Blind source separation and unmanned aerial vehicle classification using CNN with hybrid cross-channel and spatial attention module by Jiangong Ni, Zhigang Zhou

“…The experimental results indicate that the mean absolute error (MAE) of the original algorithm was 14.58%, while the MAE of the improved FastICA decreased by 10.31%, dropping to 4.27%. …”
Get full text

Research on the Injection Mold Design and Molding Process Parameter Optimization of a Car Door Inner Panel by Kefan Yang, Youmin Wang, Guoqing Wang

“…We established the objective function model with gate position as the independent variable, and used a multi-population genetic algorithm to solve the optimal position of the function model to get the best gate position. …”
Get full text

Clustering-Based Thermography for Detecting Multiple Substances Under Large-Scale Floating Covers by Yue Ma, Benjamin Steven Vien, Thomas Kuen, Wing Kong Chiu

“…Cooling constants are used to reconstruct thermal images, and clustering algorithms are explored to segment and identify different material states beneath the covers. …”
Get full text

An Intelligent Track Segment Association Method Based on Characteristic-Aware Attention LSTM Network by Jiadi Qi, Xiaoke Lu, Jinping Sun

“…The algorithm can segment and temporally align track segments containing multi-dimensional characteristics. …”
Get full text

Dementia Scale Score Classification Based on Daily Activities Using Multiple Sensors by Akira Minamisawa, Shogo Okada, Ken Inoue, Mami Noguchi

“…We then developed a feature extraction method related to daily activity patterns based on a clustering algorithm and analyzed its effectiveness. In the experimental evaluation, we trained binary classification models to classify dementia scale scores based on the Mini-Mental State Examination (MMSE) from these datasets. …”
Get full text

Research on RF Intensity Temperature Sensing based on 1D-CNN by DING Meiqi, GUI Lin, WANG Ziyi, SHANG Disen, QIAN Min, LI Qiankun

“…Finally, the Root Mean Square Error (RMSE) is used as the evaluation index, and the performance of 1D-CNN is compared with the traditional algorithms (maximum-value method, centroid method and Gaussian fitting method) to analyze its performance under different temperature conditions.…”
Get full text

MULTI-SENSORY BRANDING AS A TOOL FOR THE FORMATION OF A POSITIVE IMAGE OF THE HIGHER EDUCATION INSTITUTION by Natalya A. Spirina

“…The author also offers the algorithm of creation the educational brand, based on the five senses of consumers, consisting of six interrelated stages: audit of the sensory elements of brand, the search for ideas, the choice of scenario, creating an image, the implementation of something intended, and the results evaluation. …”
Get full text

Risk Assessment for Water Disaster of Karst Tunnel Based on the Weighting of Reliability Measurement and Improved Extension Cloud Model by Yingli Jiang, Jie Cui, Hao Liu, Yanlong Zhang

“…Secondly, according to the two different entropy algorithms of the extension cloud model, an improved extension cloud model is proposed based on the entropy algorithm fusion of game theory. …”
Get full text

Heterogeneity-Aware Personalized Federated Neural Architecture Search by An Yang, Ying Liu

“…Furthermore, we develop a model-heterogeneous FL algorithm called heteroFedAvg to facilitate collaborative model training for the discovered personalized models. …”
Get full text

Observing convective activities in complex convective organizations and their contributions to precipitation and anvil cloud amounts by Z. Wang, J. Yuan

“…Compared with previous tracking algorithms that focused only on variations in areas, the novel variable-BT tracking algorithm is designed to track the core structure in complex convective organizations and document the evolution of both the area and BT structures. …”
Get full text

Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification by Yongmin Liu, Fengjiao Xiao, Xinying Zheng, Weihao Deng, Haizhi Ma, Xinyao Su, Lei Wu

“…In order to extract comprehensive and critical feature information, a new CA-MFE algorithm is proposed. The algorithm first utilizes different convolution kernels in CNN to extract multi-scale local feature information, and then based on the global feature extraction ability of attention mechanism, parallel processing of channel and spatial attention mechanism is used to extract multidimensional global feature information. …”
Get full text

Investigating the Stroke- and Aging-Related Changes in Intermuscular Coupling by Refined Composed Multiscale Fuzzy Entropy by Hairong Yu, Yuanyu Wu, Rong Song

“…Meanwhile, the influence of aging and stroke on the human neuromuscular system is comprehensively studied by a stable and reliable entropy algorithm, and it contributes to the rehabilitation clinical evaluation of stroke patients.…”
Get full text

Unsupervised Salient Object Detection by Aggregating Multi-Level Cues by Chenxing Xia, Hanling Zhang

“…Extensive experimental results demonstrate that the proposed algorithm performs favorably against the state-of-art saliency detection methods in terms of different evaluation metrics on several benchmark datasets.…”
Get full text

Red Wine Classification Using SVM and RBF Kernel by Kevin Silvanus Hutabarat, Rosalia Arum Kumalasanti, M.T.

“…The duration of fermentation and the materials used will give different quality products. Nowadays technology is present to provide solutions to these problems by using the SVM algorithm on Machine Learning. …”
Get full text

The impact of vehicle moving violations and freeway traffic flow on crash risk: An application of plugin development for microsimulation. by Junhua Wang, Yumeng Kong, Ting Fu, Joshua Stipancic

“…A Fuzzy C-mean Clustering algorithm was developed to identify high risk states in different road segments over time. …”
Get full text

Treatment for rheumatic polymyalgia by Azamat Makhmudovich Satybaldyev

“…The role of nonsteroidal anti-inflammatory drugs in the treatment of RP is also evaluated. An algorithm is proposed for the management of a patient with RP.…”
Get full text

Enhancing Multi-Key Fully Homomorphic Encryption with Efficient Key Switching and Batched Multi-Hop Computations by Liang Zhou, Ruwei Huang, Bingbing Wang

“…Our approach eliminates the need for an auxiliary Gentry-Sahai-Waters (GSW)-type scheme, simplifying the design and significantly reducing the public key size. We propose novel algorithms for evaluation key generation and key switching that simplify the computation while allowing each party to independently precompute and share its evaluation keys, thereby reducing both computational overhead and storage costs. …”
Get full text

Dynamical and computational analysis of fractional Whitham-Broer-Kaup equations arising in shallow-water waves by Amit Kumar, Devendra Kumar, Dumitru Baleanu

“…The fractional W-B-K model is a coupled structure that describes the nonlinear evolution of shallow-water waves. The novelty of the proposed algorithm, the fractional derivative, is taken in the Caputo-Fabrizio (CF) sense, which consists of an exponential form of the non-singular kernel. …”
Get full text

Immersive simulation of skydiving in wind tunnels: exploring virtual reality for training and experience enhancement by Ján Lacko

“…For evaluation we use a meCUE 2.0 methodology. Five validated modules relate to the perception of different characteristics, to users’ emotions and to consequences. …”
Get full text

Experimental Verification of Optimized Multiscroll Chaotic Oscillators Based on Irregular Saturated Functions by J. M. Muñoz-Pacheco, D. K. Guevara-Flores, O. G. Félix-Beltrán, E. Tlelo-Cuautle, J. E. Barradas-Guevara, C. K. Volos

“…Then, the positive Lyapunov exponent is optimized using the differential evolution algorithm to obtain chaotic attractors with 2 to 5 scrolls. …”
Get full text