检索结果-内蒙古大学图书馆

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

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

How Clinicians Perceive artificial intelligence-Assisted Technologies in Diagnostic Decision Making: Mixed Methods Approach

引用

JOURNAL OF MEDICAL INTERNET RESEARCH 2021年第12期23卷 e33540页

作者： Hah, Hyeyoung Goldin, Deana Shevit Florida Int Univ Coll Business Informat Syst & Business Analyt 11200 SW 8th St Miami FL 33199 USA Florida Int Univ Nicole Wertheim Coll Nursing & Hlth Sci Miami FL 33199 USA

Background: With the rapid development of artificial intelligence (AI) and related technologies, AI algorithms are being embedded into various health information technologies that assist clinicians in clinical decision making. Objective: This study aimed to explore how clinicians perceive AI assistance in diagnostic decision making and suggest the paths forward for AI-human teaming for clinical decision making in health care. Methods: This study used a mixed methods approach, utilizing hierarchical linear modeling and sentiment analysis through natural language understanding techniques. Results: A total of 114 clinicians participated in online simulation surveys in 2020 and 2021. These clinicians studied family medicine and used AI algorithms to aid in patient diagnosis. Their overall sentiment toward AI-assisted diagnosis was positive and comparable with diagnoses made without the assistance of AI. However, AI-guided decision making was not congruent with the way clinicians typically made decisions in diagnosing illnesses. In a quantitative survey, clinicians reported perceiving current AI assistance as not likely to enhance diagnostic capability and negatively influenced their overall performance (beta=-0.421, P=.02). Instead, clinicians' diagnostic capabilities tended to be associated with well-known parameters, such as education, age, and daily habit of technology use on social media platforms. Conclusions: This study elucidated clinicians' current perceptions and sentiments toward AI-enabled diagnosis. Although the sentiment was positive, the current form of AI assistance may not be linked with efficient decision making, as AI algorithms are not well aligned with subjective human reasoning in clinical diagnosis. Developers and policy makers in health could gather behavioral data from clinicians in various disciplines to help align AI algorithms with the unique subjective patterns of reasoning that humans employ in clinical diagnosis.

关键词： artificial intelligence algorithms AI diagnostic capability virtual care multilevel modeling human-AI teaming natural language understanding

来源：评论

学校读者我要写书评

暂无评论

Method for automatic railway track surface defect classification and evaluation using a laser-based 3D model

引用

IET IMAGE PROCESSING 2020年第12期14卷 2701-2710页

作者： Ye, Jiaqi Stewart, Edward Zhang, Dingcheng Chen, Qianyu Roberts, Clive Univ Birmingham Dept Elect Elect & Syst Engn Birmingham B15 2TT W Midlands England

Inspection of physical surface defects is a significant concern in many industrial areas. In railway systems, this process mainly includes the detection and classification of defects in rails and wheels, for which laser-based optical inspection technologies have gradually been applied in the form of 2D profile measurement, benefiting from its high precision and robustness to surface conditions. However, defect classification and evaluation after the initial detection works still rely heavily on human inspectors to make maintenance suggestions. The linear nature of rails makes it possible to increase the dimension of rail measurement data from 2D to 3D by aligning 2D profiles along the rail, from which more comprehensive diagnosis information becomes available. In combination with appropriate artificial intelligence algorithms, this approach can potentially replace human-dominated defect classification and evaluation work. This study presents a 3D model-based railway track surface defect classification and evaluation method. A set of geometrical features are extracted from the 3D model of track surface defects to describe a distinguishable pattern for each category of defect. Multi-class classifiers are then tested and have shown promising results on a group of artificial track surface defects, giving a systemic solution for 3D model-based automatic track surface defect inspection.

关键词： flaw detection image classification artificial intelligence rails mechanical engineering computing railways maintenance engineering automatic optical inspection railway engineering feature extraction pattern classification wheels rail measurement data automatic railway track surface defect classification laser-based 3D model physical surface defects wheels laser-based optical inspection technologies 2D profile measurement rail maintenance artificial intelligence algorithms geometrical feature extraction multiclass classifiers

来源：评论

学校读者我要写书评

暂无评论

Machine as a smart service: a hybrid knowledge graph approach

引用

FLEXIBLE SERVICES AND MANUFACTURING JOURNAL 2024年 1-26页

作者： Ren, Huanrong Jiang, Pingyu Li, Qingzong Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710049 Peoples R China

The advancement of Information and Communication Technology has catalyzed the emergence of a new generation of manufacturing paradigms demanding increasingly "smart" equipment. Despite this, existing equipment system exhibits limitations in terms of flexibility, user interaction, and cost-effectiveness. To address these challenges and foster personalization, smartness, and a service-oriented approach, this article proposed an innovative smart equipment service system implementation of "Machine as a smart service" (MaaS). We argue that shifting the past concentration from the equipment itself to the service provided would fitting for the current advanced manufacturing paradigms more properly, and based on this proposed a hybrid Knowledge Graph (KG) approach to abstract equipment as smart services. Our MaaS is running on a cluster consisting of an arbitrary quantity of equipment and makes H2M/M2H/M2M communication through service-oriented interaction. The process and related resources would be mapped into a twin space organized with KG, which translates the MaaS physical running into KG interaction. We also introduced three enabling technologies to achieve this: Hierarchical Knowledge Graph, Event Control Framework, and resource mapping methods, and illustrate them with cases.

关键词： Smart equipment Distributed system Service-oriented Knowledge graph Smart interface artificial intelligence algorithms

来源：评论

学校读者我要写书评

暂无评论

Simulation Study on Nondestructive Testing of Winding Hot Spot Temperature Based on Ultrasonic Emission

引用

IEEE TRANSACTIONS ON DIELECTRICS AND ELECTRICAL INSULATION 2024年第4期31卷 2179-2188页

作者： Sun, Youliang He, Dongxin Geng, Pan Xu, Tao Wang, Xinbing Zang, Qingjing Su, Wenbin Shandong Power Equipment Co Ltd Jinan 250002 Shandong Peoples R China Shandong Univ Sch Elect Engn Shandong Prov Key Lab UHV Transmiss Technol & Equi Jinan 250061 Peoples R China Shandong Univ Sch Phys Jinan 250100 Peoples R China

The rise in hot spot temperature is a critical indicator of transformer winding defects, making its monitoring essential. Traditional temperature measurement methods, however, have certain constraints in obtaining hot spot information due to the complex structure of transformers. This article thus proposes a nondestructive testing for measuring the transformer winding hot spot temperature based on ultrasonic thermometry, without altering the transformer's internal structure. It also explores the potential application of ultrasonic temperature measurement technology inside transformers. The propagation pattern of ultrasound within a transformer is simulated, and the effect of hot spot faults at varying positions and temperatures on the spatiotemporal distribution of ultrasonic propagation is examined. The range of effective acoustic signals has been determined through comparison. An artificial intelligence-based hot spot temperature inversion method is proposed, leading to the establishment of an effective diagnostic technique for hot spot temperature within the hot spot region, accomplishing a preliminary inversion of hot spot faults. This research offers a novel approach to measuring the internal temperature of transformers.

关键词： Temperature measurement Oil insulation Acoustics Power transformer insulation Windings Temperature sensors Ultrasonic variables measurement artificial intelligence algorithms nondestructive testing ultrasonic propagation ultrasonic thermometry winding hot spot temperature

来源：评论

学校读者我要写书评

暂无评论

Application of fuzzy decision tree in EOR screening assessment

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2019年 177卷 167-180页

作者： Khazali, Nastaran Sharifi, Mohammad Ahmadi, Mohammad Ali Amirkabir Univ Technol Polytech Tehran Dept Petr Engn Tehran Iran Univ Calgary Dept Chem & Petr Engn Calgary AB Canada

Ranking of best possible Enhanced Oil Recovery (EOR) technics for implementing on a target field is one of the most important questions that should be answered by reservoir engineers. EOR screening can be considered as a tool for recommending the most appropriate EOR methods. Although for each candidate reservoir, the applicability of EOR processes must be investigated specifically, EOR screening can be used as an indicator before economic evaluations or reservoir descriptions are done and executive decisions are made. Implementing an EOR project for predictions that pass this screening is the next step. In this study, the fuzzy decision tree method (with the ability to rank and classify EOR methods simultaneously) is introduced for EOR screening. Basic features for this study are permeability, viscosity, depth, temperature, saturation, and API. Using a fuzzy decision tree enables us to design an expert system which generates EOR rules automatically. This is one of the noticeable features of this study which reduces the importance of a human expert role while designing the system and making it as expert as possible. Here, the fuzzy decision tree method is implemented on a dataset consisting of 548 observations related to 10 different EOR techniques. Predictions made by this method which are ranked from the most applicable EOR method to the least one include the EOR method mentioned in the dataset for every observation in both training and test set. Moreover, using the procedure introduced here for training the trees enables the expert system to be adaptive whenever the dataset is updated.

关键词： Data mining Expert system artificial intelligence algorithms EOR screening Fuzzy logic Fuzzy decision tree Automatic rule generation

来源：评论

学校读者我要写书评

暂无评论

Emerging Technologies for Real-Time Intraoperative Margin Assessment in Future Breast-Conserving Surgery

引用

ADVANCED SCIENCE 2020年第9期7卷 1901519页

作者： Pradipta, Ambara R. Tanei, Tomonori Morimoto, Koji Shimazu, Kenzo Noguchi, Shinzaburo Tanaka, Katsunori RIKEN Cluster Pioneering Res Biofunct Synthet Chem Lab 2-1 Hirosawa Wako Saitama 3510198 Japan Tokyo Inst Technol Sch Mat & Chem Technol Dept Chem Sci & Engn Meguro Ku 2-12-1 Ookayama Tokyo 1528552 Japan Osaka Univ Dept Breast & Endocrine Surg Grad Sch Med 2-2-E10 Yamadaoka Suita Osaka 5650871 Japan Kazan Fed Univ Biofunct Chem Lab A Butlerov Inst Chem 18 Kremlyovskaya St Kazan 420008 Russia RIKEN Baton Zone Program GlycoTargeting Res Lab 2-1 Hirosawa Wako Saitama 3510198 Japan

Clean surgical margins in breast-conserving surgery (BCS) are essential for preventing recurrence. Intraoperative pathologic diagnostic methods, such as frozen section analysis and imprint cytology, have been recognized as crucial tools in BCS. However, the complexity and time-consuming nature of these pathologic procedures still inhibit their broader applicability worldwide. To address this situation, two issues should be considered: 1) the development of nonpathologic intraoperative diagnosis methods that have better sensitivity, specificity, speed, and cost;and 2) the promotion of new imaging algorithms to standardize data for analyzing positive margins, as represented by artificial intelligence (AI), without the need for judgment by well-trained pathologists. Researchers have attempted to develop new methods or techniques;several have recently emerged for real-time intraoperative management of breast margins in live tissues. These methods include conventional imaging, spectroscopy, tomography, magnetic resonance imaging, microscopy, fluorescent probes, and multimodal imaging techniques. This work summarizes the traditional pathologic and newly developed techniques and discusses the advantages and disadvantages of each method. Taking into consideration the recent advances in analyzing pathologic data from breast cancer tissue with AI, the combined use of new technologies with AI algorithms is proposed, and future directions for real-time intraoperative margin assessment in BCS are discussed.

关键词： artificial intelligence algorithms breast cancer breast-conserving surgery deep learning imaging intraoperative diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Filtering Model for Evidence Gathering in an SDN-Oriented Digital Forensic and Incident Response Context

引用

IEEE ACCESS 2024年 12卷 75792-75808页

作者： Jimenez, Maria B. Fernandez, David Rivadeneira, Jorge Eduardo Flores-Moyano, Ricardo Univ Politecn Madrid Dept Telematic Syst Engn ETSI Telecomunicac Madrid 28040 Spain Univ Coimbra Ctr Informat & Syst P-3000214 Coimbra Portugal Univ San Francisco Quito Dept Comp Sci Engn Quito 170901 Ecuador

Software-defined networking (SDN) architecture enables flexible and centralized network management from the controller, making it increasingly attractive in deploying telecommunications services. However, despite the many benefits of SDN, the vulnerabilities inherent in its architecture must be considered, and potential attacks must be discarded. When this occurs, not only the technical areas are interested in the source of the problem, but also the organizational areas, since attacks can violate terms of service and lead to legal actions. Despite the shared interest in cybersecurity event information, forensics and incident response processes often operate independently, impacting the root cause determination. Considering this concern, an architectural evolution for digital forensics and incident response (DFIR) management is introduced. This paper presents an event filtering model that serves as a trigger for initialing the DFIR process, which involves the detection of unusual traffic and unexpected behavior of SDN elements. The proposal applies artificial intelligence technology and showcases the performance of the model and the presentation of a proprietary dataset obtained from OpenFlow traffic.

关键词： Proposals Filtering Feature extraction Denial-of-service attack Support vector machines Digital forensics Recurrent neural networks SDN DFIR SDN forensics SDN attacks SDN cybersecurity DDoS attacks artificial intelligence algorithms SDN dataset

来源：评论

学校读者我要写书评

暂无评论

algorithms as Defendants?

引用

COMPUTER 2024年第7期57卷 11-14页

作者： Voas, Jeffrey Miller, Keith Univ Missouri St Louis MO 63121 USA

This EIC message ponders what can be legally done now (and in the future) to algorithms when they misbehave and create problems for the humans they were designed to serve.

关键词： Accountability Black Box Effective Algorithm Short Message artificial intelligence algorithms Deep Pockets Criminal Proceedings Good Source Of Information Issue For Years

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

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：