检索结果-内蒙古大学图书馆

Discovery of dangerous self-medication methods with patients, by using social network mining

International Journal of Business Intelligence and Data Mining 2023年第3期23卷 277-287页

作者： Samizadeh, Reza Zadeh, Morteza Khavanin Jadidi, Mahsa Rezapour, Mohammad Vatankhah, Sahar Technical & Engineering Faculty Alzahra University Tehran Iran Hasheminejad Kidney Center School of Medicine Iran University of Medical Sciences Tehran Iran Alzahra University Tehran Iran Iranian Ministry of Science Research and Technology Iran Tehran University of Medical Sciences Tehran Iran

Nowadays, social networks have replaced traditional media for information, and unfortunately, some people around the world, instead of reading books, turn to writings that are easily accessible on these networks. The present study categorises Persian texts on the Telegram social network at Jam Hospital and some Iranian websites on metabolic disease, obesity, and diabetes. Classifying data was done by text mining algorithms and the naive Bayes was more accurate than support vector machine. The results conclude that the 'Venustat' is one of the treatments that are emphasised by people, and they recommend this treatment to each other. In medical science, this drug has many complications, and it should not be used arbitrarily. Also a very dangerous drug namely 'Super Slim' is another drug that is strongly recommended by users. Therefore, raising public awareness is necessary to avoid relying on unscientific media content and facilitating access to medical services such as telemedicine. © 2023 Inderscience Enterprises Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Triple-negative Breast Cancer Classification Algorithm based on High-dimensional Big Data of Breast Ultrasound Radiomics

引用

Journal of engineering science and technology Review 2023年第1期16卷 85-91页

作者： Liu, Wen Yao, Hui Leng, Xiaoling Xue, Yutong Ma, Binlin College of Computer Science and Technology Xinjiang Normal University Urumqi830054 China Artificial Intelligence and Smart Mine Engineering Technology Center Xinjiang Institute of Engineering Urumqi830023 China Xinjiang Changsen Data Technology Co. Ltd Urumqi830011 China Department of Ultrasound The Affiliated Tumor Hospital of Xinjiang Medical University Urumqi830011 China RestonVA20191 United States

In computer-aided diagnosis, breast cancer classification accuracy of artificial intelligence (AI) method might be influenced by imbalanced classification samples. Model training efficiency also decreases with the increase in data size. To decrease the influences of sample classification imbalance and increase data size on breast cancer classification efficiency, this study proposed a triple-negative breast cancer classification algorithm (TNBCC) based on similarity query. Similar breast cancer feature data could be stored in a similar region by establishing the TNBCC index. A pruning algorithm was designed based on the TNBCC index, which decreases similarity measurement with nodes of the index tree significantly during data input and query. Users could find data similar to the query object quickly and accurately through the TNBCC index using pruning algorithm, and they could obtain the molecular subtype of the query object according to the searched data. Results demonstrate that, on the real dataset provided by the Affiliated Tumor Hospital of Xinjiang medical University, the TNBCC algorithm decreases the influences of sample classification imbalance on accuracy effectively compared with the existing AI algorithm, and the classification accuracy reaches 91%. Given the mass high-dimensional data, it takes 49 s to build the TNBCC index tree, with an efficiency higher than that of the existing AI algorithm. This study provides a good reference to improve the performances of breast cancer classification algorithm. © 2023 School of science, IHU. All rights reserved.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Smart Aging technology with IoT and Deep Learning Analytics for Elderly Activity Patterns and Health Outcomes 9

Smart Aging Technology with IoT and Deep Learning Analytics ...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Srinivasan, V.Prasanna Pandey, Pramod Muthumarilakshmi, S. Konidhala, Jothibabu. Rajmohan, M. Murugan, S. R.M.D. Engineering College Department of Information Technology Kavaraipettai Tamil Nadu Chennai India Symbiosis institute of Technology Nagpur Campus Maharashtra Pune India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India University of Technology and Applied Sciences- Al Musannah Department of Electronics and Communication Engineering South Al Batina Musanna Oman Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350377972

Innovative healthcare solutions for older people have developed from the fast progress of the Internet of Things (IoT) technology and deep learning (DL). This research proposes a smart aging system that uses IoT devices and Long Short-Term Memory (LSTM) networks to track and evaluate geriatric behavior and health. The proposed approach collects real-time health and daily activity data using a wearable, smart home, and ambient sensors. A central platform uses LSTM networks to identify and forecast activity and health variables from collected data. LSTM can capture long-term relationships and patterns in time-series data, making it ideal. By evaluating these patterns, the system may detect abnormal behavior that may indicate health difficulties like falls, chronic diseases, or cognitive impairment. Preliminary findings show that LSTM-based analytics may provide accurate and timely insights to help caregivers and healthcare providers improve health outcomes. By encouraging mobility and preventive health management, the smart aging system improves older quality of life and decreases healthcare costs. To increase predicted accuracy and system dependability, LSTM models will be refined, the dataset expanded, and more health measures will be included. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Ethanol production from cassava peels using Saccharomyces cerevisiae via ethanologenic fermentation process

Arab Gulf Journal of Scientific Research

引用

Arab Gulf Journal of Scientific Research 2024年第4期42卷 1664-1684页

作者： Sokan-Adeaga, Adewale Allen R.E.E. Ana, Godson Olorunnisola, Abel Olajide Sokan-Adeaga, Micheal Ayodeji Roy, Hridoy Reza, Md Sumon Islam, Md. Shahinoor Department of Environmental Health Sciences Faculty of Public Health College of Medicine University of Ibadan Ibadan Nigeria Department of Environmental Health Science Faculty of Public Health Lead City University Ibadan Nigeria Department of Environmental Health Science Faculty of Basic Medical Sciences Ajayi Crowther University Oyo Nigeria Department of Wood Products Engineering Faculty of Technology University of Ibadan Ibadan Nigeria Department of Microbiology Environmental Microbiology Unit Faculty of Science Obafemi Awolowo University Ile-Ife Nigeria Department of Microbiology General Microbiology Unit Faculty of Science University of Ibadan Ibadan Nigeria Department of Chemical Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Faculty of Natural Sciences Research Institute of New Chemical Technologies L.N. Gumilyov Eurasian National University Astana Kazakhstan Department of Civil Engineering East West University Dhaka Bangladesh

Purpose: This study aims to assess the effect of water variation on bioethanol production from cassava peels (CP) using Saccharomyces cerevisiae yeast as the ethanologenic agent. Design/methodology/approach: The milled CP was divided into three treatment groups in a small-scale flask experiment where each 20 g CP was subjected to two-stage hydrolysis. Different amount of water was added to the fermentation process of CP. The fermented samples were collected every 24 h for various analyses. Findings: The results of the fermentation revealed that the highest ethanol productivity and fermentation efficiency was obtained at 17.38 ± 0.30% and 0.139 ± 0.003 gL⁻¹ h⁻¹. The study affirmed that ethanol production was increased for the addition of water up to 35% for the CP hydrolysate process. Practical implications: The finding of this study demonstrates that S. cerevisiae is the key player in industrial ethanol production among a variety of yeasts that produce ethanol through sugar fermentation. In order to design truly sustainable processes, it should be expanded to include a thorough analysis and the gradual scaling-up of this process to an industrial level. Originality/value: This paper is an original research work dealing with bioethanol production from CP using S. cerevisiae microbe. Highlights: Hydrolysis of cassava peels using 13.1 M H₂SO₄ at 100 ^oC for 110 min gave high Glucose productivity Highest ethanol production was obtained at 72 h of fermentation using Saccharomyces cerevisiae Optimal bioethanol concentration and yield were obtained at a hydration level of 35% agitation Highest ethanol productivity and fermentation efficiency were 17.3%, 0.139 g.L⁻¹.h⁻¹ © 2023, Adewale Allen Sokan-Adeaga, Godson R.E.E. Ana, Abel Olajide Olorunnisola, Micheal Ayodeji Sokan-Adeaga, Hridoy Roy, Md Sumon Reza and Md. Shahinoor Islam.

关键词： Bioenergy Bioethanol Fermentation Glucose productivity Lignocellulosic biomass

来源：评论

学校读者我要写书评

暂无评论

The credentialism trap: are IT certifications overrated?

引用

Strategic HR Review 2024年第2期24卷 55-63页

作者： Tomasz Szandała Department of Computer Engineering Faculty of Computer Science and Management Wroclaw University of Science and Technology Wroclaw Poland and Scuola Universitaria Professionale Della Svizzera Italiana Lugano Switzerland

Purpose This paper aims to explore whether certifications are sufficient for comprehensively evaluating the IT sector, focusing on DevOps, as this branch has the widest range of certifications. It examines the limitations of relying solely on certifications and highlights the gap between certified knowledge and practical competence in real-world settings. Design/methodology/approach The study includes a survey of 72 certified DevOps professionals with varying years of experience to gather insights on the impact of certifications. It also reviews existing literature on the origins, psychological aspects and role of certifications in recruitment within the IT sector. Findings The findings indicate that while certifications enhance technical knowledge and boost confidence among IT professionals, they do not consistently lead to career advancements and sometimes do not adequately assess practical skills and soft skills essential for DevOps roles. The survey revealed that only a minority experienced promotions postcertification, highlighting a disconnect between certifications and career progression. Research limitations/implications The survey sample was limited to 72 respondents, which may not represent the entire DevOps community. Future research with a more extensive and diverse sample could provide more generalisable results and deeper insights into the impact of certifications across different contexts. Practical implications Organisations should consider certifications as one component of a candidate’s qualifications, alongside practical experience and soft skills. Professionals are encouraged to pursue certifications for skill validation and knowledge enhancement but should integrate them with practical application and continuous learning to ensure effectiveness in DevOps environments. Social implications An overemphasis on certifications can contribute to a “credentialist” culture, potentially undervaluing practical skills and leading t

关键词： IT certifications DevOps Credentialism Professional development Training technology Recruitment Learning and development Talent

来源：评论

学校读者我要写书评

暂无评论

A Bi-population Cooperative Optimization Algorithm Assisted by an Autoencoder for Medium-scale Expensive Problems

引用

IEEE/CAA Journal of Automatica Sinica 2022年第11期9卷 1952-1966页

作者： Meiji Cui Li Li MengChu Zhou Jiankai Li Abdullah Abusorrah Khaled Sedraoui IEEE the School of Intelligent Manufacturing Nanjing University of Science and TechnologyNanjing 210094China the Department of Electronics and Information Engineering Tongji UniversityShanghai 201804China the Helen and John C.Hartmann Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07102 USA Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer EngineeringFaculty of Engineeringand K.A.CARE Energy Research and Innovation CenterKing Abdulaziz UniversityJeddah 21589Saudi Arabia

This study presents an autoencoder-embedded optimization(AEO)algorithm which involves a bi-population cooperative strategy for medium-scale expensive problems(MEPs).A huge search space can be compressed to an informative lowdimensional space by using an autoencoder as a dimension reduction *** search operation conducted in this low space facilitates the population with fast convergence towards the *** strike the balance between exploration and exploitation during optimization,two phases of a tailored teaching-learning-based optimization(TTLBO)are adopted to coevolve solutions in a distributed fashion,wherein one is assisted by an autoencoder and the other undergoes a regular evolutionary ***,a dynamic size adjustment scheme according to problem dimension and evolutionary progress is proposed to promote information exchange between these two phases and accelerate evolutionary convergence *** proposed algorithm is validated by testing benchmark functions with dimensions varying from 50 to *** indicated in our experiments,TTLBO is suitable for dealing with medium-scale problems and thus incorporated into the AEO framework as a base *** with the state-of-the-art algorithms for MEPs,AEO shows extraordinarily high efficiency for these challenging problems,t hus opening new directions for various evolutionary algorithms under AEO to tackle MEPs and greatly advancing the field of medium-scale computationally expensive optimization.

关键词： Autoencoder dimension reduction evolutionary algorithm medium-scale expensive problems teaching-learning-based optimization

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm-Based Feature Selection for Accurate Breast Cancer Classification

Genetic Algorithm-Based Feature Selection for Accurate Breas...

引用

2023 International Conference on IT and Industrial Technologies, ICIT 2023

作者： Shabbir, Attia Ali, Raja Hashim Shabbir, Muhammad Zeeshan Abideen, Zain Ul Khan, Talha Ali Ijaz, Ali Zeeshan Ali, Nisar Imad, Muhammad Bakar, Muhammad Abu Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany Department of Electrical Engineering Lahore Pakistan BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain University of Regina Faculty of Electronic Systems Engineering Regina Canada

ISBN: (纸本)9798350315974

Breast cancer is a significant global healthcare challenge, particularly in developing and underdeveloped countries, with profound physical, emotional, and psychological consequences, including mortality. Timely diagnosis and accurate treatment are crucial in addressing this issue. We propose the utilization of a feature selection technique to identify the most relevant features from among all features for breast cancer diagnosis, and show that Genetic Algorithms are impressive for this task. The study compares the results of GA with no selection and an alternative method, Principle Component Analysis (PCA). Three machine learning models, all based on supervised learning with data split into training and test data, are employed for binary classification using the selected feature subset. The evaluation metrics employed encompass accuracy, precision, recall, and F1-score. Among the selected models, Random Forest demonstrates the most favorable outcomes, achieving an accuracy score of 0.96, precision score of 0.96, recall value of 0.98, and an F1-score of 0.97. These results underscore the effectiveness of GA in feature selection for breast cancer diagnosis. Consequently, the integration of Genetic Algorithms (GA) with Random Forest showcases the superior performance among the evaluated models. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enhanced Tele-ENT: A Scalable and Secure AI-Driven Diagnostics for Remote Ear, Nose, and Throat Consultations 1

Cloud-Enhanced Tele-ENT: A Scalable and Secure AI-Driven Dia...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Thenmozhi, R. Anitha, C. Helenprabha, K. Ponkumar, D. David Neels Sivakumar, S. Velmurugan, S. College of Engineering and Technology Srm Institute of Science and Technology Department of Computing Technologies Tamil Nadu Kattankulathur India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India R.M.D. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India VelTech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Department of Computer Science Tamil Nadu Perambalur India Tjs Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350330915

The proposed cutting-edge telemedicine system is a game-changing alternative for patients seeking Ear, Nose, and Throat (ENT) consultations from a distant location. Utilizing the capabilities of Raspberry Pi devices, powerful artificial intelligence, and cloud computing, the system allows otoscopic tests to be performed without interruption while securely transmitting data to the cloud. On a web-based platform, interactive patient-professional consultations are made possible via the use of real-time communication, which is made possible by WebRTC. Cloud services are very important because of its ability to provide scalable storage as well as AI-driven diagnostics for accurate evaluations. The system complies with the requirements for healthcare compliance, has an emphasis on security and privacy, and features encryption from beginning to finish. This integrated approach promises scalability, reliability, and advanced diagnostic capabilities, and it reshapes the landscape of remote ENT care with accessible and technologically advanced healthcare solutions. With a user-friendly interface for patients and a cloud-hosted application for healthcare professionals, this integrated approach provides patients with advanced healthcare solutions. © 2023 IEEE.

关键词： Artificial Intelligence Cloud Computing Otoscopic Examinations Remote Healthcare Tele-ENT

来源：评论

学校读者我要写书评

暂无评论

Fairness Under Cover: Evaluating the Impact of Occlusions on Demographic Bias in Facial Recognition

arXiv

引用

arXiv 2024年

作者： Mamede, Rafael M. Neto, Pedro C. Sequeira, Ana F. Faculty of Engineering The University of Porto Porto Portugal Institute for Systems and Computer Engineering Technology and Science Porto Portugal

This study investigates the effects of occlusions on the fairness of face recognition systems, particularly focusing on demographic biases. Using the Racial Faces in the Wild (RFW) dataset and synthetically added realistic occlusions, we evaluate their effect on the performance of face recognition models trained on the BUPT-Balanced and BUPT-GlobalFace datasets. We note increases in the dispersion of FMR, FNMR, and accuracy alongside decreases in fairness according to Equilized Odds, Demographic Parity, STD of Accuracy, and Fairness Discrepancy Rate. Additionally, we utilize a pixel attribution method to understand the importance of occlusions in model predictions, proposing a new metric, Face Occlusion Impact Ratio (FOIR), that quantifies the extent to which occlusions affect model performance across different demographic groups. Our results indicate that occlusions exacerbate existing demographic biases, with models placing higher importance on occlusions in an unequal fashion, particularly affecting African individuals more severely. Copyright © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Child Physical Exercise with Pose Estimation Using Virtual Cartoon Avatar

Enhancing Child Physical Exercise with Pose Estimation Using...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Jyotirmay Patel Shrey Shah Vaidik Teraiya Vedant Teraiya Dweepna Garg Parth Goel Department of Computer Engineering Devang Patel Institute of Advance Technology & Research (DEPSTAR) Faculty of Technology & Engineering (FTE) Charotar University of Science & Technology (CHARUSAT) Changa India Department of Computer Science & Engineering Devang Patel Institute of Advance Technology & Research (DEPSTAR) Faculty of Technology & Engineering (FTE) Charotar University of Science & Technology (CHARUSAT) Changa India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

This research concerns the design of an intelligent workout tracking application based on OpenCV and MediaPipe that will improve user's participation and the performance of exercises. Physical activity helps to prevent diseases and improve and maintain the quality of life as it offers benefits across the system. Nowadays, in growing period, where parents give their children a smartphone to keep them busy, can have negative impacts on their growth. This research paper is designed to contribute in the discussion of replacing smartphone by reorienting children to motivate for physical and active plays. The suggested intervention utilizes colorful cartoon for helping in the refinement of fine exercise activities. This has been done through estimating the poses of the various postures. Under muscle groups, the application includes three exercises; Hands up, Hands on side, and Palm rotation, and instant feedback accompanied by a virtual model. The findings of the study suggest that its use causes enhanced exercise accuracy and user enjoyment due to the instant error messages, and the interactivity, which enhance safe and effective workouts.

关键词： Hands Accuracy Green communications Avatars Pose estimation Muscles Diseases

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：