Comparative analysis of the performance of selected machine learning algorithms depending on the size of the training sample by Kupidura Przemysław, Kępa Agnieszka, Krawczyk Piotr

“…They also showed that among the tested algorithms, the XGB algorithm is the most sensitive to the size of the training sample, while the least sensitive is SVM, which achieved relatively good results even when using training samples of the smallest sizes. …”
Get full text

Applying neural networks as direct controllers in position and trajectory tracking algorithms for holonomic UAVs by Cezary Kownacki, Slawomir Romaniuk, Marcin Derlatka

“…Abstract This study compares different neural networks as standalone control algorithms for position and trajectory tracking in holonomic UAVs, specifically quadcopters. …”
Get full text

Video dual-domain watermarking algorithm based on hybrid DWT-DCT and frame grouping by LIANG Yucheng, NIU Ke, LI Jun, MENG Yifei

“…Aiming to address the compatibility of robustness and reversibility in existing video watermarking algorithms, a video dual-domain watermarking algorithm based on hybrid DWT-DCT and frame grouping was proposed. …”
Get full text

An Effective Off-Grid DOA Estimation Algorithm Using Difference Coarrays with Limited Snapshots by Yanan Ma, Jian Wang, Lu Cao, Pengyu Guo, Guangteng Fan

“…To address these limitations, in this work, we propose a novel coarray-based off-grid DOA estimation algorithm that achieves a computationally efficient performance while maintaining a high estimation accuracy under snapshot-constrained conditions. …”
Get full text

Effective Feature Selection on Transfer Deep Learning Algorithm for Thyroid Nodules Ultrasound Detection by Ghufran Basim Alghanimi, Hadeel Aljobouri, Khaleel Akeash Alshimmari, Rasha Massoud

Get full text

Big Data and AI Algorithms for Sustainable Development Goals: A Topic Modeling Analysis by Prema Nedungadi, Simi Surendran, Kai-Yu Tang, Raghu Raman

“…These insights offer practical implications, reinforcing the potential of AI and big data to address global challenges sustainably while calling for balanced attention to ethical and regulatory dimensions.…”
Get full text

Enhanced zebra optimization algorithm for sustainable combined economic and emission dispatch in power systems by Ahmed Arkwazee, Rana Abttan

“…Moreover, for the 110-unit system, IMZOA demonstrated competitive performance comparable to advanced algorithms like EBWO and ESNS, while maintaining lower standard deviations, indicating greater solution stability. …”
Get full text

Design of an Intelligent Pear Bagging End-Effector Based on Yolov8 and SGBM Algorithm by Jing Ruijun, Liu JingKai, LiXin, ZhiguoZhao

“…These improvements significantly reduce the model’s parameters and size while enhancing detection accuracy. To provide accurate three-dimensional information to the end-effector, we use the SGBM algorithm to obtain depth information of the targets. …”
Get full text

Multiplier leadership optimization algorithm (MLOA): unconstrained global optimization approach for melanoma classification by Sukanta Ghosh, Amar Singh, Shakti Kumar

“…Abstract This paper proposes the multiplier leadership optimization algorithm, which draws inspiration from multiplier leadership principles to search for and optimize solutions to complex problems effectively. …”
Get full text

Performance enhancement in blockchain based IoT data sharing using lightweight consensus algorithm by Ehtisham Ul Haque, Waseem Abbasi, Ahmad Almogren, Jaeyoung Choi, Ayman Altameem, Ateeq Ur Rehman, Habib Hamam

“…The primary obstacle is the distributed consensus protocol, while ensuring data transparency, integrity, and immutability in a decentralized and untrusted circumstances which often compromises scalability. …”
Get full text

Stress management with HRV following AI, semantic ontology, genetic algorithm and tree explainer by Ayan Chatterjee, Michael A. Riegler, K. Ganesh, Pål Halvorsen

“…Various techniques like feature selection and dimensionality reduction are explored to improve classification accuracy while minimizing bias. Different machine learning (ML) algorithms, including traditional and ensemble methods, are employed for analyzing both imbalanced and balanced HRV datasets. …”
Get full text

A Comparison of Machine Learning Algorithms for Predicting Alzheimer’s Disease Using Neuropsychological Data by Zakaria Mokadem, Mohamed Djerioui, Bilal Attallah, Youcef Brik

“…The results indicate that ensemble learning models, particularly Gradient Boosting (GB) and Random Forest (RF), exhibited superior accuracy compared to other algorithms. Most models for the CNvsAD subset achieved the highest accuracy (97.74%), while GB achieved the best performance (94.98%) for the CNvsMCI subset. …”
Get full text

Augmented secretary bird optimization algorithm for wireless sensor network deployment and engineering problem. by Qingwen Meng, Xi Kuang, Zihan Yu, Minghui He, Hanzhi Cui

“…This mechanism ensures that individuals that fail to update have a certain probability of being retained in the next generation population, while guaranteeing that the current global optimal solution remains unchanged, thereby accelerating the algorithm's convergence. …”
Get full text

Machine heuristic in algorithm aversion: Perceived creativity and effort of output created by or with artificial intelligence by Sigurd Birk Heimstad, Anders Hauge Wien, Tarje Gaustad

“…Through two pre-registered experiments, we investigate how individuals evaluate creative content when it is labeled as created by AI, humans, or human-AI collaboration. While previous research has established algorithm aversion across various domains, our findings reveal nuanced patterns in creative contexts. …”
Get full text

Multibit image watermarking algorithm resistant to geometric attacks based on level set method

“…A multibit watermarking algorithm based on level set method was proposed.First,the stable location of the unit disk was found using level set method.Then,pseudo-Zernike moments were calculated.At last,the watermark was embedded by modifying the pseudo-Zernike moments.In the extraction process,the root-mean-square-error method was employed to detect the watermark.Simulation results show that the algorithm overcomes the defect of the traditional al-gorithm based on pseudo-Zernike moments,while be robust against geometric attacks.…”
Get full text

Mobile-YOLO: A Lightweight Object Detection Algorithm for Four Categories of Aquatic Organisms by Hanyu Jiang, Jing Zhao, Fuyu Ma, Yan Yang, Ruiwen Yi

Get full text

Construction and Application of Carbon Emissions Estimation Model for China Based on Gradient Boosting Algorithm by Dongjie Guan, Yitong Shi, Lilei Zhou, Xusen Zhu, Demei Zhao, Guochuan Peng, Xiujuan He

“…The results indicate that GDP, energy intensity, and nighttime lights exert the greatest influence on model predictions, while ecological indicators such as NDVI exhibit negative associations. …”
Get full text

Risk of AI Algorithmic Discrimination Embedded in Government Data Governance and Its Prevention and Control by PENG Lihui, ZHANG Qiong, LI Tianyi

“…[Results/Conclusions] The results of the study show that while the embedding of AI technology in government data governance has significantly improved the efficiency and accuracy of governance, it comes with a risk of algorithmic discrimination that cannot be ignored. …”
Get full text

A detection algorithm for small surface floating objects based on improved YOLOv5s by Xusheng YUE, Jun LI, Yaohong WANG, Penghao ZHU, Zhexing WANG, Xuanhao XU

“…ObjectiveTo address the challenges of false detection and missed detection in identifying floating bottles on the water surface in unmanned surface vehicle applications, this study proposes an improved small floating object detection algorithm based on YOLOv5s. Method First, data augmentation was performed on the Flow-Img dataset to expand the data and avoid model overfitting. …”
Get full text

GPS signal fast acquisition algorithm using differential code and block processing techniques by HUANG Lei, ZHANG Qi-shan, KOU Yan-hong

“…A novel GPS signal acquisition algorithm using differential C/A codes and block processing techniques was proposed.It was integrated with the advantages of serial correlation method in the time domain,differential digital matched filter method and block processing techniques in the frequency domain,and realized a good compromise be-tween acquisition time and resources consumption,which not only improved the acquisition speed but also reduced the hardware consumption while maintaining an identical processing gain.The experiment results show the algorithm can work well.…”
Get full text