A Detailed Performance Evaluation of the GK2A Fog Detection Algorithm Using Ground-Based Visibility Meter Data (2021–2023, Part I) by Hyun-Kyoung Lee, Myoung-Seok Suh

“…This study evaluated the performance of the operational GK2A (GEO-KOMPSAT-2A) fog detection algorithm (GK2A_FDA) using ground-based visibility meter data from 176 stations across South Korea from 2021 to 2023. …”
Get full text

The relevance of the data collection process in the VioGén system from a feminist perspective by Javiera Farías Pereira

“…The VioGén system is a predictive policing and algorithm tool, which has been implemented in Spain since 2007. …”
Get full text

Pri-EMO: A universal perturbation method for privacy preserving facial emotion recognition by Yong Zeng, Zhenyu Zhang, Jiale Liu, Jianfeng Ma, Zhihong Liu

“…However, cryptography-based perturbation algorithms are highly computationally expensive, and transformation-based perturbation algorithms only target specific recognition models. …”
Get full text

A deep learning based prediction model for effective elastic properties of porous materials by Chang Liu, Ran Guo, Yangming Su

“…This article randomly generates porous microstructure models through algorithms and uses efficient quadtree algorithms to calculate their mechanical properties, thereby obtaining a large amount of machine-learning sample data. …”
Get full text

Technological Catch-Up Performance: The Interplay Between Collaboration Networks and Knowledge Networks by Xiaoji Wan, Jiangmei Li, Jing Lai, Liping Zhang

“…By strengthening their cooperation with external parties and integrating internal knowledge, firms can better absorb internal and external resources, accelerating their technological catch-up performance (TCP). This study mainly explores the influence of collaboration and knowledge networks on the TCP of firms based on machine learning algorithms. …”
Get full text

MALDI-TOF mass spectrometry combined with machine learning algorithms to identify protein profiles related to malaria infection in human sera from Côte d’Ivoire by Fateneba Kone, Lucie Conrad, Jean T. Coulibaly, Kigbafori D. Silué, Sören L. Becker, Brama Kone, Issa Sy

“…In endemic areas, malaria is mainly diagnosed using microscopy or rapid diagnostic tests (RDTs), which have limited sensitivity, and microscopic expertise is waning in non-endemic regions. …”
Get full text

Optimal ecological restoration strategy development based on value-cost trade-offs by Yunxuan Liu, Cui Zhang, Miaomiao Xie, Jingyi Xie

“…In addition, we searched for Pareto-optimal solutions using the nondominated sorting genetic algorithm II (NSGA-II) to balance the trade-offs between different objectives. …”
Get full text

Joint Optimization of Caching and Recommendation with Performance Guarantee for Effective Content Delivery in IoT by Zhiyong Liu, Hong Shen, Hui Tian

“…Experimental results demonstrate that our algorithm dramatically improves the popular least-recently used (LRU) algorithm. …”
Get full text

Characteristics of R2019 Processing of MODIS Sea Surface Temperature at High Latitudes by Chong Jia, Peter J. Minnett, Malgorzata Szczodrak

“…However, as surface temperature retrieval algorithms in the infrared (IR) part of the electromagnetic spectrum are designed to compensate for atmospheric effects mainly due to water vapor, MODIS SST_skin retrievals have larger uncertainties at high latitudes where the atmosphere is very dry and cold, which is an extreme in the distribution of global conditions. …”
Get full text

An Integrated Learning Approach for Municipal Solid Waste Classification by Hieu M. Sondao, Tuan M. Le, Hung V. Pham, Minh T. Vu, Son Vu Truong Dao

“…During the feature selection phase, three metaheuristic algorithms—Whale Optimization Algorithm (WOA), Salp Swarm Algorithm (SSA), and Harris Hawk Optimization (HHO)—are applied to filter out irrelevant features and retain significant ones. …”
Get full text

Non-Destructive Identification of Virgin Cashmere and Chemically Modified Wool Fibers Based on Fractional Order Derivative and Improved Wavelength Extraction Algorithm Using NIR Sp... by Yaolin Zhu, Yong Zhang, Xin Chen, Jinni Chen, Hongsong Zhang

“…Meanwhile, common wavelength extraction algorithms few consider inherent relationship between spectral features and chemical properties, so an improved wavelength extraction algorithm using Shuffled Frog Leaping Algorithm (SFLA) and Beluga Whale Optimization (BWO) is employed to explore the connection of the two. …”
Get full text

Comparison of SVM, K-NN, RF, CART, and GNB Algorithms for Water Bodies Detection Using Sentinel-2 Level-2a Imagery in Nakhon Pathom, Thailand by Ni Putu Nita Nathalia, Gede Andra Rizqy Wijaya, Kadek Yota Ernanda Aryanto, Ni Putu Novita Puspa Dewi, Putu Hendra Saputra, Ni Putu Karisma Dewi, Mellisa Damayanti, Kadek Losinanda Prawira

“…The Pixel-Based approach is used as the main method for data extraction, while CRISP-DM is applied as a structured methodology for data management. …”
Get full text

Implementation of an algorithm for the identification of breast cancer deaths in German health insurance claims data: a validation study based on a record linkage with administrati... by Hajo Zeeb, Ulrike Haug, Jonas Czwikla, Hans Werner Hense

“…Objective To adapt a Canadian algorithm for the identification of female cases of breast cancer (BC) deaths to German health insurance claims data and to test and validate the algorithm by comparing results with official cause of death (CoD) data on the individual and the population level.Design Validation study, secondary data, medical claims.Setting Claims data of two statutory health insurance providers (SHIs) for inpatient and outpatient care, CoD added via record linkage with epidemiological cancer registry (ECR).ParticipantsAll women insured with the two SHIs and who deceased in the period 2006–2013, were residents of North Rhine Westphalia (NRW) and were linked with ECR data: n=22 413.Main outcome measures Based on inpatient and outpatient diagnoses in the year before death, six algorithms were derived and the accordance of the algorithm-based CoD with the official CoD was evaluated calculating specificity, sensitivity, negative and positive predictive values (NPV, PPV). …”
Get full text

The Acidemia Index: A Near Real-Time Risk Analytics Algorithm is Associated With Measured Acidemia in Pediatric Critical Care Patients, a Multi-Center Validation Study by Ahmed Asfari, MD, Avihu Z. Gazit, MD, Craig Futterman, MD, Robert B. Kelly, MD, Andrew Macfadyen, MD, David S. Copper, MD, Joshua W. Salvin, MD, Adam Szadkowski, MD, Santiago Borasino, MD, Joshua Wolovits, MD, Hayden J. Zaccagni, MD

“…The ACD index was calculated using a physiologic algorithm that incorporates patients’ variables including laboratory and clinical data. …”
Get full text

Suitability of different machine learning algorithms for the classification of the proportion of grassland-based forages at the herd level using mid-infrared spectral information f... by A. Birkinshaw, M. Sutter, M. Nussbaum, M. Kreuzer, B. Reidy

“…Our results suggest that in general, LASSO and PLS-DA machine learning algorithms perform better for dietary GBF classification than RF or SVM algorithms.…”
Get full text

A dual-method approach integrating dynamic QCA and LightGBM-SHAP algorithms to uncover the configuration paths and key drivers of water resource green efficiency in China by Naiming He, Rijia Ding

Get full text

TomatoWUR: An annotated dataset of tomato plants to quantitatively evaluate segmentation, skeletonisation, and plant-trait extraction algorithms for 3D plant phenotyping4TU.researc... by Bart M. van Marrewijk, Tim van Daalen, Katarína Smoleňová, Bolai Xin, Gerrit Polder, Gert Kootstra

“…To our best knowledge only five annotated datasets exist for testing and validating 3D phenotyping algorithms. However, these datasets mainly focus on the segmentation step. …”
Get full text

State and prospects of basic computer training in engineering education by O. G. Arkhipov

“…This new teaching method has such a «reference point» as fundamental programming concepts «task – method of this task solution – algorithm for solving the task – computer program».The main tasks of the discipline of the basic computer training were defined:– formation of students’ formal logic, algorithmic thinking;– learning of modern technology of structured programming, providing efficient development of algorithms and computer programs;– formation of practical skills of designing algorithms of any complexity;– learning of procedure-oriented programming languages.The article analyzes some negative aspects, related to basic computer training and appeared in the last 15–20 years in the National Research University «Moscow Power Engineering Institute» and other higher technical educational universities of Russia, including:– subjective diluting effect, changing the purpose and content of basic computer training and replacement by the other, «unconvincing» in the content subjects;– lack of a unified program of discipline «Informatics» for higher technical educational institutions of Russia;– lack of understanding of the specificity of very intensive work of lecturers, conducting such training, and the underestimation of their labor;– insufficient current level of initial computer training for the secondary school graduates;– lack of methodological interaction of higher technical educational universities of Russia among themselves and with the secondary school on basic computer training.The article emphasizes that the basic computer training in engineering education in Russia will be in perspective realized in its classic historical sense of the word, if the qualified engineers, who are able to think logically and resolve efficiently any professional tasks, will be necessary for the country as before.…”
Get full text

Novel NFA engine construction method of regular expressions by Mao-hua JING, Yi-xian YANG, Tao WANG, Yang XIN

“…A novel method for constructing smaller non-deterministic finite automata (NFA) engine from given regular expressions named PFA was proposed.There are three main algorithms in PFA,the pretreatment algorithm,the coding parser tree algorithm and the NFA construction algorithm based on the coded binary tree.The smaller NFA named NFA_p with only one start state and one final state can be obtained by using PFA construction method.NFA_phave linear size in terms of the size of given regular expressions.It is the smallest NFA comparing with current methods like Thompson NFA,follow automata,position automata and partial derivatives automata.The size of NFA_pis one third of Thompson’s and it is smaller than the size of follow automata whose size has nearly closed to optimal.…”
Get full text

Successive Refinement for Lossy Compression of Individual Sequences by Neri Merhav

Get full text