检索结果-内蒙古大学图书馆

A Review on the Applications of machine learning Algorithms for Mental Stress Detection

学校读者我要写书评

暂无评论

A Review on the Applications of Machine Learning Algorithms ...

Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Renuka Motghare Shivam Bhoyar Prateek Verma Abhay Tale Aditya Barhate Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Sawangi Wardha Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

Stress, a widespread issue affecting both individual well-being and societal productivity, has attracted significant research interest. Defined as a state of mental or emotional strain, stress arises from various factors such as work, relationships, and health concerns, manifesting physically, emotionally, and behaviorally. This paper provides a review of machine learning (ML) techniques to detect mental stress using physiological signals like ECG, GSR, and EEG. Through a review of existing studies, the paper highlights the progress made in this area and the challenges that remain, particularly concerning data quality, algorithm accuracy, and the practical deployment of stress monitoring devices. The study underscores the potential for real-time monitoring and personalized interventions, especially in daily activities. Future research should focus on enhancing model robustness, integrating multiple data sources, and addressing real-world applicability. This paper emphasizes the importance of early stress identification and personalized treatment to improve mental health outcomes

关键词： Accuracy machine learning algorithms Reviews Soft sensors Human factors Mental health Transforms Speech recognition Real-time systems Strain

A Blockchain-Based Intelligent IoT Communication System for Enhanced Security, Reliability, and Efficiency

学校读者我要写书评

暂无评论

A Blockchain-Based Intelligent IoT Communication System for ...

Advanced Computing Technologies (ICoACT), International Conference on

作者： Dinesh Kumar K J. Gobinath Jayavadivel Ravi S. Saravanakumar Senthil P B. Prabhu Shankar Department of Computer Science and Engineering Vel Tech University Chennai India Department of Computer Science and Engineering Rajiv Gandhi College of Engineering Chennai India School of Computer Science and Engineering Presidency University Bengaluru India Department of Information Technology Paavai Engineering College Paachal India Department of Artificial Intelligence and Data Science T.J.S.Engineering college Chennai India Department of Artificial Intelligence and Machine Learning Vel Tech University Chennai India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

This research proposes a new approach for developing and implementing a smart communication system of IoT through developmental blockchain technology. Regarding the proposed solution, it is suggested that a distributed ledger can improve security, reliability, and efficiency of communication of IoT devices. They tackle issues such as data integrity, privacy and security in IoT networks as well as the problem of trust in such networks. The solution provides a decentralised and secure IoT ecosystem communication hence allowing monitoring, controlling and administration of the IoT build ecosystems in real time. Blockchain technology, however, when combined with nextgeneration communication interfaces and modern data analysis techniques, can offer various superior characteristics such as device identification, origin of information, etc. to IoT applications. It also enhances the dependability and capacity of IoT systems regarding capability and efficiency. Analysis and performance comparisons substantiate the performance benefits of the proposed intelligent communication system based on blockchain technology In addition these theoretical and performance analyses and experimental evaluation confirm the applicability and potential of the blockchain-based intelligent communication system to transform IoT communication models and facilitate the new generation of eIOT applications in a number of fields. The key to the solution to incorporate blockchain fundamental infrastructure to augment the communication channel of IoT devices. Using cryptography and consensus methodologies with the decentralized framework, integrity and confidentiality of the data is properly maintained because of the barriers of malicious interception or manipulation of the data. The communication system also boosts trust within the network participants because it offers a decentralized and immutable ledger of data transactions on the blockchain. Instead, one of the compelling benefits of this solution

关键词： Performance evaluation Computers Communication systems Ecosystems Transforms Real-time systems Blockchains Internet of Things Reliability Monitoring

Network-based Neighborhood Regression

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhen, Yaoming Du, Jin-Hong Department of Statistical Sciences University of Toronto TorontoONM5G 1X6 Canada Department of Statistics and Data Science Carnegie Mellon University PittsburghPA15213 United States Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States

Given the ubiquity of modularity in biological systems, module-level regulation analysis is vital for understanding biological systems across various levels and their dynamics. Current statistical analysis on biological modules predominantly focuses on either detecting the functional modules in biological networks or sub-group regression on the biological features without using the network data. This paper proposes a novel network-based neighborhood regression framework whose regression functions depend on both the global community-level information and local connectivity structures among entities. An efficient community-wise least square optimization approach is developed to uncover the strength of regulation among the network modules while enabling asymptotic inference. With random graph theory, we derive non-asymptotic estimation error bounds for the proposed estimator, achieving exact minimax optimality. Unlike the root-n consistency typical in canonical linear regression, our model exhibits linear consistency in the number of nodes n, highlighting the advantage of incorporating neighborhood information. The effectiveness of the proposed framework is further supported by extensive numerical experiments. Application to whole-exome sequencing and RNA-sequencing Autism datasets demonstrates the usage of the proposed method in identifying the association between the gene modules of genetic variations and the gene modules of genomic differential expressions. Copyright © 2024, The Authors. All rights reserved.

关键词： Linear regression

Distribution-free uncertainty quantification for classification under label shift

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Podkopaev, Aleksandr Ramdas, Aaditya Department of Statistics & Data Science Machine Learning Department Carnegie Mellon University United States

Trustworthy deployment of ML models requires a proper measure of uncertainty, especially in safety-critical applications. We focus on uncertainty quantification (UQ) for classification problems via two avenues — prediction sets using conformal prediction and calibration of probabilistic predictors by post-hoc binning — since these possess distribution-free guarantees for i.i.d. data. Two common ways of generalizing beyond the i.i.d. setting include handling covariate and label shift. Within the context of distribution-free UQ, the former has already received attention, but not the latter. It is known that label shift hurts prediction, and we first argue that it also hurts UQ, by showing degradation in coverage and calibration. Piggybacking on recent progress in addressing label shift (for better prediction), we examine the right way to achieve UQ by reweighting the aforementioned conformal and calibration procedures whenever some unlabeled data from the target distribution is available. We examine these techniques theoretically in a distribution-free framework and demonstrate their excellent practical performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Uncertainty analysis

Median optimal treatment regimes

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Leqi, Liu Kennedy, Edward H. Machine Learning Department Department of Statistics & Data Science Carnegie Mellon University United States

Optimal treatment regimes are personalized policies for making a treatment decision based on subject characteristics, with the policy chosen to maximize some value. It is common to aim to maximize the mean outcome in the population, via a regime assigning treatment only to those whose mean outcome is higher under treatment versus control. However, the mean can be an unstable measure of centrality, resulting in imprecise statistical procedures, as well as unfair decisions that can be overly influenced by a small fraction of subjects. In this work, we propose a new median optimal treatment regime that instead treats individuals whose conditional median is higher under treatment. This ensures that optimal decisions for individuals from the same group are not overly influenced either by (i) a small fraction of the group (unlike the mean criterion), or (ii) unrelated subjects from different groups (unlike marginal median/quantile criteria). We introduce a new measure of value, the Average Conditional Median Effect (ACME), which summarizes across-group median treatment outcomes of a policy, and which the optimal median treatment regime maximizes. After developing key motivating examples that distinguish median optimal treatment regimes from mean and marginal median optimal treatment regimes, we give a nonparametric efficiency bound for estimating the ACME of a policy, and propose a new doubly robust-style estimator that achieves the efficiency bound under weak conditions. Finite-sample properties of the estimator are explored via numerical simulations and the proposed algorithm is illustrated using data from a randomized clinical trial in patients with HIV. Copyright © 2021, The Authors. All rights reserved.

关键词： Efficiency

Unbiased Risk Estimation in the Normal Means Problem via Coupled Bootstrap Techniques

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Oliveira, Natalia L. Lei, Jing Tibshirani, Ryan J. Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University United States

We develop a new approach for estimating the risk of an arbitrary estimator of the mean vector in the classical normal means problem. The key idea is to generate two auxiliary data vectors, by adding carefully constructed normal noise vectors to the original data. We then train the estimator of interest on the first auxiliary vector and test it on the second. In order to stabilize the risk estimate, we average this procedure over multiple draws of the synthetic noise vector. A key aspect of this coupled bootstrap (CB) approach is that it delivers an unbiased estimate of risk under no assumptions on the estimator of the mean vector, albeit for a modified and slightly "harder" version of the original problem, where the noise variance is elevated. We prove that, under the assumptions required for the validity of Stein’s unbiased risk estimator (SURE), a limiting version of the CB estimator recovers SURE exactly. We then analyze a bias-variance decomposition of the error of the CB estimator, which elucidates the effects of the variance of the auxiliary noise and the number of bootstrap samples on the accuracy of the estimator. Lastly, we demonstrate that the CB estimator performs favorably in various simulated experiments. © 2021, CC BY.

关键词： Vectors

Extrapolated cross-validation for randomized ensembles

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Du, Jin-Hong Patil, Pratik Roeder, Kathryn Kuchibhotla, Arun Kumar Department of Statistics and Data Science Carnegie Mellon University PittsburghPA15213 United States Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Department of Statistics University of California BerkeleyCA94720 United States

Ensemble methods such as bagging and random forests are ubiquitous in various fields, from finance to genomics. Despite their prevalence, the question of the efficient tuning of ensemble parameters has received relatively little attention. This paper introduces a cross-validation method, ECV (Extrapolated Cross-Validation), for tuning the ensemble and subsample sizes in randomized ensembles. Our method builds on two primary ingredients: initial estimators for small ensemble sizes using out-of-bag errors and a novel risk extrapolation technique that leverages the structure of prediction risk decomposition. By establishing uniform consistency of our risk extrapolation technique over ensemble and subsample sizes, we show that ECV yields δ-optimal (with respect to the oracle-tuned risk) ensembles for squared prediction risk. Our theory accommodates general predictors, only requires mild moment assumptions, and allows for high-dimensional regimes where the feature dimension grows with the sample size. As a practical case study, we employ ECV to predict surface protein abundances from gene expressions in single-cell multiomics using random forests under a computational constraint on the maximum ensemble size. Compared to sample-split and K-fold cross-validation, ECV achieves higher accuracy by avoiding sample splitting. Meanwhile, its computational cost is considerably lower owing to the use of the risk extrapolation technique. Copyright © 2023, The Authors. All rights reserved.

关键词： Extrapolation

MARK MY WORDS: DANGERS OF WATERMARKED IMAGES IN IMAGENET

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bykov, Kirill Müller, Klaus-Robert Höhne, Marina M.-C. Technische Universität Berlin Machine Learning Group Berlin10587 Germany Understandable Machine Intelligence Lab ATB Potsdam14469 Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany Korea University Department of Artificial Intelligence Seoul136-713 Korea Republic of Max Planck Institute for Informatics Saarbrücken66123 Germany Machine Learning Group UiT the Arctic University of Norway Tromsø9037 Norway Department of Computer Science University of Potsdam Potsdam14476 Germany

The utilization of pre-trained networks, especially those trained on ImageNet, has become a common practice in Computer Vision. However, prior research has indicated that a significant number of images in the ImageNet dataset contain watermarks, making pre-trained networks susceptible to learning artifacts such as watermark patterns within their latent spaces. In this paper, we aim to assess the extent to which popular pre-trained architectures display such behavior and to determine which classes are most affected. Additionally, we examine the impact of watermarks on the extracted features. Contrary to the popular belief that the Chinese logographic watermarks impact the "carton" class only, our analysis reveals that a variety of ImageNet classes, such as "monitor", "broom", "apron" and "safe" rely on spurious correlations. Finally, we propose a simple approach to mitigate this issue in fine-tuned networks by ignoring the encodings from the feature-extractor layer of ImageNet pre-trained networks that are most susceptible to watermark imprints. © 2023, CC BY.

关键词： Watermarking

An Efficient Brain tumor classification using CNN and transfer learning

学校读者我要写书评

暂无评论

An Efficient Brain tumor classification using CNN and transf...

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： P. Sasikumar Srikanth Cherukuvada P Balmurugan P Vijay Anand S. Brindasri R. Nareshkumar Department of Artificial Intelligence and Machine Learning Sphoorthy Engineering College Nadergul Hyderabad Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Bowrampet Hyderabad Telangana Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Department of Artificial Intelligence and Data Science CMR Institute of Technology Bengaluru India Department of Computer Science Hindustan Institute of Technology and Science Padur Chennai India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

The proper detection of brain tumors as quickly as possible and the administration of efficient therapy are both necessary steps in the process of curing patients. The complexities of tumor morphology, such as size, location, and texture, as well as heteromorphic appearance in medical pictures, make tumor analysis a difficult *** three most frequent types of brain cancer are brain tumors, meningiomas, and pituitary gland tumors. The purpose of this study is to investigate a classification issue known as a triple-class problem in order to correctly identify these *** a pre-trained version of the vgg16 network, the proposed classification method pulls characteristics from brain MRI scans. Classifier models that have shown their worth in practice are given to help put the retrieved attributes into meaningful groups. The presented method is carried out on the Python platform, and its efficacy is evaluated with the use of performance *** to the results, the conventional neural network (CNN) technique was outperformed by the Transfer learning method, which resulted in the model having a higher overall performance. This can be observed by demonstrating that the model had a stronger overall performance.

关键词： Accuracy Magnetic resonance imaging Transfer learning Brain cancer Brain modeling Feature extraction Pituitary gland