Shenzhen China

ISBN: (纸本)9781728176505

Federated learning enables distributed machine learning for decentralized data on edge devices. As communication is a critical bottleneck for federated learning, we utilize model compression techniques for efficient federated learning. First, we propose an adaptive quantized federated average algorithm to reduce the communication cost by dynamically quantizing neural networks' weights. then, we design a federated knowledge distillation method to achieve high-quality small models with limited labeled data. Adaptive quantized federated learning can significantly speed up model training while retaining model accuracy. With a small fraction of data as labeled data, our federated knowledge distillation can reach a fixed accuracy achieved by supervised learning with the entire labeled data set.

关键词： Training Adaptation models Quantization (signal) Machine learning algorithms High performance computing Heuristic algorithms Supervised learning

来源：评论

学校读者我要写书评

暂无评论

theoretical Model of the signal Reflected from Rotating Blades of Aerial targets

Theoretical Model of the Signal Reflected from Rotating Blad...

引用

Digital signal processing and its Applications (DSPA), International conference on

作者： Ekaterina Plotnitskaya Vladimir Veremyev Evgenii Vorobev Research Institute “Prognoz” Saint Petersburg Electrotechnical University “LETI” Saint Petersburg Russia

ISBN: (数字)9781728175287

ISBN: (纸本)9781728175294

the theoretical model representing the signal reflected from rotating blades of aerial objects with different rotor configurations is described. the proposed model is used concerning the radar operating in UHF-band for simulation of the reflected signals from the propeller-driven airplane, helicopter, and small multi-rotor drone. the simulation results are compared with the real data recorded by a passive radar utilizing signals of second-generation terrestrial digital video broadcasting standard for target illumination.

关键词： Blades Rotors Atmospheric modeling Helicopters Mathematical model Radar Airplanes

来源：评论

学校读者我要写书评

暂无评论

Position Monitoring of Multiple Moving targets Based on ZigBee and GPS

Position Monitoring of Multiple Moving Targets Based on ZigB...

引用

International conference on data Science and Business Analytics (ICDSBA)

作者： Dai Yu Wang Xuan Long Wenjia Yu Peng Ma Junyu Zhixing College of Hubei University Wuhan China

Moving target monitoring is widely used in many fields such as industrial control, military, and security. Traditional moving target monitoring generally uses infrared, ultra-sonic and other technologies, which have the disadvantages of complex implementation technology, high hardware cost and high environmental requirements. this paper proposes a low-cost, easy-to-deploy, and small-scale environment with little environmental impact by collecting GPS monitoring signals of multi-target speed and location and signal transmission and processing methods based on ZigBee wireless ad hoc network. signal acquisition and real-time data storage, transmission and processing methods have high application value and promotion significance.

关键词： Industrial control Zigbee Memory Real-time systems Hardware Trajectory Security

来源：评论

学校读者我要写书评

暂无评论

SGSF: A small Groups Based Serial Fusion Method 18

SGSF: A Small Groups Based Serial Fusion Method

引用

18th ACM/IEEE International conference on Information processing in Sensor Networks (IPSN)

作者： Wang, Nian Zhang, Zhe Li, Tingting Xiao, Jing Cui, Li Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China China Acad Chinese Med Sci Xiyuan Hosp Beijing Peoples R China

ISBN: (纸本)9781450362849

With the rapid development of Artificial Intelligence (AI) in the Internet of things (IoT), information fusion becomes one of the key technology. Serial fusion plays an important role in information fusion, which concatenates the features obtained from different sources to get a super-feature with higher discrimination. However, the performance of the serial fusion is usually affected by the poor quality of the indistinguishable real-world datasets, especially the problem of noise and imbalance. the existing noise data removal methods may destroy the data distribution, and the existing over-sampling methods may create noise samples. they may affect the result of feature reduction and further reduce the performance of the classification. To address these big practical challenges, a novel small-Groups-based Serial Fusion method (SGSF) is proposed. SGSF consists of two main parts: a small-Groups-based Noise Removal method (SGNR) and a small-groups-based Positive Region Oriented Oversampling method (PROO). Both of these two methods are based on the Neighborhood Rough Set (NRS) theory. SGNR identifies and removes low-density noise samples whilst keeps the high-density outlier samples, targeting to enlarge the limited NRS positive region and preserve the data distribution. PROO generates new samples towards the NRS positive region so that it can balance the dataset and increase the number of samples with more explicit features. Intensive experiments are carried out to verify the performance of SGSF based on 3 publicly available datasets and 6 self-collected medical datasets. the results demonstrate that SGSF increases the classification accuracy from existing 82.2% to 94.3%.

关键词： Serial Fusion Neighborhood Rough Set small Group Positive Region Oriented Oversampling Exclave Groups Noise Removal

来源：评论

学校读者我要写书评

暂无评论

Salient Representation for Lung Sound Analysis Based on the JAMF Transform 18

Salient Representation for Lung Sound Analysis Based on the ...

引用

18th IEEE Sensors conference

作者： Cazaerck, Jonathan Lauwers, Eline Ides, Kris Van Hoorenbeeck, Kim Verhulst, Stijn Daems, Walter Steckel, Jan Univ Antwerp Fac Appl Engn Res Grp CoSys Lab Antwerp Belgium Flanders Make Strateg Res Ctr Lommel Belgium Univ Antwerp Fac Med & Hlth Sc Lab Expt Med & Pediat Antwerp Belgium Univ Antwerp Fac Med & Hlth Sc REVAKI Res Grp Antwerp Belgium Antwerp Univ Hosp Dept Pediat Edegem Belgium

ISBN: (纸本)9781728116341

Obstructive lung diseases are a family of diseases affecting the respiratory tract. By auscultation of the lungs, trained physicians can determine abnormal pathologies by listening to these lung sounds. When these lung sounds are recorded, the analysis can be performed by means of digital signal processing, often referred to as Computer-Aided Lung Sound Analysis (CALSA). the human hear is somewhat limited in it's capabilities to detect and quantify small perceptual changes to the lung sound scene. the goal of CALSA is to be able to make objective conclusions on the state of the patient. In order to achieve this, the data recorded from the stethoscope must be transformed into a representation that allows efficient interpretation, either by a trained physician or a computer algorithm. In this paper, we propose the Joint Acoustic and Frequency Modulation representation as a useful tool for lung sound analysis, and illustrate the representation of various lung sounds in the transformed domain.

关键词： Digital signal processing

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：