Pruning Bayesian networks for computationally tractable multi-model calibration by Nicolas Gratius, Mario Bergés, Burcu Akinci

“…In this work, we propose a graph pruning algorithm to reduce computational cost while minimizing the loss in calibration ability by incorporating domain-driven metrics for selection purposes. …”
Get full text

Skip-Connected CNN Exploiting BNN Surrogate for Antenna Modelling by Yubo Tian, Jinlong Sun, Zhiwei Zhu

“…The combination of evolutionary algorithms with full-wave electromagnetic (EM) simulation software is an effective method for antenna optimal design. …”
Get full text

High-Precision Spotlight SAR Imaging with Joint Modified Fast Factorized Backprojection and Autofocus by Man Zhang, Haolin Li, Guanyong Wang

“…Fast factorized backprojection (FFBP) takes advantage of high accuracy of time-domain algorithms while also possessing high efficiency comparable with conventional frequency domain algorithms. …”
Get full text

Normative Production Accounting in the Digital Economy: Issues and Solutions by M. V. Polulekh

“…It was determined that the formula for the normative method requires modification while the algorithm for allocation of indirect costs requires justification and interpretation. …”
Get full text

Towards a Scalable and Adaptive Learning Approach for Network Intrusion Detection by Alebachew Chiche, Million Meshesha

“…An integrated approach of machine learning with knowledge-based system is proposed for intrusion detection. While machine learning algorithm is used to construct a classifier model, knowledge-based system makes the model scalable and adaptive. …”
Get full text

Thermal pure states for systems with antiunitary symmetries and their tensor network representations by Yasushi Yoneta

“…Thermal pure state algorithms, which employ pure quantum states representing thermal equilibrium states instead of statistical ensembles, are useful both for numerical simulations and for theoretical analysis of thermal states. …”
Get full text

Client grouping and time-sharing scheduling for asynchronous federated learning in heterogeneous edge computing environment by Qianpiao MA, Qingmin JIA, Jianchun LIU, Hongli XU, Renchao XIE, Tao HUANG

“…., edge heterogeneity, data Non-IID, and communication resource constraints, a grouping asynchronous federated learning (FedGA) mechanism was proposed.Edge nodes were divided into multiple groups, each of which performed global updated asynchronously with the global model, while edge nodes within a group communicate with the parameter server through time-sharing communication.Theoretical analysis established a quantitative relationship between the convergence bound of FedGA and the data distribution among the groups.A time-sharing scheduling magic mirror method (MMM) was proposed to optimize the completion time of a single round of model updating within a group.Based on both the theoretical analysis for FedGA and MMM, an effective grouping algorithm was designed for minimizing the overall training completion time.Experimental results demonstrate that the proposed FedGA and MMM can reduce model training time by 30.1%～87.4% compared to the existing state-of-the-art methods.…”
Get full text

RESEARCH ON PARAMETRIC ANALYSIS AND MULTI-OBJECTIVE OPTIMIZATION OF CYLINDRICAL PRESSURE STRUCTURE by LIU Feng, TU ChaoHua, ZHAO YanKai

“…In order to improve the design efficiency and performance of the cylindrical pressure structure,strength and stability analysis methods were determined,the initial scheme was analyzed. the second development of Abaqus software was carried out by using Python language,Abaqus was integrated with i Sight software,the parametric analysis flow of pressure structure was designed,could realize automatic modeling and analysis of cylindrical pressure structure. the most Latin hypercube method was used to selectting the sample points,the sensitivity analysis of the design variables were carried out,The comparison of the fitting accuracy shown that the response surface model had the highest accuracy,the approximate model of the cylindrical pressure structure based on the fourth-order response surface was obtained. the multi-objective optimization model was established,The second generation of non dominated sorting genetic algorithm was used to solving the multi-objective optimization problem,the results shown that the weight of the optimization scheme was reduced,while the ultimate strength was greatly improved,improved the performance of the cylindrical pressure structure.…”
Get full text

Machine Learning G-Code Optimization by Héctor Lasluisa-Naranjo, David Rivas-Lalaleo, Joaquín Vaquero-López, Christian Cruz-Moposita

“…This research applies the K-means machine learning clustering algorithm to optimize G-code parameters such as extruder and heated bed temperature, deposition speed, and flow control. …”
Get full text

Indoor positioning system for wireless sensor networks based on two-stage fuzzy inference by Chia-Hsin Cheng, Yi Yan

“…In this article, we present a two-stage indoor positioning scheme using a fuzzy-based algorithm aimed at minimizing uncertainty in received signal strength indicator measures from reference nodes in wireless sensor networks. …”
Get full text

Differential Evolution for Optimizing Model Parameters in Simulation of Direct Dimethyl Carbonate Synthesis by Outi Ruusunen, Riitta Keiski, Mika Ruusunen

“…The Differential Evolution (DE) algorithm was applied to optimize parameters of the model. …”
Get full text

Dual Hiding in Digital Image Files by Farah Mohammed

“…In this paper, a modified algorithm is suggested depending on two principles: double information hiding and multiple watermarking. …”
Get full text

Inverse problems for discrete Hermite nabla difference equation by B. Shiri, Y. Guang, D. Baleanu

“…Furthermore, a simple and fast recursive algorithm is proposed for computing corresponding eigenvectors. …”
Get full text

A hybrid unsupervised machine learning model with spectral clustering and semi-supervised support vector machine for credit risk assessment. by Tao Yu, Wei Huang, Xin Tang, Duosi Zheng

“…The effectiveness, efficiency, and robustness of the proposed TSC-SVM model are demonstrated through various real-world applications. The proposed algorithm is anticipated to expand the customer base for financial institutions while reducing economic losses.…”
Get full text

A Hybrid Mobile Robot Path Planning Scheme Based on Modified Gray Wolf Optimization and Situation Assessment by Yilun Liu, Xiaoming Li

“…When combined with a situation assessment mechanism, it realizes dynamic obstacle avoidance while keeping the path length as short as possible.…”
Get full text

TraIL: Pinpoint Trajectory for Indoor Localization by Shengnan Li, Zheng Qin, Chenshu Wu, Zheng Yang

“…Our basic idea is that WiFi-only localization can generate rough but absolute positions, while user motion is able to bring accurate but relative locations. …”
Get full text

Robust Mainlobe Interference Suppression Based on Joint Oblique Projection for Dual Polarization Conformal Array by Chao Liu, Xiaoyuan Zhang, Junjie Qian, Lei Zhang

“…In this paper, a robust mainlobe interference suppression algorithm is proposed in a space-polarization joint domain based on a dual-polarized conformal array. …”
Get full text

Multi-camera video collaborative analysis method based on edge computing by Zhibo QI, Lei DU, Ru HUO, Fan YANG, Tao HUANG

“…In order to reduce the processing volume of multi-camera real-time video data in smart city scenarios, a video collaborative analysis method based on machine learning algorithms at the edge was proposed.Firstly, for the important objects detected by each camera, different key windows were designed to filter the region of interest (RoI) in the video, reduce the video data volume and extract its features.Then, based on the extracted data features, the same objects in the videos from different cameras were annotated, and a strategy for calculating the association degree value between cameras was designed for further reducing the video data volume.Finally, the GC-ReID algorithm based on graph convolutional network (GCN) and re-identification (ReID) was proposed, aiming at achieving the collaborative analysis of multi-camera videos.The experimental results show that proposed method can effectively reduce the system latency and improve the video compression rate while ensuring the high accuracy, compared with the existing video analysis methods.…”
Get full text

Numerical Simulation of Freckle Defects in Nickel based Superalloys by LIU Dong rong, REN Ying, GUO Er jun

“…In order to deeply understand the formation characteristics of freckle defects in the process of directional solidification of nickelbased superalloy, three major equations of fluid mechanics were used to simulate the formation of freckles during the directional solidification of CMSX2 superalloy based on the SIMPLE (SemiImplicit Method for Pressure Linked Equations) algorithm The simulations in the reference were used to validate the model The effects of geometric shape and alloy composition on the flow field, solid fraction field and solute segregation distribution during solidification of the casting were investigated The simulations show that freckles are easily formed in the casting with shrinkage section The Al element in the alloy composition promotes the formation of freckles, while the Ta element plays a very good role in suppressing the formation of freckles…”
Get full text

A framework for detecting and predicting highway traffic anomalies via multimodal fusion and heterogeneous graph neural networks. by Shaowei Sun, Mingzhou Liu

“…For instance, the proposed MHGNN-CPLE model achieves superior accuracy and F1 score in static detection tasks while maintaining high accuracy under different noise levels in dynamic detection scenarios. …”
Get full text