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

Professional self-determination theory of senior pupils in Russian psychology by E. P. Shutova, A. S. Velikanova (Gerasimova)

“…Some researchers focus on the goal and end result of vocational self-determination, while others seek to reveal the algorithm of the process itself and/or its stages. …”
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

Monitoring Water Area Dynamics in Kashgar (2003–2023) Using Multi-Source Remote Sensing Data by Cong Ding, Chao Ren

“…This study leverages Landsat and Sentinel-2 imagery from 2003 to 2023, employing a random forest algorithm to extract water body information. Key findings are as follows: (1) both total and seasonal water area exhibit a fluctuating downward trend, while permanent water area displays a fluctuating upward trend; (2) precipitation and temperature emerged as primary drivers of water area changes, with precipitation in the surrounding regions of Kashgar exerting a particularly significant influence, while evaporation exhibited a lesser impact; (3) the influence of climate change and anthropogenic activities in surrounding areas on water area changes in Kashgar cannot be overlooked.…”
Get full text

DOA Estimation Method in Multipath Environment for Passive Bistatic Radar by Panhe Hu, Qinglong Bao, Zengping Chen

“…The proposed method combines the advantages of both spatial difference method and the IAA algorithm while avoiding their shortcomings. Simulation results validate its effectiveness; meanwhile, the good performances of the proposed method in terms of resolution probability, detection probability, and estimation accuracy are demonstrated by comparison with the existing methods.…”
Get full text

Adaptive fusion of multi-cultural visual elements using deep learning in cross-cultural visual communication design by HuPei Wang

“…We address the challenge of creating culturally appropriate digital interfaces by developing a comprehensive framework that combines convolutional neural networks, attention mechanisms, and generative adversarial networks to analyze, extract, and adaptively fuse cultural features from diverse visual communication design elements. The proposed algorithm dynamically adjusts color schemes, spatial arrangements, typography, and iconography based on target cultural preferences while maintaining visual communication design coherence and functional clarity. …”
Get full text

TCCM: Trajectory Converged Chaff-Based Mix-Zone Strategy for Enhancing Location Privacy in VANET by Yunheng Wu

“…We implemented a VANET simulation and two adversary attack algorithms to evaluate the performance of our scheme. …”
Get full text

Research on multi-condition optimization of centrifugal compressor impeller meridian profile. by Ning Yu, Xiaohan Yu, Zhi Cai, Xinle Yang, Liyong Tian, Song Li

“…The optimization goal is to improve the overall average efficiency while maintaining the high pressure ratio based on the prototype scheme. …”
Get full text