检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Madhusudhanan, Kiran Behrens, Gunnar Stubbemann, Maximilian Schmidt-Thieme, Lars University Of Hildesheim Information Systems and Machine Learning Lab Vwfs Data Analytics Research Center Germany Volkswagen Financial Services Ag Data Analytics & Ai Engineering United States

ISBN: (纸本)9798350362480

Used car pricing is a critical aspect of the automotive industry, influenced by many economic factors and market dynamics. With the recent surge in online marketplaces and increased demand for used cars, accurate pricing would benefit both buyers and sellers by ensuring fair transactions. However, the transition towards automated pricing algorithms using machine learning necessitates the comprehension of model uncertainties, specifically the ability to flag predictions that the model is unsure about. Although recent literature proposes the use of boosting algorithms or nearest neighbor-based approaches for swift and precise price predictions, encapsulating model uncertainties with such algorithms presents a complex challenge. We introduce ProbSAINT, a model that offers a principled approach for uncertainty quantification of its price predictions, along with accurate point predictions that are comparable to state-of-the-art boosting techniques. Furthermore, acknowledging that the business prefers pricing used cars based on the number of days the vehicle was listed for sale, we show how ProbSAINT can be used as a dynamic forecasting model for predicting price probabilities for different expected offer durations. Our experiments further indicate that ProbSAINT is especially accurate in instances where it is highly certain. This proves the applicability of its probabilistic predictions in real-world scenarios where trustworthiness is crucial. © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Electrophysiological Insights in Exergaming—Electroencephalography data Recording and Movement Artifact Detection: Systematic Review

引用

JMIR Serious Games 2025年 13卷 e50992页

作者： Rico-Olarte, Carolina Lopez, Diego M. Eskofier, Bjoern M. Becker, Linda Telematics Department Universidad del Cauca Popayán Colombia Machine Learning and Data Analytics Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Department of Psychology Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany

Background: Exergames are interactive solutions that require physical activity and are commonly used in learning or rehabilitation settings. For cognitive rehabilitation with exergames, the assessment of the intervention progress can be conducted by verifying the changes in brain activity. Electroencephalography (EEG) is a well-known method for this evaluation. However, motion artifacts due to large body movements can impede signal quality. No comprehensive guide on the artifact removal methods in the context of exergaming has been found. Objective: This paper aimed to identify studies that have assessed EEG signals while a user interacts with an exergame and the applied methods for data handling and analysis with a focus on dealing with movement artifacts. Methods: This review included studies on human participants while engaging in exergames, where the primary outcome was brain activity measured by EEG. A total of 5 databases were searched at 3 time points: March 2021, October 2022, and February 2024. The Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies assessed methodological quality, rating studies as “good,” “fair,” or “poor.” data were synthesized quantitatively to identify characteristics across studies, including sample demographics and intervention details, and basic statistics (mean [SD]) were calculated. Results: A total of 494 papers were screened, resulting in 17 studies having been included. All studies carried out EEG recordings during exergame interactions, primarily assessing attention and concentration, with the alpha wave being the most analyzed EEG band. Common motion artifact removal methods included visual inspection and independent component analysis. The review identified significant risks of bias, with 2 studies rated as “good,” 7 as “fair,” and 8 as “poor.” Due to the small number of studies and their heterogeneity, a meta-analysis was not feasible. Conclusions: The study successfully identifies the feasibility o

关键词： artifact removal brain activity EEG exergaming motion artifact

来源：评论

学校读者我要写书评

暂无评论

machine learning approach for feature interpretation and classification of genetic mutations leading to tumor and cancer 1st

Machine learning approach for feature interpretation and cla...

引用

1st International Conference on Advances in Electrical and Computer Technologies, ICAECT 2019

作者： Sah, Ankit Kumar Mishra, Abinash Reddy, U. Srinivasulu Machine Learning and Data Analytics Lab Department of Computer Applications National Institute of Technology TiruchirappalliTamil Nadu620015 India

ISBN: (纸本)9789811555572

As the interpretation of genetic mutation is done manually, it is difficult to diagnose a large number of patients and get reports of the same in a quick time. Hence, it needs to be automated using machine learning approach. Towards the same, natural language processing (NLP) technique, viz. term frequency-inverse document frequency (TF-IDF), is used to represent documents as fixed-size depiction for interpreting the given nine classes of genetic mutations. The main aim of this study is to identify the well-suited machine learning model which will give better results in terms of multi-class log-loss. Another important aspect of this study is to interpret the features since feature interpretability is very important in healthcare domain using various machine learning algorithms. Logistic regression (LR) with class balancing was implemented by taking top 1000 words of 3-gram TF-IDF generated features that outperformed the other classifiers to give a test log-loss of 0.98. © Springer Nature Singapore Pte Ltd 2020.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Estimating fish weight growth in aquaponic farming through machine learning techniques 3

Estimating fish weight growth in aquaponic farming through m...

引用

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Kumar, Purushottam Tiwari, Pranav Srinivasulu Reddy, U. Machine Learning & Data Analytics Lab CoE in Artificial Intelligence National Institute of Technology Trichy India Indian Institute of Information Technology Tiruchirappalli Computer Science and Engineering Trichy India National Institute of Technology Machine Learning & Data Analytics Lab Department of Computer Applications Trichy India

ISBN: (纸本)9798350338607

Due to the ever-growing population, rapid urbanization, unusual environmental change, and dwindling water supply, the food production from conventional farming techniques won't be able to keep up with increasing food demand for long, leading to severe food scarcity. Aquaponics is emerging as a viable alternative to food cultivation techniques but lacks efficiency, hindering its adoption on a large-scale production basis. The adoption of Artificial Intelligence (AI) techniques in smart aquaponic farming can further contribute to increasing the yield in aquaponics. In the study, both linear and non-linear regression algorithms such as linear regression, lasso regression, ridge regression, KNN regression, SVR, and decision tree regression were trained on aquaponic fish pond dataset, evaluated on the basis of multiple metrics like MAE, MSE, RMSE, and RMSLE, and a competitive analysis was done to determine the best algorithm for predicting the harvest weight of the fish in aquaponic ponds. The results showed that KNN regression and decision tree regression algorithms have lowest error and highest accuracy of 99.15% and 99.1% respectively, for predicting the harvest weight of the fish. The results obtained could be scaled up to commercial levels and used in regulating nutrient concentration and aquatic environmental conditions © 2023 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Increasing the robustness of the automatic IMU calibration for lower Extremity Motion Analysis

引用

Current Directions in Biomedical Engineering 2018年第1期4卷 439-442页

作者： Küderle, Arne Becker, Sebastian Disselhorst-Klug, Catherine Machine Learning and Data Analytics Lab. University of Erlangen-Nürnberg (FAU) Carl-Thiersch-Strasse 2b Erlangen Germany Department of Rehabilitation and Prevention Engineering Institute of Applied Medical Engineering RWTH Aachen University Aachen Germany

With the advances of IMU-based human motion tracking, joint angle tracking in an home environment has become a realistic goal. Achieving it, could enable novel applications in rehabilitation and sports medicine. However, in existing systems the process of aligning the mounted sensors with the body coordinate system is either not robust enough or to complicated for fully unsupervised usage. In this publication the performance of a promising existing algorithm is evaluated with a range of different calibration motions. Further, an extension to this implementation is proposed, aiming to improve its stability when only non-ideal calibration data is availab.e. It could be validated that the modification of the algorithm can increase the stability and reduce the dependency of the calibration on specific calibration motions. Based on these results, we recommend the proposed extension of the algorithm as a drop-in replacement for the existing implementation. © 2018 Arne Küderle et al.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

On the Scalab.lity of Certified Adversarial Robustness with Generated data 38

On the Scalability of Certified Adversarial Robustness with ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Altstidl, Thomas Dobre, David Kosmala, Arthur Eskofier, Björn Gidel, Gauthier Schwinn, Leo Machine Learning and Data Analytics Lab FAU Erlangen Nürnberg Germany Institute of AI for Health Helmholtz Zentrum München Germany Mila Université de Montréal Canada Canada CIFAR AI Canada Data Analytics and Machine Learning Technische Universität München Germany

Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen attacks. Still, the limited certified robustness that is currently achievable has been a bottleneck for their practical adoption. Gowal et al. and Wang et al. have shown that generating additional training data using state-of-the-art diffusion models can considerably improve the robustness of adversarial training. In this work, we demonstrate that a similar approach can substantially improve deterministic certified defenses but also reveal notable differences in the scaling behavior between certified and empirical methods. In addition, we provide a list of recommendations to scale the robustness of certified training approaches. Our approach achieves state-of-the-art deterministic robustness certificates on CIFAR-10 for the 2 (ϵ = 36/255) and ∞ (ϵ = 8/255) threat models, outperforming the previous results by +3.95 and +1.39 percentage points, respectively. Furthermore, we report similar improvements for CIFAR-100. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reducing noise using neighbourhood pixel analysis and interpretable custom kernel in CNN model for CP handwritten digit recognition

引用

International Journal of Information Technology (Singapore) 2024年 1-11页

作者： Muthureka, K. Srinivasulu Reddy, U. Janet, B. Machine Learning and Data Analytics Lab Department of Computer Applications National Institute of Technology Tiruchirappalli India Information Processing Lab Department of Computer Applications National Institute of Technology Tiruchirappalli India

Individuals with Cerebral Palsy (CP) are impacted lifetime barriers in their everyday activities, especially in writing phrase, which results from innate neural motor in co-ordination. Numerous studies have focused on recognizing normal people’s handwritten digits using benchmark datasets. However, there has been limited exploration into recognizing handwritten digits by individuals with CP. The handwriting of CP individuals is significantly more difficult to recognize than that of normal people because the CP digits are inaccurate, uneven, and complex to recognize. In this study, the authors improve the digit recognition accuracy of existing Convolutional Neural Network (CNN) models on collected CP handwritten digit’s dataset using two notable methods, first one is to reduce the noise using neighbourhood pixel analysis through Fast Non-Local Means (FNLM) algorithm and second one is to extract the feature using customized kernel technique. The experimental results show that the accuracy of existing state of art models are improved by 3% to 7.14% with the integration of aforementioned techniques. Moreover, a custom CNN model hybridised with the Prewit, Laplacian, Sobel filters, and custom kernel has following CP digit recognition accuracy values of 97.96%, 98.08%, 99.17%, and 99.60% respectively. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： Cerebral Palsy CNN Customized kernel initialization Edge detection Handwritten digit recognition

来源：评论

学校读者我要写书评

暂无评论

Could machine learning be used to approximate optimal building retrofit solutions with the use of easily accessible building data? 32

Could machine learning be used to approximate optimal buildi...

引用

32nd International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems, ECOS 2019

作者： Thrampoulidis, Emmanouil Mavromatidis, Georgios Lucchi, Aurelien Orehounig, Kristina Laboratory for Urban Energy Systems Empa Duebendorf Switzerland ETH Zurich Switzerland Institute for Machine Learning Data analytics lab ETH Zurich Switzerland

ISBN: (纸本)9788361506515

Building retrofit is of greatest importance to reduce the environmental footprint of the building stock. It typically refers to two types of interventions: the first pertaining to interventions on the building envelope, for instance by enhancing the thermal insulation of a building’s walls, and the second to energy system replacements. The latter includes not only the installation of a more efficient heating system, with the necessary capacity to meet the building's heat demands, but also the integration of renewable energy technologies and energy storage. Thus, there is a huge array of retrofit measure combinations to select from with different economic and environmental impacts. Even though there are tools and methodologies to handle the complex problem of deriving optimal retrofit solutions, they typically require increased level of expertise and highly heterogeneous building data, which are usually not availab.e or challenging to obtain. As a result, building owners can find themselves in a quandary about how to further proceed with retrofitting their buildings. In this paper, we answer the question whether a machine-learning algorithm could be used as a surrogate model that can: (a) mimic the functionality of the retrofit process, and (b) derive near-optimal solutions with the use of building features that can be easily extracted, such as the building's ground floor area or age. To answer this question an artificial neural network-based model is trained with data collected from the case study of the city of Zurich. Results show that the proposed approach can approximate very well some dimensions of the building retrofit, such as the retrofit costs (R2 ≅ 0.971) and the energy system selection (f1 score ≅ 0.894), while for others, such as the electricity storage capacity (R2 ≅ 0.505), there is still room for improvement. Such surrogate retrofit models can be more easily shared with building owners, and can contribute towards accelerating the adoption of retrofit

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Finding the transcription factor binding locations using novel algorithm segmentation to filtration (S2F)

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第9期15卷 3347-3358页

作者： Theepalakshmi, P. Srinivasulu Reddy, U. Department of Computer Science and Engineering Gandhi Institute of Technology and Management Karnataka Bengaluru India Machine Learning and Data Analytics Lab Center of Excellence in Artificial Intelligence Department of Computer Applications National Institute of Technology Tamilnadu Tiruchirappalli India

The primary aim of identifying the binding motifs in gene regulation is to understand the transcriptional regulation molecular mechanism systematically. In this study, the (, d) motif search issue was considered which entails finding the length motifs which differ by at most d substitutions. However, identifying the high-quality pattern (, d) is challenging. It is intended to address the above problem with motif discovery and handle it using the proposed algorithm S2F (Segmentation to Filtration) based on the qPMS (quorum Planted Motif Search) algorithm model. From the entire DNA sequences, five percent are chosen at random to be used in the motif discovery process. This random sub segment (subseg) portion is split up into base, sub k-mers, and its sizes (motif length ()) are determined by the iterative approach. Corresponding to the sizes of and d (mutations), the k-mers are chosen which participated in filtration techniques and the base k-mer count and frequency are updated. The highest frequency of k-mer is recognized as the motif. The algorithm’s performance was evaluated using the two real datasets Escherichia coli cyclic AMP receptor protein (CRP) and mouse Embryonic Stem Cell (mESC) ChIP-seq (Chromatin Immuno Precipitation) dataset. Results from the experiments show that S2F can identify the motifs and appear faster compared to previous state-of-the-art PMS (Planted Motif Search) and qPMS algorithms. Graphical Abstract: (Figure presented.) © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： DNA sequences

来源：评论

学校读者我要写书评

暂无评论

Superposition as data Augmentation Using Lstm and Hmm in Small Training Sets

arXiv

引用

arXiv 2019年

作者： Sivaswamy, Akilesh Pavlovskiy, Evgeniy Stream Data Analytics and Machine Learning lab Novosibirsk State University

Considering audio and image data as having quantum nature (data are represented by density matrices), we achieved better results on training architectures such as 3-layer stacked LSTM and HMM by mixing training samples using superposition augmentation and compared with plain default training and mix-up augmentation. This augmentation technique originates from the mix-up approach but provides more solid theoretical reasoning based on quantum properties. We achieved 3% improvement (from 68% to 71%) by using 38% lesser number of training samples in Russian audio-digits recognition task and 7,16% better accuracy than mix-up augmentation by training only 500 samples using HMM on the same task. Also, we achieved 1.1% better accuracy than mix-up on first 900 samples in MNIST using 3-layer stacked LSTM. Copyright © 2019, The Authors. All rights reserved.

关键词： Quantum theory

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：