检索结果-内蒙古大学图书馆

1st International Conference on AI-generated Content, AIGC 2023

作者： Bokolo, Biodoumoye George Onyehanere, Praise Ogegbene-Ise, Ebikela Olufemi, Itunu Tettey, Josiah Nii Armah Department of Computer Science Sam Houston State University HuntsvilleTX77340 United States Department of Architecture Technology and Engineering University of Brighton BrightonBN2 4AT United Kingdom Department of Computer and Software Engineering Kennesaw State University KennesawGA United States Department of Computer Science and Quantitative Methods Austin Peay State University ClarksvilleTN37044 United States Department of Computer Science and Engineering Wright State University DaytonOH45435 United States

ISBN: (纸本)9789819975860

Detecting crime intent from user-generated content on social media platforms has become increasingly important for law enforcement and crime prevention. This paper presents a comprehensive approach for crime intent detection from user tweets using machine learning techniques. The study utilizes a dataset of about 400,000 tweets and applies data preprocessing, feature selection, and model training with logistic regression, ridge regression classifier, Stochastic Gradient Descent (SGD) classifier, Random Forests, and support vector machine models. Evaluation metrics such as accuracy, precision, recall, and F1 score are employed to assess the models’ performance. The results reveal that the logistic regression model achieves the highest accuracy ratio of 0.981 in detecting crime intent from tweets. This research showcases the effectiveness of machine learning and advanced transformer-based models in leveraging social media data for crime analysis. The findings provide valuable insights into the potential for early detection and monitoring of crime intent using online platforms, contributing to the field of crime prevention and law enforcement. The utilization of machine learning techniques offers new avenues for understanding and analyzing crime-related sentiments expressed by social media users. By accurately detecting crime intent from user-generated content, law enforcement agencies can enhance their proactive measures, monitor public sentiment towards crime, and shape policies and interventions to address public concerns effectively. The research highlights the significance of leveraging social media data for crime detection and emphasizes the potential impact of advanced machine learning models in improving public safety and crime prevention efforts. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing LLM Code Generation Using Natural Language Processing in the Context of Machine Learning 28th

Enhancing LLM Code Generation Using Natural Language Process...

引用

28th International Symposium on Database Engineered Applications, IDEAS 2024

作者： Nelson, Jordan Pavlidis, Michalis Fish, Andrew Polatidis, Nikolaos School of Architecture Technology and Engineering University of Brighton BrightonBN2 4GJ United Kingdom Department of Computer Science University of Liverpool LiverpoolL69 3BX United Kingdom

ISBN: (纸本)9783031834714

The rapid rise in popularity of Generative AI and Large Language Models (LLMs) has brought both innovation and controversy, particularly regarding plagiarism and IP law infringements. However, one underexplored concern is the generation of code by these models, which, despite their potential, often includes errors and promotes poor programming practices. This paper explores new methods to address these issues by integrating LLMs with Automated Machine Learning (AutoML). By leveraging AutoML’s capabilities in hyperparameter tuning and model selection, we propose a novel approach for generating robust machine learning algorithms. This integration aims to enhance the accuracy and reliability of code generation while mitigating legal risks. Our findings include the application of Natural Language Processing (NLP) and Natural Language Understanding (NLU) techniques to interpret chatbot prompts, thereby improving the generation and customization of machine learning models. The proposed methodology demonstrates practical implementation and high prediction accuracy, offering a promising solution to the current challenges faced by LLM-based code generation. In summary the findings of the paper are as follows: A new implementation of natural language processing for natural language understanding in the context of chatbot prompts aims to serve as an initial step for feature extraction, which will be utilised by an AutoML system to generate machine learning algorithms. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Ambient intelligence for self-care and self-management

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第1期14卷 1-3页

作者： Hervás, Ramón Baños, Oresti Villalonga, Claudia Department of Technologies and Information Systems Modelling Ambient Intelligence Research Group University of Castilla-La Mancha Paseo de La Universidad 4 Ciudad Real Spain Department of Computer Architecture and Computer Technology Research Center for Information and Communication Technologies University of Granada Calle Periodista Rafael Gomez Montero 2 Granada Spain

来源：评论

学校读者我要写书评

暂无评论

Evaluating Machine Learning Classifiers for Predicting Liver Disease Outcomes

Evaluating Machine Learning Classifiers for Predicting Liver...

引用

Decision Aid Sciences and Application (DASA), International Conference on

作者： Khaled Mohamad AlMustafa Juliano Katrib Department of Electrical and Computer Engineering College of Engineering and Architecture Gulf University for Science and Technology (GUST)

ISBN: (数字)9798350369106

ISBN: (纸本)9798350369113

The increasing prevalence of liver disease necessitates the development of accurate predictive models to aid in early diagnosis and treatment. This study investigates the effectiveness of several machine learning classifiers, Random Forest, Gradient Boosting, AdaBoost, Support Vector Machine (SVM), and Logistic Regression, in predicting liver disease outcomes based on clinical and biochemical features. Each model's performance was rigorously evaluated using multiple metrics, including F1-score, accuracy, root mean square error (RMSE), mean absolute error (MAE), precision, recall, and cross-validation ROC-AUC scores. The Random Forest Classifier emerged as the most effective model, achieving a perfect accuracy of 100% and an F1-score of 1.00, suggesting its robustness in handling complex, high-dimensional data. The Gradient Boosting Classifier also demonstrated commendable performance with an accuracy of 89% and an F1-score of 0.85, indicating its efficacy in capturing the underlying patterns of liver disease. Conversely, Logistic Regression and SVM exhibited lower performance metrics, pointing to potential limitations in their ability to model the intricacies of liver disease data effectively. The insights from this study not only enhance our understanding of liver disease prediction using machine learning but also emphasize the need for further research to validate these models in diverse clinical populations. This study contributes to the growing body of literature advocating for the integration of machine learning techniques in clinical decision-making processes, ultimately aiming to improve patient outcomes in liver disease management.

关键词： Support vector machines Measurement Logistic regression Accuracy Liver diseases Biological system modeling Predictive models Boosting Root mean square Random forests

来源：评论

学校读者我要写书评

暂无评论

Hemodynamics in renal arteries with partial coverage after endovascular aneurysm repair affected by renal orientations

引用

Medicine in Novel technology and Devices 2023年第2期18卷 81-90页

作者： Jun Wen Xinhui Liu Jianguo Lei Jiarong Wang Xiyang Chen Tinghui Zheng Ding Yuan School of Computer Science and Technology Southwest University of Science and TechnologyMianyang621010China Institute of Civil Engineering and Architecture Southwest University of Science and TechnologyMianyang621010China Department of Vascular Surgery West China HospitalSichuan UniversityChengdu610041China Department of Applied Mechanics Sichuan UniversityChengdu610000China

Endovascular aortic repair(EVAR)has been increasingly used to treat abdominal aortic aneurysm(AAA)due to its lower mortality and shorter recovery ***,the complications caused by renal artery coverage remained a major *** this study,three types of renal orientation and five types of partial renal coverage degree were adopted to numerically investigate the flow pattern,wall shear stress distribution,and blood perfusion during a cardiac *** results show that as for the mild partial coverage(=<30%),the renal artery with a downward orientation suffered fewer unfavorable wall shear stress(WSS)distribution and more blood *** should be noted that the renal artery with horizontal orientation suffered more unfavorable WSS *** terms of severe coverage(≥50%),all of the renal arteries displayed highly disturbed wall shear distribution,resulting in a significant reduction in blood perfusion It was interesting to note that the artery with an upward orientation had a smaller rate of reduction in blood *** can be concluded that as for the mild renal coverage after EVAR,renal arteries with downward orientation may have the advantage of reducing the possibility of renal occlusion,while renal arteries with horizontal orientation may increase the unfavorable wall shear *** the other hand,as for serious coverage(≥50%),high risk of renal ischemia remains the main concern for all types of renal arteries due to highly disturbed wall shear distribution would significantly increase regardless of renal orientation.

关键词： Hemodynamics Orientation Follow-up Numerical simulation Renal artery

来源：评论

学校读者我要写书评

暂无评论

New Evolutionary Selection Operators for Snake Optimizer 14th

New Evolutionary Selection Operators for Snake Optimizer

引用

14th International Joint Conference on Computational Intelligence, IJCCI 2022

作者： Khurma, Ruba Abu Alazab, Moutaz Merelo, J.J. Castillo, Pedro A. Department of Computer Science Al-Ahliyya Amman University Amman Jordan Department of Artificial Intelligence Al-Balqa University Al-Salt Jordan Department of Computer Architecture and Computer Technology ETSIIT CITIC University of Granada Granada Spain

ISBN: (纸本)9789897586118

Evolutionary algorithms (EA) adopt a Darwinian theory which is known as "survival of the fittest". Snake Optimizer (SO) is a recently developed swarm algorithm that inherits the selection principle in its structure. This is applied by selecting the fittest solutions and using them in deriving new solutions for the next iterations of the algorithm. However, this makes the algorithm biased towards the highly fitted solutions in the search space, which affects the diversity of the SO algorithm. This paper proposes new selection operators to be integrated with the SO algorithm and replaces the global best operator. Four SO variations are investigated by individually integrating four different selection operators: SO-roulettewheel, SO-tournament, SO-linearrank, and SO-exponentialrank. The performance of the proposed SO variations is evaluated. The experiments show that the selection operators have a great influence on the performance of the SO algorithm. Finally, a parameter analysis of the SO variations is investigated. Copyright © 2022 by SCITEPRESS - Science and technology Publications, Lda.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Living Lab Long-Term Sustainability in Hybrid Access Positive Energy Districts - A Prosumager Smart Fog Computing Perspective

引用

IEEE Internet of Things Journal 2023年第21期10卷 18898-18908页

作者： Vohnout, Rudolf Bukovsky, Ivo Chou, Shuo-Yan Geyer, Jakub Budik, Ondrej Sharma, Rohit Prokysek, Milos Horvath, Tomas Wyckmans, Annemie University of South Bohemia in České Budějovice Faculty of Science Department of Computer Science České Budějovice37005 Czech Republic National Taiwan University of Science and Technology Department of Industrial Management Taipei106 Taiwan SRM Institute of Science and Technology NCR Campus Department of Electronics and Communication Engineering Ghaziabad201204 India Brno University of Technology Department of Telecommunications Brno61600 Czech Republic CESNET a.l.e Department of Optical Networks Prague16000 Czech Republic NTNU-Norwegian University of Science and Technology Department of Architecture and Planning Trondheim7491 Norway

Living lab, one of the recent emerging smart city concepts, faces long-term sustainability challenges associated with its complexity and breadth of use. To be efficient, it must rely on comprehensive set of information distributed appropriately among all stakeholders to unleash its full innovation potential. This is especially true in the case of positive energy districts (PEDs), where timely data dissemination is essential for prosumager decisions and their greedy behavior. This article interconnects intelligent information exchange, supported by ultralow latency hybrid access network infrastructure, with the clever use of available fog computing resources to properly disseminate complex energy details to all participating entities. As the optimal task offloading for effective information distribution constitutes the convergence problem, we reintroduced higher order neural units. These units contribute to sustaining both computational and energy efficiency, as well as the balance of the entire system. We have achieved a reliable hourly energy consumption prediction with a computationally very lightweight alternative to commonly used deep neural network approaches that can be deployed on available smart appliances with ease. The application and simulation were performed on the data set provided by one of Europe's smart city pioneers, where the prosumager PED transition has already started. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Advancements in 5G and 6G Technologies Shaping the Future of Global Connectivity and Communication 5

Advancements in 5G and 6G Technologies Shaping the Future of...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Pachar, Sunita Reddy, Satti Sudha Mohan Kompally, Gouthami Srinivasagopalan, Lakshmi Narasimhan Sangore, Rohidas Balu Katta, Sivakoteswararao GLA University IBM Department India SRKR Engineering College Department of ECE India Department of CSE-IOT India Software Development Enterprise Architecture PlanoTX United States Computer Science and Engineering MIT Art Design Technology University India KIETW Department of Mechanical Kakinada India

ISBN: (纸本)9798331530013

The evolution of wireless communication is poised for a major shift with the transition from 5G to 6G, a leap characterized by breakthroughs in speed, ultra-reliable low-latency communication, and AI-driven network optimization. This paper examines these advancements, focusing on sub-millisecond latency, terahertz spectrum utilization, and enhanced network capabilities tailored to industries such as smart infrastructure, healthcare, and autonomous vehicles. While 6G promises revolutionary improvements, it also presents new challenges, including increased computational complexity and energy demands, data privacy concerns, and efficient spectrum allocation. The proposed model aims to address these issues by integrating AI and machine learning for optimized resource management, resulting in a high-performance, cost-effective solution for real-time, data-intensive applications. To assess the model's effectiveness, comprehensive simulations and real-world trials will be conducted, measuring critical metrics such as network throughput, latency, reliability, and energy efficiency. This study offers an all-encompassing guide to understanding and harnessing the transformative potential of 6G technology, laying the groundwork for future wireless communication systems. © 2024 IEEE.

关键词： Terahertz spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Attributed Network Clustering through Mutual Affinity Propagated Non-negative Matrix Factorization

引用

SN computer Science 2025年第5期6卷 1-17页

作者： Pahari, Saikat Dey, Paramita Department of Computer Science Engineering OmDayal College of Engineering and Architecture West Bengal Howrah 711316 India Department of Information Technology Government College of Engineering and Ceramic Technology West Bengal Kolkata 700010 India

Attributed Network Clustering (ANC) has garnered significant attention in research for identifying communities within a complex network like a social, biological, or information network. Generally, such networks are represented as a graph where the nodes denote entities and edges are relationships between two adjacent nodes. In real-world networks, nodes are associated with attributes to express their properties. In this context, a community is defined as a group of nodes that interact more frequently with each other than with nodes outside their group. ANC involves creating a mapping function that converts nodes and associated attributes into lower-dimensional vector representations. Once transformed into these vectors, various machine learning algorithms are used to cluster the nodes and reveal the underlying communities. However, most ANC methods confront two major challenges. First, they assimilate node attribute information from the local neighborhood, as a result, they can’t explore the mutual affinity between node and attribute. Second, they do not consider the values of the community membership of the nodes at the time of clustering. This leads to poor performance, as the embedding method and clustering methods are independent. To address this, this article proposes a method named Mutual Affinity Propagation-based Nonnegative Matrix Factorization (MAP-NMF). The proposed method works in two phases. In the first phase, an attribute-augmented transition probability matrix is constructed to capture the mutual affinity between the node and attribute and obtain node representation using singular value decomposition of the same. The second phase produces community membership from the obtained latent representation through an NMF-based joint optimization. Moreover, a novel updating rule is proposed for the joint optimization method. Empirical study on both real-world and artificial networks proves the superiority of our proposed algorithm. © The Author(s), under exc

关键词： Attribute augmented graph Attributed network embedding Joint optimization Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Assessment of changes in a technical condition of railway bridges using a novel probabilistic algorithm

引用

Structure and Infrastructure Engineering 2025年

作者： Fabianowski, Dariusz Jakiel, Przemyslaw Rydel, Marek Bialic, Grzegorz Stanislawski, Rafal Faculty of Civil Engineering and Architecture Opole University of Technology Opole Poland Department of Computer Science Opole University of Technology Opole Poland

Planning of rehabilitation work is important for the safety of transport infrastructure. This problem needs to be properly solved, therefore a new algorithm for planning railway bridge maintenance is proposed. The input data come from periodic inspections that assess the technical condition of a bridge. These assessments are processed using hybrid Extended Fuzzy Analytic Hierarchy Process and Dominant Analytic Hierarchy Process methods. The main part of the algorithm is the Statistic Bridge Analyser, which allows a multi-variant analysis of the impact of inaccuracy and uncertainties in sub-assessments. It also takes into account a relationship between individual bridge components and estimates missing assessments using archive data. The algorithm performance has been confirmed by analysing nine different scenarios involving ranking of 10 selected railway bridges on Maintenance, Repair & Rehabilitation (MR&R) list. It has been demonstrated that even a small error in the sub-assessment of the technical condition of one element can result in a significant change in assessment of the bridge technical condition. Considering the relationship between criteria also generates changes in the final assessment of the bridge technical condition and may result in changes in position on MR&R list. This allows to avoid sudden failures, especially with limited financial resources. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Railroad bridges

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：