检索结果-内蒙古大学图书馆

Towards Predicting Menstrual Cycle Phases Exploiting Paralinguistic Features

学校读者我要写书评

暂无评论

Towards Predicting Menstrual Cycle Phases Exploiting Paralin...

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

作者： Anika A. Spiesberger Adria Mallol-Ragolta Andreas Triantafyllopoulos Björn W. Schuller CHI - Chair of Health Informatics Klinikum Rechts Der Isar Technical University of Munich Germany MCML - Munich Center for Machine Learning Germany GLAM - Group on Language Audio & Music Imperial College London UK MDSI - Munich Data Science Institute Germany

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

As a growing number of people focus on understanding their bodies, the menstrual cycle and its impact on reproduction are gaining attention. Several studies have shown that the voice changes during the menstrual cycle. However, existing research primarily employs comparative analysis to detect these differences. This paper proposes using machine learning methods to analyse paralinguistic features extracted from women’s voices for predicting menstrual cycle phases. We leverage available data recorded during the menstrual and late follicular phases of 44 naturally cycling women. Using eight paralinguistic features, we achieve an accuracy of 60 %, showcasing the feasibility of classifying those two phases using speech signals. We discuss implications and suggest future research avenues, such as the need to use personalised approaches.

关键词： Accuracy Target tracking machine learning Feature extraction Engineering in medicine and biology

Review of machine learning and Deep learning algorithms for Personality traits classification

学校读者我要写书评

暂无评论

Review of Machine Learning and Deep Learning algorithms for ...

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

作者： Satish N Bhadane Prateek Verma Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Sawangi Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning 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

Nowadays, people deal with major psychological issues on a daily basis, often in the absence of a desired support system. In the field of psychology, focus is on the thoughts, feelings, behaviors, goals, and interests of individuals. The psychologist conventionally considers various types of personality traits, like the Big 5 personality traits, the Myers-Briggs Type Indicator (MBTI), the OCEAN Model (Openness, Conscientiousness, Agreeableness, Extraversion, Neuroticism), and other methods also considered for measuring personality. To forecast personality traits like extraversion, agreeableness, openness, conscientiousness, and neuroticism, consider the name "Big Five personality traits" It is a universal model to forecast these personality traits. Studies on personality prediction that identify personality disorders from user content on social media sites like Facebook, Twitter, and WhatsApp primarily rely on user behavior on these platforms. A number of popular Deep learning (DL) techniques have advanced recently, including Deep Belief Networks (DBNs), Convolution Neural Networks (CNNs), and Recurrent Neural Networks (RNNs). Examine these methods in terms of single and multiple modalities, including psychological, audio, video, text, and image information. Researchers currently focus on predicting personality traits using single-modality text features, static facial images, audio, and video clips, including interview recordings and YouTube videos. Therefore, the current study highlights that personality prediction mostly relies on written text, audio and video datasets used in machine learning (ML) and DL models. Additional investigation is needed to resolve ethical concerns and justify the use of psychological datasets and DL models to evaluate personality traits. By combining personality traits with a psychological dataset, this study imagines a time when people everyday struggles can be effectively addressed. The integration of ML and DL in the development of p

关键词： Industries Deep learning Video on demand Recurrent neural networks Social networking (online) Reviews Psychology Sea measurements Predictive models Web sites

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

ACTIONS ON CLASSIFIABLE C*-ALGEBRAS WITHOUT EQUIVARIANT PROPERTY (SI)

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gardella, Eusebio Kranz, Julian Vaccaro, Andrea Department of Mathematical Sciences Chalmers University of Technology University of Gothenburg GothenburgSE-412 96 Sweden Data Science: Machine Learning and Data Engineering Prof. Dr. Fabian Gieseke Leonardo-Campus 3 Münster48149 Germany Mathematisches Institut Fachbereich Mathematik Informatik der Universität Münster Einsteinstrasse 62 Münster48149 Germany

We exhibit examples of actions of countable discrete groups on both simple and non-simple nuclear stably finite C*-algebras that are tracially amenable but not amenable. We furthermore obtain that, under the additional assumption of strict comparison, amenability is equivalent to tracial amenability plus the equivariant analogue of Matui-Sato's property (SI). By virtue of this equivalence, our construction yields the first known examples of actions on classifiable C*-algebras that do not have equivariant property (SI). We moreover show that such actions can be chosen to absorb the trivial action on the universal UHF algebra, thus proving that equivariant Z-stability does not in general imply equivariant property (SI). Copyright © 2024, The Authors. All rights reserved.

关键词： Algebra

The Future of Driving: A Review on the Combination of Artificial Intelligence and Autonomous Vehicles

学校读者我要写书评

暂无评论

The Future of Driving: A Review on the Combination of Artifi...

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

作者： Nikita Zade Mayur Gawande Prateek Verma Swapnil Gundewar Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Sawangi Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning 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

The convergence of Artificial Intelligence (AI) and Autonomous Vehicles (AV) are poised to revolutionize the automotive industry, offering safer, more efficient, and sustainable transportation solutions. This review article explores the current state of AVs, role of AI in AV, challenges and hurdles, Real world applications & development, its critical technological components, and their impact on society. This paper presents a wide array of applications of AI in AV, elaborating on the way complex sensor fusion, computer vision, and machine learning (ML) algorithms makes AVs perceive their surroundings, form critical opinions, and carry out accurate motions. AI is making real time interpretations of great quantities of data which are paving the way for safer and more effective navigation under a diversity of traffic circumstances, from sensor fusion to decision-making algorithms. The next section of this paper elaborates on the role of AI in the field of AV in perceiving, planning, and navigating through real world environment, while also talking about issues of integration and ethics. This paper further identifies its social, economic, and environmental consequences, resulting from mass use of AV. This article discusses the latest developments and opportunities in the regulatory environment, gives an overview of how AV define transportation in the near future. This paper also explores the levels of autonomy of AVs as defined by the Society of Automotive Engineers (SAE) and defines the process from driver assistance to full automation. It examines the ethical and technical considerations arising at each instant and emphasizes the key role AI continues to play in providing more autonomy while preserving security and dependability.

关键词： Ethics machine learning algorithms Reviews Navigation Decision making Sensor fusion Safety Artificial intelligence Socioeconomics Automotive engineering

Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hille, Tobias Stubbemann, Maximilian Hanika, Tom Knowledge & Data Engineering Group University of Kassel Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Kassel Germany Information Systems and Machine Learning Lab University of Hildesheim Hildesheim Germany Institute of Computer Science University of Hildesheim Hildesheim Germany

Difficulties in replication and reproducibility of empirical evidences in machine learning research have become a prominent topic in recent years. Ensuring that machine learning research results are sound and reliable requires reproducibility, which verifies the reliability of research findings using the same code and data. This promotes open and accessible research, robust experimental workflows, and the rapid integration of new findings. Evaluating the degree to which research publications support these different aspects of reproducibility is one goal of the present work. For this we introduce an ontology of reproducibility in machine learning and apply it to methods for graph neural networks. Building on these efforts we turn towards another critical challenge in machine learning, namely the curse of dimensionality, which poses challenges in data collection, representation, and analysis, making it harder to find representative data and impeding the training and inference processes. Using the closely linked concept of geometric intrinsic dimension we investigate to which extend the used machine learning models are influenced by the intrinsic dimension of the data sets they are trained *** Codes 68T01 68T07 68T09 51F99 Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

Generalized independent noise condition for estimating causal structure with latent variables

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of machine learning Research 2024年第1期25卷 9044-9104页

作者： Feng Xie Biwei Huang Zhengming Chen Ruichu Cai Clark Glymour Zhi Geng Kun Zhang Department of Applied Statistics Beijing Technology and Business University Beijing China Halicioglu Data Science Institute (HDSI) University of California San Diego La Jolla San Diego California School of Computer Science Guangdong University of Technology Guangzhou China and Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi UAE School of Computer Science Guangdong University of Technology Guangzhou China Department of Philosophy Carnegie Mellon University Pittsburgh PA Department of Philosophy Carnegie Mellon University Pittsburgh PA and Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi UAE

We investigate the challenging task of learning causal structure in the presence of latent variables, including locating latent variables, determining their quantity, and identifying causal relationships among both latent and observed variables. To address this, we propose a Generalized Independent Noise (GIN) condition for linear non-Gaussian acyclic causal models that incorporate latent variables, which establishes the independence between a linear combination of certain measured variables and some other measured variables. Specifically, for two observed random vectors Y and Z, GIN holds if and only if ωΤ-Y and Z are statistically independent, where ω is a non-zero parameter vector determined by the cross-covariance between Y and Z. We then give necessary and sufficient graphical criteria of the GIN condition in linear non-Gaussian acyclic causal models. From a graphical perspective, roughly speaking, GIN implies the existence of a set S such that S is causally earlier (w.r.t. the causal ordering) than Y, and that every active (collider-free) path between Y and Z must contain a node from S. Interestingly, we find that the independent noise condition (i.e., if there is no confounder, causes are independent of the residual derived from regressing the effect on the causes) can be seen as a special case of GIN. With such a connection between GIN and latent causal structures, we further leverage the proposed GIN condition, together with a well-designed search procedure, to efficiently estimate Linear, Non-Gaussian Latent Hierarchical Models (LiNGLaHs), where latent confounders may also be causally related and may even follow a hierarchical structure. We show that the underlying causal structure of a LiNGLaH is identifiable in light of GIN conditions under mild assumptions. Experimental results on both synthetic and three real-world data sets show the effectiveness of the proposed approach.

关键词： causal discovery latent variable latent hierarchical structure latent causal graph non-Gaussianity

A Smart Electronic Wheelchair Design Using Artificial Intelligence and Intelligent Sensors Association 2

学校读者我要写书评

暂无评论

A Smart Electronic Wheelchair Design Using Artificial Intell...

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Balamurugan, R. Kanchana, D. Anni Princy, B. Jaisudha, J. Malathi, P. Glory, E. Ajk College of Arts and Science Department of Artificial Intelligence and Machine Learning Tamil Nadu Coimbatore India Srm Institute of Science and Technology Department of Computer Applications Tamil Nadu Chennai India Panimalar Engineering College Department of Computer and Communication Engineering Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Ece Tamil Nadu Chennai India Simats Saveetha College of Liberal Arts and Sciences Department of Data Analytics Tamil Nadu Chennai India Simats Department of Biosciences Saveetha School of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350306415

Since the beginning of the seventeenth century, wheelchairs have been used to transport hospital patients and those with mobility impairments. The power of people is what spreads wheelchairs. Wheelchair users propel themselves forward using their upper bodies or, more commonly, require the assistance of another person to propel them. In this work, we examine how to build an autonomous electric wheelchair for the disabled at the lowest possible cost without sacrificing quality of design or control. This research presents the planning and development of an AI-enhanced electric wheelchair that can be controlled automatically to climb stairs, making it accessible to those with mobility impairments. The chair's controls allow the user to move it in any direction and raise the landing and staircases to varying heights. The chair's DC power source (battery used) may be recharged, allowing it to function for an extended period of time. In addition, a safety system was created that monitors and provides feedback on the user's pulse rate, as well as the wheelchair's functioning state (including acceleration, climate, and inclination position). This proposed AI based Wheelchair (AIWC) design is suitable for any aged people and the proposed model is cross-validated with the conventional wheelchair design using mobile based operations handling system called Mobile-Wheelchair (MWC) to test the efficiency of the proposed design in clear manner. © 2024 IEEE.

关键词： Accelerator AI Artificial Intelligence Batteries DC Power Intelligent Sensors Mobile-Wheelchair MWC Wheelchair

A fast neural hybrid Newton solver adapted to implicit methods for nonlinear dynamics

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jin, Tianyu Maierhofer, Georg Schratz, Katharina Xiang, Yang Department of Mathematics The Hong Kong University of Science and Technology Clear Water Bay Hong Kong Mathematical Institute University of Oxford United Kingdom Sorbonne Université France Algorithms of Machine Learning and Autonomous Driving Research Lab HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Futian Shenzhen China

The use of implicit time-stepping schemes for the numerical approximation of solutions to stiff nonlinear time-evolution equations brings well-known advantages including, typically, better stability behaviour and corresponding support of larger time steps, and better structure preservation properties. However, this comes at the price of having to solve a nonlinear equation at every time step of the numerical scheme. In this work, we propose a novel deep learning based hybrid Newton’s method to accelerate this solution of the nonlinear time step system for stiff time-evolution nonlinear equations. We propose a targeted learning strategy which facilitates robust unsupervised learning in an offline phase and provides a highly efficient initialisation for the Newton iteration leading to consistent acceleration of Newton’s method. A quantifiable rate of improvement in Newton’s method achieved by improved initialisation is provided and we analyse the upper bound of the generalisation error of our unsupervised learning strategy. These theoretical results are supported by extensive numerical results, demonstrating the efficiency of our proposed neural hybrid solver both in one- and two-dimensional cases. Copyright © 2024, The Authors. All rights reserved.

关键词： Nonlinear equations