检索结果-内蒙古大学图书馆

Medical Imaging 2023: Biomedical Applications in Molecular, Structural, and Functional Imaging

作者： Wismüller, Axel Vosoughi, Ali Kasturi, Akhil Hadjiyski, Nathan Department of Electrical and Computer Engineering University of Rochester NY United States Department of Imaging Sciences University of Rochester NY United States Department of Biomedical Engineering University of Rochester NY United States Faculty of Medicine and Institute of Clinical Radiology Ludwig Maximilian University Munich Germany Department of Computer Science University of Rochester NY United States

ISBN: (纸本)9781510660410

Schizophrenia is associated with alternations in brain network connectivity. We investigate whether large-scale Granger Causality (lsGC) can capture such alterations using resting-state fMRI data. Our method utilizes dimension reduction combined with the augmentation of source time-series in a predictive time-series model for estimating directed causal relationships among fMRI time-series. As a multivariate approach, lsGC identifies the relationship of the underlying dynamic system in the presence of all other time-series. Here, we examine the ability of lsGC to accurately identify schizophrenia patients from fMRI data using a subset of 31 subjects from the Centers of Biomedical Research Excellence (COBRE) data repository. We use brain connections estimated by lsGC as features for classification. After feature extraction, we perform feature selection by Kendall's tau rank correlation coefficient followed by classification using a support vector machine. For reference, we compare our results with cross-correlation, typically used in the literature as a standard measure of functional connectivity, and several other standard methods. Using 100 different training/test data splits with 10-fold cross-validation we obtain mean/std f1-scores of 84.20% ± 20.42% and mean Area Under the receiver operating characteristic Curve (AUC) values of 94.50% ± 15.24% across all tested numbers of features for lsGC, which is significantly better than the results obtained with cross-correlation (AUC=64.50% ± 33.39%, f1-score=46.67% ± 34.01%), and multiple other competing methods, including partial correlation, tangent, precision, and covariance methods. Our results suggest the applicability of lsGC as a potential imaging biomarker for schizophrenia. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Advancements in Packaging Materials: Trends, Sustainability, and Future Prospects

Circular Economy and Sustainability

引用

Circular Economy and Sustainability 2025年 1-32页

作者： Cordeiro, Alisha Hussain, Mariya Ramachandran, T. Beemkumar, N. Kumar, Raman Karthikeyan, A. Bupesh Raja, V.K. Thatoi, Dhirendra Nath Mahapatro, Abinash Nanda, Jajneswar Prakash, Chander Patil, Arun Y. Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal 576104 + 91 - *** India Department of Mechanical Engineering Vivekananda Global University Rajasthan Jaipur India School of Mechanical Engineering Rayat Bahra University Punjab Kharar 140103 India Faculty of Engineering Sohar University PO Box 44 Sohar PCI 311 Oman Department of Mechanical Engineering Chandigarh Engineering College Chandigarh Group of Colleges-Jhanjeri Punjab Mohali 140307 India Department of Mechanical Engineering Siksha ’O’ Anusandhan (Deemed to be University) Odisha Bhubaneswar 751030 India Department of Mechanical Engineering University Centre for Research and Development Chandigarh University Punjab Gharuan Mohali India Bio-inspired Design and Optimization Centre (BIODOC) Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal 576104 India Department of Mechanical Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal 576104 India

Packaging plays a crucial role in product transportation, storage, and safety, with materials evolving to meet modern demands. Plastic packaging dominates due to its versatility, while paper and metal alternatives are gaining traction due to recyclability and durability. Bioinspired packaging and damage-tolerant designs are emerging trends, with China leading in research. The COVID-19 pandemic has accelerated the demand for medical packaging, where the United States leads in innovation. Advances in biodegradable materials, including biopolymers, plant-based Fibers, and smart packaging, are shaping the future of the industry. While challenges such as cost, durability, and barrier properties persist, innovations in nanotechnology and active packaging are enhancing performance. The shift toward sustainability and the 3R principles—Reduce, Reuse, Recycle continues to drive research and industry transformation. Compliance with regulatory requirements is increasingly supported by emerging technologies, including IoT, blockchain, and cyber-physical systems. Innovations in medical packaging include nanotechnology for barrier protection, modified atmosphere packaging (MAP), and intelligent packaging (IP), enhancing product quality and safety. Key design considerations focus on tamper-evident features, sterilization, and user-friendly accessibility, especially for children and the elderly. Material selection prioritizes microbial sterility, barrier properties, and durability to ensure product integrity. Sustainability remains a critical focus, with increasing adoption of biodegradable materials and efforts to minimize environmental impact. Future research aims to address gaps in sustainable packaging, regulatory compliance, and advanced material development to further improve packaging efficiency, safety, and eco-friendliness in the medical and pharmaceutical industries. © The Author(s) 2025.

关键词： Biodegradable polymers Bioinspired packaging Medical packaging Smart packaging Sustainable packaging

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Blood Donors Classification Model Using Ensemble Learning 3rd

Machine Learning for Blood Donors Classification Model Using...

引用

3rd World Conference on Internet of Things: Applications and Future, ITAF 2023

作者： El-rashidy, Nora El-Ghamry, Amir ElSayed, Nesma E. Machine Learning and Information Retrieval Department Faculty of Artificial Intelligence Kafrelsheiksh University Kafrelsheiksh Egypt Faculty of Computers and Information Mansoura University Mansoura Egypt School of Engineering and Computer Science Hosted By Global Academic Foundation University of Hertfordshire Garden City Egypt Faculty of Computer Science and Engineering New Mansoura University Mansoura Egypt Delta Higher Institute for Management and Accounting Information Systems Mansoura Egypt

ISBN: (纸本)9789819947638

Blood transfusion is in constant demand, as it is required for several medical procedures and life-or-death operations. This study is motivated by the fact that the need for blood transfusions is steadily on the rise because of accidents, operations, diseases, etc. such that the ability to accurately predict the number of blood donors allows medical personnel to predict the future blood supply and plan accordingly to recruit enough volunteers to meet demand. We attempt to handle this supply–demand gap by using a predictive model that identifies potential donors. We model the probability of a person donating blood, depending on five specific features, using machine learning techniques. This paper implements a machine learning pipeline that includes data preprocessing and donor classification. Several ensemble models have been developed. The results show that the random forest model led to the best test set accuracy (96.3%), which beat other methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Development and Validation of Customer Intention Factors for Live-Stream Shopping 7

Development and Validation of Customer Intention Factors for...

引用

7th International Conference on New Media Studies, CONMEDIA 2023

作者： Fernando, Erick Hidayat, Desman Pengaribuan, Christian Haposan Prabowo, Yulius Denny Universitas Multimedia Nusantara Faculty of Engineering and Informatics Department of Information System Tangerang Indonesia Bina Nusantara University Binus Entrepreneurship Center Management Department Jakarta11480 Indonesia Sampoerna University Management Study Program Faculty of Business Jakarta12780 Indonesia Bina Nusantara University Binus Online Learning Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350307504

Along with technological improvements, online shopping is currently developing quickly. Online shops started by selling electronics, clothing, food, and home appliances and continue to evolve, selling various things. Currently, digital marketing has a novel technique, namely live shopping, where sellers can present, promote and offer their products directly through live streaming on social media and e-commerce platforms. This research will focus on gaining insight into the factors influencing customers to watch and purchase through live streaming. This research is an early-stage study of exploring and searching for research models. The study used a literature review approach by reviewing similar previous research articles. Several variable components were used in this study. The findings of the factors include visibility capacity, meta-vocation capacity, purchase orientation capacity, social presence, price, perceived product quality, perceived enjoyment, purchase orientation, perceived usefulness, and intention to buy. These factors were tested and proved to be valid with Cronbach's Alpha value being more than 0.5 and reliable with the value of the loading factor a greater than 0.6. Criteria The factors of the findings for further analysis of the relationship between factors and other variables. © 2023 IEEE.

关键词： Domestic appliances

来源：评论

学校读者我要写书评

暂无评论

Development of a Closed Chamber system for Cultivating Lion's Mane Mushrooms using an Internet of Things system to Increase Yield and Economic Value

Development of a Closed Chamber System for Cultivating Lion'...

引用

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Pakorn Suntornmeth Kanitha Homjun Worawit Fankam-Ai Charnyut Karnjanapiboon Atigorn Sanguansri Athiphong Deenoi Sirilux Kaewsirirung Department of Computer Science Faculty of Science and Agricultural Technology Rajamangala University of Technology Lanna Nan Nan Thailand Department of Electrical Engineering Faculty of Engineering Rajamangala University of Technology Lanna Nan Nan Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

This research investigates the development and implementation of an Internet of Things (IoT)-based closedsystem prototype for cultivating Yamabushitake (Lion's Mane) mushrooms, addressing the challenges of achieving optimal yields in Thailand's climate. Conducted at Saengkaew Mushroom Farm located in Nan Province, the study focuses on precise environmental control within the prototype chamber. The system employs an ESP32-IOXESP32U microcontroller and an AM2315 sensor to monitor and manage temperature, humidity, and airflow. A comparative analysis with a traditional evaporative cooling system reveals the closed system's superior performance in achieving higher yields and improved energy efficiency. The assessment of economic feasibility is conducted via a Cost-Benefit Analysis (CBA), demonstrating the potential for increased profitability and sustainable mushroom cultivation. This research offers significant findings regarding the utilization of IoT technology to enhance mushroom production and advance sustainable agricultural practices in Thailand.

关键词： Economics Temperature sensors Temperature measurement Scalability Prototypes Robustness Energy efficiency Maintenance Internet of Things Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Analysis of Liquid Biopsies for Uterus Cancer Biomarker Discovery 9

Deep Learning-Based Analysis of Liquid Biopsies for Uterus C...

引用

9th IEEE International Conference on Smart Structures and systems, ICSSS 2023

作者： Lalitha, S. Haque, Mohammed Irfanul Sujay, V. Shenbagapriya, M. Ganapathy, G. Salyan, Srikanth R&d Institute of Science and Technology Vel Tech Rangarajan Dr.Sagunthala Department of Cse Tamil Nadu Chennai India Jamia Millia Islamia Faculty of Dentistry Department of Anaesthesiology New Delhi India Krishna University College of Engineering and Technology Department of Computer Science and Engineering Andhra Pradesh Machilipatnam India Muthayammal Engineering College Department of BioMedical Engineering Tamilnadu Namakkal India R.M.D. Engineering College Department of Mathematics Tamil Nadu Chennai India Dayananda Sagar College of Engineering Department of Aeronautical Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350384208

In regard to the critical nature of early cancer detection, including uterine cancer, non-invasive liquid biopsies are demonstrating their utility. The present study presents an innovative deep-learning approach specifically designed for the examination of liquid specimens, aiming to detect potential biomarkers associated with uterine cancer. By employing advanced neural network architectures and sizable genomic datasets, the methodology discerns particular molecular markers that are correlated with uterine cancer. The implementation of personalized treatment plans and early intervention strategies to enhance patient outcomes is a feasible prospect rendered feasible by the results of this study. This innovative methodology signifies a turning point in the continuous effort to combat uterine cancer and exemplifies the potential transformative effects that deep learning techniques could have on cancer prognosis and precision medicine. © 2023 IEEE.

关键词： Biopsy

来源：评论

学校读者我要写书评

暂无评论

Development of a Closed Chamber system for Cultivating Lion's Mane Mushrooms using an Internet of Things system to Increase Yield and Economic Value 10

Development of a Closed Chamber System for Cultivating Lion'...

引用

10th International Conference on Digital Arts, Media and Technology and 8th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2025

作者： Suntornmeth, Pakorn Homjun, Kanitha Fankam-Ai, Worawit Karnjanapiboon, Charnyut Sanguansri, Atigorn Deenoi, Athiphong Kaewsirirung, Sirilux Rajamangala University of Technology Lanna Nan Faculty of Science and Agricultural Technology Department of Computer Science Nan Thailand Rajamangala University of Technology Lanna Nan Faculty of Engineering Department of Electrical Engineering Nan Thailand

ISBN: (纸本)9798331543273

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Estimation Large-Scale Fading Channels for Transmit Orthogonal Pilot Reuse Sequences in Massive MIMO system

Estimation Large-Scale Fading Channels for Transmit Orthogon...

引用

2022 International Conference on Intelligent Technology, system and Service for Internet of Everything, ITSS-IoE 2022

作者： Abdullah, Qazwan Shah, Nor Shahida Mohd Hamzah, Shipun Salh, Adeb Mohamad, Mahathir Nordin, Shahilah Abu, Maisarah Albaom, Mohammed Abdo Sadeq, Safwan Community College of Yareem Ibb Yemen Universiti Tun Hussein Faculty of Engineering Technology Johor Malaysia Universiti Tun Hussein Faculty of Electrical and Electronic Engineering Johor Malaysia Universiti Tun Hussein Faculty of Applied Sciences and Technology Johor Malaysia Malaysia Faculty of Electrical Engineering Pulau Pinang Malaysia University Technical Malaysia Malacca Faculty of Electronic and Computer Engineering Malacca Malacca City Malaysia Universiti Putra Serdang Faculty of Computer Science and Information Technology Department of Computer Science Malaysia Universiti Teknologi Petronas Department of Mechanical Engineering Perak Malaysia

ISBN: (数字)9781665459983

ISBN: (纸本)9781665459983

Massive multiple-input multiple-output (MIMO) is a critical technology for future fifth-generation (5G) systems. Reduced pilot contamination (PC) enhanced system performance, and reduced inter-cell interference and improved channel estimation. However, because the pilot sequence transmitted by users in a single cell to neighboring cells is not orthogonal, massive MIMO systems are still constrained. We propose channel evaluation using orthogonal pilot reuse sequences (PRS) and zero forced (ZF) pre-coding techniques to eliminate channel quality in end users with poor channel quality based on channel evaluation, large-scale shutdown evaluation, and analysis of maximum transmission efficiency. We derived the lower bounds on the downlink data rate (DR) and signal-to-interference noise ratio (SINR) that can be achieved based on PRS assignment to a group of users where the number of antenna elements mitigated the interference when the number of antennas reaches infinity. The channel coherence interval limitation, the orthogonal PRS cannot be allocated to all UEs in each cell. The short coherence intervals able to reduce the PC and improve the quality of channel. The results of the modelling showed that higher DR can be achieved due to better channel evaluation and lower loss. © 2022 IEEE.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

Identification of a Distant Speaker and Its Robustness*

引用

Chinese Journal of Electronics 2023年第2期20卷 278-282页

作者： Ye Jiang Zhenmin Tang Longbiao Wang School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China Department of System Engineering Shizuoka University Japan

Robust speaker identification is presented for speech recorded by distant microphones. Three compensation approaches are investigated to improve the robustness of speaker identification in such environments. The first approach applies spectral subtraction before feature extraction to reduce the late-reverberation effect. The second approach makes use of feature warping as feature compensation in distant speaker identification under mismatched training-testing conditions. The third approach employs a novel method of initializing Gaussian mixture model parameters: combined division and k-means clustering. The experiment results show that, relative to the baseline system based on CMN, the channel-average recognition rates for the compensated system were 11.4%, 15.4%, 17.0%, and 17.8% higher for the TIMIT database and 6.8%, 6.4%, 9.3%, and 14.0% higher for the JNAS database for four different environments. In addition, the results show that the combination of the three approaches has better performance than the use of a single compensation method.

关键词： Databases Feature extraction Robustness Gaussian mixture model Microphones

来源：评论

学校读者我要写书评

暂无评论

Real-Time Scheduling for Energy Optimization: Smart Grid Integration with Renewable Energy 7

Real-Time Scheduling for Energy Optimization: Smart Grid Int...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Gopalakrushna, A. Raj, Vijilius Helena Vani, V. Divya Singh, Navdeep Jethabhai, Patel Yogeshkumar Chakravarthi, M. Kalyan Vignana Bharathi Institute of technology Telangana Hyderabad India New Horizon College of Engineering Department of Applied Sciences Karnataka Bangalore India Institute of Aeronautical Engineering Dundigal Hyderabad India Lovely Professional University Phagwara India Sankalchand Patel University Faculty of Computer Science Shri C.J. Patel College of Computer Studies Gujarat Visnagar India University of Technology and Applied Sciences Department of Electronics and Communication Engineering Muscat Oman

ISBN: (纸本)9798350350067

Reliable power system operations, cost reduction, demand and supply balance maintenance, and efficient load scheduling all depend on real-time energy optimisation. Nevertheless, the unpredictability of electric loads and renewable energy sources (RES) makes real-time energy optimization difficult. As a result, the Energy Management Controller (EMC) was developed, which can automatically react to DR signals and resolve energy-related issues. In light of this, EDGE, a hybrid algorithm combining elements of genetic algorithm (GA) and enhanced differential evolution (EDE), is devised in this work. The EDGE algorithm is used to train the EMC to automatically react to DR signals and schedule the 3 classes of household loads - hybrid, non-interruptible, and interruptible - to handle energy management issues. The results show that in terms of power cost reduction, minimizing carbon release, PAR relief, and client discomfort maximization, the suggested EDGE algorithm performs better than benchmark methods. © 2024 IEEE.

关键词： energy optimization renewable energy Smart grid

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：