检索结果-内蒙古大学图书馆

TextAI 3.0 (Multimodal): multimodal sentiment analysis using attention-enabled ensemble-based deep learning in hyperbolic space

引用

International Journal of Information Technology (Singapore) 2025年 1-16页

作者： Singh, Jaskaran Sanga, Prabhav Khanna, Narendra N. Laird, John R. Singh, Inder M. Kalra, Mannudeep K. Mantella, Laura E. Johri, Amer M. Faa, Gavino Tiwari, Ekta Singh, Rajesh Abbas, Mohamed Saba, Luca Suri, Jasjit S. Stroke Monitoring and Diagnostic Division AtheroPoint™ Roseville 95661 CA United States Bharati Vidyapeeth’s College of Engineering New Delhi India Department of Cardiology Indraprastha APOLLO Hospitals New Delhi 110001 India Department of Neurology and Stroke Program University of Maryland School of Medicine Baltimore United States Department of Radiology Harvard Medical School Boston 02115 MA United States Department of Biomedical and Molecular Sciences Queen’s University Kingston ON Canada Division of Cardiology Department of Medicine Queen’s University Kingston ON Canada Department of Pathology University of Cagliari Cagliari Italy Department of Computer Science Visvesvaraya National Institute of Technology (VNIT) Nagpur 440010 India Department of Research and Innovation Uttaranchal Institute of Technology Uttaranchal University Dehradun 248007 India Central Labs King Khalid University P.O. Box 960 AlQura’a Abha Saudi Arabia Electrical Engineering Department College of Engineering King Khalid University Abha 61421 Saudi Arabia Department of Neurology University of Cagliari Cagliari Italy Department of ECE Idaho State University Pocatello 83209 ID United States Department of CE Graphic Era Deemed to Be University Dehradun 248002 India University Center for Research and Development Chandigarh University Mohali India Symbiosis Institute of Technology Symbiosis International (Deemed University) Nagpur Campus Pune India Department of Innovation Global Biomedical Technologies Inc. Roseville 95661 CA United States

The rising prevalence of depression presents a significant global health challenge, underscoring the need for effective early detection through sentiment analysis. Traditional multimodal sentiment analysis methods, which rely on Euclidean space for data representation, often fail to capture the complex hierarchical relationships and non-linear structures inherent in multimodal data. To address this limitation, we propose a novel multimodal architecture that operates in hyperbolic space and incorporates attention-based ensemble learning to enhance feature representation and model performance. We developed and evaluated ten AI models—five utilizing Euclidean space and five leveraging hyperbolic space—on the Spoken Language Understanding Evaluation (SLUE) benchmark dataset. The models were assessed using cross-validation techniques to ensure robustness, and statistical analyses were conducted to validate the findings. Our results indicate that hyperbolic-based multimodal models achieve a 2.32% improvement in accuracy compared to their Euclidean counterparts, while the integration of self-attention mechanisms further contributes an average accuracy gain of 0.96%. Additionally, we observed a 3.76% decline in performance when reducing the training-to-test data ratio from 90:10 to 50:50, highlighting the importance of data distribution in model training. These findings confirm that attention-enhanced multimodal models in hyperbolic space offer superior representations for sentiment analysis. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.

关键词： Attention-enabled Deep learning Euclidean space Hyperbolic space Multimodal Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Complexity Analysis based on Parietal Fuzzy Entropy to Facilitate ADHD Diagnosis in Young Children

Complexity Analysis based on Parietal Fuzzy Entropy to Facil...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： I-Wen Huang Yu-Ci Jheng I-Chun Chen Li-Wei Ko Institute of Biomedical Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan International Program in Interdisciplinary Neuroscience College of Biological Science and Technology National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Physical Medicine and Rehabilitation Ton-Yen General Hospital Hsinchu Taiwan Drug Development and Value Creation Research Center Kaohsiung Medical University Kaohsiung Taiwan

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Attention deficit hyperactivity disorder (ADHD) is the most common condition affecting the development of neurons in children. Therefore, early and accurate diagnosis of ADHD in young children is of paramount importance. In this study, the 8-channel wireless wearable EEG measurement device was employed to record EEG data from 30 children diagnosed with ADHD and 30 typical development (TD) young children aged 4-7 years. The data was collected both during rest and while the children performed a Kiddie Continuous Performance Test (K-CPT). We extract relative power spectral density (PSD) unaffected by factors like skull resistance and thickness. Additionally, a range of complex entropy values based on the time domain were extracted. These included sample entropy (SaEn), permutation entropy (PeEn), singular value decomposition entropy (SvdEn), and fuzzy entropy (FuEn). We compare the performance of k-Nearest Neighbors (kNN), Support Vector Machine (SVM), and XGBoost, and utilized the sequential forward selection (SFS) feature selection method in the wrapper approach. Through this process, the study identified the most effective EEG data segments and feature subsets. The findings indicated that using a combination of resting and K-CPT EEG data yielded greater discriminability. Notably, the study found that extracting beta power from the right occipital lobe along with fuzzy entropy from the parietal lobe resulted in optimal accuracy of 90% in distinguishing between children with ADHD and TD children. These outcomes highlight the potential of relative PSD and complexity metrics to support the clinical diagnosis of early ADHD. Furthermore, these metrics may contain unique neurobiomarkers that could be valuable for devising early intervention strategies.

关键词： Support vector machines Performance evaluation Pediatrics Accuracy Aging Feature extraction Entropy Electroencephalography Complexity theory Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Halobacterium salinarum NRC-1 Sustains Voltage Production in a Dual-Chambered Closed Microbial Fuel Cell

引用

Scientific World Journal 2022年第1期2022卷 3885745页

作者： Goncalves, Rodrigo Oliveira Salehi, Ali Publico, Marlon Nyende, Jimmy Nadarajah, Nalina Ghoreyshi, Soheil Shastri, Padmaja Biomedical Engineering Program Applied Biological and Environmental Science Centennial College 941 Progress Avenue Scarborough M1G 3T8 Canada Biotechnology Program Applied Biological and Environmental Science Centennial College 755 Morningside Avenue Scarborough M1C 4Z4 Canada

Sustained bioenergy production from organisms that thrive in high salinity, low oxygen, and low nutrition levels is useful in monitoring hypersaline polluted environments. Microbial fuel cell (MFC) studies utilizing single species halophiles under salt concentrations higher than 1 M and as a closed microbial system are limited. The current study aimed to establish baseline voltage, current, and power density from a dual-chambered MFC utilizing the halophile Halobacterium salinarum NRC-1. MFC performance was determined with two different electrode sizes (5 cm2 and 10 cm2), under oscillating and nonoscillating conditions, as well as in a stacked series. A closed dual-chamber MFC system of 100 mL capacity was devised with Halobacterium media (4.3 M salt concentration) as both anolyte and catholyte, with H. salinarum NRC-1 being the anodic organism. The MFC measured electrical output over 7, 14, 28, and 42 days. MFC output increased with 5 cm2 sized electrodes under nonoscillating (p<0.0001) relative to oscillating conditions. However, under oscillating conditions, doubling the electrode size increased MFC output significantly (p=0.01). The stacked series MFC, with an electrode size of 10 cm2, produced the highest power density (1.2672 mW/m2) over 14 days under oscillation. Our results highlight the potentiality of H. salinarum as a viable anodic organism to produce sustained voltage in a closed-MFC system. © 2022 Rodrigo Oliveira Goncalves et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Export- and import-based economic models for predicting global trade using deep learning

引用

Expert Systems with Applications 2023年第1期218卷

作者： Yang, Cheng-Hong Lee, Cheng-Feng Chang, Po-Yin Department of Information Management Tainan University of Technology Tainan City710302 Taiwan Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung80778 Taiwan Drug Development and Value Creation Research Center Kaohsiung Medical University Kaohsiung80708 Taiwan Ph. D. Program in Biomedical Engineering Kaohsiung Medical University Kaohsiung80708 Taiwan School of Dentistry Kaohsiung Medical University Kaohsiung80708 Taiwan Department of Business Administration National Kaohsiung University of Science and Technology Kaohsiung80778 Taiwan Department of Computer Science and Information Engineering National Quemoy University Kinmen County 892 Taiwan

Forecasting global foreign trade is essential for developing government trade policies and management strategies for multinational corporations. However, achieving an accurate trade forecast is challenging because of the complex structural relationships between exports, imports and other economic variables. Many traditional forecasting models, such as time series, econometric, and machine learning, provide less accurate forecasts for trade data. This paper proposes an ensemble learning approach to improve forecasting performance by hybridizing the structural relationships between trade and deep learning models to predict foreign trade for ten major countries. The proposed method first establishes a cointegration relationship between exports and imports and their structural variables. The cointegrated models are then used to predict the future of trade, which is used as a benchmark model for comparison. A hybrid deep learning algorithm uses the cointegrated variables as input variables to predict trade data, and then are compared with time-series forecasts and economic structural models. The experimental results reveal that the ensemble learning method can achieve excellent forecasting performance for the tested periods of trade data. In most cases, the root means square error and mean absolute percentage error values are smaller than the time series and economic structural models. © 2023 Elsevier Ltd

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Computational modeling of the physical features that influence breast cancer invasion into adipose tissue

arXiv

引用

arXiv 2024年

作者： Zheng, Yitong Wang, Dong Beeghly, Garrett Fischbach, Claudia Shattuck, Mark D. O’Hern, Corey S. Department of Mechanical Engineering & Materials Science Yale University New HavenCT06520 United States Integrated Graduate Program in Physical and Engineering Biology Yale University New HavenCT06520 United States Nancy E. and Peter C. Meinig School of Biomedical Engineering Cornell University IthacaNY14853 United States Benjamin Levich Institute Physics Department City College of New York New YorkNY10031 United States Department of Physics Yale University New HavenCT06520 United States

Breast cancer invasion into adipose tissue strongly influences disease progression and metastasis. The degree of cancer cell invasion into adipose tissue depends on numerous biochemical and physical properties of cancer cells, adipocytes, and other key components of adipose tissue. We model breast cancer invasion into adipose tissue as a physical process by carrying out simulations of active, cohesive spherical particles (cancer cells) invading into confluent packings of deformable polyhedra (adipocytes). We quantify the degree of invasion by calculating the interfacial area At between cancer cells and adipocytes. We determine the long-time value of At versus the activity and strength of the cohesion between cancer cells, as well as mechanical properties of the adipocytes and extracellular matrix (ECM) in which the adipocytes are embedded. We show that the degree of invasion collapses onto a master curve by plotting it versus a dimensionless energy scale Ec, which grows linearly with mean-square fluctuations and persistence time of the cancer cell velocities, is inversely proportional to the pressure of the system, and has an offset that increases with the cancer cell cohesive energy. The condition, Ec 1, indicates that cancer cells will invade the adipose tissue, whereas for Ec 1, the cancer cells and adipocytes remain demixed. We also show that constraints on adipocyte positions by the ECM decrease At relative to that obtained for unconstrained adipocytes. Finally, spatial heterogeneity in structural and mechanical properties of the adipocytes in the presence of ECM impedes invasion relative to adipose tissue with uniform properties. © 2024, CC BY-NC-ND.

关键词： Cancer cells

来源：评论

学校读者我要写书评

暂无评论

The effect of ultraviolet exposure on physical properties of electrospun nanofiber membrane based on polyvinyl alcohol and aloe vera 4th

The effect of ultraviolet exposure on physical properties of...

引用

4th Padjadjaran International Physics Symposium, PIPS 2019

作者： Hikmawati, Dyah Maharani, Noveni Putri Putra, Alfian Pramudita Siswanto Department of Physics Faculty of Science and Technology Universitas Airlangga SurabayaEast Java60115 Indonesia Biomedical Engineering Study Program Department of Physics Faculty of Science and Technology Universitas Airlangga SurabayaEast Java60115 Indonesia Biomedical Signals and Systems Research Group Faculty of Science and Technology Universitas Airlangga SurabayaEast Java60115 Indonesia

ISBN: (纸本)9783035716979

Ultraviolet (UV) irradiation in biomaterial synthesis is commonly used to do sterilization and to improve the physical characteristics. This study is aimed to study the characteristics of polyvinyl alcohol-Aloe vera (PVA-AV) nanofibers from electrospinning process, that was exposed by UV for 6 h with various power of 8, 10, 15, and 20 W. The physical properties of the fiber were characterized by using Scanning Electron Microscope (SEM), Fourier Transform Infrared (FTIR), Differential Scanning Calorimetry (DSC) test, and water absorption test. The SEM images showed that the nanofibers were formed with s homogeneous structure and no bead was observed. The diameter and the thickness of the nanofibers are increased with the increase of the power of UV exposed to the samples. The biggest diameter was 319.60 ± 56.17 nm obtained at UV exposure power of 20 W. The FTIR test result indicated that there was no new chemical bond after the PVA-AV was exposed by UV. Meanwhile, the DSC test showed that the increase of power could increase the melting temperature (Tm) with the highest value of 189.51°C at UV exposure power of 20 W. The water absorption test showed that the highest water absorption was 739.6 % obtained at UV exposure power of 20 W. © 2020 Trans Tech Publications Ltd, Switzerland.

关键词： Nanofibers

来源：评论

学校读者我要写书评

暂无评论

k-mer-based approaches to bridging pangenomics and population genetics

arXiv

引用

arXiv 2024年

作者： Roberts, Miles D. Davis, Olivia Josephs, Emily B. Williamson, Robert J. Genetics and Genome Sciences Program Michigan State University East LansingMI48824 United States Department of Computer Science and Software Engineering Rose-Hulman Institute of Technology Terre HauteIN47803 United States Department of Biology and Biomedical Engineering Rose-Hulman Institute of Technology Terre HauteIN47803 United States Department of Plant Biology Michigan State University East LansingMI48824 United States Ecology Evolution and Behavior Program Michigan State University East LansingMI48824 United States Plant Resilience Institute Michigan State University East LansingMI48824 United States

Many commonly studied species now have more than one chromosome-scale genome assembly, revealing a large amount of genetic diversity previously missed by approaches that map short reads to a single reference. However, many species still lack multiple reference genomes and correctly aligning references to build pangenomes is challenging, limiting our ability to study this missing genomic variation in population genetics. Here, we argue that k-mers are a crucial stepping stone to bridging the reference-focused paradigms of population genetics with the reference-free paradigms of pangenomics. We review current literature on the uses of k-mers for performing three core components of most population genetics analyses: identifying, measuring, and explaining patterns of genetic variation. We also demonstrate how different k-mer-based measures of genetic variation behave in population genetic simulations according to the choice of k, depth of sequencing coverage, and degree of data compression. Overall, we find that k-mer-based measures of genetic diversity scale consistently with pairwise nucleotide diversity (π) up to values of about π = 0.025 (R2 = 0.97) for neutrally evolving populations. For populations with even more variation, using shorter k-mers will maintain the scalability up to at least π = 0.1. Furthermore, in our simulated populations, k-mer dissimilarity values can be reliably approximated from counting bloom filters, highlighting a potential avenue to decreasing the memory burden of k-mer based genomic dissimilarity analyses. For future studies, there is a great opportunity to further develop methods to identifying selected loci using k-mers. © 2024, CC BY.

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Generation of spheroids using an aqueous two-phase system droplet microfluidic platform 24

Generation of spheroids using an aqueous two-phase system dr...

引用

24th International Conference on Miniaturized Systems for Chemistry and Life sciences, MicroTAS 2020

作者： Kieda, Jennifer Jeyhani, Morteza Navi, Maryam Chan, Katherine Tsai, Scott S.H. Graduate Program in Biomedical Engineering Ryerson University Toronto Canada Department of Mechanical and Industrial Engineering Ryerson University Toronto Canada Keenan Research Centre for Biomedical Science St. Michael's Hospital Toronto Canada -a Partnership Between Ryerson University St. Michael's Hospital Canada

ISBN: (纸本)9781733419017

Two-dimensional (2-D) cell culture platforms fail to mimic in vivo physiological functions, such as intercellular interactions [1], so a three-dimensional (3-D) cell structure platform is desired to facilitate physiological insights. We present a new droplet microfluidic platform for the generation of cancer cell spheroids by encapsulation and isolation of Caki-2 cancer cells in droplets based on the higher affinity of the cells to the droplet phase in an aqueous two-phase system (ATPS) droplet microfluidic device. © 2020 CBMS-0001

关键词： Cancer cells

来源：评论

学校读者我要写书评

暂无评论

Fracture risk assessment from 2D-DXA scan by supervised machine learning modeling

引用

Osteoporosis and Sarcopenia 2023年第4期9卷 S2-S2页

作者： Heesun Choi Luca Quagliato Yoon-Sok Chung Taeyong Lee Division of Mechanical and Biomedical Engineering Ewha Womans University Republic of Korea Division of Mechanical and Biomedical Engineering Graduate Program in System Health Science and Engineering Ewha Womans University Republic of Korea Ajou University Hospital Republic of Korea

来源：评论

学校读者我要写书评

暂无评论

Machine learning for improved current-density reconstruction from two-dimensional vector magnetic images

引用

Physical Review Applied 2025年第3期23卷 034035-034035页

作者： Niko R. Reed Danyal Bhutto Matthew J. Turner Declan M. Daly Sean M. Oliver Jiashen Tang Kevin S. Olsson Nicholas Langellier Mark J.H. Ku Department of Physics University of Maryland College Park Maryland USA Quantum Technology Center University of Maryland College Park Maryland USA Joint Quantum Institute University of Maryland College Park Maryland USA Department of Biomedical Engineering Boston University Boston Massachusetts USA A. A. Martinos Center for Biomedical Imaging Massachusetts General Hospital Charlestown Massachusetts USA Department of Electrical and Computer Engineering University of Maryland College Park Maryland USA The MITRE Corporation McLean Virginia 22102 USA Intelligence Community Postdoctoral Research Fellowship Program University of Maryland College Park Maryland 20742 USA Department of Physics Harvard University Cambridge Massachusetts USA Present address: VideaHealth Inc. Boston MA. Department of Materials Science and Engineering University of Delaware Newark Delaware 19716 USA Department of Physics and Astronomy University of Delaware Newark Delaware 19716 USA Present address: Northrop Grumman Mission Systems Linthicum Maryland 21090 USA.

The reconstruction of electrical current densities from magnetic field measurements is an important technique with applications in materials science, circuit design, quality control, plasma physics, and biology. Analytic reconstruction methods exist for planar currents, but break down in the presence of high-spatial-frequency noise or large standoff distance, restricting the types of systems that can be studied. Here, we demonstrate the use of a deep convolutional neural network for current density reconstruction from two-dimensional images of vector magnetic fields acquired by a quantum diamond microscope . Trained network performance significantly exceeds analytic reconstruction for data with high noise or large standoff distances. This machine learning technique can perform quality inversions on lower-signal-to-noise-ratio data, significantly reducing the data collection time and permitting reconstructions of weaker and three-dimensional current sources.

关键词： Signal to noise ratio

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：