检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Yingnan Zhu, Qingling Chen, Jianyong College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Multivariate time series (MTS) forecasting has been extensively applied across diverse domains, such as weather prediction and energy consumption. However, current studies still rely on the vanilla point-wise self-attention mechanism to capture cross-variable dependencies, which is inadequate in extracting the intricate cross-correlation implied between variables. To fill this gap, we propose Variable Correlation Transformer (VCformer), which utilizes Variable Correlation Attention (VCA) module to mine the correlations among variables. Specifically, based on the stochastic process theory, VCA calculates and integrates the cross-correlation scores corresponding to different lags between queries and keys, thereby enhancing its ability to uncover multivariate relationships. Additionally, inspired by Koopman dynamics theory, we also develop Koopman Temporal Detector (KTD) to better address the non-stationarity in time series. The two key components enable VCformer to extract both multivariate correlations and temporal dependencies. Our extensive experiments on eight real-world datasets demonstrate the effectiveness of VCformer, achieving top-tier performance compared to other state-of-the-art baseline models. Code is available at this repository: https://***/CSyyn/VCformer. Copyright © 2024, The Authors. All rights reserved.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Developing a Speech Recognition Service for Korean Speakers with Dysarthria 14th

Developing a Speech Recognition Service for Korean Speakers ...

引用

14th International Conference on Computer science and its Applications, CSA 2022 and the 16th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2022

作者： Choi, Go Woon Kim, Min Hyuk Park, Ha Young Choi, Young Hae Oh, Se Jong Doo, Ill Chul Department of Thai Studies Hankuk University of Foreign Studies Seoul Korea Republic of Department of English Linguistic and Language Technology Hankuk University of Foreign Studies Seoul Korea Republic of Department of Big Data Science Korea University Sejong Korea Republic of Linguistics and Cognitive Science Hankuk University of Foreign Studies Yongin Korea Republic of Artificial Intelligence Education Hankuk University of Foreign Studies Yongin Korea Republic of

ISBN: (纸本)9789819912513

The purpose of this study is to provide an API for converting the speech of people with dysarthria into a text form by constructing a model that learns the speech characteristics of Korean speakers with dysarthria. A speech recognition model was constructed by using the Korean speech recognition open-source toolkit (Kospeech) which embodies DeepSpeech2 model. Ten thousand voice files which recorded the speech of people with dysarthria and the corresponding transcription files were also collected. Both files were augmented and used for model training. By performing the WER/CER evaluation, it was confirmed that the model constructed in this study recognized the speech of the Korean speakers with dysarthria better than the existing speech recognition model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Measuring Teachers’ Visual Expertise Using the Gaze Relational Index Based on Real-world Eye-tracking data and Varying Velocity Thresholds

arXiv

引用

arXiv 2023年

作者： Kosel, Christian Mooseder, Angelina Seidel, Tina Pfeffer, Jürgen Educational Psychology School of Social Science and Technology Technical University Munich Germany Computational Social Science and Big Data School of Social Science and Technology Technical University Munich Germany

This article adds to the understanding of teachers’ visual expertise by measuring visual information processing in real-world classrooms (mobile eye-tracking) with the newly introduced Gaze Relational Index (GRI) metric, which is defined as the ratio of mean fixation duration to mean fixation number. In addition, the aim was to provide a methodological contribution to future research by showing to what extent the selected configurations (i.e. varying velocity thresholds and fixation merging) of the eye movement event detection algorithm for detecting fixations and saccades influence the results of eye-tracking studies. Our study leads to two important take-home messages: First, by following a novice-expert paradigm (2 novice teachers & 2 experienced teachers), we found that the GRI can serve as a sensitive measure of visual expertise. As hypothesized, experienced teachers’ GRI was lower, suggesting that their more fine-graded organization of domain-specific knowledge allows them to fixate more rapidly and frequently in the classroom. Second, we found that the selected velocity threshold parameter alter and, in the worst case, bias the results of an eye-tracking study. Therefore, in the interest of further generalizability of the results within visual expertise research, we emphasize that it is highly important to report configurations that are relevant for the identification of eye movements. Copyright © 2023, The Authors. All rights reserved.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

CAUSAL CONTEXTUAL BANDITS WITH TARGETED INTERVENTIONS 10

CAUSAL CONTEXTUAL BANDITS WITH TARGETED INTERVENTIONS

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Subramanian, Chandrasekar Ravindran, Balaraman Robert Bosch Centre for Data Science and Artificial Intelligence Indian Institute of Technology Madras Chennai India Department of Computer Science and Engineering Indian Institute of Technology Madras Chennai India

We study a contextual bandit setting where the learning agent has the ability to perform interventions on targeted subsets of the population, apart from possessing qualitative causal side-information. This novel formalism captures intricacies in real-world scenarios such as software product experimentation where targeted experiments can be conducted. However, this fundamentally changes the set of options that the agent has, compared to standard contextual bandit settings, necessitating new techniques. This is also the first work that integrates causal side-information in a contextual bandit setting, where the agent aims to learn a policy that maps contexts to arms (as opposed to just identifying one best arm). We propose a new algorithm, which we show empirically performs better than baselines on experiments that use purely synthetic data and on real world-inspired experiments. We also prove a bound on regret that theoretically guards performance. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Deep Learning Model for Diabetic Retinopathy Identification 9

An Ensemble Deep Learning Model for Diabetic Retinopathy Ide...

引用

9th IEEE International Conference on Smart Structures and Systems, ICSSS 2023

作者： Hussain, Mohammad Manzoor Shanmugam, P. Moorthi, K. Sakthivelu, U. Rajasekar, A. Kumar, R. Naresh B v Raju Institute of Technology Department of Computer Science and Engineering Telangana Medak India Rajalakshmi Engineering College Department Computer Science and Engineering Chennai India Sairam Engineering College Department Electronics and Communication Engineering Chennai India Srm Institute of Science and Technology School of Computing Department of Networking and Communications Tamilnadu Kattankulathur India Sri Sairam Institute of Technology Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798350384208

Diabetic Retinopathy (DR) is an eye disease that can potentially cause significant injury in those diagnosed with diabetes. The condition arises due to issues with blood circulation to the retina, the delicate tissue in the posterior part of the eye. DR is recognized as the leading factor contributing to visual impairment among those affected by diabetes. However, timely identification and intervention might mitigate the occurrence of this condition. Conversely, the timely identification of DR poses challenges, while the diagnostic process can be laborious and time-intensive. The automated detection of DR necessitates categorizing colour retinal fundus pictures. This article presents a computer-aided diagnostic strategy that utilizes Deep Learning (DL) algorithms. In order to classify retinal fundus pictures, this study employed a combination of DL models, specifically ResNet50 and Inception V3. The studies are being conducted on the DIARETDB1 dataset. An analysis is conducted to compare the results of the suggested methodology. The comparison study results show that the proposed approach has more significant accuracy levels than the other methods. A high degree of accuracy, that is, 98.37%, has been attained by utilising the proposed techniques. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Citywide Flow Forecasting through Deep Learning and Spatial Temporal Learning 2

Enhancing Citywide Flow Forecasting through Deep Learning an...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Parvathi, R. Sarkar, Swagata Supraja, M. Swagatha, J.P. Kanagajothi, D. Srimathi, S. SRM Arts and Science College Computer Science Kattankulathur India Sri Sairam Engineering College Department of Artificial Intelligence and Data Science Chennai India Rajarajeshwari College of Engineering Electronics and Communication Engineering Bangalore India Panimalar Engineering College Department of IT Poonamallee India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Mathematics India SIMATS Technology Saveetha School of Engineering Department of Bio Chennai India

ISBN: (纸本)9798350317558

Safe traffic management requires citywide flow projections. Transportation, public safety, and municipal planning are substantially affected. It forecasts city intake and outflow using flow data. Traditional methods are inaccurate and less scalable in complex, dynamic metropolitan settings. This study uses deep learning to predict crow traffic. Deep learning can handle complicated nonlinear circumstances, making neural network crowd flow prediction more popular. However, deep learning has solved this problem, but it requires plenty of data. data shortages may develop when a city's service or infrastructure is installed. This research introduces a deep spatial temporal transfer learning system that predicts crowd movement in a data-sparse target city using data from a data-rich source city. Geographic and temporal patterns in crow traffic data may be captured by trained algorithms, enhancing prediction accuracy. We found that our deep learning-based solution is more accurate and robust than prior methods. Crow migration patterns are properly predicted by this research, improving urban planning and management. © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A new network intrusion detection system based on auto-encoding and variance analysis

A new network intrusion detection system based on auto-encod...

引用

IEEE International Conference on Civil Aviation Safety and Information technology (ICCASIT)

作者： Dequ Chen Ming Zhang Fujian Provincial Key Laboratory of Big Data Mining and Applications/School of Computer Science and Mathematics Fujian University of Technology Fuzhou China

In today's big data era, ensuring the network security of information technology (IT) communication facilities is one of the most challenging issues. In fact, with progress in technology, hackers have developed increasingly complex and risky network attacks, making malicious access identification a very tired task. Under various threats, the existing analysis methods encounter many challenges in detecting and mitigating these illegal accesses. This work presents a new network intrusion detection system (IDS) which combines deep learning method and mathematical strategy. Indeed, our IDS makes full use of data analysis, mathematical modeling, and deep learning to select and optimize features that are more relevant for classification. We use NSL-KDD dataset to test the performance of the IDS. The experimental results show that our proposed method has better performance compared with traditional deep learning, machine learning and recently proposed advanced methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Motion Planning in Automated Vehicles Based on Hierarchical MPC 1

Motion Planning in Automated Vehicles Based on Hierarchical ...

引用

1st International Conference on Advances in Computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Kapila, Pooja Kumar, Pankaj Negi, Rahul Bharti, Bhupender Kumar Punhani, Akash Bisht, Suraj Singh IIMT College of Engineering Department of Artifical Intelligence & Data Science India Amity University Department of Statistics Kolkata India Tula's Institute Department of ECE Dehradun248197 India Department of Mechanical Engineering VMSB UTU Campus Pithoragarh India KIET Group of Institutions Department of Computer Science Noida India Bipin Tripathi Kumaon Institute of Technology Department of ECE Dwarahat Almora India

ISBN: (纸本)9798331518578

In this study, a thorough hierarchical control structure that supports autonomous decision-making that arises in autonomous systems and robots is proposed. Distinct state and decision/control sets are frequently used to describe high-level decision making in a conventional hierarchical control architecture. To keep up with proficiency, wellbeing, and solace, robotized vehicles generally depend serious areas of strength for on powerful movement arranging calculations. The capacity of Model Prescient Control (MPC) to oversee imperatives and upgrade directions progressively has made it a strong system for movement arranging. To approve the proposed strategy, this exploration utilizes MATLAB recreations to look at various levelled MPC for movement arranging in robotized vehicles. With the low-level regulator guaranteeing exact direction observing and the undeniable level organizer computing a worldwide direction, a two-layer progressive MPC structure is fabricated. The discoveries show how well the progressive MPC handles street ebb and flow, dynamic hindrances, and continuous computational impediments. It is demonstrated that the suggested autonomous decision-making scheme's recursive practicality and stability are ensured by carefully crafting its essential components. An intelligent vehicle's autonomous lane-changing system is developed using the suggested framework. Simulation demonstrates that it has a potential capacity to manage a variety of behaviours in complex and dynamic contexts. It is anticipated that the suggested framework will be useful for autonomous decision-making in a variety of robotics along with autonomous technologies where safety as well as optimality are important factors. © 2025 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Content-Based Image Retrieval System Using Convolutional Neural Network Models 8th

Optimizing Content-Based Image Retrieval System Using Convol...

引用

8th International Conference on Information and Communication technology for Intelligent Systems, ICTIS 2024

作者： Kashid, Shraddha S. Takale, Dattatray G. Gawali, Piyush P. Deshmukh, Gopal B. Mahalle, Parikshit N. Sule, Bipin Deshpande, Arati V. Salve, Bhausaheb S. Department of Computer Engineering MIT ADT University Pune India Department of Computer Engineering Vishwakarma Institute of Information Technology SPPU Pune India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Information Technology SPPU Pune India and Humanities Vishwakarma Institute of Technology Pune India Computer Engineering Department Sandip University Mahiravani Trimbak Road Maharashtra Nashik India

ISBN: (纸本)9789819766741

This study focuses on improving "Content-Based Image Retrieval" (CBIR) systems through the utilization of optimized convolutional neural network (CNN) models. Traditionally, CBIR relied on text-based approaches, which proved inefficient in the digital era. In this research, we propose a novel visual content-based retrieval method, leveraging key image features like color, texture, and shape. To expedite the process, we employ pre-trained CNN models, such as the ResNet architecture, trained on extensive datasets like Image-Net. Our experiments, conducted on the "Paris 6K and Oxford 5K datasets, demonstrate the superior performance" of the ResNet model compared to the state-of-the-art AlexNet. This is attributed to ResNet’s ability to reduce training time without sacrificing accuracy. The evaluation, based on average mean precision, yielded promising results of 92.12% for Paris 6K and 84.81% for Oxford 5K, showcasing the efficacy of our approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Molecule-dynamic-based Aging Clock and Aging Roadmap Forecast with Sundial

arXiv

引用

arXiv 2025年

作者： Wu, Wei Deng, Zizhen Zhang, Chi Liao, Can Wang, Jinzhuo Department of Big Data and Biomedical AI College of Future Technology Peking University Beijing100871 China Institute of Bioinformatics University of Georgia AthensGA United States

Addressing the unavoidable bias inherent in supervised aging clocks, we introduce Sundial, a novel framework that models molecular dynamics through a diffusion field, capturing both the population-level aging process and the individual-level relative aging order. Sundial enables unbiased estimation of biological age and the forecast of aging roadmap. Faster-aging individuals from Sundial exhibit a higher disease risk compared to those identified from supervised aging clocks. This framework opens new avenues for exploring key topics, including age- and sex-specific aging dynamics and faster yet healthy aging paths. © 2025, CC BY.

关键词： Molecular dynamics

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：