检索结果-内蒙古大学图书馆

3rd International Conference on Language Processing and Knowledge Management, LPKM 2024

作者： Turki, Houcemeddine Ellouze, Kawthar Ben Ammar, Hager Hadj Taieb, Mohamed Ali Adel, Imed Ben Aouicha, Mohamed Farri, Pier Luigi Bennour, Abderrezak Data Engineering and Semantics Research Unit University of Sfax Sfax Tunisia Association Derja Tunis Tunisia University of Sousse Sousse Tunisia VBScuola Rome Italy

ISBN: (纸本)9783031850660

Tunisian Arabic (ISO 693-3: aeb) is a distinct variety native to Tunisia, derived from Arabic and enriched by various historical influences. This research introduces the "Normalized Orthography for Tunisian Arabic" (NOTA), an adaptation of CODA* guidelines for transcribing Tunisian Arabic using Arabic script. The aim is to enhance language resource development by ensuring user-friendliness and consistency. The updated standard addresses challenges in accurately representing Tunisian phonology and morphology, correcting issues from transcriptions based on Modern Standard Arabic. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Arabic Script Normalization Orthography Tunisian

来源：评论

学校读者我要写书评

暂无评论

Oil Palm Particleboard: Properties and Fungi Susceptibility

引用

Journal of Renewable Materials 2025年第1期13卷 163-180页

作者： Nur Azreena Idris Madihah Ahmad Zairun Aisyah Humaira Alias Zawawi Ibrahim Noorshamsiana Abdul Wahab Biomass Technology Unit Engineering and Processing DivisionMalaysian Palm Oil BoardNo.6Persiaran InstitusiBandar Baru BangiKajang43000Malaysia Plant Pathology&Biosecurity Unit Biology Research Division Malaysian Palm Oil BoardNo.6Persiaran InstitusiBandar Baru BangiKajang43000Malaysia

The utilization of oil palm biomass in the production of high-value products has increased *** to the presence of sugars and starches in their tissues,oil palms have an exceptionally low natural resistance to fungi,making them susceptible to *** this study,the properties of particleboard made from oil palmﬁbers,namely empty fruit bunches(EFB),oil palm trunks(OPT),and oil palm fronds(OPF)ﬁbers and its poten-tial for fungal attack were *** chemical composition,spectroscopic characterization,morphological features,and elemental analysis of oil palm biomassﬁbers were identiﬁed and thoroughly *** mechan-ical properties and dimensional stability of the boards were assessed based on Japanese Industrial Standards(JIS)and American National Standards Institute(ANSI)*** density,strength,and moisture resistance of particleboard made from OPTﬁbers may vary from those made from OPF and EFB due to inherent changes in chemical composition andﬁber *** differences have an impact on the overall performance of the *** on the ANOVA and Tukey’s test results,signiﬁcant differences in elasticity properties were observed mainly between OPT and otherﬁbers,while bending strength revealed notable differences between various pairs of *** evaluation also highlighted variations in dimensional stability and water absorption ***,bending strength properties did not demonstrate any signiﬁcant *** the fungi test,fungal activity on the boards was observed over a two-week period in a controlled *** study revealed that oil palm-based particleboard exhibited susceptibility to fungal attacks,particularly from Aspergillus sp.,Trichoderma sp.,and Paecilomyces ***ﬁndings highlight the necessity for additional treatments to control or prevent fungal growth,thereby enhancing the commercial value of the particleboards.

关键词： Particleboard medium densityﬁberboard(MDF) empty fruit bunches(EFB) oil palm trunks(OPT) and oil palm fronds(OPF)

来源：评论

学校读者我要写书评

暂无评论

Patch-based Deep-learning Model with Limited Training Dataset for Liver Tumor Segmentation in Contrast-enhanced Hepatic Computed Tomography

引用

IEEE Access 2025年 13卷 86863-86873页

作者： Yang, Yuqiao Sato, Muneyuki Jin, Ze Suzuki, Kenji Institute of Science Tokyo School of Engineering Biomedical Artificial Intelligence Research Unit (BMAI) Institute of Integrated Research & Department of Information and Communications Engineering Tokyo Japan

The automatic segmentation of liver tumors plays an important role in the diagnosis and treatment of liver cancer. While deep convolutional neural network (DCNN) models are widely used for segmentation tasks in medical imaging, they require 1,000 to 10,000 annotated cases for effective training. However, assembling datasets of this size is a significant challenge due to the labor-intensive nature of tumor annotation, which often requires the expertise of radiologists. We propose a multi-scale Hessian-enhanced patch-based neural network, which we call an MHP-Net, for liver tumor segmentation with a limited dataset. Our approach involves sampling 3D patches from the input images for training a neural network, rather than using all input images, which are commonly used in DCNN training. We applied a multi-scale Hessian ellipsoid enhancer to extract multi-scale features of the liver tumor. We implemented a region-stratified sampling strategy to prevent overfitting in patch-based neural network training. We evaluated the effectiveness of our model using a dataset from the Liver Tumor Segmentation Benchmark. To investigate the performance of the model under limited sample-size conditions, we trained it and state-of-the-art (SOTA) deep learning models with 7, 14, and 28 tumors. Our model achieved average Dice scores of 0.691, 0.709, and 0.719 which were higher than those ranging between 0.395 and 0.641 with the SOTA models. Remarkably, our model also achieved a Dice score (0.709) on par with the top model (0.702) in the MICCAI 2017 worldwide competition, despite utilizing only 1.5% (14 out of 908 tumors) of the training data. © 2013 IEEE.

关键词： Artificial Intelligence Deep Learning Liver Tumor Segmentation Medical Image Analysis Small-data AI

来源：评论

学校读者我要写书评

暂无评论

Bearing capacity prediction of open caissons in two-layered clays using five tree-based machine learning algorithms

Intelligent Geoengineering

引用

Intelligent Geoengineering 2025年第2期2卷 55-65页

作者： Rungroad Suppakul Kongtawan Sangjinda Wittaya Jitchaijaroen Natakorn Phuksuksakul Suraparb Keawsawasvong Peem Nuaklong Research Unit in Sciences and Innovative Technologies for Civil Engineering Infrastructures Department of Civil Engineering Faculty of Engineering Thammasat School of Engineering Thammasat University Pathum Thani 12120 Thailand

Open caissons are widely used in foundation engineering because of their load-bearing efficiency and adaptability in diverse soil conditions. However, accurately predicting their undrained bearing capacity in layered soils remains a complex challenge. This study presents a novel application of five ensemble machine (ML) algorithms—random forest (RF), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), and categorical boosting (CatBoost)—to predict the undrained bearing capacity factor ( N c ) of circular open caissons embedded in two-layered clay on the basis of results from finite element limit analysis (FELA). The input dataset consists of 1188 numerical simulations using the Tresca failure criterion, varying in geometrical and soil parameters. The FELA was performed via OptumG2 software with adaptive meshing techniques and verified against existing benchmark studies. The ML models were trained on 70 % of the dataset and tested on the remaining 30 %. Their performance was evaluated using six statistical metrics: coefficient of determination ( R² ), mean absolute error ( MAE ), root mean squared error ( RMSE ), index of scatter ( IOS ), RMSE-to-standard deviation ratio ( RSR ), and variance explained factor ( VAF ). The results indicate that all the models achieved high accuracy, with R² values exceeding 97.6 % and RMSE values below 0.02. Among them, AdaBoost and CatBoost consistently outperformed the other methods across both the training and testing datasets, demonstrating superior generalizability and robustness. The proposed ML framework offers an efficient, accurate, and data-driven alternative to traditional methods for estimating caisson capacity in stratified soils. This approach can aid in reducing computational costs while improving reliability in the early stages of foundation design.

关键词： Two-layered clay Open caisson Tree-based algorithms FELA Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Adaptive Dead-Time Control Method for GaN-Based Motor Drives

引用

IEEE Transactions on Energy Conversion 2025年第1期40卷 258-269页

作者： Qin, Haihong Zheng, Xiaoxue Wang, Wenlu Xun, Qian Nanjing University of Aeronautics and Astronautics Department of Electrical Engineering Nanjing210016 China Nanjing University of Aeronautics and Astronautics Center for More-Electric-Aircraft Power System Nanjing210016 China RISE Research Institutes of Sweden Unit of Energy Conversion Borås50462 Sweden

Compared to Si devices, Gallium Nitride (GaN) devices are more suitable for achieving high switching frequency in motor drive applications, thereby improving power density. However, increasing switching frequency can also lead to extra switching losses and poor total harmonic distortion (THD). A smaller dead-time can mitigate these issues, but conventional constant dead-time design methods struggle to ensure optimal performance across all load ranges. This paper proposes a novel adaptive dead-time control method for GaN high electron mobility transistors (HEMTs) in phase-legs to simultaneously enhance the efficiency and THD of motor drives. To achieve this, the detailed switching process of GaN HEMTs in a double-pulse test circuit is modeled and analyzed. The optimization principle of the dead-time setting is revealed, considering the tradeoff effect of dead-time on switching losses and THD. The adaptive dead-time control method dynamically adjusts the dead-time under different load conditions. The effectiveness of the proposed method is verified on a 1 kW GaN-based permanent magnet synchronous machine drive platform. Extensive experimental results show that the proposed method can increase efficiency up to 0.85% at full load with a switching frequency of 100 kHz compared to constant dead-time. Meanwhile, THD is reduced by 1.44% under the same condition. © 1986-2012 IEEE.

关键词： Threshold voltage

来源：评论

学校读者我要写书评

暂无评论

Long-read sequencing reveals novel genetic polymorphisms in the major histocompatibility complex region and their impacts on the Han Chinese population

引用

Science China Life Sciences 2025年第5期68卷 1400-1409页

作者： Cong Zhou Tingting Gong Shuhang Li Li Jin Shaohua Fan State Key Laboratory of Genetic Engineering Lab for Evolutionary SynthesisSchool of Life SciencesHuman Phenome InstituteFudan University Research Unit of Dissecting the Population Genetics and Developing New Technologies for Treatment and Prevention of Skin Phenotypes and Dermatological Diseases (2019RU058) Chinese Academy of Medical Sciences

Human leukocyte antigen(HLA) genes in the major histocompatibility complex(MHC) region are crucial for immunity and are associated with numerous diseases and phenotypes. The MHC region's complexity and high genetic diversity make it challenging to analyze using short-read sequencing(SRS) technology. We sequence the MHC region of 100 Han Chinese individuals using both long-read sequencing(LRS) and SRS platforms at approximately 30X coverage to study genetic alterations and their potential functional impacts. LRS provides significantly greater coverage of the MHC region and eight classical HLA genes, particularly at the HLA-DRB1 locus, compared with SRS. We detect 78,249 single nucleotide polymorphisms(SNPs) using LRS, with 26.0% undetectable by SRS. Based on SNP and inferred HLA allele types, we construct an LRS-based MHC reference panel for the Han Chinese, containing approximately 2.6 times more genetic variants than the SRS-based Han-MHC reference panel. A phenome-wide association study assessing 26,024 phenotypes across 15 categories identifies significant associations for 7,879 independent variants(including 809 LRS-specific SNPs) with 409 phenotypes in nine categories. This analysis reveals 24 unreported HLA allele associations in the bioelectric and cellular categories. The conditional analysis identifies 530 independent signals across the 409 phenotypes, including 28 previously unreported signals of eight classical HLA genes associated with 33 phenotypes. Of the top-associated SNPs, 191 are detected by LRS only. Fine-mapping identifies 126 independent candidate causal SNPs for three immune-related cellular phenotypes, with 17 detected exclusively by LRS. Our study reveals previously unreported variants and their functional impacts in the MHC region, enhancing our understanding of genetic diversity and its potential biological implications in the Han Chinese population.

关键词： long-read sequencing major histocompatibility complex region HLA typing genetic diversity phenome-wide association study

来源：评论

学校读者我要写书评

暂无评论

Enhancing malware detection performance: leveraging K-Nearest Neighbors with Firefly Optimization Algorithm

引用

Multimedia Tools and Applications 2025年第12期84卷 10071-10094页

作者： Al Saaidah, Adeeb Abualhaj, Mosleh M. Shambour, Qusai Y. Abu-Shareha, Ahmad Adel Abualigah, Laith Al-Khatib, Sumaya N. Alraba’nah, Yousef H Department of Networks and Cybersecurity Al-Ahliyya Amman University Amman Jordan Department of Software Engineering Al-Ahliyya Amman University Amman Jordan Department of Data Science and Artificial Intelligence Al-Ahliyya Amman University Amman Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Research Center University of Tabuk Tabuk71491 Saudi Arabia MEU Research Unit Middle East University Amman11831 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon College of Engineering Yuan Ze University Taoyuan32003 Taiwan Applied Science Research Center Applied Science Private University Amman11931 Jordan School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia

Malware detection plays a crucial role in ensuring robust cybersecurity amidst the ever-evolving cyber threats. This research paper delves into the realm of machine learning (ML) algorithms for malware detection, with a specific emphasis on the K-Nearest Neighbors (KNN) algorithm, utilizing tailored parameter settings and the Firefly Optimization Algorithm (FOA). The study leverages the MalMem-2022 dataset to assess the efficacy of KNN and KNN with FOA in malware detection. The impact of parameter tuning and feature selection on classification is elucidated by comparing the performance of both approaches. Encouragingly, the results reveal promising advancements in one of the multiclass classification scenarios when employing KNN with FOA, yielding noteworthy enhancements in Accuracy, Recall, Precision, Matthews Correlation Coefficient, TNR, and F1-score by 2.65%, 2.65%, 2.47%, 3.59%, 0.17%, and 2.61%, respectively. These findings accentuate the significance of optimizing KNN’s parameters and implementing FOA for feature selection, culminating in heightened accuracy in malware detection. The symbiotic fusion of KNN and FOA exhibits remarkable effectiveness in augmenting the classification model’s performance, thus offering valuable insights for bolstering cybersecurity measures. Adopting ML algorithms, particularly KNN with specific parameter settings and FOA, presents a promising avenue for enhancing malware detection capabilities. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Demonstration of the High Efficiency of an Air Plasma Jet Combining Electric Field and RONS in the Treatment of Chronic Wounds

引用

IEEE Transactions on Radiation and Plasma Medical Sciences 2025年第5期9卷 680-688页

作者： Daniel Cortazar, Osvaldo Megia-Macias, Ana Hontanilla, Bernardo Cortazar-Gallicchio, Hernan Comillas Pontifical University Superior Industrial School of Engineering Mechanical Engineering Department Madrid28840 Spain Superior Industrial School of Engineering Institute of Technological Research Comillas Pontifical University Mechanical Engineering Department Madrid28840 Spain Clinica Universidad de Navarra Department of Plastic and Reconstructive Surgery Pamplona31008 Spain Multiprofessional Teaching Unit of Mental Health of the University Hospital Complex Insular Materno-Infantil Canary Health Service Las Palmas de Gran Canaria35016 Spain

A cold atmospheric air plasma jet (CAAPJ) for the treatment of skin injuries in medicine and veterinary medicine is presented with experimental evidence that point to the electric field inside the plasmas jet could be a determinant therapeutic mechanism. The device is characterized by producing a CAAPJ compatible with living tissues at a low-heat transfer rate with a temperature on the skin surface below 40 °C. It has a practical design to be used by physicians and veterinaries during daily practice, with a special focus on the treatment of skin injuries and unhealed ulcers. Plasma diagnostics, including currents-voltage signals, UV-VIS spectroscopy, IR images of the skin, and electric field measurements in the air cold plasma jet, are presented. The last is made for the first time in this type of plasma, and them can justify the induction of local electric currents on the wound surface to accelerate healing by highlighting the possible synergy with reactive oxygen and nitrogen species (RONSs) as a decontaminant agent for bacteria (including resistant), fungi and viruses without damaging healthy tissue. A remarkable clinical case study example is reported. © 2017 IEEE.

关键词： Veterinary medicine

来源：评论

学校读者我要写书评

暂无评论

Analysis of the gap between self-reported and actual pro-environmental behaviors of hotel customers

Consumer Behavior in Tourism and Hospitality

引用

Consumer Behavior in Tourism and Hospitality 2025年第1期20卷 88-103页

作者： Sousa, Natalina Eusébio, Celeste Paço, Arminda School of Economics and Management University of Minho Braga Portugal Department of Economics Management Industrial Engineering and Tourism Research Unit on Governance Competitiveness and Public Policies (GOVCOPP) University of Aveiro Aveiro Portugal Research Centre for Business Sciences (UIDB/04630/2020) University of Beira Interior Covilhã Portugal

Purpose: This paper aims to explore customers’ pro-environmental behaviors (PEBs) adopted at hotels that implement green practices. A method to examine the gap between self-reported and actual PEBs is presented. Design/methodology/approach: The empirical study is divided in two parts. The first one comprised a survey questionnaire administered to 136 customers who stayed in Portuguese hotels (Sample 1). The second one consisted of 495 in-room consumer PEBs observations (Sample 2). A method was developed to compare self-reported and actual PEBs, combining the answers given to the questionnaire and the observed PEBs implemented by customers during their stay. The aggregate observations of in-room consumer’s PEBs enabled the development of an index to assess the actual PEBs (ACTUALPEBI). This index was then compared with the self-reported PEB index (REPORTEDPEBI). Findings: The majority of guests indicated adopting environmentally friendly practices while at the hotel, and 50% of REPORTEDPEBI rank similarly to ACTUALPEBI. research limitations/implications: Understanding and measuring both actual and reported PEBs of guests offers valuable insights for hotel managers and marketers. This information can be used to target specific consumer segments with green marketing campaigns and develop educational programs that effectively encourage guest participation in hotel sustainability efforts. While the survey participants were international, the research itself was limited to hotels in Portugal. Therefore, future research should involve more participants and be conducted across different countries. Practical implications: Understanding and measuring both actual and reported PEBs of guests offers valuable insights for hotel managers and marketers. This information can be used to target specific consumer segments with green marketing campaigns and develop educational programs that effectively encourage guest participation in hotel sustainability efforts. Originality/value: Thi

关键词： Field research Hotel customer Hotel environmental practices Methodology Pro-environmental behavior

来源：评论

学校读者我要写书评

暂无评论

Resilience in Online Federated Learning: Mitigating Model-Poisoning Attacks via Partial Sharing

引用

IEEE Transactions on Signal and Information Processing over Networks 2025年 11卷 388-400页

作者： Lari, Ehsan Arablouei, Reza Gogineni, Vinay Chakravarthi Werner, Stefan Commonwealth Scientific and Industrial Research Organisation PullenvaleQLD4069 Australia University of Southern Denmark Applied AI and Data Science Unit The Maersk Mc-Kinney Moller Institute Faculty of Engineering Odense5230 Denmark Norwegian University of Science and Technology Department of Electronic Systems Trondheim7034 Norway Aalto University Department of Information and Communications Engineering Espoo02150 Finland

Federated learning (FL) allows training machine learning models on distributed data without compromising privacy. However, FL is vulnerable to model-poisoning attacks where malicious clients tamper with their local models to manipulate the global model. In this work, we investigate the resilience of the partial-sharing online FL (PSO-Fed) algorithm against such attacks. PSO-Fed reduces communication overhead by allowing clients to share only a fraction of their model updates with the server. We demonstrate that this partial sharing mechanism has the added advantage of enhancing PSO-Fed's robustness to model-poisoning attacks. Through theoretical analysis, we show that PSO-Fed maintains convergence even under Byzantine attacks, where malicious clients inject noise into their updates. Furthermore, we derive a formula for PSO-Fed's mean square error, considering factors like stepsize, attack probability, and the number of malicious clients. Interestingly, we find a non-trivial optimal stepsize that maximizes PSO-Fed's resistance to these attacks. Extensive numerical experiments confirm our theoretical findings and showcase PSO-Fed's superior performance against model-poisoning attacks compared to other leading FL algorithms. © 2015 IEEE.

关键词： Federated learning

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：