De l'attrait des médias sociaux pour l'apprentissage des langues – Regard sur l'état de l'art by Katerina Zourou

“…We then critically discuss three key features of web 2.0 technologies (user participation, openness and network effects). …”
Get full text

Science of science by S. Fortunato, C. T. Bergstrom, K. Börner, J. A. Evans, D. Helbing, S. Milojević, A. M. Petersen, F. Radicchi, R. Sinatra, B. Uzzi, A. Vespignani, L. Waltman, D. Wang, A.-L. Barabási

“…Identifying fundamental drivers of science and developing predictive models to capture its evolution are instrumental for the design of policies that can improve the scientific enterprise – for example, through enhanced career paths for scientists, better performance evaluation for organizations hosting research, discovery of novel effective funding vehicles, and even identification of promising regions along the scientific frontier. …”
Get full text

RGB-FIR Multimodal Pedestrian Detection with Cross-Modality Context Attentional Model by Han Wang, Lei Jin, Guangcheng Wang, Wenjie Liu, Quan Shi, Yingyan Hou, Jiali Liu

“…Existing work has focused on the design of fusion modules after feature extraction of RGB and FIR branch backbone networks, achieving a multimodal backbone network framework based on back-end fusion. …”
Get full text

Machine learning for defect condition rating of wall wooden columns in ancient buildings by Yufeng Li, Wu Ouyang, Zhenbo Xin, Houjiang Zhang, Shuqi Sun, Dian Zhang, Wenbo Zhang

“…Data processing algorithms were introduced to process the source data, fuse their features, and augment the datasets. Using traditional rating results as labels, Machine Learning classification models for rating the defect conditions of wooden columns were trained and evaluated. …”
Get full text

Detecting Falls and Slips of Wheelchair Users Using Low-Resolution Thermal Image Analysis by Shisei Nakamura, Masaaki Yamauchi, Miwa Sugita, Yoshihiro Aso, Yuichi Ohsita, Hideyuki Shimonishi

“…” Additionally, to enhance the generalizability of the system to various environmental conditions, we incorporated multi-task learning and a two-layer LSTM network, extending FDCTF. As a result, in a single-environment evaluation, our system achieved an F1 score of 1.0 for fall detection. …”
Get full text

Study on incentive mechanism of reward and punishment on work efficiency of PCB welder based on recurrence quantification analysis and electroencephalogram signals by Zhang Qian, Mingyue Guo, Fuwang Wang

“…The accuracy of the twin support vector machine (TWSVM) reaches 98.71%, which is 0.79% and 14.37% higher than existing EEG-based incentive evaluation methods, such as the phase-locking value combined with convolutional neural network (accuracy: 97.92%) and spectral power features (accuracy: 84.34%). …”
Get full text

Specific Management of Business-Ecosystem Shaping and Developing by O. E. Kalenov

“…To understand specificity of management the author suggests studying business-ecosystem as a triad of views integrated by mandatory use of digital tools and technologies. By researching evolution of business-models the author identifies key characteristics of business-ecosystem, such as building by the module principle, self-regulation and coordination, customization, creating value at the expense of cooperation and co-competition, intensifying the role of intangible factors, network and ecosystem effect, etc., which substantiate certain specific features that should be taken into account in management. …”
Get full text

APPLYING TRANSFORMER ARCHITECTURE TO ENHANCE ATTACK DETECTION PERFORMANCE IN INTRUSION DETECTION SYSTEMS by Vu Thi Phuong*, Hoang Thi Hong Ha, Dinh Gia Truong, Tran Thi Yen

“…The UNSW-NB15 dataset is utilized for model training and evaluation. The data preprocessing pipeline includes handling missing values, encoding categorical features, normalizing numerical features, and splitting stratified training and testing sets. …”
Get full text

Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs by Liying Zhu, Sen Wang, Mingfang Chen, Aiping Shen, Xuangang Li

“…Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. …”
Get full text

Face super-resolution via iterative collaboration between multi-attention mechanism and landmark estimation by Chang-Teng Shi, Meng-Jun Li, Zhi Yong An

“…To address this issue, we propose a face super-resolution method based on iterative collaboration between a facial reconstruction network and a landmark estimation network. This method employs a Multi-Convolutional Attention Block for multi-scale feature extraction, and an Attention Fusion Block is introduced to enhance features using facial priors. …”
Get full text

Multi-View Intrusion Detection Framework Using Deep Learning and Knowledge Graphs by Min Li, Yuansong Qiao, Brian Lee

“…This paper proposes a knowledge graph-enhanced multi-view deep learning framework, considering the strategy of integrating network traffic, host behavior, and semantic relationships; and evaluates the impact of the secondary fusion strategy on feature fusion to identify the optimal multi-view model configuration. …”
Get full text

Deep Learning-Based Music Quality Analysis Model by Jing Jing

“…In the literature, shallow learning is a traditional music-related quality recognition method, that is, artificial statistical feature extraction and recognition are designed. Meanwhile, our deep learning module leverages the so-called PCANET network to implement the feature extraction process, and subsequently takes the spectrogram describing the music-related information as the network input. …”
Get full text

DB-Net and DVR-Net: Optimized New Deep Learning Models for Efficient Cardiovascular Disease Prediction by Aymin Javed, Nadeem Javaid, Nabil Alrajeh, Muhammad Aslam

“…To predict CVD, we constructed two models: Dense Belief Network (DB-Net) and Deep Vanilla Recurrent Network (DVR-Net). …”
Get full text

A skin disease classification model based on multi scale combined efficient channel attention module by Hui Liu, Yibo Dou, Kai Wang, Yunmin Zou, Gan Sen, Xiangtao Liu, Huling Li

“…Firstly, the model has improved the pyramid segmentation attention module to extract multi-scale features of the image entirely. Secondly, the reverse residual structure is used to replace the residual structure in the backbone network, and the attention module is integrated into the reverse residual structure to achieve better multi-scale feature extraction. …”
Get full text

Prediction of stress-strain behavior of rock materials under biaxial compression using a deep learning approach. by Changsheng Li, Xinsong Zhang

“…The LSTM-AE approach uses the LSTM network to construct both the encoder and decoder, where the encoder extracts features from the input data and the decoder generates the target sequence for prediction. …”
Get full text

Atmospheric Water Monitoring by Using Ground-Based GPS during Heavy Rains Produced by TPV and SWV by Guoping Li, Jia Deng

“…Results indicate that an increase in GPS precipitable water (GPS-PW) occurs prior to the development of the TPV and SWV; rainfall occurs mainly during high levels of GPS-PW. The evolution features of GPS-PW in rainfall process caused by different weather systems over the Tibetan Plateau (TP) also differ. …”
Get full text

Object-translocation induces event coding in the rat hippocampus by Ya-Li Duan, Shu-Yi Hu, Xiao-Fan Ge, Jia-Li Long, Chu Deng, Yu-Ming Sun, Cheng-Ji Li, Rong Zhang, Xing Cai, Li Lu

Get full text

Reveal your microbes, and i’ll reveal your origins: geographical traceability via Scomber colias intestinal tract metagenomics by Bernardo Duarte, Eduardo Feijão, Ana Cruz-Silva, Pedro Pascoal, Mónica Nunes, Marcelo Pereira, Andreia Figueiredo, Ricardo P. Dias, Susanne E. Tanner, Vanessa F. Fonseca

Get full text

Research on concrete structure damage detection based on piezoelectric sensing technology and morphological fractal method by Hanqing Zhong, Liwei Shuai, Dongmin Deng

“…Compared with the traditional wavelet packet transform method, the intelligent recognition model established by integrating fractal features and neural networks has a higher recognition accuracy rate for the degree of damage.…”
Get full text

Detection of Inverted Channels Using Sentinel-1 Data and Sentinel-2 Data on Google Earth Engine: A Comparative Analysis by Xuhua Weng

“…Accurate mapping of these features is crucial for understanding landscape evolution in arid regions. …”
Get full text