检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Aydın, Ömer Karaarslan, Enis Erenay, Fatih Safa Džakula, Nebojša Bačanin Manisa Celal Bayar University Faculty of Engineering and Natural Sciences Department of Computer Sciences Manisa Turkey University of Waterloo Faculty of Engineering Management Science and Engineering Ontario Canada Mugla Sitki Kocman University Faculty of Engineering Department of Computer Engineering Mugla Turkey Singidunum University Faculty of Informatics and Computing Belgrade Serbia

Deepseek and Qwen LLMs became popular at the beginning of 2025 with their low-cost and open-access LLM solutions. A company based in Hangzhou, Zhejiang, China, announced its new LLM, DeepSeek v3, in December 2024. Then, Alibaba released its AI model, Qwen 2.5 Max, on January 29, 2025. These tools, which are free and open-source have made a significant impact on the world. Deepseek and Qwen also have the potential to be used by many researchers and individuals around the world in academic writing and content creation. Therefore, it is important to determine the capacity of these new LLMs to generate high-quality academic content. This study aims to evaluate the academic writing performance of both Qwen 2.5 Max and DeepSeek v3 by comparing these models with popular systems such as ChatGPT, Gemini, Llama, Mistral, and Gemma. In this research, 40 articles on the topics of Digital Twin and Healthcare were used. The method of this study involves using generative AI tools to generate texts based on posed questions and paraphrased abstracts of these 40 articles. Then, the generated texts were evaluated through the plagiarism tool, AI detection tools, word count comparisons, semantic similarity tools and readability assessments. It was observed that plagiarism test result rates were generally higher for the paraphrased abstract texts and lower for the answers generated to the questions, but both were above acceptable levels. In the evaluations made with the AI detection tool, it was determined with high accuracy that all the generated texts were detected as AI-generated. In terms of the generated word count comparison, it was evaluated that all chatbots generated satisfactory amount of content. Semantic similarity tests show that the generated texts have high semantic overlap with the original texts. The readability tests indicated that the generated texts were not sufficiently readable. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Odd Cycle Transversal on P5-free Graphs in Polynomial Time

引用

ACM Transactions on Algorithms 2025年第2期21卷 1-14页

作者： Akanksha Agrawal Paloma T. Lima Daniel Lokshtanov Paweł Rzążewski Saket Saurabh Roohani Sharma Indian Institute of Technology Madras Chennai India IT University of Copenhagen Copenhagen Denmark UCSB Santa Barbara CA USA Warsaw University of Technology Faculty of Mathematics and Information Science Warszawa Poland and University of Warsaw Institute of Informatics Warszawa Poland Theoretical Computer Science Group The Institute of Mathematical Sciences Chennai India Department of Informatics University of Bergen Bergen Norway

An independent set in a graph \(G\) is a set of pairwise non-adjacent vertices. A graph \(G\) is bipartite if its vertex set can be partitioned into two independent sets. In the Odd Cycle Transversal problem, the input is a graph \(G\) along with a weight function w associating a rational weight with each vertex, and the task is to find a minimum weight vertex subset \(S\) in \(G\) such that \(G-S\) is bipartite; the weight of \(S\), \(\text{w}(S)=\sum_{v\in S}\text{w}(v)\). We show that Odd Cycle Transversal is polynomial-time solvable on graphs excluding \(P_{5}\) (a path on five vertices) as an induced subgraph. The problem was previously known to be polynomial-time solvable on \(P_{4}\)-free graphs and NP-hard on \(P_{6}\)-free graphs [Dabrowski, Feghali, Johnson, Paesani, Paulusma and Rzążewski, Algorithmica 2020]. Bonamy, Dabrowski, Feghali, Johnson and Paulusma [Algorithmica 2019] posed the existence of a polynomial-time algorithm on \(P_{5}\)-free graphs as an open problem. This was later re-stated by Rzążewski [Dagstuhl Reports, 9(6): 2019], by Chudnovsky, King, Pilipczuk, Rzążewski, and Spirkl [SIDMA 2021] who gave an algorithm with running time \(n^{O(\sqrt{n})}\) for the problem, and by Agrawal, Lima, Lokshtanov, Saurabh, and Sharma [SODA 2024] who gave a quasi-polynomial time algorithm.

关键词： Odd Cycle Transversal special graph classes P5-free graphs independent set polynomial time

来源：评论

学校读者我要写书评

暂无评论

FLTrans-Net: Transformer-based feature learning network for wheat head detection

引用

computers and Electronics in Agriculture 2025年 229卷

作者： Yousafzai, Samia Nawaz Nasir, Inzamam Mashood Tehsin, Sara Fitriyani, Norma Latif Syafrudin, Muhammad Department of Computer Science HITEC University Taxila Taxila Pakistan Seoul05006 Korea Republic of Faculty of Informatics Kaunas University of Technology Kaunas51368 Lithuania Department of Artificial Intelligence and Data Science Sejong University Seoul05006 Korea Republic of

The accurate identification of wheat heads is critical for assessing production and managing agricultural fields effectively. One major challenge lies in detecting overlapping and small wheat spikes amidst complex backgrounds. Recent advancements in deep learning, specifically Convolutional Neural Networks (CNNs), have been employed to address this challenge. However, conventional CNNs often struggle with capturing global interdependencies due to their focus on local features and limited scale invariance. To overcome these limitations, this study proposes a Transformer-based Feature Learning Network (FLTrans-Net). FLTrans-Net aims to learn discriminative features while reducing background noise. The methodology comprises three key components: a Multi-Scale Fusion Block, a Spatial Attention Block, and a Lightweight RetinaNet Detection Block. The Multi-Scale Fusion Block integrates high-scale and low-scale features to extract multi-scale representations, essential for detecting small-sized wheat heads in complex backgrounds. The Spatial Attention Block utilizes transformer encoders to highlight salient object characteristics, enhancing the model's performance. Additionally, a Lightweight RetinaNet Detection Block is incorporated to capture potentially valuable features extracted by preceding blocks. Experimental results demonstrate FLTrans-Net's effectiveness in wheat head detection in challenging field environments, indicating its potential for real-time deployment on resource-constrained devices. Overall, FLTrans-Net represents a significant advancement in wheat head detection, offering both efficacy and efficiency in handling complex agricultural landscapes. © 2024 Elsevier B.V.

关键词： Light-weight Detection Multi-Scale Fusion Spatial Attention Transformer Wheat Head Detection

来源：评论

学校读者我要写书评

暂无评论

Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation

arXiv

引用

arXiv 2025年

作者： Thillainathan, Sarubi Yuan, Songchen Lee, En-Shiun Annie Jayasena, Sanath Ranathunga, Surangika Department of Computer Science and Engineering University of Moratuwa Sri Lanka Department of Language Science and Technology Saarland Informatics Campus Saarland University Germany Department of Computer Science University of Toronto Canada Faculty of Science University of Ontario of Technology Canada School of Mathematical and Computational Sciences Massey University New Zealand

Fine-tuning multilingual sequence-to-sequence large language models (msLLMs) has shown promise in developing neural machine translation (NMT) systems for low-resource languages (LRLs). However, conventional single-stage fine-tuning methods struggle in extremely low-resource NMT settings, where training data is very limited. This paper contributes to artificial intelligence by proposing two approaches for adapting msLLMs in these challenging scenarios: (1) continual pre-training (CPT), where the msLLM is further trained with domain-specific monolingual data to compensate for the under-representation of LRLs, and (2) intermediate task transfer learning (ITTL), a method that fine-tunes the msLLM with both in-domain and out-of-domain parallel data to enhance its translation capabilities across various domains and tasks. As an application in engineering, these methods are implemented in NMT systems for Sinhala, Tamil, and English (six language pairs) in domain-specific, extremely low-resource settings (datasets containing fewer than 100,000 samples). Our experiments reveal that these approaches enhance translation performance by an average of +1.47 bilingual evaluation understudy (BLEU) score compared to the standard single-stage fine-tuning baseline across all translation directions. Additionally, a multi-model ensemble further improves performance by an additional BLEU score. © 2025, CC BY.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

PERFECT STATE TRANSFER ON GCD-GRAPHS OVER A FINITE FROBENIUS RING, I: GENERAL THEORY AND RESULTS FOR LOCAL RINGS

arXiv

引用

arXiv 2025年

作者： Nguyen, Tung T. Tân, Nguyen Duy Department of Mathematics and Computer Science Lake Forest College Lake ForestIL United States Faculty Mathematics and Informatics Hanoi University of Science and Technology 1 Dai Co Viet Road Hanoi Viet Nam

The existence of perfect state transfer (PST) on quantum spin networks is a fundamental problem in mathematics and physics. Various works in the literature have explored PST in graphs with arithmetic origins, such as gcd-graphs over Z and cubelike graphs. In this article, building on our recent work on gcd-graphs over an arbitrary finite Frobenius ring, we investigate the existence of PST on these graphs. Our approach is algebraic in nature, enabling us to unify various existing results in the literature. © 2025, CC BY.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

ON GCD-GRAPHS OVER FINITE RINGS

arXiv

引用

arXiv 2025年

作者： Nguyen, Tung T. Tân, NGUYêN DUY Department of Mathematics and Computer Science Lake Forest College Illinois Lake Forest United States Faculty Mathematics and Informatics Hanoi University of Science and Technology 1 Dai Co Viet Road Hanoi Viet Nam

Gcd-graphs represent an interesting and historically important class of integral graphs. Since the pioneering work of Klotz and Sander, numerous incarnations of these graphs have been explored in the literature. In this article, we define and establish some foundational properties of gcd-graphs defined over a general finite commutative ring. In particular, we investigate the connectivity and diameter of these graphs. Additionally, when the ring is a finite symmetric Z /n-algebra, we give an explicit description of their spectrum using the theory of Ramanujan sums that gives a unified treatment of various results in the literature. © 2025, CC BY.

关键词： Choquet integral

来源：评论

学校读者我要写书评

暂无评论

LSTM and CNN hybrid model for enhanced fingerprint recognition

Emerging Trends in Drugs, Addictions, and Health

引用

Emerging Trends in Drugs, Addictions, and Health 2025年 5卷 100174-100174页

作者： Sameer, Nahla Abdulnabee Nema, Bashar M. Informatics Institute for Postgraduate Studies Information Technology & Communications University Baghdad Iraq Department of Computer Science Faculty of Sciences Mustansiriyah University Baghdad Iraq

The paper introduces an advanced hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to enhance fingerprint detection and matching within large datasets. The CNN component is employed for feature extraction and learning from image data, while the LSTM component is utilized for sequence prediction in temporal series, yielding optimal results compared to existing methods based on specific criteria. This hybrid approach achieves a fingerprint recognition accuracy of 99.85 %. The proposed method effectively reduces errors in recognition and false rejection rates in fingerprint recognition systems, thereby improving overall usability and security. The integration of CNN and LSTM in fingerprint recognition signifies a substantial advancement in biometric authentication technology, with potential applications in law enforcement, border security, and access control systems. © 2025

关键词： Biometric recognition Classification methods CNN Fingerprint forgery detection Image feature engineering LSTM

来源：评论

学校读者我要写书评

暂无评论

Open and Closed Source Models for LLM-Generated Metaheuristics Solving Engineering Optimization Problem

Open and Closed Source Models for LLM-Generated Metaheuris...

引用

28th European Conference on Applications of Evolutionary Computation, EvoApplications 2025, held as part of EvoStar 2025

作者： Senkerik, Roman Viktorin, Adam Kadavy, Tomas Kovac, Jozef Janku, Peter Pekar, Libor Guzowski, Hubert Smolka, Maciej Byrski, Aleksander Pluhacek, Michal A.I.Lab Faculty of Applied Informatics Tomas Bata University Zlin Czech Republic Department of Automation and Control Engineering Faculty of Applied Informatics Tomas Bata University Zlin Czech Republic Faculty of Computer Science AGH University of Krakow Krakow Poland Center of Excellence in Artificial Intelligence AGH University of Krakow Krakow Poland

ISBN: (纸本)9783031900648

This paper explores the applicability of generative AI (genAI), specifically Large Language Models (LLMs), for the automatic generation and configuration of metaheuristic algorithms to address a real-world engineering problem: the optimal parameter estimation of time-delay systems in interconnected heating-cooling loops. The study introduces a pioneering workflow and iterative architecture with feedback within the emerging field of genAI-driven optimization for real optimization problems, eliminating the need for manually crafted or modified algorithms. This automated system empowers domain experts in engineering to solve complex optimization problems with minimal knowledge of optimization algorithms, lowering the barrier to entry for sophisticated algorithm use. We demonstrate how LLMs can generate effective optimizers under conditions like connstrained optimization problems where the solution lies near the boundaries of the search space. Four state-of-the-art LLMs (closed and open-sourced) have been selected for experiments. These are GPT-4o, GPT-4o mini, Claude Sonnet 3.5 and Llama 3.1. All studied LLMs generated metaheuristics that outperformed the initialization baseline optimization method (Random Search and CMA-ES). Notably, the Claude Sonnet 3.5 model generated a metaheuristic with the best mean results, almost matching the performance of the tuned state-of-the-art DISH algorithm, as an example of adaptive Differential Evolution. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Time of arrival

来源：评论

学校读者我要写书评

暂无评论

Comparison of Electronic Prescription Systems in the European Union: Benchmarking Development, Use, and Future Trends

引用

IEEE Journal of Biomedical and Health informatics 2025年第5期29卷 3712-3722页

作者： Bruthans, Jan Duftschmid, Georg Hammar, Tora Kardas, Przemyslaw Bertalan, Lorant Hug, Martin J. Bullow, Cille Muscat, Hugo Agius Lillevali, Anett Jormanainen, Vesa Fernandez-Llimos, Fernando Fidalgo, Luz Karanikas, Haralampos Nyssen, Marc Popescu, Nirvana Cudejkova, Maria Tachkov, Konstantin Hadziabdic, Maja Ortner Neofytou, Marios Dauksiene, Jurgita Huisman, Anneke Ryan, Brid Kasparans, Aris Napoleoni, Matteo Perfili, Mirko Smet, Daisy Calafiore, Matthieu Stanimirovic, Dalibor Czech Technical University in Prague Department of Biomedical Technology Faculty of Biomedical Engineering Prague Czech Republic Medical University of Vienna Section for Medical Information Management Center for Medical Data Science Vienna Austria Linnaeus University eHealth Institute Kalmar Sweden Medical University of Lodz Medication Adherence Research Centre Department of Family Medicine Lodz Poland Semmelweis University Faculty of Health Sciences Budapest Hungary Medical Center-University of Freiburg Pharmacy Freiburg Germany Bispebjerg and Frederiksberg University Hospital Department of Clinical Pharmacology Copenhagen Denmark Ministry for Health and Active Ageing Directorate for Health Information & Research Valletta Malta Estonian Health Insurance Fund Tallinn Estonia University of Helsinki Department of Public Health Faculty of Medicine Helsinki Finland University of Porto Applied Molecular Biosciences Unit Laboratory of Pharmacology Faculty of Pharmacy Porto Portugal Ministry of Health Madrid Spain University of Thessaly Department of Computer Science and Biomedical Informatics Lamia Greece Vrije Universiteit Brussel Department of Public Health Brussel Belgium National University of Science and Technology POLITEHNICA Bucharest Computer Science Department Bucharest Romania National Health Information Centre Bratislava Slovakia Medical University of Sofia Faculty of Pharmacy Sofia Bulgaria University of Zagreb Faculty of Pharmacy and Biochemistry Zagreb Croatia University of Cyprus Electronic Health Laboratory Computer Science Department Nicosia Cyprus Lithuanian University of Health Sciences Drug technology and Social Pharmacy Department Vilnius Lithuania Royal Dutch Pharmacists Association The Hague Netherlands Health Service Executive ePharmacy Programme Dublin Ireland National Health Service of Latvia Riga Latvia GE Healthcare Milan Italy Bambino Gesu' Children's Research Hospital IRCCS Rome Italy Agence eSanté Luxembourg Luxe

While Electronic Prescription Systems (EPS) adoption varies across EU Member States, there's a lack of comprehensive comparative analysis. Existing studies focus on single EPSs, employ diverse methodologies, and lack up-to-date data. This study fills this gap by providing a comprehensive overview of EPS development, functionalities, and usage statistics in each EU Member State. Most EU Member States widely adopted EPS by 2022, with exceptions including Germany, France, and Luxembourg, where pilot projects or just plans existed at that time. Out of the 27 EPSs, 25 employ a similar design featuring a central server and end-user software or web-based applications. Among these, 22 are structured as single national systems. The fundamental technical solution is remarkably similar across the EU. Despite these similarities, functionalities, authentication methods, prescription validity, and medication coverage differ significantly among EPSs. A multinational team, including co-authors from each EU Member State, collected data using a structured questionnaire. The study underscores the need for standardized methodologies in EPS research and emphasizes the importance of comprehensive comparative analysis to inform healthcare policies and digitalization efforts. © 2013 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Weighted Density for The Win: Accurate Subspace Density Clustering

Weighted Density for The Win: Accurate Subspace Density Clus...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Maixuan Peng Yuyang Wu Yang Lu Mengke Li Yiqun Zhang Yiu-Ming Cheung School of Computer Science and Technology Guangdong University of Technology Guangzhou China Faculty of Science Wilfrid Laurier University Brantford Canada Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University Xiamen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science Hong Kong Baptist University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

k-clustering typically struggles with the detection of irregular-distributed clusters due to the natural bias, while density clustering usually cannot well-adapt to different datasets and clustering tasks as it is not an oriented optimization process. This paper, therefore, proposes to perform density clustering in dynamically learned subspaces. To exploit the irregular-distributed clusters obtained by density clustering for the subspace determination, we design a new strategy to appropriately evaluate the importance of attributes. It turns out that the proposed Weighted Density-based Subspace Clustering (WDSC) algorithm inherits the unbiased merits of density clustering, and also upgrades the unlearning density clustering to be learnable under the subspace learning paradigm of k-clustering. A comprehensive evaluation including significance tests, ablation studies, qualitative comparisons, etc., shows the superiority of WDSC.

关键词： Accuracy Heuristic algorithms Signal processing algorithms Clustering algorithms Signal processing Acoustics Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：