检索结果-内蒙古大学图书馆

Optimising knee injury detection with spatial attention and validating localisation ability

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Belton, Niamh Welaratne, Ivan Dahlan, Adil Hearne, Ronan T. Hagos, Misgina Tsighe Lawlor, Aonghus Curran, Kathleen M. Science Foundation Ireland Centre for Research Training in Machine Learning School of Medicine University College Dublin Department of Radiology Mater Misericordiae University Hospital Dublin Ireland School of Electronic Engineering University College Dublin School of Computer Science University College Dublin Insight Centre for Data Analytics University College Dublin Dublin Ireland

This work employs a pre-trained, multi-view Convolutional Neural Network (CNN) with a spatial attention block to optimise knee injury detection. An open-source Magnetic Resonance Imaging (MRI) data set with image-level labels was leveraged for this analysis. As MRI data is acquired from three planes, we compare our technique using data from a single-plane and multiple planes (multi-plane). For multi-plane, we investigate various methods of fusing the planes in the network. This analysis resulted in the novel 'MPFuseNet' network and state-of-the-art Area Under the Curve (AUC) scores for detecting Anterior Cruciate Ligament (ACL) tears and Abnormal MRIs, achieving AUC scores of 0.977 and 0.957 respectively. We then developed an objective metric, Penalised Localisation Accuracy (PLA), to validate the model's localisation ability. This metric compares binary masks generated from Grad-Cam output and the radiologist's annotations on a sample of MRIs. We also extracted explainability features in a model-agnostic approach that were then verified as clinically relevant by the radiologist. Copyright © 2021, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

The 28th AIAI irish conference on artificial intelligence and cognitive science

学校读者我要写书评

暂无评论

CEUR Workshop Proceedings 2020年 2771卷

作者： Longo, Luca Rizzo, Lucas Hunter, Elizabeth Pakrashi, Arjun Technological University Dublin School of Computer Science Ireland Machine Learning Labs Science Foundation Ireland Centre for Research Training Ireland D-Real Science Foundation Ireland Centre for Research Training in Digitally-Enhanced Reality Ireland CeADAR Enterprise Ireland's Centre for Applied Artificial Intelligence Ireland University College Dublin School of Computer Science Ireland Insight Centre for Data Analytics Ireland

Language-Agnostic Bias Detection in Language Models with Bias Probing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Koksal, Abdullatif Yalcin, Omer Faruk Akbiyik, Ahmet Kilavuz, M. Tahir Korhonen, Anna Schutze, Hinrich Center for Information and Language Processing LMU Munich Germany Munich Center for Machine Learning Germany Data Analytics and Computational Social Science University of Massachusetts Amherst United States Harvard Kennedy School United States Middle East Initiative Harvard Kennedy School United States Marmara University Turkey Language Technology Lab University of Cambridge United Kingdom

Pretrained language models (PLMs) are key components in NLP, but they contain strong social biases. Quantifying these biases is challenging because current methods focusing on fill-the-mask objectives are sensitive to slight changes in input. To address this, we propose a bias probing technique called LABDet, for evaluating social bias in PLMs with a robust and language-agnostic method. For nationality as a case study, we show that LABDet "surfaces" nationality bias by training a classifier on top of a frozen PLM on non-nationality sentiment detection. We find consistent patterns of nationality bias across monolingual PLMs in six languages that align with historical and political context. We also show for English BERT that bias surfaced by LABDet correlates well with bias in the pretraining data;thus, our work is one of the few studies that directly links pretraining data to PLM behavior. Finally, we verify LABDet's reliability and applicability to different templates and languages through an extensive set of robustness checks. We publicly share our code and dataset in https://***/akoksal/LABDet. Copyright © 2023, The Authors. All rights reserved.

关键词： machine learning

A Mobile Solution for Rhythmic Auditory Stimulation Gait Training

学校读者我要写书评

暂无评论

A Mobile Solution for Rhythmic Auditory Stimulation Gait Tra...

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

作者： Katharina Aholt Christine F. Martindale Arne Küderle Heiko Gaßner Till Gladow Javier Rojo Samanta Villanueva-Mascato Jochen Klucken Maria Teresa Arredondo Waldmeyer Bjoern M. Eskofier Machine Learning and Data Analytics Lab Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany University Hospital Erlangen Germany Escuela Técnica Superior de Ingenieros de Telecomunicación Universidad Politécnica de Madrid Madrid Spain Life Supporting Technologies Universidad Politécnica de Madrid Spain

Recent studies showed that Parkinson's disease (PD) patients improved their gait parameters while walking with rhythmic auditory stimulation (RAS). They achieved a longer stride length, a reduced stride time variability and a higher walking speed. Combining RAS with mobile gait analysis would allow continuous monitoring of RAS effects and gait in natural environments. This paper proposes a mobile solution for home-based assessment of RAS by combining RAS gait training and a mobile system for data acquisition. Existing datasets were used to investigate the cadence of PD patients and to propose suitable frequencies for RAS gait training. The cadence calculation was implemented using a peak detection algorithm, which uses the time difference between two mid-swing events as stride time values. We validated our system as a whole using a cohort of 13 PD patients who performed RAS gait training. The algorithms were also validated against the eGaIT system, a state-of-the-art system, and achieved a mean F 1 score for detected strides of 97.57 % ± 0.86 % and a mean absolute error for the cadence of 0.16 spm ± 0.09 spm. This study lays the ground work for further clinical studies investigating the effectiveness of mobile RAS within a home environment.

关键词： Training Sensors Mobile handsets Parkinson's disease Legged locomotion Gyroscopes data analysis

Big data = Big Insights? Operationalising Brooks’ Law in a Massive GitHub data Set

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gote, Christoph Schweitzer, Frank Mavrodiev, Pavlin Scholtes, Ingo Department of Systems Design ETH Zurich Weinbergstrasse 56/58 Zurich8092 Switzerland Department of Computer Science XV - Machine Learning for Complex Networks Julius-Maximilians-Universität Würzburg Friedrich-Bergius-Ring 30 Würzburg97076 Germany Data Analytics Group University of Zurich Binzmühlestrasse 14 Zurich8050 Switzerland

Massive data from software repositories and collaboration tools are widely used to study social aspects in software development. One question that several recent works have addressed is how a software project’s size and structure influence team productivity, a question famously considered in Brooks’ law. Recent studies using massive repository data suggest that developers in larger teams tend to be less productive than smaller teams. Despite using similar methods and data, other studies argue for a positive linear or even super-linear relationship between team size and productivity, thus contesting the view of software economics that software projects are diseconomies of scale. In our work, we study challenges that can explain the disagreement between recent studies of developer productivity in massive repository data. We further provide, to the best of our knowledge, the largest, curated corpus of GitHub projects tailored to investigate the influence of team size and collaboration patterns on individual and collective productivity. Our work contributes to the ongoing discussion on the choice of productivity metrics in the operationalisation of hypotheses about determinants of successful software projects. It further highlights general pitfalls in big data analysis and shows that the use of bigger data sets does not automatically lead to more reliable insights. Copyright © 2022, The Authors. All rights reserved.

关键词： Productivity

T-Cell Receptor Optimization with Reinforcement learning and Mutation Polices for Precision Immunotherapy 27th

学校读者我要写书评

暂无评论

T-Cell Receptor Optimization with Reinforcement Learning an...

27th International Conference on Research in Computational Molecular Biology, RECOMB 2023

作者： Chen, Ziqi Min, Martin Renqiang Guo, Hongyu Cheng, Chao Clancy, Trevor Ning, Xia Computer Science and Engineering The Ohio State University ColumbusOH43210 United States Machine Learning Department NEC Labs PrincetonNJ08540 United States Digital Technologies Research Centre National Research Council Canada Ontario Canada Department of Medicine Baylor College of Medicine HoustonTX77030 United States NEC Oncolmmunity AS Oslo Cancer Cluster Innovation Park Ullernchausséen 64 Oslo0379 Norway Biomedical Informatics The Ohio State University ColumbusOH43210 United States Translational Data Analytics Institute The Ohio State University ColumbusOH43210 United States

ISBN: (纸本)9783031291180

T cells monitor the health status of cells by identifying foreign peptides displayed on their surface. T-cell receptors (TCRs), which are protein complexes found on the surface of T cells, are able to bind to these peptides. This process is known as TCR recognition and constitutes a key step for immune response. Optimizing TCR sequences for TCR recognition represents a fundamental step towards the development of personalized treatments to trigger immune responses killing cancerous or virus-infected cells. In this paper, we formulated the search for these optimized TCRs as a reinforcement learning (Formula Presented) problem, and presented a framework (Formula Presented) with a mutation policy using proximal policy optimization. (Formula Presented) mutates TCRs into effective ones that can recognize given peptides. (Formula Presented) leverages a reward function that combines the likelihoods of mutated sequences being valid TCRs measured by a new scoring function based on deep autoencoders, with the probabilities of mutated sequences recognizing peptides from a peptide-TCR interaction predictor. We compared (Formula Presented) with multiple baseline methods and demonstrated that (Formula Presented) significantly outperforms all the baseline methods to generate positive binding and valid TCRs. These results demonstrate the potential of(Formula Presented) for both precision immunotherapy and peptide-recognizing TCR motif discovery. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Reinforcement learning

Radar-based Recognition of Activities of Daily Living in the Palliative Care Context Using Deep learning

学校读者我要写书评

暂无评论

Radar-based Recognition of Activities of Daily Living in the...

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Johanna Braeunig Desar Mejdani Daniel Krauss Stefan Griesshammer Robert Richer Christian Schuessler Julia Yip Tobias Steigleder Christoph Ostgathe Bjoern M. Eskofier Martin Vossiek Department Electrical Engineering Institute of Microwaves and Photonics Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany Department Artificial Intelligence in Biomedical Engineering (AIBE) Machine Learning and Data Analytics Lab (MaD Lab) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany Department of Palliative Medicine Universitätsklinikum Erlangen Erlangen Germany

The accurate detection and quantification of activities of daily life (ADL) are crucial for assessing the health status of palliative patients to allow an optimized treatment in the last phase of life. Current evaluation methods heavily rely on subjective self-reports or external observations by clinical staff, lacking objectivity. To address this limitation, we propose a radar-based approach for recognizing ADLs in a palliative care context. In our proof of concept study, we recorded five different ADLs relevant to palliative care, all occurring within a hospital bed, from N=14 healthy participants (57% women, aged 28.6 ± 5.3years). All movements were recorded using two frequency-modulated continuous wave radar systems measuring velocity, range, and angle. A convolutional neural network combined with long short-term memory achieved a classification accuracy of 99.8 ± 0.4% across five cross-validation folds. Furthermore, we compare our initial approach, which takes into account all dimensions of the available radar data, to a simplified version, where only velocity information over time is fed into the network. While these results demonstrate the high potential of radar-based sensing to automatically detect and quantify activities in a palliative care context, future work is still necessary to assess the applicability to real-world hospital scenarios.

关键词：

Facial Expression Recognition Using Multi-Block Deep CNN

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Multi-Block Deep CNN

International Conference on Circuits, Communication, Control and Computing

作者： Priyadarshini V Srinivasulu Reddy U Venkata Rami Reddy Chirra Mrudula M Suneetha M Dept. of Computer Science & Engineering National Institute of Technology Andhra Pradesh India Dept. of Computer Applications Machine Learning & Data Analytics lab National Institute of Technology Tiruchirappalli India School of Computer Science & Engineering VIT-AP University Amaravathi India Department of CSE Malla Reddy College of Engineering Telangana India Independent Researcher Amaravati India

ISBN: (数字)9798331528539

ISBN: (纸本)9798331528546

Emotions play a crucial role in decision-making, moral judgments, and other cognitive processes. The goal of this work is to identify people's facial emotions from face images. Facial expression recognition (FER), a highly diverse field with many commonalities between classes, is a challenging problem. The capabilities of current FER systems are limited in this regard. In this work, a multi-block Deep Convolutional Neural Networks (DCNN) model was proposed to identify facial expressions. Five blocks with different computational components were defined in a multi-block DCNN to extract the unique characteristics from input images. The second model (DCNN-SVM) is developed with an ensemble of SVM classifier to improve predictability and stability. The third model (DCNN-MV) is based on the majority voting with 4 classifiers SVM, KNN, Random Forest, and Decision Tree. The CK+ dataset was utilized and expanded via image data augmentation to enhance model performance and generalization. By adjusting hyperparameters, the suggested DCNN model's accuracy was investigated. The DCNN model reports an accuracy score of 97.71%. Both DCNN-SVM and DCNN-MV models achieved 97.79% accuracy. On the CK+ dataset, the proposed models demonstrated good accuracy in identifying facial expressions. When compared to existing models, the proposed model outperformed existing models in terms of accuracy.

关键词： Support vector machines Accuracy Computational modeling Face recognition Stability analysis Circuit stability Convolutional neural networks Integrated circuit modeling Thermal stability Random forests

The Conditional Cauchy-Schwarz Divergence with Applications to Time-Series data and Sequential Decision Making

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Shujian Li, Hongming Løkse, Sigurd Jenssen, Robert Príncipe, José C. The Machine Learning Group UiT - The Arctic University of Norway Tromsø Norway The Quantitative Data Analytics Group Vrije Universiteit Amsterdam Netherlands The Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States The Drones and Autonomous Systems group at NORCE Norwegian Research Centre Tromsø Norway The Pioneer AI Centre Copenhagen University The Norwegian Computing Center Oslo Norway

The Cauchy-Schwarz (CS) divergence was developed by Príncipe et al. in 2000. In this paper, we extend the classic CS divergence to quantify the closeness between two conditional distributions and show that the developed conditional CS divergence can be simply estimated by a kernel density estimator from given samples. We illustrate the advantages (e.g., rigorous faithfulness guarantee, lower computational complexity, higher statistical power, and much more flexibility in a wide range of applications) of our conditional CS divergence over previous proposals, such as the conditional KL divergence and the conditional maximum mean discrepancy. We also demonstrate the compelling performance of conditional CS divergence in two machine learning tasks related to time series data and sequential inference, namely time series clustering and uncertainty-guided exploration for sequential decision making. Copyright © 2023, The Authors. All rights reserved.

关键词： machine learning