Results 61 to 70 of about 6,757 (229)

A Real-Time Automatic Kurdistan Numberplate Recognition System

Eurasian Journal of Science and Engineering, 2022
The current paper presents a real-time implementation of a numberplate recognition system for Kurdistan region of Iraq. Automatic numberplate recognition systems (ANPR) have played a key role in many places in enforcing regulations on safe driving and ...
Abubakar M. Ashir
doaj   +1 more source

Knowledge Graph for Methane Selective Conversion: Revisiting and Predicting Product Selectivity and Methane Conversion

Advanced Science, Volume 12, Issue 48, December 29, 2025.
With the help of large language models, deep neural network learning, and kinetic calculation, a knowledge graph prediction of prior research in methane conversion is conducted. This knowledge graph provides a comprehensive understanding of the relationships among catalyst materials, catalytic performance, and reaction conditions, providing guidance ...
Boyu Xu, Gaoyang Li, Bohan Wang, Jiawei Bian, Hui Pan, Yulin Min, Guodong Qi, Jun Xu, Feng Deng, Feng Ju, Hao Ling, Zhendong Wang   +11 more
wiley   +1 more source

A Computer Algorithm For Engineering Off-Shell Multiplets With Four Supercharges On The World Sheet [PDF]

, 2012
We present an adinkra-based computer algorithm implemented in a Mathematica code and use it in a limited demonstration of how to engineer off-shell, arbitrary N-extended world-sheet supermultiplets.
Burghardt, K., Gates Jr, S. J.
core  

Advertisement Image Classification—Visual (RESNET) Versus Textual (BERT) Features: An Experimental Study

Engineering Reports, Volume 7, Issue 12, December 2025.
This experimental study compares Visual features with Textual features for advertisement image classification and reveals that for Advertisement Images, Textual Features provide superior image understanding, resulting in significantly higher classification accuracies (96.88% to 97.37%) as compared to the highest classification accuracy of 71.41 ...
Pooja Jain, Rohini Arora, Kavita Taneja, Harmunish Taneja   +3 more
wiley   +1 more source

Computer vision for Pokémon Battles: A YOLO and Tesseract-Based System for Automated Recognition and Gameplay Analysis

Interfases
Pokémon Double Battles present a complex decision-making environment that has traditionally relied on manual data analysis. This paper introduces an automated system leveraging computer vision and deep learning to extract structured gameplay data from ...
Miguel R. Lladó, Terence Morley
doaj   +1 more source

Identifying Going Concern Audit Opinions Using Supervised Machine Learning

Intelligent Systems in Accounting, Finance and Management, Volume 32, Issue 4, December 2025.
ABSTRACT This paper evaluates the use of supervised machine learning to automatically identify going concern–modified audit reports. Models based on two different classifiers—logistic regression and extreme gradient boosting—achieve strong classification performance for this task.
Dennis Hedback
wiley   +1 more source

A Diagram Is Worth A Dozen Images

, 2016
Diagrams are common tools for representing complex concepts, relationships and events, often when it would be difficult to portray the same information with natural images.
B Alexe, CL Zitnick, F Pedregosa, J von Engelhardt, JRR Uijlings, M Twyman, R Horn, R Koncel-Kedziorski, RK Srihari, RW Ferguson, S Antol, S Hochreiter, SC Zhu, SK Card   +13 more
core   +1 more source

The Future of AI in the GCC Post‐NPM Landscape: A Comparative Analysis of Kuwait and the UAE

Politics &Policy, Volume 53, Issue 6, December 2025.
ABSTRACT Comparative evidence of how two Gulf Cooperation Council (GCC) states translate artificial intelligence (AI) ambitions into post–New Public Management (post‐NPM) outcomes are scarce because most studies focus on Western democracies. To fill this gap, we examine constitutional, collective choice, and operational rules that shape AI uptake in ...
Mohammad Rashed Albous, Bedour Alboloushi, Arnaud Lacheret   +2 more
wiley   +1 more source

ДОСЛІДЖЕННЯ СУМІСНОГО ВИКОРИСТАННЯ МАТЕМАТИЧНОЇ МОРФОЛОГІЇ ТА ЗГОРТКОВИХ НЕЙРОННИХ МЕРЕЖ ДЛЯ ВИРІШЕННЯ ЗАДАЧІ РОЗПІЗНАВАННЯ ЦІННИКІВ

Вісник Національного технічного університету "ХПÌ": Системний аналіз, управління та інформаційні технології, 2020
Робота присвячена вирішенню задачі розпізнавання зображень, що містять інформацію символьного типу, штрих коди, логотипи, або інші знаки. Прикладом таких зображень є цінники в торговельних центрах, флаєра, запрошення, білети на різні заходи.
Andrii Kovtunenko, Olena Yakovleva, Valentyn Liubchenko, Olha Yanholenko   +3 more
doaj   +1 more source

Automating Data Extraction From Scientific Literature and General PDF Files Using Large Language Models and KNIME: An Application in Toxicology

WIREs Computational Molecular Science, Volume 15, Issue 5, September/October 2025.
This study presents an innovative automated KNIME workflow that integrates document parsing tools and large language models (LLMs) to streamline the extraction of key data from publications. Demonstrating high accuracy, the method enhances data processing efficiency and access, thereby supporting advancements in toxicological research and beyond ...
José Teófilo Moreira‐Filho, Dhruv Ranganath, Ricardo S. Tieghi, Robert Patton, Vicki Sutherland, Charles Schmitt, Andrew A. Rooney, Jennifer Fostel, Vickie R. Walker, Trey Saddler, David Reif, Kamel Mansouri, Nicole Kleinstreuer   +12 more
wiley   +1 more source