Spectroscopic measurement of near-infrared soil pH parameters based on GhostNet-CBAM. by Jianguo Zhu, Wenjin Wang, Peng Tian

“…The method firstly utilizes Monte Carlo Cross Validation (MCCV) method to reject the anomalous samples in the data, and then uses GhostNet combined with CBAM algorithm to train and predict the PH values of the four Lucas soil spectral data measured by the two different methods, and compares the prediction results with those of PLSR and VGGNet-16 methods. …”
Get full text

Deep Learning-Based Video Anomaly Detection Using Optimised Attention-Enhanced Autoencoders by Anjali S, Don S

“…Our adaptive thresholding technique leverages reconstruction cost, peak signal-to-noise ratio (PSNR) and frame brightness for optimal threshold identification, enhancing adaptability to different scenarios. Comparing with dynamic threshold methods, we assess our model using ROC and AUC metrics. …”
Get full text

Modulation Format Identification Method Based on Multi-Feature Input Hybrid Neural Network by Zhiqi Huang, Xiangjun Xin, Qi Zhang, Haipeng Yao, Feng Tian, Fu Wang

“…The method enhances MFI accuracy by leveraging features of different modulation formats and representations at different neural network levels. …”
Get full text

Anomaly-Based Intrusion Detection System for the Internet of Medical Things by Eichie Franklin, Bernardi Pranggono

“…However, there was no single best model in classifying all attack labels, as each model performed differently in terms of different metrics.…”
Get full text

Enhanced prediction of hemolytic activity in antimicrobial peptides using deep learning-based sequence analysis by Ibrahim Abdelbaky, Mohamed Elhakeem, Hilal Tayara, Elsayed Badr, Mustafa Abdul Salam

“…Peptide sequences are represented using one-hot encoding, and the CNN architecture consists of multiple convolutional and fully connected layers. The model was trained on six different datasets: HemoPI-1, HemoPI-2, HemoPI-3, RNN-Hem, Hlppredfuse, and AMP-Combined, achieving Matthew’s correlation coefficients of 0.9274, 0.5614, 0.6051, 0.6142, 0.8799, and 0.7484, respectively. …”
Get full text

Multibranch 3D-Dense Attention Network for Hyperspectral Image Classification by Junru Yin, Changsheng Qi, Wei Huang, Qiqiang Chen, Jiantao Qu

“…This network is able to reuse features to fully exploit the shallow spatial-spectral information of HSI. Meanwhile, the convolutional kernels of different sizes are used to extract multi-scale spatial-spectral features. …”
Get full text

L2-GNN: Graph neural networks with fast spectral filters using twice linear parameterization by Siying Huang, Xin Yang, Zhengda Lu, Hongxing Qin, Huaiwen Zhang, Yiqun Wang

“…To improve learning on irregular 3D shapes, such as meshes with varying discretizations and point clouds with different samplings, we propose L2-GNN, a new graph neural network that approximates the spectral filters using twice linear parameterization. …”
Get full text

Novel feature extraction method for signal analysis based on independent component analysis and wavelet transform. by Mariusz Topolski, Jędrzej Kozal

“…Several base wavelet functions with different classifiers were used in experiments. Best was selected with 5-fold cross-validation and Wilcoxon test with significance level 0.05. …”
Get full text

COSMIC-2 RFI Prediction Model Based on CNN-BiLSTM-Attention for Interference Detection and Location by Cheng-Long Song, Rui-Min Jin, Chao Han, Dan-Dan Wang, Ya-Ping Guo, Xiang Cui, Xiao-Ni Wang, Pei-Rui Bai, Wei-Min Zhen

“…Research shows that the SNR in different GNSS signal channels shows a correlated change under the influence of RFI. …”
Get full text

Development of a deep learning model for automated detection of calcium pyrophosphate deposition in hand radiographs by Thomas Hügle, Elisabeth Rosoux, Guillaume Fahrni, Deborah Markham, Tobias Manigold, Fabio Becce

“…CPPD presence was then predicted using a convolutional neural network. We tested seven CPPD models, each with a different combination of sites out of TFCC, MCP-2 and MCP-3. …”
Get full text

A Deep Learning Framework for Using Search Engine Data to Predict Influenza-Like Illness and Distinguish Epidemic and Nonepidemic Seasons: Multifeature Time Series Analysis by Ji Li, Xiangyu Yan, Xingjie Chu, Ying Zhang, Guoliang Liu, Lin Li, Yue Li, Xiaochun Dong, Zihan Mei, Zhengkun Liu, Jinyue Yuan, Xiaohan Sun, Chunxia Cao

“…ObjectiveThe aim of this study was to propose a deep learning framework for different influenza epidemic states based on Baidu index and percentage of influenza-like illness (ILI%). …”
Get full text

A Sensor Data Prediction and Early-Warning Method for Coal Mining Faces Based on the MTGNN-Bayesian-IF-DBSCAN Algorithm by Mingyang Liu, Xiaodong Wang, Wei Qiao, Hongbo Shang, Zhenguo Yan, Zhixin Qin

“…Multidimensional analysis diagrams (e.g., residual distribution, 45° diagonal error plot, and boxplots) further validate the model’s robustness in different spatial locations, particularly in capturing abrupt changes and low-concentration anomalies. …”
Get full text

DASNet a dual branch multi level attention sheep counting network by Yini Chen, Ronghua Gao, Qifeng Li, Hongtao Zhao, Rong Wang, Luyu Ding, Xuwen Li

“…The varying flight altitudes, diverse scenes, and different density levels captured by the drones endow our dataset with a high degree of diversity. …”
Get full text

The Role of ChatGPT in Dermatology Diagnostics by Ziad Khamaysi, Mahdi Awwad, Badea Jiryis, Naji Bathish, Jonathan Shapiro

“…Artificial intelligence (AI), especially large language models (LLMs) like ChatGPT, has disrupted different medical disciplines, including dermatology. …”
Get full text

Adjusting U-Net for the aortic abdominal aneurysm CT segmentation case by R.U. Epifanov, N.A. Nikitin, A.A. Rabtsun, L.N. Kurdyukov, A.A. Karpenko, R.I. Mullyadzhanov

“…As a result of our study, macro dice score for classes of interest reaches 83.12% ± 4.27%. We explored different augmentation styles and showed the importance of applying intensity augmentation style to improve segmentation algorithm robustness in conditions of clinical data diversity. …”
Get full text

HyperspectralMamba: A Novel State Space Model Architecture for Hyperspectral Image Classification by Jianshang Liao, Liguo Wang

“…The method addresses limitations in existing techniques through three key innovations: (1) a novel dual-stream architecture that combines SSM global modeling with parallel convolutional local feature extraction, distinguishing our approach from existing single-stream SSM methods; (2) a band-adaptive feature recalibration mechanism specifically designed for hyperspectral data that adaptively adjusts the importance of different spectral band features; and (3) an effective feature fusion strategy that integrates global and local features through residual connections. …”
Get full text

Fault Diagnosis for Bearing Based on 1DCNN and LSTM by Haibin Sun, Shichao Zhao

“…The results show that the proposed classifier with good generalization performance not only diagnoses the category of fault quickly and accurately under different load conditions but also achieves an average fault identification accuracy of 99.95%. …”
Get full text

Quality enhancement of VVC intra-frame coding for multimedia services over the Internet by Seunghyun Cho, Dong-Wook Kim, Seung-Won Jung

“…In this article, versatile video coding, the next-generation video coding standard, is combined with a deep convolutional neural network to achieve state-of-the-art image compression efficiency. …”
Get full text

Vibration-Based Anomaly Detection in Industrial Machines: A Comparison of Autoencoders and Latent Spaces by Luca Radicioni, Francesco Morgan Bono, Simone Cinquemani

“…The methodology involves training CAEs and VAEs on data from machinery in healthy condition and testing them on new data samples representing different levels of system degradation. The results indicate that models with spatial latent spaces outperform those with dense latent spaces in terms of reconstruction accuracy and AD capabilities. …”
Get full text

Analysis of the Urban Development Technologies of Ukek using Neural Networks (preliminary research results) by Singatulin Rustam A.

“…Complex patterns and associations between archaeological, historical, and geological data from different years were identified. The software tools included convolutional neural networks for image analysis, recurrent neural networks for time sequence analysis, and deep neural networks for complex classification, modeling, and verification tasks. …”
Get full text