Dual-hybrid intrusion detection system to detect False Data Injection in smart grids. by Saad Hammood Mohammed, Mandeep S Jit Singh, Abdulmajeed Al-Jumaily, Mohammad Tariqul Islam, Md Shabiul Islam, Abdulmajeed M Alenezi, Mohamed S Soliman

“…Additionally, the IDS employs a hybrid deep learning classifier that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to capture the smart grid data's spatial and temporal features. …”
Get full text

Research on Oil Well Production Prediction Based on GRU-KAN Model Optimized by PSO by Bo Qiu, Jian Zhang, Yun Yang, Guangyuan Qin, Zhongyi Zhou, Cunrui Ying

“…To overcome the shortcomings in the current study of oil well production prediction, we propose a hybrid model (GRU-KAN) with the gated recurrent unit (GRU) and Kolmogorov–Arnold network (KAN). The GRU-KAN model utilizes GRU to extract temporal features and KAN to capture complex nonlinear relationships. …”
Get full text

Sound-Based Unsupervised Fault Diagnosis of Industrial Equipment Considering Environmental Noise by Jeong-Geun Lee, Kwang Sik Kim, Jang Hyun Lee

“…To achieve this, statistical features of Mel frequency cepstral coefficients were extracted, generating features applicable regardless of signal length. …”
Get full text

An enhanced method of CNNs by incorporating the clustering-guided block for concrete crack recognition by Hui Li, Chenyu Liu, Ning Zhang, Wei Shi

“…This paper introduces a novel Crack Segmentation method known as CG-CNNs, which combines a Clustering-guided (CG) block with a Convolutional Neural Network (CNN). The innovative CG block operates by categorizing extracted image features into K groups, merging these features, and then simultaneously feeding the augmented features and original image into the CNN for precise crack image segmentation. …”
Get full text

Two-dimensional spatial orientation relation recognition between image objects by Gong Peiyong, Zheng Kai, Jiang Yi, Zhao Huixuan, Huai Honghao, Guan Ruijie

“…TSOVF algorithm introduces the learnable spatial orientation vector field to effectively encode the spatial orientation relation into a deep convolutional neural network model. The proposed architecture features a dual-branch design: the T-branch identifies object central points and classifies categories via keypoint estimation, while the S-branch constructs a pixel-level spatial orientation vector field. …”
Get full text

Low-hit frequency-hopping communication systems for power Internet of things random access by Shu DU, Mei MA, Bo ZHAO, Qi ZENG, Xing LIU

“…The communication network is an essential component of the data acquisition and information transmission in power Internet of things (IoT).To meet the development requirements of multiple power service in the future, the wireless communication technique with flexible-access and high scalability is one of the development directions for power IoT.Due to the features of large-scale access, random access time, high security and reliability for information transmission of power IoT, a frequency-hopping (FH) technique with low-hit rate for random access was proposed.The construction algorithm of such FH pattern was based upon the combination and shift operation of conventional FH sequences.By the theoretical arithmetic and numerical simulation, the properties of the proposed FH pattern and the error-rate of the FH-based power IoT were evaluated.The analysis reveals that the new class of FH sequences and the system can meet the requirements of large-scale access and highly reliable communication for the power IoT, which has good application prospects.…”
Get full text

Leveraging BiLSTM-CRF and adversarial training for sentiment analysis in nature-based digital interventions: Enhancing mental well-being through MOOC platforms by Juanjuan Zang

“…This ensures high-quality feature extraction, precise label assignment, and the derivation of evaluation metrics. …”
Get full text

Enhanced stroke risk prediction in hypertensive patients through deep learning integration of imaging and clinical data by Hui Li, Tianyu Zhang, Guochao Han, Zonghui Huang, Huiyu Xiao, Yunzhe Ni, Bo Liu, Wennan Lin, Yuan Lin

“…ResNet50 was employed to automatically segment the carotid intima-media and extract key structural features. These imaging features, along with clinical variables such as age, blood pressure, and smoking history, were fused using a Vision Transformer (ViT) and fed into a Radial Basis Probabilistic Neural Network (RBPNN) for risk stratification. …”
Get full text

RBFT: Resilience-Oriented Blockchain Consensus Protocol by Oumaima Fadi, Karim Zkik, Adil Bahaj, Abdellatif El Ghazi, Mohammed Boulmalf

“…However, before adopting these protocols in real-world applications, it is crucial to evaluate their specific features and how they influence the resilience of blockchain. …”
Get full text

DeepContainer: A Deep Learning-based Framework for Real-time Anomaly Detection in Cloud-Native Container Environments by Ke Xiong, Zhonghao Wu,  Xuzhong Jia

“…The proposed framework addresses critical security challenges in containerized infrastructures through an innovative integration of neural network architectures and automated response mechanisms. …”
Get full text

Fact-Checking 5G Security: Bridging the Gap Between Expectations and Reality by Oscar Lasierra, Norbert Ludant, Gines Garcia-Aviles, Esteban Municio, Guevara Noubir, Antonio Skarmeta, Xavier Costa-Perez

“…In this work, we evaluate the security of currently deployed 5G commercial networks in Europe and North America. …”
Get full text

Efficient Side-Tuning for Remote Sensing: A Low-Memory Fine-Tuning Framework by Haichen Yu, Wenxin Yin, Hanbo Bi, Chongyang Li, Yingchao Feng, Wenhui Diao, Xian Sun

“…The proposed EST Block is the main component of the parallel network, which uses the multichannel adapter fusion module, gate layer and depthwise convolution to achieve feature selection and enhancement effects. …”
Get full text

VirtualPainting: Addressing Sparsity with Virtual Points and Distance-Aware Data Augmentation for 3D Object Detection by Sudip Dhakal, Deyuan Qu, Dominic Carrillo, Mohammad Dehghani Tezerjani, Qing Yang

“…In recent times, there has been a notable surge in multimodal approaches that decorate raw LiDAR point clouds with camera-derived features to improve object detection performance. However, we found that these methods still grapple with the inherent sparsity of LiDAR point cloud data, primarily because fewer points are enriched with camera-derived features for sparsely distributed objects. …”
Get full text

A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity by Ryan L'Abbate, Anthony D'Onofrio, Samuel Stein, Samuel Yen-Chi Chen, Ang Li, Pin-Yu Chen, Juntao Chen, Ying Mao

“…On the quantum side, we propose a quantum-state-fidelity-based evaluation function to iteratively train the network through a feedback loop between the two sides. co-TenQu has been implemented and evaluated with both simulators and the IBM-Q platform. …”
Get full text

High-throughput behavioral screening in Caenorhabditis elegans using machine learning for drug repurposing by Antonio García-Garví, Antonio-José Sánchez-Salmerón

“…In this study, we propose a high-throughput screening method based on machine learning, using classifiers that provide a recovery percentage as a measure of treatment effect. We evaluate two main approaches: traditional machine learning models based on behavioral features extracted from the worm’s skeleton using Tierpsy Tracker, and deep neural networks that directly analyse video sequences. …”
Get full text

Cross-Domain Facial Expression Recognition Based on Transductive Deep Transfer Learning by Keyu Yan, Wenming Zheng, Tong Zhang, Yuan Zong, Chuangao Tang, Cheng Lu, Zhen Cui

“…In this paper, we proposed a novel end-to-end transductive deep transfer learning network (TDTLN) to deal with the challenging cross-domain expression recognition problem, in which both the source and target databases are utilized to jointly learn optimal nonlinear discriminative features so as to improve the label prediction performance of the target data samples. …”
Get full text

CrackNet: A Hybrid Model for Crack Segmentation with Dynamic Loss Function by Yawen Fan, Zhengkai Hu, Qinxin Li, Yang Sun, Jianxin Chen, Quan Zhou

“…CrackNet is trained and evaluated on three public crack datasets, and experimental results show that the proposed model outperforms several well-known deep neural networks, with a particularly noticeable improvement in recall rate.…”
Get full text

UNet-Based End-to-End Anomaly Detection With Computational Hyperspectral Imaging by Weiming Shi, Junren Wen, Yipeng Chen, Yu Shao, Haiqi Gao, Xuehui Wang, Chenying Yang

“…This system employs a UNet-based end-to-end neural network that can adapt to various scene complexities without the need for retraining and further fine-tuning, specifically designed to extract features from the ELI with computational hyperspectral imaging. …”
Get full text

Deep Neural Framework With Visual Attention and Global Context for Predicting Image Aesthetics by Yifei Xu, Nuo Zhang, Pingping Wei, Genan Sang, Li Li, Feng Yuan

“…In this paper, we propose a deep neural framework with visual attention module, self-generated global features and hybrid loss to address this problem. Specifically, the framework can be any state-of-the-art convolution classification network compatible with visual attention. …”
Get full text

Efficient human activity recognition on edge devices using DeepConv LSTM architectures by Haotian Zhou, Xiujun Zhang, Yu Feng, Tongda Zhang, Lijuan Xiong

“…This study aims to deploy lightweight deep learning models for human activity recognition (HAR) using TinyML on edge devices. We designed and evaluated three models: a 2D Convolutional Neural Network (2D CNN), a 1D Convolutional Neural Network (1D CNN), and a DeepConv LSTM. …”
Get full text