An Empirical Configuration Study of a Common Document Clustering Pipeline by Anton Eklund, Mona Forsman, Frank Drewes

“…The results suggest that BERT embeddings combined with UMAP dimension reduction to no less than 15 dimensions provides a good basis for clustering, regardless of the specific clustering algorithm used. Moreover, while UMAP performed better than PCA in our experiments, tuning the UMAP settings showed little impact on the overall performance. …”
Get full text

Research of the Shift Schedule and Ratio Optimization for the Transmission System of a Two-speed Electric Vehicle by Zhou Yunshan, Yang Kefeng

“…Taking the coupling effect of the shift schedule in optimization process into account,the rule of developing a comprehensive shift strategy,which associates with ratios and considers the dynamic and economic performances is determined. An enumeration algorithm,which has the function of non- dominated comparing and filtering,is designed to obtain the Pareto- optimal solution set for the dual objective function. …”
Get full text

Energy-efficient and fast method on storage and querying in wireless sensor networks by PENG Shao-liang, LI Shan-shan, PENG Yu-xing, LIAO Xiang-ke, XIAO Nong

“…In order to make more practical, a localized data dissemination algorithm, called BubbleGeocast, is designed. It is made up of two components: adaptive accurate data diffusion in real-time and rejection-based uniform data diffusion. …”
Get full text

Single-Object-Based Region Growth: Key Area Localization Model for Remote Sensing Image Scene Classification by Feiyang Li, Jiangtao Wang, Mingyang Wang, Ziyang Wang

“…To tackle this problem, this paper proposes a single-object-based region growth algorithm to effectively localize the most key area in the whole image, so as to generate more discriminative local fine-grained features for the image scene. …”
Get full text

Deep reinforcement learning-based resource joint optimization for millimeter-wave massive MIMO systems by LIU Qingli, LI Xiaoyu, LI Rui

“…Experimental results show that the proposed joint optimization method significantly improves the throughput and energy efficiency of the system compared with the single-stage all-digital precoding and hybrid precoding equal resource allocation methods and the particle swarm optimization-based resource allocation algorithm.…”
Get full text

Active Contour Model Coupling with Higher Order Diffusion for Medical Image Segmentation by Guodong Wang, Jie Xu, Qian Dong, Zhenkuan Pan

“…To enhance the efficiency of the segmentation, the fast Split Bregman algorithm is designed for the segmentation implementation. …”
Get full text

A New Synergistic Forecasting Method for Short-Term Traffic Flow with Event-Triggered Strong Fluctuation by Darong Huang, Zhenping Deng, Bo Mi

“…Directing against the shortcoming of low accuracy in short-term traffic flow prediction caused by strong traffic flow fluctuation, a novel method for short-term traffic forecasting based on the combination of improved grey Verhulst prediction algorithm and first-order difference exponential smoothing is proposed. …”
Get full text

Region-based lossless data hiding with high capacity for medical images by Xiao-hong DENG, Zhi-gang CHEN, Di-qing LIANG, Yi-min MAO

“…In view of the significant regional features of medical images,a new high capacity lossless data hiding method based on region and histogram shifting was presented.Firstly,the presented method utilized segmentation method of the maximum class separation distance to get the foreground region of medical images,and then used the polymeric polygonal approximation and image fitting algorithm to get the embedding region of region foreground.In the embedding procedure,the difference histogram circular shifting method and the code-based histogram shifting method were presented to embed hidden data in foreground and background region respectively,which improved the limit embedding capacity and resolved the overflow and underflow in traditional histogram shifting method.Experimental results show that the proposed method achieves high embedding capacity with 1 bit/pixel and stego-image quality about 40 dB.The presented method can be applied to the quality of sensitive image's large capacity information hiding with regional feature.…”
Get full text

Information Retrieval and Graph Analysis Approaches for Book Recommendation by Chahinez Benkoussas, Patrice Bellot

“…These results extend the applicability of link analysis algorithms to different environments.…”
Get full text

Research Progress of Synthesis and Modification Methods Based on Dynamic Substructures by Jintao Su, Bangdong Wang

“…Finally, the development trend of dynamic substructure synthesis and modification algorithm is proposed.…”
Get full text

Adaptive guaranteed time slots allocation policy in wireless sensor networks with mobility awareness by LI Xiao-ji1, CHEN Chen1, QIU Hong-bing2, MO Wei2

“…To improve the connectivity in mobile wireless sensor networks,an adaptive GTS（guaranteed time slot） allocation algorithm with nodal mobility awareness was proposed.At first,the nodal location in next state was given by Kalman filters forecasting model.Then,a method that considered velocity,direction and relative mobility was used to define mobility level,based on which the nodal priorities for GTS reservation could be determined initially.Subsequently,the priorities could be adjusted adaptively according to the usage status feedback from allocated slots.Finally,the priorities could be used to determine the order for using GTS and the right of use an extra reservation slot.Simulation results show that the proposed scheme could increase the success rate of random access and ensure a lower average packets transmission delay and higher delivery ratio.Furthermore,with the adaptive adjustment scheme for reservation priorities base on usage feedback,the rate of correct utilization of allocated slots is increased significantly in the overall networks.…”
Get full text

Optimizing vehicle routing and scheduling under time constraints by Bala Karlo, Bandecchi Michele, Brcanov Dejan, Gvozdenović Nebojša

“…This paper presents a two-stage algorithm for Vehicle Routing Problem with Time Windows. …”
Get full text

Passive Infrared Sensing Using Plasmonic Resonant Dust Particles by Mark Mirotznik, William Beck, Kimberly Olver, John Little, Peter Pa

“…Here, we present a computational design algorithm along with experimental results that validate the design methodology.…”
Get full text

Robust Estimation of the Unbalance of Rotor Systems Based on Sparsity Control of the Residual Model by Tingpeng Zang, Guangrui Wen, Zhifen Zhang

“…With the help of the sparsity of external disturbances, the unbalance identification is converted into a convex optimization problem and solved by a sparse signal reconstruction algorithm. Experiment results have shown that the proposed method is robust and effective in identifying the unbalance of rotor systems in a complex environment, improving the precision of unbalance estimation and simplifying the balancing process.…”
Get full text

Improvement of and Parameter Identification for the Bimodal Time-Varying Modified Kanai-Tajimi Power Spectral Model by Huiguo Chen, Ting Zhong, Guocui Liu, Junru Ren

“…Based on the Kanai-Tajimi power spectrum filtering method proposed by Du Xiuli et al., a genetic algorithm and a quadratic optimization identification technique are employed to improve the bimodal time-varying modified Kanai-Tajimi power spectral model and the parameter identification method proposed by Vlachos et al. …”
Get full text

Parallel RFSAI-BFGS Preconditioners for Large Symmetric Eigenproblems by L. Bergamaschi, A. Martínez

“…The overall RFSAI-BFGS preconditioned Newton algorithm has shown comparable efficiencies with a well-established eigenvalue solver on all the test problems.…”
Get full text

Uplink assisted downlink channel estimation method of extra-large scale MIMO-OTFS system by Xumin PU, Kaiyuan DENG, Qianbin CHEN

“…A low complexity downlink channel estimation method for high-speed mobile scenarios was proposed for the extra-large scale multiple-input multiple-output (MIMO) orthogonal time-frequency space (OTFS) system.Different from the existing studies, the proposed method considers the significant spatial non-stationary characteristics of extra-large scale MIMO-OTFS system.Based on the visible path region, an enhanced sparse orthogonal matching pursuit (OMP) algorithm with low complexity was proposed, uplink-assisted downlink channel estimation was achieved using the mapping relationship between the uplink and downlink channels in the frequency-division duplex (FDD) mode.Simulation results show that the proposed uplink-assisted downlink channel estimation method can accurately represent the non-stationary of the system, and achieve significant improvement in the channel estimation performance while reducing the computational complexity , and still perform well in high-mobility IoT scenarios.…”
Get full text

On Mixed Equilibrium Problems in Hadamard Spaces by Chinedu Izuchukwu, Kazeem Olalekan Aremu, Olawale Kazeem Oyewole, Oluwatosin Temitope Mewomo, Safeer Hussain Khan

“…We then prove a strong convergence of the resolvent and a Δ-convergence of the proximal point algorithm to a solution of the mixed equilibrium problem under some suitable conditions. …”
Get full text

Fault Detection and Diagnosis in Process Data Using Support Vector Machines by Fang Wu, Shen Yin, Hamid Reza Karimi

“…PCA-SVM and SVM-RFE can effectively detect and diagnose these common faults. In RFE algorithm, all variables are decreasingly ordered according to their contributions. …”
Get full text

Assessment of the food security level in the regions of the European North of Russia based on benchmarking methodology by O. G. Moronova, O. B. Kirik, N. A. Kremlyova

“…On the basis of the author’s methodology, the study develops an algorithm for the benchmarking procedure and tests it on the subjects of the North-West Federal District. …”
Get full text