Generic speech enhancement with self-supervised representation space loss by Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takafumi Moriya, Takanori Ashihara, Ryo Masumura

“…To this end, we propose a novel training criterion that minimizes the distance between the enhanced and the ground truth clean signal in the feature representation domain of self-supervised learning models. …”
Get full text

Convolution of the physical point cloud for predicting the self-assembly of colloidal particles by Seunghoon Kang, Young Jin Lee, Kyung Hyun Ahn

“…In the field of pattern recognition, GCNs are widely utilized to classify arbitrary 3D objects by learning multidimensional relationships within feature spaces defined by spatial coordinates. In contrast, our study constructs a feature space based on the micromechanical stresses imparted on colloidal particles during their self-assembly, rather than relying on spatial information. …”
Get full text

Methodology for Object-Level Change Detection in Post-Earthquake Building Damage Assessment Based on Remote Sensing Images: OCD-BDA by Zhengtao Xie, Zifan Zhou, Xinhao He, Yuguang Fu, Jiancheng Gu, Jiandong Zhang

“…In this context, the accuracy of employing various AI models in pixel-level change detection methods is significantly dependent on the consistency between pre- and post-disaster building images, particularly regarding variations in resolution, viewing angle, and lighting conditions; in object-level feature recognition methods, the low richness of semantic details of damaged buildings in images leads to a poor detection accuracy. …”
Get full text

A Methodological and Structural Review of Parkinson’s Disease Detection Across Diverse Data Modalities by Abu Saleh Musa Miah, Taro Suzuki, Jungpil Shin

“…Based on over 342 articles from leading scientific databases, this review examines key aspects such as data collection methods, settings, feature representations, and system performance, with a focus on recognition accuracy and robustness. …”
Get full text

FSID: a novel approach to human activity recognition using few-shot weight imprinting by Mohammad Belal, Taimur Hassan, Abdelfatah Hassan, Divya Velayudhan, Noureldin Elhendawi, Ahmad Aljarah, Irfan Hussain

“…These spectrograms are then passed to a pre-trained DINO model, which is used as a feature extractor due to its ability to learn global, transferable representations without requiring manual labels. …”
Get full text

Research on Reasoning concerning Emergency Measures for Industrial Project Scheduling Control by Xiaokang Han, Wenzhou Yan, Mei Lu

“…In this paper, the rough set approach is used to represent the case feature information in a case reasoning model for industrial project scheduling control, attribute reduction is used to determine the weights of the feature attributes in the rough set representation, and the similarity between cases is calculated for case retrieval. …”
Get full text

Peer Effects in Corporate Disclosure Decisions Mohammad Hossein Safarzadeh*: Associate professor of Accounting, Faculty of Management and Accounting, Shahid Beheshti University, Te... by Mohammad Hossein Safarzadeh, Hamideh Asnaashari, Alireza Panahalipour

“…Regarding the moderating role of reliance on external financing in the relationship between peer disclosure and corporate disclosure, the results showed that this factor does not have a significant effect on this relationship. Therefore, this feature does not have a significant impact on the effect of peers on corporate disclosure.IntroductionThe disclosure of information is considered one of the most important aspects of corporate performance and decision-making. …”
Get full text

Utilizing Machine Learning and Multi-Station Observations to Investigate the Visibility of Sea Fog in the Beibu Gulf by Qin Huang, Peng Zeng, Xiaowei Guo, Jingjing Lyu

“…However, the performance of these models varies by station, suggesting that additional feature variables, such as geographical or topographical variables, may be needed for training the models and improving their accuracy.…”
Get full text

Parallel boosting neural network with mutual information for day-ahead solar irradiance forecasting by Ubaid Ahmed, Anzar Mahmood, Ahsan Raza Khan, Levin Kuhlmann, Khurram Saleem Alimgeer, Sohail Razzaq, Imran Aziz, Amin Hammad

“…Traditional deep learning (DL) models and decision tree (DT)-based algorithms have been widely employed for this purpose. …”
Get full text

Development and Training Strategy of Badminton Action Recognition System Under the Background of Artificial Intelligence by Hongjun Ma, Fan Zhang, Ni Liang

“…In the experimental section, the performance of three mainstream models—Spatial-Temporal Graph Convolutional Network (ST-GCN), Vision-Attention Transformer for Real-time Motion Recognition (VATRM), and Multi-Modal Network for Sports Action Recognition (MM-Net)—is compared from two dimensions: recognition performance and computational efficiency. …”
Get full text

An improved multiscale fusion dense network with efficient multiscale attention mechanism for apple leaf disease identification by Hui LIU, Dandan DAI

“…Second, this work used three attention mechanisms, and the efficient multiscale attention mechanism obtained the best performance. Third, the convolution layers and bottlenecks were modified without performance degradation, reducing half of the computational load compared with the original models. …”
Get full text

Development of a Path Tracker Based on a 4WS Vehicle for Low-Speed Automated Driving Systems by Heung-Sik Park, Moon-Sik Kim

“…The performance of the proposed path tracker was evaluated through simulations and real-car experiments.…”
Get full text

Transformers for Neuroimage Segmentation: Scoping Review by Maya Iratni, Amira Abdullah, Mariam Aldhaheri, Omar Elharrouss, Alaa Abd-alrazaq, Zahiriddin Rustamov, Nazar Zaki, Rafat Damseh

“…Studies generally reported increased segmentation accuracy and the ability to model both local and global features in brain images. …”
Get full text

Micro-electrical Discharge Machining of Micro-holes Based on Integrated Orthogonal Experiments and CNN Methods by Yuandong MO, Yazhi WANG, Shuqi HUANG, Jiajun ZHONG

“…All the predicted values have relative errors below 12%, affirming a resilient fit of the PyTorch-based CNN and demonstrating exceptional predictive performance. The model’s applicability extends impressively, showcasing the capability to utilize orthogonal-experiment data for predicting any parameter combination, thereby effectively meeting practical production and machining requirements. …”
Get full text

Exhaled volatile organic compounds as novel biomarkers for early detection of COPD, asthma, and PRISm: a cross-sectional study by Jiaxin Tian, Qiurui Zhang, Minhua Peng, Leixin Guo, Qianqian Zhao, Wei Lin, Sitong Chen, Xuefei Liu, Simin Xie, Wenxin Wu, Yijie Li, Junqi Wang, Jin Cao, Ping Wang, Min Zhou

“…The sensitivity, specificity, and accuracy of these models were calculated to assess their overall discriminatory performance. …”
Get full text

SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor Networks by Xianwei Gao, Xiang Yao, Bi Chen, Honghao Zhang

“…Traditional CS methods have limited performance, so many deep learning-based CS models have been proposed. …”
Get full text

MSMCE: A novel representation module for classification of raw mass spectrometry data. by Fengyi Zhang, Boyong Gao, Yinchu Wang, Lin Guo, Wei Zhang, Xingchuang Xiong

“…Additionally, we implement a feature fusion mechanism by concatenating the initial encoded representation with the multi-channel embeddings along the channel dimension, significantly enhancing the classification performance of subsequent models. …”
Get full text

cigChannel: a large-scale 3D seismic dataset with labeled paleochannels for advancing deep learning in seismic interpretation by G. Wang, G. Wang, G. Wang, X. Wu, X. Wu, X. Wu, W. Zhang, W. Zhang, W. Zhang

“…Manual labeling of paleochannels in 3D seismic volumes is tedious and subjective, potentially leading to mislabeling that degrades deep learning model's performance. To address this, we propose a workflow to generate a synthetic seismic dataset, <i>cigChannel</i>, consisting of 1600 seismic volumes with over 10 000 labeled paleochannels. …”
Get full text

A Novel Hypersonic Target Trajectory Estimation Method Based on Long Short-Term Memory and a Multi-Head Attention Mechanism by Yue Xu, Quan Pan, Zengfu Wang, Baoquan Hu

“…In model training, information redundancy is reduced, and information validity is improved through feature selection and data preprocessing. …”
Get full text

Fatigue trajectories by wearable remote monitoring of breast cancer patients during radiotherapy by Angela Barillaro, Chiara Feoli, Adriano Tramontano, Marco Comerci, Mara Caroprese, Renato Cuocolo, Oscar Tamburis, Mario Petrazzuoli, Maria Anna D’Arienzo, Antonio Farella, Caterina Oliviero, Stefania Clemente, Laura Cella, Mario Magliulo, Manuel Conson, Roberto Pacelli

“…The best-performing classifier was the Bagged Trees model, showing a cross-validated ROC-AUC of 89% (95% CI 88–90%). …”
Get full text