ATBShellFinder: A Bytecode-Level Webshell Detector Based on Adversarial Training by Yuqin Xie, Yuan Zhang, Daofeng Li, Guoren Xiong

“…To address these challenges, this study proposes ATBShellFinder, an enhanced detection framework based on adversarial training. ATBShellFinder applies adversarial training techniques from computer vision to the embedding layer of the Bidirectional Encoder Representations from Transformers (BERT) to generate adversarial word embeddings. …”
Get full text

Development of IoT-based pulse rate detection bracelet for volleyball endurance training by Nur Ahmad Muharram, Budiman Agung Pratama, Pungky Indarto

“…Objective: This research aims to develop an IoT-based pulse rate detection bracelet designed specifically for endurance training in volleyball. …”
Get full text

Graph-based vision transformer with sparsity for training on small datasets from scratch by Peng Li, Lu Huang, Jin Li, Haiyan Yan, Dongjing Shan

“…To overcome this low-rank bottleneck in attention heads, we employ talking-heads technology based on bilinear pooled features and sparse selection of attention tensors. …”
Get full text

Wavelet-Based Analysis of Motor Current Signals for Detecting Obstacles in Train Doors by Yaojung Shiao, Premkumar Gadde, Chun-Yu Liu

Get full text

FeTT: Class-Incremental Learning with Feature Transformation Tuning by Sunyuan Qiang, Yanyan Liang

“…Then, we propose the feature transformation tuning (FeTT) model, which concurrently alleviates the inadequacy of previous PTM-based CIL in terms of stability and plasticity. …”
Get full text

Electrogastrogram-based detection of cybersickness with the application of wavelet transformation and machine learning: A case study by Ilija V. Tanasković, Nenad B. Popović, Jaka J. Sodnik, Sašo J. Tomažič, Nadica S. Miljković

“…Furthermore, recovery signs appear approximately 8 minutes after the first VR experience supporting the idea of conducting multiple sessions the same day i.e., intensive VR-based training. Conclusions: The unsupervised ML shows potential in identifying CSaffected EGG signal segments with feature extraction based on DWT, offering a novel approach for enhancing the prevention of CS occurrence in VR-based military training and other VR-related environments.…”
Get full text

The features of changes in orientations to employment among bachelor’s graduates by A. V. Merenkov, D. G. Sandler, V. S. Shavrin

Get full text

Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity Disorder by Elahe Hosseini, Seyyed Ali Hosseini, Stijn Servaes, Brandon Hall, Pedro Rosa-Neto, Ali-Reza Moradi, Ajay Kumar, Mir Mohsen Pedram, Sanjeev Chawla

“…<b>Methods:</b> Leveraging the ADHD200 dataset, which encompasses demographic information and anatomical MRI scans collected from a diverse ADHD population, our study focused on developing modern deep learning-based diagnostic models. The data preprocessing employed a pre-trained Visual Geometry Group16 (VGG16) network to extract two-dimensional (2D) feature maps from three-dimensional (3D) anatomical MRI data to reduce computational complexity and enhance diagnostic power. …”
Get full text

Research on Automatic Train Operation System Based on Fuzzy Adaptive PID Algorithm by ZHOU Ruilin, LEI Chengjian, LIU Ze, SU Huiliang

“…The traditional PID algorithm used in the currently existing automatic train operation system is limited due to fixed parameters, making it difficult to achieve excellent control effects in actual operation scenes featuring strong coupling and high nonlinearity, which is mainly attributed to difficulties in overcoming nonlinear disturbances.In light of this, this paper proposes an automatic train operation approach that relies on a fuzzy adaptive PID algorithm, which can adjust the PID parameters in real time according to the preset fuzzy rules, thus improving the PID controller's performance in speed tracking and leading to an improved train control effect. …”
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

Unsupervised Visual-to-Geometric Feature Reconstruction for Vision-Based Industrial Anomaly Detection by Dinh-Cuong Hoang, Phan Xuan Tan, Anh-Nhat Nguyen, Duc-Thanh Tran, Van-Hiep Duong, Anh-Truong Mai, Duc-Long Pham, Khanh-Toan Phan, Minh-Quang Do, Ta Huu Anh Duong, Tuan-Minh Huynh, Son-Anh Bui, Duc-Manh Nguyen, Viet-Anh Trinh, Khanh-Duong Tran, Thu-Uyen Nguyen

“…Specifically, we use pre-trained 2D and 3D models to extract visual features from color images and geometric features from 3D point clouds. …”
Get full text

Semantically-Enhanced Feature Extraction with CLIP and Transformer Networks for Driver Fatigue Detection by Zhen Gao, Xiaowen Chen, Jingning Xu, Rongjie Yu, Heng Zhang, Jinqiu Yang

“…Experiments show that the CLIP pre-trained model more accurately extracts facial and behavioral features from driver video frames, improving the model’s AUC by 7% over the ImageNet-based pre-trained model. …”
Get full text

Cross-Domain Feature Enhancement-Based Password Guessing Method for Small Samples by Cheng Liu, Junrong Li, Xiheng Liu, Bo Li, Mengsu Hou, Wei Yu, Yujun Li, Wenjun Liu

Get full text

Nomogram construction for overall survival in breast angiosarcoma based on clinicopathological features: a population-based cohort study by Peikai Ding, Luxiao Zhang, Shengbin Pei, Zheng Qu, Xiangyi Kong, Zhongzhao Wang, Jing Wang, Yi Fang

Get full text

A range spread target detection algorithm based on polarimetric features and SVDD by Qiang LI, Yuanxin YAO, Xiangqi KONG

“…Multi-polarization range high resolution radar is an important mean for ground target detection.In the echo formed by it, the target occupies multiple range cells and becomes an extended target.The traditional spread target detection method relies on energy, and the detection performance decreases when the signal-to-clutter ratio decreases.A spread target detection algorithm based on polarization decomposition features was proposed, which improved the detection performance under low signal-to-clutter ratio by using the difference of polarization scattering characteristics between target and clutter.Specifically, 16 kinds of polarization decomposition features were extracted to form feature vectors as detection statistics, and then support vector data description (SVDD) was used to obtain the detection threshold.When training the detection threshold, the polarization decomposition features of clutter were extracted as training data.In order to ensure the false alarm probability, two penalty parameters were introduced into the objective function of SVDD.The experimental results show that the proposed method requires a signal-to-clutter ratio of about 12.6 dB in the case of Gobi background, false alarm probability of 10^-4 and detection probability of 90%, which is about 1.7 dB lower than the energy-based methods.…”
Get full text

Automatic Feature Engineering-Based Optimization Method for Car Loan Fraud Detection by Jian Yang, Zixin Tang, Zhenkai Guan, Wenjia Hua, Mingyu Wei, Chunjie Wang, Chenglong Gu

“…Compared with traditional automatic feature engineering methods, the number of features and training time are reduced by 92.5% and 54.3%, respectively, whereas accuracy is improved by 23%. …”
Get full text

Early Prediction of Epilepsy after Encephalitis in Childhood Based on EEG and Clinical Features by Xiaojuan Sun, Jinhua Zhao, Chunyun Guo, Xiaoxiao Zhu

“…The present study was designed to establish and evaluate an early prediction model of epilepsy after encephalitis in childhood based on electroencephalogram (ECG) and clinical features. …”
Get full text

Feature-Based Dataset Fingerprinting for Clustered Federated Learning on Medical Image Data by Daniel Scheliga, Patrick Mäder, Marco Seeland

“…Additionally, shared raw data fingerprints can directly leak sensitive visual information, in certain cases even resembling the original client training data. To alleviate these problems, we propose a Feature-based dataset FingerPrinting mechanism (FFP). …”
Get full text

Sports Motion Recognition Using MCMR Features Based on Interclass Symbolic Distance by Yu Wei, Libin Jiao, Shenling Wang, Rongfang Bie, Yinfeng Chen, Dalian Liu

“…In this paper, we discuss motion recognition in sports training using features extracted from distance estimation of different kinds of sensors. …”
Get full text

An object detection method in foggy weather based on novel feature enhancement and fusion by ZHU Lei, ZHAO Han, WANG Weili

“…Additionally, coordinate attention was introduced in the feature fusion module to accurately locate object during training and reduce the loss of object feature information. …”
Get full text