检索结果-内蒙古大学图书馆

Machine learning-based gene expression biomarkers to distinguish Zika and Dengue virus infections: implications for diagnosis

引用

VirusDisease 2024年第3期35卷 446-461页

作者： Zeba, Ayesha Rajalingam, Aruna Sekar, Kanagaraj Ganjiwale, Anjali Department of Life Science Bangalore University Laboratory for Structural Biology and Bio-Computing Department of Computational and Data Sciences Indian Institute of Science

Zika virus (ZIKV) and Dengue virus (DENV) infections cause severe disease in humans and are significant socio-economic burden worldwide. These flavivirus infections are difficult to diagnose serologically due to antigenic overlap. The phylogenetic analysis shows that ZIKV clusters with DENVs at a higher node of the phylogenetic tree with significant genomic and structural similarity. Our study aims to identify gene biomarkers for the classification of Dengue and Zika viral infections using machine learning algorithms and bioinformatics analysis. The gene expression count matrix for single-cell RNA sequencing dataset GSE110496 was analyzed using binary classifiers, namely Logistic regression, Support Vector Machines, Random Forest, and Decision trees. The GSE110496 dataset represents a unique study of the transcriptional and translational dynamics of DENV and ZIKV infections at 4-, 12-, 24-, and 48-h time points for human hepatoma (Huh7) cells. Out of which 24-h time point has been analyzed in this study, at the optimal threshold of viral molecules. Feature selection was performed using two different approaches Random Forest Classifier (RFC) for gene ranking and Recursive Feature Elimination (RFE). Out of which RFE, showed more accuracy and precision. The classification accuracy of 89.4% and the precision of 90% were obtained using selected 10 gene features. SCY1 Like Pseudokinase 3 (SCYL3), Chromosome 1 Open Reading Frame 112 (C1orf112), Complement factor H (CFH), Heme-binding protein 1 (HEBP1), Cadherin 1 (CDH1), Nibrin (NBN), Histone deacetylase 5 (HDAC5), nuclear receptor subfamily 0, group B, member 2 (NR0B2), Annexin A9 (ANXA9) and Alcohol dehydrogenase 6 (ADH6) are the proposed gene biomarkers in this study. The functional analysis of the reported biomarkers was performed using KEGG and GO with the WEB-based Gene SeT AnaLysis Toolkit (WebGestalt). The relationship of the selected biomarkers with DENV and ZIKV infections analyzed using a gene–gene interaction n

关键词： Biomarkers Dengue Machine learning Single cell RNA sequencing Zika

来源：评论

学校读者我要写书评

暂无评论

Lexicon-based fine-tuning of multilingual language models for low-resource language sentiment analysis

引用

CAAI Transactions on Intelligence Technology 2024年第5期9卷 1116-1125页

作者： Vinura Dhananjaya Surangika Ranathunga Sanath Jayasena Department of Computer Science and Engineering University of MoratuwaMoratuwaSri Lanka School of Mathematical and Computational Sciences Massey UniversityPalmerston NorthNew Zealand

Pre-trained multilingual language models (PMLMs) such as mBERT and XLM-R have shown good cross-lingual transferability. However, they are not specifically trained to capture cross-lingual signals concerning sentiment words. This poses a disadvantage for low-resource languages (LRLs) that are under-represented in these models. To better fine-tune these models for sentiment classification in LRLs, a novel intermediate task fine-tuning (ITFT) technique based on a sentiment lexicon of a high-resource language (HRL) is introduced. The authors experiment with LRLs Sinhala, Tamil and Bengali for a 3-class sentiment classification task and show that this method outperforms vanilla fine-tuning of the PMLM. It also outperforms or is on-par with basic ITFT that relies on an HRL sentiment classification dataset.

关键词： deep learning natural languages natural language processing

来源：评论

学校读者我要写书评

暂无评论

A Tutorial on Federated Learning from Theory to Practice:Foundations,Software Frameworks,Exemplary Use Cases,and Selected Trends

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 824-850页

作者： M.Victoria Luzón Nuria Rodríguez-Barroso Alberto Argente-Garrido Daniel Jiménez-López Jose M.Moyano Javier Del Ser Weiping Ding Francisco Herrera Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Communications Engineering University of the Basque Country(UPV/EHU)and also with TECNALIABasque Research&Technology Alliance(BRTA)Spain School of Information Science and Technology Nantong UniversityNantong 226019China

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(ML)models in a distributed and decentralized *** allows ML models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third *** paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data *** virtue of FL,models can be learned from all such distributed data sources while preserving data *** aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software ***,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different ML approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL *** ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

关键词： data privacy distributed machine learning federated learning software frameworks

来源：评论

学校读者我要写书评

暂无评论

Automated Quality Assessment Using Appearance-Based Simulations and Hippocampus Segmentation on Low-Field Paediatric Brain MR Images 1st

Automated Quality Assessment Using Appearance-Based Simulati...

引用

1st MICCAI Challenge on Low Field Pediatric Brain Magnetic Resonance Image Segmentation and Quality Assurance, LISA 2024, held in Conjunction with Medical Image Computing and computer Assisted Intervention Conference, MICCAI 2024

作者： Sundaresan, Vaanathi Dinsdale, Nicola K Department of Computational and Data Sciences Indian Institute of Science Bangalore560012 India Oxford Machine Learning in NeuroImaging Lab Department of Computer Science University of Oxford Oxford United Kingdom

ISBN: (纸本)9783031830105

Understanding the structural growth of paediatric brains is a key step in the identification of various neuro-developmental disorders. However, our knowledge is limited by many factors, including the lack of automated image analysis tools, especially in Low and Middle Income Countries from the lack of high field MR images available. Low-field systems are being increasingly explored in these countries, and, therefore, there is a need to develop automated image analysis tools for these images. In this work, as a preliminary step, we consider two tasks: 1) automated quality assurance and 2) hippocampal segmentation, where we compare multiple approaches. For the automated quality assurance task a DenseNet combined with appearance-based transformations for synthesising artefacts produced the best performance, with a weighted accuracy of 82.3%, thus ranking in the 1st place in the LISA2024 Challenge. For the segmentation task, registration of an average atlas performed the best, with a final Dice score of 0.61. Our results show that although the images can provide understanding of large scale pathologies and gross scale anatomical development, there still remain barriers for their use for more granular analyses. © The Author(s) 2025.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Evaluating Negative Sampling Approaches for Neural Topic Models

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5630-5642页

作者： Adhya, Suman Lahiri, Avishek Sanyal, Debarshi Kumar Das, Partha Pratim Indian Association for the Cultivation of Science School of Mathematical and Computational Sciences Kolkata700032 India Ashoka University Department of Computer Science Haryana Sonipat131029 India

Negative sampling has emerged as an effective technique that enables deep learning models to learn better representations by introducing the paradigm of 'learn-to-compare.' The goal of this approach is to add robustness to deep learning models to learn better representation by comparing the positive samples against the negative ones. Despite its numerous demonstrations in various areas of computer vision and natural language processing, a comprehensive study of the effect of negative sampling in an unsupervised domain such as topic modeling has not been well explored. In this article, we present a comprehensive analysis of the impact of different negative sampling strategies on neural topic models. We compare the performance of several popular neural topic models by incorporating a negative sampling technique in the decoder of variational autoencoder-based neural topic models. Experiments on four publicly available datasets demonstrate that integrating negative sampling into topic models results in significant enhancements across multiple aspects, including improved topic coherence, richer topic diversity, and more accurate document classification. Manual evaluations also indicate that the inclusion of negative sampling into neural topic models enhances the quality of the generated topics. These findings highlight the potential of negative sampling as a valuable tool for advancing the effectiveness of neural topic models. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Building a portable parallel asynchronous PDE solver using Kokkos 31

Building a portable parallel asynchronous PDE solver using K...

引用

31st IEEE International Conference on High Performance Computing, data, and Analytics Workshops, HiPCW 2024

作者： Bhat, Ranjan Aditya, Konduri Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Computational and Data Sciences Indian Institute of Science Bengaluru India

ISBN: (纸本)9798331509118

In this study, we outline the design and implementation of a portable massively parallel asynchronous solver for time-dependent partial differential equations (PDEs). The solver is implemented using Kokkos library for portability across different node architectures and is coupled with the communication-avoiding algorithm that relaxes the communication across nodes, thus improving the scalability. Asynchrony-tolerant finite difference schemes for spatial derivatives along with the low storage Runge-Kutta scheme for time integration are used to achieve high-order accuracy. The efficacy of the implementation is demonstrated using a mini-app that solves the three-dimensional diffusion problem. © 2024 IEEE

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Co-Linear Chaining on Pangenome Graphs 23

Co-Linear Chaining on Pangenome Graphs

引用

23rd International Workshop on Algorithms in Bioinformatics, WABI 2023

作者： Rajput, Jyotshna Chandra, Ghanshyam Jain, Chirag Department of Computational and Data Sciences Indian Institute of Science Bangalore India

ISBN: (纸本)9783959772945

Pangenome reference graphs are useful in genomics because they compactly represent the genetic diversity within a species, a capability that linear references lack. However, efficiently aligning sequences to these graphs with complex topology and cycles can be challenging. The seed-chain-extend based alignment algorithms use co-linear chaining as a standard technique to identify a good cluster of exact seed matches that can be combined to form an alignment. Recent works show how the co-linear chaining problem can be efficiently solved for acyclic pangenome graphs by exploiting their small width [Makinen et al., TALG'19] and how incorporating gap cost in the scoring function improves alignment accuracy [Chandra and Jain, RECOMB'23]. However, it remains open on how to effectively generalize these techniques for general pangenome graphs which contain cycles. Here we present the first practical formulation and an exact algorithm for co-linear chaining on cyclic pangenome graphs. We rigorously prove the correctness and computational complexity of the proposed algorithm. We evaluate the empirical performance of our algorithm by aligning simulated long reads from the human genome to a cyclic pangenome graph constructed from 95 publicly available haplotype-resolved human genome assemblies. While the existing heuristic-based algorithms are faster, the proposed algorithm provides a significant advantage in terms of accuracy. © Jyotshna Rajput, Ghanshyam Chandra, and Chirag Jain;licensed under Creative Commons License CC-BY 4.0.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Secured and Privacy-Preserving GPU-Based Machine Learning Inference in Trusted Execution Environment: A Comprehensive Survey 17

Secured and Privacy-Preserving GPU-Based Machine Learning In...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Chaudhuri, Arunava Shukla, Shubhi Bhattacharya, Sarani Mukhopadhyay, Debdeep Indian Institute of Technology Kharagpur Department of Computer Science and Engineering Kharagpur India Indian Institute of Technology Kharagpur Centre for Computational and Data Sciences Kharagpur India

ISBN: (纸本)9798331531195

With the rapid advancement of machine learning (ML) models and their widespread application across various sectors such as intrusion detection, medical diagnosis, natural language processing, and autonomous driving, these technologies have achieved remarkable success. However, this progress has also raised significant concerns about ensuring the security of ML models and protecting both private training data and model outputs from getting exposed in a shared cloud environment. To address these challenges, researchers have proposed various methodologies to create privacy-preserving, secure, and trustworthy model execution environments to prevent adversarial attacks. This study provides a comprehensive review of Trusted Execution Environment (TEE) implementations across different hardware accelerators. It also offers an overview of modern techniques for preserving privacy and security in execution environments, while identifying critical research gaps that require attention. In essence, this survey is an important resource for researchers, providing insights into recent methodologies and guiding them to focus on pressing research challenges. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

Few-shot Prompting for Pairwise Ranking: An Effective Non-Pa...

引用

2024 Findings of the Association for computational Linguistics, EMNLP 2024

作者： Sinhababu, Nilanjan Parry, Andrew Ganguly, Debasis Samanta, Debasis Mitra, Pabitra Centre for Computational and Data Sciences IIT Kharagpur India School of Computing Science University of Glasgow United Kingdom Department of Computer Science and Engineering IIT Kharagpur India

ISBN: (纸本)9798891761681

A supervised ranking model, despite its effectiveness over traditional approaches, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that can work in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline. © 2024 Association for computational Linguistics.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

UATTA-QSM: Uncertainty-Aware Test Time Adaptation for Improved Quantitative Susceptibility Mapping 22

UATTA-QSM: Uncertainty-Aware Test Time Adaptation for Improv...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Ravishankar, Hariharan Paluru, Naveen Sudhakar, Prasad Yalavarthy, Phaneendra K. Indian Institute of Science Department of Computational and Data Sciences Bangalore India Ge HealthCare Science and Technology Organization Bangalore India

ISBN: (纸本)9798331520526

This work addresses the problem of deriving improved quantitative susceptibility mapping (QSM) from magnetic resonance (MR) acquisitions. Deep learning based models that map measured MR local phase field to QSM maps, have recently demonstrated satisfactory reconstruction quality. However, they suffer from poor generalization on acquisitions that deviate from training settings. To address this, this work proposes a patient-specific, test-time adaptation method for modifying pre-trained deep learning models, conditioned on individual subject data. The proposed method of uncertainty-aware test-time adaptation (UATTA-QSM), for the first-time introduces, lipschitz constraints on local phase field measurements and QSM reconstructions to jointly reduce uncertainty and adapt model weights during inference time with functional regularization. This framework was evaluated on multiple adaptation scenarios like changing field strength, limited data training and different architectures. On unseen datasets, the proposed method of UATTA-QSM consistently demonstrates performance improvement on all metrics of interest. © 2025 IEEE.

关键词： Inverse problems

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：