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

An Intelligent LLM-Powered Personalized Assistant for Digital Banking Using LangGraph and Chain of Thoughts 22

An Intelligent LLM-Powered Personalized Assistant for Digita...

引用

22nd IEEE International Symposium on Intelligent Systems and Informatics, SISY 2024

作者： Easin, Arafat Md Sourav, Saha Tamas, Orosz Data Science and Engineering Dept. Budapest Hungary Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350385601

Text-based applications and chatbots are increasingly popular for delivering banking services and educational tools, offering convenient and efficient solutions for users. Whereas, personalized assistants have transformed user engagement in the digital banking space by utilizing Large Language Models (LLMs) in conjunction with autonomous agents. This study proposes the development of an intelligent personalized assistant for digital banking, utilizing a multi-agent framework based on the LangGraph and Chain of Thoughts (COT) prompting. While COT guarantees context-aware replies, the LangGraph design maps characteristics to nodes to improve user interactions. The objectives of this system are to enhance task efficiency and elevate the capabilities of digital banking assistants. We present a customizable digital banking system powered by LLM-based models, designed to deliver an interactive and personalized banking experience. The system supports a range of services, including adding money, transferring funds, paying bills, accessing telco services like mobile recharge, managing savings interest rates, DPS schemes, fixed deposits, and answering FAQs related to banking information. Therefore, integrating COT for logical reasoning enhances the effectiveness of multi-agent systems, as each single agent benefits from the structured reasoning process. In addition, LangGraph is employed for structured data management, enabling the assistant to support and accelerate various digital banking processes efficiently. The code implementation of this work is available for public access at: https://***/srv-sh/digital-agent. © 2024 IEEE.

关键词： Information management

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

CLASSIFICATION BY A STACKING MODEL USING CNN FEATURES FOR MEDICAL IMAGE DIAGNOSIS

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2024年第1期86卷 3-18页

作者： Mutasher Rashed, Baidaa Popescu, Nirvana Computer Science Dept. National University of Science and Technology POLITEHNICA of Bucharest Romania Computer Science Dept. University POLITEHNICA of Bucharest Romania

Medical imaging coupled with Artificial Intelligence (AI) applications, in particular Deep learning (DL) and Machine Learning (ML), can speed up the disease diagnostic process. The purpose of this work is to present a novel disease detection system by suggesting a new Convolutional Neural Network (CNN) model and combining the CNN features with three of ML classifiers and suggesting a new classifier using the stacking model. The proposed system was used in binary and multi-classification and applied to two different medical datasets. The proposed model was evaluated using accuracy, sensitivity, specificity, precision, recall, F1 score, and AUC, achieving robust results. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Detection of Cattle Behavior Using YOLOv9 with AutoAugment and Mixup data Augmentation Techniques

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第12期73卷 2326-2332页

作者： Lee, Su-Bin Park, Jae-Beom Cho, Hyun-Chong Dept. of Electronics Engineering Dept. of Data Science Kangwon National University Korea Republic of Dept. of Data Science Kangwon National University Korea Republic of Dept. of Interdisciplinary Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of

As the number of livestock farms in Korea decreases, the scale of individual farms has grown, necessitating advanced methods for efficient livestock management. Recent studies have increasingly applied computer vision and deep learning to monitor livestock behavior, health, and disease, aiming to enhance productivity and animal welfare. This study introduces a real-time cattle behavior detection system utilizing YOLOv9, a state-of-the-art object detection algorithm known for its high accuracy and efficiency. The YOLOv9-s model, optimized for real-time detection with minimal computational overhead, was employed. To further enhance detection accuracy, we incorporated AutoAugment, a data augmentation technique that automatically selects the optimal augmentation policies, and mixup, a method that improves model generalization by creating new training samples through linear interpolation of existing ones. The application of AutoAugment improved the mean Average Precision (mAP) from 0.926 to 0.941, while the addition of mixup raised the mAP to 0.947, representing a 2.1% performance increase. These results confirm the system's capability for accurate and efficient real-time detection of cattle behavior. Copyright © The Korean Institute of Electrical Engineers.

关键词： Livestock

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

ROBOT PATH PLANNING WITH A HYBRID ARITHMETIC OPTIMIZATION ALGORITHM

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2024年第3期86卷 197-210页

作者： Song, Qiang Dept. of Computer Science and Software Engineering Zhaoqing University Zhaoqing China

To address the premature convergence and search stagnation of arithmetic optimization algorithm (AOA), the paper proposes a hybrid arithmetic optimization algorithm (HAOA) and applies it to the practical robot path planning (RPP) problem. In initialization phase, the chaotic mechanism is used to create high-quality individuals. In evolution phase, the stochastic disturbance method is applied to enhance the exchange of information between different individuals. The solution space information around the candidate solution was integrated by Levy flight to enhance gene diversity and enhance search performance. In order to better solver the RPP problem, the Spline interpolation method is adapted to the HAOA algorithm for path optimization, so as to smooth the path curve and ensure the planning accuracy. Finally, numeric experiments of benchmark functions and RPP instances verify HAOA’s excellent performance in accuracy and robustness. This research shows arithmetic optimization algorithm can quickly find the global optimal solution, and has fast convergence speed and accuracy. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

AI in CS Education: Opportunities, Challenges, and Pitfalls to Avoid

引用

ACM Inroads 2024年第3期15卷 52-57页

作者： Vahid, Frank Dept. of Computer Science and Engineering University of California Riverside United States

Csinstructors realize education may be impacted by generative AI (artificial intelligence). This article describes (1) opportunities, like 24/7 help or auto-grading, (2) challenges, like increased cheating or student isolation, and (3) pitfalls to avoid, like inequitable access or false cheating accusations. The descriptions come from 15 CS educators and practitioners, from diverse institutions, who met at a 2023 NSF workshop on AI in CS education. The article aims to assist the CS community to take advantage of generative AI to improve courses, embark on new research, treat students equitably, and ultimately improve CS education for instructors and students. © 2024 Association for Computing Machinery. All rights reserved.

关键词： Students

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 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

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：