检索结果-内蒙古大学图书馆

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

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

A Novel Music Recommendation System Using Filtering Techniques

Informatica (Slovenia)

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

Moth flame optimization algorithm for efficient feature selection and hybrid classification technique for intrusion detection system

引用

Multimedia Tools and Applications 2025年 1-21页

作者： Keerthanarani, U. Selvakumar, V. Singaravelan, S. Raja, S. Edwin Thenmozhi, K. Shunmugam, D. Arun Dept. of Computer Science and Engineering P.S.R Engineering College Sivakasi India Dept.Of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & d Institute of Science and Technology Chennai Avadi India Dept. Of Computer Science and Engineering Coimbatore Institute of Engineering and Technology Coimbatore India Dept. Of Electronics and Communication Engineering P.S.R Engineering College Sivakasi India

The rapid expansion of the Internet of Things (IoT) brings numerous benefits but further presents fresh difficulties, especially in terms of security. The distributed and interconnected nature of IoT devices makes them susceptible to various security threats. An Intrusion Detection System (IDS) plays a crucial role in safeguarding IoT networks by monitoring, detecting, and responding to potential security incidents. The Internet of Things (IoT) connects billions of devices, sensors, and systems, transforming industries and everyday life. However, this extensive interconnectivity also introduces significant security risks, making Intrusion Detection Systems (IDS) a critical component for safeguarding IoT environments. Feature selection is a crucial aspect of building effective Intrusion Detection Systems (IDS). Selecting relevant features not only helps in achieving better classification accuracy but also contributes to reducing false alarm rates. In the proposed system a moth flame optimizer is utilized to select the efficient features from the dataset, overall accuracy of over 97%. Further it is classified employing Random Forest and J48 classifier which attains high classification accuracy and low false alarm rate. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Short-term renewable energy uncertainties and inertia consideration in power system generation expansion planning

引用

Energy Reports 2025年 13卷 5978-5992页

作者： Ayamolowo, Oladimeji Joseph Kusakana, K. Dept. of Electrical Electronic and Computer Engineering Central University of Technology Free State South Africa

In modern power systems, renewable energy (RE) sources are increasingly integrated to reduce reliance on fossil-fuel-based generation. However, the uncertainties and lack of rotational inertia associated with renewable energy generators (REGs) pose challenges to grid stability. This paper proposes a novel mixed-integer linear programming (MILP) model that optimizes energy costs while enhancing system inertia in the presence of RE uncertainties. The model incorporates both REG uncertainties and inertia requirements into the planning process. To validate its effectiveness, RE uncertainty data from Mangaung Municipality, Free State Province, South Africa, is used for analysis, and the model is tested on the IEEE 6-bus test system. Simulation results demonstrate that the proposed approach improves system inertia from 5.875 s to 6.304 s while reducing energy costs from $1752.88/MWh to $1614.50/MWh in Case 3, where both RE uncertainties and system inertia are considered. These results show a clear advantage over Case 1 (cost minimization only) and Case 2 (inertia maximization only), highlighting the model's ability to balance economic and stability objectives in renewable-integrated power grids. © 2025 The Authors

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

A Novel Identity Authentication Mechanism forUnmanned Maritime Vessels Communication Based on MITRE ATT&CK Framework

引用

Journal of Marine Science and technology (Taiwan) 2024年第2期32卷 170-180页

作者： He, Jun-Xian Chang, Shih-Hao Dept. of Computer Science and Information Engineering Tamkang University New Taipei City Taiwan Dept. of Computer Science and Information Engineering National Taipei University of Technology Taipei City Taiwan

With the development of the smart shipping industry, unmanned vessel technology is rapidly evolving, accompanied by a demand for robust Internet of Things (IoT) communication security practices. Key communication technologies for the operation of unmanned vessels include external vessel communication. One crucial aspect is the verification of the identities of the parties involved in these communication systems, as this ensures secure and trusted interactions between unmanned vessels and port management authorities. Identity authentication plays a vital role in ensuring the secure communication of unmanned vessels. This paper aims to analyze potential risks related to identity authentication technology in unmanned vessel communication systems. To effectively address these risks, we propose leveraging digital certificates and blockchain technology to achieve device non-repudiation and substitution. Based on this technology, we organize and implement defense strategies using the MITRE ATT&CK framework. This framework provides a comprehensive and systematic approach to understanding potential threats and designing appropriate defense measures. By utilizing this framework, security teams can better comprehend vulnerabilities and formulate effective countermeasures. To validate the effectiveness of the proposed defense framework, we conducted simulation experiments. These experiments helped us evaluate the efficiency and reliability of the strategies in real-world scenarios. Through these experiments, we could ascertain whether the countermeasures effectively mitigated the identified risks and ensured the secure communication of unmanned vessels. © 2024 National Taiwan Ocean University

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Optimizing relay node placement and routing in WBANs using free search krill herd and harmony search algorithm

引用

Multimedia Tools and Applications 2025年第10期84卷 7257-7295页

作者： Patra, Sushree Chinmayee Samal, Tusharkanta Kabat, Manas Ranjan Mishra, Manas Ranjan Barik, Ram Chandra Dept. of Computer Sc. & Engineering Veer Surendra Sai University of Technology Odisha Sambalpur India Dept. of Computer Sc. & Engineering DRIEMS University Odisha Cuttack India Dept. of Computer Sc. & Engineering C.V. Raman Global University Odisha Bhubaneswar India

Wireless Body Area Network (WBAN) plays an important role in healthcare applications like in medical, non-medical and psychological sector for remote monitoring of health conditions of patients. Since the biosensors in WBAN are energy constrained in nature, the architecture of energy efficient and cost sensitive WBAN has attracted the researchers during the last decade. In this paper, a mathematical model for optimization of relay node placement in WBAN using Free Search Krill Herd (FSKH) algorithm because of its diversified phases of searching has been proposed. Furthermore, a routing protocol for energy efficient and reliable for data transmission over WBAN by using Harmony Search (HS) algorithm has been designed. The proposed algorithm has less 11.02%, 6.8% energy consumption in standing position, 5.6% and 11.02% in siting position and 12.5% and 18.75% siting on chair than its counterparts EAWD and Modified EAWD. Throughput has increased significantly by approximately 4–5 times as compare to iM-SIMPLE and *** proposed methodology has also shown greater improvement as its first node is completely exhausted after 28,545 rounds of data transmission while its existing counterpart’s iM-SIMPLE and Co-LAEEBA first node dies at 5100 rounds and 6800 rounds of transmission respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Light-Weight Gated Recurrent Unit for Electroencephalogram Emotion Classification 13

Light-Weight Gated Recurrent Unit for Electroencephalogram E...

引用

13th International Electrical engineering Congress, iEECON 2025

作者： Sitjongsataporn, Suchada Du, Wenzhang Sakarin, Pipat Faculty of Engineering and Technology Dept. of Electronic Engineering Bangkok Thailand Faculty of Engineering and Technology Mahanakorn University of Technology Dept. of Computer Engineering Thailand

ISBN: (纸本)9798331543952

This experiment investigates the impact of reducing GRU units and dense layer neurons in a lightweight GRU architecture (LW-GRU-RU) compared to a baseline GRU model for electroencephalogram (EEG) emotion classification. A baseline GRU model is used as a reference, with an optimized GRU variant utilizing feature selection through a Random Forest-based algorithm. Experiments are conducted on a labeled emotion dataset, comparing accuracy and training efficiency across five trials. Results highlight the trade-off between model complexity, accuracy, and computational efficiency, providing insights for practical applications. Both models are evaluated on an emotion dataset for accuracy and training efficiency. The lightweight model achieves a competitive accuracy of 97.486% while reducing the average training time to 0.19 seconds per epoch, showcasing its potential for efficient real-world applications. © 2025 IEEE.

关键词： Baseline GRU model Electroencephalogram (EEG) signal GRU with Feature selection

来源：评论

学校读者我要写书评

暂无评论

Application of VGIS Digital Twin Platform for Enhanced Oilfield Disaster Management and Environmental Protection

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第14期48卷 27-42页

作者： Alabbasi, Awab Aljabery, Maalim A. Bölük, Pınar Sarısaray Faculty of Engineering and Natural Sciences Electrical and Computer Engineering Dept. Bahcesehir University Istanbul34353 Turkey Faculty of Computer Science and Information Technology Computer Science Dept. University of Basrah Basrah61004 Iraq Faculty of Engineering and Natural Sciences Software Engineering Dept. Bahçeşehir University Istanbul34353 Turkey

VGIS (Virtual Geographic Information System) Platform is a unified oilfield operations management platform based on MaaS (Management as a Service) that integrates advanced technologies such as AIoT (Artificial Intelligence & Internet of Things), GIS (Geographic Information System), Digital Twin, and AR (Augmented Reality)/ VR (Virtual Reality). The VGIS platform connects, collects, integrates, analyses, and acts on disparate data sources to provide the oilfield with a centralized view to help make informed decisions fast, bring operational visibility across all assets to improve safety and operational efficiency, reduce costs and improve margins, provide comprehensive analytics and decision support, increase business agility, and reduce management complexity. This is a case study of the application of the VGIS platform Majnoon oilfield, Basrah, Iraq. VGIS digital transformation, production process, and KPIs (Key performance indicators) are highly managed taking oilfield management to a higher level globally, in this study, the objective is to address and resolve the issue of high costs associated with using cloud services by utilising a local Data Center (a large group of networked computer servers typically used by organizations for the remote storage, processing, or distribution of large amounts of data). This approach involves directly uploading 3D maps to ensure faster service on the intranet, eliminating the need to pay for cloud *** aims providing a platform for researching and implementing monitoring and controlling processes in a more convenient and remote manner. The vGIS platform has emerged as a crucial instrument in the realm of disaster response and crisis management. This technology enables responders to rapidly evaluate, analyse, and respond to crucial information in real-time. This research examined the application of vGIS technology in disaster response and analyse the potential advantages and obstacles associated with its utilisation. © 2

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Knee Osteoarthritis detection and classification using a customized CenterNet with DenseNet201 3

Knee Osteoarthritis detection and classification using a cus...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Shirisha, N. Shilpa, K. Meghana, C.H. Rahman, Mohammed Abdul MLR Institute of Technology Dept. of Computer Science and Engineering Hyderabad India MLR Institute of Technology Dept. of Computer Science and Engineering Nalgonda India

ISBN: (纸本)9798331523893

Knee osteoarthritis (KOA) is a prevalent joint disorder diagnosed using imaging modalities like MRI, CT scans, and X-rays, with X-rays being the most cost-effective. Early detection is crucial for effective management. This study presents an automated deep learning approach to detect and classify KOA severity based on the Kellgren-Lawrence (KL) grading system using single posteroanterior standing knee X-ray images. Utilizing the Osteoarthritis Initiative dataset, we employed transfer learning to fine-tune DenseNet-201, enhancing model performance. Additionally, knowledge distillation was applied to reduce computational complexity while maintaining accuracy. Our model achieved over 95% accuracy on both testing and cross-validation datasets, outperforming existing methods. This approach offers a reliable tool for early KOA diagnosis and grading, potentially aiding clinical decision-making © 2025 IEEE.

关键词： Diagnostic radiography

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：