检索结果-内蒙古大学图书馆

Future connected vehicles:Communications demands,privacy and cyber-security

Communications in Transportation Research 2022年第1期2卷 39-41页

作者： Tomas Olovsson Tommy Svensson Jiaming Wu Department of Computer Science and Engineering Chalmers University of TechnologyGothenburgSE41296Sweden Department of Electrical Engineering Chalmers University of TechnologyGothenburgSE41296Sweden Department of Architecture and Civil Engineering Chalmers University of TechnologyGothenburgSE41296Sweden

*** With the advance of data collection,data processing,telecommunication and vehicular technologies,connected vehicles(CVs)have been emerging as a crucial branch of smart mobility(Olia et al.,2015;Li et al.,2021).Its basic idea is to realize real-time exchanges and processing of essential information,such as positions and destinations,among surrounding vehicles and infrastructures.

关键词： connected branch destination

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

Investigating Context-Aware Collaborative Text Entry on Smartphones using Large Language Models 25

Investigating Context-Aware Collaborative Text Entry on Smar...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Chen, Weihao Shi, Yuanchun Wang, Yukun Shi, Weinan Chen, Meizhu Gao, Cheng Mei, Yu Zhu, Yeshuang Zhang, Jinchao Yu, Chun Department of Computer Science and Technology Tsinghua University Beijing China Qinghai University Qinghai Xining China School of Architecture Tsinghua University Beijing China Pattern Recognition Center WeChat AI Tencent Inc. Beijing China

ISBN: (纸本)9798400713941

Text entry is a fundamental and ubiquitous task, but users often face challenges such as situational impairments or difficulties in sentence formulation. Motivated by this, we explore the potential of large language models (LLMs) to assist with text entry in real-world contexts. We propose a collaborative smartphone-based text entry system, CATIA, that leverages LLMs to provide text suggestions based on contextual factors, including screen content, time, location, activity, and more. In a 7-day in-the-wild study with 36 participants, the system offered appropriate text suggestions in over 80% of cases. Users exhibited different collaborative behaviors depending on whether they were composing text for interpersonal communication or information services. Additionally, the relevance of contextual factors beyond screen content varied across scenarios. We identified two distinct mental models: AI as a supportive facilitator or as a more equal collaborator. These findings outline the design space for human-AI collaborative text entry on smartphones. © 2025 Copyright held by the owner/author(s).

关键词： Ambient intelligence

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

To meet this goal, it is essential to address important challenges related to continuous monitoring—to provide both users and practitioners with a new dimension of health-related data; integration of this data with cloud, fog, and edge computing and social networks—to share information and experiences with peer groups; or guiding people in the self-management of their conditions through intelligent coaching services—to ensure proper handling of diseases and care. [...]the authors present a set of consolidated usability problems categorized by severity index, source, and other factors, with a special focus on the impact of these types of issues from the perspective of diabetic patients. [...]understanding parents’ behaviors turns to be of much relevance, and apparently, it has remained a largely unexplored area in ubiquitous computing. [...]another trending challenge in self-care and self-management is to reduce the effort of creating, customizing and maintaining services that typically collect IoT data from heterogeneous sources.

关键词：

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

Zero-day Android botnet detection using neural networks

引用

Neural Computing and Applications 2025年第17期37卷 10795-10805页

作者： Seraj, Saeed Pimenidis, Elias Trovati, Marcello Polatidis, Nikolaos Department of Computer Science Royal Holloway University EghamTW20 0EX United Kingdom School of Computing and Creative Technologies University of the West of England BristolBS16 1QY United Kingdom Department of Computer Science Edge Hill University OrmskirkL39 4QP United Kingdom School of Architecture Technology and Engineering University of Brighton BrightonBN2 4GJ United Kingdom

Android devices have evolved to offer a diverse array of services, spanning applications related to banking, business, health, and entertainment. The widespread adoption of Android devices, coupled with the open-source architecture of the Android operating system, has rendered them a prime target for malicious actors. Among the most perilous threats are Android botnets, which enable malicious actors, often referred to as botmasters, to exert remote control for the execution of destructive attacks. Android botnets have huge potential to be an emerging threat to mobile device security. In this paper, we focus on detecting evolving Android botnets and introduce a new dataset of 3458 apps, represented by 455 permission-based features. We propose an improved multilayer perceptron neural network for zero-day botnet detection. Our methodology, in this way, achieves an accuracy of 98.5%, thus outperforming traditional classifiers. It has a lot of functionality and is based on the neural network approach, making it able to identify slight botnet behaviours in order to improve Android security. © The Author(s) 2024.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

A New IoT-Based Smart Greenhouse for Cultivation of Water Convolvulus 13

A New IoT-Based Smart Greenhouse for Cultivation of Water Co...

引用

13th International Electrical Engineering Congress, iEECON 2025

作者： Akkaraekthalin, Prayoot Somwong, Tanee Chudpooti, Nonchanutt Hirun, Nuttawut Meesomklin, Suwaluck King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok10800 Thailand Rajamangala University of Technology Suvarnabhumi Faculty of Engineering and Architecture Department of Electronic and Telecommunications Engineering Nonthaburi11000 Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Industrial Physics and Medical Instrumentation Bangkok10800 Thailand King Mongkut's University of Technology North Bangkok College of Industrial Technology Department of Electronics Engineering Technology Bangkok10800 Thailand

ISBN: (纸本)9798331543952

This paper presents a new IOT system for monitoring and controlling plant cultivation in greenhouse system. The system aims to regulate and monitor the environmental conditions suitable for plant cultivation in real-time. The system utilizes sensors to measure environmental conditions, such as soil moisture sensor, light intensity sensor, temperature sensor, and air humidity sensor. The Node MCU ESP32 is used for processing and controlling these operations. The system is designed to send notifications through Line application and allows farmers to monitor the system's performance and plant growth in real-time via a smartphone application. It can utilize the Blynk IoT application on a smartphone for remotely monitoring and controlling the environmental conditions and provides historical data. This experiment demonstrates that the designed system can successfully cultivate plants and promote better growth compared to traditional cultivation methods with a 13.38% improvement. Additionally, it provides convenience and ease of management for plant cultivation. © 2025 IEEE.

关键词： greenhouse system IOT smart agriculture Smart farming water convolvulus

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

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

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：