Connected Vehicles Security: A Lightweight Machine Learning Model to Detect VANET Attacks by Muawia A. Elsadig, Abdelrahman Altigani, Yasir Mohamed, Abdul Hakim Mohamed, Akbar Kannan, Mohamed Bashir, Mousab A. E. Adiel

“…In other words, two layers of enhancements were applied—using a suitable feature selection technique and fixing the dataset imbalance problem. …”
Get full text

UAVAI-YOLO: dense small target detection algorithm based on UAV aerial images by HE Zhiqian, CAO Lijie

“…An improved UAVAI-YOLO model was proposed to address the problem of poor target detection in UAV aerial images. …”
Get full text

SAR ship target detection method based on CNN structure with wavelet and attention mechanism. by Shiqi Huang, Xuewen Pu, Xinke Zhan, Yucheng Zhang, Ziqi Dong, Jianshe Huang

“…Ship target detection in synthetic aperture radar (SAR) images is an important application field. …”
Get full text

Research on Target Detection Algorithm for Solder Joint Defects Based on the Improved YOLOv8 by Chengkai Zhang, Xiaocui Feng, Pujun Mao, Fuyan Lv

“…Aiming at the problem of low accuracy in solder joint defect detection caused by the complex background and difficult to extract defect features of circuit boards using through-hole technology (THT), an improved YOLOv8 solder joint defect target detection algorithm was proposed. …”
Get full text

Passive indoor human daily behavior detection method based on channel state information by Xiaochao DANG, Yaning HUANG, Zhanjun HAO, Xiong SI

“…The daily behavior detection of indoor human based on CSI is developing rapidly in the field of WSN.At present,most of the research is still in the environment of 2.4 GHz,so the detection rate,robustness and overall performance still need to be improved.In order to solve this problem,a passive indoor human behavior detection method HDFi (Human Detection with Wi-Fi) based on CSI signal was proposed.The method was used to detect the indoor human daily behavior in a 5 GHz band environment,which was divided into three steps:data acquisition,data processing,feature extraction,online detection.Firstly,the experiment collected typical daily behavioral data in complex laboratory and relatively empty meeting room.Secondly,the amplitude and phase data with more obvious features were extracted and processed by low-pass filtering to obtain a set of stable and noise-free data,and then the fingerprint database was established effectively.Finally,in the real-time detection stage,the collected data features were classified by SVM algorithm to extract more stable eigenvalues,and a classification model of indoor human daily behavior detection was established,and then matched the data in the fingerprint database.The experimental results show that the proposed method has the characteristics of high efficiency,high precision and good robustness,and the method does not need any testing personnel to carry any electronic equipment,so it has high practicability.…”
Get full text

DAKBNet: Multiscale Fusion With Dynamic Assembly Kernels and Bilateral Feature Enhancement for Land Use Classification of Remote Sensing Images by Chenke Yue, Yin Zhang, Junhua Yan, Zhaolong Luo, Yong Liu, Pengyu Guo

Get full text

Self-attention-based graph transformation learning for anomaly detection in multivariate time series by Qiushi Wang, Yueming Zhu, Zhicheng Sun, Dong Li, Yunbin Ma

“…In this paper, we propose a self-attention based graph transformation learning (AT-GTL) method to solve this problem. AT-GTL uses a global self-attention graph pooling (GATP) module to aggregate all node features to obtain global features. …”
Get full text

Combined Thermal Index Development for Urban Heat Island Detection in Area of Split, Croatia by Majda Ćesić, Katarina Rogulj, Andrija Krtalić

“…UHIs are becoming an increasingly common problem in large cities, which appear due to excessive urbanization and reductions in natural cover and vegetation. …”
Get full text

Detecting cyber attacks in vehicle networks using improved LSTM based optimization methodology by C. Jayasri, V. Balaji, C. M. Nalayini, S. Pradeep

“…To address this problem, this study proposes an enhanced deep learning-based optimization framework for detecting cyberattacks in vehicle networks. …”
Get full text

FsDAOD: Few-shot domain adaptation object detection for heterogeneous SAR image by Siyuan Zhao, Yong Kang, Hang Yuan, Guan Wang, Hui Wang, Shichao Xiong, Ying Luo

“…In which the small sample of data scarcity is becoming an urgent problem for researchers. Therefore, this paper proposes a novel few-shot domain adaptation object detection (FsDAOD) method based on Faster Region Convolutional Neural Network baseline to cope with the above problem. …”
Get full text

A Parts Detection Network for Switch Machine Parts in Complex Rail Transit Scenarios by Jiu Yong, Jianwu Dang, Wenxuan Deng

“…The rail transit switch machine ensures the safe turning and operation of trains on the track by switching switch positions, locking switch rails, and reflecting switch status in real time. However, in the detection of complex rail transit switch machine parts such as augmented reality and automatic inspection, existing algorithms have problems such as insufficient feature extraction, large computational complexity, and high demand for hardware resources. …”
Get full text

Text-Guided Distribution Calibration for Few-Shot Object Detection in Remote Sensing Images by Yu Cao, Jingyi Chen, Haoyu Wang, Lei Zhang, Chen Ding, Wei Wei, Shiqi Cao, Meilin Xie

“…Considering the limited visual information of the novel classes, we propose a cross-modal knowledge transfer strategy, which aims to extract the corresponding text feature of the object class name through a multimodal pretraining model CLIP and transfer the text knowledge to the FSOD model, to mitigate the feature bias problem. …”
Get full text

Detecting and Identifying Industrial Gases by a Method Based on Olfactory Machine at Different Concentrations by Yunlong Sun, Dehan Luo, Hui Li, Chuchu Zhu, Ou Xu, Hamid Gholam Hosseini

“…In this work, we measure four typical industrial gases including CO2, CH4, NH3, and volatile organic compounds (VOCs) based on electronic nose (EN) at different concentrations. To solve the problem of effective classification and identification of different industrial gases, we propose an algorithm based on the selective local linear embedding (SLLE) to reduce the dimensionality and extract the features of high-dimensional data. …”
Get full text

Remote Sensing Change Detection With Forward–Backward Diffusion and Multidirectional Scanning by Hexin Yuan, Peng Wang, Haibo Wang, Cui Ni, Yali Liu, Chao Ma

“…In addition, a significant issue remains in the detection of large continuous change regions, which often leads to leakage problems. …”
Get full text

FPFS-YOLO: An Insulator Defect Detection Model Integrating FasterNet and an Attention Mechanism by Yujiao Chai, Xiaomin Yao, Manlong Chen, Sirui Shan

“…In this study, to mitigate parameter redundancy in the backbone of the YOLO11n model, the FasterNet lightweight network was introduced, and some convolution was embedded into the shallow network to enhance its feature extraction ability. To solve problems such as insufficient attention to important features and the low detection ability of small defects in the YOLO11n model network, the ParNet attention mechanism was added, along with a small-defect detection layer, which improved the detection accuracy of the model. …”
Get full text

Hyperspectral Target Detection Based on Macro–Micro Spectrum Contrastive Learning by Jiacheng Tian, Dunbin Shen, Wenfeng Kong, Min Li, Hongyu Wang, Xiaorui Ma

“…Depending on single target example under the influence of spectral variation, deep learning-based hyperspectral target detection (HTD) methods are challenged by the problem of insufficient target knowledge. …”
Get full text

Cloud-Edge Collaborative Defect Detection Based on Efficient Yolo Networks and Incremental Learning by Zhenwu Lei, Yue Zhang, Jing Wang, Meng Zhou

“…This paper addresses the problem of insufficient detection accuracy of existing lightweight models on resource-constrained edge devices by presenting a new lightweight YoloV5 model, which integrates four modules, SCDown, GhostConv, RepNCSPELAN4, and ScalSeq. …”
Get full text

Enhancing Fake Review Detection Using Linguistic Exaggeration, BERT Embeddings, and Fuzzy Logic by Mohammed Ennaouri, Ahmed Zellou

“…However, the presence of fake reviews threatens the credibility of review platforms, which requires advanced detection mechanisms. The core objective of this work is to develop a hybrid model that combines interpretable handcrafted linguistic cues with deep semantic features for more accurate, robust, and accurate fake review detection. …”
Get full text

Infrared Image Classification and Detection Algorithm for Power Equipment Based on Improved YOLOv10 by Xiu Ji, Zheyu Yue, Hongliu Yang, Zehong Zhang

“…However, infrared imaging technology has shortcomings such as poor signal clarity and serious background noise interference. To address this problem, this paper proposes an infrared image classification and detection algorithm for power equipment based on the improved YOLOv10, named YOLOv10plus. …”
Get full text

Multi-Class Urinary Sediment Particles Detection Based on YOLOv7 With Attention Modules by Tatsuki Komori, Hiroki Nishikawa, Keita Sasaki, Ittetsu Taniguchi, Takao Onoye

“…Traditional machine learning techniques approach the task of urine sediment particle detection as an image classification problem, wherein the particles are segmented based on features like edges or thresholds. …”
Get full text