检索结果-南通市图书馆

Sound event localization and detection based on deep learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2024年第2期35卷 294-301页

作者： ZHAO Dada DING Kai qi Xiaogang CHEN Yu feng Hailin School of Mathematics and Statistics Xidian UniversityXi’an 710071China Science and Technology on Near-Surface Detection Laboratory Wuxi 214035China

Acoustic source localization(ASL)and sound event detection(SED)are two widely pursued independent research *** recent years,in order to achieve a more complete spatial and temporal representation of sound field,sound event localization and detection(SELD)has become a very active research *** paper presents a deep learning-based multioverlapping sound event localization and detection algorithm in three-dimensional ***-Mel spectrum and generalized cross-correlation spectrum are joined together in channel dimension as input *** features are classified and regressed in parallel after training by a neural network to obtain sound recognition and localization results *** channel attention mechanism is also introduced in the network to selectively enhance the features containing essential information and suppress the useless ***,a thourough comparison confirms the efficiency and effectiveness of the proposed SELD *** experiments show that the proposed algorithm is robust to reverberation and environment and can achieve higher recognition and localization accuracy compared with the baseline method.

关键词： sound event localization and detection(SELD) deep learning convolutional recursive neural network(CRNN) channel attention mechanism

维普期刊数据库

A robust viscoelastic surfactant tolerating 20% HCl up to 150℃ for oil well stimulation

在线全文

学校读者我要写书评

暂无评论

Petroleum Science 2024年第3期21卷 1865-1874页

作者： Ji Wang Ning qi Hong-Yao Yin Yu-Jun feng Polymer Research Institute State Key Laboratory of Polymer Materials EngineeringSichuan UniversityChengdu610065SichuanPR.China Tianfu Yongxing Laboratory New Theory and Technology of CO_(2) Capture Research CenterChengdu610065SichuanPR China School of Petroleum Engineering China University of Petroleum(East China)Qingdao266580ShandongPR China

Viscoelastic surfactants(VES)are often used as viscous diverters in acidizing stimulation to prolong the acid consumption time and maximize zonal coverage of the acid for improving well ***,the ceiling temperature of commercial VES cannot exceed 120℃in practical use because of the poor thermal stability and fragile molecular structure,hindering their implementation in hightemperature oil reservoirs,i.e.,≥150℃.Here we synthesized a novel C22-tailed diamine,N-erucaminopropyl-N,N-dimethylamine(EDPA),and examined comparatively its rheological behavior,assemblies morphology and molecular stability in 20 wt%HCl with a commercial VES,erucyl dimethyl amidopropyl betaine(EDAB).The feasibility of EDPA for acidizing stimulation was assessed by acid etching of carbonate rock with its HCl solution at 150℃.Rheological results showed that the 2.5 wt%EDPA—20 wt%HCl solution maintains stable viscosity of 90 m Pa s at 150℃for 60 min,while that of 2.0 wt%EDAB HCl solution is just 1 m Pa s under identical conditions.1H NMR spectra and cryo-TEM observations revealed that the chemical structure and self-assembled architectures of EDPA remained intact in such context,but the EDAB suffered from degradation due to the hydrolysis of the amide group,accounting for the poor heat-resistance and *** reaction rate of 2.5 wt%EDPA HCl solution with carbonate rock was one order of magnitude lower than that of 20 wt%HCl solution at 150℃,underpinning the potential of EDPA to be used in the high-temperature reservoirs *** work improved the thermal tolerance of VES in highly concentrated HCl solution,paving a feasible way for the acidization of high-temperature reservoir environments(~150℃).

关键词： Viscoelastic surfactants Thermal stability Self-diverting acid Wormlike micelles Acidizing stimulation

维普期刊数据库

Hybrid pedestrian positioning system using wearable inertial sensors and ultrasonic ranging

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第3期33卷 327-338页

作者： Lin qi Yu Liu Chuanshun Gao Tao feng Yue Yu School of Communication and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Department of Land Surveying and Geo-Informatics The Hong Kong Polytechnic UniversityHong Kong 999077China

Pedestrian positioning system(PPS)using wearable inertial sensors has wide applications towards various emerging fields such as smart healthcare,emergency rescue,soldier positioning,*** performance of traditional PPS is limited by the cumulative error of inertial sensors,complex motion modes of pedestrians,and the low robustness of the multi-sensor collaboration *** paper presents a hybrid pedestrian positioning system using the combination of wearable inertial sensors and ultrasonic ranging(H-PPS).A robust two nodes integration structure is developed to adaptively combine the motion data acquired from the single waist-mounted and foot-mounted node,and enhanced by a novel ellipsoid constraint *** addition,a deep-learning-based walking speed estimator is proposed by considering all the motion features provided by different nodes,which effectively reduces the cumulative error originating from inertial ***,a comprehensive data and model dual-driven model is presented to effectively combine the motion data provided by different sensor nodes and walking speed estimator,and multi-level constraints are extracted to further improve the performance of the overall *** results indicate that the proposed H-PPS significantly improves the performance of the single PPS and outperforms existing algorithms in accuracy index under complex indoor scenarios.

关键词： Pedestrian positioning system Wearable inertial sensors Ultrasonic ranging Deep-learning Data and model dual-driven

维普期刊数据库

Visible Light Indoor Positioning System Based on Pisarenko Harmonic Decomposition and Neural Network

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 195-203页

作者： Li ZHAO Yi REN qi WANG Lange DENG feng ZHANG School of Electronic Information Engineering Xi’an Technological University

Visible-light indoor positioning is a new generation of positioning technology that can be integrated into smart lighting and optical communications. The current received signal strength(RSS)-based visible-light positioning systems struggle to overcome the interferences of background and indoor-reflected noise. Meanwhile, when ensuring the lighting, it is impossible to use the superposition of each light source to accurately distinguish light source information; furthermore, it is difficult to achieve accurate positioning in complex indoor environments. This study proposes an indoor positioning method based on a combination of power spectral density detection and a neural network. The system integrates the mechanism for visible-light radiation detection with RSS theory, to build a back propagation neural network model fitting for multiple reflection channels. Different frequency signals are loaded to different light sources at the beacon end, and the characteristic frequency and power vectors are obtained at the location end using the Pisarenko harmonic decomposition method. Then, a complete fingerprint database is established to train the neural network model and conduct location tests. Finally, the location effectiveness of the proposed algorithm is verified via actual positioning experiments. The simulation results show that, when four groups of sinusoidal waves with different frequencies are superimposed with white noise, the maximum frequency error is 0.104 Hz and the maximum power error is 0.03.2 W. For the measured positioning stage, a 0.8 m × 0.8 m × 0.8 m solid wood stereoscopic positioning model is constructed, and the average error is 4.28 cm. This study provides an effective method for separating multi-source signal energies, overcoming background noise, and improving indoor visible-light positioning accuracies.

关键词： Neural networks Measurement uncertainty Position measurement Harmonic analysis Light emitting diodes Frequency estimation Indoor positioning systems

Multi-party privacy-preserving decision tree training with a privileged party

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第8期67卷 253-268页

作者： Yiwen TONG qi feng Min LUO Debiao HE Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology(Shandong Academy of Sciences)

Currently, a decision tree is the most commonly used data mining algorithm for classification tasks. While a significant number of studies have investigated privacy-preserving decision trees, the methods proposed in these studies often have shortcomings in terms of data privacy breach or efficiency. Additionally,these methods typically only apply to symmetric frameworks, which consist of two or more parties with equal privilege, and are not suitable for asymmetric scenarios where parties have unequal privilege. In this paper,we propose SecureCART, a three-party privacy-preserving decision tree training scheme with a privileged party. We adopt the existing pMPL framework and design novel secure interactive protocols for division,comparison, and asymmetric multiplication. Compared to similar schemes, our division protocol is 93.5–560.4× faster, with the communication overhead reduced by over 90%; further, our multiplication protocol is approximately 1.5× faster, with the communication overhead reduced by around 20%. Our comparison protocol based on function secret sharing maintains good performance when adapted to pMPL. Based on the proposed secure protocols, we implement SecureCART in C++ and analyze its performance using three real-world datasets in both LAN and WAN environments. he experimental results indicate that SecureCART is significantly faster than similar schemes proposed in past studies, and that the loss of accuracy while using SecureCART remains within an acceptable range.

关键词： privacy protection decision trees secure multi-party computation secret sharing privileged party

Assessing the dynamics of O2 desorption from cobalt phthalocyanine by in situ electrochemical scanning tunneling microscopy

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第11期98卷 144-148页

作者： Yu-qi Wang Yue feng Xiang Wang Dong Wang CAS Key Laboratory of Molecular Nanostructure and Nanotechnology CAS Research/Education Center for Excellence in Molecular Sciences Beijing National Laboratory for Molecular Science (BNLMS) Institute of Chemistry Chinese Academy of Sciences University of Chinese Academy of Sciences

We report here the in situ electrochemical scanning tunneling microscopy（ECSTM） study of cobalt phthalocyanine（CoPc）-catalyzed O2evolution reaction（OER） and the dynamics of *** self-assembled CoPc monolayer is fabricated on Au（111） substrate and resolved by ECSTM in 0.1 M KOH *** OH-adsorption on CoPc prior to OER is observed in ECSTM *** OER,the generated O2adsorbed on Co Pc is observed in the CoPc *** step experiment is employed to monitor the desorption of OER-generated O2from CoPc,which results in the decreasing surface coverage of CoPc-O2with *** rate constant of O2desorption is evaluated through data *** insights into the dynamics of Co-O2dissociation at the molecular level via in situ imaging help understand the role of Co-O2in oxygen reduction reaction（ORR） and OER.

关键词： Cobalt phthalocyanine Electrochemical scanning tunneling microscopy Oxygen evolution reaction

Analyzing the spatiotemporal evolution and driving forces of gross ecosystem product in the upper reaches of the Chaobai River Basin

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Environmental Science & Engineering 2024年第8期18卷 117-132页

作者： Jiacheng Li qi Han Liqiu Zhang Li feng Guihuan Liu Beijing Key Laboratory for Source Control Technology of Water Pollution College of Environmental Science and EngineeringBeijing Forestry UniversityBeijing 100083China Engineering Research Center for Water Pollution Source Control&Eco-remediation College of Environmental Science and EngineeringBeijing Forestry UniversityBeijing 100083China Center of Eco-compensation Chinese Academy of Environmental PlanningMinistry of Ecology of EnvironmentBeijing 100041China

The Chaobai River Basin,which is a crucial ecological barrier and primary water source area within the Beijing-Tianjin-Hebei region,possesses substantial ecological *** gross ecosystem product(GEP)in the Chaobai River Basin is a reflection of ecosystem conditions and quantifies nature’s contributions to humanity,which provides a basis for basin ecosystem service management and *** study investigated the spatiotemporal evolution of GEP in the upper Chaobai River Basin and explored the driving factors influencing GEP spatial *** patterns from 2005 to 2020 were analyzed,and GEP was calculated for 2005,2010,2015,and *** driving factors influencing GEP spatial differentiation were identified using the optimal parameter-based geographical detector(OPGD)*** key findings are as follows:(1)From 2005 to 2020,the main ecosystem types were forest,grassland,and *** areas experienced significant changes,and conversions mainly occurred among urban,water,grassland and agricultural ecosystems.(2)Temporally,the GEP in the basin increased from 2005 to 2020,with regulation services *** the county(district)scale,GEP exhibited a north-west-high and south-east-low pattern,showing spatial differences between per-unit-area GEP and county(district)GEP,while the spatial variations in per capita GEP and county(district)GEP were similar.(3.Differences in the spatial distribution of GEP were influenced by regional natural geographical and socioeconomic *** these factors,gross domestic product,population density,and land-use degree density contributed *** among different driving forces noticeably impacted GEP spatial *** findings underscore the necessity of incorporating factors such as population density and the intensity of land-use development into ecosystem management decision-making processes in the upper reaches of the Chaobai River *** policies

关键词： Ecosystem pattern Gross ecosystem product(GEP) Spatiotemporal evolution Optimal parameter-based geographical detector(OPGD) Chaobai River Basin

LMR-CBT: learning modality-fused representations with CB-Transformer for multimodal emotion recognition from unaligned multimodal sequences

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第4期18卷 39-47页

作者： Ziwang FU feng LIU qing XU Xiangling FU Jiayin qi School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Beijing 100876China Shanghai International School of Chief Technology Officer East China Normal UniversityShanghai 200062China School of Computer Science and Technology East China Normal UniversityShanghai 200062China School of Cyberspace Security Guangzhou UniversityGuangdong 510006China

Learning modality-fused representations and processing unaligned multimodal sequences are meaningful and challenging in multimodal emotion *** approaches use directional pairwise attention or a message hub to fuse language,visual,and audio ***,these fusion methods are often quadratic in complexity with respect to the modal sequence length,bring redundant information and are not *** this paper,we propose an efficient neural network to learn modality-fused representations with CB-Transformer(LMR-CBT)for multimodal emotion recognition from unaligned multi-modal ***,we first perform feature extraction for the three modalities respectively to obtain the local structure of the ***,we design an innovative asymmetric transformer with cross-modal blocks(CB-Transformer)that enables complementary learning of different modalities,mainly divided into local temporal learning,cross-modal feature fusion and global self-attention *** addition,we splice the fused features with the original features to classify the emotions of the ***,we conduct word-aligned and unaligned experiments on three challenging datasets,IEMOCAP,CMU-MOSI,and *** experimental results show the superiority and efficiency of our proposed method in both *** with the mainstream methods,our approach reaches the state-of-the-art with a minimum number of parameters.

关键词： modality-fused representations cross-model blocks multimodal emotion recognition unaligned multimodal sequences computational affection

Hybrid Analytical and Data-Driven Model Based Instance-Transfer Method for Power System Online Transient Stability Assessment

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第4期10卷 1664-1675页

作者： feng Li qi Wang Yi Tang Yan Xu Jie Dang School of Electrical Engineering Southeast UniversityNanjing 210000China Center for Power Engineering(CPE) School of Electrical and Electronic EngineeringNanyang Technological UniversitySingapore 639798Singapore Central China Branch of State Grid Corporation of China Wuhan 430077China

Data-driven methods are widely recognized and generate conducive results for online transient stability ***,the tedious and time-consuming process of sample collection is often *** functioning of power systems involves repetitive sample collection due to the constant variations occurring in the operation mode,thereby highlighting the importance of collection *** a means to achieve high sample collection efficiency following the operation mode change,we propose a novel instance-transfer method based on compression and matching strategy,which facilitates the direct acquisition of useful previous samples,used for creating the new sample ***,we present a hybrid model to ensure rationality in the process of sample similarity comparison and selection,where features of analytical modeling with special significance are introduced into data-driven *** the same time,a data-driven method can also be integrated in the hybrid model to achieve rapid error correction of analytical models,enabling fast and accurate post-disturbance transient stability *** a paradigm,we consider a scheme for online critical clearing time estimation,where integrated extended equal area criterion and extreme learning machine are employed as analytical model part and data-driven error correction model part,*** results validate the credible efficacy of the proposed method.

关键词： Critical clearing time extreme learning machine instance-transfer method transient stability assessment