检索结果-内蒙古大学图书馆

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Pandey, Anoop Kumar Tamma, Bheemarjuna Reddy Rao, M.V. Panduranga IIT Hyderabad Dept. of Computer Science and Engineering India

ISBN: (纸本)9798331531195

Deciding a route for the transfer of quantum information (namely, qubits) on a quantum network is a significant problem that is being studied extensively. In this work, we investigate the problem of routing on a quantum network of heterogeneous nodes both with and without fidelity and timing *** propose a Path Request Packet (PRP) based routing scheme for dynamically selecting a path that maximizes the overall probability of transmission success while maintaining fidelity above a threshold and adhering to time constraints. While the proposed scheme can perform suboptimally under fidelity and timing constraints, we discuss a straightforward proof of optimality in the absence of these constraints. Simulations on random graphs demonstrate that the PRP-based scheme performs better, both in terms of reliability and fidelity, than a non-trivial baseline routing algorithm. © 2025 IEEE.

关键词： Quantum electronics

来源：评论

学校读者我要写书评

暂无评论

MOPO-HBT: A movie poster dataset for title extraction and recognition

引用

Multimedia Tools and Applications 2024年第18期83卷 54545-54568页

作者： Ghosh, Mridul Roy, Sayan Saha Banik, Bivan Mukherjee, Himadri Obaidullah, Sk Md Roy, Kaushik Dept. of Computer Science Shyampur Siddheswari Mahavidyalaya Howrah India Dept. of Computer Science & Engineering Aliah University Kolkata India Dept. of Electronics & Electrical Communication Engineering IIT Kharagpur Kharagpur India TISA Lab Dept. of Computer Science West Bengal State University Barasat India

Real-world images often encompass embedded texts that adhere to disparate disciplines like business, education, and amusement, to name a few. Such images are graphically rich in terms of font attributes, color distribution, foreground-background similarity, and component organization. This aggravates the difficulty of recognizing texts from these images. Such characteristics are very prominent in the case of movie posters. One of the first pieces of information on movie posters is the title. Automatic recognition of movie titles from images can aid in efficient indexing as well as information conveyance. However, it is accompanied by other texts like the names of actors, producers, taglines, dates, etc. Though the organization of components is somewhat similar across different film industries like Tollywood (West Bengal), Bollywood (Mumbai), and Hollywood (Los Angeles), the graffiti patterns differ in multifarious instances. To address the problem of movie title understanding, we propose a dataset named MOvie POsters-Hollywood Bollywood Tollywood (MOPO-HBT) that encompasses movie posters from the aforementioned industries. The entire dataset is publicly available (http://***/11564) for research purposes. The baseline results of title identification and recognition were obtained with a CNN-based (Convolutional Neural Network) approach, wherein the titles were extracted using the M-EAST (Modified-Efficient and Accurate Scene Text) detector model. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Dynamic Real-Time Scheduling on Distributed Hierarchical Fog Networks 31

Dynamic Real-Time Scheduling on Distributed Hierarchical Fog...

引用

31st IEEE International Conference on High Performance Computing, Data, and Analytics Workshops, HiPCW 2024

作者： Sharma, Amit Auluck, Nitin Dept. of Computer Science & Engineering IIT Ropar India

ISBN: (纸本)9798331509118

We present a novel approach for efficient task scheduling on hierarchical fog nodes, catering to real-time (RT) and non-real-time (NRT) tasks with varying sizes and deadline constraints. Leveraging machine learning (ML) techniques, our proposed solution autonomously allocates tasks across fog nodes, dynamically adapting to changing workload patterns and system conditions. Our novel methodology integrates supervised learning algorithms to predict workload patterns and resource availability, enabling intelligent decision-making in task assignment. Our findings contribute to advancing the state-of-the-art in fog computing by offering a scalable and adaptive solution for dynamic task scheduling in hierarchical heterogeneous environments. © 2024 IEEE

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Domain-Specific ASR Performance Using Finetuning and Zero-Shot Prompting: A Study in the Medical Domain 6

Enhancing Domain-Specific ASR Performance Using Finetuning a...

引用

6th Doctoral Symposium on Intelligence Enabled Research, DoSIER 2024

作者： Maulik, Utsav Bandyopadhyay Mitra, Pabitra Sarkar, Sudeshna Dept. of Computer Science and Engineering IIT Kharagpur West Bengal India

Domain Adaptation has emerged as an important development in Speech Recognition systems for improving the transcription accuracy of the input audio. This study explores the enhancement of Domain-specific Automatic Speech Recognition performance through finetuning and postprocessing using Large Language Models, focusing specifically on the medical domain. We investigate how domain-specific finetuning and advanced text postprocessing techniques can significantly improve transcription accuracy in medical contexts, reducing errors in specialized terminology, acronyms, and abbreviations. Our findings highlight the benefits of integrating Large Language Model based postprocessing with Automatic Speech Recognition systems to achieve better results in complex domains. © 2025 Copyright for this paper by its authors.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A simplified hybrid model for state of charge estimation using 1-D Kalman filter and Coulomb counting 50

A simplified hybrid model for state of charge estimation usi...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Garg, Kritika Sarker, Rahul Ahmad, Aaqib Kaur, Mehakpreet Teja, A.V. Ravi Dept. of Electrical Engineering IIT Ropar Rupnagar India Dept. of Computer Science Engineering PU Patiala India

ISBN: (纸本)9781665464543

This document is a model with an accurate estimation of the battery’s State Of Charge (SOC), which is pivotal for prime performance and optimal lifespan of the rechargeable batteries. Though traditional methods, like Open Circuit Voltage (OCV) and Coulomb Counting (CC), are advantageous, they suffer from several limitations, such as sensitivity to temperature changes, frequent calibration, ageing effects, and measurement inaccuracies. This paper proposes 1-D Kalman Filter (1-D HKF) with an approach that incorporates the OCV and CC results into the state space model for better and more accurate SOC estimation. So, the model is called 1-D HKF or Hybrid Kalman filter that, influenced the long-term stability and estimation accuracy of CC and the accuracy of OCV at specific points to get over the individual limitations. The model trained by 1-D HKF adapts itself and adjusts the gain based on the uncertainties of each measured value to ensure optimal value information. So, We evaluate the performance of the 1-D HKF versus the traditional methods Kalman Filter using examples and exploratory data. The proposed approach illustrates significantly improved accuracy and robustness across various operating conditions, including varying temperatures and discharge rates. © 2024 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-ViT architecture to exploit spatio-temporal feature for fire recognition trained through transfer learning

引用

Multimedia Tools and Applications 2025年第8期84卷 4703-4732页

作者： Shahid, Mohammad Wang, Hong-Cyuan Chen, Yung-Yao Hua, Kai-Lung Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Dept. of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

Fires are becoming one of the major natural hazards that threaten the ecology, economy, human life and even more worldwide. Therefore, early fire detection systems are crucial to prevent fires from spreading out of control and causing destruction. Based on vision sensors, many fire detection techniques have evolved with the recent surge of curiosity in deep learning, which exploits the spatial features of individual images. However, fire can take different forms, scales, and combustion materials can produce different colors, making accurate fire detection from an image challenging. Small fires captured from long-distance cameras lack salient features, further complicating detection. This paper proposes a hybrid structure that uses attention-enhanced convolutional neural networks and vision transformers (CNN-ViT) to detect fire. The proposed CNN-ViT first pays spatial attention to every frame and then aggregates temporal contextual information from neighboring frames to improve detection performance. Due to the limited availability of training fire datasets, the study employs deep transfer learning for feature extraction using pre-trained CNN. We used various metrics to examine the efficacy of the proposed approach. The results showed that the CNN-ViT method outperformed previous models based on spatial-temporal characteristics by achieving a relative improvement in accuracy and F1 score. The satisfactory results on images contaminated with different intensities of noise confirm the robustness of the approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Efficient Spectral Attention Block for Cascaded Hyperspectral Image Super-Resolution Architectures 14

Efficient Spectral Attention Block for Cascaded Hyperspectra...

引用

14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2024

作者： Patibandla, Tarun Pv, Arun Porwal, Alok IIIT Sri City Computer Science Dept. India IIT Bombay Computer Science Dept. India

ISBN: (纸本)9798331513139

Hyperspectral image (HSI) super-resolution has seen significant advancements with the emergence of diffusion models, demonstrating impressive results in prior works. However, existing approaches often take up cascaded architectures for feature extraction, often suffering from high computational costs, gradient instability, and training difficulties. This paper introduces a novel Efficient Spectral Attention Block (ESAB) that addresses these challenges by leveraging atrous convolutional blocks and channel attention within a multiscale feature extraction strategy. ESAB enables effective spectral feature extraction while maintaining computational efficiency, leading to improved performance. Furthermore, a unique loss function is proposed to enhance spectral fidelity by comparing the spectral slopes of the ground truth and predicted image pixels. Experimental results demonstrate that the proposed approach achieves great performance in super-resolving HSIs, achieving high spectral fidelity with reduced model complexity. © 2024 IEEE.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Fast Anomaly Detection For Multivariate Industrial Time Series Data 14

Fast Anomaly Detection For Multivariate Industrial Time Seri...

引用

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

作者： Kumar, Suraj Gupta, Gagan Raj Parihar, Roodra Pratap Singh Iit Bhilai Computer Science and Engineering Dept. Raipur India Iit Bhilai Mechatronics Engineering Dept. Raipur India

ISBN: (纸本)9798350335095

Anomaly detection is used to identify/predict atypical patterns or outliers within datasets. It proves highly beneficial in numerous applications like industrial monitoring, healthcare and cybersecurity etc. With the advent of Industry 4.0, system automation is rapidly increasing, resulting in an exponential surge in data generation. In a factory setting, a sudden deviation in signal values can result in significant losses. Having a robust anomaly detection system in place becomes crucial to promptly identify and flag anomalies, thereby minimizing potential losses. In this paper, the proposal entails a down-sampling technique that offers advantages in terms of mitigating noise, reducing storage requirements, and diminishing computational demands by 88% for a representative dataset. Additionally, an anomaly interval detection algorithm designed to label data is introduced by us, thereby facilitating its application in supervised anomaly detection methods and predictive anomaly detection. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Novel Music Recommendation System Using Filtering Techniques

引用

Informatica (Slovenia) 2024年第4期48卷 595-610页

作者： Vashishtha, Srishti Varshney, Deepika Sarin, Eva Kaur, Simran Computer Science and Engineering Dept. Bharati Vidyapeeth’s College of Engineering GGSIPU New Delhi India Computer Science and Engineering Dept. Jaypee Institute of Information Technology Noida India

With the growth of the World Wide Web, a large amount of music data is available on the Internet. A large number of people listen to music online rather than downloading and listening offline. But only some sites provide personalized and accurately recommended songs while they listen to an auto-playing playlist. Hence the need for recommendation systems arises. Two approaches can be applied to the recommendation system: content based filtering and collaborative filtering. While in content-based filtering approach, analysis on the songs’ content which has been preferred by the user in history is done and the songs with relative similarity are recommended. While latter suggests songs that certain users of similar listening pattern have preferred. But collaborative filtering-based recommendation systems not only requires time to attain stability but also might recommend unsuitable music because it is not personalized to each user’s preference. Also, the latter requires the songs to be listened by a few users already to recommend it any other user. Hence for overall analysis, answers to few questions need to be implemented in recommendation systems: the very first one is how the properties should be analyzed, next one is how the analysis should be done and last is how the songs related to the user’s preference should be chosen. So, for suggesting the better system which solves these three questions as well as provides better and personalized recommendations, In this paper we build a collaborative filtering as well as content based filtering recommendation system, where various factors determine the essence of the songs, i.e. liveliness, keys used, loudness, pitch, valence, etc., are analyzed for comparison. From the experimental analysis in has been identified that content-based filtering technique performed best on KNN machine learning classifier with accuracy of 85%. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Time series forecasting using transformer neural network

引用

International Journal of computers and Applications 2024年第10期46卷 880-888页

作者： Bhogade, Vaibhav Nithya, B. Dept. of Computer Science and Engineering National Institute of Technology Tiruchirappalli India

Time series forecasting is a vital component of data science, giving essential insights that help decision-makers to predict future trends across a number of sectors. This paper focuses on projecting complicated stock market price dynamics, weather data variations, and hourly traffic occupancy rates. The Informer-Based Time Series Forecasting (IBTSF) model, which employs a transformer-based architecture to capture long-term relationships and give probabilistic predictions, is *** model is assessed against Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN) and Gated Recurrent Unit (GRU) model to benchmark its performance. Simulation findings demonstrate that the IBTSF model considerably outperforms other models across all datasets. For traffic data, the IBTSF model achieves a Mean Squared Error (MSE) of 10.1 and a Mean Absolute Scaled Error (MASE) of 1.69, compared to other model's larger mistakes. In stock data forecasting, the IBTSF model reports an MSE of 8.04 and a MASE of 1.53, again outperforming other models. Similarly, using meteorological data, the IBTSF model obtains an MSE of 86.12 and a MASE of 0.7, whereas other models fall short. These results underline the IBTSF model's resilience and accuracy in capturing subtle patterns and relationships within time series data, giving precise insights that benefit decision-making processes. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Prediction models

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：