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

J-NECORA: A Framework for Optimal Resource Allocation in Cloud-Edge-Things Continuum for Industrial Applications With Mobile Nodes

引用

IEEE Internet of Things Journal 2025年第11期12卷 16525-16542页

作者： Pettorali, Marco Righetti, Francesca Vallati, Carlo Das, Sajal K. Anastasi, Giuseppe Univ. of Pisa Dept. of Information Engineering Italy Missouri Univ. of Science and Technology Dept. of Computer Science RollaMO United States

In the Industrial Internet of Things (IIoT) landscape, where the Cloud-to-Things Continuum (C2TC) paradigm is now a reality, industrial applications need to cope with highly heterogeneous network and computing resources. Moreover, many industrial applications also involve Mobile Nodes (MNs). Efficient allocation of network and computing resources to meet the stringent requirements of such applications is often a very challenging task. In this paper, we propose J-NECORA (Joint NEtwork and COmputing Resource Allocation), a comprehensive analytical framework to derive the optimal joint allocation of network and computing resources in the C2TC, that guarantees the application requirements, even in the presence of MNs. If the optimal allocation does not exist, J-NECORA provides a best-effort allocation that minimizes the delay. The proposed framework is highly modular and flexible, and can be easily customized to different scenarios. We validated its effectiveness through simulation experiments, focusing on a specific use case. For the considered scenarios, the performance predicted by our framework matches quite closely the simulation results. © 2014 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Cognitive Training Systems Based on Extended Reality and BCI Technology 7

Design and Development of Cognitive Training Systems Based o...

引用

7th IEEE Eurasian Conference on Educational Innovation, ECEI 2024

作者： Lin, Pei-Jung Ku, Hsiu-Chien Lin, Li-Lun Feng Chia University Dept. of Information Engineering and Computer Science Taichung Taiwan Hungkuang University Dept. of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9798350307207

Dementia is considered a Mild Cognitive Impairment (MCI), representing a blurred transition from normal cognitive function to dementia. MCI might be a precursor to dementia being caused by various neurodegenerative diseases, including Alzheimer's disease, stroke, metabolic disorders, and mental health conditions. According to the World Health Organization (WHO), over 55 million people worldwide are suffering from dementia, with nearly 10 million new cases each year. This number is expected to rise to 78 million by 2030. Numerous studies have proposed various training methods targeting specific cognitive domains in dementia. For instance, reminiscence therapy encourages individuals to recall buried memories, while reality orientation therapy focuses on strengthening orientation cues to help patients with dementia establish a stronger sense of control. With aging, changes occur in cognitive and physical functions. Research suggests that memory functions can be improved through training. Therefore, the primary goal of this study was to develop an Extended Reality (XR) cognitive system to assist MCI patients in enhancing logical thinking, increasing independence in daily life, and improving response accuracy. The application of extended reality technology in the medical field is expanding, covering areas such as surgical assistance, medical consultation, disease treatment, and medical training. We integrated mixed reality devices with brain-computer interface (BCI) equipment. By detecting brainwave signals in the frontal region of the brain through sensors, neural activity was quantified, and digital brainwave data was transmitted to the system. This data was then visualized on screen in real-time to analyze changes in brainwave data during training. Through multifaceted task training, the system enhanced cognitive response and sensory perception, stimulating brain activity with the goal of strengthening cognitive functions. © 2024 IEEE.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-rule-decided small cell offloading for rate-adaptive SVC-DASH video streaming over the vehicle environment

引用

computer Communications 2023年 212卷 1-20页

作者： Huang, Chung-Ming Wang, Han-I Dept. of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan

This paper proposed an SVC-DASH video streaming method over the vehicular environment based on the Multi-access Edge Computing (MEC) architecture. For the streaming concern, a control scheme using the Segment-Set-based buffer-aware bitrate adaptation with the backward quality's increment control was proposed;for the mobility concern, a Small Cell Video Streaming Offloading (SC–VSO) control scheme adopting the multiple attribute fuzzy-based decision for deciding whether it can offload the video streaming traffic from a macro cell to a small cell or not was proposed. To have the suitable bitrate adaptation and stable quality variation, three factors that the proposed streaming control scheme considers are (i) estimated bandwidth, (ii) buffer occupancy and (iii) quality variation. Since the vehicle is moving across many types of Base Stations (BSs), the proposed mobility control scheme can decide whether to have SC-VSO or not before vehicle X entering into the ahead small cell's signal coverage based on (i) the network situations of the corresponding macro and small cell and (ii) the reported context from vehicle X using the proposed fuzzy logic mechanism. The performance evaluation results shown that the proposed method has the higher video quality and better quality stability for video streaming over the vehicle environment. © 2023 Elsevier B.V.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

An Integrated Framework with Enhanced Primitives for Post-Quantum Cryptography: HEDT and ECSIDH for Cloud Data Security and Key Exchange

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第11期49卷 165-176页

作者： Ilias, Shaik Mohammad Sharmila, V. Ceronmani Durga, V. Sathya Dept. of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India Department of Information Technology Hindustan Institute of Technology and Science Chennai India Department of Computer Science&Engineering Hindustan Institute of Technology and Science Chennai India

If adversaries were to obtain quantum computers in the future, their massive computing power would likely break existing security schemes. Since security is a continuous process, more substantial security schemes must be developed. Current PQC schemes primarily focus on data security or key exchange, and further improvement towards enhanced PQC primitives is required. Our proposal in this research is an innovative paradigm for PQC-focused cloud data security. The proposed HEDT approach achieves encryption and decryption with significantly lower latency (20% improvement) and higher reliability than AES, DES, and RSA, as demonstrated through experimental results. Furthermore, ECSIDH, a hybrid key exchange mechanism combining SIDH and ECDH, improves security strength by 50% while maintaining computational costs within 1.13x of SIDH. Compared to individual key exchange schemes like SIDH, ECSIDH offers superior security as a PQC candidate. These results confirm the robustness and efficiency of the proposed framework in ensuring secure data outsourcing and key exchange in cloud environments. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Exploring Taiwan Monkeypox Virus (MPOX/MPXV) Clade IIb by Establishing Dataset and Clustering by using Sequence and Image Similarity Comparisons 24

Exploring Taiwan Monkeypox Virus (MPOX/MPXV) Clade IIb by Es...

引用

7th International Conference on Computational Intelligence and Intelligent Systems, CIIS 2024

作者： Wang, Tzung-Wei Li, Ming-Kuang Lou, Der-Chyuan Lin, Chun-Yuan Dept. of Electronics Engineering Chang Gung University Taoyuan Taiwan Dept. of Computer Science and Information Engineering Asia University Taiwan Taichung Taiwan Dept. of Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan

ISBN: (纸本)9798400717437

Based on the MPXV Clade IIb cases in Taiwan, 175 segments were identified from OPG001 to OPG210. The first focus of this paper is on sequence analysis of the MPXV cases in Taiwan, detailing the procedures, including semi-automated segmentation and dataset creation from a large number of MPXV Clade IIb nucleotide sequences found in the NCBI and GISAID databases. The second feature highlights the pioneering establishment of an MPXV Clade IIb RNA 2nd structure image dataset in Taiwan, as such a dataset does not yet exist globally. The third characteristic involves the use of unsupervised learning methods for the rapid clustering of MPXV Clade IIb RNA 2nd structure images. This approach allows not only for the quick detection and clustering of unknown MPXV Clade IIb cases but also for the rapid identification of new MPXV mutations and structural changes. Compared to traditional sequence analysis, this new hybrid systematic method significantly enhances overall efficiency, improving processing speed by at least 24 hours when handling the alignment of 10 MPXV sequences from Taiwan. Future plans include using this prototype analytical model and method to accelerate the analysis of critical lethal factors in MPXV Clade IIb, such as D14L, ultimately helping biologists reduce the time required for analysis and antiviral drug development. © 2024 Copyright held by the owner/author(s).

关键词： Nucleotides

来源：评论

学校读者我要写书评

暂无评论

A Narrative Assistant for Traffic Accidents Based on Large Language Models (LLM) 37

A Narrative Assistant for Traffic Accidents Based on Large L...

引用

37th Annual Conference on Legal Knowledge and information Systems, JURIX 2024

作者： Kung, Jo-Chi Chang, Chia-Hui Huang, Huai-Hsuan Chien, Kuo-Chun Dept. of Computer Science & Information Engineering National Central University Taiwan

ISBN: (纸本)9781643685625

This study introduces the Collision Clarification Generator (CCG), a Large Language Model-based system designed to assist in documenting traffic accidents. The CCG comprises three modules: Questioning, information Extraction, and Accident Sequence Generation, which collectively streamline the process of gathering and structuring accident information. The system employs predefined question templates and a standardized Traffic Accident Record Format (TARF) to ensure comprehensive data collection. Evaluation of the CCG involved both human assessment and LLM-based automatic evaluation. Results showed an F1 score of 0.909 in human evaluation, and scores exceeding 7 out of 10 for accuracy and completeness in LLM-based assessment. These findings demonstrate the CCG’s effectiveness in accurately documenting accident information, potentially facilitating subsequent legal and insurance processes. © 2024 The Authors.

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

Harmonizing the Musical Metaverse: unveiling needs, tools, and challenges from experts’ point of view

Harmonizing the Musical Metaverse: unveiling needs, tools, a...

引用

International Conference on New Interfaces for Musical Expression, NIME 2024

作者： Boem, Alberto Tomasetti, Matteo Turchet, Luca Dept. of Information Engineering and Computer Science University of Trento Trento Italy

The Musical Metaverse (MM) represents an innovative frontier for the field of New Interfaces for Musical Expression (NIME). The MM holds the potential to redefine areas such as musical composition and performance via immersive environments based on technologically mediated social interactions. Despite substantial research on single-user immersive systems, the intersection of NIME and the MM remains largely unexplored. In this paper, we systematically explore this domain by examining previous and current approaches, alongside conducting interviews with eleven experts who have created multi-user immersive musical environments and authored publications on this topic. The goal is to map such an uncharted territory by collecting valuable insights and leveraging the perspective of experts to provide an understanding of the potentials and challenges inherent in creating immersive social environments for musical activities. Our results reveal that existing multi-user immersive environments make use of diverse implementation approaches but face challenges due to the absence of standardized technology stacks, particularly in networking and data synchronization. © 2024, International Conference on New Interfaces for Musical Expression. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Physical Layer Authentication via Underwater Acoustic Multipath Channel Crafting

Physical Layer Authentication via Underwater Acoustic Multip...

引用

OCEANS 2024 - Halifax, OCEANS 2024

作者： Eccher, Davide Casari, Paolo University of Trento Dept. of Information Engineering and Computer Science Trento Italy

ISBN: (纸本)9798331540081

With the increasing number of actors in the under-water environment and the development of new applications, such as large-scale monitoring and autonomous underwater vehicle control, securing underwater communications is becoming a primary necessity. Security was not prioritized in the past due to the constraints of underwater acoustic communications, which cannot sustain the overhead of typical cryptographic techniques. In this paper, we propose a method to authenticate a network device by exploiting the physical properties of the acoustic channel. In particular, our method hinges on the uniqueness and quasi-reciprocity of the channel, from which the authenticator (Alice) node can extract several parameters such as the number of multi path channel components, their delay and amplitude. These values are similar on both ends of a link between Alice and a legitimate transmitter (Bob), and can be used as a seed to craft a new artificial channel, that is then applied to transmissions from Bob to Alice. With this procedure, Alice can distinguish Bob from an impersonating attacker (Eve), given a previous message exchange history. Eve can try to bypass the protocol by estimating the channel parameters and by trying to replicate Bob's signal by crafting a similar channel. In our tests, we observe that the estimation error for Eve, caused by her wrong channel estimates, becomes significant even for short distances betwen Eve and Bob. This error results in a discrepancy between the signal generated by Eve and the one expected by Alice, and reveals Eve as an attacker. © 2024 IEEE.

关键词： Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

Prosecutorial Outcome Predication with LoRA and QLoRA 37

Prosecutorial Outcome Predication with LoRA and QLoRA

引用

37th Annual Conference on Legal Knowledge and information Systems, JURIX 2024

作者： Chien, Kuo-Chun Chang, Chia-Hui Huang, Huai-Hsuan Kung, Jo-Chi Dept. of Computer Science & Information Engineering National Central University Taiwan

ISBN: (纸本)9781643685625

Our study on Legal Judgment Prediction (LJP) focuses on indictments, designing innovative tasks for prosecutors to predict reasons, imprisonment, fines, and penalty types. We investigated multi-task learning (MTL), Low-Rank Adaptation (LoRA), and its quantized version (QLoRA). Results show that the MTL framework, combined with LoRA and QLoRA, excels in prediction while optimizing resource use. Error analysis in the Reason field of TWPJD dataset was conducted to guide future predictions. Future work will focus on balancing sub-task performance and collecting more investigative data to enhance legal AI applications. © 2024 The Authors.

关键词： Multi-task learning

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：