Text Detection Method With Emphasis on Text Component Importance and Lightweight Design by Lanlan Yin, Qiming Wu

“…Therefore, this study proposes an image scene text detection method based on a lightweight deep relation inference scene text detection algorithm. This algorithm simplifies the network of detection algorithms that consider the importance of text components, aiming to reduce computational complexity while addressing issues such as excessive smoothing. …”
Get full text

Improved Combinatorial Benders Decomposition for a Scheduling Problem with Unrelated Parallel Machines by Francisco Regis Abreu Gomes, Geraldo Robson Mateus

“…For the first set the proposed method performs 21.85% on average faster than the standard implementation of the Benders algorithm. For the second set the proposed method failed to find an optimal solution in only 31 in 600 instances, obtained an average gap of 0.07%, and took an average computational time of 377.86 s, while the best results of the other methods were 57, 0.17%, and 573.89 s, respectively.…”
Get full text

ASSESSMENT OF THE EFFICACY OF DOSE RADIATION THERAPY REGIMENS FOR TREATING CANCER ACCORDING TO CRITERIA FOR EARLY TOXICITY OF RADIOTHERAPY by V. A. Lisin

“…Optimization of dose fractionation regimens is an important way to increase the effectiveness of radiotherapy for malignant tumors. …”
Get full text

Deep reinforcement learning for integrated vessel path planning with safe anchorage allocation by Gil-Ho Shin, Hyun Yang

“…Additionally, the system ensured practicality through path simplification using the Douglas-Peucker algorithm while maintaining safety standards. The visualized optimal paths enhance navigational guidance, thereby improving both maritime traffic safety and port operational efficiency.…”
Get full text

UAV spatiotemporal crowdsourcing resource allocation based on deep reinforcement learning by Yaxi LIU, Xulong LI, Jiahao HUO, Wei HUANGFU

“…This approach aims to minimize the average AoI across the network while also reducing the energy consumption of IoT devices. …”
Get full text

High-robustness integrated adversarial training method for fingerprint-based indoor localization systems by ZHANG Xuejun, LI Mei, CHEN Hui, WANG Guohua

“…These findings verify that EDEAD optimizes computational efficiency while maintaining high robustness.…”
Get full text

Toward Energy Efficiency and Fairness in UAV-Based Task Offloading by Mohamed El-Emary, Ali Ranjha, Diala Naboulsi, Razvan Stanica

“…This results in a joint optimization framework combining 1) a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm for UAV trajectory control to enhance service coverage and energy efficiency, with 2) a low-complexity task offloading algorithm for UEs. …”
Get full text

A Hybrid Approach to Cloud Data Security Using ChaCha20 and ECDH for Secure Encryption and Key Exchange by Rebwar Khalid Muhammed, Zryan Najat Rashid, Shaida Jumaah Saydah

“…This approach enhances security during data transmission and storage while mitigating the common vulnerabilities found in single-algorithm solutions. …”
Get full text

Automated irrigation of apple trees based on dendrometer sensors by Thainná Waldburger, Thomas Anken, Marianne Cockburn, Achim Walter, Matthias Hatt, Camilo Chiang, Hassan-Roland Nasser

“…Although the tested algorithm proved to be efficient, the results also indicated the potential for optimization. …”
Get full text

Effects of PET image reconstruction parameters and tumor-to-background uptake ratio on quantification of PET images from PET/MRI and PET/CT systems by Amena Ali Hussain, Eva Forssell-Aronsson, Tobias Rosholm, Esmaeil Mehrara

“…The Bayesian penalized likelihood (BPL) algorithm, recently introduced, uses a noise penalty factor (β) to achieve full convergence while controlling noise. …”
Get full text

Informative Path Planning Using Physics-Informed Gaussian Processes for Aerial Mapping of 5G Networks by Jonas F. Gruner, Jan Graßhoff, Carlos Castelar Wembers, Kilian Schweppe, Georg Schildbach, Philipp Rostalski

“…The algorithm combines the physics-informed GP models with Bayesian optimization and is developed and tested in a hardware-in-the-loop simulation. …”
Get full text

Enhancing grid-connected PV-EV charging station performance through a real-time dynamic power management using model predictive control by Aziz Watil, Hamid Chojaa

“…Furthermore, these systems often require multiple power electronics converters, increasing complexity and costs while reducing overall system efficiency. To overcome these limitations, the proposed algorithm dynamically switches between on-grid and off-grid modes based on real-time weather conditions, grid availability, and the state of charge of the battery electric vehicle (BEV). …”
Get full text

Three-dimensional reconstruction and structural surface identification of high steep slopes based on UAV close-range photogrammetry by Linfeng WANG, Hui JIANG, Ning TANG, Xiaoming HUANG, Guojin TAN

“…An adaptive KNN algorithm is introduced to enhance the coplanarity detection passing rate in point clouds, while optimal planar equations are fitted using the least squares method. …”
Get full text

Task Allocation and Path Planning Method for Unmanned Underwater Vehicles by Feng Liu, Wei Xu, Zhiwen Feng, Changdong Yu, Xiao Liang, Qun Su, Jian Gao

“…Experimental results demonstrate that the proposed task allocation mechanism and improved path planning algorithm exhibit significant advantages in task completion rate and path optimization efficiency.…”
Get full text

PCMINN: A GPU-Accelerated Conditional Mutual Information-Based Feature Selection Method by Nikolaos Papaioannou, Georgios Myllis, Alkiviadis Tsimpiris, Stamatis Aggelopoulos, Vasiliki Vrana

“…Conditional Mutual Information Nearest-Neighbor (CMINN) is an algorithm developed to address this challenge by using Conditional Mutual Information (CMI) to assess the relevance of individual features to the target variable, while identifying redundancy among similar features. …”
Get full text

Efficient collision-avoidance navigation strategy for autonomous surface vehicles in unstructured and constricted marine environments by Wenlong Meng, Rongdian Ku, Yanbo Pu, Xiaoxiao Shi, Ya Gong

“…Current path planning algorithms designed for unstructured environments, particularly those characterized by narrow spaces, often face difficulties in efficiently exploring the target area while producing high-quality paths. …”
Get full text

A quantum random access memory (QRAM) using a polynomial encoding of binary strings by Priyanka Mukhopadhyay

“…Abstract Quantum algorithms claim significant speedup over their classical counterparts for solving many problems. …”
Get full text

Adaptive Fast Refocusing for Ship Targets With Complex Motion in SAR Images by Xinqi Xu, Xiangguang Leng, Zhongzhen Sun, Xiangdong Tan, Kefeng Ji, Gangyao Kuang

“…This algorithm can adaptively adjust algorithm parameters based on SAR images from different SAR platforms, thereby more accurately determining the optimal rotation interval (ORI), reducing computational cost, and achieving adaptive fast refocusing. …”
Get full text

Understanding the flowering process of litchi through machine learning predictive models by SU Zuanxian, NING Zhenchen, WANG Qing, CHEN Houbin

“…The algorithms (RF and STR) with the smallest Mean Absolute Error (MAE) and the highest residual error (RMSE) and the highest correlation coefficient (RP2) were selected for further parameter optimization and evaluation. …”
Get full text

PP-QADMM: A Dual-Driven Perturbation and Quantized ADMM for Privacy Preserving and Communication-Efficient Federated Learning by Anis Elgabli

“…We provide a rigorous theoretical proof of convergence, showing that PP-QADMM converges to the optimal solution for convex problems while achieving a convergence rate comparable to standard ADMM, but with significantly lower communication and energy costs, and robust privacy protection. …”
Get full text