检索结果-内蒙古大学图书馆

BRAIN-TO-TEXT BENCHMARK’24: LESSONS LEARNED

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Willett, Francis R. Li, Jingyuan Le, Trung Fan, Chaofei Chen, Mingfei Shlizerman, Eli Chen, Yue Zheng, Xin Okubo, Tatsuo S. Benster, Tyler Lee, Hyun Dong Kounga, Maxwell Buchanan, E. Kelly Zoltowski, David Linderman, Scott W. Henderson, Jaimie M. Department of Neurosurgery Stanford University United States Department of Electrical & Computer Engineering University of Washington United States Department of Computer Science Stanford University United States Department of Applied Mathematics University of Washington United States China Neurosciences Phd Program Stanford University United States Wu Tsai Neurosciences Institute Department of Statistics Stanford University United States

Speech brain-computer interfaces aim to decipher what a person is trying to say from neural activity alone, restoring communication to people with paralysis who have lost the ability to speak intelligibly. The Brain-to-Text Benchmark’24 and associated competition was created to foster the advancement of decoding algorithms that convert neural activity to text. Here, we summarize the lessons learned from the competition ending on June 1, 2024 (the top 4 entrants also presented their experiences in a recorded webinar). The largest improvements in accuracy were achieved using an ensembling approach, where the output of multiple independent decoders was merged using a fine-tuned large language model (an approach used by all 3 top entrants). Performance gains were also found by improving how the baseline recurrent neural network (RNN) model was trained, including by optimizing learning rate scheduling and by using a diphone training objective. Improving upon the model architecture itself proved more difficult, however, with attempts to use deep state space models or transformers not yet appearing to offer a benefit over the RNN baseline. The benchmark will remain open indefinitely to support further work towards increasing the accuracy of brain-to-text algorithms. © 2024, CC BY.

关键词： Recurrent neural networks

COEM: Cross-Modal Embedding for MetaCell Identification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mao, Haiyi Jia, Minxue Dou, Jason Xiaotian Zhang, Haotian Benos, Panayiotis V. Department of Computational and Systems Biology University of Pittsburgh PA United States Joint Carnegie Mellon University University of Pittsburgh PhD Program in Computational Biology United States Department of Electrical and Computer Engineering University of Pittsburgh PA United States

Metacells are disjoint and homogeneous groups of single-cell profiles, representing discrete and highly granular cell states. Existing metacell algorithms tend to use only one modality to infer metacells, even though single-cell multi-omics datasets profile multiple molecular modalities within the same cell. Here, we present Cross-MOdal Embedding for MetaCell Identification (COEM), which utilizes an embedded space leveraging the information of both scATAC-seq and scRNA-seq to perform aggregation, balancing the trade-off between fine resolution and sufficient sequencing coverage. COEM outperforms the state-of-the-art method SEACells by efficiently identifying accurate and well-separated metacells across datasets with continuous and discrete cell types. Furthermore, COEM significantly improves peak-to-gene association analyses, and facilitates complex gene regulatory inference tasks. © 2022, CC BY.

关键词： Embeddings

Probabilistic Genotype-Phenotype Maps Reveal Mutational Robustness of RNA Folding, Spin Glasses, and Quantum Circuits

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sappington, Anna Mohanty, Vaibhav Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States Program for Health Sciences and Technology Harvard Medical School BostonMA02115 United States Massachusetts Institute of Technology CambridgeMA02139 United States Harvard/MIT MD-PhD Program Harvard Medical School BostonMA02115 United States Department of Chemistry and Chemical Biology Harvard University CambridgeMA02138 United States

Recent studies of genotype-phenotype (GP) maps have reported universally enhanced phenotypic robustness to genotype mutations, a feature essential to evolution. Virtually all of these studies make a simplifying assumption that each genotype—represented as a sequence—maps deterministically to a single phenotype, such as a discrete structure. Here, we introduce probabilistic genotype-phenotype (PrGP) maps, where each genotype maps to a vector of phenotype probabilities, as a more realistic and universal language for investigating robustness in a variety of physical, biological, and computational systems. We study three model systems to show that PrGP maps offer a generalized framework which can handle uncertainty emerging from various physical sources: (1) thermal fluctuation in RNA folding, (2) external field disorder in spin glass ground state finding, and (3) superposition and entanglement in quantum circuits, which are realized experimentally on IBM quantum computers. In all three cases, we observe a novel biphasic robustness scaling which is enhanced relative to random expectation for more frequent phenotypes and approaches random expectation for less frequent phenotypes. We derive an analytical theory for the behavior of PrGP robustness, and we demonstrate that the theory is highly predictive of empirical robustness. © 2023, CC BY.

关键词： Quantum computers

Multiplexed Serial Imaging of Immunotherapy Response with Serrs Nanoprobes

学校读者我要写书评

暂无评论

Multiplexed Serial Imaging of Immunotherapy Response with Se...

IEEE International Symposium on Biomedical Imaging

作者： Naxhije Berisha Konstantinos Plakas Matthieu Gigoux Taha Merghoub Chrysafis Andreou Hunter College of the City University of New York New York NY USA PhD Program in Chemistry The Graduate Center of the City University of New York NY USA Memorial Sloan Kettering Cancer Center New York NY USA Department of Chemistry University at Buffalo The State University of New York Buffalo NY USA Weill Cornell Medicine New York NY USA Department of Electrical and Computer Engineering University of Cyprus Nicosia Cyprus

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

With the advent of new and promising cancer therapies, and with increased interest in precision medicine, there is an urgent need to develop non-invasive technologies that evaluate heterogeneity in treatment response. We demonstrate an 8-plex imaging platform based on surface enhanced resonance Raman scattering nanoparticles (SERRS NPs) to monitor the expression of 4 immunomarkers before and after treatment with checkpoint blockade therapy with anti-CTLA4 and anti-PD-1 antibodies in immunotherapy models of colon (CT26) and breast (4T1) cancers. We found that CT26 tumors showed an early treatment response, while the typically refractory 4T1 tumors demonstrated an unexpected treatment response, suggesting that the nanoparticles may have synergistically contributed to the treatment. Serial imaging of multiple markers during therapy can help predict treatment efficacy and uncover new theranostic adjuvants.

关键词： Nanoparticles Multiplexing Precision medicine Raman scattering Immunotherapy Resonance Surface treatment

Towards innovative electrodiagnosis tests to investigate neuromuscular excitability dysfunction in critically ill patients: an agreement study

学校读者我要写书评

暂无评论

Research on Biomedical engineering 2023年第4期39卷 949-958页

作者： Silva, Paulo Eugênio Martins, Henrique Resende de Deus Macedo, José Roberto de Queiroz, Alessandra Vasconcelos Ultra de Aguiar, Agda Martins, Emerson Fachin Physical Therapy Division Hospital de Base do Distrito Federal. Instituto de Gestão Estratégica de Saúde do Distrito Federal SMHS Área Especial Quadra 101 DF BrasíliaCEP 70.330-150 Brazil Universidade de São Paulo Faculdade de Medicina SP São Paulo Brazil Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais MG Belo Horizonte Brazil Health Sciences and Technologies PhD Program University of Brasilia DF Brasília Brazil Intensive Care Division Hospital de Base do Distrito Federal Instituto de Gestão Estratégica de Saúde do Distrito Federal DF Brasília Brazil Physical Therapy Division Hospital Regional de Ceilândia Secretaria de Estado de Saúde do Distrito Federal DF Brasília Brazil Physical Therapy Division Hospital de Base do Distrito Federal Instituto de Gestão Estratégica de Saúde do Distrito Federal DF Brasília Brazil Graduate Programs in Health Sciences and Technologies and in Rehabilitation Sciences Physical Therapy Department Faculdade de Ceilândia Universidade de Brasília DF Brasília Brazil

Purpose: Early diagnosis of ICU-acquired weakness can support the ICU team in applying appropriate interventions which may lead to better results at clinical and functional outcomes. Thus, interest has increased in non-invasive and more feasible methods to diagnose neuromuscular dysfunction, such as the stimulus electrodiagnosis test (SET) and strength-duration test (SDT). The aim of the present study was to assess the agreement of the SET and SDT carried out automatically using an innovative method. Methods: We performed a prospective observational study to determine the agreement of SET and SDT, performed automatically using a biofeedback circuit to detect muscle contractions, comprised of an accelerometer module connected to an electrical stimulator. These tests were applied in healthy and critically ill participants. Results: Twenty-one participants were analyzed in the study, and 168 assessments of SET and SDT were performed. The Bland-Altman analysis of automatic SET and SDT in the control group showed a low bias of −25 (95% CI, −94.3 to 44.3 μs) and 0.6 (95% CI, −1.9 to 3.1 μC) respectively. In the critically ill group, automatic SET and SDT presented a low bias of −104.5 (95% CI, −1716 to 1507μs) and −12.6 (95% CI, −119.4 to 94.1 μC) respectively. Conclusions: We demonstrated that an innovative method to carry out SET and SDT automatically presents low agreement bias and good to excellent reliability. © 2023, The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering.

关键词： Intensive care units

Dish-Trend: Intervention Modeling Simulator That Accounts for Trend Influences

学校读者我要写书评

暂无评论

Dish-Trend: Intervention Modeling Simulator That Accounts fo...

Simulation Winter Conference

作者： Stefan Andjelkovic Natasa Miskov-Zivanov Computational and Systems Biology Joint Carnegie Mellon University and University of Pittsburgh Computational Biology PhD Program University of Pittsburgh Pittsburgh PA USA Electrical and Computer Engineering Bioengineering Computational and Systems Biology University of Pittsburgh Pittsburgh PA USA

ISBN: (纸本)9781665433129

Simulation on directed graphs is an important method for understanding the dynamics in the systems where connectivity graphs contain cycles. Discrete Stochastic Heterogeneous Simulator (DiSH) is one of the simulation tools with wide application, which uses regulator values to calculate state updates of regulated elements. Here we present a new simulation approach DiSH-trend which also takes into account the trends in regulating elements. We demonstrate the features of trend-based regulation, as well as hybrid regulation, which is a combination of the trend- and level-based approaches. The modeling capabilities are demonstrated on a small toy model, showcasing different functionalities. Real-world capabilities are demonstrated on a larger network model of food insecurity in the Ethiopian region Oromia. Adding trend-based regulation to models results in increased modeling flexibility, and hybrid regulation improves qualitative dynamic behavior prediction. With appropriate data, DiSH-trend becomes a powerful tool for exploring intervention strategies.

关键词： Regulators Toy manufacturing industry Stochastic processes Predictive models Market research Regulation Data models

Probabilistic Power Flow Analysis Based on Low Rank Approximation and Principle Component Analysis

学校读者我要写书评

暂无评论

Probabilistic Power Flow Analysis Based on Low Rank Approxim...

Conference on Power, Energy and Innovations (ICPEI)

作者： Jirasak Laowanitwattana Sermsak Uatrongjit PhD’s Degree Program in Electrical Engineering Faculty of Engineering Chiang Mai University Chiang Mai Thailand Faculty of Engineering Chiang Mai University Chiang Mai Thailand

Probabilistic power flow (PPF) analysis is usually applied for evaluating the effects of uncertain parameters on power system performances. This paper presents a technique to enhance the arbitrary polynomial chaos expansion (aPCE) based PPF analysis technique when applying to system with many uncertain parameters. The proposed method represents a power system response as low rank approximation (LRA). In addition, the principle component analysis (PCA) is applied to reduce the number of uncertain parameters and also de-correlate them. This combination enables the proposed method to perform PPF of the power system having large number of uncertain parameters. Based on preliminary numerical results on the modified IEEE 57-bus system, it can be noticed that the proposed modified method is able to find accurate statistical characteristics of the responses but uses less computation time compared to the MCS based PPF analysis.

关键词： Chaos Technological innovation Probabilistic logic Power systems Principal component analysis Load flow analysis

Spatial atlas of the mouse central nervous system at molecular resolution (vol 622, pg 552, 2023)

学校读者我要写书评

暂无评论

NATURE 2024年第7993期625卷 E6-E6页

作者： Shi, Hailing He, Yichun Zhou, Yiming Huang, Jiahao Maher, Kamal Wang, Brandon Tang, Zefang Luo, Shuchen Tan, Peng Wu, Morgan Lin, Zuwan Ren, Jingyi Thapa, Yaman Tang, Xin Chan, Ken Y. Deverman, Benjamin E. Shen, Hao Liu, Albert Liu, Jia Wang, Xiao Broad Institute of MIT and Harvard Cambridge MA USA Department of Chemistry Massachusetts Institute of Technology Cambridge MA USA John A. Paulson School of Engineering and Applied Sciences Harvard University Boston MA USA Computational and Systems Biology PhD Program Massachusetts Institute of Technology Cambridge MA USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Department of Biology Massachusetts Institute of Technology Cambridge MA USA Klarman Cell Observatory Broad Institute of MIT and Harvard Cambridge MA USA Department of Chemistry and Chemical Biology Harvard University Cambridge MA USA Stanley Center for Psychiatric Research Broad Institute of MIT and Harvard Cambridge MA USA

A Framework for Interpretability in Machine Learning for Medical Imaging

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Alan Q. Karaman, Batuhan K. Kim, Heejong Rosenthal, Jacob Saluja, Rachit Young, Sean I. Sabuncu, Mert R. School of Electrical and Computer Engineering Cornell University Cornell Tech New YorkNY10044 United States Department of Radiology Weill Cornell Medical School New YorkNY10065 United States Weill Cornell/Rockefeller/Sloan Kettering Tri-Institutional MD-PhD Program New YorkNY10065 United States Martinos Center for Biomedical Imaging Harvard Medical School BostonMA02129 United States Computer Science and Artificial Intelligence Laboratory MIT CambridgeMA02139 United States

Interpretability for machine learning models in medical imaging (MLMI) is an important direction of research. However, there is a general sense of murkiness in what interpretability means. Why does the need for interpretability in MLMI arise? What goals does one actually seek to address when interpretability is needed? To answer these questions, we identify a need to formalize the goals and elements of interpretability in MLMI. By reasoning about real-world tasks and goals common in both medical image analysis and its intersection with machine learning, we identify five core elements of interpretability: localization, visual recognizability, physical attribution, model transparency, and actionability. From this, we arrive at a framework for interpretability in MLMI, which serves as a step-by-step guide to approaching interpretability in this context. Overall, this paper formalizes interpretability needs in the context of medical imaging, and our applied perspective clarifies concrete MLMI-specific goals and considerations in order to guide method design and improve real-world usage. Our goal is to provide practical and didactic information for model designers and practitioners, inspire developers of models in the medical imaging field to reason more deeply about what interpretability is achieving, and suggest future directions of interpretability research. © 2023, CC0.

关键词： Machine learning