检索结果-内蒙古大学图书馆

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Kulba, Vladimir Medennikov, Viktor V.A. Trapeznikov Institute of Control Sciences of the Russian Academy of Sciences Laboratory of Modular Data Processing and Control Systems Moscow Russia Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences Information and Computing Systems Department Moscow Russia

ISBN: (纸本)9798350337907

The paper considers a mathematical model for managing a scientific digital ecosystem exemplified by the agriculture case;the model enables assessing the impact science exerts on the regions' socioeconomic position in order to build an adequate response to the advanced economies' regime of severe sanctions against Russia. For these purposes, a systemic analysis of the subject identification and classification of ecosystems was conducted to address the critical issue of determining the basic concepts and terms of the country's digitalization. © 2023 IEEE.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Learning discretized neural networks under Ricci flow

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 18901-18944页

作者： Jun Chen Hanwen Chen Mengmeng Wang Guang Dai Ivor W. Tsang Yong Liu Institute of Cyber-Systems and Control Zhejiang University China and School of Computer Science and Technology Zhejiang Normal University China Institute of Cyber-Systems and Control Zhejiang University China SGIT AI Lab State Grid Corporation of China China Centre for Frontier Artificial Intelligence Research Agency for Science Technology and Research (A*STAR) Singapore and Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore and College of Computing and Data Science Nanyang Technological University Singapore

In this paper, we study Discretized Neural Networks (DNNs) composed of low-precision weights and activations, which suffer from either infinite or zero gradients due to the nondifferentiable discrete function during training. Most training-based DNNs in such scenarios employ the standard Straight-Through Estimator (STE) to approximate the gradient w.r.t. discrete values. However, the use of STE introduces the problem of gradient mismatch, arising from perturbations in the approximated gradient. To address this problem, this paper reveals that this mismatch can be interpreted as a metric perturbation in a Riemannian manifold, viewed through the lens of duality theory. Building on information geometry, we construct the Linearly Nearly Euclidean (LNE) manifold for DNNs, providing a background for addressing perturbations. By introducing a partial differential equation on metrics, i.e., the Ricci flow, we establish the dynamical stability and convergence of the LNE metric with the L2-norm perturbation. In contrast to previous perturbation theories with convergence rates in fractional powers, the metric perturbation under the Ricci ow exhibits exponential decay in the LNE manifold. Experimental results across various datasets demonstrate that our method achieves superior and more stable performance for DNNs compared to other representative training-based methods.

关键词： discretized neural networks gradient perturbation information geometry ricci flow riemannian manifold

来源：评论

学校读者我要写书评

暂无评论

Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks

引用

IEEE Transactions on Mobile computing 2025年

作者： Du, Baoxia Du, Hongyang Niyato, Dusit Li, Ruidong Kanazawa University Institute of Science and Engineering Kanazawa920-1192 Japan University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong Nanyang Technological University College of Computing and Data Science Singapore

Task-oriented semantic communication has emerged as a fundamental approach for enhancing performance in various communication scenarios. While recent advances in Generative Artificial Intelligence (GenAI), such as Large Language Models (LLMs), have been applied to semantic communication designs, the potential of Large Multimodal Models (LMMs) remains largely unexplored. In this paper, we investigate an LMM-based vehicle AI assistant using a Large Language and Vision Assistant (LLaVA) and propose a task-oriented semantic communication framework to facilitate efficient interaction between users and cloud servers. To reduce computational demands and shorten response time, we optimize LLaVA's image slicing to selectively focus on areas of utmost interest to users. Additionally, we assess the importance of image patches by combining objective and subjective user attention, adjusting energy usage for transmitting semantic information. This strategy optimizes resource utilization, ensuring precise transmission of critical information. We construct a Visual Question Answering (VQA) dataset for traffic scenarios to evaluate effectiveness. Experimental results show that our semantic communication framework significantly increases accuracy in answering questions under the same channel conditions, performing particularly well in environments with poor Signal-to-Noise Ratios (SNR). Accuracy can be improved by 13.4% at an SNR of 12dB and 33.1% at 10dB, respectively. © 2002-2012 IEEE.

关键词： large multimodal models (LMMs) resource allocation Semantic communication user attention

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Evaluation of the data as Partner (DAP) Framework

A Conceptual Evaluation of the Data as Partner (DAP) Framewo...

引用

IEEE International Smart Cities Conference (ISC2)

作者： Sonia Hassan Drishty Sobnath Esther Snell Olufemi Isiaq Department of Science and Engineering Solent University Southampton England Department of Computer and Data Science and AI Creative Computing Institute Universiy of Arts London

This paper explores the innovative data As Partner (DAP) philosophy as a transformative approach to organisational data strategy, drawing upon established concepts of information value, technology acceptance, and inclusivity for people with disabilities (PwD) in smart cities. The study conducted a comprehensive systematic review, after meticulous screening, 20 eligible papers were selected, forming the foundation for deriving the key components of the DAP framework. Subsequently, a qualitative focus group study engaged 18 participants from diverse sectors to evaluate the practical applicability of the DAP conceptual framework. Thematic analysis of the focus group sessions revealed five key themes: practical value, pragmatic performance, ethical perspective, clarity of the framework, and enhancement tools. These findings offer valuable insights for refining the DAP framework and optimising its integration into real-world scenarios, in empowering individuals in smart cities, especially those with disabilities. Future research should explore larger and more diverse samples to generalise findings and assess the framework's long-term impact through longitudinal evaluations. By adopting user-centred methodologies, the DAP framework can be further enhanced as a strategic tool, empowering data to actively participate in organisational decision-making processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning in Cognitive Robots for Autonomous Path Planning

Reinforcement Learning in Cognitive Robots for Autonomous Pa...

引用

data Intelligence and Cognitive Informatics (ICDICI), International Conference on

作者： Archana Das R. Indu Poornima G. Gokila Deepa K. Selva Sheela Akshya J Mani Deepak Choudhry Department of Information Science and Engineering New Horizon College of Engineering Bengaluru Department of Information Technology KGiSL Institute of Technology Coimbatore Department of Artificial Intelligence and Data Science PPG Institute of Technology Coimbatore Department of Artificial Intelligence and Data Science KGiSL Institute of Technology Coimbatore Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

Cognitive robots are intelligent systems that learn from their environment, adapt to dynamic changes, and make decisions without a human's direct intervention. This research studies the integration of Reinforcement Learning in cognitive robots with Q-Learning for autonomous path planning. The study addresses the most critical issues in traditional A* and Dynamic Programming algorithms by devising path-planning techniques, mainly the lack of adaptability and computational efficiency in real-time and unpredictable environments. Our approach is based on Q-Learning, which is a model-free RL algorithm allowing the robots to find paths autonomously by optimizing their paths and avoiding obstacles. The Q-Learning algorithm provides the possibility of learning optimal policies for the robot through iterative interaction with its environment balanced between exploration and exploitation of the decision process. A reward system is utilized by the proposed model, encouraging the robot to explore shorter, collision-free paths and adjust based on feedback in real time from its surroundings. The model was found to be significantly better than its counterparts. In this context, as indicated, the Q-Learning model runs at 11.5 seconds, faster than A* at 18.3 seconds and Dynamic Programming at 16.7 seconds, yet with an accuracy of 94% and was found to have the highest collision avoidance rate at 98%. Additionally, the adaptability of the model about the environment presents a marked difference in terms of path length optimization, having done so with a mean path length of 12.3, compared to approaches or models. The robustness and scalability of the Q-Learning model make it highly applicable in real-world applications.

关键词： Adaptation models Q-learning Accuracy Navigation Heuristic algorithms Real-time systems Dynamic programming Cognitive robotics Collision avoidance Robots

来源：评论

学校读者我要写书评

暂无评论

EmoSync: Facial Emotion Detection for Adaptive Music Playback

EmoSync: Facial Emotion Detection for Adaptive Music Playbac...

引用

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

作者： Devikanniga Devarajan K Rajkumar Computer Science and Engineering GITAM Deemed to be University Nagadenahalli Doddabalpur Bangalore Karnataka Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

This work investigates using Convolutional Neural Networks (CNN) and VGGNet architecture, for realtime emotion detection. Raw data from the FER-2013 dataset is transformed from CSV format into organized image directories, segmented by distinct emotions. The resulting model, equipped with convolutional, pooling, and dense layers, effectively classifies emotions from 48x48 grayscale images. In application, the model overlays detected emotions onto a webcam stream. An integrated music player module synchronizes music with the subject’s emotions. Overall, this research explores a comprehensive interactive system focused on recognizing and responding to human emotions. Without further training data, our model, to the best of our understanding, achieves modern single-network accuracy of 74.57% on FER2013

关键词： Emotion recognition Image segmentation Webcams Interactive systems Training data Streaming media Gray-scale

来源：评论

学校读者我要写书评

暂无评论

Resfusion: denoising diffusion probabilistic models for image restoration based on prior residual noise 24

Resfusion: denoising diffusion probabilistic models for imag...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhenning Shi Haoshuai Zheng Chen Xu Changsheng Dong Bin Pan Xueshuo Xie Along He Tao Li Huazhu Fu College of Computer Science Nankai University School of Statistics and Data Science Nankai University Haihe Lab of ITAI College of Computer Science Nankai University and Haihe Lab of ITAI Institute of High Performance Computing A*STAR

ISBN: (纸本)9798331314385

Recently, research on denoising diffusion models has expanded its application to the field of image restoration. Traditional diffusion-based image restoration methods utilize degraded images as conditional input to effectively guide the reverse generation process, without modifying the original denoising diffusion process. However, since the degraded images already include low-frequency information, starting from Gaussian white noise will result in increased sampling steps. We propose Resfusion, a general framework that incorporates the residual term into the diffusion forward process, starting the reverse process directly from the noisy degraded images. The form of our inference process is consistent with the DDPM. We introduced a weighted residual noise, named resnoise, as the prediction target and explicitly provide the quantitative relationship between the residual term and the noise term in resnoise. By leveraging a smooth equivalence transformation, Resfusion determine the optimal acceleration step and maintains the integrity of existing noise schedules, unifying the training and inference processes. The experimental results demonstrate that Resfusion exhibits competitive performance on ISTD dataset, LOL dataset and Raindrop dataset with only five sampling steps. Furthermore, Resfusion can be easily applied to image generation and emerges with strong versatility. Our code and model are available at https://***/nkicsl/Resfusion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unveiling Hidden Water Resources: Deep Learning and Remote Sensing for Subsurface Hydrology for Environmental Health

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 352-364页

作者： Babu, Jampani Satish G, Dinesh Suganya, R. Radhakrishnan, P. Sutar, Anand S, Alex David Rao, L. Malleswara Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur AP Vaddeswaram India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur (KTR) Chennai India Department of Computer Science and Engineering (Data Science) New Horizon College of Engineering Karnataka Bengaluru India Department of ECE Tagore Engineering College Chennai India Department of Electronics and Telecommunication Bharati Vidyapeeth College of Engineering Navi Mumbai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & d Institute of Science and Technology Chennai India Department of Physics Sri Y N College (A) West Godavari District Andhra Pradesh Narsapur India

Water scarcity in arid regions necessitates innovative solutions to uncover and manage subsurface water resources for environmental health. This study explores the potential of GeoHydroNet, a specialized deep learning framework, in identifying hidden water resources within arid regions. Utilizing remote sensing data such as multispectral and hyperspectral imagery, geological maps, and soil moisture datasets, GeoHydroNet combines graph neural Networks (GNNs), AutoEncoders, and generative adversarial networks (GANs) to address challenges in subsurface hydrology. The model achieved an accuracy of 93.5%, surpassing traditional models like CNNs (85.4%), LSTMs (88.1%), and RNNs (82.6%). GeoHydroNet demonstrates significant precision (0.88), recall (0.87), and sensitivity to data imbalance (0.91). Its physics-informed learning approach incorporates hydrological principles, ensuring realistic predictions. By analyzing subsurface water patterns, recharge zones, and geological influences, the model not only enhances prediction accuracy but also aids in sustainable groundwater management. GeoHydroNet’s performance in identifying groundwater levels, with minimal errors ranging from 0.62 to 3.07%, indicates its robustness in tackling water scarcity challenges in data-constrained environments. These findings highlight its transformative role in hydrological modeling and sustainable water resource management in arid regions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Aquifers Arid regions Deep learning Generative adversarial networks GeoHydroNet Physics-informed learning Remote sensing Subsurface hydrology Sustainable water management

来源：评论

学校读者我要写书评

暂无评论

Predicting the Impact of Road Conditions on Battery Health Via Transfer Learning

Predicting the Impact of Road Conditions on Battery Health V...

引用

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： Rahul Anil Nair Dev Karan Suresh Rajeswari D Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu India

Battery life of EV (electric vehicles) depends on various factors. These factors include temperature of the battery, duration of use or the type and condition of the road traversed by the vehicle. This may cause the battery to discharge faster than it used to. Understanding what may cause the battery life to shorten can help us alleviate the given problem and can preserve the battery for longer time. This research focuses on the effects road conditions have on battery life to be able to recommend the favourable conditions to extend it. It proposes to find the routes taken by the vehicles and classifying them based on their battery health upon reaching the destination. In this paper, an attempt has been made to predict the category of the routes by employing Transfer learning via a pre-trained model VGG-16. Observations indicate that paths which have more turns and curves are generally worse for battery life as compared to straight and narrow paths. Another model which is an artificial neural network has been developed to predict the based on the average vehicle speed and the distance covered by the vehicle. The VGG-16 model predicts the data with which it is validated with an accuracy of 84.29% and the testing data with an accuracy of 83.56%. The artificial neural network model predicts the category of the data with an accuracy of 88.02%.

关键词： Geometry Temperature Roads Transfer learning Artificial neural networks Learning (artificial intelligence) Predictive models

来源：评论

学校读者我要写书评

暂无评论

Indoor Navigation Using Ultra Wide Band

Indoor Navigation Using Ultra Wide Band

引用

Intelligent computing and Control for Engineering and Business Systems (ICCEBS)

作者： Divya B T Veeramakali S Revathi Harisharajan R R Adhirooban D Ebishdon G V Dept of Computer Science and Engineering Sri Sai Ram Institute of Technology Dept of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Tamilnadu India

Indoor positioning is a significant and intriguing topic in navigation systems that present numerous use cases for investigation. Researchers are exploring technologies capable of providing accurate locations in indoor spaces where GNSS positioning systems are ineffective. In the numerous solutions available for indoor location services, Ultra-wideband (UWB) technology was chosen for its ability to provide high-precision positioning information for multiple points in real-time. This paper presents a UWB indoor positioning system that utilizes time of flight (TOF) algorithm. At times, time difference of arrival (TDOA) algorithms compute range measurements, this facilitates the trans-receiver (TAG) plane position algorithm's location determination. UWB technology was chosen because it is the latest technology available on Android 12 and further also offers high accuracy, resistance to interference and minimal signal reflection from walls. UltraWide Band(UWB) localization encounters various obstacles, such as multipath distortions, additional signal delays, time discrepancies in clocks, signal interference, and the computational resources necessary to determine the user's location.

关键词：

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：