Legal Perspectives for Explainable Artificial Intelligence in Medicine - Quo Vadis? by Cătălin-Mihai PESECAN, Lăcrămioara STOICU-TIVADAR

“…Grad-CAM will generate heatmaps based on the gradient from the last layer (because it contains the most information) of a convolutional neural network. …”
Get full text

DANC-Net: Dual-Attention and Negative Constraint Network for Point Cloud Classification by Hang Sun, Yuanyue Zhang, Jinmei Shi, Shuifa Sun, Guanqun Sheng, Yirong Wu

“…Convolutional neural networks, as a branch of deep neural networks, have been widely used in multidimensional signal processing, especially in point cloud signal processing. …”
Get full text

A deep learning framework for gender sensitive speech emotion recognition based on MFCC feature selection and SHAP analysis by Qingqing Hu, Yiran Peng, Zhong Zheng

“…Abstract Speech is one of the most efficient methods of communication among humans, inspiring advancements in machine speech processing under Natural Language Processing (NLP). …”
Get full text

Multi-physiological signal fusion for objective emotion recognition in educational human–computer interaction by Wanmeng Wu, Enling Zuo, Weiya Zhang, Xiangjie Meng

“…Feature extraction was performed using time-domain and time-frequency domain analysis methods, followed by feature selection to eliminate redundant features. A convolutional neural network (CNN) with attention mechanisms was employed as the decision-making model.ResultsThe proposed system demonstrated superior accuracy in recognizing emotional states than existing methods. …”
Get full text

Deep Learning-Based Navigation System for Automatic Landing Approach of Fixed-Wing UAVs in GNSS-Denied Environments by Ying-Xi Lin, Ying-Chih Lai

“…This study addresses these problems by combining runway detection and localization methods, YOLOv8 and CNN (convolutional neural network) regression, to demonstrate the robustness of deep learning approaches. …”
Get full text

Machine learning-enabled multiscale modeling platform for damage sensing digital twin in piezoelectric composite structures by Somnath Ghosh, Saikat Dan, Preetam Tarafder

“…Abstract Nondestructive evaluation (NDE) of aerospace structures plays a crucial role in their successful operation under harsh environments. Most NDE methods, however, lack real-time in-situ predictive capabilities of evolving damage and are conducted in a post-mortem manner. …”
Get full text

THE APPLICATION OF ARTIFICIAL INTELLIGENCE IN WHITE BLOOD CELL CLASSIFICATION BASED ON MICROSCOPIC IMAGES: A SCOPING REVIEW by Annisa Nur Hasanah, Oktafirani Al Sas, Yosua Darmadi Kosen

“…Findings indicate that the most commonly used method is Convolutional Neural Network (CNN), either standalone or hybrid (e.g., YOLOv5, ResNet, Vision Transformer), achieving accuracies up to 99.7%. …”
Get full text

<italic>DynaTrack</italic>: Low-Power Channel-Aware Dynamic Smartphone Tracking Using UWB DL-TDOA by Junyoung Choi, Sagnik Bhattacharya, Joohyun Lee

“…Among the various Ultra-wideband (UWB) ranging methods, the absence of uplink communication or centralized computation makes downlink time-difference-of-arrival (DL-TDOA) localization the most suitable for large-scale industrial deployments. …”
Get full text

Deep learning in time series forecasting with transformer models and RNNs by Rogerio Pereira dos Santos, João P. Matos-Carvalho, Valderi R. Q. Leithardt

“…In contrast, RNN models such as auto-temporal convolutional networks (TCN) and bidirectional TCN (BiTCN) were better suited to short-term forecasting, despite being more prone to significant errors. …”
Get full text

Dual-branch attention network-based stereoscopicvideo compression by TANG Shu, ZHAO Yu, YANG Shuli, XIE Xian-Zhong

“…Compared to traditional stereoscopic video (dual-view) compression methods, deep learning-based stereoscopic video compression coding methods achieve superior rate-distortion performance and have become a popular research focus in recent years. However, most existing deep learning-based stereoscopic video compression networks only use convolutional operations to extract and fuse features, which limits their ability to effectively capture non-repetitive texture details within local areas and cannot capture global features, thus affects the quality of image reconstruction during decoding seriously. …”
Get full text

Globally scalable glacier mapping by deep learning matches expert delineation accuracy by Konstantin A. Maslov, Claudio Persello, Thomas Schellenberger, Alfred Stein

“…Here we address this gap and propose Glacier-VisionTransformer-U-Net (GlaViTU), a convolutional-transformer deep learning model, and five strategies for multitemporal global-scale glacier mapping using open satellite imagery. …”
Get full text

Enhancing Brain Tumor Detection on MRI Images Using an Innovative VGG-19 Model-Based Approach by Burhan Ergen, Abdullah Şener

“…In a conducted study, a new model was developed by utilizing the VGG-19 architecture, a popular convolutional neural network model, to achieve high accuracy in brain tumor detection. …”
Get full text

An Intrusion Detection System over the IoT Data Streams Using eXplainable Artificial Intelligence (XAI) by Adel Alabbadi, Fuad Bajaber

“…Three different DL models, i.e., customized 1-D convolutional neural networks (1-D CNNs), deep neural networks (DNNs), and pre-trained model TabNet, are proposed. …”
Get full text

Screen shooting resistant watermarking based on cross attention by Lianshan Liu, Peng Xu, Qianwen Xue

“…In order to identify the origin of information violations, Screen-Shooting Resistant Watermarking (SSRW) has attracted a lot of attention. Most existing solutions are based on Convolutional Neural Networks (CNNs) for the embedding of watermarks. …”
Get full text

Flexible integration of spatial and expression information for precise spot embedding via ZINB-based graph-enhanced autoencoder by Jiacheng Leng, Jiating Yu, Ling-Yun Wu, Hongyang Chen

“…To address these issues, we introduce Spot2vector, a computational framework that leverages a graph-enhanced autoencoder integrating zero-inflated negative binomial distribution modeling, combining both graph convolutional networks and graph attention networks to extract the latent embeddings of spots. …”
Get full text

Towards Explainable Graph Embeddings for Gait Assessment Using Per-Cluster Dimensional Weighting by Chris Lochhead, Robert B. Fisher

“…To address this applicational barrier, an end-to-end pipeline is introduced here for creating graph feature embeddings, generated using a bespoke Spatio-temporal Graph Convolutional Network and per-joint Principal Component Analysis. …”
Get full text

GLClick: Interactive Segmentation Combining Global and Local Features by Jiaying Tang, Hongyuan Wang, Zongyuan Ding, Zihao Xin

“…Convolutional neural networks (CNNs) are the backbone of most modern interactive segmentation algorithms. …”
Get full text

Spatiotemporal evaluation of irrigation groundwater quality in Hungarian agricultural sites using hydrochemical and machine learning approaches by Musaab A. A. Mohammed, Norbert P. Szabó, Viktória Mikita, Péter Szűcs

“…HCA indicated low to moderate mineralization in most samples, while SOMs revealed notable spatial and temporal shifts, including gradual degradation due to natural and anthropogenic factors. …”
Get full text

Multiscale Mask R-CNN–Based Lung Tumor Detection Using PET Imaging by Rui Zhang PhD, Chao Cheng PhD, Xuehua Zhao PhD, Xuechen Li PhD

“…Positron emission tomography (PET) imaging serves as one of the most competent methods for the diagnosis of various malignancies, such as lung tumor. …”
Get full text

High-Precision Qiantang River Water Body Recognition Based on Remote Sensing Image by Hongcui Wang, Yihong Zheng, Ouxiang Chen

“…., are applied, Currently there are few works on the water body identification of Qiantang River, Here, one major challenge for high-precision Qiantang water body recognition is the real complex water body features and complicated geological environment, They are the dense distribution of small water bodies in the Qiantang River Basin, large differences in water body nutrition, and the high complexity of surface environments such as mountains and plains, We investigated two traditional and several deep learning methods and found that WatNet was the most effective model for Qiantang River, This model adopts the structure based on encoder-decoder convolutional network, It uses MobileNetV2 as the encoder, which makes it extract more water feature information while being lightweight and uses ASPP module to capture global multi-scale features in deep layers, Experimental results show that the MIoU and OA (Overall Accuracy) can reach 0. 97 and 0. 99 respectively.…”
Get full text