The Detection Optimization of Low-Quality Fake Face Images: Feature Enhancement and Noise Suppression Strategies by Ge Wang, Yue Han, Fangqian Xu, Yuteng Gao, Wenjie Sang

“…To address these limitations, this paper proposes a novel algorithm, YOLOv9-ARC, which is designed to enhance the accuracy of detecting low-quality fake facial images. …”
Get full text

Energy-Efficient Route and Velocity Planning for Electric Vehicles: A Hierarchical Eco-Driving Framework Integrating Traffic and Road Information by Dong Xie, Jianhua Guo, Yu Jiang, Zhuoran Hou, Jintao Deng

“…Then, an energy-efficient route is efficiently planned using the proposed multi-heuristic A* algorithm. Finally, based on the route information from the upper level, along with traffic, kinematic, and road information, a convex optimization algorithm is employed to achieve accurate and efficient velocity planning. …”
Get full text

Point Cloud Completion of Occluded Corn with a 3D Positional Gated Multilayer Perceptron and Prior Shape Encoder by Yuliang Gao, Zhen Li, Tao Liu, Bin Li, Lifeng Zhang

“…To obtain the complete shape and pose of corn under occlusion, this study proposes a point cloud completion algorithm for completing the fragmented corn point cloud after segmentation. …”
Get full text

Effectiveness of biomarker-guided duration of antibiotic treatment in children hospitalised with confirmed or suspected bacterial infection: the BATCH RCT by Cherry-Ann Waldron, Philip Pallmann, Simon Schoenbuchner, Debbie Harris, Lucy Brookes-Howell, Céu Mateus, Jolanta Bernatoniene, Katrina Cathie, Saul N Faust, Josie Henley, Lucy Hinds, Kerry Hood, Chao Huang, Sarah Jones, Sarah Kotecha, Sarah Milosevic, Helen Nabwera, Sanjay Patel, Stéphane Paulus, Colin VE Powell, Jenny Preston, Huasheng Xiang, Emma Thomas-Jones, Enitan D Carrol

“…The qualitative evaluation showed that parent perceptions on acceptability and implementation of the intervention and trial processes were largely positive, although most parents were concerned about their child having to have extra blood tests if they were in the intervention arm. HCPs took a while to become familiar with the intervention algorithm, and as the intervention test did not align with the clinical pathway, often there were delays in getting the PCT results, which meant that adherence to the algorithm was low. …”
Get full text

Modeling and control strategy of small unmanned helicopter rotation based on deep learning by Hui Xia

“…To study the rotation phenomenon of small UAV landing process and propose control strategy, the study completes the rotation modeling of small unmanned helicopter based on deep learning algorithm and proposes the control strategy. The results show that the CNN with ReLU function has the best performance, and the model converges in the 5th iteration with this function, while the model with Sigmoid function converges in the 36th iteration, and the fitting effect of the rotation model constructed by the study is higher than that of the traditional rotation model. …”
Get full text

Accuracy–Efficiency Trade-Off: Optimizing YOLOv8 for Structural Crack Detection by Jiahui Zhang, Zoia Vladimirovna Beliaeva, Yue Huang

“…YOLO (You Only Look Once) is a real-time object detection algorithm known for its high speed and decent accuracy. …”
Get full text

Simplified system for isolated word recognition by R. GUBRYNOWICZ, K. MARASEK, W. MIKIEL, W. WIĘŹLAK

“…This leads to a reduction of the number range in further calculations. The DTW algorithm was used in the recognition process, while templates of individual words are introduced once, in principle separately for individual operators. …”
Get full text

Trade-off between gradient measurement efficiency and expressivity in deep quantum neural networks by Koki Chinzei, Shinichiro Yamano, Quoc Hoan Tran, Yasuhiro Endo, Hirotaka Oshima

“…Abstract Quantum neural networks (QNNs) require an efficient training algorithm to achieve practical quantum advantages. …”
Get full text

Quality of Experience Optimization for AR Service in an MEC Federation System by Huong Mai do, Tuan Phong Tran, Myungsik Yoo

“…Experiments demonstrate that our method improves QoE by nearly 8% compared with TD3 while cutting training time in half.…”
Get full text

Arrhythmia classification based on multi-input convolutional neural network with attention mechanism. by Bin Zheng, Wenbo Luo, Mingming Zhang, Huiyuan Jin

“…In this work, we propose a novel arrhythmia classification algorithm based on a multi-input convolutional neural network (CNN) enhanced with a Squeeze-and-Excitation (SE) attention mechanism. …”
Get full text

Analysis for Improvement of Doppler Tomography Imaging of Objects Scattering Continuous Ultrasonic Waves by Tomasz ŚWIETLIK, Krzysztof J. OPIELINSKI

“…In the conventional method, the probe remains stationary, while in the DT method, the probe moves and the examined tissue remains stationary. …”
Get full text

AFD: Defending Convolutional Neural Networks Without Using Adversarial Samples by Nupur Thakur, Yuzhen Ding, Baoxin Li

“…In this paper, we present a novel training strategy named Adversarial-Free Defense (AFD), which introduces a minimal change to a network architecture (by modifying the first convolution layer) while employing a learning algorithm that leads to special properties of the first-layer kernels. …”
Get full text

Image preference estimation with a data-driven approach: A comparative study between gaze and image features by Yusuke Sugano, Yasunori Ozaki, Hiroshi Kasai, Keisuke Ogaki, Yoichi Sato

“…A dataset of eye movements is collected while the participants are viewing pairs of natural images, and it is used to train image preference label classifiers. …”
Get full text

Scalable and cohesive swarm control based on reinforcement learning by Marc-Andrė Blais, Moulay A. Akhloufi

“…We propose an approach based on agent masking to enable a simple Deep Q-Network algorithm to scale on large swarms while training on relatively smaller swarms. …”
Get full text

Edge-LLM Inference With Cost-Aware Layer Allocation and Adaptive Scheduling by Sama Habibi, Ozgur Ercetin

“…FCIM is an auction-based mechanism that selects cost-effective, memory-feasible devices while minimizing task latency, reward cost, and device usage. …”
Get full text

Dynamic UAV Task Allocation and Path Planning with Energy Management Using Adaptive PSO in Rolling Horizon Framework by Zhen Han, Weian Guo

“…We introduce an enhanced Particle Swarm Optimization (PSO) algorithm, incorporating adaptive perturbation strategies and a local search mechanism based on simulated annealing, to optimize UAV task assignments and routes. …”
Get full text

The ethics of AI at the intersection of transgender identity and neurodivergence by Max Parks

“…I conclude with technical and policy recommendations intended to promote fairness while acknowledging the potential benefits and risks of AI systems, and suggest avenues for future research.…”
Get full text

Rotor Flux Controller for Induction Machines Considering Main Inductance Saturation by Diachenko G.

“…This paper discusses the problem of controlling electromechanical systems with maximum per-formance while maintaining accuracy and minimum power consumption. …”
Get full text

Optimization and Modeling of Optical Emission Spatial Coverage from Underwater Multi-Faceted Optical Base Stations by Junjie Shi, Chunbo Ma, Xu Tian, Hanjun Guo, Jun Ao

“…These advancements aim to enhance beam coverage performance while also providing technical support for achieving omnidirectional communication in underwater optical wireless networks (UOWN).…”
Get full text

Design of Privacy Preservation Model for Data Stream Using Condensation Based Anonymization by Latha P, Thangaraj M

“…As data streams become increasingly prevalent across various sectors, preserving the privacy of sensitive information while maintaining data utility is a significant challenge. …”
Get full text