Generalization challenges in video deepfake detection: methods, obstacles, and technological advances by LI Junjie, WANG Jianzong, ZHANG Xulong, QU Xiaoyang

“…To address this issue, researchers have proposed various solutions, such as neural network architecture design, multi-task learning, new loss functions, data augmentation, innovative training procedures, and the integration of biometric recognition technologies. …”
Get full text

Differences in spatiotemporal dynamics for processing specific semantic categories: An EEG study by Trang Thi Le, Do Anh Quan Luong, Hyosung Joo, Dongseok Kim, Jihwan Woo

“…Despite recent advances in brain imaging techniques and data analysis algorithms, the mechanisms underlying human brain semantic representations remain a topic of debate, specifically whether this occurs through the activation of selectively separated cortical regions or via a network of distributed and overlapping regions. …”
Get full text

TOPS-speed complex-valued convolutional accelerator for feature extraction and inference by Yunping Bai, Yifu Xu, Shifan Chen, Xiaotian Zhu, Shuai Wang, Sirui Huang, Yuhang Song, Yixuan Zheng, Zhihui Liu, Sim Tan, Roberto Morandotti, Sai T. Chu, Brent E. Little, David J. Moss, Xingyuan Xu, Kun Xu

“…Abstract Complex-valued neural networks process both amplitude and phase information, in contrast to conventional artificial neural networks, achieving additive capabilities in recognizing phase-sensitive data inherent in wave-related phenomena. …”
Get full text

Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning Framework by Songxi Yang, Bo Peng, Tang Sui, Meiliu Wu, Qunying Huang

“…Building change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their damage severity. …”
Get full text

Correlations Between Morpho-structural Properties of the Brain and Cognitive and Motor Deficits in Individuals with Traumatic Brain Injury by Alaleh Alivar, Soha Saleh, Michael Glassen, Easter S. Suviseshamuthu, Vikram Shenoy Handiru, Didier Allexandre, Guang H. Yue

“…This study explores the relationship between neurobehavioral as well as physical function deficits and structural changes in brain white matter (WM) and gray matter (GM) in individuals with TBI by evaluating morphometric magnetic resonance imaging (MRI) and diffusion tensor imaging (DTI) data. …”
Get full text

Alzheimer’s Disease Prediction Using Fisher Mantis Optimization and Hybrid Deep Learning Models by Sameer Abbas, Mustafa Yeniad, Javad Rahebi

“…This study proposes a novel hybrid deep learning framework, GLCM + VGG16 + FMO + CNN-LSTM, to improve AD diagnosis using MRI data. <b>Methods</b>: MRI images were preprocessed through normalization and noise reduction. …”
Get full text

A novel deep learning approach to field-road semantic segmentation by Bei Wang, Wenze Wang

“…., turning and transporting) through the analysis of global navigation satellite system (GNSS) data. …”
Get full text

Revolutionizing sleep disorder diagnosis: A Multi-Task learning approach optimized with genetic and Q-Learning techniques by Soraya Khanmohmmadi, Toktam Khatibi, Golnaz Tajeddin, Elham Akhondzadeh, Amir Shojaee

“…The study proposes an innovative multi-task learning convolutional neural network with a partially shared structure that uses frequency-time images generated from EEG signals to address these limitations. …”
Get full text

Artificial Intelligence in Patch Testing: Comprehensive Review of Current Applications and Future Prospects in Dermatology by Hilary S Tang, Joseph Ebriani, Matthew J Yan, Shannon Wongvibulsin, Mehdi Farshchian

“…Most studies employed convolutional neural networks (CNN) for image analysis, with accuracy rates ranging from 90.1% to 99.5%. …”
Get full text

Heterogeneous energetic material damage simulator (HEDS): A deep learning approach to simulate damage–sensitivity linkages by Irene Fang, Shobhan Roy, Phong Nguyen, Stephen Baek, H. S. Udaykumar

Get full text

Real-Time Object Detection for Edge Computing-Based Agricultural Automation: A Case Study Comparing the YOLOX and YOLOv12 Architectures and Their Performance in Potato Harvesting S... by Joonam Kim, Giryeon Kim, Rena Yoshitoshi, Kenichi Tokuda

“…Although both models achieved an equivalent overall detection accuracy (F1-score, 0.97), YOLOv12 demonstrated specialized capabilities for challenging classes, achieving 42% higher recall for underrepresented soil clod objects (0.725 vs. 0.512, <i>p</i> < 0.01) and superior precision for small objects (0–3000 pixels). Architectural analysis identified a YOLOv12 residual efficient layer aggregation network backbone and area attention mechanism as key enablers of balanced precision–recall characteristics, which were particularly valuable for addressing agricultural data imbalance. …”
Get full text

PASeg: positional-guided segmenter with multimodal semantic alignment for enhancing urban scene 3D semantic segmentation by Yang Luo, Ting Han, Xiaorong Zhang, Yujun Liu, Duxin Zhu, Jinyuan Li, Yiping Chen, Yundong Wu, Guorong Cai, Yingchao Piao, Jinhe Su

Get full text

A Microscopic Experimental Study on the Dominant Flow Channels of Water Flooding in Ultra-High Water Cut Reservoirs by Chunlei Yu, Min Zhang, Wenbin Chen, Shiming Zhang, Shuoliang Wang

“…Through microscopic physical simulation of water flooding, color mixing recognition and image analysis technology were used to visualize the evolution characteristics of water flooding seepage channels and their changes during the control process. …”
Get full text

Monitoring Vegetation Dynamics in Desertification Restoration Areas of Wuzhumuqin Grassland Ecosystem by Fuguang Yang, Zhiguo Wang, Yongguang Zhai, Xiangli Yang, Tengfei Bao, Yonghui Wang

“…At the same time, a transform three-branch network structure based on deep learning is proposed to extract visual features. …”
Get full text

Disproportionate impact of the COVID-19 pandemic on socially vulnerable communities: the case of Jane and Finch in Toronto, Ontario by Zahra Movahedi Nia, Zahra Movahedi Nia, Zahra Movahedi Nia, Cheryl Prescod, Michelle Westin, Patricia Perkins, Patricia Perkins, Mary Goitom, Mary Goitom, Kesha Fevrier, Kesha Fevrier, Sylvia Bawa, Sylvia Bawa, Jude Dzevela Kong, Jude Dzevela Kong, Jude Dzevela Kong, Jude Dzevela Kong, Jude Dzevela Kong, Jude Dzevela Kong

Get full text

Multimodal Deep Learning Integrating Tumor Radiomics and Mediastinal Adiposity Improves Survival Prediction in Non‐Small Cell Lung Cancer: A Prognostic Modeling Study by Ye Niu, Han‐bing Xie, Hao‐bo Jia, Lin Zhao, Le Liu, Ping‐ping Liu, Xue‐meng Li, Rui‐tao Wang, Yuan‐zhou Li

“…Tumor radiomic features were extracted using a DenseNet121 convolutional neural network architecture, while mediastinal fat area (MFA) was quantified through semiautomated segmentation using ImageJ software. …”
Get full text

Deep learning radiomics nomogram predicts lymph node metastasis in laryngeal squamous cell carcinoma by Yun Liang, Yun Liang, Min He, Wenqing Chen, Wenqing Chen, Lizhen Li, Lizhen Li, Yumeng Dong, Yumeng Dong, Gang Liang, Hui Huangfu, Zengyu Jiang, Zengyu Jiang, Sheng He, Sheng He, Sheng He

“…Both conventional radiomics, involving data analysis of high-throughput quantitative features extracted from medical images, as well as deep learning networks, improved LNM diagnostic accuracy in LSCC, but the combination of both approaches has not been fully examined. …”
Get full text

DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization. by Sundreen Asad Kamal, Youtian Du, Majdi Khalid, Majed Farrash, Sahraoui Dhelim

“…This study proposes a novel approach to the identification of DR employing methods such as synthetic data generation, K- Means Clustering-Based Binary Grey Wolf Optimizer (KCBGWO), and Fully Convolutional Encoder-Decoder Networks (FCEDN). …”
Get full text

Forged Video Detection Using Deep Learning: A SLR by Maryam Munawar, Iram Noreen, Raed S. Alharthi, Nadeem Sarwar

“…In today’s digital landscape, video and image data have emerged as pivotal and widely adopted means of communication. …”
Get full text

Different radiomics models in predicting the malignant potential of small intestinal stromal tumors by Yuxin Xie, Chongfeng Duan, Xuzhe Zhou, Xiaoming Zhou, Qiulin Shao, Xin Wang, Shuai Zhang, Fang Liu, Zhenbo Sun, Ruirui Zhao, Gang Wang

“…The clinical data and CT performance were selected using univariate analysis and to construct clinical model. …”
Get full text