检索结果-内蒙古大学图书馆

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Lee, Hyunjong Jung, Han Hee Kwak, Jeongho Yea, Junwoo Choi, Jihwan P. Jang, Kyung-In Department of Electrical Engineering and Computer Science Daegu Korea Republic of Dgist Department of Robotics and Mechatronics Engineering Daegu Korea Republic of Dgist Department of Electrical Engineering and Computer Science Daegu Korea Republic of Department of Aerospace Engineering Dajeon Korea Republic of

ISBN: (纸本)9798350313277

Analyzing wine using taste data is a promising field due to the explosive expansion of online commerce. However, because of the wide variety of wine types with different flavors and aromas, it is difficult for consumers to choose the wine that suits their taste, and also difficult for sellers to recommend appropriate wines to consumers. Therefore, it is necessary to numerically analyze and classify wine, and a deep learning algorithm which mimics the human brain is appropriate for analyzing the wine data [1]. In this paper, we introduce several studies of wine classification using deep learning architectures and propose preprocessing methods for applying the taste data of wine to deep learning networks. © 2023 IEEE.

关键词： data augmentation deep learning preprocessing taste classification taste sensor wine

来源：评论

学校读者我要写书评

暂无评论

Existing Approaches & A Proposal to Content Analysis of Pilots' Speech Activities

Existing Approaches & A Proposal to Content Analysis of Pilo...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Diana Bogdanova Azamat Giniiatullin Jaspreet Singh Batth Ufa University of Science and Technology Institute of Computer Science Mathematics and Robotics Ufa Russia Chandigarh University Computer Science and Engineering Chandigarh India

Content analysis of pilot speech is a key tool for improving flight safety as it allows to identify potential problems in communication between pilots, dispatchers and crew. The development of efficient algorithms for analyzing pilot speech contributes to improving communication skills, preventing incidents and improving overall airline safety. The research focuses on the possibility of applying machine learning techniques and deep neural networks to analyze speech data, which opens new perspectives for information processing and interpretation. The results of the study emphasize the interdisciplinary nature of the topic and suggest new methodological approaches, including the use of fuzzy set theory and fuzzy logic systems to handle uncertainty in speech data, which in turn helps to improve communication performance in complex and stressful flight conditions. The finalization of the work includes the evaluation of the developed methods and approaches in terms of their applicability and impact on improving flight safety, incorporating model training results and addressing testing errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MULTI-ROBOT MOTION PLANNING WITH DIFFUSION MODELS

arXiv

引用

arXiv 2024年

作者： Shaoul, Yorai Mishani, Itamar Vats, Shivam Li, Jiaoyang Likhachev, Maxim Robotics Institute School of Computer Science Carnegie Mellon University United States

Diffusion models have recently been successfully applied to a wide range of robotics applications for learning complex multi-modal behaviors from data. However, prior works have mostly been confined to single-robot and small-scale environments due to the high sample complexity of learning multi-robot diffusion models. In this paper, we propose a method for generating collision-free multi-robot trajectories that conform to underlying data distributions while using only single-robot data. Our algorithm, Multi-robot Multi-model planning Diffusion (MMD), does so by combining learned diffusion models with classical search-based techniques—generating data-driven motions under collision constraints. Scaling further, we show how to compose multiple diffusion models to plan in large environments where a single diffusion model fails to generalize well. We demonstrate the effectiveness of our approach in planning for dozens of robots in a variety of simulated scenarios motivated by logistics environments. View video demonstrations in our supplementary material, and our code at: https://***/yoraish/mmd. Copyright © 2024, The Authors. All rights reserved.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Multiple Linear Regression Model for Prediction of Roughness of Grind Surface

Multiple Linear Regression Model for Prediction of Roughness...

引用

2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2023

作者： Sahu, Neelesh Kumar Patel, Ruchi Verma, Ashok Kumar Robotics and Artificial Intelligence Gyan Ganga Intititue of Technology and Sciences Jabalpur India Computer Science and Engineering Gyan Ganga Intititue of Technology and Sciences Jabalpur India

ISBN: (纸本)9798350312126

Multiple linear regression is process of attempting linear relation between response and a set of variables. In the present work, the roughness of grind surface was considered as a regressed variable during cylindrical grinding operation performed on lathe machine. The data was generated after performing experiments with varying regressor variables i.e. grinding wheel rotation (RPM), feed motion (mm/rev), and grinding depth cut (mm). These independent variables are varied in sequential manner using central composite design (CCD) under Response surface methodology (RSM). Regression coefficients are estimated to develop linear regression model. Later on, inference of regressor variables on regressed variable is done to interpret the regression model. The value of R2 and Adjusted R2 are found to be 95% and 94% respectively which suggests that model can be correlated with experimental data. Multicollinearity among regressor variables is done to check the correlations for assurance of interpretation of individual regressor variable over regressed variable. A hypothesis testing was done for predicting roughness of grind surface for 95 % confidence interval and found acceptable. Regression model is validated with additional experimental values of roughness of grind surface and found within acceptable range (max. 10% absolute error). Regression model can be interpreted as reduction in roughness of grind surface with increase in grinding wheel (RPM) whereas it increases with increase in grinding depth (mm) and feed motion (mm/rev). © 2023 IEEE.

关键词： Grinding (machining)

来源：评论

学校读者我要写书评

暂无评论

CF-AMVRGO: Collaborative Filtering based Adaptive Moment Variance Reduction Gradient Optimizer for Movie Recommendations

引用

International Journal of computers and Applications 2022年第11期44卷 1015-1023页

作者： Lakshmi Chetana, V. Seetha, Hari School of Computer Science and Engineering VIT-AP University Andhra Pradesh Vijayawada India Center of Excellence AI and Robotics VIT-AP University Andhra Pradesh Vijayawada India

In recent decades, recommendation systems are used in a variety of applications like social connections, movies, music, and venues. The existing algorithms has certain limitations like data sparsity, cold start problem, and poor scalability to degrade the movie recommendation performance. To address the aforementioned concerns, a new matrix factorization-based collaborative filtering algorithm is developed to enhance movie recommendation performance. In a neural collaborative filtering algorithm, an adaptive moment variance reduction gradient optimizer is applied in low-rank matrix factorization for representing the users and items in a low dimensional latent space to obtain effective movie recommendation performance. In this paper, the proposed algorithm performance is evaluated on three benchmark datasets;movielens 100K, 1M, and 10M datasets. Simulation results showed that the proposed algorithm obtained the difference of 0.08 and 0.056 roots mean square error value in movielens 1M and 10M datasets, which are better compared to the existing collaborative filtering-based deep learning algorithm. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset

arXiv

引用

arXiv 2024年

作者： Hu, Yubin Wen, Kairui Zhou, Heng Guo, Xiaoyang Liu, Yong-Jin Department of Computer Science and Technology Tsinghua University China Horizon Robotics China

Reconstructing accurate 3D surfaces for street-view scenarios is crucial for applications such as digital entertainment and autonomous driving simulation. However, existing street-view datasets, including KITTI, Waymo, and nuScenes, only offer noisy LiDAR points as ground-truth data for geometric evaluation of reconstructed surfaces. These geometric ground-truths often lack the necessary precision to evaluate surface positions and do not provide data for assessing surface normals. To overcome these challenges, we introduce the SS3DM dataset, comprising precise Synthetic Street-view 3D Mesh models exported from the CARLA simulator. These mesh models facilitate accurate position evaluation and include normal vectors for evaluating surface normal. To simulate the input data in realistic driving scenarios for 3D reconstruction, we virtually drive a vehicle equipped with six RGB cameras and five LiDAR sensors in diverse outdoor scenes. Leveraging this dataset, we establish a benchmark for state-of-the-art surface reconstruction methods, providing a comprehensive evaluation of the associated challenges. For more information, visit our homepage at https://***. © 2024, CC BY-NC-ND.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Predicting Threat Degree for Onset of Type 2 Diabetes Mellitus Based on Machine Learning Methods 6th

Predicting Threat Degree for Onset of Type 2 Diabetes Mellit...

引用

6th Computational Methods in Systems and Software, CoMeSySo 2022

作者： Shakhmametova, Gyuzel Vakkazov, Nikita Klimets, Sofya Computer Science and Robotics Department Ufa State Aviation Technical University Ufa Russia Faculty of General Medicine Bashkir State Medical University Ufa Russia

ISBN: (纸本)9783031214349

This article discusses the use of machine learning methods to predict the degree of threat for onset of type 2 diabetes mellitus in patients aged 25 years. Type 2 diabetes mellitus is a disease that complicates the course of other concomitant diseases, and predicting the threat of its occurrence is an important element in forming the trajectory of diagnosis and treatment of the patient. A binary classification model based on the logistic regression method has been proposed and developed. The developed approach identifies the threat of diabetes mellitus onset using indicators such as age, sex, body mass index (BMI) and glycated hemoglobin (HbA1c). The paper describes how to build a model, and how to generate and prepare data for binary logistic regression. To implement the described approaches, the Python programming language, the Jupyter Lab development environment and scikit-learn, scipy, pandas, and numpy packages were used. Performance analysis showed accuracy of the proposed model as 0.98 on test data. The developed software can be used as a separate application and be built as a module into the clinical decision support system #COMESYSO1120. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Logistic regression Machine learning Predicting Type 2 diabetes mellitus

来源：评论

学校读者我要写书评

暂无评论

Search Space Optimization for Autonomous Mobile Robots Using Meta-Heuristics 14

Search Space Optimization for Autonomous Mobile Robots Using...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Benni, Rashmi Totad, Shashikumar Karibasappa, K.G. Karadgi, Sachin Kle Technological University School of Computer Science Karnataka Hubballi580031 India Kle Technological University Department of Automation & Robotics Karnataka Hubballi580031 India

ISBN: (纸本)9798350335095

Optimizing search space for autonomous mobile robots is a critical problem that affects their ability to efficiently navigate and perform tasks in various environments. Considering the growing level of complexity of robotic systems, the area of search space for finding optimal solutions can be very large and time-consuming. Meta-heuristics are a class of algorithms designed for exploring large search spaces and locating near-optimal solutions. Their application is one of the strategies and approaches to addressing this challenge. This research paper presents metaheuristic techniques such as the firefly algorithm(FA), particle swarm optimization(PSO), and differential evolution(DE) in search space optimization of autonomous mobile robots. Also, it covers an overview of each algorithm, indicating its benefits and drawbacks and demonstrating how it potentially performs in varied search space environments. The study also looks at how various hyper-parameters influence the way each algorithm performs. The findings indicate that these factors significantly affect the algorithm's functioning and the most appropriate values can be identified through a parameter-tuning technique. We also discuss some challenges and possibilities for future study in this area. Furthermore, for researchers and practitioners interested in using meta-heuristics to address search space optimization problems for robots or any other search space-related applications this study offers insightful guidance. © 2023 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

VIDA: HOMEOSTATIC VISUAL DOMAIN ADAPTER FOR CONTINUAL TEST TIME ADAPTATION 12

VIDA: HOMEOSTATIC VISUAL DOMAIN ADAPTER FOR CONTINUAL TEST T...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Liu, Jiaming Yang, Senqiao Jia, Peidong Zhang, Renrui Lu, Ming Guo, Yandong Xue, Wei Zhang, Shanghang National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China AI2Robotics China The Chinese University of Hong Kong Hong Kong Hong Kong University of Science and Technology Hong Kong

Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existing methods mainly focus on model-based adaptation, which aims to leverage a self-training manner to extract the target domain knowledge. However, pseudo labels can be noisy and the updated model parameters are unreliable under dynamic data distributions, leading to error accumulation and catastrophic forgetting in the continual adaptation process. To tackle these challenges and maintain the model plasticity, we design a Visual Domain Adapter (ViDA) for CTTA, explicitly handling both domain-specific and domain-shared knowledge. Specifically, we first comprehensively explore the different domain representations of the adapters with trainable high-rank or low-rank embedding spaces. Then we inject ViDAs into the pre-trained model, which leverages high-rank and low-rank features to adapt the current domain distribution and maintain the continual domain-shared knowledge, respectively. To exploit the low-rank and high-rank ViDAs more effectively, we further propose a Homeostatic Knowledge Allotment (HKA) strategy, which adaptively combines different knowledge from each ViDA. Extensive experiments conducted on four widely used benchmarks demonstrate that our proposed method achieves state-of-the-art performance in both classification and segmentation CTTA tasks. Note that, our method can be regarded as a novel transfer paradigm for large-scale models, delivering promising results in adaptation to continually changing distributions. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Semantic Traffic Element Removal by Learning to Follow Linguistic Instructions

Semantic Traffic Element Removal by Learning to Follow Lingu...

引用

2023 IEEE International Conference on Unmanned Systems, ICUS 2023

作者： Feng, Xiaodan Su, Yuanqi Liu, Yuehu Zhang, Chi School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Shaanxi Xi'an China

ISBN: (纸本)9798350316308

We propose a novel task of semantic object removal in traffic scenes through human-guided image editing. Unlike traditional methods, our model does not require image masks;instead, it effectively removes semantic elements from a traffic scene image based solely on an input image and linguistic instruction. To achieve this objective, we use large-scale pre-trained models to construct a traffic scene image dataset suitable for human-guided image editing. We train a text-guided image translation model on this dataset. During inference, our model quickly generalizes to photorealistic traffic scene images and user-written instructions, obviating the need for fine-tuning and enabling rapid removal of semantic object elements from images within seconds. Experimental results demonstrate that our model achieves satisfying removal performance in the traffic scene semantic object removal task, showing the potential advantages of text guidance in image processing tasks. © 2023 IEEE.

关键词： Semantics

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：