The dual-edged potential of AI autonomously defining loss functions by Abbas Ghori

“…This paper discusses classical loss functions, including mean squared error (MSE), cross-entropy, Huber loss, and a range of other problem-specific variants that appear in scenarios dealing with imbalanced data, adversarial learning, and reinforcement learning. …”
Get full text

Topological Sequences Connected With Inverse Graphs of Finite Flexible Weak Inverse Property Quasigroups: An Approach From Polynomials to Machine Learning by Faizah D. Alanazi

“…They indicate feature significance, nonlinear interactions, and error dynamics. Moreover, they empower models to extrapolate complex real-world data, facilitating tasks like regression, classification, optimized performance, and feature adaptation. …”
Get full text

Closed-Loop Control Strategies for a Modular Under-Actuated Smart Surface: From Threshold-Based Logic to Decentralized PID Regulation by Edoardo Bianchi, Francisco Javier Brosed Dueso, José A. Yagüe-Fabra

“…For both control methods, promising results were obtained in terms of handling capability and errors in achieving the desired movement.…”
Get full text

Generation of an optimal triangulated irregular network for topographic surface via optimal transport theory by Feng Li, Haihong Zhu, Wei Li, Chengcheng Liu, Jianfang Ma, Lin Li

“…Experimental results confirm that the proposed method effectively generates the optimal digital representation of the topographic surface with the lowest elevation errors and minimal deviations from the original topographic features. …”
Get full text

Research on Traffic Marking Segmentation Detection Algorithm Based on Feature Fusion by Zhonghe He, Zizheng Gan, Pengfei Gong, Min Li, Kailong Li

“…However, road traffic markings are interfered with by a variety of factors, such as being obscured and the viewpoint of the vehicle sensors, resulting in large errors in the existing detection methods. In order to make the target detection task applicable to irregular objects or to detection tasks with higher accuracy requirements while reducing the waste of computational resources, this paper improves the accuracy of traffic marking segmentation detection by designing a multi-type traffic marking segmentation detection model based on image segmentation algorithms and designing a segmentation guidance matrix module based on a rank guidance matrix computation method. …”
Get full text

MeStanG—Resource for High-Throughput Sequencing Standard Data Sets Generation for Bioinformatic Methods Evaluation and Validation by Daniel Ramos Lopez, Francisco J. Flores, Andres S. Espindola

“…MeStanG allows samples to be designed with user-defined organism abundances expressed as number of reads, reference sequences, and predetermined or custom errors by sequencing profiles. The simulator pipeline was evaluated by analyzing its output mock metagenomic samples containing known read abundances using read mapping, genome assembly, and taxonomic classification on three scenarios: a bacterial community composed of nine different organisms, samples resembling pathogen-infected wheat plants, and a viral pathogen serial dilution sampling. …”
Get full text

Hyperdimensional computing: a framework for stochastic computation and symbolic AI by Mike Heddes, Igor Nunes, Tony Givargis, Alexandru Nicolau, Alex Veidenbaum

“…Moreover, our approach remains unaffected by a realistic level of memory errors which causes significant mismatches for existing methods.…”
Get full text

Airborne Laser Scanning for Corridor Mapping: Georeferencing with Tightly-coupled Multi-view LiDAR by F. Pöppl, A. Spitzer, A. Ullrich, N. Pfeifer

“…Airborne laser scanning enables efficient acquisition of 3D point clouds, particularly in corridor mapping applications. This article presents a georeferencing workflow which integrates GNSS, and IMU and LiDAR data within a non-linear least-squares adjustment framework. …”
Get full text

Benchmarking of Anomaly Detection Methods for Industry 4.0: Evaluation, Ranking, and Practical Recommendations by Aurélie Cools, Mohammed Amin Belarbi, Sidi Ahmed Mahmoudi

“…Real-time visual inspection ensures early detection of manufacturing defects, assembly errors, or texture inconsistencies, preventing defective products from reaching customers. …”
Get full text

DMN-YOLO: A Robust YOLOv11 Model for Detecting Apple Leaf Diseases in Complex Field Conditions by Lijun Gao, Hongwu Cao, Hua Zou, Huanhuan Wu

“…Additionally, a normalized Wasserstein distance (NWD) loss function is introduced to mitigate localization errors, particularly for small or overlapping lesions. …”
Get full text

Using UMAP for Partially Synthetic Healthcare Tabular Data Generation and Validation by Carla Lázaro, Cecilio Angulo

“…In addition, the common case of lack of information due to technical issues, transcript errors, or differences between descriptors considered in different health centers leads to the need for data imputation and partial data generation techniques. …”
Get full text

Pavement damage decay performance of ordinary national and provincial trunk lines by Jianguo Rong, Xiaodong Sha, Zongjun Pan, Hai Zhang

“…The ‘predictionworksheet’ model, characterized by its low residual sum of squares (RSS) and minimal absolute and relative errors, has been identified as an effective tool for predicting PCI attenuation on ordinary national and provincial trunk lines in A province. …”
Get full text

A tree crown edge-aware clipping algorithm for airborne LiDAR point clouds by Shangshu Cai, Yong Pang

“…It reduces crown fragmentation errors by 73.29% on average and maintains an average area difference of 6.42% compared to regular clippings. …”
Get full text

State of Charge Estimation on Lithium-Ion Batteries Using Particle Swarm Optimization Method by Muhammad Ridho Dewanto, Riza Hadi Saputra, Kharis Sugiarto, Agung Adi Saputra

“…PSO can provide more accurate predictions with smaller errors, both in terms of the RMSE value of 0.0391 and the MAPE value of 12.028%. …”
Get full text

Initial Orbit Determination Solution Distribution with Gooding Algorithm and Performance Enhancement by Zhengyuan Zhang, Bin Li, Zhenwei Li, Xiaohong Zhang, Jizhang Sang

“…Thus, the IOD solutions may have additional errors if the observations are not corrected for perturbation effects. …”
Get full text

A vertical-mode extrapolation scheme applied to the Brazil Current domain: quasi-synoptic scenarios by João P. M. Amorim, João P. M. Amorim, Ilson C. A. da Silveira, Milton Borges-Silva, Pedro W. M. Souza-Neto, Wellington C. Belo, Cauê Z. Lazaneo, Piero S. Bernardo, Marcelo Dottori, Renato P. Martins, Daniel L. Moreira

“…Normalized mean squared errors below 10% and radar diagrams show that the presented methodology was able to reproduce the main dynamic features observed by LADCP transects. …”
Get full text

Overhead Transmission Line Modeling Strategies for EMT-Based Traveling-Wave Analysis and Fault Location by Adrian Wilmer Diaz Sarmiento, Jaimis Sajid Leon Colqui, Jose Pissolato Filho

“…The results show that: 1) uniform soil resistivity assumptions introduce negligible errors in TW arrival times despite minor amplitude variations; 2) shield wires significantly affect modal structure, compromising the effectiveness of Clarke transformation for ground quasi-mode decoupling while preserving aerial quasi-mode reliability; 3) exact eigenvector-based decomposition improves ground mode identification but remains impractical for field applications; 4) the classical two-terminal fault location method maintains high accuracy across all modeling configurations; and 5) simplified OHTL modeling uniformly distributed sections at both terminals achieves an optimal balance between accuracy and computational efficiency for simulating TWs. …”
Get full text

Evaluation of the APSIM common bean model using different cultivars and water-management scenarios by Seyedreza Amiri, Nader Zakeri, Tayebeh Yousefi

“…This study aimed to assess the applicability of the APSIM common bean model under different water-management conditions and cultivars in southeastern Iran. …”
Get full text

RaNet: a residual attention network for accurate prostate segmentation in T2-weighted MRI by Muhammad Arshad, Chengliang Wang, Muhammad Wajeeh Us Sima, Jamshed Ali Shaikh, Salem Alkhalaf, Fahad Alturise

“…The MSAF enhances segmentation by dynamically focusing on key regions, refining feature selection and minimizing errors, while the FFM optimizes the handling of spatial hierarchies and varying object sizes, improving boundary delineation. …”
Get full text

Conscious and Correct Use of Biostatistical Methods in Medical Researches: From Planning to Reporting the Results - Part II by Erdem Karabulut, Mehmet Ali Sungur

“…Understanding the terms related to type I and type II errors, p-value, power of the study, effect size, and confidence interval will contribute to the correct interpretation of both the results obtained from statistical tests in scientific research and the findings of articles read from the literature. …”
Get full text