检索结果-内蒙古大学图书馆

Effect of Introducing Leucine Residues into 2-Aminoisobutyric Acid-Based Amphiphilic Helical Peptides on Intermolecular Interactions and Peptide Self-Assembly

引用

ACS Omega 2025年第21期10卷 22184-22190页

作者： Kasumi Yamaguchi Tomoichiro Kusumoto Takeshi Araki Yuki Gomibuchi Takuo Yasunaga Satoshi Osada Junichi Taira Department of Chemistry and Applied Chemistry Faculty of Science and Engineering Saga University Saga 840-8502 Japan Department of Bioscience and Bioinformatics Fukuoka 820-8502 Japan Department of Physics and Information Technology Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka 820-8502 Japan

In recent years, self-assembling de novo-designed peptides have attracted increasing attention as materials for constructing submicrometer-scale structures. We have previously conducted structure–activity relationship studies on the BXBA-20 series of 20-residue amphiphilic peptides containing 2-aminoisobutyric acid (Aib) [Higashimoto, Y. et al. (1999)J. Biochem. 125, 705–712; Hara, T. et al. (2001)J. Biochem. 130,749–755; Taira, J. et al. (2010)J. Pept. Sci. 16,607–612]. These peptides share the common sequence Ac-(Aib-Xxx-Aib-Ala)5-NH2, where the introduction of a hydrophilic amino acid at the Xxx position results in the formation of a hydrophilic face on one side of the helix. Among them, some peptides exhibited weak intermolecular association and interactions with lipid membranes, though none demonstrated the ability to form submicrometer-scale structures through self-assembly. In this study, we present BKBL-20, a new member of this peptide series incorporating leucine on the hydrophobic face and lysine on the hydrophilic face. Circular dichroism spectroscopy indicated strong association in buffer, while hemolysis assays revealed significant membrane disruption. Transmission electron microscopy further confirmed the formation of ordered fibrous or array-like structures. These findings suggest that BKBL-20 successfully combines self-assembly and membrane-disruptive functions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bridging research gaps in breast cancer detection: An ensemble approach informed by bibliometric analysis

引用

Biomedical Signal Processing and Control 2025年 109卷

作者： ZainEldin, Hanaa Bamaqa, Amna Farsi, Mohammed Badawy, Mahmoud Elhosseini, Mostafa A. Computers and Control Systems Engineering Department Mansoura University Faculty of Engineering Mansoura35516 Egypt Department of Computer Science and Information Applied College Taibah University Madinah42353 Saudi Arabia Department of Information Systems College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia

One of the leading causes of cancer-related death for women is still breast cancer, which highlights the importance of early and precise diagnosis techniques. Despite medical imaging and deep learning advances, current models fail to combine innovative object identification and classification methods, limiting their diagnostic performance. A bibliometric study of 1145 research articles identified key gaps, including the lack of integration between advanced object detection models like YOLOv9 and YOLOv10 with high-performance classification architectures such as EfficientNet B7, as well as the limited utilization of diverse imaging modalities. This study proposes a novel ensemble model for Breast Cancer Classification and Detection by combining YOLOv9, YOLOv10, and EfficientNet B7 (BC2D-Y/EN) to address these gaps. The proposed model combines the advanced object detection capabilities of YOLOv9 and YOLOv10 with the high-performance classification power of EfficientNet B7. This method aims to improve detection accuracy and computational efficiency in breast cancer identification. The proposed approach is validated using four publicly available datasets: CBIS-DDSM, CBIS-DDSM RGB breast cancer dataset, The Breast1 MRI dataset, and the Breast Ultrasound Tumor Object Detection dataset, all containing expert-annotated cases of benign and malignant tumors. The experimental findings indicate that the suggested model surpasses other models, achieving precision rates of 98.56% with EfficientNet B7, 98.3% with YOLOv9, and 100% with YOLOv9. These findings highlight the advantages of advanced models and diverse imaging methodologies to enhance diagnostic accuracy and effectiveness in breast cancer detection. © 2025 Elsevier Ltd

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Robust speech perception and classification-driven deep convolutional neural network with natural language processing

引用

Alexandria engineering Journal 2025年 123卷 358-368页

作者： Alshammari, Alya Alzaidi, Muhammad Swaileh A. Alrusaini, Othman Alshuhail, Asma Allafi, Randa Yafoz, Ayman Alsini, Raed Khadidos, Alaa O. Department of Applied Linguistics College of Languages Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of English Language College of Language Sciences King Saud University P. O. Box 145111 Riyadh Saudi Arabia Department of Engineering and Applied Sciences Applied College Umm Al-Qura University Makkah Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Department of Computer Science College of Sciences Northern Border University Arar Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

Speech recognition systems use computer algorithms to interpret and process spoken words and translate them into text. Speech-to-text, or Speech detection, is the proficiency of a program or machine to find spoken words aloud and translate them into plain text. Speech detection systems are the most common complex systems that use wide-ranging research in computer engineering, linguistics, and computer science. In today's significant data era, several machine learning (ML) approaches for processing raw, unlabelled speech data still need to be improved. Deep learning (DL) models, on the other hand, with their powerful modelling ability for extensive data, are capable of directly processing unlabelled data and have become a crucial area of research in the domain of automated speech recognition. The DL model has recently gained popularity for voice disorders and automated speech detection. DL is an ML that exploits artificial neural networks (ANN) to gain meaningful insights from data. The DL approach demonstrated great success and achieved significant attention in different fields comprising speech processing, computer vision (CV), and natural language processing (NLP). Therefore, this article develops a Deep Learning with Natural Language Processing based Robust Speech Detection (DLNLP-RSD) technique. The DLNLP-RSD technique derives features from the mel-frequency cepstral coefficient (MFCC) technique. Followed by the DLNLP-RSD technique employs a one-dimensional deep convolutional neural network (CNN) approach for the detection and classification of speech. Moreover, the parameter tuning model uses the grasshopper fractals optimization algorithm (GOA) approach. The performance evaluation of the proposed technique highlights its significant performance over other models concerning distinct measures. An extensive simulation analysis is executed to examine the improved results of the DLNLP-RSD model. The experimental validation of the DLNLP-RSD technique portrayed a sup

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Sustainable energy management in the AI era: a comprehensive analysis of ML and DL approaches

引用

Computing 2025年第6期107卷 1-64页

作者： Javed, Haseeb Eid, Fatma El-Sappagh, Shaker Abuhmed, Tamer Department of Computer Science and Engineering College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of Technology Management Stony Brook University NY11794 United States Applied Artificial Intelligence College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Information Systems Department Faculty of Computers and Artificial Intelligence Benha University Banha13518 Egypt

This study comprehensively analyzes the application of innovative deep learning (DL) and machine learning (ML) techniques in smart energy management systems (EMSs), with an emphasis on load forecasting, demand response, and the development of smart energy sectors. The application of various ML and DL models were examined in over 200 studies from 2014 to 2024 in an electrical network's EMS to highlight the key benefits and advances made by each technology for the sustainable management systems in energy sector. The findings emphasize DL and ML models’ enhanced precision and predictive capabilities in load forecasting, their efficacy in enabling efficient demand response mechanisms, and their significance in supporting the development of smart energy sectors. Furthermore, recommendations are made based on the survey results to assist in incorporating these techniques into EMS frameworks, such as investment in data infrastructure, model training and validation, and collaboration between researchers, industry experts, and policymakers. The study also discusses the limitations identified in the literature, such as limited real-world implementations, challenges regarding quality and data availability, and the need for enhanced ML and DL model interpretability. Addressing these limitations can assist in increasing the application and efficacy of ML and DL techniques in EMSs, enabling a more efficient and sustainable energy landscape. Finally, this study facilitates researchers' exploration of ML and DL in energy management, highlighting relevant limitations, strengths, and alternative approaches associated with sustainable energy management. It also indicates potential future research directions for further investigation. © The Author(s) 2025.

关键词： Power management (telecommunication)

来源：评论

学校读者我要写书评

暂无评论

Aligning Food Ingredients with Multiple Semantic Resources 16th

Aligning Food Ingredients with Multiple Semantic Resources

引用

16th International Conference on ICT Innovations, ICT Innovations 2024

作者： Sasanski, Darko Todorovski, Andrej Trpeski, Bojan Trajanov, Dimitar Eftimov, Tome Stojanov, Riste Faculty of Computer Science and Engineering Ss. Cyril and Methodius University Skopje Macedonia Computer Systems Department Jozef Stefan Institute Ljubljana Slovenia

ISBN: (纸本)9783031861611

To address the lack of integrated resources that combine nutritional, chemical, and semantic information, we have integrated the Recipe1M+ dataset with the USDA National Nutrient Database, FooDB, and the FoodOn ontology. This integration brings significant advantages by enriching the dataset with comprehensive information across multiple domains. By linking Recipe1M+ ingredients to the USDA database, we provide detailed nutritional profiles that enable a comprehensive analysis of recipes, supporting researchers and dietitians in developing personalized nutrition plans based on accurate nutrient data. Furthermore, incorporating FooDB enhances the dataset with in-depth chemical compositions and health effects of food constituents, facilitating research on functional foods and their role in disease prevention and health promotion. Mapping ingredients to FoodOn further expands the dataset’s semantic context, encompassing food products, production, agriculture, and environmental impacts. This integration promotes interdisciplinary research and the creation of comprehensive knowledge graphs, bridging gaps between nutrition, food science, agriculture, and health domains. Our methodology has been validated, demonstrating significantly better results with a precision of 76.25%. Adhering to the FAIR principles, we ensure the data is findable, accessible, interoperable, and reusable. The enriched Recipe1M+ dataset supports advanced applications, such as predictive modeling of dietary impacts, food recommendation systems, and sustainable food system studies, making it a valuable resource for the research community and beyond (The data and code are publicly available at the following link). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Vitamins

来源：评论

学校读者我要写书评

暂无评论

Structural Properties of Non-Linear Cellular Automata: Permutivity, Surjectivity and Reversibility

arXiv

引用

arXiv 2025年

作者： Ramdhane, Firas Ben Dennunzio, Alberto Margara, Luciano Menara, Giuliamaria Department of Informatics Systems and Communications University of Milano-Bicocca Italy Department of Computer Science and Engineering University of Bologna Cesena Italy University of Sfax Faculty of Sciences of Sfax Tunisia

This paper explores the algebraic conditions under which a cellular automaton with a non-linear local rule exhibits surjectivity and reversibility. We also analyze the role of permutivity as a key factor influencing these properties and provide conditions that determine whether a non-linear CA is (bi)permutive. Through theoretical results and illustrative examples, we characterize the relationships between these fundamental properties, offering new insights into the dynamical behavior of non-linear CA. Copyright © 2025, The Authors. All rights reserved.

关键词： Linear algebra

来源：评论

学校读者我要写书评

暂无评论

PrivBox: Privacy-Preserving Deep Packet Inspection with Dual Double-masking Obfuscated Rule Generation

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Wu, Pengfei Ning, Jianting Huang, Xinyi Chen, Rongmao Zhang, Kai Liang, Kaitai Wuhan University School of Cyber Science and Engineering Wuhan China Singapore Management University School of Computing and Information Systems Singapore City University of Macau Faculty of Data Science Macau China Fujian Normal University College of Computer and Cyber Security Fuzhou China Jinan University College of Cyber Security Guangzhou China National University of Defense Technology College of Computer Changsha China Shanghai University of Electric Power College of Computer Science and Technology Shanghai China Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Netherlands

Many network middleboxes have been deployed to perform deep packet inspection (DPI) over packet payloads. However, such middleboxes cannot accomplish their tasks when the traffic is encrypted. BlindBox (SIGCOMM 2015) provided the first solution for performing DPI over encrypted traffic. To improve its efficiency, a later proposal PrivDPI (CCS 2019) introduced a practical technique to generate encrypted rules. However, a recent proposal P2DPI (ASIACCS 2021) showed that the rule generator in PrivDPI can comprise the user's privacy. In this paper, we present a new attack on P2DPI and show that the privacy of its endpoints can still be compromised by the rule generator. We comprehensively analyze the vulnerability of prior studies and present PrivBox, a new DPI system that achieves the same privacy guarantee as BlindBox while maintaining practical efficiency. This is based on a new technique called dual double-masking obfuscated rule generation. For a ruleset of 3,000, PrivBox achieves connection establishment time on the endpoint side comparable to PrivDPI and supports up to 4,672 token encryptions per second, which is sufficient for a number of real-world applications. Overall, our experiment demonstrates that PrivBox is practical and well-suited for short, frequently established sessions, especially when token repeating is common. ©2004-2012 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Addressing Non-stationarity with Stochastic Trend in the Context of Limited Time Series Data: An Experimental Survey

Research Square

引用

Research Square 2025年

作者： Batoure Bamana, Apollinaire Sokdou Bila Lamou, Yannick Fotsa-Mbogne, David Jaures Shafiee Kamalabad, Mahdi Department of Computer Engineering University Institute of Technology The University of Ngaoundere Cameroon Department of Robotic and Industrial Computing School of Chemical Engineering and Mineral Industries The University of Ngaoundere Cameroon Department of Mathematics and Computer Science Faculty of Science The University of Ngaoundere Cameroon Laboratory of Mathematics Computer Science and Applications Department of Mathematics and Computer Science National Higher School of Agro-Industrial Sciences The University of Ngaoundéré Cameroon Laboratory of Mathematics and Computer Science Department of Mathematics Statistics and Computer Science Faculty of Science The University of Bertoua Cameroon Department of Methodology and Statistics Faculty of Social and Behavioural Sciences Utrecht University Utrecht Netherlands Centre for Complex Systems Studies Utrecht University Utrecht Netherlands

Stationarity in time series is a key property for practical data analysis, inferences, and predictions particularly in biosciences. Stationarity can be either deterministic or stochastic. If a time series data is not stationary, it can be rendered stationary through detrending or differentiation techniques. Differentiation can be performed in either an integer or fractional form. This paper investigates non-stationarity in time series data, focusing specifically on stochastic trends characterised by a unit root. It hypothesises that fractional differentiation can enhance forecast accuracy for datasets with limited volume. For experiments, 24 series corresponding to weekly Malaria and Typhoid Fever from Adamawa Region (Cameroon) are analysed and forecasted. Each series comprises 156 observations covering January 2021 to December 2023. After collecting, checking and classifying the data, four forecasting models, Auto Regressive Integrated Moving Average (ARIMA), Fractional ARIMA (ARFIMA), Long Short-Term Memory (LSTM), and the proposed Fractional Differencing and LSTM (FD-LSTM), are implemented. The models' performances are evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of determination (R2) metrics, which inform further analysis and recommendations. Results reveal that ARFIMA outperformed the ARIMA by 93% in training and 100% in testing. Similarly, FD-LSTM achieved a 100% improvement over LSTM in training and testing. These findings underscore the value of achieving stationarity through fractional differentiation, enhancing model performance and providing a robust framework for forecasting in datasets with limited observations. © 2025, CC BY.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Individual Confidential Computing of Polynomials over Non-Uniform Information

arXiv

引用

arXiv 2025年

作者： Tarnopolsky, Saar Deng, Zirui Ramkumar, Vinayak Raviv, Netanel Cohen, Alejandro Faculty of ECE Technion Israel Department of Computer Science and Engineering Washington University in St. Louis St. Louis United States Department of Electrical Engineering–Systems Tel Aviv University Israel

In this paper, we address the problem of secure distributed computation in scenarios where user data is not uniformly distributed, extending existing frameworks that assume uniformity, an assumption that is challenging to enforce in data for computation. Motivated by the pervasive reliance on single service providers for data storage and computation, we propose a privacy-preserving scheme that achieves information-theoretic security guarantees for computing polynomials over non-uniform data distributions. Our framework builds upon the concept of perfect subset privacy and employs linear hashing techniques to transform non-uniform data into approximately uniform distributions, enabling robust and secure computation. We derive leakage bounds and demonstrate that information leakage of any subset of user data to untrusted service providers, i.e., not only to colluding workers but also (and more importantly) to the admin, remains negligible under the proposed scheme. © 2025, CC BY.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Improving the Performance of Job Backfilling Based on Job's Weight and Back Propagation Neural Network

Improving the Performance of Job Backfilling Based on Job's ...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hazem Alnajjar Nadia Al-Rousan Syed Sahal Nazli Alhady Syed Hassan Junita Mohamad-Saleh Department of Computer Science College of Information Technology University of Petra Amman Jordan Department of computer engineering College of Engineering AlBalqa Applied University Salt Jordan Department of Computer Engineering Faculty of Electrical Engineering and Information Systems German Jordanian University Amman Jordan Colleage of Engineering and Architecture School of Electrical & Electronic Engineering Engineering Branch Campus Universiti Sains Malaysia Malaysia

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Nowadays, the grid computing environment faces many difficulties executing new jobs, especially jobs requiring large resource requirements and long execution times. This motivates researchers and scholars to find cheap and fast methods to improve the efficiency of grid environments. One of the cheap and fast methods is to implement job scheduling algorithms based on cheap and fast techniques. This paper proposes a new job ranking backfilling algorithm based on the job's weight and back propagation neural network. To define the weight of the job, first, the proposed model will use a clustering algorithm to cluster the job's dataset into groups, and then the groups will be ranked using an experimental ranking equation. A discrete event simulator is used to validate the proposed algorithm's capability and robustness. The average results revealed that the new algorithm outperforms previous algorithms. The improvement of the studied metrics is between 1.19 and 6.30, respectively. The results proved that the proposed model is efficient and can be used with low overhead in a real environment.

关键词： Backpropagation Measurement Scheduling algorithms Computational modeling Neural networks Clustering algorithms Grid computing Mathematical models Robustness Faces

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：