检索结果-内蒙古大学图书馆

Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer's dementia recognition from spontaneous speech

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Rohanian, Morteza Hough, Julian Purver, Matthew Cognitive Science Group School of Electronic Engineering and Computer Science Queen Mary University of London Department of Knowledge Technologies Jožef Stefan Institute

This paper is a submission to the Alzheimer's Dementia Recognition through Spontaneous Speech (ADReSS) challenge, which aims to develop methods that can assist in the automated prediction of severity of Alzheimer's Disease from speech data. We focus on acoustic and natural language features for cognitive impairment detection in spontaneous speech in the context of Alzheimer's Disease Diagnosis and the mini-mental state examination (MMSE) score prediction. We proposed a model that obtains unimodal decisions from different LSTMs, one for each modality of text and audio, and then combines them using a gating mechanism for the final prediction. We focused on sequential modelling of text and audio and investigated whether the disfluencies present in individuals' speech relate to the extent of their cognitive impairment. Our results show that the proposed classification and regression schemes obtain very promising results on both development and test sets. This suggests Alzheimer's Disease can be detected successfully with sequence modeling of the speech data of medical sessions. © 2021, CC BY.

关键词： Neurodegenerative diseases

Alzheimer's dementia recognition using acoustic, lexical, disfluency and speech pause features robust to noisy inputs

学校读者我要写书评

暂无评论

arXiv 2021年

We present two multimodal fusion-based deep learning models that consume ASR transcribed speech and acoustic data simultaneously to classify whether a speaker in a structured diagnostic task has Alzheimer's Disease and to what degree, evaluating the ADReSSo challenge 2021 data. Our best model, a BiLSTM with highway layers using words, word probabilities, disfluency features, pause information, and a variety of acoustic features, achieves an accuracy of 84% and RSME error prediction of 4.26 on MMSE cognitive scores. While predicting cognitive decline is more challenging, our models show improvement using the multimodal approach and word probabilities, disfluency, and pause information over word-only models. We show considerable gains for AD classification using multimodal fusion and gating, which can effectively deal with noisy inputs from acoustic features and ASR hypotheses. © 2021, CC BY.

关键词： Neurodegenerative diseases

Learning Fair Representations through Uniformly Distributed Sensitive Attributes

学校读者我要写书评

暂无评论

Learning Fair Representations through Uniformly Distributed ...

Secure and Trustworthy Machine Learning (SaTML), IEEE Conference on

作者： Patrik Joslin Kenfack Adín Ramírez Rivera Adil Mehmood Khan Manuel Mazzara Machine Learning and Knowledge Representation Lab Innopolis University Innopolis Russia Department of Informatics Digital Signal Processing and Image Analysis (DSB) group University of Oslo Oslo Norway School of Computer Science University of Hull Hull UK Institute of Software Development and Engineering Innopolis University Innopolis Russia

Machine Learning (ML) models trained on biased data can reproduce and even amplify these biases. Since such models are deployed to make decisions that can affect people's lives, ensuring their fairness is critical. One approach to mitigate possible unfairness of ML models is to map the input data into a less-biased new space by means of training the model on fair representations. Several methods based on adversarial learning have been proposed to learn fair representation by fooling an adversary in predicting the sensitive attribute (e.g., gender or race). However, adversarial-based learning can be too difficult to optimize in practice; besides, it penalizes the utility of the representation. Hence, in this research effort we train bias-free representations from the input data by inducing a uniform distribution over the sensitive attributes in the latent space. In particular, we propose a probabilistic framework that learns these representations by enforcing the correct reconstruction of the original data, plus the prediction of the attributes of interest while eliminating the possibility of predicting the sensitive ones. Our method leverages the inability of Deep Neural Networks (DNNs) to generalize when trained on a noisy label space to regularize the latent space. We use a network head that predicts a noisy version of the sensitive attributes in order to increase the uncertainty of their predictions at test time. Our experiments in two datasets demonstrated that the proposed model significantly improves fairness while maintaining the prediction accuracy of downstream tasks.

关键词：

A Reliable Method to Estimate the Bispectral Index Value Using a Single Frontal EEG Channel for Intra and Inter Subject Variability

学校读者我要写书评

暂无评论

A Reliable Method to Estimate the Bispectral Index Value Usi...

2023 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2023

作者： Shahbakhti, Mohammad Beiramvand, Matin Krycinska, Roza Nasiri, Erfan Chen, Wei Sole-Casals, Jordi Wierzchon, Michal Broniec-Wojcik, Anna Augustyniak, Piotr Marozas, Vaidotas Biomedical Engineering Institute Kaunas University of Technology Kaunas Lithuania Tampere University Faculty of Information Technology and Communication Tempere Finland Jagiellonian University Medical College Doctoral School in Medical and Health Sciences Krakow Poland Jagiellonian University Collegium Medicum Department of Interdisciplinary Intensive Care Krakow Poland Allameh Tabataba'i University Faculty of Statistics Mathematics and Computer Tehran Iran Fudan University Center for Intelligent Medical Electronics School of Information Science and Technology Shanghai China University of Vic-Central University of Catalonia Data and Signal Processing Research Group Vic Spain Institute of Psychology Jagiellonian University Krakow Poland Agh University of Science and Technology Department of Biocybernetics and Biomedical Engineering Krakow Poland

ISBN: (纸本)9781665493840

Objective: Monitoring the depth of anesthesia (DoA) plays an important role for administering the drug injection during a surgery, i.e., preventing undesired awareness and inordinate anesthetic depth. Although the bispectral index (BIS) monitor is the golden standard system for the DoA monitoring, it is still not affordable for the developing countries. Alternatively, a low-cost electroencephalogram (EEG) headband can be used. The objective of this paper is to present a new algorithm for estimating the BIS values using a single frontal EEG channel. Method: In the first step, the EEG signal is filtered for the elimination of artifacts and is split into its sub-bands. In the second step, several linear and nonlinear features are extracted from each sub-band and fed to a random forest regression model in order to estimate the BIS. The performance of the proposed algorithm is assessed using EEG data recorded from twenty-four subjects during the general anesthesia and is validated in terms of correlation coefficient (CC) and absolute error (AE) between the reference and estimated BIS values. Results: The proposed algorithm achieved the mean CC of 0.83 and AE of 6.5 for intra subject variability and mean CC of 0.87 and AE of 5.5 for inter subject variability. Significance: Given the similar results for both intra and inter subject variability, the proposed algorithm has the potential to be used in the real-world scenario. © 2023 IEEE.

关键词： Electroencephalography

Nondestructive Chicken Egg Fertility Detection Using CNN-Transfer Learning Algorithms

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Saifullah, Shoffan Drezewski, Rafal Yudhana, Anton Pranolo, Andri Kaswijanti, Wilis Suryotomo, Andiko Putro Putra, Seno Aji Khaliduzzaman, Alin Prabuwono, Anton Satria Japkowicz, Nathalie Institute of Computer Science AGH University of Krakow Krakow30-059 Poland Department of Informatics Universitas Pembangunan Nasional Veteran Yogyakarta Yogyakarta55281 Indonesia Center of Knowledge Engineering and Data Science Department of Electrical Engineering and Informatics Universitas Negeri Malang Malang65145 Indonesia Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55191 Indonesia College of Computer and Information Hohai University Nanjing211100 China Department of Informatics Faculty of Industrial Technology Universitas Ahmad Dahlan Yogyakarta55166 Indonesia Faculty of Agricultural Engineering and Technology Sylhet Agricultural University Sylhet3100 Bangladesh Faculty of Computing and Information Technology in Rabigh King Abdulaziz University Jeddah21589 Saudi Arabia Department of Computer Science American University WashingtonDC20016 United States

This study explored the application of CNN-Transfer Learning for nondestructive chicken egg fertility detection for precise poultry hatchery practices. Four models, VGG16, ResNet50, InceptionNet, and MobileNet, were trained and evaluated on a dataset (200 single egg images) using augmented images (rotation, flip, scale, translation, and reflection). The training results demonstrated that all models achieved high accuracy, indicating their ability to learn and classify chicken eggs’ fertility. However, variations in accuracy and performance were observed when these models were evaluated on the testing datasets. The InceptionNet exhibited the best overall performance, accurately classifying fertile and non-fertile eggs. It demonstrated excellent performance in all parameters of the evaluation metrics for both training and testing datasets. When evaluated on the testing datasets, it achieved an accuracy of 0.98, a sensitivity of 1 for detecting fertile eggs, and a specificity of 0.96 for identifying non-fertile eggs. The higher performance is attributed to its unique architecture, efficiently capturing features at different scales, which leads to improved accuracy and robustness. Further optimization and fine-tuning of the models might be necessary to address the limitations in accurately detecting fertile and non-fertile eggs using other models. This study highlighted the potential of CNN-transfer learning for nondestructive fertility detection and emphasized the need for further research to enhance the models’ capabilities and to ensure accurate *** Codes CS-Class: 68T07, 68T45, 68U10, ICT-Class: 94A08 © 2023, CC BY-SA.

关键词： Image classification

Synthetic Instance Segmentation from Semantic Image Segmentation Masks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shen, Yuchen Zhang, Dong Zhang, Zhao Fu, Liyong Ye, Qiaolin College of Information Science and Technology & Artificial Intelligence Nanjing Forestry University Jiangsu Nanjing210037 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230009 China College of Information Science and Technology Nanjing Forestry University Jiangsu Nanjing210037 China Institute of Forest Resource Information Techniques Chinese Academy of Forestry Beijing100091 China

In recent years, instance segmentation has garnered significant attention across various applications. However, training a fully-supervised instance segmentation model requires costly both instance-level and pixel-level annotations. In contrast, weakly-supervised instance segmentation methods, such as those using image-level class labels or point labels, often struggle to satisfy the accuracy and recall requirements of practical scenarios. In this paper, we propose a novel paradigm called Synthetic Instance Segmentation (SISeg). SISeg achieves instance segmentation results by leveraging image masks generated by existing semantic segmentation models, and it is highly efficient as we do not require additional training for semantic segmentation or the use of instance-level image annotations. In other words, the proposed model does not need extra manpower or higher computational expenses. Specifically, we first obtain a semantic segmentation mask of the input image via an existent semantic segmentation model. Then, we calculate a displacement field vector for each pixel based on the segmentation mask, which can indicate representations belonging to the same class but different instances, i.e., obtaining the instance-level object information. Finally, the instance segmentation results are refined by a learnable category-agnostic object boundary branch. Extensive experimental results on two challenging datasets highlight the effectiveness of SISeg in achieving competitive results when compared to state-of-the-art methods, especially fully-supervised methods. The code will be released at: SISeg Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

TOWARDS RELIABLE data-BASED OPTIMAL AND PREDICTIVE CONTROL USING EXTENDED DMD

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Schaller, Manuel Worthmann, Karl Philipp, Friedrich Peitz, Sebastian Nüske, Feliks Technische Universität Ilmemau Institute of Mathematics Optimization-based Control Group Germany Paderborn University Department of Computer Science Data Science for Engineering Germany Max Planck Institute for Dynamics of Complex Technical Systems Magdeburg Germany

While Koopman-based techniques like extended Dynamic Mode Decomposition are nowadays ubiquitous in the data-driven approximation of dynamical systems, quantitative error estimates were only recently established. To this end, both sources of error resulting from a finite dictionary and only finitely-many data points in the generation of the surrogate model have to be taken into account. We generalize the rigorous analysis of the approximation error to the control setting while simultaneously reducing the impact of the curse of dimensionality by using a recently proposed bilinear approach. In particular, we establish uniform bounds on the approximation error of state-dependent quantities like constraints or a performance index enabling data-based optimal and predictive control with guarantees. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamic mode decomposition

MassSpecGym: A benchmark for the discovery and identification of molecules

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bushuiev, Roman Bushuiev, Anton de Jonge, Niek F. Young, Adamo Kretschmer, Fleming Samusevich, Raman Heirman, Janne Wang, Fei Zhang, Luke Dührkop, Kai Ludwig, Marcus Haupt, Nils A. Kalia, Apurva Brungs, Corinna Schmid, Robin Greiner, Russell Wang, Bo Wishart, David S. Liu, Li-Ping Rousu, Juho Bittremieux, Wout Rost, Hannes Mak, Tytus D. Hassoun, Soha Huber, Florian van der Hooft, Justin J.J. Stravs, Michael A. Böcker, Sebastian Sivic, Josef Pluskal, Tomáš Institute of Organic Chemistry and Biochemistry The Czech Academy of Sciences Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Czech Republic Bioinformatics Group Wageningen University & Research Netherlands Department of Computer Science University of Toronto Canada Institute for Computer Science Friedrich Schiller University Jena Germany Department of Computer Science University of Antwerp Belgium Department of Computing Science University of Alberta Canada Alberta Machine Intelligence Institute Canada Department of Molecular Genetics University of Toronto Canada Bright Giant GmbH Germany Department of Computer Science Tufts University United States Department of Biological Sciences University of Alberta Canada Department of Computer Science Aalto University Finland Mass Spectrometry Data Center National Institute of Standards and Technology United States Department of Chemical and Biological Engineering Tufts University United States Centre for Digitalisation and Digitality University of Applied Sciences Düsseldorf Germany Department of Biochemistry University of Johannesburg South Africa Eawag: Swiss Federal Institute of Aquatic Science and Technology Switzerland

The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym – the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at https://***/pluskal-lab/MassSpecGym. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Analysis of Panoramic Images using Deep Learning For Dental Disease Identification

学校读者我要写书评

暂无评论

Analysis of Panoramic Images using Deep Learning For Dental ...

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： Mohamed Mallick Midhun Kumar A Sakthi Govindaraju A. Suresh Kumar Manivel Kandasamy P Anitha Rathinam Group of Institutions Coimbaotore Database Engineer Indian Biological Data Center Center for Biotechnology Faridabab School of Computing Science and Engineering Galogotias University Delhi NCR Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Unitedworld School of Computational Intelligence Karnavati University Gujarat India OASYS Institute of Technology Trichy India

Dental caries is a distinct disease strategy caused by the metabolic action of dental biofilm, which continually demineralizes lacquer and dentine. Its commonly known as tooth rot, is one of the most prevalent and long- lasting dental illnesses, affecting people at all stages of their lives. There are a few different sorts of dental x-rays, each of which records a different perspective on dental living systems for caries detection and has the highest symptomatic accuracy, whereas panoramic radiography has the lowest Despite this, Bitewing has a few downsides, such as patient unease. Because of the lack of knowledge among administrators, Bitewing imaging frequently results in increased patient radiation exposure as a result of the need for image retakes. On the other hand, panoramic x-ray scans, also known as Orthopantomogram (OPG), are commonly utilized to capture the whole mouth with a small amount of radiation. OPG has a low radiation content, is simple to use, takes less time, and provides exceptional patient comfort. In this way, when compared to intraoral frameworks, pediatric, impaired, and senior people would profit greatly from panoramic imaging frameworks. This research work explores panoramic photos to detect accurate dental disease using deep learning. As a result, most patients can benefit from panoramic imaging, which covers a large portion of the maxillofacial region, including all of the teeth.

关键词： Deep learning Lacquers Visualization Laplace equations Teeth X-rays Learning (artificial intelligence)