Robustness evaluation of commercial liveness detection platform by Pengcheng WANG, Haibin ZHENG, Jianfei ZOU, Ling PANG, Hu LI, Jinyin CHEN

“…Liveness detection technology has become an important application in daily life, and it is used in scenarios including mobile phone face unlock, face payment, and remote authentication.However, if attackers use fake video generation technology to generate realistic face-swapping videos to attack the living body detection system in the above scenarios, it will pose a huge threat to the security of these scenarios.Aiming at this problem, four state-of-the-art Deepfake technologies were used to generate a large number of face-changing pictures and videos as test samples, and use these samples to test the online API interfaces of commercial live detection platforms such as Baidu and Tencent.The test results show that the detection success rate of Deepfake images is generally very low by the major commercial live detection platforms currently used, and they are more sensitive to the quality of images, and the false detection rate of real images is also high.The main reason for the analysis may be that these platforms were mainly designed for traditional living detection attack methods such as printing photo attacks, screen remake attacks, and silicone mask attacks, and did not integrate advanced face-changing detection technology into their liveness detection.In the algorithm, these platforms cannot effectively deal with Deepfake attacks.Therefore, an integrated live detection method Integranet was proposed, which was obtained by integrating four detection algorithms for different image features.It could effectively detect traditional attack methods such as printed photos and screen remakes.It could also effectively detect against advanced Deepfake attacks.The detection effect of Integranet was verified on the test data set.The results show that the detection success rate of Deepfake images by proposed Integranet detection method is at least 35% higher than that of major commercial live detection platforms.…”
Get full text

Development and Performance Analysis of Pneumatic Soft-Bodied Bionic Basic Execution Unit by Yu Zhang, Wenchuan Zhao, Ning Wang, Dengyu Lu

“…Response surface analysis and numerical simulation algorithm are used to determine the optimal combination of structural dimension parameters by taking the maximum output bending angle of the basic executing unit as the optimization objective. …”
Get full text

3D printable and myoelectrically sensitive hydrogel for smart prosthetic hand control by Jinxin Lai, Longya Xiao, Beichen Zhu, Longhan Xie, Hongjie Jiang

“…Systematic in vivo studies were used to investigate its efficacy to control a prosthetic hand by decoding sEMG signals from the human hand via a multiple-channel readout circuit and a sophisticated artificial intelligence algorithm. Our findings demonstrate that the 3D printed gel myoelectric sensing system enables real-time and highly precise control of a prosthetic hand.…”
Get full text

An Enhanced and Lightweight YOLOv8-Based Model for Accurate Rice Pest Detection by Guisuo Liu, Juxing Di, Qing Wang, Yan Zhao, Yang Yang

“…Furthermore, to facilitate the deployment of the new algorithm on embedded terminal devices, we applied Layer Adaptive Magnitude Pruning and Knowledge Distillation techniques for a lightweight model. …”
Get full text

LSTM‐based real‐time stress detection using PPG signals on raspberry Pi by Amin Rostami, Koorosh Motaman, Bahram Tarvirdizadeh, Khalil Alipour, Mohammad Ghamari

“…In this study, the authors implement key TensorFlow toolkit optimisation techniques including quantisation aware training (QAT), Pruning and prune‐preserving quantisation aware training. …”
Get full text

Digital mapping of peat thickness and extent in Finland using remote sensing and machine learning by Jonne Pohjankukka, Timo A. Räsänen, Timo P. Pitkänen, Arttu Kivimäki, Ville Mäkinen, Tapio Väänänen, Jouni Lerssi, Aura Salmivaara, Maarit Middleton

“…Feature selection included an initial screening for multicollinearity using correlation-based feature pruning, followed by final selection using a genetic algorithm. …”
Get full text

Architected Design and Fabrication of Soft Mechanical Metamaterials by Thileepan Stalin, Aby Raj Plamootil Mathai, Naresh Kumar Thanigaivel, Elgar Kanhere, Saikrishna Dontu, Gumawang Hiramandala, Aaron Chooi, Arturo Castillo Ugalde, Pablo Valdivia Y Alvarado

“…Planar printing tool paths, utilized in layer‐by‐layer printing such as fused deposition modeling (FDM) and prevalently used in most slicing algorithms, severely limit the realization of complex topologies required in metamaterials. …”
Get full text

Enhancing Sports Team Management Through Machine Learning by Ling Zhang, Yifan An

“…By applying machine learning algorithms and pruning techniques, several classifications were developed to identify the most critical functional attributes of players. …”
Get full text

Enhancing mechanical and bioinspired materials through generative AI approaches by Silvia Badini, Stefano Regondi, Raffaele Pugliese

“…., failure mechanics-3D printing). In addition, generative AI techniques, including generative adversarial networks (GAN), genetic algorithms, and large language models (LLMs), offer efficient and tunable solutions for optimizing material properties, reducing production costs, and accelerating the development timelines.In the field of mechanical materials design, generative AI enables the rapid generation of novel structures with enhanced mechanical performance. …”
Get full text

Fiber Bragg grating flexible sensor for deformation monitoring in steel structure engineering by Chenguang Huang, Hui Zong, Xuepeng Chen, Peng Luo, Zongli Luo, Haixing Luo, Xiang Wu, Jie Huang

“…At the same time, a deformation monitoring model for steel structure engineering was constructed using the Kalman filtering algorithm. Using the FBGFS to monitor the deformation of steel structure engineering, the average error rate of 50 experiments was only 1.46%. …”
Get full text

Analysis of Generalization Ability for Different AdaBoost Variants Based on Classification and Regression Trees by Shuqiong Wu, Hiroshi Nagahashi

“…Some researchers compared different AdaBoost variants by experiments in their own fields, and others reviewed various AdaBoost variants by basically introducing these algorithms. However, there is a lack of mathematical analysis of the generalization abilities for different AdaBoost variants. …”
Get full text

Lightweight coal miners and manned vehicles detection model based on deep learning and model compression techniques: A case study of coal mines in Guizhou region by Beijing XIE, Heng LI, Zheng LUAN, Zhen LEI, Xiaoxu LI, Zhuo LI

“…In the model compression phase, the proposed FCW-YOLO model undergoes channel-level sparsity through a collaborative pruning algorithm, automatically identifying unimportant channels and reducing them, resulting in the FCWP-YOLO model, achieving secondary lightweight design of the coal mine pedestrian-vehicle detection model. …”
Get full text

Scalable reinforcement learning for large-scale coordination of electric vehicles using graph neural networks by Stavros Orfanoudakis, Valentin Robu, E. Mauricio Salazar, Peter Palensky, Pedro P. Vergara

“…We prove that EV-GNN enhances classic Reinforcement Learning (RL) algorithms’ scalability and sample efficiency by combining an end-to-end Graph Neural Network (GNN) architecture with RL and employing a branch pruning technique. …”
Get full text

Unified Mathematical Framework for Slicing and Symmetry Reduction over Event Structures by Xinyan Gao, Yingcai Ding, Wenbo Liu, Kaidi Zheng, Siyu Huang, Ning Zhou, Dakui Li

“…Nonclassical slicing and symmetry reduction can act as efficient structural abstract methods for pruning state space when dealing with verification problems. …”
Get full text

Local differential privacy-based frequent sequence mining by Teng Wang, Zhi Hu

“…Besides, PrivFSM leverages a threshold-based pruning strategy to prune fake nodes, which reduces perturbations and computation costs. …”
Get full text

Research of color models in digital graphics by Hetman Oksana, Shpetna Svitlana

“…Different types of color models are applied depending on the specific tasks and fields, including displays, mobile devices, printing technologies, and color correction systems. …”
Get full text

Improved YOLO for long range detection of small drones by Sicheng Zhou, Lei Yang, Huiting Liu, Chongqin Zhou, Jiacheng Liu, Yang Wang, Shuai Zhao, Keyi Wang

“…Additionally, deep learning algorithms often demand substantial computational resources, limiting their use on low-capacity platforms. …”
Get full text

Effects of Hybridizing the U-Net Neural Network in Traffic Lane Detection Process by Aron Csato, Florin Mariasiu

“…A vision-based lane detection system is difficult to implement in vehicles due to the unique characteristics of algorithms, neural network architectures, limitations, and strict hardware/software requirements. …”
Get full text

A redundant weight removal method inspired by specific immunotherapy for boosting transfer learning security by Qing Huang, Hongli Deng, Junxiang Wang, Tao Yang, Bochuan Zheng

“…Currently, redundant weights are removed mainly through pruning algorithms designed by correlating student data with teacher model nodes. …”
Get full text

Design, Fabrication, and Application of Large-Area Flexible Pressure and Strain Sensor Arrays: A Review by Xikuan Zhang, Jin Chai, Yongfu Zhan, Danfeng Cui, Xin Wang, Libo Gao

“…Fabrication techniques include 3D printing, screen printing, laser etching, magnetron sputtering, and molding, each influencing sensor performance in different ways. …”
Get full text