PLFF-SLAM: A Point and Line Feature Fused Visual SLAM Algorithm for Dynamic Illumination Environments by Shucheng Huang, Wenhan Ren, Mingxing Li

“…Firstly, we designed a point feature extraction method based on the GCNV2 network, which improves the extraction performance of the point feature network by modifying the encoding layer structure and reconstructing the loss function. …”
Get full text

Investigating the Effect of Climatic Parameters Predicting the Mortality Rate Due to Cardiovascular and Respiratory Disease with Soft Computing Methods by Hamidreza Ghazvinian, Hojat Karami

“…It can be very important to accurately identify and predict with smart models in disease outbreaks and as a result in mortality statistics. This study was conducted with the aim of comparing the performance of multilayer perceptron (MLP) neural network, radial basis function (RBF) and regression support vector machine (SVR) methods in modeling and predicting the time series of mortality caused by cardiovascular and respiratory diseases based on climatic parameters and pollutants. …”
Get full text

A Mechanism-aid Deep Learning Method for Li-ion Battery State-of-charge Estimation by Zhanghua Xiao, Cheng Ji, Fangyuan Ma, Jingde Wang, Wei Sun, Chi Zhai

“…For this purpose, a mechanism-aid deep learning method is proposed, in which the loss function of the LSTM neural network is modified by the equivalent circuit model. …”
Get full text

Transient Characteristics and Line Selection of Two-Point Grounding Faults on Same Phase in Resonant Grounding System by Yingtong LIU, Chun HUANG, Jingbo YUAN, Sen YAN

“…Aiming at the low accuracy problem in line selection of two-point grounding faults on same phase in distribution network, a new fault feeder identification method suitable for two-point grounding faults on same phase in resonant grounding systems is proposed according to the transient characteristics of zero-sequence current (ZSC) and zero-sequence voltage (ZSV). …”
Get full text

A Deep Reinforcement Learning Approach for Portfolio Management in Non-Short-Selling Market by Ruidan Su, Chun Chi, Shikui Tu, Lei Xu

“…A loss penalty term is also designed in the reward function to prevent sharp drawdown during trading. …”
Get full text

Highly stretchable transparent Ag nanowire-polyurethane hybrid bilayer electrodes for multifunctional applications by Fang Luo, Seo-Yun Choi, Yewon Lee, Jun-Hyeok Kang, Joon Jang, Hyun-Jung Jung, Seungmin Lee, Ji-Yoon Chae, Han-Ki Kim

“…In the AgNW-PU mixed composite, PU functioned as a stretchable matrix, preserving the high conductivity and transparency of the AgNW network even under applied mechanical stress. …”
Get full text

Deformable Feature Fusion and Accurate Anchors Prediction for Lightweight SAR Ship Detector Based on Dynamic Hierarchical Model Pruning by Yue Guo, Shiqi Chen, Ronghui Zhan, Wei Wang, Jun Zhang

“…In recent years, convolutional neural networks (CNNs) have been extensively utilized for synthetic aperture radar (SAR) ship detection tasks. …”
Get full text

Active RIS-NOMA Uplink in URLLC, Jamming Mitigation via Surrogate and Deep Learning by Ghazal Asemian, Mohammadreza Amini, Burak Kantarci

“…A thorough examination of various network parameters is conducted, including user transmit powers, active RIS elements amplitude, and the number of RIS elements. …”
Get full text

A formal notation of legal rules applicable in the local space by Anna M. Barańska, Konrad Eckes

“…The third aspect considered are differences in the way users move around the local road network and in elementary spatial fields. The network structure is represented by intersections, which are noted as node matrices. …”
Get full text

Blockchain-Based Trusted Traceability Scheme for Food Quality and Safety by Ting Guo, Yineng Chen, Qingshan Ren, Di Li, Weiqiong Bo, Xiayu Wang

Get full text

基于系统特性盲辨识的齿轮箱故障诊断 by 曹学岩, 黄晋英, 赵仕龙

“…Blind system identification is a signal processing technology,which obtains the function of system characteristics from its output data only.The system characteristics are associated with its own structure,peroperating mode corresponding to a particular working state.Gearbox fault diagnosis can be conducted by combining the system structure and working condition.Firstly,using independent component analysis to preprocess the output data,the fault frequency of signal as the responding signal of a systemmodel is extracted.Secondly,the time series model is built by using high order cumulants of eliminating and attenuating characteristics of Gaussian noise.Finally,the ARMA bispectrum qualitatively analysis isobtained according to the coefficients of the model.In the meanwhile,the quantitative criteria is obtained by using quantum self-organizing feature map neural network.The results show that,the method can provide some valuable conclusions for presence and type of the fault diagnosis of the gearbox.…”
Get full text

A Bifunctional Fibrous Scaffold Implanted with Amorphous Co2P as both Cathodic and Anodic Stabilizer for High‐Performance Li─S Batteries by Gang Zhao, Tianran Yan, Lei Wang, Cheng Yuan, Tong Chen, Bin Wang, Chen Cheng, Pan Zeng, Yude Su, Liang Zhang

Get full text

Integrated single-cell and transcriptomic analysis of bone marrow-derived metastatic neuroblastoma reveals molecular mechanisms of metabolic reprogramming by Jing Chu, Rong Qin, Shu-Jing Wang, Qiang Wang, Qiang Wu

“…Finally, in vitro experiments were carried out to validate the roles of selected genes in regulating NB cell proliferation, migration, invasion, and mitochondrial function. Single-cell transcriptomic analysis of bone marrow–derived NB samples identified nine distinct cell subpopulations with diverse intercellular communication networks. …”
Get full text

High genetic relatedness between multidrug resistant bacteria before and after the 2022 invasion of Ukraine by Francois Lebreton, Viacheslav Kondratiuk, Valentyn Kovalchuk, Niels Pfennigwerth, Ting L. Luo, Brendan T. Jones, Nadiia Fomina, Frieder Fuchs, Jörg B. Hans, Jessica Eisfeld, Ana Ong, Sören Gatermann, Jason W. Bennett, Patrick Mc Gann

Get full text

VRU-YOLO: A Small Object Detection Algorithm for Vulnerable Road Users in Complex Scenes by Yunxiang Liu, Yuqing Shi

“…Finally, to alleviate the deficiencies of traditional loss functions in shape matching and computational efficiency, we propose the Wise-Powerful Intersection over Union (WPIoU) loss function, which further optimizes the regression of target bounding boxes. …”
Get full text

An Improved DeepSORT-Based Model for Multi-Target Tracking of Underwater Fish by Shengnan Liu, Jiapeng Zhang, Haojun Zheng, Cheng Qian, Shijing Liu

“…This study proposes an underwater fish object tracking method based on the improved DeepSORT algorithm, utilizing ResNet as the backbone network, embedding Deformable Convolutional Networks v2 to enhance adaptive receptive field capabilities, introducing Triplet Loss function to improve discrimination ability among similar fish, and integrating Convolutional Block Attention Module to enhance key feature learning. …”
Get full text

Protein-protein interaction analysis highlights additional loci of interest for multiple sclerosis. by Giammario Ragnedda, Giulio Disanto, Gavin Giovannoni, George C Ebers, Stefano Sotgiu, Sreeram V Ramagopalan

“…However, the relative candidate genes that underlie these associations and their functions are largely unknown. We conducted a protein-protein interaction (PPI) analysis of gene products coded in loci recently reported to be MS associated at the genome-wide significance level and in loci suggestive of MS association. …”
Get full text

YOLO-BOS: An Emerging Approach for Vehicle Detection with a Novel BRSA Mechanism by Liang Zhao, Lulu Fu, Xin Jia, Beibei Cui, Xianchao Zhu, Junwei Jin

“…Lastly, we introduce Shape-IOU, a new loss function that significantly enhances the accuracy and robustness of detection results for vehicles of varying sizes. …”
Get full text

Leveraging BiLSTM-CRF and adversarial training for sentiment analysis in nature-based digital interventions: Enhancing mental well-being through MOOC platforms by Juanjuan Zang

“…To achieve this, we integrate a Bidirectional Long Short-Term Memory (BiLSTM) network with a Conditional Random Field (CRF). The BiLSTM captures word associations in both forward and backward directions, feeding these results into the CRF network to establish the conditional distribution between the feature function and labels. …”
Get full text

miR-100-5p Is a Novel Biomarker That Suppresses the Proliferation, Migration, and Invasion in Skin Cutaneous Melanoma by Xiao Zhang, Yuqi Deng, Xiao Liang, Yamin Rao, Haiyan Zheng, Fei Liu, Xusong Luo, Jun Yang, Jun Chen, Di Sun

“…Finally, we constructed a regulatory network to illustrate the regulatory relationship of miR-100-5p. …”
Get full text