Pedestrian Evacuation Model considering Dynamic Emotional Update in Direction Perception Domain by Qian Xiao, Jiayang Li

“…This paper addresses the problem by constructing a dynamic evolution mechanism among emotion, state, and behavior. …”
Get full text

Optimal View Estimation Algorithm and Evaluation with Deviation Angle Analysis by Meng Yuan, Hongjun Li

“…Image-based viewpoint estimation is one of the tasks in image analysis, and another is the inverse problem of selecting the best viewpoint for displaying a three-dimensional object. …”
Get full text

Speaker verification method based on cross-domain attentive feature fusion by Zhen YANG, Tianlang WANG, Haiyan GUO, Tingting WANG

“…Aiming at the problem that the lack of structure information among speech signal sample in the front-end acoustic features of speaker verification system, a speaker verification method based on cross-domain attentive feature fusion was proposed.Firstly, a feature extraction method based on the graph signal processing (GSP) was proposed to extract the structural information of speech signals, each sample point in a speech signal frame was regarded as a graph node to construct the speech graph signal and the graph frequency information of the speech signal was extracted through the graph Fourier transform and filter banks.Then, an attentive feature fusion network with the residual neural network and the squeeze-and- excitation block was proposed to fuse the features in the traditional time-frequency domain and those in the graph frequency domain to promote the speaker verification system performance.Finally, the experiment was carried out on the VoxCeleb, SITW, and CN-Celeb datasets.The experimental results show that the proposed method performs better than the baseline ECAPA-TDNN model in terms of equal error rate (EER) and minimum detection cost function (min-DCF).…”
Get full text

ADAFT：an storage architecture of large-scale SDN flow tables based on adaptive deep aggregations by XIONG Bing, YUAN Yue, ZHAO Jinyuan, ZHAO Baokang, HE Shiming, ZHANG Jin

“…To solve the problem of resource shortage of ternary content addressable memory (TCAM) in the data plane of software defined network (SDN), a deep flow table aggregation method was proposed based on content entry trees, and a storage architecture of large-scale SDN flow tables named ADAFT was established. …”
Get full text

A Non-Convex Partition of Unity and Stress Analysis of a Cracked Elastic Medium by Won-Tak Hong

“…We further extend the idea of the almost everywhere partition of unity and apply it to linear elasticity problem. We use a special mapping to build a partition of unity on a non-convex domain. …”
Get full text

Modernité, anachronisme et ambivalence des risques et catastrophes naturelles à travers l’approche géohistorique by Nancy Meschinet De Richemond

“…Historical data allows to raise the problem of natural hazard consideration in territorial management in an original way. …”
Get full text

Distributed data trading algorithm based on multi-objective utility optimization by Xiaohong HUANG, Yong ZHANG, Desheng SHAN, Yekui QIAN, Lu HAN, Dandan LI, Qun CONG

“…The traditional centralized data trading models are not well applicable to the current intelligent era where everything is interconnected and real-time data is generated, and in order to maximize the use of collected data, it is essential to design an effective data trading framework.Therefore, a distributed data trading framework based on consortium blockchain was proposed, which realized P2P data trading without relying on a third party.Aiming at the problem that existing data trading models only consider the factors of the data itself and ignore the factors related to user tasks, a bi-level multi-objective optimization model was constructed based on multi-dimensional factors, such as data quality, data attributes, attribute relevance and consumer competition, to optimize the utilities of data provider (DP) and data consumer (DC).To solve the above model, an improved multi-objective genetic algorithm-collaborative NSGAII was proposed, calculated by the cooperation of DP, DC and data aggregator (AG).The simulation results show that the collaborative NSGAII achieves better performance in terms of the utilities of DP and DC, thus realizing more effective data trading.…”
Get full text

Music in the Novel “Point Counter Point” by Aldous Huxley by Nataliia Liubarets

“…The article considers the problem of interaction between word and music in Aldous Huxley’s novel “Point Counter Point”. …”
Get full text

Euthanasia in Ecuador and Latin America: A Comparative Study using Neutrosophic Logic and Multivariate Analysis by Manuel Richard Naranjo Rodríguez, Sandra Dayanara Correa Solis, Alexander Joshua Bajaña Jiménez

“…To this end, a database with 300 records was constructed, integrating quantitative, qualitative, and neutrosophic variables, which allow for the capture of both structural data and ambiguous assessments of morality and professional opinion. …”
Get full text

The utility of practical theology: mapping the domain, goals, strategies and criteria of practical theological research by C. Hermans, W. J. Schoeman

“…If practical theology wants to construct knowledge about the improvement of practice, some strategies are preferable compared to other strategies. …”
Get full text

Self-supervised speech representation learning based on positive sample comparison and masking reconstruction by Wenlin ZHANG, Xuepeng LIU, Tong NIU, Qi CHEN, Dan QU

“…To solve the problem that existing contrastive prediction based self-supervised speech representation learning methods need to construct a large number of negative samples, and their performance depends on large training batches, requiring a lot of computing resources, a new speech representation learning method based on contrastive learning using only positive samples was proposed.Combined with reconstruction loss, the proposed method could obtain better representation with lower training cost.The proposed method was inspired by the idea of the SimSiam method in image self-supervised representation learning.Using the siamese network architecture, two random augmentations of the input speech signals were processed by the same encoder network, then a feed-forward network was applied on one side, and a stop-gradient operation was applied on the other side.The model was trained to maximize the similarity between two sides.During training processing, negative samples were not required, so small batch size could be used and training efficiency was improved.Experimental results show that the representation model obtained by the new method achieves or exceeds the performance of existing mainstream speech representation learning models in multiple downstream tasks.…”
Get full text

Numerical Solutions for Coupled Trapezoidal Fully Fuzzy Sylvester Matrix Equations by Ahmed AbdelAziz Elsayed, Nazihah Ahmad, Ghassan Malkawi

“…However, there are some situations in which the crisp Sylvester matrix equations are not well equipped to deal with the uncertainty problem during the stability analysis of control systems. …”
Get full text

Recognition Algorithm of AE Signal of Rock Fracture Based on Multiscale 1DCNN-BLSTM by Weihua Wang

“…Determining the brittle mineral content of rock according to the acoustic emission characteristics of rock is helpful to understand the mechanical behavior of rock in field monitoring. This article constructs a deep learning algorithm model to identify acoustic emission signals released from rock fractures with different brittle mineral contents. …”
Get full text

Speaker verification method based on cross-domain attentive feature fusion by Zhen YANG, Tianlang WANG, Haiyan GUO, Tingting WANG

“…Aiming at the problem that the lack of structure information among speech signal sample in the front-end acoustic features of speaker verification system, a speaker verification method based on cross-domain attentive feature fusion was proposed.Firstly, a feature extraction method based on the graph signal processing (GSP) was proposed to extract the structural information of speech signals, each sample point in a speech signal frame was regarded as a graph node to construct the speech graph signal and the graph frequency information of the speech signal was extracted through the graph Fourier transform and filter banks.Then, an attentive feature fusion network with the residual neural network and the squeeze-and- excitation block was proposed to fuse the features in the traditional time-frequency domain and those in the graph frequency domain to promote the speaker verification system performance.Finally, the experiment was carried out on the VoxCeleb, SITW, and CN-Celeb datasets.The experimental results show that the proposed method performs better than the baseline ECAPA-TDNN model in terms of equal error rate (EER) and minimum detection cost function (min-DCF).…”
Get full text

Natural Frequency Analysis of Permanent Magnet Eddy Current Couplings Based on the Riccati Transfer Matrix Method by Xu Chengxi, Wang Jian

“…In order to improve the accuracy of natural frequency analysis and calculation for the coupling rotor system, a transfer matrix method is proposed to construct a dynamic analysis model of the rotor when conducting modal characteristics research on permanent magnet eddy current couplings. …”
Get full text

Soft label collaborative view consistency enhancement with application to incomplete multi-view clustering. by Jie Zhang, Jiali Tang

“…Firstly, we leverage the encoders of Transformers to construct a soft-label view information interaction module, which fully utilizes soft-labels to enhance view feature embeddings. …”
Get full text

Research on resource allocation algorithm of centralized and distributed Q-learning in machine communication by Yunhe YU, Jun SUN

“…Under the premise of ensuring partial machine type communication device (MTCD)’s quality of service (QoS) requirements, the resource allocation problem was studied with the goal of maximizing system throughput in the massive machine type communication (mMTC) scenario.Two resource allocation algorithms based on Q-learning were proposed: centralized Q-learning algorithm (team-Q) and distributed Q-learning algorithm (dis-Q).Firstly, taking into account MTCD’s geographic location and multi-level QoS requirements, a clustering algorithm based on cosine similarity (CS) was designed.In the clustering algorithm, multi-dimensional vectors that represent MTCD and data aggregator (DA) were constructed, and MTCDs can be grouped according to the CS value between multi-dimensional vectors.Then in the MTC network, the team-Q learning algorithm and dis-Q learning algorithm were used to allocate resource blocks and power for the MTCD.In terms of throughput performance, team-Q and dis-Q algorithms have an average increase of 16% and 23% compared to the dynamic resource allocation algorithm and the greedy algorithm, respectively.In terms of complexity performance, the dis-Q algorithm is only 25% of team-Q algorithm and even below, the convergence speed is increased by nearly 40%.…”
Get full text

Analysis of a Weak Galerkin Mixed Formulation for Modified Maxwell’s Equations by Abdelhamid Zaghdani, Abdelhalim Hasnaoui

“…In this paper, we are interested in studying a mixed formulation of weak Galerkin type to approach the electric field and a Lagrange multiplier, which are solutions of a problem deriving from Maxwell’s equations. Our numerical scheme is formed with stable finite elements constructed of usual polynomials of degree <i>k</i> for the electric field and of degree <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>k</mi><mo>+</mo><mn>1</mn></mrow></semantics></math></inline-formula> for the Lagrange multiplier; its consistency and well-posedness are shown. …”
Get full text

Dual Convolution Neural Networks of Ensemble Learning with Attention Mechanism for Rice Classification by Cheng Linfeng

“…The aim of this project is to develop a dual convolutional neural network for ensemble learning based on the initial model and the res network model, and apply the ensemble model to the rice classification problem. The ensemble model in this article combines two deep models, InceptionNet and ResNet, and incorporates self-attention block method to construct an attention mechanism that uses multi head attention layers to capture relationships in the input. …”
Get full text

On the issue of impact of income inequality on the socio-economic development of territories by M. L. Bykova

“…The issues of economic inequality and justice were considered in the works of the philosophers of Ancient Greece. Over time, the problem of income inequality has not lost its relevance, which is confirmed by domestic and foreign studies. …”
Get full text