检索结果-内蒙古大学图书馆

A Novel Wireless Sensor Network Data Aggregation Algorithm Based on Self-organizing Feature Mapping Neutral Network

学校读者我要写书评

暂无评论

Ingenierie des Systemes d'Information 2019年第1期24卷 119-123页

作者： Zhou, Hong Yu, Kunming Program in Engineering Science Chung Hua University Hsinzhu30012 Taiwan Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai’an223005 China College of Computer Science and Electrical Engineer Chung Hua University Hsinzhu30012 Taiwan

Data aggregation is an efficient method to save energy and prolong the service life of wireless sensor networks (WSNs). In light of this, a data aggregation algorithm was constructed based on self-organizing feature mapping (SOFM) neural network and WSN cluster routing protocol. In this algorithm, each cluster was designed as a three-layer neural network model, which collect a large number of raw data. Then, the feature data were extracted from the raw data, and sent to the sink node. Through a simulation experiment, it is proved that the proposed algorithm, denoted as SOFMDA, outperformed a popular data aggregation method in energy consumption and data accuracy. © 2019 Lavoisier. All rights reserved.

关键词： Wireless sensor networks

A Deep Learning Model with Radiomics Analysis Integration for Glioblastoma Post-Resection Survival Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Zongsheng Yang, Zhenyu Zhang, Haozhao Vaios, Eugene Lafata, Kyle Yin, Fang-Fang Wang, Chunhao Medical Physics Graduate Program Duke Kunshan University Jiangsu Kunshan215316 China Department of Radiation Oncology Duke University DurhamNC27710 United States Department of Radiology Duke University DurhamNC27710 United States Department of Electrical and Computer Engineering Duke University DurhamNC27710 United States

Purpose: To develop a novel deep learning model that integrates radiomics analysis in a multi-dimensional feature fusion workflow for glioblastoma (GBM) post-resection survival prediction Methods: A cohort of 235 GBM patients with complete surgical resection was divided into short-term/long-term survival groups with 1-yr survival time threshold. Each patient received a pre-surgery multi-parametric MRI exam with 4 scans: T1, contrast-enhanced T1 (T1ce), T2, and FLAIR. Three tumor subregions were segmented by neuroradiologists, and the whole dataset was divided into training, validation, and test groups following a 7:1:2 ratio. The developed model comprises three data source branches: in the 1st radiomics branch, 456 radiomics features (RF) were calculated from the three tumor subregions of each patient’s MR images;in the 2nd deep learning branch, an encoding neural network architecture was trained for survival group prediction using each single MR modality, and high-dimensional parameters from the last two network layers were extracted as deep features (DF). The extracted radiomics features and deep features were processed by a feature selection procedure to reduce the dimension size of each feature space. In the 3rd branch, patient-specific clinical features (PSCF), including patient age and three tumor subregions volumes, were collected from the dataset. Finally, data sources from all three branches were fused as an integrated input for a supporting vector machine (SVM) execution for survival group prediction. Different strategies of model design were investigated in comparison studies, including 1) 2D/3D-based image analysis, 2) different radiomics feature space dimension reduction methods, and 3) different data source combinations in SVM input design. Results: The model achieved 0.638 prediction accuracy in the test set when using patient-specific clinical features only, which was higher than the results using radiomics features/deep features as sole input of SVM

关键词： Magnetic resonance imaging

Current status of the preclinical evaluation of alternating electric fields as a form of cancer therapy

学校读者我要写书评

暂无评论

Bioelectrochemistry 2023年 149卷 108287页

作者： Pohling, Christoph Nguyen, Ha Chang, Edwin Schubert, Keith E. Nie, Ying Bashkirov, Vladimir Yamamoto, Vicky Zeng, Yuping Stupp, Roger Schulte, Reinhard W. Patel, Chirag B. Division of Biomedical Engineering Sciences Loma Linda University School of Medicine Loma LindaCA92350 United States Department of Electrical and Computer Engineering Baylor University WacoTX76798 United States Molecular Imaging Program at Stanford Department of Radiology Stanford University School of Medicine StanfordCA94305 United States Department of Neurosurgery Loma Linda University School of Medicine Loma LindaCA92350 United States Norris Comprehensive Cancer Center University of Southern California Keck School of Medicine Los AngelesCA90033 United States Department of Electrical and Computer Engineering University of Delaware NewarkDE19716 United States Department of Neurosurgery Department of Neurology Division of Neuro-OncologyDepartment of Medicine Division of Hematology/Oncology Northwestern University Feinberg School of Medicine ChicagoIL60611 United States Department of Neuro-Oncology The University of Texas MD Anderson Cancer Center HoustonTX77030 United States Neuroscience Graduate Program The University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences HoustonTX77030 United States Cancer Biology Graduate Program The University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences HoustonTX77030 United States

Exposing cancer cells to alternating electric fields of 100-300 kHz frequency and 1-4 V/cm strength has been shown to significantly reduce cancer growth in cell culture and in human patients. This form of anti-cancer therapy is more commonly referred to as tumor treating fields (TTFields), a novel treatment modality that has been approved by the U.S. Food and Drug Administration for use in patients with glioblastoma and malignant pleural mesothelioma. Pivotal trials in other solid organ cancer trials are underway. In regards to overall survival, TTFields alone is comparable to chemotherapy alone in recurrent glioblastoma. However, when combined with adjuvant chemotherapy, TTFields prolong median survival by 4.9 months in newly-diagnosed glioblastoma. TTFields hold promise as a therapeutic approach to numerous solid organ cancers. This review summarizes the current status of TTFields research at the preclinical level, highlighting recent aspects of a relatively complex working hypothesis. In addition, we point out the gaps between limited preclinical in vivo studies and the available clinical data. To date, no customized system for TTFields delivery in rodent models of glioblastoma has been presented. We aim to motivate the expansion of TTFields preclinical research and facilitate the availability of suitable hardware, to ultimately improve outcomes in patients with cancer. © 2022 The Authors

关键词： Tumors

Advanced Methods for Connectome-Based Predictive Modeling of Human Intelligence: A Novel Approach Based on Individual Differences in Cortical Topography

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Anderson, Evan D. Wilcox, Ramsey Nayak, Anuj Zwilling, Christopher Robles-Granda, Pablo Kim, Been Varshney, Lav R. Barbey, Aron K. Neuroscience Program University of Illinois UrbanaIL United States Department of Psychology University of Illinois UrbanaIL United States Department of Electrical & Computer Engineering University of Illinois UrbanaIL United States Beckman Institute University of Illinois UrbanaIL United States Department of Computer Science University of Illinois UrbanaIL United States Google Brain Mountan View CA United States

Individual differences in human intelligence can be modeled and predicted from in vivo neurobiological connectivity. Many established modeling frameworks for predicting intelligence, however, discard higher-order information about individual differences in brain network topology, and show only moderate performance when generalized to make predictions in out-of-sample subjects. In this paper, we propose that connectome-based predictive modeling, a common predictive modeling framework for neuroscience data, can be productively modified to incorporate information about brain network topology and individual differences via the incorporation of bagged decision trees and the network based statistic. These modifications produce a novel predictive modeling framework that leverages individual differences in cortical tractography to generate accurate regression predictions of intelligence scores. Network topology-based feature selection provides for natively interpretable networks as input features, increasing the model's explainability. Investigating the proposed modeling framework's efficacy, we find that advanced connectome-based predictive modeling generates neuroscience predictions that account for a significantly greater proportion of variance in general intelligence scores than previously established methods, advancing our scientific understanding of the network architecture that underlies human intelligence. © 2022, CC BY-SA.

关键词： Forecasting

Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Rajendran, Suraj Pan, Weishen Sabuncu, Mert R. Chen, Yong Zhou, Jiayu Wang, Fei Tri-Institutional Computational Biology & Medicine Program Cornell University NY United States Division of Health Informatics Department of Population Health Sciences Weill Cornell Medicine New YorkNY United States School of Electrical and Computer Engineering Cornell University IthacaNY United States Cornell Tech New YorkNY United States Department of Radiology Weill Cornell Medical School New YorkNY United States Department of Biostatistics Epidemiology and Informatics University of Pennsylvania PhiladelphiaPA United States Department of Computer Science and Engineering Michigan State University East LansingMI United States

Machine learning (ML) in healthcare presents numerous opportunities for enhancing patient care, population health, and healthcare providers' workflows. However, the real-world clinical and cost benefits remain limited due to challenges in data privacy, heterogeneous data sources, and the inability to fully leverage multiple data modalities. In this perspective paper, we introduce "patchwork learning" (PL), a novel paradigm that addresses these limitations by integrating information from disparate datasets composed of different data modalities (e.g., clinical free-text, medical images, omics) and distributed across separate and secure sites. PL allows the simultaneous utilization of complementary data sources while preserving data privacy, enabling the development of more holistic and generalizable ML models. We present the concept of patchwork learning and its current implementations in healthcare, exploring the potential opportunities and applicable data sources for addressing various healthcare challenges. PL leverages bridging modalities or overlapping feature spaces across sites to facilitate information sharing and impute missing data, thereby addressing related prediction tasks. We discuss the challenges associated with PL, many of which are shared by federated and multimodal learning, and provide recommendations for future research in this field. By offering a more comprehensive approach to healthcare data integration, patchwork learning has the potential to revolutionize the clinical applicability of ML models. This paradigm promises to strike a balance between personalization and generalizability, ultimately enhancing patient experiences, improving population health, and optimizing healthcare providers' workflows. © 2023, CC BY.

关键词： Data privacy

Active Pixel TFT Arrays for Digital Fluoroscopy in a-Si:H Technology

学校读者我要写书评

暂无评论

MRS Online Proceedings Library 2020年第1期862卷 2241-2246页

作者： Jackson Lai Nader Safavian Arokia Nathan John A. Rowlands Electrical and Computer Engineering Department University of Waterloo Waterloo Ontario Canada Imaging Research Program Sunnybrook Health Science Centre Toronto Ontario Canada

Major development challenges in application of hydrogenated amorphous silicon (a-Si:H) technology to large area digital X-ray imaging and technological attributes such as low temperature deposition and high uniformity over large area evolve around dynamic imaging modalities such as fluoroscopy, which demands both high speed readout and signal amplification capabilities in addition to long term device stability. This work reports on initial results of a variety of TFT active pixel sensor (APS) structures in a-Si:H technology, each demonstrating unique capabilities such as enhancements in signal gain, TFT threshold voltage immunity, and real-time high speed readout.

关键词：

Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets 1

学校读者我要写书评

暂无评论

Reduce Fingerprint Construction for Positioning IoT Devices ...

1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020

作者： Tarekegn, Getaneh Berie Juang, Rong-Terng Lin, Hsin-Piao Munaye, Yirga Yayeh Belay Adege, Abebe National Taipei University of Technology Department of International Graduate Program in Electrical Engineering and Computer Science Taipei Taiwan Feng Chia University Department of Electronic Engineering Taichung Taiwan National Taipei University of Technology Department of Electronic Engineering Taipei Taiwan Debre Markos University Department of Information Technology Debre Markos Ethiopia

ISBN: (纸本)9781665404839

Fingerprint-based positioning is popular and applicable for Internet of Things (IoT) applications to offer seamless, intelligent and adaptive location-aware services for IoT devices. However, it takes time and cost to build the radio-map. This paper proposed deep convolutional Generative adversarial nets (DCGANs) to minimize the site survey time and cost, and to mitigate signal fluctuations. The radio-map was designed for receiving radio signals from detectable wireless local area network (WLAN) and cellular networks in scalable environments. The proposed fingerprinting-based positioning is a sequential combination of the hybrid support vector machine and long short-term memory algorithms. The experimental results indicate that the proposed method achieves a promising and reasonable positioning performance for IoT devices in scalable wireless environments. © 2020 IEEE.

关键词： Support vector machines

Implementing ASLNet V1.0: Progress and plans 11

学校读者我要写书评

暂无评论

Implementing ASLNet V1.0: Progress and plans

11th Global Wordnet Conference, GWC 2021

作者： Lualdi, Colin P. Wright, Elaine Hudson, Jack Caselli, Naomi K. Fellbaum, Christiane SignSchool Inc. MadisonWI United States Department of Physics University of Illinois Urbana-ChampaignIL United States Department of Electrical Engineering Princeton University PrincetonNJ United States Program in Linguistics Princeton University PrincetonNJ United States Programs in Deaf Studies Boston University BostonMA United States Department of Computer Science Princeton University PrincetonNJ United States

ISBN: (纸本)9789464027310

We report on the development of ASLNet, a wordnet for American Sign Language (ASL). ASLNet V1.0 is currently under construction by mapping easy-to-translate ASL lexical nouns to Princeton WordNet synsets. We describe our data model and mapping approach, which can be extended to any sign language. Analysis of the 390 synsets processed to date indicates the success of our procedure yet also highlights the need to supplement our mapping with the "merge" method. We outline our plans for upcoming work to remedy this, which include use of ASL free-association data. © GWC 2021. All rights reserved.

关键词： Mapping

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORKS

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of AIIS ASRI INMC ISRC NSI Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks