检索结果-内蒙古大学图书馆

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Li, Chenyi Wu, Guande Chan, Gromit Yeuk-Yin Turakhia, Dishita Gdi Castelo Quispe, Sonia Li, Dong Welch, Leslie Silva, Claudio Qian, Jing Tandon School of Engineering New York University New YorkNY United States Adobe Research San JoseCA United States Visualization and Data Analytics Lab New York University New YorkNY United States Tandon School of Engineering BrooklynNY United States Brown University ProvidenceRI United States New York University New York CityNY United States Tandon School of Engineering New York University BrooklynNY United States

ISBN: (纸本)9798400713941

Augmented Reality (AR) assistance is increasingly used for supporting users with physical tasks like assembly and cooking. However, most systems rely on reactive responses triggered by user input, overlooking rich contextual and user-specific information. To address this, we present Satori, a novel AR system that proactively guides users by modeling both - their mental states and environmental contexts. Satori integrates the Belief-Desire-Intention (BDI) framework with the state-of-the-art multi-modal large language model (LLM) to deliver contextually appropriate guidance. Our system is designed based on two formative studies involving twelve experts. We evaluated the system with a sixteen within-subject study and found that Satori matches the performance of designer-created Wizard-of-Oz (WoZ) systems, without manual configurations or heuristics, thereby improving generalizability, reusability, and expanding the potential of AR assistance. Code is available at https://***/VIDA-NYU/satori-assistance. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

UNIVERSAL APPROXIMATION OF PARAMETRIC OPTIMIZATION VIA NEURAL NETWORKS WITH PIECEWISE LINEAR POLICY APPROXIMATION

arXiv

引用

arXiv 2023年

作者： Bae, Hyunglip Kim, Jang Ho Kim, Woo Chang Department of Industrial and System Engineering KAIST Korea Republic of Depart of Industrial and Management System Engineering Department of Big Data Analytics Kyung Hee University Korea Republic of

Parametric optimization solves a family of optimization problems as a function of parameters. It is a critical component in situations where optimal decision making is repeatedly performed for updated parameter values, but computation becomes challenging when complex problems need to be solved in real-time. Therefore, in this study, we present theoretical foundations on approximating optimal policy of parametric optimization problem through Neural Networks and derive conditions that allow the Universal Approximation Theorem to be applied to parametric optimization problems by constructing piecewise linear policy approximation explicitly. This study fills the gap on formally analyzing the constructed piecewise linear approximation in terms of feasibility and optimality and show that Neural Networks (with ReLU activations) can be valid approximator for this approximation in terms of generalization and approximation error. Furthermore, based on theoretical results, we propose a strategy to improve feasibility of approximated solution and discuss training with suboptimal solutions. © 2023, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Dynamic Locomotion of Quadruped Robot in Sloping Terrain

Dynamic Locomotion of Quadruped Robot in Sloping Terrain

引用

International Symposium on Autonomous Systems (ISAS)

作者： Donglin Chen Dehong Cong Xiangman Song National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Key Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Ministry of Education Shenyang China Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Shenyang China

In order to improve the locomotion capability of quadruped robot in the sloping terrain and enhance whose adaptability to the environment, this paper proposes a method to realize dynamic locomotion of quadruped robot in sloping terrain completely based on model predictive control (MPC) and proprioception. According to the foot contact signal and the robot body posture information measured by inertial measurement unit (IMU), quadruped robot actively changes whose body posture to adapt to different sloping terrains. This paper builds quadruped robot virtual prototype and test terrain in Webots simulation environment. The experimental results show that with this method, the roll angle fluctuation range of the quadruped robot is less than 0.05rad and the yaw angle fluctuation range is not more than 0.003rad. At the same time, when the angle of slope changes, the terrain adaptation time of the quadruped robot is less than 1.8s. The above results show that quadruped robot has excellent movement ability in sloping terrain and environmental adaptability under the condition of ensuring stability with the method proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal data Fusion Approach Using the Structured and Sparse Principal Component Analysis (MMSSCA)

Multi-Modal Data Fusion Approach Using the Structured and Sp...

引用

2023 IEEE International Conference on Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario, ICPSITIAGS 2023

作者： Kandpal, Jyoti Jonitha, A. Sivakumar, Janaki Ray, Rejon Kumar School of Computing Graphic Era Hill University Uttarakhand Dehradun India Universiti Malaysia Faculty of Data Science & Computing Kelantan Malaysia Global College of Engineering and Technology Computer Science and Creative Technologies Muscat Oman Gannon University Department of Business Analytics PA Erie United States

ISBN: (纸本)9798350329773

There are many different sorts of data that can be gathered and analyzed, including pictures, videos, texts, speeches, music, and other noises, Video content, for example, generally includes minimum some types of audible sounds or any type of visual image, and often also useful text data that can be of some specific type of titles or subtitles, which may consist of some unique type text language which is different type of speech. 'Modality' is basically defines each different type of acquisition strategy. As natural phenomena tend to be quite complex, it is unusual for a single modality to provide exhaustive understanding of the phenomenon of interest. The process of combining and interpreting the useful data between the same modal or in different modal, and also interaction with the human beings with multi-modal data fusion &the accurate and deep interpretation and understanding of data obtained from the combining process from it, are central to the research challenge on multimodal data analysis. We contend that many of these challenges are shared by researchers in different fields. Both the 'why' and the 'how' of data fusion are addressed in this paper. Various examples from the realms of science and technology serve as inspiration for the first problem, which is then suggested by a various types of mathematical based model framework demonstrating the utility of data fusion. To solve the second problem, we introduce the idea of 'diversity' as a central concept and discuss several data-driven solutions based on matrix and tensor decompositions, highlighting how they take into account diversity in the underlying data sets to address the aforementioned issues, this research suggests a novel approach for modeling multi data fusion implemented using sparse technique and structural analysis. © 2023 IEEE.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Gaitmap - An Open Ecosystem for IMU-based Human Gait Analysis and Algorithm Benchmarking

TechRxiv

引用

TechRxiv 2023年

作者： Küderle, Arne Ullrich, Martin Roth, Nils Ollenschläger, Malte Ibrahim, Alzhraa Moradi, Hamid Richer, Robert Seifer, Ann-Kristin Zürl, Matthias Sîmpetru, Raul Herzer, Liv Prossel, Dominik Kluge, Felix Eskofier, Bjoern Friedrich-Alexander-Universität Erlangen-Nürnberg Machine Learning and Data Analytics Lab Department of Artificial Intelligence in Biomedical Engineering Germany

来源：评论

学校读者我要写书评

暂无评论

Melanoma Detection with Transfer Learning

Melanoma Detection with Transfer Learning

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： Pragadeshwar Vishnu S Krishvadana C Rani Rajeev Khoodeeram Ahmed Bouridane M Rajesh Kumar School of Electronics Engineering Vellore Institute of Technology Vellore India Department of Emerging Technologies Université Des Mascareignes Mauritius Centre for Data Analytics University of Sharjah Sharjah UAE

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

The abnormal growth of skin cells that are exposed to the sun is identified as skin cancer. Even though skin cancer is curable, late diagnosis and improper treatment can lead to severe effects and death. Melanoma has been identified as the deadliest type of skin cancer and it is responsible for $85 \%$ of skin cancer deaths. Even though research on melanoma identification is prominent, still it has not been perfected. Automated Melanoma recognition is a challenging task due to various artifacts such as low-contrast dermoscopic images, and large and similar varieties of other skin cancers. In this study, we take on this challenge using neural networks. We implement an approach in which two trained neural networks are combined to give a higher accuracy output. With the lack of training data for classification, we employ data augmentation techniques. The proposed Model makes use of two types of learning approaches by combining their weights and predicting the output. The combined or ensemble model categorizes the output into 6 different categories with an accuracy of up to $89 \%$. The approach is simple to implement and surpasses other avant-garde techniques in terms of accuracy.

关键词： Accuracy Neural networks Transfer learning Training data Melanoma Learning (artificial intelligence) Predictive models

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Campus Parking Utilization to Cloud on Blynk Application

Enhancing IoT Campus Parking Utilization to Cloud on Blynk A...

引用

IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS)

作者： NorakmarArbain Sulaiman Murizah Kassim Nor Syazwani Mohd Pakhrudin Muhammad Afiq Azman Shuria Saaidin Yuslinda Wati Mohamad Yusof School of Electrical Engineering College of Engineering Universiti Teknologi MARA Shah Alam Selangor Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Shah Alam Selangor Malaysia

ISBN: (数字)9798350372106

ISBN: (纸本)9798350372113

Issues with parking spaces are crucial to the growing number of vehicles especially in campus universities. Automatic gates have been implemented but still parking spaces were taken by unauthorized users. To address this issue, this study investigates the usage of Internet of Things (IoT) technology, which permits data flow without human interaction, making it appropriate for a wide range of applications in modern society. This paper describes the creation of the Campus Parking Monitoring System (CPMS), a simple mobile application created with Blynk on cloud platform. The CPMS was designed to assist students in locating available parking spaces in specific lots. It also intends to address the issue of double parking by offering a more systematic and user-friendly approach to parking lot management. CPMS has been designed and tested for a week. Three main days of data collection have been presented. As the parking system is designed and implemented in a prototype mode, the combination of the CPMS application and the parking prototype kit displays its efficiency in solving and analyzing parking-related issues during weekday tests and simulations based on real-life circumstances.

关键词： Space vehicles Cloud computing Systematics Prototypes Hardware Mobile applications Wire

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

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

引用

Intelligent Technologies (CONIT), International Conference on

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

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

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Breast Cancer Diagnosis with Vision Transformers: A Novel Approach using MaskGuided Attention for Ultrasound Image Classification

Enhancing Breast Cancer Diagnosis with Vision Transformers: ...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Deena Sivakumar Anamika Kumari Divya Dharshini K Samiksha S Hemachandran M Department of Computer Science and Engineering Sri Ramachandra Institute of Higher Education and Research Chennai Department of Computer Science (AI & Data Analytics) Sri Ramachandra Institute of Higher Education and Research Chennai

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Deep learning models, notably convolutional neural networks (CNNs), demonstrate great promise in medical image processing. Nonetheless, CNNs frequently encounter challenges in capture holistic context and long- range dependencies in high-resolution images, which are crucial for accurate medical diagnostics. A new state-of-the-art technique called Vision Transformers (ViTs) uses self-attention mechanisms for gathering global correlations between image patches, thereby addressing some of the inherent limitations of CNNs. This study investigates the application of ViTs for diagnosing breast cancer from ultrasound images of tumor. The findings suggest that ViTs not only achieve competitive accuracy in identifying breast cancer lesions but also offer superior interpretability through attention mechanism, which can aid clinicians in understanding model decisions. This paper highlights the potential of ViTs as a powerful tool in medical imaging, particularly for breast cancer diagnosis, and outlines future research directions for enhancing clinical applicability.

关键词： Deep learning Computer vision Accuracy Attention mechanisms Ultrasonic imaging Transformers Breast cancer Convolutional neural networks Medical diagnosis Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

From Occasional to Steady: Habit Formation Insights From a Comprehensive Fitness Study

arXiv

引用

arXiv 2025年

作者： Demirci, Ege Tüzün, Efe Ün, Ahmet Furkan Sönmez, Taner Giray Varol, Onur Faculty of Engineering and Natural Sciences Sabanci University Istanbul34956 Turkey Mars Athletic Club Istanbul34340 Turkey Center of Excellence in Data Analytics Sabanci University Istanbul34956 Turkey

Exercising regularly is widely recognized as a cornerstone of health, yet the challenge of sustaining consistent exercise habits persists. Understanding the factors that influence the formation of these habits is crucial for developing effective interventions. This study utilizes data from Mars Athletic Club, Türkiye’s largest sports chain, to investigate the dynamics of gym attendance and habit formation. The general problem addressed by this study is identifying the critical periods and factors that contribute to the successful establishment of consistent exercise routines among gym-goers. Here we show that there are specific periods during which gym attendance is most crucial for habit formation. By developing a survival metric based on gym attendance patterns, we pinpoint these critical periods and segment members into distinct clusters based on their visit patterns. Our analysis reveals significant differences in how various subgroups respond to interventions, such as group classes, personal trainer sessions, and visiting different clubs. Using causal inference analysis, we demonstrate that personalized guidance and social dynamics are key drivers of sustained long-term engagement. By systematically examining these variables and considering the specific characteristics of different clusters, our research demonstrates the importance of a tailored, multi-dimensional approach to promoting exercise habits, which integrates social dynamics, personalized guidance, and strategic interventions to sustain long-term engagement. Copyright © 2025, The Authors. All rights reserved.

关键词： Cluster analysis

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：