检索结果-内蒙古大学图书馆

Assessment of the Potential of Indirect Measurement for Sap Flow Using Environmental Factors and artificial intelligence Approach: A Case Study of Magnolia denudata in Shanghai Urban Green Spaces

引用

FORESTS 2023年第9期14卷 1768-1768页

作者： Zhang, Biao Zhang, Dongmei Feng, Zhongke Zhang, Lang Zhang, Mingjuan Fu, Renjie Wang, Zhichao Beijing Forestry Univ Precis Forestry Key Lab Beijing Tsinghua East Rd Beijing 100083 Peoples R China Shanghai Acad Landscape Architecture Sci & Plannin 899 Longwu Rd Shanghai 200232 Peoples R China

The measurement of plant sap flow has long been a traditional method for quantifying transpiration. However, conventional direct measurement methods are often costly and complex, thereby limiting the widespread application of tree sap flow monitoring techniques. The concept of a Virtual Measurement Instrument (VMI) has emerged in response to this challenge by combining simple instruments with artificial intelligence (AI) algorithms to indirectly assess specific measurement objects. This study proposes a tree sap flow estimation method based on environmental factors and AI algorithms. Through the acquisition of environmental factor data and the integration of AI algorithms, we successfully achieved indirect measurement of tree sap flow. Accounting for the time lag response of the flow to environmental factors, we constructed the Magnolia denudata sap flow estimation model using the K-Nearest Neighbor (KNN), Random Forest (RF), Backpropagation Neural Network (BPNN), and Long Short-Term Memory network (LSTM) algorithms. The research results showed that the LSTM model demonstrated greater reliability in predicting sap flow velocity, with R-2 of 0.957, MAE of 0.189, MSE of 0.059, and RMSE of 0.243. The validation of the target tree yielded an R-2 of 0.821 and an error rate of only 4.89% when applying the model. In summary, this sap flow estimation method based on environmental factors and AI provides new insights and has practical value in the field of tree sap flow monitoring.

关键词： artificial intelligence algorithms computational virtual measurement environmental factors sap flow virtual measuring instrument

来源：评论

学校读者我要写书评

暂无评论

Sports health monitoring management system based on artificial intelligence algorithm

引用

FRONTIERS IN PHYSICS 2023年 11卷

作者： Tong, Yunlong Ye, Lina Jilin Normal Univ Inst Phys Educ Siping Peoples R China Jilin Normal Univ Coll Math & Comp Siping Peoples R China

With the improvement of people's material living standards, more and more people start to pay attention to health issues. This paper takes the health field as the main research object, and discusses the current development and status quo of the health field. Through literature review, it is found that the current health field mainly focuses on the single monitoring of a certain organ or body function, and there are limitations in systematic health monitoring research, and most of the research stays at the stage of human body monitoring. Therefore, this paper intends to design a sports health monitoring and management system based on artificial intelligence. The system is mainly divided into a body temperature monitoring module, a blood pressure monitoring module and an exercise monitoring module, through which the user's health data is monitored. In order to ensure the practicability of the system, this paper selects three common life states in daily life for experimental testing, namely exercise state, rest state and sick state. The experimental test results show that each monitoring module can operate correctly and normally under three different states. The lowest temperature was 36.5 degrees and the highest temperature was 37.1 degrees under the exercise state. The lowest blood pressure is 70 in the resting state, and the highest blood pressure is 80. In the sick state, the maximum value of motor threshold is 0.2, the minimum value is 0.1, and the threshold difference is 0.1. Each module reads and backs up relevant data, and sends it to the platform for intelligent analysis. The platform will analyze and compare the data of different modules at the same time, judge the health status of the user at that time, choose whether to issue a health alert for the user, and finally complete the entire system process of the health monitoring management system. This proves that the sports health monitoring management system based on artificial intelligence algorithm designed

关键词： sports health monitoring and management system artificial intelligence algorithms body temperature monitoring monitoring of blood pressure artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Graph-theoretic approach to detecting real-time intents within purchase conversion funnel using clickstream data

引用

KYBERNETES 2023年第11期52卷 5139-5163页

作者： Gao, Hongming Liu, Hongwei Lin, Weizhen Chen, Chunfeng Guangzhou Univ Sch Management Guangzhou Peoples R China Guangdong Univ Technol Sch Management Guangzhou Peoples R China

Purpose Purchase conversion prediction aims to improve user experience and convert visitors into real buyers to drive sales of firms;however, the total conversion rate is low, especially for e-retailers. To date, little is known about how e-retailers can scientifically detect users' intents within a purchase conversion funnel during their ongoing sessions and strategically optimize real-time marketing tactics corresponding to dynamic intent states. This study mainly aims to detect a real-time state of the conversion funnel based on graph theory, which refers to a five-class classification problem in the overt real-time choice decisions (RTCDs)-click, tag-to-wishlist, add-to-cart, remove-from-cart and purchase-during an ongoing session. Design/methodology/approach The authors propose a novel graph-theoretic framework to detect different states of the conversion funnel by identifying a user's unobserved mindset revealed from their navigation process graph, namely clickstream graph. First, the raw clickstream data are identified into individual sessions based on a 30-min time-out heuristic approach. Then, the authors convert each session into a sequence of temporal item-level clickstream graphs and conduct a temporal graph feature engineering according to the basic, single-, dyadic- and triadic-node and global characteristics. Furthermore, the synthetic minority oversampling technique is adopted to address with the problem of classifying imbalanced data. Finally, the authors train and test the proposed approach with several popular artificial intelligence algorithms. Findings The graph-theoretic approach validates that users' latent intent states within the conversion funnel can be interpreted as time-varying natures of their online graph footprints. In particular, the experimental results indicate that the graph-theoretic feature-oriented models achieve a substantial improvement of over 27% in line with the macro-average and micro-average area under the precision-reca

关键词： Purchase conversion CRM Intent Clickstream graph Conversion funnel artificial intelligence algorithms

来源：评论

学校读者我要写书评

暂无评论

AI Emmbedded in Drone Control 10th

AI Emmbedded in Drone Control

引用

10th International Work-Conference on the Interplay Between Natural and artificial Computation (IWINAC)

作者： Caballero-Martin, Daniel Lopez-Guede, Jose Manuel Estevez, Julian Grana, Manuel Univ Basque Country UPV EHU Fac Engn Vitoria Gasteiz Vitoria Spain Univ Basque Country Fac Engn Gipuzkoa UPV EHU San Sebastian Spain Univ Basque Country Fac Comp Sci UPV EHU San Sebastian Spain Univ Basque Country UPV EHU Grp Computat Intelligence San Sebastian Spain

ISBN: (纸本)9783031611360;9783031611377

The significant improvement of drones has supported research in advanced technologies, highlighting the integration of artificial intelligence (AI). This study examines the impact of AI on drones, addressing several areas from automation to complex real time decision making. In fields unrelated to logistics and cargo transportation, the synergy between drones and AI has led to notable progress in areas such as agriculture, construction, security and exploration. This combination the generation of new applications, although on the other hand, it poses ethical and regulatory challenges. In summary, AI not only transforms logistics but also drives innovation in several industries, offering a safer and more efficient future.

关键词： artificial intelligence algorithms Drones Cargo Transport Autonomous Decisions

来源：评论

学校读者我要写书评

暂无评论

Research on Mobile Network User Complaint Warning Method Based on Multimodal Data 8

Research on Mobile Network User Complaint Warning Method Bas...

引用

IEEE 8th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)

作者： Di, Zixiang Xiao, Tian Li, Bei Peng, Yunfeng Li, Jianfei Cheng, Xinzhou Xu, Lexi Zhu, Xiaomeng Zheng, Hangbo China United Network Commun Corp Res Inst Beijing 100037 Peoples R China Univ Sci & Technol Beijing Beijing 100083 Peoples R China Zhejiang Airport Digital Technol Co Ltd Hangzhou 310051 Peoples R China

ISBN: (纸本)9798350319514

With the rapid development of information and communication technology, the types of service applications for mobile terminals are becoming increasingly diverse. Each application has varying requirements for network performance, and each user's preferences, usage frequency, and sensitivity are different. When the quality of the operator network cannot meet the specific service needs of users and exceeds the threshold that users can tolerate, it will trigger user complaints. This article proposes a method for mobile network user complaint warning based on multimodal data. The method can be used to identify potential complaint users in the network and reduce the number of user complaints. In this method, a multimodal user level application rating feature dataset is constructed based on multi-source data, combined with factors such as user preferences and usage perception. Then, AI algorithms and great network computing power are used to generate complaint prediction models for different service applications at the user level. By integrating multiple application business complaint models at the user level and comprehensively evaluating user complaint expectations, it is used to improve the accuracy of user complaint warning.

关键词： Mobile service applications artificial intelligence algorithms Complaint warning Multi-source data Multimodal

来源：评论

学校读者我要写书评

暂无评论

Micro-Nano Multi-Photon Tactile Neurons

Micro-Nano Multi-Photon Tactile Neurons

引用

2024 Light Conference

作者： Zhou Hongyu Yu Yang Zhang Chao Nong, Hengchang Zhang Zhenrong Natl Univ Def Technol Coll Sci Changsha Peoples R China Guangxi Univ Sch Comp Elect & Informat Nanning Peoples R China

ISBN: (数字)9798350392272

ISBN: (纸本)9798350392289;9798350392272

The integration of embodied tactile sensing technology with artificial intelligence algorithms holds promise for creating robust interpretive and representational models for object morphology perception. However, currently reported tactile sensor technologies have failed to comprehensively and concretely perceive an object from three aspects: shape, hardness, and surface texture, thus impeding their application in the field of human-computer interaction. Here, we report a tactile skin based on micro/nano-photonic neurons (OMAS), which mimics the interdigitated distribution of tactile neurons in human epidermis using a grid-like arrangement of micro/nano optical fiber waist regions. This device features high sensitivity (-0.83 N/V) and fast response time (72 ms). We demonstrate that combining the signals collected by OMAS with artificial intelligence algorithms enables the identification of objects of different hardness and shapes with an accuracy of 99.3%, and the classification of fabrics with different surface textures with accuracy of 98.5%. This tactile skin based on micro/nano-photonic neurons provides a promising solution for human-computer interaction and intelligent sensing technology.

关键词： multiphoton neurons micro nano photons tactile sensing artificial intelligence algorithms human-computer interaction

来源：评论

学校读者我要写书评

暂无评论

Interactive Crime Map Integrating Geospatial Data to Improve Public Safety in the City of Lima 16

Interactive Crime Map Integrating Geospatial Data to Improve...

引用

16th IEEE International Conference on Computational intelligence and Communication Networks, CICN 2024

作者： Pena-Carrillo, Cesar Gonzales-Loli, Martha Rodriguez, Diego Rodriguez, Ciro Escuela de Ing. de Software Universidad Nacional Federico Villarreal Lima Peru Universidad Peruana de Ciencias Aplicadaas Facultad de Ciencias de la Salud Lima Peru Escuela de Ingenieria Informatica Universidad Nacional Mayor de San Marcos Peru

ISBN: (纸本)9798331505264

Insecurity is a growing concern in Latin America and some parts of the world, and the city of Lima is no exception. Crimes such as assaults, robberies and other crimes are on the rise, generating great concern among the population. In this context, it is important to interact with the population by geo-referencing danger zones with crime maps. This paper aims to develop a real-time application that allows the tracking and monitoring of danger zones, using machine learning techniques and visualization of critical zones. The methodology uses a dataset of crime reports provided by the Peruvian Police from 2018 to 2023, using tools such as Power BI and libraries such as Pandas, Plotly, and Mapbox from Python to extract latitude and longitude. The process includes data analysis and prediction, application development, interactive map creation, data visualization, and application testing. The study concludes that crime mapping is a valuable tool for combating insecurity. Integrating crime data with georeferencing technologies allows detailed visualization of crime patterns, enabling better resource planning, prioritization, and data-driven decision-making to address criminal activity effectively. © 2024 IEEE.

关键词： artificial intelligence algorithms citizen security crime map geospatial data

来源：评论

学校读者我要写书评

暂无评论

Ambient Assisted Living: Scoping Review of artificial intelligence Models, Domains, Technology, and Concerns

引用

JOURNAL OF MEDICAL INTERNET RESEARCH 2022年第11期24卷 e36553页

作者： Jovanovic, Mladjan Mitrov, Goran Zdravevski, Eftim Lameski, Petre Colantonio, Sara Kampel, Martin Tellioglu, Hilda Florez-Revuelta, Francisco Singidunum Univ Dept Comp Sci Danijelova 32 Belgrade 11000 Serbia Univ St Cyril & Methodius Fac Comp Sci & Engn Skopje North Macedonia Natl Res Council Italy Inst Informat Sci & Technol Signals & Images Lab Pisa Italy Vienna Univ Technol Fac Informat Vienna Austria Univ Alicante Dept Comp Technol Alicante Spain

Background: Ambient assisted living (AAL) is a common name for various artificial intelligence (AI)-infused applications and platforms that support their users in need in multiple activities, from health to daily living. These systems use different approaches to learn about their users and make automated decisions, known as AI models, for personalizing their services and increasing outcomes. Given the numerous systems developed and deployed for people with different needs, health conditions, and dispositions toward the technology, it is critical to obtain clear and comprehensive insights concerning AI models used, along with their domains, technology, and concerns, to identify promising directions for future work. Objective: This study aimed to provide a scoping review of the literature on AI models in AAL. In particular, we analyzed specific AI models used in A.L systems, the target domains of the models, the technology using the models, and the major concerns from the end-user perspective. Our goal was to consolidate research on this topic and inform end users, health care professionals and providers, researchers, and practitioners in developing, deploying, and evaluating future intelligent AAL systems. Methods: This study was conducted as a scoping review to identify, analyze, and extract the relevant literature. It used a natural language processing toolkit to retrieve the article corpus for an efficient and comprehensive automated literature search. Relevant articles were then extracted from the corpus and analyzed manually. This review included 5 digital libraries: IEEE, PubMed, Springer, Elsevier, and MDPI. Results: We included a total of 108 articles. The annual distribution of relevant articles showed a growing trend for all categories from January 2010 to July 2022. The AI models mainly used unsupervised and semisupervised approaches. The leading models are deep learning, natural language processing, instance-based learning, and clustering. Activity assist

关键词： ambient assisted living AAL assisted living active living digital health digital well-being automated learning approach artificial intelligence algorithms human-centered AI review implications artificial intelligence mobile phone

来源：评论

学校读者我要写书评

暂无评论

The Deep Neural Network Compilers for FPGAs: A Survey 3

The Deep Neural Network Compilers for FPGAs: A Survey

引用

3rd International Conference on Electronic Information Engineering and Computer Communication, EIECC 2023

作者： Tian, Jing Shi, Tianjie Zhao, Yixuan Liu, Feiyang Xi'An Aeronautics Computing Technique Research Institute AVIC Xi'an China

ISBN: (纸本)9798350359961

In embedded systems, the low-latency, low-power consumption, and reconfigurable FPGA component undertakes the inference operations of a large number of computationally intensive tasks, such as artificial intelligence algorithms, making the deep neural network compiler for FPGAs a hot topic. This FPGA compiler can automatically optimize the model calculation diagrams and hardware structure design, and can achieve the end-To-end deployment of neural network models, efficiently and rapidly. This paper summarizes the general framework structure of the neural network compiler for FPGAs, focuses on the development of three representative compilers, compares the deployment performance of specific algorithms on the FPGA platform, summarizes the development advantages and limitations, and finally proposes its application prospects and important research directions in embedded systems, providing a theoretical basis for the rapid iteration and deployment of artificial intelligence algorithms in embedded computing systems. © 2023 IEEE.

关键词： algorithm deployment artificial intelligence algorithms compilers deep neural network FPGA

来源：评论

学校读者我要写书评

暂无评论

Intelligent Energy Management Systems in Industry 5.0: Cybersecurity Applications in Examples

引用

ENERGIES 2024年第23期17卷 5871页

作者： Wyrzykowska, Barbara Szczepaniuk, Hubert Szczepaniuk, Edyta Karolina Rytko, Anna Kacprzak, Marzena Warsaw Univ Life Sci SGGW Inst Managment Nowoursynowska 166 St PL-02787 Warsaw Poland Polish Air Force Univ Dywizjonu 303 St 35 PL-08521 Deblin Poland Warsaw Univ Life Sci SGGW Inst Econ & Finance Nowoursynowska 166 St PL-02787 Warsaw Poland

The article examines modern approaches to energy management in the context of the development of Industry 5.0 with a particular focus on cybersecurity. Key tenets of Industry 5.0 are discussed, including the integration of advanced technologies with intelligent energy management systems (IEMSs) and the growing need to protect data in the face of increasing cyber threats. The challenges faced by small and medium-sized enterprises (SMEs) using solutions based on renewable energy sources, such as photovoltaic farms, are also analyzed. The article presents examples of IEMS applications and discusses methods for securing these systems, offering an overview of cyber threat protection tools in the context of modern energy management. The analysis carried out provided information that will help businesses make rational decisions and contribute to shaping the state's macroeconomic policy on cybersecurity and energy savings. The results of this research can also help develop more effective strategies for managing technology and IT infrastructure, which is crucial in the digital age of Industry 5.0.

关键词： intelligent energy management systems Industry 5.0 cybersecurity attack vectors artificial intelligence 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：